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.1698824082.rhmmedcatt-proliant-ml350-gen10 b/.summary/0/events.out.tfevents.1698824082.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..359ddc631edcffc039adf29d29d6a809e8743ffe --- /dev/null +++ b/.summary/0/events.out.tfevents.1698824082.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46a9650243c3504948a11814a18f1389b23d100815904bc484c1c234e00e6edc +size 89267843 diff --git a/.summary/1/events.out.tfevents.1698824082.rhmmedcatt-proliant-ml350-gen10 b/.summary/1/events.out.tfevents.1698824082.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..e24c56ac57f40ac8c1373f0e4d1f071ac840d7b3 --- /dev/null +++ b/.summary/1/events.out.tfevents.1698824082.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e58b84e4bf3e81d71e8f1743774ac095c78b9362005397cd24477866d5c4675 +size 46890053 diff --git a/README.md b/README.md index 19cd218b75b39abb767715e458ce2dd0f970eec8..85187e3ebe0e8d99fbf53a34a8d16cf527aacea1 100644 --- a/README.md +++ b/README.md @@ -15,35 +15,39 @@ model-index: type: atari_doubledunk metrics: - type: mean_reward - value: -0.60 +/- 1.80 + value: -0.20 +/- 0.60 name: mean_reward verified: false --- -A(n) **APPO** model trained on the **atari_doubledunk** 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_doubledunk -``` +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_doubledunk** 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_doubledunk +``` + + ## Using the model To run the model after download, use the `enjoy` script corresponding to this environment: diff --git a/checkpoint_p0/best_001536216_393273344_reward_0.460.pth b/checkpoint_p0/best_001536216_393273344_reward_0.460.pth new file mode 100644 index 0000000000000000000000000000000000000000..1658b205a4378ffd82a4509863b11e6278159a18 --- /dev/null +++ b/checkpoint_p0/best_001536216_393273344_reward_0.460.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d77295abf4b7986952e38f47b4e13be1bbb1011df772fb165ba4a19f54ffa2dd +size 20795763 diff --git a/checkpoint_p0/checkpoint_001951928_499695616.pth b/checkpoint_p0/checkpoint_001951928_499695616.pth new file mode 100644 index 0000000000000000000000000000000000000000..9006430eddf255031ca8620f202e30dcc6d7d905 --- /dev/null +++ b/checkpoint_p0/checkpoint_001951928_499695616.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd411de43d6812c7c557b0a74eb375228c5c2138c94382239761f52de561ec97 +size 20796099 diff --git a/checkpoint_p0/checkpoint_001953080_500006912.pth b/checkpoint_p0/checkpoint_001953080_500006912.pth new file mode 100644 index 0000000000000000000000000000000000000000..2cc1b9b234d40a9eb6d30fa4439bf0ab9e68a040 --- /dev/null +++ b/checkpoint_p0/checkpoint_001953080_500006912.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43000c5814518eed059e252dfb47c6ff31fab2dd8ff879f853f493faeadf509c +size 20796099 diff --git a/checkpoint_p0/milestones/checkpoint_000012384_3170304.pth b/checkpoint_p0/milestones/checkpoint_000012384_3170304.pth new file mode 100644 index 0000000000000000000000000000000000000000..9daba1e0a9bd0f3d70855d7bbecfeae55af75888 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000012384_3170304.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:debb76056cdf332a007842729591a75aef607ebad96427f31ab4e9f6a9ddc772 +size 20796955 diff --git a/checkpoint_p0/milestones/checkpoint_000025280_6471680.pth b/checkpoint_p0/milestones/checkpoint_000025280_6471680.pth new file mode 100644 index 0000000000000000000000000000000000000000..42211bfeddb9b4bf1dbbb529bba176fcb624e598 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000025280_6471680.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dff08274cc148d15aaed32494f5ddedd992d5187358d0e81709f1618a1f96d2 +size 20796955 diff --git a/checkpoint_p0/milestones/checkpoint_000038176_9773056.pth b/checkpoint_p0/milestones/checkpoint_000038176_9773056.pth new file mode 100644 index 0000000000000000000000000000000000000000..61fa207baa3470f87c2fcc967a669cb625ea4ece --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000038176_9773056.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ece6167d47566435eecb7815c0132be1d39d60da36c0f301d6b46034eab4a36c +size 20796955 diff --git a/checkpoint_p0/milestones/checkpoint_000050976_13049856.pth b/checkpoint_p0/milestones/checkpoint_000050976_13049856.pth new file mode 100644 index 0000000000000000000000000000000000000000..a42dda98464f84daed423d12cc2cdf61f0ec6459 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000050976_13049856.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6d261989c2e7ba360e970648f3927af36548819a0187e58809ca6972551d73a +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000063904_16359424.pth b/checkpoint_p0/milestones/checkpoint_000063904_16359424.pth new file mode 100644 index 0000000000000000000000000000000000000000..247ef7a013ee69d0ddbd2dcd8c9a3681c9202560 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000063904_16359424.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8cff83324c588b469264c92315c2fec18710502d4ef1be2a4eb201382f41f13 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000076800_19660800.pth b/checkpoint_p0/milestones/checkpoint_000076800_19660800.pth new file mode 100644 index 0000000000000000000000000000000000000000..5c5bb0bf366ea9c9334492c4f73a033162a8dfc8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000076800_19660800.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6e2a2189f74b84433e23f1e82d6b39972b9aae60763c1ca8f0e6fb4e947e0bd +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000089664_22953984.pth b/checkpoint_p0/milestones/checkpoint_000089664_22953984.pth new file mode 100644 index 0000000000000000000000000000000000000000..90052149757d702470f14a02515e8c6ac3438953 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000089664_22953984.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a35abf779719e4095e0eb376de99b78df6c3599acd1c3e1442fd2b014d64c8d2 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000102592_26263552.pth b/checkpoint_p0/milestones/checkpoint_000102592_26263552.pth new file mode 100644 index 0000000000000000000000000000000000000000..826123f2f880c85e48a7263c6515d044755b8938 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000102592_26263552.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edabee6277ae45e342c04e959627d76875fb3611be9d3528a59565cca54130b7 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000115392_29540352.pth b/checkpoint_p0/milestones/checkpoint_000115392_29540352.pth new file mode 100644 index 0000000000000000000000000000000000000000..60b95955a74affc46238b225fa78ccd14bc29254 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000115392_29540352.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0f960727b8afde31ecd02f791619da19f905ff1ea69428e84b077d3a8081682 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000128160_32808960.pth b/checkpoint_p0/milestones/checkpoint_000128160_32808960.pth new file mode 100644 index 0000000000000000000000000000000000000000..51321e158b179147c81c2a406505c8770b0e24e6 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000128160_32808960.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c2cc1b5d06571afd74027a98943b430e28d0462afaa396285dfeb0fd9d4d4d2 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000141024_36102144.pth b/checkpoint_p0/milestones/checkpoint_000141024_36102144.pth new file mode 100644 index 0000000000000000000000000000000000000000..2090e94ecac19d398b30f4a33a96bad462877481 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000141024_36102144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c62de335b1131119baf8e3031594f2a2abf9cfcb1f210477daec952e9b707c22 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000153888_39395328.pth b/checkpoint_p0/milestones/checkpoint_000153888_39395328.pth new file mode 100644 index 0000000000000000000000000000000000000000..2555e8a4fb1663971bbed1d31f1995b8e5f4ef49 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000153888_39395328.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a69f93337475901a709b2704a3162a15d6254acc6d33c175525b03b14ae033af +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000166560_42639360.pth b/checkpoint_p0/milestones/checkpoint_000166560_42639360.pth new file mode 100644 index 0000000000000000000000000000000000000000..cc17e8b6d3cecea5939945c715945876c38d77c2 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000166560_42639360.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7236a51efb1dbfb273f178ce4b036ac24b21dc799055b1a43336cae780185d3c +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000179392_45924352.pth b/checkpoint_p0/milestones/checkpoint_000179392_45924352.pth new file mode 100644 index 0000000000000000000000000000000000000000..3426f20d584790bc428ce99c8a5753f635bf76d3 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000179392_45924352.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a18c33bdc166f3050d28013e18b9ed774910819650808f7c8fe63b3126589ff +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000192224_49209344.pth b/checkpoint_p0/milestones/checkpoint_000192224_49209344.pth new file mode 100644 index 0000000000000000000000000000000000000000..b52b5990ff45ca08ed649acc783aaa2578984f73 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000192224_49209344.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e465facda97ab3afb34740fe76af866f8751ac5053ffc2b5e49f67012fe0ed56 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000204960_52469760.pth b/checkpoint_p0/milestones/checkpoint_000204960_52469760.pth new file mode 100644 index 0000000000000000000000000000000000000000..17e8dabd257cb8ce01f1bae00b1da1b697f5ce33 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000204960_52469760.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e909a2815bdc2638572205f095437ff5611b25b4e251995b49a0443324f334b2 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000217632_55713792.pth b/checkpoint_p0/milestones/checkpoint_000217632_55713792.pth new file mode 100644 index 0000000000000000000000000000000000000000..b26edf92917176b9347d3ec342f47f18ac89dbf4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000217632_55713792.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1d03b5c527026c8502ee5660dc06e6bb2c796030fef399c6fdea826f10105f2 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000230432_58990592.pth b/checkpoint_p0/milestones/checkpoint_000230432_58990592.pth new file mode 100644 index 0000000000000000000000000000000000000000..bb2bae30215aa9d5aaa9f7894300db80dbc43cb0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000230432_58990592.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d258e97d687f763e8dc76cca763b89ac121503d74cb584910b34f16aadd73286 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000243232_62267392.pth b/checkpoint_p0/milestones/checkpoint_000243232_62267392.pth new file mode 100644 index 0000000000000000000000000000000000000000..25d5dcbd5320bec287e155874dc7e71ba61b20a5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000243232_62267392.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:967eea47e89c55a6dec336c1317c97a85b5e1034622fb0c48755a789baf099b8 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000256064_65552384.pth b/checkpoint_p0/milestones/checkpoint_000256064_65552384.pth new file mode 100644 index 0000000000000000000000000000000000000000..a0edf0a7de705c168217cdfa100fa6a27b069e72 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000256064_65552384.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ae4ea7cd75c0f8040e9ea34e9ed7dd7a85fd073893af079b302c170fe826071 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000268992_68861952.pth b/checkpoint_p0/milestones/checkpoint_000268992_68861952.pth new file mode 100644 index 0000000000000000000000000000000000000000..7eeab903ecb4ace11a8a313bc7207fda3b4c051a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000268992_68861952.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4542c6d54740df221ff2e2ce4128a0b27adf4f3d9d09a75e01b0544bf25fc85b +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000281824_72146944.pth b/checkpoint_p0/milestones/checkpoint_000281824_72146944.pth new file mode 100644 index 0000000000000000000000000000000000000000..b16c34a008303caf35049ff1528a4ff25f2383d4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000281824_72146944.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e67d797f7676478fae3862fca1d1d4a28d2f2f5f995c8489f274e7eec2c8a1d8 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000294720_75448320.pth b/checkpoint_p0/milestones/checkpoint_000294720_75448320.pth new file mode 100644 index 0000000000000000000000000000000000000000..815a770a8da5712e958a91e45699de6519d1026d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000294720_75448320.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83d4f35c105c110ccdb069d8620af5428d76024368014656b2ec5f69700339ae +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000307680_78766080.pth b/checkpoint_p0/milestones/checkpoint_000307680_78766080.pth new file mode 100644 index 0000000000000000000000000000000000000000..3161fb8520d549b6733a05616bae698af3c1c3b1 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000307680_78766080.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9d25ecf637495ac12d22e973f8be3a51358c6f115bf7ce4052ee4eeef40369b +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000320416_82026496.pth b/checkpoint_p0/milestones/checkpoint_000320416_82026496.pth new file mode 100644 index 0000000000000000000000000000000000000000..f2fa6c40d13f9a9e9d11d0cc3b06566837f03525 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000320416_82026496.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cb5423726a065eef11d85b4c6c6fc0fb52bb533722bbed007d1c895c13f0124 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000332608_85147648.pth b/checkpoint_p0/milestones/checkpoint_000332608_85147648.pth new file mode 100644 index 0000000000000000000000000000000000000000..d5217809da055f7d84b300ac24bc51158b2448ca --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000332608_85147648.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcd4b7ff894760e31352e18d3d6376fe7811afbb77fd85624df0264f4dccea8f +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000345312_88399872.pth b/checkpoint_p0/milestones/checkpoint_000345312_88399872.pth new file mode 100644 index 0000000000000000000000000000000000000000..e6381e3a6192103159c6ab1db1d02f5f3f6495b6 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000345312_88399872.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0259d418b4f00c6aae2e0ae3bab69955aabc7e2bc567e5d1e79de90e3b505c38 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000358176_91693056.pth b/checkpoint_p0/milestones/checkpoint_000358176_91693056.pth new file mode 100644 index 0000000000000000000000000000000000000000..e37e428b930a3740cdd1541ffb61c9e719f58b02 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000358176_91693056.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6aeba675041972d80f85c376cf2ad416520ff568e713a111097085462b2767b2 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000371072_94994432.pth b/checkpoint_p0/milestones/checkpoint_000371072_94994432.pth new file mode 100644 index 0000000000000000000000000000000000000000..d8de5f8a0cad9cf78ae0d4f8473fa8d68765ed47 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000371072_94994432.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5339ac0d0cca46fdebbdf8e04480fa62d84725ab5fe96f5924591d2f4fac13cb +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000383936_98287616.pth b/checkpoint_p0/milestones/checkpoint_000383936_98287616.pth new file mode 100644 index 0000000000000000000000000000000000000000..60a361fbb636173f5a697e026ed2d45abfdd8bda --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000383936_98287616.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd9f71064f4b0c28ad36784443f03c194af813a53e7e3d854e1a154f7889a510 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000396832_101588992.pth b/checkpoint_p0/milestones/checkpoint_000396832_101588992.pth new file mode 100644 index 0000000000000000000000000000000000000000..b1268500f745f99918d330c1cee861f3451dbe05 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000396832_101588992.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eebc7d7edd5017e6252a121fbd5344a50117713e21e9861ab70de7ebd5fd5ff1 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000409728_104890368.pth b/checkpoint_p0/milestones/checkpoint_000409728_104890368.pth new file mode 100644 index 0000000000000000000000000000000000000000..08efae0c10aa412b15ca6a2dad55892b88edff59 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000409728_104890368.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48b3f43f921e2908dfe78354574dc1c6c8278deacac894a9956953fdd3f997e6 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000422592_108183552.pth b/checkpoint_p0/milestones/checkpoint_000422592_108183552.pth new file mode 100644 index 0000000000000000000000000000000000000000..04847bba4c7a9ecf704ac8fe4637ab058b25841e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000422592_108183552.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1249b783103506e3018603800707efa8b22cec039958fbaa1cf32f80fec2e4f +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000435392_111460352.pth b/checkpoint_p0/milestones/checkpoint_000435392_111460352.pth new file mode 100644 index 0000000000000000000000000000000000000000..4c0b90f108772c5a57e979337d2ca7dd7213adf4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000435392_111460352.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf688786db384003e8f0759f5e2e5543f4b4678672b9a236f765f0de47ea8f29 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000448256_114753536.pth b/checkpoint_p0/milestones/checkpoint_000448256_114753536.pth new file mode 100644 index 0000000000000000000000000000000000000000..a306e3c11ee7290f1478bcc0f1b5e9a471971f5b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000448256_114753536.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e19c8808e00180da3bcf910f2fda4fc191ae991a814c4e9fe99f019ead633fce +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000461152_118054912.pth b/checkpoint_p0/milestones/checkpoint_000461152_118054912.pth new file mode 100644 index 0000000000000000000000000000000000000000..99e3bbe0ecdb6f141c2e1e943a0a16c4b3a3424b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000461152_118054912.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7aaf328cbaf76488a1f2f3006879d81729cc8762aa1eab522fc21624650549b1 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000473952_121331712.pth b/checkpoint_p0/milestones/checkpoint_000473952_121331712.pth new file mode 100644 index 0000000000000000000000000000000000000000..83e765aafa31b4c2edbfb3c77c57671c74eb5ae8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000473952_121331712.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b6cb566c54ad255a070e69cdd42868ecf4d9410963bb43430a196028fec2ed9 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000486816_124624896.pth b/checkpoint_p0/milestones/checkpoint_000486816_124624896.pth new file mode 100644 index 0000000000000000000000000000000000000000..07f2e0277cc91cd71d8793d57a2d27b15368aedd --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000486816_124624896.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72c7015186577d8d8ce4f4424a7dac6559afad4a1cee1f031412936543c8c811 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000499584_127893504.pth b/checkpoint_p0/milestones/checkpoint_000499584_127893504.pth new file mode 100644 index 0000000000000000000000000000000000000000..4e942a622bd5223a84f52a36b299b823ceeecd59 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000499584_127893504.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:346063ebc930d6c2d09a3ff5b88b62c840d82b7b54562352c201d59ed0712626 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000512384_131170304.pth b/checkpoint_p0/milestones/checkpoint_000512384_131170304.pth new file mode 100644 index 0000000000000000000000000000000000000000..002cd352b1e87a5a7000ca4395f45b4219b830db --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000512384_131170304.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3131df0bcf9ca3c88d703f5ab9cfa025304669fd59a85ea44d89ff06be52b26c +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000525248_134463488.pth b/checkpoint_p0/milestones/checkpoint_000525248_134463488.pth new file mode 100644 index 0000000000000000000000000000000000000000..53341ca3ed832fea5be9a24f7e180aac778a07c5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000525248_134463488.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66ec390938911291e15071bcb725b733cdf4b9d31f32866da0319bcfe4917a33 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000538208_137781248.pth b/checkpoint_p0/milestones/checkpoint_000538208_137781248.pth new file mode 100644 index 0000000000000000000000000000000000000000..1a517d3f9ed60ee33ba26bab4405c1d8f5646712 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000538208_137781248.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bffa2a88e5e440062223e86bcca79c4c6c79d70b4421382507227709f093d114 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000550976_141049856.pth b/checkpoint_p0/milestones/checkpoint_000550976_141049856.pth new file mode 100644 index 0000000000000000000000000000000000000000..853cab484cc40a957c0916a0376a1bbd03416e21 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000550976_141049856.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39154d96ca27e8f6134e3863d2dda5e8bb4f74aa61de27c071903f52c70176c8 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000563872_144351232.pth b/checkpoint_p0/milestones/checkpoint_000563872_144351232.pth new file mode 100644 index 0000000000000000000000000000000000000000..898effa5cec7fad72d72d22004686ce00b64e920 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000563872_144351232.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f03b2bcbb546cf8929306b8cd4f4f9f02e61a731260733a0345824112935f40 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000576672_147628032.pth b/checkpoint_p0/milestones/checkpoint_000576672_147628032.pth new file mode 100644 index 0000000000000000000000000000000000000000..a1a0e854a677d081b51c038f98a45385ccf86eb8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000576672_147628032.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66bafe3eec5bdfdd9cf701fc29bab801f0cb0eb8652a9842db19f23c8544b741 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000589600_150937600.pth b/checkpoint_p0/milestones/checkpoint_000589600_150937600.pth new file mode 100644 index 0000000000000000000000000000000000000000..c3925907c35daa59fec420c6797cb5556690d8c3 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000589600_150937600.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1fe36e87648102d2ede5182a7dfff8a27e6d9b58c508e5b560b68854d5a303a +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000602400_154214400.pth b/checkpoint_p0/milestones/checkpoint_000602400_154214400.pth new file mode 100644 index 0000000000000000000000000000000000000000..dfa70cfdea41903c4a3a13195932349e07af30c6 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000602400_154214400.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b218abeb11527af1bd3621e6b6eecf01706a4d3ea1d93df08ab39465c3d4218f +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000615232_157499392.pth b/checkpoint_p0/milestones/checkpoint_000615232_157499392.pth new file mode 100644 index 0000000000000000000000000000000000000000..a1c830c677c3707538f8294ae99fd7b41df93423 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000615232_157499392.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09dbe6ad02bd97b22d46df6c59ea8e705a3ebafc77a41b46f4a74dce91e9dabb +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000628160_160808960.pth b/checkpoint_p0/milestones/checkpoint_000628160_160808960.pth new file mode 100644 index 0000000000000000000000000000000000000000..b3a8ce5ea36b79b2cfeafb6b1e440e70f56023fd --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000628160_160808960.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db10ffa4f647988fb74b54fac296383cdf65dc83451f2c380a352af1b6f2bb8c +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000641024_164102144.pth b/checkpoint_p0/milestones/checkpoint_000641024_164102144.pth new file mode 100644 index 0000000000000000000000000000000000000000..479a50b1a7261a90ee0dcbc88941cba7e3b08592 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000641024_164102144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:107a256efd210999f4ed494a378d08c8509ceabedddfd4dfba58eb0c6394de45 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000653888_167395328.pth b/checkpoint_p0/milestones/checkpoint_000653888_167395328.pth new file mode 100644 index 0000000000000000000000000000000000000000..a642834cc307b597f86f6dc0a843a88eb3b9b8b1 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000653888_167395328.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:121157454dd106ce892e02f8827020ef45b66e61cdd9897bbaa8387fad553e01 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000666720_170680320.pth b/checkpoint_p0/milestones/checkpoint_000666720_170680320.pth new file mode 100644 index 0000000000000000000000000000000000000000..886481d7984464afb08b30238e0a7f6fca2cfbd2 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000666720_170680320.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92593111f0bb91bbf87f3ab72fb25332f7098609874a741accf294cf08ac73a2 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000679680_173998080.pth b/checkpoint_p0/milestones/checkpoint_000679680_173998080.pth new file mode 100644 index 0000000000000000000000000000000000000000..e8267698a32320badcf8f87745a2288fd7ef195b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000679680_173998080.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53f596eef80f46e14a647c2ca033e1b844cf7f35556af8251196d40b535e77b1 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000692544_177291264.pth b/checkpoint_p0/milestones/checkpoint_000692544_177291264.pth new file mode 100644 index 0000000000000000000000000000000000000000..cd25a1a30b6ec3e4bb0884c14d66420569dc30fc --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000692544_177291264.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15cde3dbfe5c4b2c00954c7164d66ba17e2117907f6d102dfeee13c676ab6a35 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000705440_180592640.pth b/checkpoint_p0/milestones/checkpoint_000705440_180592640.pth new file mode 100644 index 0000000000000000000000000000000000000000..3df13ad30e29a624623b22e555b88bdee506e8f5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000705440_180592640.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ae3e5b17d71905d8872369a22445c4db06b7a0c841ddd934d18be56bac3a40f +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000718328_183894016.pth b/checkpoint_p0/milestones/checkpoint_000718328_183894016.pth new file mode 100644 index 0000000000000000000000000000000000000000..12feba4128231da4cdf6998e487f101c8566e5b0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000718328_183894016.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94ffb29974449a4ef272408986319e9ee7b0d06fc7d1153840d2ecbad3ef5bc5 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000731288_187211776.pth b/checkpoint_p0/milestones/checkpoint_000731288_187211776.pth new file mode 100644 index 0000000000000000000000000000000000000000..52aa581687dbdbcaf251165eecb9e37116c492b1 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000731288_187211776.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be3f52acdc1a57019a86c758488b3035f3e3d39a25efde2a7677955ea0e01d95 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000744120_190496768.pth b/checkpoint_p0/milestones/checkpoint_000744120_190496768.pth new file mode 100644 index 0000000000000000000000000000000000000000..1d451e2740e5ec8445ef877555160dbf29d3b7c7 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000744120_190496768.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:003cfdc08b4da4ae3b9532f516c1fa19c1167bd1e4c8ab535381a49263056b5c +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000756920_193773568.pth b/checkpoint_p0/milestones/checkpoint_000756920_193773568.pth new file mode 100644 index 0000000000000000000000000000000000000000..003b2fcc84a70337f3fb2d754a2c4a50c28f78ab --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000756920_193773568.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe751555539d5828b84f02e35c87e79d45742fb2946c6286fe9334737478b268 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000769784_197066752.pth b/checkpoint_p0/milestones/checkpoint_000769784_197066752.pth new file mode 100644 index 0000000000000000000000000000000000000000..0e736c404af601d33f3abea720aff887b1f9db52 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000769784_197066752.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31f030915c67de90431e20aec8661ff281bd67cfb4fef0e5cb11bd9602889cab +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000782776_200392704.pth b/checkpoint_p0/milestones/checkpoint_000782776_200392704.pth new file mode 100644 index 0000000000000000000000000000000000000000..58224776be28c52e4ac8de7a47749208b594a16e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000782776_200392704.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f85e84edf267469ec5dc8b743fb04487d5a99020a6fd96500a82552fb49132f +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000795672_203694080.pth b/checkpoint_p0/milestones/checkpoint_000795672_203694080.pth new file mode 100644 index 0000000000000000000000000000000000000000..db65da394a855794fa82d40295f276e59380d71c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000795672_203694080.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62a646556b573f5031bc9fad35e27a1d798dbabe51b54e81c63c34538b8fddd5 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000808664_207020032.pth b/checkpoint_p0/milestones/checkpoint_000808664_207020032.pth new file mode 100644 index 0000000000000000000000000000000000000000..cb2c4d784d1c0cdce1874286aadda4bb921f7694 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000808664_207020032.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fe0dbafbc7e255ac700401a6aaf733d4e3edc782c6cc4995a8d000ff3b376e8 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000821528_210313216.pth b/checkpoint_p0/milestones/checkpoint_000821528_210313216.pth new file mode 100644 index 0000000000000000000000000000000000000000..d3d0c2af5f73770fdd02357c6e6f74cada22f0ca --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000821528_210313216.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:837dfac7e2701cb173e9c12c66b7422844d72a1cafb9d19d8ba8579d7cb63386 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000834424_213614592.pth b/checkpoint_p0/milestones/checkpoint_000834424_213614592.pth new file mode 100644 index 0000000000000000000000000000000000000000..a9ae7533eeb5a9f41a3f8db5410f1876ceb06d2c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000834424_213614592.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66ec38eab07de0f69ba75d4aa61e15613b63c9ba2937bbd0abde2e61cd1b9fb7 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000847352_216924160.pth b/checkpoint_p0/milestones/checkpoint_000847352_216924160.pth new file mode 100644 index 0000000000000000000000000000000000000000..c4cefc9c96dd7d3e8df66eab721a8ba4544a597e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000847352_216924160.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37be31b0fd759b7c411131b304487005d95edddf65635b9b37ceaccf8a0d1ce0 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000860280_220233728.pth b/checkpoint_p0/milestones/checkpoint_000860280_220233728.pth new file mode 100644 index 0000000000000000000000000000000000000000..b56fe2484f8975a2cf20f07557cdd954e9d49ee7 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000860280_220233728.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:715dfe5b1e8aa5e298cfbc8a21c63724431de5fa9682f124661c9bd042765fbb +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000873144_223526912.pth b/checkpoint_p0/milestones/checkpoint_000873144_223526912.pth new file mode 100644 index 0000000000000000000000000000000000000000..331413afbc77d2dcf916bab882a284f3a8748067 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000873144_223526912.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf552039969bc9a5a9cf76b3a4a81856b9e86cdc8f6573a270501a3a4687ed74 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000886008_226820096.pth b/checkpoint_p0/milestones/checkpoint_000886008_226820096.pth new file mode 100644 index 0000000000000000000000000000000000000000..0b4061695917c40893e6a8930c2d8199219605f1 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000886008_226820096.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32a25b0bb2e83253b492a2b2222ab1d853a9378d32627a2b7188893b4d33b52b +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000898872_230113280.pth b/checkpoint_p0/milestones/checkpoint_000898872_230113280.pth new file mode 100644 index 0000000000000000000000000000000000000000..adba142617e45376602172f4de586025f31b1770 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000898872_230113280.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75a634ff19bf13e66631d2b4f37af1da269912f14ca67938d8aaa506405e8f3f +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000911800_233422848.pth b/checkpoint_p0/milestones/checkpoint_000911800_233422848.pth new file mode 100644 index 0000000000000000000000000000000000000000..9964f2fe01d0f232919400d3949ca9e1ae1cbf9c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000911800_233422848.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc98292cdc2ee175cef29c5292a4dcf86896802c050215ae7e2fab757f32572d +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000924696_236724224.pth b/checkpoint_p0/milestones/checkpoint_000924696_236724224.pth new file mode 100644 index 0000000000000000000000000000000000000000..2a1e1e250735f38a64f2b16c145d323cecf12aba --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000924696_236724224.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95f1c2cf2186027d8d2624593f882c1b8b06499ae7e67afb91e40c4290912aff +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000937592_240025600.pth b/checkpoint_p0/milestones/checkpoint_000937592_240025600.pth new file mode 100644 index 0000000000000000000000000000000000000000..58868353aae92206523dc5b53ab7014adf1f90ee --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000937592_240025600.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee7b42fb58ae27ec75ef01747b5325aae342a7b2cd6ffb1f3f0219e7669baa4e +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000950520_243335168.pth b/checkpoint_p0/milestones/checkpoint_000950520_243335168.pth new file mode 100644 index 0000000000000000000000000000000000000000..0fd7c5ecb4e5cb654e9ed0955f46c4e5fe06828b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000950520_243335168.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5d4eeafdad38914477c3f615fa452769dd17241a20502e15011c8d27f688c3c +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000963512_246661120.pth b/checkpoint_p0/milestones/checkpoint_000963512_246661120.pth new file mode 100644 index 0000000000000000000000000000000000000000..28c54c825c03b46b847e142655e87a9e2fee38e1 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000963512_246661120.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86d21482937d146a688b1e4efd115dd42e5a154a56ec27e799c19cb585703f51 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000976344_249946112.pth b/checkpoint_p0/milestones/checkpoint_000976344_249946112.pth new file mode 100644 index 0000000000000000000000000000000000000000..62e7f9460084d096bca1ae059dad39dcbf40aa02 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000976344_249946112.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc8ee4921ee440cc3cbb2ed00525387777fc7487564d7f6f6eba1f873b800590 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000989240_253247488.pth b/checkpoint_p0/milestones/checkpoint_000989240_253247488.pth new file mode 100644 index 0000000000000000000000000000000000000000..c49881eaaf0b418f4000a9c0f18a096cd92064ca --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000989240_253247488.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b8ec98e42a7eb75bec60e2b9c728b5fb9add76c9507f1549fb63c0e7063c02f +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001002104_256540672.pth b/checkpoint_p0/milestones/checkpoint_001002104_256540672.pth new file mode 100644 index 0000000000000000000000000000000000000000..323ed4b3229c9c807cb5f41227609fa93af1d70e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001002104_256540672.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9154d05c95b69555a065f93aaa17dfa28ee9d4f93562326385f25ad63c3dc7dc +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001014968_259833856.pth b/checkpoint_p0/milestones/checkpoint_001014968_259833856.pth new file mode 100644 index 0000000000000000000000000000000000000000..d45e33ec30cf55de3fff864e38f00225a87bed6a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001014968_259833856.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:064eccbbb004a3689d338636fcd1c83778181fbbc3ef577efeba564f1d5878e7 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001027992_263168000.pth b/checkpoint_p0/milestones/checkpoint_001027992_263168000.pth new file mode 100644 index 0000000000000000000000000000000000000000..7aa86e4c4965c8dffb1ab5c81274c519e2e4f920 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001027992_263168000.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91dc4446e01d1e735a9ba94d0e6945d231a4d33791a4d2f9b0d6f2d905f75d1b +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001040920_266477568.pth b/checkpoint_p0/milestones/checkpoint_001040920_266477568.pth new file mode 100644 index 0000000000000000000000000000000000000000..8a9abdc3fab48ca1b0d3da4941c35ca1db96bdc3 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001040920_266477568.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c17425ecada616addb1c5456bd9a0deb5cf7d7663aded6d7b3e4fa85d1d888d +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001053816_269778944.pth b/checkpoint_p0/milestones/checkpoint_001053816_269778944.pth new file mode 100644 index 0000000000000000000000000000000000000000..70f492679765b340b9fd392c5825e1d1ebb01a17 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001053816_269778944.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e650349089a6557f1500da432ffb4e1f84a9b29b27ac8c598eebcd2aebefa116 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001066616_273055744.pth b/checkpoint_p0/milestones/checkpoint_001066616_273055744.pth new file mode 100644 index 0000000000000000000000000000000000000000..380c62d1b0424217aae6c85c834a416edbd00760 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001066616_273055744.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36e4cde248f9f0788a7167115438e6aba8af53aab58fa45b31bb9c2ed9c81ba7 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001079416_276332544.pth b/checkpoint_p0/milestones/checkpoint_001079416_276332544.pth new file mode 100644 index 0000000000000000000000000000000000000000..0d909aea900701d7d977cde0b5a8e7f775d7ced8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001079416_276332544.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d7abf8130ed2348a57ca4434a33fbf5b6f4153fbd37d8823c960ecd2f14ba87 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001092248_279617536.pth b/checkpoint_p0/milestones/checkpoint_001092248_279617536.pth new file mode 100644 index 0000000000000000000000000000000000000000..d07e084e7ee48f3705a177ca04b5780313734880 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001092248_279617536.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1c0ccb8e786fa2c65390027d6579f2451ef5b14295c8e8a1fb9ed6e43d10e22 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001105080_282902528.pth b/checkpoint_p0/milestones/checkpoint_001105080_282902528.pth new file mode 100644 index 0000000000000000000000000000000000000000..79b24e830b3b9269f2616001b4921b21c990f49e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001105080_282902528.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8f084cb5907b3c2593c8be0d36e3e543dbcd71fd6ff7f022ab984e103d30df8 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001117912_286187520.pth b/checkpoint_p0/milestones/checkpoint_001117912_286187520.pth new file mode 100644 index 0000000000000000000000000000000000000000..b47be41c9ef9144302090af2caccc57b2575e2a7 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001117912_286187520.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:213bf05c51f42c35473034541f02d877b33fd2ee56121e35a7e892028eef0224 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001130840_289497088.pth b/checkpoint_p0/milestones/checkpoint_001130840_289497088.pth new file mode 100644 index 0000000000000000000000000000000000000000..d7734e451788bd1279de91ac4caf08de76e07e09 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001130840_289497088.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:074d633eb2ba40ddc841fe7dd0c6747963f9ff3ffb25a0beeb1cac77a3009224 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001143672_292782080.pth b/checkpoint_p0/milestones/checkpoint_001143672_292782080.pth new file mode 100644 index 0000000000000000000000000000000000000000..61f9cb8c9fd3d5ef1a566c9a60eb98de3f29cb8e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001143672_292782080.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b6e6b8cff21c29972611027a69235330a6d466d3b48197983e6ae980b0c219e +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001156472_296058880.pth b/checkpoint_p0/milestones/checkpoint_001156472_296058880.pth new file mode 100644 index 0000000000000000000000000000000000000000..e4918b42fa8772602bd160bfa132c4ee2e7ee056 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001156472_296058880.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f5c87995c4c1b53ba8c11b9d584762f40cc24bb0a2d361c5125ad255e7861ae +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001169400_299368448.pth b/checkpoint_p0/milestones/checkpoint_001169400_299368448.pth new file mode 100644 index 0000000000000000000000000000000000000000..b3168a1220470ca7180f730cfc486df6b147987a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001169400_299368448.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbbaa4e519d994641571f7af867cf7e80d6b7b5339d89e63cb8f2ea366178491 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001182328_302678016.pth b/checkpoint_p0/milestones/checkpoint_001182328_302678016.pth new file mode 100644 index 0000000000000000000000000000000000000000..0725b1af671e9f823aeb05d86180bfa7293e35de --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001182328_302678016.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92fb82192118110c31d8faf0e97c98d62a343d306b07ff4636d486a0c8cc56f4 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001195192_305971200.pth b/checkpoint_p0/milestones/checkpoint_001195192_305971200.pth new file mode 100644 index 0000000000000000000000000000000000000000..180c6932ee41ec8bb2d650fda26983541417e2a9 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001195192_305971200.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7b5d4e290874a42ea38b62068524dc3d4c3cb69e44d1daca22fe99ecc712499 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001208088_309272576.pth b/checkpoint_p0/milestones/checkpoint_001208088_309272576.pth new file mode 100644 index 0000000000000000000000000000000000000000..e725196801b85840213e536897aa502cd5a79282 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001208088_309272576.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4124c98d699a3df168b099b0820bd7f13076f2e526ca42e26db74d9c5309db67 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001220888_312549376.pth b/checkpoint_p0/milestones/checkpoint_001220888_312549376.pth new file mode 100644 index 0000000000000000000000000000000000000000..29d6c267c217c5b398f314e7fa2db5068320dc34 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001220888_312549376.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74d8fad14a749fb1b4b027a7e4d0b8ede8f9c972ac8781644f0504bed8f52578 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001233656_315817984.pth b/checkpoint_p0/milestones/checkpoint_001233656_315817984.pth new file mode 100644 index 0000000000000000000000000000000000000000..13b3b7a7b0a16694b1f1cd90ec69475a5e527e0f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001233656_315817984.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49a1befefeadfdd9a60ff4725fae5eb70930e14a4db394ad2fcc5f5a0d897603 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001246552_319119360.pth b/checkpoint_p0/milestones/checkpoint_001246552_319119360.pth new file mode 100644 index 0000000000000000000000000000000000000000..99ed2e831fb412e99532b2b34429e2ebb181788e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001246552_319119360.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:392343445be0fa07570262369230256d35d7f9834cb72d147aab5f537f3bde54 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001259480_322428928.pth b/checkpoint_p0/milestones/checkpoint_001259480_322428928.pth new file mode 100644 index 0000000000000000000000000000000000000000..294fc8a3161a187c5860b62594b7a0693b610f20 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001259480_322428928.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77a8211576760d96a49c719192aa5973c515e66df3e658986b96e49e7371c257 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001272440_325746688.pth b/checkpoint_p0/milestones/checkpoint_001272440_325746688.pth new file mode 100644 index 0000000000000000000000000000000000000000..cf3488eeb6be455433bd379d211aa0e9a2cbe62a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001272440_325746688.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e27c5b202719c669eaa2ae9a0aa4d7fcf29e93ae89aa824c98e5ed4d97a2f92 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001285272_329031680.pth b/checkpoint_p0/milestones/checkpoint_001285272_329031680.pth new file mode 100644 index 0000000000000000000000000000000000000000..e8cfef4c0d5263227545aee234bf4e5dec357aa6 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001285272_329031680.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc6d5ee4d8d1b643af34b536eded031ed09aecc483c7bcf2ec43d0ac564702b7 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001298168_332333056.pth b/checkpoint_p0/milestones/checkpoint_001298168_332333056.pth new file mode 100644 index 0000000000000000000000000000000000000000..cb801a6a7227fee191f24251f92c397adac8d75f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001298168_332333056.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe09be5c5e42b888823311a2187d9b5494ff469566616e3a4c66bece793ae9a1 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001311064_335634432.pth b/checkpoint_p0/milestones/checkpoint_001311064_335634432.pth new file mode 100644 index 0000000000000000000000000000000000000000..bbeae59b8e68c9fbdc9b1c458fdf704cd933448a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001311064_335634432.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:710352a7a64f508730b6312740e6143f214344faf3779da93d1772d4fa889416 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001323960_338935808.pth b/checkpoint_p0/milestones/checkpoint_001323960_338935808.pth new file mode 100644 index 0000000000000000000000000000000000000000..ba4ce9f36c96fd7ce57bd816ea5a1b445097b64f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001323960_338935808.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:346b0f86faa537132d82550d59f64f8845987da10859b5a46dfd90e2004fbf7f +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001336856_342237184.pth b/checkpoint_p0/milestones/checkpoint_001336856_342237184.pth new file mode 100644 index 0000000000000000000000000000000000000000..3a1e371eadbadf2dd1495decc026606e85d629b4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001336856_342237184.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d462480564655d63a4d875ea6d5bd8807b9a45ad40ddd997a545f022ab194cae +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001349720_345530368.pth b/checkpoint_p0/milestones/checkpoint_001349720_345530368.pth new file mode 100644 index 0000000000000000000000000000000000000000..26bc6a1bc187aad8ff07a5b9f7ed33eac13d92ed --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001349720_345530368.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06c27788529eab9db7d550169e62f82c93b1c3c1b8afc7b6acab33e03e124cd3 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001362648_348839936.pth b/checkpoint_p0/milestones/checkpoint_001362648_348839936.pth new file mode 100644 index 0000000000000000000000000000000000000000..55c1ac4604db9060c11e7a370c171cbca3411452 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001362648_348839936.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bc0856d2d4c5d8b8e7199ad5aa4a147fa27f1854ba61c0156d959c7bdb69b1f +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001375608_352157696.pth b/checkpoint_p0/milestones/checkpoint_001375608_352157696.pth new file mode 100644 index 0000000000000000000000000000000000000000..b0aa90916e4f867123f6efa11e5711db4cb494a6 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001375608_352157696.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a5fb817ca1686a6984849d5573766378221bae28b1f92b09d30e5fa4288a8a1 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001388568_355475456.pth b/checkpoint_p0/milestones/checkpoint_001388568_355475456.pth new file mode 100644 index 0000000000000000000000000000000000000000..54ccc5a2bd6a11c31623cf595698bc346189ab22 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001388568_355475456.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c512e45ebc225873cd860451ef986da56ba145585900cb119572d15a51add89 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001401432_358768640.pth b/checkpoint_p0/milestones/checkpoint_001401432_358768640.pth new file mode 100644 index 0000000000000000000000000000000000000000..738331e93f0753fdda924f6e681982cc5294d855 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001401432_358768640.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e38b4f54dce89d1377e281ca3bce819bc03db9c6c2fec1ff22cc16f95b061c0e +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001414296_362061824.pth b/checkpoint_p0/milestones/checkpoint_001414296_362061824.pth new file mode 100644 index 0000000000000000000000000000000000000000..242389178f2797e7c9ab63536700760484c567b8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001414296_362061824.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff93ad6cd2b9c87eb22803b266c348fa5e8fcbbf635ea568829cb86e91851f4c +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001427160_365355008.pth b/checkpoint_p0/milestones/checkpoint_001427160_365355008.pth new file mode 100644 index 0000000000000000000000000000000000000000..eb6f574afda43fcac65fcc86913886b815ef417d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001427160_365355008.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:212d5f116f67f447148db49ded00f785be31fdfddf7ffac355ccd443c6ae2468 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001440024_368648192.pth b/checkpoint_p0/milestones/checkpoint_001440024_368648192.pth new file mode 100644 index 0000000000000000000000000000000000000000..056de6c9fcd57c8dea4704ef459a92766808f71b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001440024_368648192.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8f5a72e5a6d67e806f8bef3d7507421f8a08733bf8cbf80dce07de37b85cd55 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001452984_371965952.pth b/checkpoint_p0/milestones/checkpoint_001452984_371965952.pth new file mode 100644 index 0000000000000000000000000000000000000000..c10927b937d656c97c54950fcb81c3b0920e62d3 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001452984_371965952.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32891cd2fb83eea18a33fe988b6823282851d366ef8a8ca7976f08e087979035 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001465944_375283712.pth b/checkpoint_p0/milestones/checkpoint_001465944_375283712.pth new file mode 100644 index 0000000000000000000000000000000000000000..a06961488b3384c7ed20aa721a9c932db3fe82a1 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001465944_375283712.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f0a2cec09a674b15921ee7b1f822c0f79f46e489a450bad6acb49f01db470e5 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001478840_378585088.pth b/checkpoint_p0/milestones/checkpoint_001478840_378585088.pth new file mode 100644 index 0000000000000000000000000000000000000000..ee6df17ed0b6f8d4e5493eb5bc38249500cb0c87 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001478840_378585088.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:756525a1f5a3ffff8d955ba0f52f0f711c280e215e799363cd179a6ab58b36b8 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001491672_381870080.pth b/checkpoint_p0/milestones/checkpoint_001491672_381870080.pth new file mode 100644 index 0000000000000000000000000000000000000000..f6a0d306142b032a365b156410c72213d595d035 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001491672_381870080.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fdf92f46416e48200e4d1f51e145e97d2f258d66e3743eaaa4dc27e3c908611 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001504568_385171456.pth b/checkpoint_p0/milestones/checkpoint_001504568_385171456.pth new file mode 100644 index 0000000000000000000000000000000000000000..a93525ccceceffe9b7c1ac51358fc6d50bcb8204 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001504568_385171456.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e143e2b68fb7d1df66f5aa05669119ad377f60082ffdafd47abbf043513e56d +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001517464_388472832.pth b/checkpoint_p0/milestones/checkpoint_001517464_388472832.pth new file mode 100644 index 0000000000000000000000000000000000000000..a13aa61bd77ceaff16a116017e83dc50648aa49d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001517464_388472832.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c25a62fba7b51ee3d41d737b4861d9f008881331ac8bd3375cfd6cd8a101cce +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001530392_391782400.pth b/checkpoint_p0/milestones/checkpoint_001530392_391782400.pth new file mode 100644 index 0000000000000000000000000000000000000000..2abeac827f7bc74116fbeb397391ba8d4e36cd5b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001530392_391782400.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ebe7dd2db1e063743785ba3b7accbc8ec5a7bb7bd52156304ee648b40c57d0b +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001543192_395059200.pth b/checkpoint_p0/milestones/checkpoint_001543192_395059200.pth new file mode 100644 index 0000000000000000000000000000000000000000..0b87a8bb2da764c3b70397a95a63475ddfa45075 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001543192_395059200.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:832f6016a3494ffecf30a1e59220b27f4a942d2db44f530ed241f7825133ae16 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001556056_398352384.pth b/checkpoint_p0/milestones/checkpoint_001556056_398352384.pth new file mode 100644 index 0000000000000000000000000000000000000000..1561f86f0a56e1c13783415c8efef52445036d2c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001556056_398352384.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ef58e654d328a93ee969770d7effceb7ecf0606d3d48e6450d7b12e4fd6e29b +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001569016_401670144.pth b/checkpoint_p0/milestones/checkpoint_001569016_401670144.pth new file mode 100644 index 0000000000000000000000000000000000000000..0865c07f02a0abdf35387e75595796af295b2e57 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001569016_401670144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4457fbdfb7fdc6f13e81e634fc393eaf4b18845972634169ae650487f31e0945 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001581912_404971520.pth b/checkpoint_p0/milestones/checkpoint_001581912_404971520.pth new file mode 100644 index 0000000000000000000000000000000000000000..ff63fe3f0471949d2e9fb77a77666ef63daece52 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001581912_404971520.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45139b80db5f829fe9892ddfa2653517f44a911f80391bb406ac18fd3ff2dd1d +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001594776_408264704.pth b/checkpoint_p0/milestones/checkpoint_001594776_408264704.pth new file mode 100644 index 0000000000000000000000000000000000000000..6116d1a976ea94647ccffe12b8caaec4051ab0f7 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001594776_408264704.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd04957ff5b7219f5bbb32ca521286c7cfd26f76300dc39c20b86c959f19d7f7 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001607640_411557888.pth b/checkpoint_p0/milestones/checkpoint_001607640_411557888.pth new file mode 100644 index 0000000000000000000000000000000000000000..a0fbaf002391bd33ad89087429e10fa8ef3a53bc --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001607640_411557888.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0a5bab0b42574ad12c04193b9b3b61be77af6b6ab685c5e8910a4d667200b97 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001620568_414867456.pth b/checkpoint_p0/milestones/checkpoint_001620568_414867456.pth new file mode 100644 index 0000000000000000000000000000000000000000..378d9c419383ba37b1c82d87e711fa810896a65d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001620568_414867456.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f739108f2772d1890100cffb326d3a8d3db5121cc1137af437c4fa233cc1cdb +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001633496_418177024.pth b/checkpoint_p0/milestones/checkpoint_001633496_418177024.pth new file mode 100644 index 0000000000000000000000000000000000000000..299be32b1e7c92a0e3d5207ee85724260782a0e1 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001633496_418177024.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fdf33dcabd3d41b5657a4dff6667e2ea8d8f1cdb55a13b82bfa76abc742325f +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001646520_421511168.pth b/checkpoint_p0/milestones/checkpoint_001646520_421511168.pth new file mode 100644 index 0000000000000000000000000000000000000000..85e139b6e33d245e06039dc666a9a919c83fd6c5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001646520_421511168.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17ae5ba997489c0af3a81d2fa5496e1cfc53d38782ae6de1f17d36f5ab67f098 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001659416_424812544.pth b/checkpoint_p0/milestones/checkpoint_001659416_424812544.pth new file mode 100644 index 0000000000000000000000000000000000000000..bf6f4bffa1977bbf6b6ffbc5cc0700b4777fed3c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001659416_424812544.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90372def0b96763bca7e30492e3dcf0ea0c1fc53a47eacfe2b696714805af1e0 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001672312_428113920.pth b/checkpoint_p0/milestones/checkpoint_001672312_428113920.pth new file mode 100644 index 0000000000000000000000000000000000000000..a456809463e5e1c308fd1becafed3770aae893c4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001672312_428113920.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d5a55676adce5adf176e5e13244ed127cc784de58bde034bdccd5a3fc308781 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001685208_431415296.pth b/checkpoint_p0/milestones/checkpoint_001685208_431415296.pth new file mode 100644 index 0000000000000000000000000000000000000000..cbf26a864bc74a207f6f8a871d081833d2df5651 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001685208_431415296.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a68cff5c83641a26b6314e6a10ca1b534f7477f0d47db9759251b08782064b2c +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001698104_434716672.pth b/checkpoint_p0/milestones/checkpoint_001698104_434716672.pth new file mode 100644 index 0000000000000000000000000000000000000000..0eb9256f49e47956b08c4c6c48975e485ad3a775 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001698104_434716672.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:beea317f2d817652e72ff96ff1aac7dd71e5a7f30bd677baa014e47a778b007e +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001710904_437993472.pth b/checkpoint_p0/milestones/checkpoint_001710904_437993472.pth new file mode 100644 index 0000000000000000000000000000000000000000..6ba399b5650a363ac8e7b746eb9e569ce55fe590 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001710904_437993472.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:590bd2436bbda75f85e579f8559b3822127f7a64d616a7c9ded6e21f1018c1ad +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001723832_441303040.pth b/checkpoint_p0/milestones/checkpoint_001723832_441303040.pth new file mode 100644 index 0000000000000000000000000000000000000000..5d1c24091ce7efd3755178fc450ab04bcacd3454 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001723832_441303040.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec768cb22fe1939358dc225b3409bfe449a1f8adc3ac4d7fd3a1a2e33bedfa14 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001736760_444612608.pth b/checkpoint_p0/milestones/checkpoint_001736760_444612608.pth new file mode 100644 index 0000000000000000000000000000000000000000..5ada4b7d95ef89f4b0dcbae2392cedab02b02ee8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001736760_444612608.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:175dc2a57bc38c1ed0cb6cf247a017fb51c7393d047eab28576f2ae847e424bd +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001749688_447922176.pth b/checkpoint_p0/milestones/checkpoint_001749688_447922176.pth new file mode 100644 index 0000000000000000000000000000000000000000..247099667bc7e9c5078cd516fff50c146153b06b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001749688_447922176.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ace20f807761f056bd63536b20bd323656fa23e7e49613e6d47209982f7d641 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001762520_451207168.pth b/checkpoint_p0/milestones/checkpoint_001762520_451207168.pth new file mode 100644 index 0000000000000000000000000000000000000000..aa95a5454207550e1c45b7e67e8da5dcaca39ea8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001762520_451207168.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:350b3aef758a071861166a41d3daeaecc9f1055815260a11dc4f1eec094dad4e +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001775352_454492160.pth b/checkpoint_p0/milestones/checkpoint_001775352_454492160.pth new file mode 100644 index 0000000000000000000000000000000000000000..484e8f4623f2dda2266e1f89b60c6a7ed9a838dc --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001775352_454492160.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46bd78d80d9acd52c245d4a15b08503cd7fe3d1420cb5a3f312bc572aad3dd99 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001788216_457785344.pth b/checkpoint_p0/milestones/checkpoint_001788216_457785344.pth new file mode 100644 index 0000000000000000000000000000000000000000..b82d6c4a77e512acae21e0bf61ac5c4c4af4aa05 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001788216_457785344.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d74b91057b8852a6833a1a18fa6881df1def6d8f71b81afa99ec923f606445dd +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001801144_461094912.pth b/checkpoint_p0/milestones/checkpoint_001801144_461094912.pth new file mode 100644 index 0000000000000000000000000000000000000000..0380f2676187a6f4c8b262fea568c68c99f990d5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001801144_461094912.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c6400734761c9b798cb5abcae40c0081be9f2f6ea57b11b4c67209acba98b7f +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001814040_464396288.pth b/checkpoint_p0/milestones/checkpoint_001814040_464396288.pth new file mode 100644 index 0000000000000000000000000000000000000000..bfb417efe2f5ebf183c4ab2ddcde0a0a3c71091f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001814040_464396288.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1decff24061e75a69235c95f0a62e2fcec841e2b309577eeba4f73f63bb05e0b +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001826936_467697664.pth b/checkpoint_p0/milestones/checkpoint_001826936_467697664.pth new file mode 100644 index 0000000000000000000000000000000000000000..e858a955efcc7e5133020621c9f22a078b508391 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001826936_467697664.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89182cf9fa61db8821b15b137fe8ffa8e0ceb8ce498db7d28259007e5ccf160f +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001839864_471007232.pth b/checkpoint_p0/milestones/checkpoint_001839864_471007232.pth new file mode 100644 index 0000000000000000000000000000000000000000..5928b19af0778820ecdf352228f0baf66bdfc8b8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001839864_471007232.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:088239aa8e74b52c929ac0d6945ac7a093434573f2b192f50322fa654cc498d8 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001852728_474300416.pth b/checkpoint_p0/milestones/checkpoint_001852728_474300416.pth new file mode 100644 index 0000000000000000000000000000000000000000..d13b0fa49e08715ae1619a2778f10dfef87ba1a0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001852728_474300416.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a7ad13186e61aa8dbd3d651de8f230927053c09a13264144f0e03cb48ce89cb +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001865592_477593600.pth b/checkpoint_p0/milestones/checkpoint_001865592_477593600.pth new file mode 100644 index 0000000000000000000000000000000000000000..cf230dcc4539916f2fce6bcd3fe562b77304116c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001865592_477593600.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e4f3780f73f32e2417890b04e30083f1a8d42ab6bdeb1ff6d7910ba9057db01 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001878520_480903168.pth b/checkpoint_p0/milestones/checkpoint_001878520_480903168.pth new file mode 100644 index 0000000000000000000000000000000000000000..7ee325b51c9542ceccf20df573bdfd3c04608276 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001878520_480903168.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25b7c5a689d752731d8ca7b6783982c6407433f6c146ec6cc629082ed0501140 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001891352_484188160.pth b/checkpoint_p0/milestones/checkpoint_001891352_484188160.pth new file mode 100644 index 0000000000000000000000000000000000000000..8d3583b786fca555bb23bb0f9f8e5e2897b8e7a4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001891352_484188160.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a546d4745da07065623d6b728aeb4ead64051884dc7cf53a6f59043a2979352 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001904216_487481344.pth b/checkpoint_p0/milestones/checkpoint_001904216_487481344.pth new file mode 100644 index 0000000000000000000000000000000000000000..26881daa87f823ddfaa9e3f9452fcf23eb478d86 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001904216_487481344.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac2c445befc96046b2b89854e5bbdfc59e1fe45173e884ca4d0a2b0acba7df7d +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001917176_490799104.pth b/checkpoint_p0/milestones/checkpoint_001917176_490799104.pth new file mode 100644 index 0000000000000000000000000000000000000000..9fd29c6f089885337ca4559efc8688ad51516a04 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001917176_490799104.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:656c924cef500fca0d75cd6ff4efe41e78b168f50732a15a525b2750b137ee88 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001930040_494092288.pth b/checkpoint_p0/milestones/checkpoint_001930040_494092288.pth new file mode 100644 index 0000000000000000000000000000000000000000..a03b2e62d6cabe8faef957bbb961a1aeb0785e4b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001930040_494092288.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21841e27e2f6e0fc363ebd3f7d125b3fc83b3644ebae12879a6898287a496bd2 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001942904_497385472.pth b/checkpoint_p0/milestones/checkpoint_001942904_497385472.pth new file mode 100644 index 0000000000000000000000000000000000000000..cfee1a2abc4049042899d78c7b8149a36f467abe --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001942904_497385472.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:497baa722590edfd739d930eed546601cef78544e446540120524b053f685a21 +size 20797067 diff --git a/checkpoint_p1/best_001948480_498810880_reward_0.440.pth b/checkpoint_p1/best_001948480_498810880_reward_0.440.pth new file mode 100644 index 0000000000000000000000000000000000000000..7877c4fd0864b23a280b8bb516da165c8c1e628d --- /dev/null +++ b/checkpoint_p1/best_001948480_498810880_reward_0.440.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e616457c0b4b6ce94efc0a391f6a7a34a0b6ae3398a617591d2b149f5a70568c +size 20795763 diff --git a/checkpoint_p1/checkpoint_001954272_500621312.pth b/checkpoint_p1/checkpoint_001954272_500621312.pth new file mode 100644 index 0000000000000000000000000000000000000000..da7ace68977171dda63513d4eff29048415858f1 --- /dev/null +++ b/checkpoint_p1/checkpoint_001954272_500621312.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c61ce923726cd83b454e562e95c923dce4bda50fa3f02e6d99a5c6a2a954b40d +size 20796099 diff --git a/checkpoint_p1/checkpoint_001954944_500965376.pth b/checkpoint_p1/checkpoint_001954944_500965376.pth new file mode 100644 index 0000000000000000000000000000000000000000..c4bdd757d6612aaa036197cb6cca637fe123f8a3 --- /dev/null +++ b/checkpoint_p1/checkpoint_001954944_500965376.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e806c6660dbb59997c34ed92465279ed582d873bad58dbb326ca07756d3bf75f +size 20796099 diff --git a/checkpoint_p1/milestones/checkpoint_000012512_3203072.pth b/checkpoint_p1/milestones/checkpoint_000012512_3203072.pth new file mode 100644 index 0000000000000000000000000000000000000000..fecb556b9a265e3b173f2d664260c7e47fe87adb --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000012512_3203072.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7bb7ef79fc3bb6616865252c8564dfdcf31f59b9730ae44902b84093902cdfc +size 20796955 diff --git a/checkpoint_p1/milestones/checkpoint_000025344_6488064.pth b/checkpoint_p1/milestones/checkpoint_000025344_6488064.pth new file mode 100644 index 0000000000000000000000000000000000000000..1f98b1115d2bb0c080ea0ea89095a0f3b555c219 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000025344_6488064.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5fe5e17b72023f5b449831a0f28c1f42de8aee5f358905556e0f63d26886c0c +size 20796955 diff --git a/checkpoint_p1/milestones/checkpoint_000038272_9797632.pth b/checkpoint_p1/milestones/checkpoint_000038272_9797632.pth new file mode 100644 index 0000000000000000000000000000000000000000..b5e49a0b7eee8910d848452370aa27870da97d70 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000038272_9797632.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70278b08c5490ad921131e35d3257bce9d655e2db8f3419e3c639a831e36c043 +size 20796955 diff --git a/checkpoint_p1/milestones/checkpoint_000051104_13082624.pth b/checkpoint_p1/milestones/checkpoint_000051104_13082624.pth new file mode 100644 index 0000000000000000000000000000000000000000..e0184068ae8fc67ba654fb7a804ca30e62e13898 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000051104_13082624.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e933436273fb7cfbbdcceb4914a482ac2632b0acef58691f8f4343d0d120654 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000063936_16367616.pth b/checkpoint_p1/milestones/checkpoint_000063936_16367616.pth new file mode 100644 index 0000000000000000000000000000000000000000..ba0ccc76390da090a35439cd0b02089932322cb0 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000063936_16367616.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88976153fd0e13caca4724e723e9795605693b5bc2def0ecdaad3cca1c3531ec +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000076800_19660800.pth b/checkpoint_p1/milestones/checkpoint_000076800_19660800.pth new file mode 100644 index 0000000000000000000000000000000000000000..10cc92fdad49f1d4897fb84bcbe8ad9c7e51df08 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000076800_19660800.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1aced3f217c2f01a36c8cf86a50d0ff06991fef8d100fab4bd32bc6284729f5 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000089664_22953984.pth b/checkpoint_p1/milestones/checkpoint_000089664_22953984.pth new file mode 100644 index 0000000000000000000000000000000000000000..59a94c4de799ddedff1dc6ce35c6b2a758f985a0 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000089664_22953984.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73dba7dc57b9469818fa1b76b1cf3eda6770244546e0f8d6cc429e881108b9df +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000102528_26247168.pth b/checkpoint_p1/milestones/checkpoint_000102528_26247168.pth new file mode 100644 index 0000000000000000000000000000000000000000..5471a7266e6391d5fbc772f3e8d44aceedc8c087 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000102528_26247168.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ae3be536faec81462b15d03a08299d5eb9be76958cedd51227dc864e03f5be1 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000115424_29548544.pth b/checkpoint_p1/milestones/checkpoint_000115424_29548544.pth new file mode 100644 index 0000000000000000000000000000000000000000..8fe0da829183e112ac256ab2c9f91599501b6fe9 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000115424_29548544.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:613a146085f818e92610234748c1a22f8b547e2883ff4862117d6dcbda476370 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000128288_32841728.pth b/checkpoint_p1/milestones/checkpoint_000128288_32841728.pth new file mode 100644 index 0000000000000000000000000000000000000000..9e619550733d33d2cc9779463bd71ac1643a303d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000128288_32841728.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:befdb678692bfc0049b2701e9484dc53640fe011e53065119b860fb1e6db5164 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000141152_36134912.pth b/checkpoint_p1/milestones/checkpoint_000141152_36134912.pth new file mode 100644 index 0000000000000000000000000000000000000000..ddfc66e15a01416e9a0e4255e3be0bd6f2212cf0 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000141152_36134912.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f7c6756a73ff647a170639c0d84505a5c9ea061e3e8658f1cc494065ba534da +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000153984_39419904.pth b/checkpoint_p1/milestones/checkpoint_000153984_39419904.pth new file mode 100644 index 0000000000000000000000000000000000000000..261b7063240305fe4d093031e1207a7ec559836c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000153984_39419904.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e46e43ca070478143681f1006888589026828bcb00434f48eab8822ac523df9e +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000166848_42713088.pth b/checkpoint_p1/milestones/checkpoint_000166848_42713088.pth new file mode 100644 index 0000000000000000000000000000000000000000..b89d8391a628d58da4116bf37bed4ec36a1eb5a6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000166848_42713088.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07b3216044211ec1f258cee92e6105f08787c311e3e58d55d99acff8b4ad3915 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000179648_45989888.pth b/checkpoint_p1/milestones/checkpoint_000179648_45989888.pth new file mode 100644 index 0000000000000000000000000000000000000000..99a072d1fd288740247407396e109586185e8570 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000179648_45989888.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f021b1e8374efc290362b5e758028075f0660349bbd7746a05b3d1c7fb72e986 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000192448_49266688.pth b/checkpoint_p1/milestones/checkpoint_000192448_49266688.pth new file mode 100644 index 0000000000000000000000000000000000000000..40724f9b41c69bd6fea24a68b3bec57d12c43112 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000192448_49266688.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c45a1b544d8ab917eca9cac3af3cc7a6e1267806eba91a155adf42d5d45ee74 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000205248_52543488.pth b/checkpoint_p1/milestones/checkpoint_000205248_52543488.pth new file mode 100644 index 0000000000000000000000000000000000000000..fdf080b28c50ce0ecbaa635275588043f8c69680 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000205248_52543488.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80dd9f99ac01a622741c6ef6867046374db6cc591225fd687ba2fcb5880ffdf7 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000218016_55812096.pth b/checkpoint_p1/milestones/checkpoint_000218016_55812096.pth new file mode 100644 index 0000000000000000000000000000000000000000..be296e39ed95db869600c9cf495fc1878e05fe93 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000218016_55812096.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b6cec418a29eeb8a4835ca298d717df593cebbdcc1c0268c3bdeb81917c5984 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000230880_59105280.pth b/checkpoint_p1/milestones/checkpoint_000230880_59105280.pth new file mode 100644 index 0000000000000000000000000000000000000000..76021bbd056973ced317a036203730a394484d16 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000230880_59105280.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fd7e2a8667a8838c693245b0983ee377ff16b2e7c306c637fac075f3cbd5850 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000243648_62373888.pth b/checkpoint_p1/milestones/checkpoint_000243648_62373888.pth new file mode 100644 index 0000000000000000000000000000000000000000..50ca4ba0a61f8595c1622c891c3338480b5abe43 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000243648_62373888.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99cbbea2ddff91893fe15ba6d587a1f275bc9ea32b3a623b14473fc0922fc11f +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000256480_65658880.pth b/checkpoint_p1/milestones/checkpoint_000256480_65658880.pth new file mode 100644 index 0000000000000000000000000000000000000000..4cb9ea4bd47b965a50ead9cb813832f814db4796 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000256480_65658880.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f00bc8c676286c3fbce79d91fba81c62b26e12bfbf701379f832f72efa832c7 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000269344_68952064.pth b/checkpoint_p1/milestones/checkpoint_000269344_68952064.pth new file mode 100644 index 0000000000000000000000000000000000000000..f3c2f667cbdc7ac4c758ac15258f8a23743c716e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000269344_68952064.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec182a1c84a908992db924a43c9538afc10e3b796c214b9b24cfab230da422a9 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000282176_72237056.pth b/checkpoint_p1/milestones/checkpoint_000282176_72237056.pth new file mode 100644 index 0000000000000000000000000000000000000000..e96c7df5f79300a2f86f9f386bddf105714915c5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000282176_72237056.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:042e70b10374762d6304a7d588aabdce300de5ed9253e6131cdfd02bb67556b4 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000295008_75522048.pth b/checkpoint_p1/milestones/checkpoint_000295008_75522048.pth new file mode 100644 index 0000000000000000000000000000000000000000..99037abe794739c9252f34abc325ce23db9e9e5a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000295008_75522048.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:489d3c3c081f5c5e85b577fb838af2a924e5bdbb3d7d2ea8f72d4475d750e57c +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000307904_78823424.pth b/checkpoint_p1/milestones/checkpoint_000307904_78823424.pth new file mode 100644 index 0000000000000000000000000000000000000000..52eb688a7dc5ac96b9cdf4ddab0624a89d08a86d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000307904_78823424.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dda2577f9b858d53a14c19ee06aec6300e69498caf976423a55f1a00904c9cf8 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000320608_82075648.pth b/checkpoint_p1/milestones/checkpoint_000320608_82075648.pth new file mode 100644 index 0000000000000000000000000000000000000000..b03c3c1ffa37d5ae9ccb30c90195ba4f6b47d664 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000320608_82075648.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bce73124f5a413781617e4704c126adb3130747ee6467b38a6e8502af1312c6b +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000332832_85204992.pth b/checkpoint_p1/milestones/checkpoint_000332832_85204992.pth new file mode 100644 index 0000000000000000000000000000000000000000..c48176ee50fe56159308af630452e0ce33498593 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000332832_85204992.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db98c89fa132d92d33c3e26743bf143810ac064ea7ac33c4c1fe736dccaec56f +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000345472_88440832.pth b/checkpoint_p1/milestones/checkpoint_000345472_88440832.pth new file mode 100644 index 0000000000000000000000000000000000000000..4100e0c0f3ac5edb5d2b400b50cf38b00f4cb45f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000345472_88440832.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30ff50965040d03859dd1a03ac48b4de274f2ef42823494651ac19934d064ef1 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000358400_91750400.pth b/checkpoint_p1/milestones/checkpoint_000358400_91750400.pth new file mode 100644 index 0000000000000000000000000000000000000000..4228694ea52c66284afd73f84eaad89ff8de663c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000358400_91750400.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fcec89de39e6de68cd2f085b31b6d12da9ecab3f3ef4850e907e5afcb8412e3 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000371296_95051776.pth b/checkpoint_p1/milestones/checkpoint_000371296_95051776.pth new file mode 100644 index 0000000000000000000000000000000000000000..25a6f85eaece71804dbe2dbf5d8d624d7b388d16 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000371296_95051776.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c56670029d8a1b6a017c4169aee844770c06f76cd18471b33029c24e1d496ac3 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000384160_98344960.pth b/checkpoint_p1/milestones/checkpoint_000384160_98344960.pth new file mode 100644 index 0000000000000000000000000000000000000000..2fe0a41e60fab5cb8eb4f7a4b3de4aad9dbc6de0 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000384160_98344960.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f97af97ca988b27dee6f28d1d451d86eb67970dcbd1a201b6d98d26c0bc37792 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000397056_101646336.pth b/checkpoint_p1/milestones/checkpoint_000397056_101646336.pth new file mode 100644 index 0000000000000000000000000000000000000000..5dc31f1699744e8935f10aa366db51d328310d13 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000397056_101646336.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c49aa93bd1e826a88e7ec0812353c794c465e735501b54a205a053298cd116c +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000409952_104947712.pth b/checkpoint_p1/milestones/checkpoint_000409952_104947712.pth new file mode 100644 index 0000000000000000000000000000000000000000..54739cffdb768f20d7c16f0015547689c1ebfe91 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000409952_104947712.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:727c2dfd2f71b41f3b6c731a42175914ada29842f2697018d371161fa8771c3a +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000422816_108240896.pth b/checkpoint_p1/milestones/checkpoint_000422816_108240896.pth new file mode 100644 index 0000000000000000000000000000000000000000..33595cc8f042b4e69e210f9908fb6ae7c53de307 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000422816_108240896.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f25e6af1cf10a0ee7b2a2487d6a63f8374bd374137e585a8a19f405b62afe763 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000435712_111542272.pth b/checkpoint_p1/milestones/checkpoint_000435712_111542272.pth new file mode 100644 index 0000000000000000000000000000000000000000..3e2dccb7f1adb1db83471b8d07bc4688b997b7ae --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000435712_111542272.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27db06f6734d68df06a20cd4c0cac9f9888b923a651adc0a6d275ee9bcdf715b +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000448608_114843648.pth b/checkpoint_p1/milestones/checkpoint_000448608_114843648.pth new file mode 100644 index 0000000000000000000000000000000000000000..d43bff318cba5e82ba243b6dc6275090d352dc56 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000448608_114843648.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd78b59ab229e5aa09420719fbc18af29a27a1d7d9005fdb18199abea21691f2 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000461472_118136832.pth b/checkpoint_p1/milestones/checkpoint_000461472_118136832.pth new file mode 100644 index 0000000000000000000000000000000000000000..6f907065e850c904ebf49cd914d095bb6efcc60e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000461472_118136832.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cde2c642433750e053217c9b7cfc380123aab2c3d9bf93b417230644c0498a77 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000474336_121430016.pth b/checkpoint_p1/milestones/checkpoint_000474336_121430016.pth new file mode 100644 index 0000000000000000000000000000000000000000..73dc3b143152cbbda47b02c7a189347223945077 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000474336_121430016.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2064965414f40864e4ad9f6d1a39f35e48d44a8030b25c5a35e00693649cdfd3 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000487264_124739584.pth b/checkpoint_p1/milestones/checkpoint_000487264_124739584.pth new file mode 100644 index 0000000000000000000000000000000000000000..b52d5e912390fab246256086ccbd85d1264a59b8 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000487264_124739584.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed1a7d0dfdbab842960c027734a2b51daae25c16f6a7131505973f4e4612a6e2 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000500160_128040960.pth b/checkpoint_p1/milestones/checkpoint_000500160_128040960.pth new file mode 100644 index 0000000000000000000000000000000000000000..dfd6601e7ab929b04af1bee64d14c0fcfbab0aa2 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000500160_128040960.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7428db60ab266974a75071ee8f09bef4f0e7a65c55fa2085b994a5aed333e63c +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000512992_131325952.pth b/checkpoint_p1/milestones/checkpoint_000512992_131325952.pth new file mode 100644 index 0000000000000000000000000000000000000000..b329fd749e22194411a0cd83c59e9af17c915f60 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000512992_131325952.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb4863b609f85ccc9f2e0ba876cc73a14e950591655551d209c5641231b9e7c8 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000525920_134635520.pth b/checkpoint_p1/milestones/checkpoint_000525920_134635520.pth new file mode 100644 index 0000000000000000000000000000000000000000..4ca7945ac9d20a51f2ca7d7434137f3b85b2b5b8 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000525920_134635520.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37be45f3f575628294c06b001dcf1c34e33441d0bae86164118e0e07b3ce0c8f +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000538848_137945088.pth b/checkpoint_p1/milestones/checkpoint_000538848_137945088.pth new file mode 100644 index 0000000000000000000000000000000000000000..65374aa3e6007ae5daf2a6f2d3e1194270bd8c6c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000538848_137945088.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:514f588a45c705c9a71c3df9ee1cc82682a0dfb77b6a2426ad5e3cff16ef9ed8 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000551712_141238272.pth b/checkpoint_p1/milestones/checkpoint_000551712_141238272.pth new file mode 100644 index 0000000000000000000000000000000000000000..8d9a76e893f8560be51000a474628a164d062866 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000551712_141238272.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d52ece118fe224219fb98366771afac5cf848adcaaadee527435fdd9dfbfe7ec +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000564480_144506880.pth b/checkpoint_p1/milestones/checkpoint_000564480_144506880.pth new file mode 100644 index 0000000000000000000000000000000000000000..179a0915a9ac28ba8620f79cb7d74ac91aea739a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000564480_144506880.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8579a0c08b7b7763ed8d9c7e0b7c7fd4f790165cf6330f73056ac78c9c38b03a +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000577376_147808256.pth b/checkpoint_p1/milestones/checkpoint_000577376_147808256.pth new file mode 100644 index 0000000000000000000000000000000000000000..098ec9fb27dd88d188cb97132d12aa622c869e7c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000577376_147808256.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34300210c260ebc5ffdf6b4f07df24421272dbf9b7ee34314205aceec35af14a +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000590208_151093248.pth b/checkpoint_p1/milestones/checkpoint_000590208_151093248.pth new file mode 100644 index 0000000000000000000000000000000000000000..0fafa17402cf44e3c57e9e4485045856fbc2887a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000590208_151093248.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b746b9bd5975fbd6cb03caf6377ea2c1a5edad57d50af5fd5e479eacbf6c687b +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000603104_154394624.pth b/checkpoint_p1/milestones/checkpoint_000603104_154394624.pth new file mode 100644 index 0000000000000000000000000000000000000000..eb5cd781c7076ce6d554ba9fa5f96fbb1103a212 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000603104_154394624.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edbab28285ccfe9fe73abe138f6c30bce1219870f091122bbd2cc5ca5931ced3 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000615936_157679616.pth b/checkpoint_p1/milestones/checkpoint_000615936_157679616.pth new file mode 100644 index 0000000000000000000000000000000000000000..4851041600fed83d29dc45f51b91e2ad16a5b3e0 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000615936_157679616.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96eec46ad9cb6190f08da08a3e98b177051c149ffafa08e0615c9c579c605ae8 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000628800_160972800.pth b/checkpoint_p1/milestones/checkpoint_000628800_160972800.pth new file mode 100644 index 0000000000000000000000000000000000000000..9dd7792a469be50e322f3f69a895852774c8d0d1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000628800_160972800.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aece91fb3cc3c0b3351f5a2f43bff7669ecc074f7ca99c2762d91031d61f12a7 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000641696_164274176.pth b/checkpoint_p1/milestones/checkpoint_000641696_164274176.pth new file mode 100644 index 0000000000000000000000000000000000000000..61c3dce06fa9bd4d6160c22f7fb01b015d37b24a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000641696_164274176.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d821d48300e0e25de20ff956b0b6447ad8c97e6cfcc214ff198bece925b2733 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000654592_167575552.pth b/checkpoint_p1/milestones/checkpoint_000654592_167575552.pth new file mode 100644 index 0000000000000000000000000000000000000000..9b16bdbd1a3ba1110ff722396422fbedd06c5675 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000654592_167575552.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cd4b14d59061b7da427837b7684469184748abcb2328880d81b089f6c00676f +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000667520_170885120.pth b/checkpoint_p1/milestones/checkpoint_000667520_170885120.pth new file mode 100644 index 0000000000000000000000000000000000000000..583a84dbc174d2483e45942c340d4bbc7fff92fe --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000667520_170885120.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd104e52e81734fa846d748d2e34a4715f211c773e066fd5f4d6805c0e91c0f6 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000680288_174153728.pth b/checkpoint_p1/milestones/checkpoint_000680288_174153728.pth new file mode 100644 index 0000000000000000000000000000000000000000..c167d5af8bbc10b98c1f2f0575f00f11b13e4d4b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000680288_174153728.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d19990e319d5073cd47b39b04eb96ef86497bddbca67166aa491bc2d5ba2ac8a +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000693184_177455104.pth b/checkpoint_p1/milestones/checkpoint_000693184_177455104.pth new file mode 100644 index 0000000000000000000000000000000000000000..415eeb9d72fc84b74512b7ed93543f2dc7da5e70 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000693184_177455104.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:150278fd01647b7a5f1e4440ccba5efa4f15e31cec208808e09e8172dee36104 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000706112_180764672.pth b/checkpoint_p1/milestones/checkpoint_000706112_180764672.pth new file mode 100644 index 0000000000000000000000000000000000000000..0901919eb87c5e1809d87d6c3d309545bc3defad --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000706112_180764672.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b47ced42bfdc865d52a75bec63e471c6252ff866dc58119654ecce209af96d4 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000719072_184082432.pth b/checkpoint_p1/milestones/checkpoint_000719072_184082432.pth new file mode 100644 index 0000000000000000000000000000000000000000..ba028cbe39226266fd3512779388dd781a6984d1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000719072_184082432.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8e3b42b6473a5a5b0869bf36568aa17171fb6b81371b39f48442ee850909a17 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000732000_187392000.pth b/checkpoint_p1/milestones/checkpoint_000732000_187392000.pth new file mode 100644 index 0000000000000000000000000000000000000000..b569239444402509ad6ef1decc921d9a57e0c88b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000732000_187392000.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a53770467cb8bb38e734489df45bf42e44702f1c9f66914b7d8487372ba5307 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000744928_190701568.pth b/checkpoint_p1/milestones/checkpoint_000744928_190701568.pth new file mode 100644 index 0000000000000000000000000000000000000000..74536eb63d92165d4faf8ba2b1cfd5cbf8bd677f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000744928_190701568.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:773759db682be5d0bb1dc7de60234a547af25a7ff62cb478a1395ce115b0824e +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000757824_194002944.pth b/checkpoint_p1/milestones/checkpoint_000757824_194002944.pth new file mode 100644 index 0000000000000000000000000000000000000000..e6def83583d0f7dfc3124acb83a848cb6cbfab37 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000757824_194002944.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05a1e4ad5d84b7c2abc7a804852fe42466d851a12352e9264a0ee54587ffc5ea +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000770752_197312512.pth b/checkpoint_p1/milestones/checkpoint_000770752_197312512.pth new file mode 100644 index 0000000000000000000000000000000000000000..a7e4f399c42810e93ee9047fbb6fff3bc39f86ca --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000770752_197312512.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f3942f2cc95e42aad42eaf8e6dc3a95f1d32245ab721962dc4a977937ae9186 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000783712_200630272.pth b/checkpoint_p1/milestones/checkpoint_000783712_200630272.pth new file mode 100644 index 0000000000000000000000000000000000000000..5b5c9dc0def3183549d2fc3604a236368a015611 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000783712_200630272.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df42079f1c27a1fab565e5ff9ab5256edaa7f28de88f9bf9c8fcaf7222e7f09a +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000796480_203898880.pth b/checkpoint_p1/milestones/checkpoint_000796480_203898880.pth new file mode 100644 index 0000000000000000000000000000000000000000..6cc8b0e5e08db6a2caf55ade5354f5beacc13d6d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000796480_203898880.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42dddfe3871a112e71a461ed71aeb04e983e8ec65de5a6877548417340115ec4 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000809408_207208448.pth b/checkpoint_p1/milestones/checkpoint_000809408_207208448.pth new file mode 100644 index 0000000000000000000000000000000000000000..2abbcbebcf2471d7df4e1d67f2317d5a7bb70e6d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000809408_207208448.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:529271103fd6dc398b9a2d14128bb6636cddf2e30c21ada77513ece17983ad9c +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000822304_210509824.pth b/checkpoint_p1/milestones/checkpoint_000822304_210509824.pth new file mode 100644 index 0000000000000000000000000000000000000000..489e8dc3fbd1ca0f37196f91f860ff5308c39110 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000822304_210509824.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3d1667bf2bf3581cbcbc5fc8af9ed3bb09e8d34b0554f9116de46647cca9599 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000835296_213835776.pth b/checkpoint_p1/milestones/checkpoint_000835296_213835776.pth new file mode 100644 index 0000000000000000000000000000000000000000..05a653bdf4fa3f69a4a647af0b78759d583f3d16 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000835296_213835776.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69aa87cd25bc41133d185712c45b7bc13584debfc0bb5c778f38becf965f76db +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000848256_217153536.pth b/checkpoint_p1/milestones/checkpoint_000848256_217153536.pth new file mode 100644 index 0000000000000000000000000000000000000000..796404378e3cd6d7a1c904971649965a45280820 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000848256_217153536.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1518b11363b1512eb408b08f08868bcbc645a77e2d76d571a8967a946ef57227 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000861152_220454912.pth b/checkpoint_p1/milestones/checkpoint_000861152_220454912.pth new file mode 100644 index 0000000000000000000000000000000000000000..9b06249517239f69c2b2616001f6c90be4303fc3 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000861152_220454912.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72383f9269a50a17d34a06c0d94a587d670dcf957d2ad1e3be77b81b9994c289 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000874080_223764480.pth b/checkpoint_p1/milestones/checkpoint_000874080_223764480.pth new file mode 100644 index 0000000000000000000000000000000000000000..9fd212b97972cfec270ceff64522e4c1e3f01490 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000874080_223764480.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f6420ee237d9faf888a4d823ada21bd4865b2e66af820c73ea284fe178e0f4a +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000887040_227082240.pth b/checkpoint_p1/milestones/checkpoint_000887040_227082240.pth new file mode 100644 index 0000000000000000000000000000000000000000..8a4282ed77e52cec6f9b09f924137154982a1a3d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000887040_227082240.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c510dad379d984e2247893bd70cdcee2ee2c0194aebdfbe54986357b2bf720c +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000899904_230375424.pth b/checkpoint_p1/milestones/checkpoint_000899904_230375424.pth new file mode 100644 index 0000000000000000000000000000000000000000..566eb008af9633031d45b514a0e36f4ce901bdc0 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000899904_230375424.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed60d9ffbba7b7d5708910d514dc7d77df93c945f999c11e74574d41f0335885 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000912864_233693184.pth b/checkpoint_p1/milestones/checkpoint_000912864_233693184.pth new file mode 100644 index 0000000000000000000000000000000000000000..598de48d13421cbde11cfe91e1976383239059f4 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000912864_233693184.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a993567a8dab17a3dd02f8371c5a495c9123e66a00d3a8e80297c39a87fbd4ee +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000925792_237002752.pth b/checkpoint_p1/milestones/checkpoint_000925792_237002752.pth new file mode 100644 index 0000000000000000000000000000000000000000..9e98d5e435e3a2d1261ed0cfe6b36ad21ae76898 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000925792_237002752.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4c743d5ba2602fe64eb6ef74e4a8f37750c7bbdba946319406eeb61d6c3fa3d +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000938688_240304128.pth b/checkpoint_p1/milestones/checkpoint_000938688_240304128.pth new file mode 100644 index 0000000000000000000000000000000000000000..fefaacd913069d85622b2f76c33c70f87b3650f3 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000938688_240304128.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d578bcfad209b0a24be87a534226e7b3e1a878db73c05b63f51554822f204bc +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000951712_243638272.pth b/checkpoint_p1/milestones/checkpoint_000951712_243638272.pth new file mode 100644 index 0000000000000000000000000000000000000000..f03007b2569351fdb48600b1dd6dd521a79cf994 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000951712_243638272.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e9c1b8677c8bc113f82980ad89520fce30c4e9dc762a85b6372415076f0853e +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000964704_246964224.pth b/checkpoint_p1/milestones/checkpoint_000964704_246964224.pth new file mode 100644 index 0000000000000000000000000000000000000000..79a2e1e5bc57eb27864433c63bbde2fa82f760aa --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000964704_246964224.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52af1f6a6d260254c38cc100a80b50a69218cb14e7d934980dde00c93817ea83 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000977600_250265600.pth b/checkpoint_p1/milestones/checkpoint_000977600_250265600.pth new file mode 100644 index 0000000000000000000000000000000000000000..cf057ad3f21e4f509182ede5a9939f04b0fd0cc1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000977600_250265600.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db05b0d79a74cad0b1dd61befd0d448b29e50489c8284c49d86e96210c73ce95 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000990560_253583360.pth b/checkpoint_p1/milestones/checkpoint_000990560_253583360.pth new file mode 100644 index 0000000000000000000000000000000000000000..0c87d7e4c21834a183824bffe1f715bafdb5005a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000990560_253583360.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e6dbaf7510a4ddadaa8ac419ffb8d6b2c4a33a3ab47527043974c43dcddfbc0 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001003488_256892928.pth b/checkpoint_p1/milestones/checkpoint_001003488_256892928.pth new file mode 100644 index 0000000000000000000000000000000000000000..b46764f46c753ba71ec6bd639cb89ae97e07598d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001003488_256892928.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c00a5c6b917052209af54f5251f9f0a2767409b152d1443ad075ddea39caa5f +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001016448_260210688.pth b/checkpoint_p1/milestones/checkpoint_001016448_260210688.pth new file mode 100644 index 0000000000000000000000000000000000000000..0e9a6e5ff9ae138eb9770f3c5826283739b08bc3 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001016448_260210688.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f24afc68a682e660658609db49f7fd2871089bdbab06f8e30118ef2733a96b5 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001029280_263495680.pth b/checkpoint_p1/milestones/checkpoint_001029280_263495680.pth new file mode 100644 index 0000000000000000000000000000000000000000..f702450d5aba4d3855750b29e8a10fc4d1a75a8e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001029280_263495680.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e5bb55d973f9ee172347a9f48dca71d694bbbfae741fbf96532815e17905de8 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001042112_266780672.pth b/checkpoint_p1/milestones/checkpoint_001042112_266780672.pth new file mode 100644 index 0000000000000000000000000000000000000000..33b06bc2d55b9e4f24912c9dd573fddaccf90f6f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001042112_266780672.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4565f4bb9625ef0fbeda59c9b3131b90010fba7437f8f39e338f84409291e93b +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001054976_270073856.pth b/checkpoint_p1/milestones/checkpoint_001054976_270073856.pth new file mode 100644 index 0000000000000000000000000000000000000000..f89bf15b44c350beb469f56354531df62051acea --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001054976_270073856.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62d5b412cb9b83a42dcc7cae2df4277f69701073c08a4c217fdea30f5fc4f7be +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001067744_273342464.pth b/checkpoint_p1/milestones/checkpoint_001067744_273342464.pth new file mode 100644 index 0000000000000000000000000000000000000000..51bb80705e341375da39fd92a1b060e73bdc44d7 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001067744_273342464.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d702d42c06ce3bbef4c40c617659e5abdd216b767927b1be58ce2c348598463 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001080544_276619264.pth b/checkpoint_p1/milestones/checkpoint_001080544_276619264.pth new file mode 100644 index 0000000000000000000000000000000000000000..ed819d0e824863ff5a491d4a70ded525c9ac6f76 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001080544_276619264.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9baf520bb0c7252db6d8559bd3f0611220916bea8bcab228769644205569392 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001093408_279912448.pth b/checkpoint_p1/milestones/checkpoint_001093408_279912448.pth new file mode 100644 index 0000000000000000000000000000000000000000..485345814ecd3bc6cd3d3ede850a1b18ac518221 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001093408_279912448.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a6a5441bffc96b368d45e205ade03a340992535ea8e4312c1f117819f0fe11c +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001106272_283205632.pth b/checkpoint_p1/milestones/checkpoint_001106272_283205632.pth new file mode 100644 index 0000000000000000000000000000000000000000..b8d576ef1faa08a46645a6917be56c7d31b185f9 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001106272_283205632.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ab63ececd5cc4fa50276bba68464df90fba5535b0c3ed00417c66b3311d30d4 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001119168_286507008.pth b/checkpoint_p1/milestones/checkpoint_001119168_286507008.pth new file mode 100644 index 0000000000000000000000000000000000000000..228b6f068f00bb5e9dc89edf81980850fec01ada --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001119168_286507008.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e1e035c7935f4ea5a240591dd5acb501dd95e2e0233a96273924cd978fe5ca4 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001132064_289808384.pth b/checkpoint_p1/milestones/checkpoint_001132064_289808384.pth new file mode 100644 index 0000000000000000000000000000000000000000..6de8800643215334bb545b5e81a9b58643159285 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001132064_289808384.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c54ddcbfee01c6529952b15438d9097826795261e79498d05de200c3671f0cca +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001144928_293101568.pth b/checkpoint_p1/milestones/checkpoint_001144928_293101568.pth new file mode 100644 index 0000000000000000000000000000000000000000..d5872f4565a00343f795aa75a81d20a94c16db32 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001144928_293101568.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46f3211ed8aea8cb00947ef57e2cf2d3a0b4dfd47f5c92cb8a9c86188182246d +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001157728_296378368.pth b/checkpoint_p1/milestones/checkpoint_001157728_296378368.pth new file mode 100644 index 0000000000000000000000000000000000000000..ea1ae358861e92ca7c1dcaa1bc6726137c7337f5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001157728_296378368.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79f74cdcf92936ad2004fd45dc7aae3d954c63a16c4273974ec212a8996ac26c +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001170624_299679744.pth b/checkpoint_p1/milestones/checkpoint_001170624_299679744.pth new file mode 100644 index 0000000000000000000000000000000000000000..9e483dce10e38f21285a80fbb87340c26eeeb600 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001170624_299679744.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68ad321f679ff562ed4e73b0478441cb600e7298c763a99ea9934541df405046 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001183488_302972928.pth b/checkpoint_p1/milestones/checkpoint_001183488_302972928.pth new file mode 100644 index 0000000000000000000000000000000000000000..db006b93dbfce20125e5605f8b8ffb9f049fd0da --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001183488_302972928.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec03daa3076d2a2cc739f81ff8d7f57547ce706e8640f7e60e9002eb5191fdd2 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001196544_306315264.pth b/checkpoint_p1/milestones/checkpoint_001196544_306315264.pth new file mode 100644 index 0000000000000000000000000000000000000000..0ce5877911f381d702c2537c3e3e1f43af126a92 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001196544_306315264.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7aa3548aa148ff182db11dea7c147c4a5857c74c86e1acd162de6751607464c +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001209472_309624832.pth b/checkpoint_p1/milestones/checkpoint_001209472_309624832.pth new file mode 100644 index 0000000000000000000000000000000000000000..5be0eb5f40cdf98f0d8fa24b728b311e5774159c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001209472_309624832.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cabb4951b2221d6c8741da085a2675c70a55d6123f74c30cf1c68bf60a2c9442 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001222336_312918016.pth b/checkpoint_p1/milestones/checkpoint_001222336_312918016.pth new file mode 100644 index 0000000000000000000000000000000000000000..5169b3652f31f9ad5178a86ea8c9260c7d342fc1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001222336_312918016.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9df7da94a7909479eaeb9c7527655602ac467329b5ba98bb43f151a3f5d26634 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001235168_316203008.pth b/checkpoint_p1/milestones/checkpoint_001235168_316203008.pth new file mode 100644 index 0000000000000000000000000000000000000000..b85590ab84a6ed2934d88832cc6ccf59ae265e82 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001235168_316203008.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdf5e3f1e5e645b54daa2dfb2304405b465a9e3378172156008a33ab0cf1c033 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001248128_319520768.pth b/checkpoint_p1/milestones/checkpoint_001248128_319520768.pth new file mode 100644 index 0000000000000000000000000000000000000000..4a5e1071f5a4dbb367b944d5dac2a410440910a5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001248128_319520768.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42802fa60a0077cb3fb78722b403d169c43cd1a13ee579d0aa8b19e14d6f395b +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001261056_322830336.pth b/checkpoint_p1/milestones/checkpoint_001261056_322830336.pth new file mode 100644 index 0000000000000000000000000000000000000000..37e9c79ee035d953396d80d16285865a4c293b86 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001261056_322830336.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d802e3016716ced5485fdae9d8a4499ce9990bf4f8e9de0ca1dcfcaedda2d53 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001274016_326148096.pth b/checkpoint_p1/milestones/checkpoint_001274016_326148096.pth new file mode 100644 index 0000000000000000000000000000000000000000..bc568692a1776efcb35180eec95ed46e6ee34f7c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001274016_326148096.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d44c8fd1822fc7ef84c2523f475eea4e89fa1c66c19cd224ed30e10eb814890 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001287008_329474048.pth b/checkpoint_p1/milestones/checkpoint_001287008_329474048.pth new file mode 100644 index 0000000000000000000000000000000000000000..e772ff0f9625270155ce75729d6c2f22f3496e7e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001287008_329474048.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fad2030f0ea83d6b1bde2462beed3042e436e6ab8b30915f96019a519fbb5aca +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001299936_332783616.pth b/checkpoint_p1/milestones/checkpoint_001299936_332783616.pth new file mode 100644 index 0000000000000000000000000000000000000000..152542e674f4c478c13dad1ad546394407568519 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001299936_332783616.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e5fd59a5d4bb4d381443c67a1a24262e8924c70b963ed032ab1f8ff5602eb0a +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001312896_336101376.pth b/checkpoint_p1/milestones/checkpoint_001312896_336101376.pth new file mode 100644 index 0000000000000000000000000000000000000000..2c3bfa281b80240f98bc7fcf498345a9c2ff6a0c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001312896_336101376.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48cf17608d4636ebdf78f3965dad9e73875795d37af4152d3153fbc1c8fd8cbb +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001325824_339410944.pth b/checkpoint_p1/milestones/checkpoint_001325824_339410944.pth new file mode 100644 index 0000000000000000000000000000000000000000..bb6607a574aac6c7caae7f89161f44e5698bc855 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001325824_339410944.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8ce38786c595ac63e46e9b2835b90c4ce8c519d230073071855ab80bd867a8f +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001338720_342712320.pth b/checkpoint_p1/milestones/checkpoint_001338720_342712320.pth new file mode 100644 index 0000000000000000000000000000000000000000..c4e38cbc8b754a54e4f4d6f352531b51d4d45d96 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001338720_342712320.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5afd2d18177c70cab0f7f676d3c58d10caf13a9d45d72602172f2ce72772a668 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001351648_346021888.pth b/checkpoint_p1/milestones/checkpoint_001351648_346021888.pth new file mode 100644 index 0000000000000000000000000000000000000000..c8b1483e757e71465019f9a63b3570e0acf0237a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001351648_346021888.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70785a8946467c9d89f4bfdd64e7bbe8e972c2ae04c3fe4b9c81fb72e96e83e0 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001364576_349331456.pth b/checkpoint_p1/milestones/checkpoint_001364576_349331456.pth new file mode 100644 index 0000000000000000000000000000000000000000..9554d45150d17754d09aa5a4da76edf37306918f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001364576_349331456.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a552204ee45cfa1c297c89b5e275787ca79f58ed5c4e315be63ad9e886d06e9 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001377504_352641024.pth b/checkpoint_p1/milestones/checkpoint_001377504_352641024.pth new file mode 100644 index 0000000000000000000000000000000000000000..ec3e7751b4d6b4df319ad5e0265ff9d3ab397fa3 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001377504_352641024.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55d71014e1971466be153a3c2369ff3884f6831b5606f66df3d2a977145c7a6a +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001390400_355942400.pth b/checkpoint_p1/milestones/checkpoint_001390400_355942400.pth new file mode 100644 index 0000000000000000000000000000000000000000..d97473478cdebb545fe31b15445b7a30cf14d9b0 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001390400_355942400.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f78bcd61bc0472ee195a5cfaa8cc7447ee4066a1aafbe8bd4a27d0ec2d3f549d +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001403360_359260160.pth b/checkpoint_p1/milestones/checkpoint_001403360_359260160.pth new file mode 100644 index 0000000000000000000000000000000000000000..ae79fcfc9abada33334cb2493015b7d3f5a13aee --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001403360_359260160.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:008749dbcae125c28c25228e3b76703dda0978d988ba7d388a7d7b81f148785e +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001416288_362569728.pth b/checkpoint_p1/milestones/checkpoint_001416288_362569728.pth new file mode 100644 index 0000000000000000000000000000000000000000..85a0aada273fe6cf1a7f06bffa294b199f07381a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001416288_362569728.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c7b13873697917f69335ee9a76378accd123d626f16567a127c05cd3ac7b205 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001429280_365895680.pth b/checkpoint_p1/milestones/checkpoint_001429280_365895680.pth new file mode 100644 index 0000000000000000000000000000000000000000..ce3c9a7f4b96af2a784e97f1ae8d070d0d64db85 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001429280_365895680.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:312551a12698d0d6c7c12a7949e1d6c0227b2a6725aa0d112ea1a1862e5896cf +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001442208_369205248.pth b/checkpoint_p1/milestones/checkpoint_001442208_369205248.pth new file mode 100644 index 0000000000000000000000000000000000000000..8a1243341580163f31ea1673777304eb5fd28438 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001442208_369205248.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0648e0cac2c6c774e29c86695969f90d7d71af7e52621630db47d190a3b8ed14 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001455040_372490240.pth b/checkpoint_p1/milestones/checkpoint_001455040_372490240.pth new file mode 100644 index 0000000000000000000000000000000000000000..0d8b678192f31618f2bdf8840121b47022746df1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001455040_372490240.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2a8b5a7b47c2ad1a04233a0d9f494aabaed78258d6c50e41ecb103cb6bb58e2 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001467968_375799808.pth b/checkpoint_p1/milestones/checkpoint_001467968_375799808.pth new file mode 100644 index 0000000000000000000000000000000000000000..1d7e985f0b2ae9f8e79a3226a39da0308df7f997 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001467968_375799808.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3439a77d26294742ec78c77669cc55f60cabdedc0c736c5dbfcb78fe1aebb3f +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001480928_379117568.pth b/checkpoint_p1/milestones/checkpoint_001480928_379117568.pth new file mode 100644 index 0000000000000000000000000000000000000000..e1378459d96773ea2b49c887343549fd39d2f6fb --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001480928_379117568.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38d6081ff82021ca21e95642b033206ab2c0ddffd0ab2402fa70891bf07f51e8 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001493856_382427136.pth b/checkpoint_p1/milestones/checkpoint_001493856_382427136.pth new file mode 100644 index 0000000000000000000000000000000000000000..452b18e0409b0e49885cf00c25c0ea00f499de5f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001493856_382427136.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f8466563e4a85c4e0c1ea279cba8ccb79ea8d66b19abc2c131233f94f641444 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001506784_385736704.pth b/checkpoint_p1/milestones/checkpoint_001506784_385736704.pth new file mode 100644 index 0000000000000000000000000000000000000000..06ad95315622e40d8c0357a4efccf6d24b003561 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001506784_385736704.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c3e97b389099a4a681a2a7c593ba0ffa6f8e507886e5a06c8bbd80e0b25d421 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001519744_389054464.pth b/checkpoint_p1/milestones/checkpoint_001519744_389054464.pth new file mode 100644 index 0000000000000000000000000000000000000000..038da804f8a67e51a6d393f1b652bcc5b9134e9a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001519744_389054464.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f855930e02b4ccf2f28845f831e248fce18f7e68bd85ebc8ef5681d6a6db4da +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001532672_392364032.pth b/checkpoint_p1/milestones/checkpoint_001532672_392364032.pth new file mode 100644 index 0000000000000000000000000000000000000000..3993bc43440cab3d7d801944416929c0473e8374 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001532672_392364032.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0843ca01e026560927818e86251851e4621fbd6a610709c10bf77351f60fb733 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001545568_395665408.pth b/checkpoint_p1/milestones/checkpoint_001545568_395665408.pth new file mode 100644 index 0000000000000000000000000000000000000000..17225655168fa723c1391080628bf428d6262de6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001545568_395665408.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:528b5592433aaa8a20f73cfdd355df2922d76eeb3222ad36dd01296b2d375d54 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001558496_398974976.pth b/checkpoint_p1/milestones/checkpoint_001558496_398974976.pth new file mode 100644 index 0000000000000000000000000000000000000000..452f0e4d2ca94f03f9d01d927fa50a98aecfaf33 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001558496_398974976.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78062bf16d2b823047163527244ca8806121e31b766d2ab9c3dec9e6c1067266 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001571424_402284544.pth b/checkpoint_p1/milestones/checkpoint_001571424_402284544.pth new file mode 100644 index 0000000000000000000000000000000000000000..c0d93b266dd52d26b5ca09a3b963f3189aa5144f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001571424_402284544.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9469c127e8b54bed3ba78237f977b591685f65376d6ce81b072319271774219 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001584352_405594112.pth b/checkpoint_p1/milestones/checkpoint_001584352_405594112.pth new file mode 100644 index 0000000000000000000000000000000000000000..49d65dfec79667eb9d67e7d4c141e09ec86173dc --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001584352_405594112.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5af37adc59a206e1373ceafcbb89b5fe3fa072b6c6c21f79207447987e275d81 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001597312_408911872.pth b/checkpoint_p1/milestones/checkpoint_001597312_408911872.pth new file mode 100644 index 0000000000000000000000000000000000000000..5553453a5b62be3fe1bbbb87e61ff7a0e169851d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001597312_408911872.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bc5a86fec526692a1313a1059e5c24cec4634f9fd1c19aadf4dad65c5d1cccd +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001610208_412213248.pth b/checkpoint_p1/milestones/checkpoint_001610208_412213248.pth new file mode 100644 index 0000000000000000000000000000000000000000..2366f37e7c77ec2addf17c0989febdd95a30ea44 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001610208_412213248.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28caddd3d0bca1f38dc3d07ad5e2c6bdc1e8732986409e459f2fea3b382db1ff +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001623136_415522816.pth b/checkpoint_p1/milestones/checkpoint_001623136_415522816.pth new file mode 100644 index 0000000000000000000000000000000000000000..df2665578b204d617bdc1241eb2d4dd0bae382a4 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001623136_415522816.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6426bcea631bc2210153df8bef6391b74d471a033c4f19a56e1940cc366c7d69 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001636096_418840576.pth b/checkpoint_p1/milestones/checkpoint_001636096_418840576.pth new file mode 100644 index 0000000000000000000000000000000000000000..77c594a7a69aaffd21cdf0127914fa60b4ba15d5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001636096_418840576.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64019bd467293b98551f7364ad9ba018fcb2d0d0726d3a6992107c65504443b3 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001649024_422150144.pth b/checkpoint_p1/milestones/checkpoint_001649024_422150144.pth new file mode 100644 index 0000000000000000000000000000000000000000..80023b2cb745b231f15144c6bbde4fe79496d2ec --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001649024_422150144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32a518dd37681c65861069bf7612d70a2311866784a77c2f56352fd1611bac82 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001661952_425459712.pth b/checkpoint_p1/milestones/checkpoint_001661952_425459712.pth new file mode 100644 index 0000000000000000000000000000000000000000..5c00a95f652e5671ad9c0f3590024288af5ddd4d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001661952_425459712.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68eb861242144b8d55c6d5d7748bce7624e0f88a698a5c4a24d48c3013d8c705 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001674912_428777472.pth b/checkpoint_p1/milestones/checkpoint_001674912_428777472.pth new file mode 100644 index 0000000000000000000000000000000000000000..d30caf38946a198f62259fe1c695abef4e8dcd5f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001674912_428777472.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e2e338a4b73be2ea961caf1f908e337f2fe65458c69e6428423220a9e73a65a +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001687776_432070656.pth b/checkpoint_p1/milestones/checkpoint_001687776_432070656.pth new file mode 100644 index 0000000000000000000000000000000000000000..e149c4ccf300124f22030cb31f16db51e1b0783a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001687776_432070656.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff5881df8e3e1343418992fc858e5cb3edfd521558db0daa17de0ce55867e842 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001700704_435380224.pth b/checkpoint_p1/milestones/checkpoint_001700704_435380224.pth new file mode 100644 index 0000000000000000000000000000000000000000..efbd0df30f477dee79a5dea102b061b3d5fa195f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001700704_435380224.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c5fe12a34bbe5e0088a6c5229183e6d7623f5337eec6f3f75f96ff263e1019b +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001713632_438689792.pth b/checkpoint_p1/milestones/checkpoint_001713632_438689792.pth new file mode 100644 index 0000000000000000000000000000000000000000..2b1d4e24dd3ebc2899c72b6bb5295aca5286d403 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001713632_438689792.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1451e4a09af8b46ea9e049362d57fdc2ed97442a731f855f6624c347e4c08d71 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001726560_441999360.pth b/checkpoint_p1/milestones/checkpoint_001726560_441999360.pth new file mode 100644 index 0000000000000000000000000000000000000000..ee20d4df241cbc49a4fc0708cc87e7eb2849fcb1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001726560_441999360.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c6cc052d3a18dcbad31b10891cb423e702b935488773f424fa57fc7b5183bcb +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001739552_445325312.pth b/checkpoint_p1/milestones/checkpoint_001739552_445325312.pth new file mode 100644 index 0000000000000000000000000000000000000000..dd513e60eb45b4b2ac7eeb0f983433c2885fa813 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001739552_445325312.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42f93e8022b3ee582c032811c2fa2281d4ca502db812b74b80453059494ac80a +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001752512_448643072.pth b/checkpoint_p1/milestones/checkpoint_001752512_448643072.pth new file mode 100644 index 0000000000000000000000000000000000000000..c2950b7054dec7c56f6c65896d7bd03c9f5da647 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001752512_448643072.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13f911c628f4afcd1c7ee05a3454745032d992a2240a0719ae2a05811eb80a37 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001765376_451936256.pth b/checkpoint_p1/milestones/checkpoint_001765376_451936256.pth new file mode 100644 index 0000000000000000000000000000000000000000..b839389d00017456c788de91c0dba7e5a11be997 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001765376_451936256.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef20f788dad231e3d51a63b0a8502bd48fe728b1cfd37505cb7f001231b9b1b5 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001778336_455254016.pth b/checkpoint_p1/milestones/checkpoint_001778336_455254016.pth new file mode 100644 index 0000000000000000000000000000000000000000..c3feab800893636f15b9145cae4bbc82d0f954da --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001778336_455254016.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c9ed89d6754a3a8c76bc6dc1e68ce61b5b9275591fb71e071daa764674cadcb +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001791296_458571776.pth b/checkpoint_p1/milestones/checkpoint_001791296_458571776.pth new file mode 100644 index 0000000000000000000000000000000000000000..309c86c3e6f4cef9e50a48c0d343231c24d461d3 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001791296_458571776.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a76b764bcf7d8d6bb94e0836c0960b0deb33d7dd1b701a6f1bf1a1fbbffa05c +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001804224_461881344.pth b/checkpoint_p1/milestones/checkpoint_001804224_461881344.pth new file mode 100644 index 0000000000000000000000000000000000000000..bf8d90794bcdf74800cf5bf549b3c9ae81cdfe5f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001804224_461881344.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13aa98092e03241906a6e88fdbcbdbee5272900c1859e83480a97831dd3161c6 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001817184_465199104.pth b/checkpoint_p1/milestones/checkpoint_001817184_465199104.pth new file mode 100644 index 0000000000000000000000000000000000000000..7a6cd37bcc26b318637b5a6750c532b7a8c3e85b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001817184_465199104.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5810239d297c38ed356043dfc4ca889e87202032697b9dc2a52e3f6be78b6c5 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001830208_468533248.pth b/checkpoint_p1/milestones/checkpoint_001830208_468533248.pth new file mode 100644 index 0000000000000000000000000000000000000000..134985f5cd417245bea55f01a840ea32b500999f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001830208_468533248.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4451d39d83494346ff272864e02884a67430922d0d0e3fc4d9b19d618090053b +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001843104_471834624.pth b/checkpoint_p1/milestones/checkpoint_001843104_471834624.pth new file mode 100644 index 0000000000000000000000000000000000000000..8c4f6b017fa87829471d61cd3c851a23ac744275 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001843104_471834624.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc8a84b4f2f4166ad49a9ce2e843036ebf91db144e01f6c22e82355021b3bf5f +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001856064_475152384.pth b/checkpoint_p1/milestones/checkpoint_001856064_475152384.pth new file mode 100644 index 0000000000000000000000000000000000000000..f94fc6cfa037995c7438b1b67854ae331031c1ad --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001856064_475152384.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe4440acfdd3575b93db6f2bf276616be9c484b88d561d1754372319be0cf30b +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001868896_478437376.pth b/checkpoint_p1/milestones/checkpoint_001868896_478437376.pth new file mode 100644 index 0000000000000000000000000000000000000000..97519f7ccac98b12b5c90c1a7d93e63fc5c17d10 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001868896_478437376.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:823368c8831c6695c64dded524855148c77650a6cda2f5ff4f3154d0438b7b1e +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001881792_481738752.pth b/checkpoint_p1/milestones/checkpoint_001881792_481738752.pth new file mode 100644 index 0000000000000000000000000000000000000000..a099682a828765059c12c87c73d176a38eaf4796 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001881792_481738752.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bc86ab3631d7f0f77c3e8e95173189b5f25dd66dbe635b578adf1d684790cd7 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001894752_485056512.pth b/checkpoint_p1/milestones/checkpoint_001894752_485056512.pth new file mode 100644 index 0000000000000000000000000000000000000000..ab9ff6e2f6bae01d0640abf8da7c5888cb0ea1d6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001894752_485056512.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80b1ce4a30b577c5a6f3782b1f68d28c2fddc3a45a7f97b1c3d6a138e82e0fb6 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001907584_488341504.pth b/checkpoint_p1/milestones/checkpoint_001907584_488341504.pth new file mode 100644 index 0000000000000000000000000000000000000000..42a45a7dec10bd98dfd5b376a860119855fb2532 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001907584_488341504.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cd9393e34357582aaa59c0fe775f7bcd53205b0282a4aac7d2c96ea3794f38c +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001920576_491667456.pth b/checkpoint_p1/milestones/checkpoint_001920576_491667456.pth new file mode 100644 index 0000000000000000000000000000000000000000..3ca9070850c132aa88df71e070c338e571e77513 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001920576_491667456.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3959704a62f110dab9e8034aebaf3de76a9dc40eca7dd9d5672f04bd7a553801 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001933408_494952448.pth b/checkpoint_p1/milestones/checkpoint_001933408_494952448.pth new file mode 100644 index 0000000000000000000000000000000000000000..954d545bce650733752e2eb966f0188f6325cb7b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001933408_494952448.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fc02cb2d2f4c0d6e64b319912d22f91cea4e6ad1ac8b3534bb9aeb77fed88f9 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001946304_498253824.pth b/checkpoint_p1/milestones/checkpoint_001946304_498253824.pth new file mode 100644 index 0000000000000000000000000000000000000000..e97418ec3b9a6444abb330cf5930148eb02f82bb --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001946304_498253824.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a847dcf71fccb8c9ffd9e0378a7af1247111a7ae5157a3a43ff8c03e7cf401bd +size 20797067 diff --git a/config.json b/config.json index 9002be1dc1a9982563bd20118f67d8b6c2762763..f7c55433d844f4c39d9280bd9967a84743f33f52 100644 --- a/config.json +++ b/config.json @@ -4,7 +4,7 @@ "env": "atari_doubledunk", "experiment": "atari_doubledunk_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_doubledunk --experiment=atari_doubledunk_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_doubledunk --wandb_job_type=SF --wandb_tags=atari", + "command_line": "--algo=APPO --env=atari_doubledunk --experiment=atari_doubledunk_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_doubledunk --wandb_job_type=SF --wandb_tags=atari", "cli_args": { "algo": "APPO", "env": "atari_doubledunk", "experiment": "atari_doubledunk_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_doubledunk_APPO_20231010_204032_825502" + "wandb_unique_id": "atari_doubledunk_APPO_20231101_073439_380248" } \ 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 4d5ea5b1409f573b73634dd560dbd589c5322381..21ff02c46dbbdfd848f9ec920711ed8609188ecd 100644 --- a/replay.mp4 +++ b/replay.mp4 @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:0697101f1bc4bc04deebdd816982f2228200a555e0b8a8f7a75ac7bb4dd1bb6f -size 13202730 +oid sha256:5bf05e725a6612959647d54bdc81751484e05b01cf03049ca02876274818311e +size 13243085 diff --git a/sf_log.txt b/sf_log.txt index a17609aa0f3a01ac0645eec098cdd0977a1ecb26..e74dc95891c2f282a020029a8295146c235bca5a 100644 --- a/sf_log.txt +++ b/sf_log.txt @@ -1,26861 +1,3 @@ -[2023-10-10 20:40:39,433][97672] Saving configuration to ./train_atari/atari_doubledunk_APPO/config.json... -[2023-10-10 20:40:39,750][97672] Rollout worker 0 uses device cpu -[2023-10-10 20:40:39,751][97672] Rollout worker 1 uses device cpu -[2023-10-10 20:40:39,751][97672] Rollout worker 2 uses device cpu -[2023-10-10 20:40:39,752][97672] Rollout worker 3 uses device cpu -[2023-10-10 20:40:39,752][97672] Rollout worker 4 uses device cpu -[2023-10-10 20:40:39,753][97672] Rollout worker 5 uses device cpu -[2023-10-10 20:40:39,754][97672] Rollout worker 6 uses device cpu -[2023-10-10 20:40:39,754][97672] Rollout worker 7 uses device cpu -[2023-10-10 20:40:39,755][97672] Rollout worker 8 uses device cpu -[2023-10-10 20:40:39,755][97672] Rollout worker 9 uses device cpu -[2023-10-10 20:40:39,756][97672] Rollout worker 10 uses device cpu -[2023-10-10 20:40:39,756][97672] Rollout worker 11 uses device cpu -[2023-10-10 20:40:39,757][97672] Rollout worker 12 uses device cpu -[2023-10-10 20:40:39,757][97672] Rollout worker 13 uses device cpu -[2023-10-10 20:40:39,757][97672] Rollout worker 14 uses device cpu -[2023-10-10 20:40:39,757][97672] Rollout worker 15 uses device cpu -[2023-10-10 20:40:40,047][97672] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-10 20:40:40,048][97672] InferenceWorker_p0-w0: min num requests: 2 -[2023-10-10 20:40:40,051][97672] Using GPUs [1] for process 1 (actually maps to GPUs [1]) -[2023-10-10 20:40:40,051][97672] InferenceWorker_p1-w0: min num requests: 2 -[2023-10-10 20:40:40,097][97672] Starting all processes... -[2023-10-10 20:40:40,097][97672] Starting process learner_proc0 -[2023-10-10 20:40:41,752][97672] Starting process learner_proc1 -[2023-10-10 20:40:41,755][98385] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-10 20:40:41,756][98385] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 -[2023-10-10 20:40:41,774][98385] Num visible devices: 1 -[2023-10-10 20:40:41,791][98385] Setting fixed seed 1234 -[2023-10-10 20:40:41,792][98385] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-10 20:40:41,792][98385] Initializing actor-critic model on device cuda:0 -[2023-10-10 20:40:41,792][98385] RunningMeanStd input shape: (4, 84, 84) -[2023-10-10 20:40:41,793][98385] RunningMeanStd input shape: (1,) -[2023-10-10 20:40:41,804][98385] ConvEncoder: input_channels=4 -[2023-10-10 20:40:41,981][98385] Conv encoder output size: 512 -[2023-10-10 20:40:41,983][98385] Created Actor Critic model with architecture: -[2023-10-10 20:40:41,984][98385] ActorCriticSharedWeights( - (obs_normalizer): ObservationNormalizer( - (running_mean_std): RunningMeanStdDictInPlace( - (running_mean_std): ModuleDict( - (obs): RunningMeanStdInPlace() - ) - ) - ) - (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) - (encoder): MultiInputEncoder( - (encoders): ModuleDict( - (obs): ConvEncoder( - (enc): RecursiveScriptModule( - original_name=ConvEncoderImpl - (conv_head): RecursiveScriptModule( - original_name=Sequential - (0): RecursiveScriptModule(original_name=Conv2d) - (1): RecursiveScriptModule(original_name=ReLU) - (2): RecursiveScriptModule(original_name=Conv2d) - (3): RecursiveScriptModule(original_name=ReLU) - (4): RecursiveScriptModule(original_name=Conv2d) - (5): RecursiveScriptModule(original_name=ReLU) - ) - (mlp_layers): RecursiveScriptModule( - original_name=Sequential - (0): RecursiveScriptModule(original_name=Linear) - (1): RecursiveScriptModule(original_name=ReLU) - ) - ) - ) - ) - ) - (core): ModelCoreIdentity() - (decoder): MlpDecoder( - (mlp): Identity() - ) - (critic_linear): Linear(in_features=512, out_features=1, bias=True) - (action_parameterization): ActionParameterizationDefault( - (distribution_linear): Linear(in_features=512, out_features=18, bias=True) - ) -) -[2023-10-10 20:40:42,556][98385] Using optimizer -[2023-10-10 20:40:42,557][98385] No checkpoints found -[2023-10-10 20:40:42,557][98385] Did not load from checkpoint, starting from scratch! -[2023-10-10 20:40:42,557][98385] Initialized policy 0 weights for model version 0 -[2023-10-10 20:40:42,558][98385] LearnerWorker_p0 finished initialization! -[2023-10-10 20:40:42,559][98385] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-10 20:40:43,450][97672] Starting all processes... -[2023-10-10 20:40:43,453][98439] Using GPUs [1] for process 1 (actually maps to GPUs [1]) -[2023-10-10 20:40:43,454][98439] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [1]) for learning process 1 -[2023-10-10 20:40:43,459][97672] Starting process inference_proc0-0 -[2023-10-10 20:40:43,459][97672] Starting process inference_proc1-0 -[2023-10-10 20:40:43,459][97672] Starting process rollout_proc0 -[2023-10-10 20:40:43,472][98439] Num visible devices: 1 -[2023-10-10 20:40:43,459][97672] Starting process rollout_proc1 -[2023-10-10 20:40:43,489][98439] Setting fixed seed 1234 -[2023-10-10 20:40:43,460][97672] Starting process rollout_proc2 -[2023-10-10 20:40:43,490][98439] Using GPUs [0] for process 1 (actually maps to GPUs [1]) -[2023-10-10 20:40:43,490][98439] Initializing actor-critic model on device cuda:0 -[2023-10-10 20:40:43,491][98439] RunningMeanStd input shape: (4, 84, 84) -[2023-10-10 20:40:43,460][97672] Starting process rollout_proc3 -[2023-10-10 20:40:43,491][98439] RunningMeanStd input shape: (1,) -[2023-10-10 20:40:43,465][97672] Starting process rollout_proc4 -[2023-10-10 20:40:43,465][97672] Starting process rollout_proc5 -[2023-10-10 20:40:43,467][97672] Starting process rollout_proc6 -[2023-10-10 20:40:43,471][97672] Starting process rollout_proc7 -[2023-10-10 20:40:43,472][97672] Starting process rollout_proc8 -[2023-10-10 20:40:43,503][98439] ConvEncoder: input_channels=4 -[2023-10-10 20:40:43,475][97672] Starting process rollout_proc9 -[2023-10-10 20:40:43,476][97672] Starting process rollout_proc10 -[2023-10-10 20:40:43,476][97672] Starting process rollout_proc11 -[2023-10-10 20:40:43,477][97672] Starting process rollout_proc12 -[2023-10-10 20:40:43,478][97672] Starting process rollout_proc13 -[2023-10-10 20:40:43,917][98439] Conv encoder output size: 512 -[2023-10-10 20:40:43,920][98439] Created Actor Critic model with architecture: -[2023-10-10 20:40:43,921][98439] ActorCriticSharedWeights( - (obs_normalizer): ObservationNormalizer( - (running_mean_std): RunningMeanStdDictInPlace( - (running_mean_std): ModuleDict( - (obs): RunningMeanStdInPlace() - ) - ) - ) - (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) - (encoder): MultiInputEncoder( - (encoders): ModuleDict( - (obs): ConvEncoder( - (enc): RecursiveScriptModule( - original_name=ConvEncoderImpl - (conv_head): RecursiveScriptModule( - original_name=Sequential - (0): RecursiveScriptModule(original_name=Conv2d) - (1): RecursiveScriptModule(original_name=ReLU) - (2): RecursiveScriptModule(original_name=Conv2d) - (3): RecursiveScriptModule(original_name=ReLU) - (4): RecursiveScriptModule(original_name=Conv2d) - (5): RecursiveScriptModule(original_name=ReLU) - ) - (mlp_layers): RecursiveScriptModule( - original_name=Sequential - (0): RecursiveScriptModule(original_name=Linear) - (1): RecursiveScriptModule(original_name=ReLU) - ) - ) - ) - ) - ) - (core): ModelCoreIdentity() - (decoder): MlpDecoder( - (mlp): Identity() - ) - (critic_linear): Linear(in_features=512, out_features=1, bias=True) - (action_parameterization): ActionParameterizationDefault( - (distribution_linear): Linear(in_features=512, out_features=18, bias=True) - ) -) -[2023-10-10 20:40:44,752][98439] Using optimizer -[2023-10-10 20:40:44,752][98439] No checkpoints found -[2023-10-10 20:40:44,753][98439] Did not load from checkpoint, starting from scratch! -[2023-10-10 20:40:44,753][98439] Initialized policy 1 weights for model version 0 -[2023-10-10 20:40:44,755][98439] LearnerWorker_p1 finished initialization! -[2023-10-10 20:40:44,755][98439] Using GPUs [0] for process 1 (actually maps to GPUs [1]) -[2023-10-10 20:40:45,649][97672] Starting process rollout_proc14 -[2023-10-10 20:40:45,655][98602] Worker 9 uses CPU cores [18, 19] -[2023-10-10 20:40:45,660][97672] Starting process rollout_proc15 -[2023-10-10 20:40:45,665][98599] Worker 5 uses CPU cores [10, 11] -[2023-10-10 20:40:45,666][98560] Using GPUs [1] for process 1 (actually maps to GPUs [1]) -[2023-10-10 20:40:45,666][98560] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [1]) for inference process 1 -[2023-10-10 20:40:45,684][98560] Num visible devices: 1 -[2023-10-10 20:40:45,976][98598] Worker 4 uses CPU cores [8, 9] -[2023-10-10 20:40:46,090][98607] Worker 13 uses CPU cores [26, 27] -[2023-10-10 20:40:46,189][98600] Worker 6 uses CPU cores [12, 13] -[2023-10-10 20:40:46,202][98597] Worker 3 uses CPU cores [6, 7] -[2023-10-10 20:40:46,216][98592] Worker 0 uses CPU cores [0, 1] -[2023-10-10 20:40:46,226][98603] Worker 8 uses CPU cores [16, 17] -[2023-10-10 20:40:46,234][98595] Worker 2 uses CPU cores [4, 5] -[2023-10-10 20:40:46,331][98606] Worker 12 uses CPU cores [24, 25] -[2023-10-10 20:40:46,375][98604] Worker 10 uses CPU cores [20, 21] -[2023-10-10 20:40:46,378][98596] Worker 1 uses CPU cores [2, 3] -[2023-10-10 20:40:46,406][98601] Worker 7 uses CPU cores [14, 15] -[2023-10-10 20:40:46,499][98560] RunningMeanStd input shape: (4, 84, 84) -[2023-10-10 20:40:46,499][98560] RunningMeanStd input shape: (1,) -[2023-10-10 20:40:46,514][98560] ConvEncoder: input_channels=4 -[2023-10-10 20:40:46,519][98559] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-10 20:40:46,519][98559] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 -[2023-10-10 20:40:46,539][98559] Num visible devices: 1 -[2023-10-10 20:40:46,578][98605] Worker 11 uses CPU cores [22, 23] -[2023-10-10 20:40:46,624][98560] Conv encoder output size: 512 -[2023-10-10 20:40:47,168][98559] RunningMeanStd input shape: (4, 84, 84) -[2023-10-10 20:40:47,169][98559] RunningMeanStd input shape: (1,) -[2023-10-10 20:40:47,180][98559] ConvEncoder: input_channels=4 -[2023-10-10 20:40:47,280][98559] Conv encoder output size: 512 -[2023-10-10 20:40:47,551][99352] Worker 15 uses CPU cores [30, 31] -[2023-10-10 20:40:47,593][97672] Inference worker 1-0 is ready! -[2023-10-10 20:40:47,595][99320] Worker 14 uses CPU cores [28, 29] -[2023-10-10 20:40:47,595][97672] Inference worker 0-0 is ready! -[2023-10-10 20:40:47,596][97672] All inference workers are ready! Signal rollout workers to start! -[2023-10-10 20:40:47,597][98601] EnvRunner 7-0 uses policy 1 -[2023-10-10 20:40:47,597][98600] EnvRunner 6-0 uses policy 0 -[2023-10-10 20:40:47,597][98604] EnvRunner 10-0 uses policy 0 -[2023-10-10 20:40:47,597][98598] EnvRunner 4-0 uses policy 0 -[2023-10-10 20:40:47,597][98599] EnvRunner 5-0 uses policy 1 -[2023-10-10 20:40:47,597][98595] EnvRunner 2-0 uses policy 0 -[2023-10-10 20:40:47,597][98597] EnvRunner 3-0 uses policy 1 -[2023-10-10 20:40:47,598][98596] EnvRunner 1-0 uses policy 1 -[2023-10-10 20:40:47,597][98607] EnvRunner 13-0 uses policy 1 -[2023-10-10 20:40:47,598][98602] EnvRunner 9-0 uses policy 1 -[2023-10-10 20:40:47,598][98603] EnvRunner 8-0 uses policy 0 -[2023-10-10 20:40:47,598][98606] EnvRunner 12-0 uses policy 0 -[2023-10-10 20:40:47,598][98592] EnvRunner 0-0 uses policy 0 -[2023-10-10 20:40:47,598][98605] EnvRunner 11-0 uses policy 1 -[2023-10-10 20:40:47,598][97672] 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) -[2023-10-10 20:40:47,711][99320] EnvRunner 14-0 uses policy 0 -[2023-10-10 20:40:47,759][99352] EnvRunner 15-0 uses policy 1 -[2023-10-10 20:40:50,035][97672] Heartbeat connected on Batcher_0 -[2023-10-10 20:40:50,038][97672] Heartbeat connected on LearnerWorker_p0 -[2023-10-10 20:40:50,041][97672] Heartbeat connected on Batcher_1 -[2023-10-10 20:40:50,044][97672] Heartbeat connected on LearnerWorker_p1 -[2023-10-10 20:40:50,051][97672] Heartbeat connected on InferenceWorker_p0-w0 -[2023-10-10 20:40:50,057][97672] Heartbeat connected on InferenceWorker_p1-w0 -[2023-10-10 20:40:50,058][97672] Heartbeat connected on RolloutWorker_w0 -[2023-10-10 20:40:50,059][97672] Heartbeat connected on RolloutWorker_w1 -[2023-10-10 20:40:50,063][97672] Heartbeat connected on RolloutWorker_w2 -[2023-10-10 20:40:50,063][97672] Heartbeat connected on RolloutWorker_w3 -[2023-10-10 20:40:50,066][97672] Heartbeat connected on RolloutWorker_w4 -[2023-10-10 20:40:50,071][97672] Heartbeat connected on RolloutWorker_w6 -[2023-10-10 20:40:50,076][97672] Heartbeat connected on RolloutWorker_w5 -[2023-10-10 20:40:50,078][97672] Heartbeat connected on RolloutWorker_w7 -[2023-10-10 20:40:50,079][97672] Heartbeat connected on RolloutWorker_w9 -[2023-10-10 20:40:50,080][97672] Heartbeat connected on RolloutWorker_w8 -[2023-10-10 20:40:50,084][97672] Heartbeat connected on RolloutWorker_w10 -[2023-10-10 20:40:50,084][97672] Heartbeat connected on RolloutWorker_w11 -[2023-10-10 20:40:50,088][97672] Heartbeat connected on RolloutWorker_w12 -[2023-10-10 20:40:50,092][97672] Heartbeat connected on RolloutWorker_w14 -[2023-10-10 20:40:50,095][97672] Heartbeat connected on RolloutWorker_w15 -[2023-10-10 20:40:50,096][97672] Heartbeat connected on RolloutWorker_w13 -[2023-10-10 20:40:50,556][97672] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 831.5, 1: 336.7. Samples: 3456. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-10-10 20:40:55,556][97672] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 1062.8, 1: 876.1. Samples: 15430. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-10-10 20:40:57,513][98559] Updated weights for policy 0, policy_version 10 (0.0009) -[2023-10-10 20:40:57,708][98560] Updated weights for policy 1, policy_version 10 (0.0008) -[2023-10-10 20:40:57,878][98559] Updated weights for policy 0, policy_version 20 (0.0009) -[2023-10-10 20:40:58,077][98560] Updated weights for policy 1, policy_version 20 (0.0008) -[2023-10-10 20:40:58,248][98559] Updated weights for policy 0, policy_version 30 (0.0009) -[2023-10-10 20:40:58,435][98560] Updated weights for policy 1, policy_version 30 (0.0007) -[2023-10-10 20:41:00,556][97672] Fps is (10 sec: 6553.6, 60 sec: 5057.5, 300 sec: 5057.5). Total num frames: 65536. Throughput: 0: 1294.6, 1: 1173.8. Samples: 31986. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-10 20:41:00,836][98559] Updated weights for policy 0, policy_version 40 (0.0009) -[2023-10-10 20:41:00,928][98560] Updated weights for policy 1, policy_version 40 (0.0008) -[2023-10-10 20:41:01,201][98559] Updated weights for policy 0, policy_version 50 (0.0009) -[2023-10-10 20:41:01,297][98560] Updated weights for policy 1, policy_version 50 (0.0008) -[2023-10-10 20:41:01,581][98559] Updated weights for policy 0, policy_version 60 (0.0008) -[2023-10-10 20:41:01,651][98560] Updated weights for policy 1, policy_version 60 (0.0008) -[2023-10-10 20:41:05,020][98559] Updated weights for policy 0, policy_version 70 (0.0008) -[2023-10-10 20:41:05,277][98560] Updated weights for policy 1, policy_version 70 (0.0009) -[2023-10-10 20:41:05,396][98559] Updated weights for policy 0, policy_version 80 (0.0008) -[2023-10-10 20:41:05,556][97672] Fps is (10 sec: 13107.1, 60 sec: 7298.6, 300 sec: 7298.6). Total num frames: 131072. Throughput: 0: 1471.4, 1: 1424.1. Samples: 51998. Policy #0 lag: (min: 33.0, avg: 33.0, max: 33.0) -[2023-10-10 20:41:05,557][97672] Avg episode reward: [(0, '-17.000'), (1, '-19.500')] -[2023-10-10 20:41:05,646][98560] Updated weights for policy 1, policy_version 80 (0.0008) -[2023-10-10 20:41:05,756][98559] Updated weights for policy 0, policy_version 90 (0.0009) -[2023-10-10 20:41:06,003][98560] Updated weights for policy 1, policy_version 90 (0.0008) -[2023-10-10 20:41:09,517][98559] Updated weights for policy 0, policy_version 100 (0.0008) -[2023-10-10 20:41:09,591][98560] Updated weights for policy 1, policy_version 100 (0.0009) -[2023-10-10 20:41:09,882][98559] Updated weights for policy 0, policy_version 110 (0.0007) -[2023-10-10 20:41:09,957][98560] Updated weights for policy 1, policy_version 110 (0.0008) -[2023-10-10 20:41:10,259][98559] Updated weights for policy 0, policy_version 120 (0.0008) -[2023-10-10 20:41:10,323][98560] Updated weights for policy 1, policy_version 120 (0.0007) -[2023-10-10 20:41:10,556][97672] Fps is (10 sec: 16384.0, 60 sec: 9991.0, 300 sec: 9991.0). Total num frames: 229376. Throughput: 0: 1370.1, 1: 1319.2. Samples: 61740. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-10 20:41:10,556][97672] Avg episode reward: [(0, '-17.400'), (1, '-17.167')] -[2023-10-10 20:41:10,558][98385] Saving new best policy, reward=-17.400! -[2023-10-10 20:41:14,249][98559] Updated weights for policy 0, policy_version 130 (0.0008) -[2023-10-10 20:41:14,436][98560] Updated weights for policy 1, policy_version 130 (0.0009) -[2023-10-10 20:41:14,616][98559] Updated weights for policy 0, policy_version 140 (0.0009) -[2023-10-10 20:41:14,810][98560] Updated weights for policy 1, policy_version 140 (0.0008) -[2023-10-10 20:41:14,986][98559] Updated weights for policy 0, policy_version 150 (0.0009) -[2023-10-10 20:41:15,167][98560] Updated weights for policy 1, policy_version 150 (0.0007) -[2023-10-10 20:41:15,364][98559] Updated weights for policy 0, policy_version 160 (0.0009) -[2023-10-10 20:41:15,539][98560] Updated weights for policy 1, policy_version 160 (0.0007) -[2023-10-10 20:41:15,556][97672] Fps is (10 sec: 19661.1, 60 sec: 11720.3, 300 sec: 11720.3). Total num frames: 327680. Throughput: 0: 1499.2, 1: 1462.2. Samples: 82796. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:41:15,557][97672] Avg episode reward: [(0, '-17.538'), (1, '-17.067')] -[2023-10-10 20:41:15,557][98439] Saving new best policy, reward=-17.067! -[2023-10-10 20:41:19,524][98559] Updated weights for policy 0, policy_version 170 (0.0008) -[2023-10-10 20:41:19,533][98560] Updated weights for policy 1, policy_version 170 (0.0008) -[2023-10-10 20:41:19,893][98560] Updated weights for policy 1, policy_version 180 (0.0007) -[2023-10-10 20:41:19,894][98559] Updated weights for policy 0, policy_version 180 (0.0009) -[2023-10-10 20:41:20,254][98559] Updated weights for policy 0, policy_version 190 (0.0008) -[2023-10-10 20:41:20,256][98560] Updated weights for policy 1, policy_version 190 (0.0009) -[2023-10-10 20:41:20,556][97672] Fps is (10 sec: 16384.1, 60 sec: 11930.7, 300 sec: 11930.7). Total num frames: 393216. Throughput: 0: 1562.8, 1: 1543.4. Samples: 102374. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:41:20,556][97672] Avg episode reward: [(0, '-17.500'), (1, '-17.222')] -[2023-10-10 20:41:24,110][98560] Updated weights for policy 1, policy_version 200 (0.0008) -[2023-10-10 20:41:24,347][98559] Updated weights for policy 0, policy_version 200 (0.0009) -[2023-10-10 20:41:24,482][98560] Updated weights for policy 1, policy_version 210 (0.0007) -[2023-10-10 20:41:24,722][98559] Updated weights for policy 0, policy_version 210 (0.0008) -[2023-10-10 20:41:24,847][98560] Updated weights for policy 1, policy_version 220 (0.0007) -[2023-10-10 20:41:25,088][98559] Updated weights for policy 0, policy_version 220 (0.0007) -[2023-10-10 20:41:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 12085.7, 300 sec: 12085.7). Total num frames: 458752. Throughput: 0: 1510.7, 1: 1474.6. Samples: 113314. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:41:25,557][97672] Avg episode reward: [(0, '-18.000'), (1, '-18.538')] -[2023-10-10 20:41:28,915][98560] Updated weights for policy 1, policy_version 230 (0.0008) -[2023-10-10 20:41:29,168][98559] Updated weights for policy 0, policy_version 230 (0.0008) -[2023-10-10 20:41:29,282][98560] Updated weights for policy 1, policy_version 240 (0.0008) -[2023-10-10 20:41:29,537][98559] Updated weights for policy 0, policy_version 240 (0.0008) -[2023-10-10 20:41:29,641][98560] Updated weights for policy 1, policy_version 250 (0.0008) -[2023-10-10 20:41:29,907][98559] Updated weights for policy 0, policy_version 250 (0.0007) -[2023-10-10 20:41:30,556][97672] Fps is (10 sec: 13107.3, 60 sec: 12204.6, 300 sec: 12204.6). Total num frames: 524288. Throughput: 0: 1562.5, 1: 1550.4. Samples: 133726. Policy #0 lag: (min: 4.0, avg: 8.7, max: 36.0) -[2023-10-10 20:41:30,557][97672] Avg episode reward: [(0, '-17.429'), (1, '-18.357')] -[2023-10-10 20:41:33,844][98560] Updated weights for policy 1, policy_version 260 (0.0009) -[2023-10-10 20:41:33,861][98559] Updated weights for policy 0, policy_version 260 (0.0007) -[2023-10-10 20:41:34,207][98560] Updated weights for policy 1, policy_version 270 (0.0008) -[2023-10-10 20:41:34,233][98559] Updated weights for policy 0, policy_version 270 (0.0007) -[2023-10-10 20:41:34,577][98560] Updated weights for policy 1, policy_version 280 (0.0008) -[2023-10-10 20:41:34,599][98559] Updated weights for policy 0, policy_version 280 (0.0008) -[2023-10-10 20:41:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 12298.6, 300 sec: 12298.6). Total num frames: 589824. Throughput: 0: 1655.1, 1: 1665.4. Samples: 152878. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 20:41:35,557][97672] Avg episode reward: [(0, '-17.467'), (1, '-18.250')] -[2023-10-10 20:41:38,624][98560] Updated weights for policy 1, policy_version 290 (0.0008) -[2023-10-10 20:41:38,734][98559] Updated weights for policy 0, policy_version 290 (0.0007) -[2023-10-10 20:41:39,033][98560] Updated weights for policy 1, policy_version 300 (0.0008) -[2023-10-10 20:41:39,137][98559] Updated weights for policy 0, policy_version 300 (0.0008) -[2023-10-10 20:41:39,401][98560] Updated weights for policy 1, policy_version 310 (0.0008) -[2023-10-10 20:41:39,509][98559] Updated weights for policy 0, policy_version 310 (0.0008) -[2023-10-10 20:41:39,767][98560] Updated weights for policy 1, policy_version 320 (0.0009) -[2023-10-10 20:41:39,881][98559] Updated weights for policy 0, policy_version 320 (0.0009) -[2023-10-10 20:41:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 12375.0, 300 sec: 12375.0). Total num frames: 655360. Throughput: 0: 1650.7, 1: 1658.3. Samples: 164336. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:41:40,556][97672] Avg episode reward: [(0, '-17.647'), (1, '-18.432')] -[2023-10-10 20:41:43,709][98560] Updated weights for policy 1, policy_version 330 (0.0007) -[2023-10-10 20:41:43,872][98559] Updated weights for policy 0, policy_version 330 (0.0007) -[2023-10-10 20:41:44,063][98560] Updated weights for policy 1, policy_version 340 (0.0008) -[2023-10-10 20:41:44,244][98559] Updated weights for policy 0, policy_version 340 (0.0008) -[2023-10-10 20:41:44,427][98560] Updated weights for policy 1, policy_version 350 (0.0009) -[2023-10-10 20:41:44,613][98559] Updated weights for policy 0, policy_version 350 (0.0010) -[2023-10-10 20:41:45,556][97672] Fps is (10 sec: 13107.6, 60 sec: 12438.2, 300 sec: 12438.2). Total num frames: 720896. Throughput: 0: 1677.5, 1: 1696.7. Samples: 183824. Policy #0 lag: (min: 26.0, avg: 28.5, max: 53.0) -[2023-10-10 20:41:45,556][97672] Avg episode reward: [(0, '-17.610'), (1, '-18.462')] -[2023-10-10 20:41:48,482][98560] Updated weights for policy 1, policy_version 360 (0.0008) -[2023-10-10 20:41:48,553][98559] Updated weights for policy 0, policy_version 360 (0.0009) -[2023-10-10 20:41:48,850][98560] Updated weights for policy 1, policy_version 370 (0.0008) -[2023-10-10 20:41:48,923][98559] Updated weights for policy 0, policy_version 370 (0.0008) -[2023-10-10 20:41:49,225][98560] Updated weights for policy 1, policy_version 380 (0.0008) -[2023-10-10 20:41:49,297][98559] Updated weights for policy 0, policy_version 380 (0.0009) -[2023-10-10 20:41:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12491.3). Total num frames: 786432. Throughput: 0: 1686.6, 1: 1680.9. Samples: 203534. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-10-10 20:41:50,557][97672] Avg episode reward: [(0, '-17.783'), (1, '-18.409')] -[2023-10-10 20:41:53,247][98559] Updated weights for policy 0, policy_version 390 (0.0009) -[2023-10-10 20:41:53,400][98560] Updated weights for policy 1, policy_version 390 (0.0009) -[2023-10-10 20:41:53,618][98559] Updated weights for policy 0, policy_version 400 (0.0007) -[2023-10-10 20:41:53,765][98560] Updated weights for policy 1, policy_version 400 (0.0008) -[2023-10-10 20:41:53,987][98559] Updated weights for policy 0, policy_version 410 (0.0007) -[2023-10-10 20:41:54,136][98560] Updated weights for policy 1, policy_version 410 (0.0008) -[2023-10-10 20:41:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 12536.6). Total num frames: 851968. Throughput: 0: 1696.4, 1: 1703.8. Samples: 214748. Policy #0 lag: (min: 22.0, avg: 24.4, max: 54.0) -[2023-10-10 20:41:55,556][97672] Avg episode reward: [(0, '-17.918'), (1, '-18.392')] -[2023-10-10 20:41:57,912][98560] Updated weights for policy 1, policy_version 420 (0.0009) -[2023-10-10 20:41:58,095][98559] Updated weights for policy 0, policy_version 420 (0.0010) -[2023-10-10 20:41:58,280][98560] Updated weights for policy 1, policy_version 430 (0.0008) -[2023-10-10 20:41:58,464][98559] Updated weights for policy 0, policy_version 430 (0.0009) -[2023-10-10 20:41:58,644][98560] Updated weights for policy 1, policy_version 440 (0.0007) -[2023-10-10 20:41:58,837][98559] Updated weights for policy 0, policy_version 440 (0.0008) -[2023-10-10 20:42:00,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 12575.7). Total num frames: 917504. Throughput: 0: 1673.2, 1: 1681.9. Samples: 233778. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-10-10 20:42:00,557][97672] Avg episode reward: [(0, '-18.038'), (1, '-18.481')] -[2023-10-10 20:42:02,665][98560] Updated weights for policy 1, policy_version 450 (0.0007) -[2023-10-10 20:42:02,897][98559] Updated weights for policy 0, policy_version 450 (0.0011) -[2023-10-10 20:42:03,030][98560] Updated weights for policy 1, policy_version 460 (0.0008) -[2023-10-10 20:42:03,268][98559] Updated weights for policy 0, policy_version 460 (0.0008) -[2023-10-10 20:42:03,401][98560] Updated weights for policy 1, policy_version 470 (0.0007) -[2023-10-10 20:42:03,630][98559] Updated weights for policy 0, policy_version 470 (0.0009) -[2023-10-10 20:42:03,763][98560] Updated weights for policy 1, policy_version 480 (0.0008) -[2023-10-10 20:42:03,998][98559] Updated weights for policy 0, policy_version 480 (0.0008) -[2023-10-10 20:42:05,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 12609.8). Total num frames: 983040. Throughput: 0: 1693.1, 1: 1687.5. Samples: 254502. Policy #0 lag: (min: 1.0, avg: 8.9, max: 33.0) -[2023-10-10 20:42:05,556][97672] Avg episode reward: [(0, '-17.759'), (1, '-18.500')] -[2023-10-10 20:42:07,750][98560] Updated weights for policy 1, policy_version 490 (0.0009) -[2023-10-10 20:42:08,017][98559] Updated weights for policy 0, policy_version 490 (0.0010) -[2023-10-10 20:42:08,113][98560] Updated weights for policy 1, policy_version 500 (0.0008) -[2023-10-10 20:42:08,381][98559] Updated weights for policy 0, policy_version 500 (0.0007) -[2023-10-10 20:42:08,488][98560] Updated weights for policy 1, policy_version 510 (0.0008) -[2023-10-10 20:42:08,762][98559] Updated weights for policy 0, policy_version 510 (0.0010) -[2023-10-10 20:42:10,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 12639.8). Total num frames: 1048576. Throughput: 0: 1678.7, 1: 1697.4. Samples: 265240. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-10 20:42:10,557][97672] Avg episode reward: [(0, '-17.683'), (1, '-18.066')] -[2023-10-10 20:42:12,567][98560] Updated weights for policy 1, policy_version 520 (0.0007) -[2023-10-10 20:42:12,784][98559] Updated weights for policy 0, policy_version 520 (0.0008) -[2023-10-10 20:42:12,926][98560] Updated weights for policy 1, policy_version 530 (0.0008) -[2023-10-10 20:42:13,165][98559] Updated weights for policy 0, policy_version 530 (0.0008) -[2023-10-10 20:42:13,292][98560] Updated weights for policy 1, policy_version 540 (0.0008) -[2023-10-10 20:42:13,531][98559] Updated weights for policy 0, policy_version 540 (0.0008) -[2023-10-10 20:42:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12666.4). Total num frames: 1114112. Throughput: 0: 1677.7, 1: 1672.7. Samples: 284492. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 20:42:15,556][97672] Avg episode reward: [(0, '-17.642'), (1, '-17.971')] -[2023-10-10 20:42:17,243][98560] Updated weights for policy 1, policy_version 550 (0.0007) -[2023-10-10 20:42:17,561][98559] Updated weights for policy 0, policy_version 550 (0.0008) -[2023-10-10 20:42:17,612][98560] Updated weights for policy 1, policy_version 560 (0.0007) -[2023-10-10 20:42:17,924][98559] Updated weights for policy 0, policy_version 560 (0.0009) -[2023-10-10 20:42:17,975][98560] Updated weights for policy 1, policy_version 570 (0.0009) -[2023-10-10 20:42:18,303][98559] Updated weights for policy 0, policy_version 570 (0.0008) -[2023-10-10 20:42:20,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 12690.1). Total num frames: 1179648. Throughput: 0: 1691.9, 1: 1699.7. Samples: 305500. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:42:20,557][97672] Avg episode reward: [(0, '-17.743'), (1, '-17.971')] -[2023-10-10 20:42:21,944][98560] Updated weights for policy 1, policy_version 580 (0.0009) -[2023-10-10 20:42:22,317][98560] Updated weights for policy 1, policy_version 590 (0.0009) -[2023-10-10 20:42:22,422][98559] Updated weights for policy 0, policy_version 580 (0.0007) -[2023-10-10 20:42:22,682][98560] Updated weights for policy 1, policy_version 600 (0.0008) -[2023-10-10 20:42:22,798][98559] Updated weights for policy 0, policy_version 590 (0.0008) -[2023-10-10 20:42:23,166][98559] Updated weights for policy 0, policy_version 600 (0.0010) -[2023-10-10 20:42:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12711.4). Total num frames: 1245184. Throughput: 0: 1670.6, 1: 1684.1. Samples: 315296. Policy #0 lag: (min: 17.0, avg: 19.5, max: 45.0) -[2023-10-10 20:42:25,556][97672] Avg episode reward: [(0, '-17.711'), (1, '-17.889')] -[2023-10-10 20:42:26,551][98560] Updated weights for policy 1, policy_version 610 (0.0008) -[2023-10-10 20:42:26,955][98560] Updated weights for policy 1, policy_version 620 (0.0010) -[2023-10-10 20:42:27,324][98560] Updated weights for policy 1, policy_version 630 (0.0010) -[2023-10-10 20:42:27,406][98559] Updated weights for policy 0, policy_version 610 (0.0010) -[2023-10-10 20:42:27,683][98560] Updated weights for policy 1, policy_version 640 (0.0008) -[2023-10-10 20:42:27,831][98559] Updated weights for policy 0, policy_version 620 (0.0008) -[2023-10-10 20:42:28,198][98559] Updated weights for policy 0, policy_version 630 (0.0007) -[2023-10-10 20:42:28,570][98559] Updated weights for policy 0, policy_version 640 (0.0008) -[2023-10-10 20:42:30,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12730.6). Total num frames: 1310720. Throughput: 0: 1686.0, 1: 1692.9. Samples: 335874. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-10 20:42:30,556][97672] Avg episode reward: [(0, '-17.829'), (1, '-17.974')] -[2023-10-10 20:42:31,661][98560] Updated weights for policy 1, policy_version 650 (0.0010) -[2023-10-10 20:42:32,025][98560] Updated weights for policy 1, policy_version 660 (0.0010) -[2023-10-10 20:42:32,387][98560] Updated weights for policy 1, policy_version 670 (0.0008) -[2023-10-10 20:42:32,542][98559] Updated weights for policy 0, policy_version 650 (0.0008) -[2023-10-10 20:42:32,922][98559] Updated weights for policy 0, policy_version 660 (0.0009) -[2023-10-10 20:42:33,294][98559] Updated weights for policy 0, policy_version 670 (0.0008) -[2023-10-10 20:42:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.3, 300 sec: 12748.0). Total num frames: 1376256. Throughput: 0: 1692.7, 1: 1714.7. Samples: 356866. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:42:35,556][97672] Avg episode reward: [(0, '-17.738'), (1, '-17.975')] -[2023-10-10 20:42:35,560][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000000672_688128.pth... -[2023-10-10 20:42:35,561][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000000672_688128.pth... -[2023-10-10 20:42:36,429][98560] Updated weights for policy 1, policy_version 680 (0.0010) -[2023-10-10 20:42:36,805][98560] Updated weights for policy 1, policy_version 690 (0.0009) -[2023-10-10 20:42:37,166][98559] Updated weights for policy 0, policy_version 680 (0.0008) -[2023-10-10 20:42:37,168][98560] Updated weights for policy 1, policy_version 700 (0.0007) -[2023-10-10 20:42:37,534][98559] Updated weights for policy 0, policy_version 690 (0.0007) -[2023-10-10 20:42:37,910][98559] Updated weights for policy 0, policy_version 700 (0.0009) -[2023-10-10 20:42:40,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12763.9). Total num frames: 1441792. Throughput: 0: 1675.4, 1: 1686.4. Samples: 366030. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-10 20:42:40,557][97672] Avg episode reward: [(0, '-17.674'), (1, '-17.885')] -[2023-10-10 20:42:41,137][98560] Updated weights for policy 1, policy_version 710 (0.0009) -[2023-10-10 20:42:41,501][98560] Updated weights for policy 1, policy_version 720 (0.0009) -[2023-10-10 20:42:41,875][98560] Updated weights for policy 1, policy_version 730 (0.0009) -[2023-10-10 20:42:41,918][98559] Updated weights for policy 0, policy_version 710 (0.0008) -[2023-10-10 20:42:42,281][98559] Updated weights for policy 0, policy_version 720 (0.0010) -[2023-10-10 20:42:42,661][98559] Updated weights for policy 0, policy_version 730 (0.0008) -[2023-10-10 20:42:45,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 12778.5). Total num frames: 1507328. Throughput: 0: 1700.5, 1: 1708.5. Samples: 387186. Policy #0 lag: (min: 4.0, avg: 5.9, max: 25.0) -[2023-10-10 20:42:45,557][97672] Avg episode reward: [(0, '-17.543'), (1, '-17.912')] -[2023-10-10 20:42:45,797][98560] Updated weights for policy 1, policy_version 740 (0.0009) -[2023-10-10 20:42:46,159][98560] Updated weights for policy 1, policy_version 750 (0.0008) -[2023-10-10 20:42:46,535][98560] Updated weights for policy 1, policy_version 760 (0.0007) -[2023-10-10 20:42:46,694][98559] Updated weights for policy 0, policy_version 740 (0.0008) -[2023-10-10 20:42:47,068][98559] Updated weights for policy 0, policy_version 750 (0.0008) -[2023-10-10 20:42:47,438][98559] Updated weights for policy 0, policy_version 760 (0.0009) -[2023-10-10 20:42:50,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12791.8). Total num frames: 1572864. Throughput: 0: 1701.0, 1: 1714.7. Samples: 408208. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 20:42:50,557][97672] Avg episode reward: [(0, '-17.381'), (1, '-17.830')] -[2023-10-10 20:42:50,561][98385] Saving new best policy, reward=-17.381! -[2023-10-10 20:42:50,630][98560] Updated weights for policy 1, policy_version 770 (0.0008) -[2023-10-10 20:42:51,001][98560] Updated weights for policy 1, policy_version 780 (0.0007) -[2023-10-10 20:42:51,350][98559] Updated weights for policy 0, policy_version 770 (0.0007) -[2023-10-10 20:42:51,366][98560] Updated weights for policy 1, policy_version 790 (0.0008) -[2023-10-10 20:42:51,725][98559] Updated weights for policy 0, policy_version 780 (0.0007) -[2023-10-10 20:42:51,732][98560] Updated weights for policy 1, policy_version 800 (0.0008) -[2023-10-10 20:42:52,105][98559] Updated weights for policy 0, policy_version 790 (0.0008) -[2023-10-10 20:42:52,480][98559] Updated weights for policy 0, policy_version 800 (0.0009) -[2023-10-10 20:42:55,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12804.2). Total num frames: 1638400. Throughput: 0: 1687.3, 1: 1696.5. Samples: 417512. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-10 20:42:55,556][97672] Avg episode reward: [(0, '-17.380'), (1, '-17.796')] -[2023-10-10 20:42:55,557][98385] Saving new best policy, reward=-17.380! -[2023-10-10 20:42:55,757][98560] Updated weights for policy 1, policy_version 810 (0.0009) -[2023-10-10 20:42:56,127][98560] Updated weights for policy 1, policy_version 820 (0.0010) -[2023-10-10 20:42:56,451][98559] Updated weights for policy 0, policy_version 810 (0.0008) -[2023-10-10 20:42:56,504][98560] Updated weights for policy 1, policy_version 830 (0.0007) -[2023-10-10 20:42:56,826][98559] Updated weights for policy 0, policy_version 820 (0.0007) -[2023-10-10 20:42:57,192][98559] Updated weights for policy 0, policy_version 830 (0.0008) -[2023-10-10 20:43:00,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12815.6). Total num frames: 1703936. Throughput: 0: 1706.8, 1: 1719.8. Samples: 438688. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-10 20:43:00,557][97672] Avg episode reward: [(0, '-17.400'), (1, '-17.720')] -[2023-10-10 20:43:00,587][98560] Updated weights for policy 1, policy_version 840 (0.0009) -[2023-10-10 20:43:00,952][98560] Updated weights for policy 1, policy_version 850 (0.0007) -[2023-10-10 20:43:01,006][98559] Updated weights for policy 0, policy_version 840 (0.0008) -[2023-10-10 20:43:01,329][98560] Updated weights for policy 1, policy_version 860 (0.0007) -[2023-10-10 20:43:01,379][98559] Updated weights for policy 0, policy_version 850 (0.0008) -[2023-10-10 20:43:01,764][98559] Updated weights for policy 0, policy_version 860 (0.0009) -[2023-10-10 20:43:05,337][98560] Updated weights for policy 1, policy_version 870 (0.0009) -[2023-10-10 20:43:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12826.1). Total num frames: 1769472. Throughput: 0: 1707.3, 1: 1720.6. Samples: 459758. Policy #0 lag: (min: 15.0, avg: 37.3, max: 40.0) -[2023-10-10 20:43:05,556][97672] Avg episode reward: [(0, '-17.280'), (1, '-17.640')] -[2023-10-10 20:43:05,709][98560] Updated weights for policy 1, policy_version 880 (0.0008) -[2023-10-10 20:43:05,853][98559] Updated weights for policy 0, policy_version 870 (0.0009) -[2023-10-10 20:43:06,086][98560] Updated weights for policy 1, policy_version 890 (0.0007) -[2023-10-10 20:43:06,229][98559] Updated weights for policy 0, policy_version 880 (0.0010) -[2023-10-10 20:43:06,610][98559] Updated weights for policy 0, policy_version 890 (0.0009) -[2023-10-10 20:43:06,822][98385] Saving new best policy, reward=-17.280! -[2023-10-10 20:43:10,076][98560] Updated weights for policy 1, policy_version 900 (0.0007) -[2023-10-10 20:43:10,437][98560] Updated weights for policy 1, policy_version 910 (0.0009) -[2023-10-10 20:43:10,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 12835.9). Total num frames: 1835008. Throughput: 0: 1697.0, 1: 1712.5. Samples: 468724. Policy #0 lag: (min: 16.0, avg: 37.2, max: 48.0) -[2023-10-10 20:43:10,557][97672] Avg episode reward: [(0, '-17.280'), (1, '-17.600')] -[2023-10-10 20:43:10,665][98559] Updated weights for policy 0, policy_version 900 (0.0008) -[2023-10-10 20:43:10,805][98560] Updated weights for policy 1, policy_version 920 (0.0007) -[2023-10-10 20:43:11,040][98559] Updated weights for policy 0, policy_version 910 (0.0008) -[2023-10-10 20:43:11,414][98559] Updated weights for policy 0, policy_version 920 (0.0007) -[2023-10-10 20:43:14,787][98560] Updated weights for policy 1, policy_version 930 (0.0007) -[2023-10-10 20:43:15,199][98560] Updated weights for policy 1, policy_version 940 (0.0010) -[2023-10-10 20:43:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12845.1). Total num frames: 1900544. Throughput: 0: 1698.1, 1: 1716.7. Samples: 489542. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 20:43:15,556][97672] Avg episode reward: [(0, '-17.200'), (1, '-17.500')] -[2023-10-10 20:43:15,567][98560] Updated weights for policy 1, policy_version 950 (0.0009) -[2023-10-10 20:43:15,584][98559] Updated weights for policy 0, policy_version 930 (0.0008) -[2023-10-10 20:43:15,937][98560] Updated weights for policy 1, policy_version 960 (0.0008) -[2023-10-10 20:43:15,974][98559] Updated weights for policy 0, policy_version 940 (0.0009) -[2023-10-10 20:43:16,341][98559] Updated weights for policy 0, policy_version 950 (0.0009) -[2023-10-10 20:43:16,708][98385] Saving new best policy, reward=-17.200! -[2023-10-10 20:43:16,710][98559] Updated weights for policy 0, policy_version 960 (0.0009) -[2023-10-10 20:43:19,905][98560] Updated weights for policy 1, policy_version 970 (0.0009) -[2023-10-10 20:43:20,286][98560] Updated weights for policy 1, policy_version 980 (0.0010) -[2023-10-10 20:43:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12853.7). Total num frames: 1966080. Throughput: 0: 1694.2, 1: 1710.1. Samples: 510058. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:43:20,557][97672] Avg episode reward: [(0, '-17.260'), (1, '-17.460')] -[2023-10-10 20:43:20,646][98560] Updated weights for policy 1, policy_version 990 (0.0008) -[2023-10-10 20:43:20,714][98559] Updated weights for policy 0, policy_version 970 (0.0008) -[2023-10-10 20:43:21,090][98559] Updated weights for policy 0, policy_version 980 (0.0008) -[2023-10-10 20:43:21,470][98559] Updated weights for policy 0, policy_version 990 (0.0009) -[2023-10-10 20:43:24,631][98560] Updated weights for policy 1, policy_version 1000 (0.0009) -[2023-10-10 20:43:25,000][98560] Updated weights for policy 1, policy_version 1010 (0.0010) -[2023-10-10 20:43:25,368][98560] Updated weights for policy 1, policy_version 1020 (0.0010) -[2023-10-10 20:43:25,496][98559] Updated weights for policy 0, policy_version 1000 (0.0008) -[2023-10-10 20:43:25,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13069.2). Total num frames: 2064384. Throughput: 0: 1690.0, 1: 1718.0. Samples: 519392. Policy #0 lag: (min: 21.0, avg: 22.9, max: 51.0) -[2023-10-10 20:43:25,556][97672] Avg episode reward: [(0, '-17.280'), (1, '-17.320')] -[2023-10-10 20:43:25,874][98559] Updated weights for policy 0, policy_version 1010 (0.0008) -[2023-10-10 20:43:26,248][98559] Updated weights for policy 0, policy_version 1020 (0.0009) -[2023-10-10 20:43:29,305][98560] Updated weights for policy 1, policy_version 1030 (0.0009) -[2023-10-10 20:43:29,676][98560] Updated weights for policy 1, policy_version 1040 (0.0009) -[2023-10-10 20:43:30,050][98560] Updated weights for policy 1, policy_version 1050 (0.0008) -[2023-10-10 20:43:30,401][98559] Updated weights for policy 0, policy_version 1030 (0.0008) -[2023-10-10 20:43:30,556][97672] Fps is (10 sec: 16384.5, 60 sec: 13653.3, 300 sec: 13070.3). Total num frames: 2129920. Throughput: 0: 1684.2, 1: 1715.0. Samples: 540148. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-10 20:43:30,556][97672] Avg episode reward: [(0, '-17.320'), (1, '-17.320')] -[2023-10-10 20:43:30,776][98559] Updated weights for policy 0, policy_version 1040 (0.0010) -[2023-10-10 20:43:31,152][98559] Updated weights for policy 0, policy_version 1050 (0.0011) -[2023-10-10 20:43:33,958][98560] Updated weights for policy 1, policy_version 1060 (0.0008) -[2023-10-10 20:43:34,319][98560] Updated weights for policy 1, policy_version 1070 (0.0008) -[2023-10-10 20:43:34,690][98560] Updated weights for policy 1, policy_version 1080 (0.0008) -[2023-10-10 20:43:35,088][98559] Updated weights for policy 0, policy_version 1060 (0.0010) -[2023-10-10 20:43:35,460][98559] Updated weights for policy 0, policy_version 1070 (0.0011) -[2023-10-10 20:43:35,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13071.4). Total num frames: 2195456. Throughput: 0: 1674.1, 1: 1692.9. Samples: 559724. Policy #0 lag: (min: 3.0, avg: 5.1, max: 34.0) -[2023-10-10 20:43:35,556][97672] Avg episode reward: [(0, '-17.300'), (1, '-17.120')] -[2023-10-10 20:43:35,836][98559] Updated weights for policy 0, policy_version 1080 (0.0011) -[2023-10-10 20:43:38,894][98560] Updated weights for policy 1, policy_version 1090 (0.0008) -[2023-10-10 20:43:39,263][98560] Updated weights for policy 1, policy_version 1100 (0.0010) -[2023-10-10 20:43:39,629][98560] Updated weights for policy 1, policy_version 1110 (0.0010) -[2023-10-10 20:43:39,763][98559] Updated weights for policy 0, policy_version 1090 (0.0011) -[2023-10-10 20:43:39,997][98560] Updated weights for policy 1, policy_version 1120 (0.0008) -[2023-10-10 20:43:40,136][98559] Updated weights for policy 0, policy_version 1100 (0.0007) -[2023-10-10 20:43:40,505][98559] Updated weights for policy 0, policy_version 1110 (0.0007) -[2023-10-10 20:43:40,556][97672] Fps is (10 sec: 13106.7, 60 sec: 13653.3, 300 sec: 13072.4). Total num frames: 2260992. Throughput: 0: 1683.7, 1: 1711.4. Samples: 570290. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:43:40,559][97672] Avg episode reward: [(0, '-17.320'), (1, '-16.980')] -[2023-10-10 20:43:40,560][98439] Saving new best policy, reward=-16.980! -[2023-10-10 20:43:40,874][98559] Updated weights for policy 0, policy_version 1120 (0.0010) -[2023-10-10 20:43:44,060][98560] Updated weights for policy 1, policy_version 1130 (0.0007) -[2023-10-10 20:43:44,435][98560] Updated weights for policy 1, policy_version 1140 (0.0007) -[2023-10-10 20:43:44,793][98560] Updated weights for policy 1, policy_version 1150 (0.0009) -[2023-10-10 20:43:44,913][98559] Updated weights for policy 0, policy_version 1130 (0.0007) -[2023-10-10 20:43:45,283][98559] Updated weights for policy 0, policy_version 1140 (0.0009) -[2023-10-10 20:43:45,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13073.4). Total num frames: 2326528. Throughput: 0: 1682.5, 1: 1708.8. Samples: 591300. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 20:43:45,557][97672] Avg episode reward: [(0, '-17.380'), (1, '-16.820')] -[2023-10-10 20:43:45,558][98439] Saving new best policy, reward=-16.820! -[2023-10-10 20:43:45,659][98559] Updated weights for policy 0, policy_version 1150 (0.0007) -[2023-10-10 20:43:48,830][98560] Updated weights for policy 1, policy_version 1160 (0.0008) -[2023-10-10 20:43:49,206][98560] Updated weights for policy 1, policy_version 1170 (0.0008) -[2023-10-10 20:43:49,582][98560] Updated weights for policy 1, policy_version 1180 (0.0009) -[2023-10-10 20:43:49,727][98559] Updated weights for policy 0, policy_version 1160 (0.0008) -[2023-10-10 20:43:50,100][98559] Updated weights for policy 0, policy_version 1170 (0.0007) -[2023-10-10 20:43:50,475][98559] Updated weights for policy 0, policy_version 1180 (0.0007) -[2023-10-10 20:43:50,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13074.4). Total num frames: 2392064. Throughput: 0: 1665.3, 1: 1678.8. Samples: 610242. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:43:50,556][97672] Avg episode reward: [(0, '-17.000'), (1, '-16.780')] -[2023-10-10 20:43:50,568][98439] Saving new best policy, reward=-16.780! -[2023-10-10 20:43:50,625][98385] Saving new best policy, reward=-17.000! -[2023-10-10 20:43:53,631][98560] Updated weights for policy 1, policy_version 1190 (0.0008) -[2023-10-10 20:43:54,000][98560] Updated weights for policy 1, policy_version 1200 (0.0008) -[2023-10-10 20:43:54,378][98560] Updated weights for policy 1, policy_version 1210 (0.0009) -[2023-10-10 20:43:54,503][98559] Updated weights for policy 0, policy_version 1190 (0.0009) -[2023-10-10 20:43:54,873][98559] Updated weights for policy 0, policy_version 1200 (0.0009) -[2023-10-10 20:43:55,251][98559] Updated weights for policy 0, policy_version 1210 (0.0009) -[2023-10-10 20:43:55,556][97672] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13249.6). Total num frames: 2490368. Throughput: 0: 1693.3, 1: 1705.8. Samples: 621684. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:43:55,556][97672] Avg episode reward: [(0, '-16.900'), (1, '-16.480')] -[2023-10-10 20:43:55,557][98385] Saving new best policy, reward=-16.900! -[2023-10-10 20:43:55,557][98439] Saving new best policy, reward=-16.480! -[2023-10-10 20:43:58,354][98560] Updated weights for policy 1, policy_version 1220 (0.0009) -[2023-10-10 20:43:58,729][98560] Updated weights for policy 1, policy_version 1230 (0.0010) -[2023-10-10 20:43:59,102][98560] Updated weights for policy 1, policy_version 1240 (0.0010) -[2023-10-10 20:43:59,351][98559] Updated weights for policy 0, policy_version 1220 (0.0009) -[2023-10-10 20:43:59,728][98559] Updated weights for policy 0, policy_version 1230 (0.0009) -[2023-10-10 20:44:00,102][98559] Updated weights for policy 0, policy_version 1240 (0.0009) -[2023-10-10 20:44:00,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13245.9). Total num frames: 2555904. Throughput: 0: 1694.5, 1: 1692.8. Samples: 641970. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:44:00,556][97672] Avg episode reward: [(0, '-16.860'), (1, '-16.540')] -[2023-10-10 20:44:00,557][98385] Saving new best policy, reward=-16.860! -[2023-10-10 20:44:03,103][98560] Updated weights for policy 1, policy_version 1250 (0.0008) -[2023-10-10 20:44:03,472][98560] Updated weights for policy 1, policy_version 1260 (0.0008) -[2023-10-10 20:44:03,844][98560] Updated weights for policy 1, policy_version 1270 (0.0008) -[2023-10-10 20:44:04,161][98559] Updated weights for policy 0, policy_version 1250 (0.0009) -[2023-10-10 20:44:04,219][98560] Updated weights for policy 1, policy_version 1280 (0.0009) -[2023-10-10 20:44:04,579][98559] Updated weights for policy 0, policy_version 1260 (0.0009) -[2023-10-10 20:44:04,950][98559] Updated weights for policy 0, policy_version 1270 (0.0008) -[2023-10-10 20:44:05,323][98559] Updated weights for policy 0, policy_version 1280 (0.0010) -[2023-10-10 20:44:05,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13242.4). Total num frames: 2621440. Throughput: 0: 1670.6, 1: 1674.5. Samples: 660588. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:44:05,557][97672] Avg episode reward: [(0, '-17.000'), (1, '-16.460')] -[2023-10-10 20:44:05,570][98439] Saving new best policy, reward=-16.460! -[2023-10-10 20:44:08,150][98560] Updated weights for policy 1, policy_version 1290 (0.0009) -[2023-10-10 20:44:08,524][98560] Updated weights for policy 1, policy_version 1300 (0.0009) -[2023-10-10 20:44:08,888][98560] Updated weights for policy 1, policy_version 1310 (0.0007) -[2023-10-10 20:44:09,393][98559] Updated weights for policy 0, policy_version 1290 (0.0008) -[2023-10-10 20:44:09,773][98559] Updated weights for policy 0, policy_version 1300 (0.0008) -[2023-10-10 20:44:10,145][98559] Updated weights for policy 0, policy_version 1310 (0.0007) -[2023-10-10 20:44:10,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13239.0). Total num frames: 2686976. Throughput: 0: 1697.2, 1: 1699.0. Samples: 672220. Policy #0 lag: (min: 26.0, avg: 33.4, max: 58.0) -[2023-10-10 20:44:10,557][97672] Avg episode reward: [(0, '-17.020'), (1, '-16.260')] -[2023-10-10 20:44:10,559][98439] Saving new best policy, reward=-16.260! -[2023-10-10 20:44:12,997][98560] Updated weights for policy 1, policy_version 1320 (0.0010) -[2023-10-10 20:44:13,368][98560] Updated weights for policy 1, policy_version 1330 (0.0008) -[2023-10-10 20:44:13,740][98560] Updated weights for policy 1, policy_version 1340 (0.0007) -[2023-10-10 20:44:14,129][98559] Updated weights for policy 0, policy_version 1320 (0.0009) -[2023-10-10 20:44:14,497][98559] Updated weights for policy 0, policy_version 1330 (0.0007) -[2023-10-10 20:44:14,869][98559] Updated weights for policy 0, policy_version 1340 (0.0009) -[2023-10-10 20:44:15,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13235.9). Total num frames: 2752512. Throughput: 0: 1692.4, 1: 1672.8. Samples: 691580. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-10 20:44:15,556][97672] Avg episode reward: [(0, '-16.900'), (1, '-16.120')] -[2023-10-10 20:44:15,557][98439] Saving new best policy, reward=-16.120! -[2023-10-10 20:44:17,801][98560] Updated weights for policy 1, policy_version 1350 (0.0008) -[2023-10-10 20:44:18,164][98560] Updated weights for policy 1, policy_version 1360 (0.0010) -[2023-10-10 20:44:18,531][98560] Updated weights for policy 1, policy_version 1370 (0.0008) -[2023-10-10 20:44:18,703][98559] Updated weights for policy 0, policy_version 1350 (0.0008) -[2023-10-10 20:44:19,083][98559] Updated weights for policy 0, policy_version 1360 (0.0008) -[2023-10-10 20:44:19,451][98559] Updated weights for policy 0, policy_version 1370 (0.0011) -[2023-10-10 20:44:20,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13232.9). Total num frames: 2818048. Throughput: 0: 1685.7, 1: 1684.5. Samples: 711384. Policy #0 lag: (min: 10.0, avg: 12.5, max: 42.0) -[2023-10-10 20:44:20,556][97672] Avg episode reward: [(0, '-16.820'), (1, '-16.220')] -[2023-10-10 20:44:20,565][98385] Saving new best policy, reward=-16.820! -[2023-10-10 20:44:22,771][98560] Updated weights for policy 1, policy_version 1380 (0.0008) -[2023-10-10 20:44:23,144][98560] Updated weights for policy 1, policy_version 1390 (0.0009) -[2023-10-10 20:44:23,517][98560] Updated weights for policy 1, policy_version 1400 (0.0007) -[2023-10-10 20:44:23,551][98559] Updated weights for policy 0, policy_version 1380 (0.0008) -[2023-10-10 20:44:23,927][98559] Updated weights for policy 0, policy_version 1390 (0.0009) -[2023-10-10 20:44:24,290][98559] Updated weights for policy 0, policy_version 1400 (0.0010) -[2023-10-10 20:44:25,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13230.0). Total num frames: 2883584. Throughput: 0: 1705.9, 1: 1686.5. Samples: 722946. Policy #0 lag: (min: 10.0, avg: 12.9, max: 42.0) -[2023-10-10 20:44:25,557][97672] Avg episode reward: [(0, '-16.760'), (1, '-16.220')] -[2023-10-10 20:44:25,559][98385] Saving new best policy, reward=-16.760! -[2023-10-10 20:44:27,587][98560] Updated weights for policy 1, policy_version 1410 (0.0008) -[2023-10-10 20:44:27,960][98560] Updated weights for policy 1, policy_version 1420 (0.0008) -[2023-10-10 20:44:28,337][98560] Updated weights for policy 1, policy_version 1430 (0.0008) -[2023-10-10 20:44:28,471][98559] Updated weights for policy 0, policy_version 1410 (0.0009) -[2023-10-10 20:44:28,699][98560] Updated weights for policy 1, policy_version 1440 (0.0007) -[2023-10-10 20:44:28,842][98559] Updated weights for policy 0, policy_version 1420 (0.0009) -[2023-10-10 20:44:29,219][98559] Updated weights for policy 0, policy_version 1430 (0.0008) -[2023-10-10 20:44:29,589][98559] Updated weights for policy 0, policy_version 1440 (0.0009) -[2023-10-10 20:44:30,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13227.2). Total num frames: 2949120. Throughput: 0: 1679.2, 1: 1658.7. Samples: 741508. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-10 20:44:30,557][97672] Avg episode reward: [(0, '-16.700'), (1, '-16.120')] -[2023-10-10 20:44:30,558][98385] Saving new best policy, reward=-16.700! -[2023-10-10 20:44:32,586][98560] Updated weights for policy 1, policy_version 1450 (0.0008) -[2023-10-10 20:44:32,958][98560] Updated weights for policy 1, policy_version 1460 (0.0007) -[2023-10-10 20:44:33,327][98560] Updated weights for policy 1, policy_version 1470 (0.0007) -[2023-10-10 20:44:33,646][98559] Updated weights for policy 0, policy_version 1450 (0.0008) -[2023-10-10 20:44:34,015][98559] Updated weights for policy 0, policy_version 1460 (0.0008) -[2023-10-10 20:44:34,390][98559] Updated weights for policy 0, policy_version 1470 (0.0007) -[2023-10-10 20:44:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13224.6). Total num frames: 3014656. Throughput: 0: 1689.9, 1: 1686.0. Samples: 762158. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-10 20:44:35,557][97672] Avg episode reward: [(0, '-16.480'), (1, '-16.160')] -[2023-10-10 20:44:35,569][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000001472_1507328.pth... -[2023-10-10 20:44:35,569][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000001472_1507328.pth... -[2023-10-10 20:44:35,611][98385] Saving new best policy, reward=-16.480! -[2023-10-10 20:44:37,277][98560] Updated weights for policy 1, policy_version 1480 (0.0007) -[2023-10-10 20:44:37,636][98560] Updated weights for policy 1, policy_version 1490 (0.0010) -[2023-10-10 20:44:38,002][98560] Updated weights for policy 1, policy_version 1500 (0.0008) -[2023-10-10 20:44:38,284][98559] Updated weights for policy 0, policy_version 1480 (0.0007) -[2023-10-10 20:44:38,659][98559] Updated weights for policy 0, policy_version 1490 (0.0007) -[2023-10-10 20:44:39,026][98559] Updated weights for policy 0, policy_version 1500 (0.0009) -[2023-10-10 20:44:40,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13222.1). Total num frames: 3080192. Throughput: 0: 1691.7, 1: 1672.2. Samples: 773060. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:44:40,556][97672] Avg episode reward: [(0, '-16.500'), (1, '-16.000')] -[2023-10-10 20:44:40,557][98439] Saving new best policy, reward=-16.000! -[2023-10-10 20:44:42,126][98560] Updated weights for policy 1, policy_version 1510 (0.0008) -[2023-10-10 20:44:42,567][98560] Updated weights for policy 1, policy_version 1522 (0.0009) -[2023-10-10 20:44:42,933][98560] Updated weights for policy 1, policy_version 1532 (0.0010) -[2023-10-10 20:44:42,937][98559] Updated weights for policy 0, policy_version 1510 (0.0007) -[2023-10-10 20:44:43,305][98559] Updated weights for policy 0, policy_version 1520 (0.0007) -[2023-10-10 20:44:43,689][98559] Updated weights for policy 0, policy_version 1530 (0.0009) -[2023-10-10 20:44:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13219.7). Total num frames: 3145728. Throughput: 0: 1675.3, 1: 1671.9. Samples: 792596. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 20:44:45,557][97672] Avg episode reward: [(0, '-16.640'), (1, '-15.960')] -[2023-10-10 20:44:45,558][98439] Saving new best policy, reward=-15.960! -[2023-10-10 20:44:47,020][98560] Updated weights for policy 1, policy_version 1542 (0.0009) -[2023-10-10 20:44:47,398][98560] Updated weights for policy 1, policy_version 1552 (0.0009) -[2023-10-10 20:44:47,665][98559] Updated weights for policy 0, policy_version 1540 (0.0008) -[2023-10-10 20:44:47,760][98560] Updated weights for policy 1, policy_version 1562 (0.0007) -[2023-10-10 20:44:48,031][98559] Updated weights for policy 0, policy_version 1550 (0.0007) -[2023-10-10 20:44:48,404][98559] Updated weights for policy 0, policy_version 1560 (0.0010) -[2023-10-10 20:44:50,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13217.3). Total num frames: 3211264. Throughput: 0: 1705.0, 1: 1694.7. Samples: 813574. Policy #0 lag: (min: 17.0, avg: 28.8, max: 49.0) -[2023-10-10 20:44:50,557][97672] Avg episode reward: [(0, '-16.580'), (1, '-15.860')] -[2023-10-10 20:44:50,568][98439] Saving new best policy, reward=-15.860! -[2023-10-10 20:44:51,910][98560] Updated weights for policy 1, policy_version 1572 (0.0009) -[2023-10-10 20:44:52,309][98560] Updated weights for policy 1, policy_version 1582 (0.0007) -[2023-10-10 20:44:52,474][98559] Updated weights for policy 0, policy_version 1570 (0.0007) -[2023-10-10 20:44:52,676][98560] Updated weights for policy 1, policy_version 1592 (0.0008) -[2023-10-10 20:44:52,879][98559] Updated weights for policy 0, policy_version 1580 (0.0008) -[2023-10-10 20:44:53,243][98559] Updated weights for policy 0, policy_version 1590 (0.0009) -[2023-10-10 20:44:53,621][98559] Updated weights for policy 0, policy_version 1600 (0.0010) -[2023-10-10 20:44:55,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13215.1). Total num frames: 3276800. Throughput: 0: 1688.0, 1: 1668.5. Samples: 823260. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-10 20:44:55,557][97672] Avg episode reward: [(0, '-16.800'), (1, '-15.740')] -[2023-10-10 20:44:55,557][98439] Saving new best policy, reward=-15.740! -[2023-10-10 20:44:56,632][98560] Updated weights for policy 1, policy_version 1602 (0.0008) -[2023-10-10 20:44:57,001][98560] Updated weights for policy 1, policy_version 1612 (0.0008) -[2023-10-10 20:44:57,370][98560] Updated weights for policy 1, policy_version 1622 (0.0009) -[2023-10-10 20:44:57,587][98559] Updated weights for policy 0, policy_version 1610 (0.0011) -[2023-10-10 20:44:57,739][98560] Updated weights for policy 1, policy_version 1632 (0.0008) -[2023-10-10 20:44:57,962][98559] Updated weights for policy 0, policy_version 1620 (0.0010) -[2023-10-10 20:44:58,340][98559] Updated weights for policy 0, policy_version 1630 (0.0010) -[2023-10-10 20:45:00,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13213.0). Total num frames: 3342336. Throughput: 0: 1686.5, 1: 1687.8. Samples: 843424. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-10 20:45:00,556][97672] Avg episode reward: [(0, '-16.840'), (1, '-15.700')] -[2023-10-10 20:45:00,557][98439] Saving new best policy, reward=-15.700! -[2023-10-10 20:45:01,830][98560] Updated weights for policy 1, policy_version 1642 (0.0008) -[2023-10-10 20:45:02,200][98560] Updated weights for policy 1, policy_version 1652 (0.0008) -[2023-10-10 20:45:02,274][98559] Updated weights for policy 0, policy_version 1640 (0.0009) -[2023-10-10 20:45:02,573][98560] Updated weights for policy 1, policy_version 1662 (0.0008) -[2023-10-10 20:45:02,650][98559] Updated weights for policy 0, policy_version 1650 (0.0009) -[2023-10-10 20:45:03,029][98559] Updated weights for policy 0, policy_version 1660 (0.0011) -[2023-10-10 20:45:05,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13210.9). Total num frames: 3407872. Throughput: 0: 1700.5, 1: 1698.0. Samples: 864318. Policy #0 lag: (min: 4.0, avg: 11.8, max: 36.0) -[2023-10-10 20:45:05,557][97672] Avg episode reward: [(0, '-16.800'), (1, '-15.740')] -[2023-10-10 20:45:06,777][98560] Updated weights for policy 1, policy_version 1672 (0.0007) -[2023-10-10 20:45:07,022][98559] Updated weights for policy 0, policy_version 1670 (0.0008) -[2023-10-10 20:45:07,142][98560] Updated weights for policy 1, policy_version 1682 (0.0007) -[2023-10-10 20:45:07,396][98559] Updated weights for policy 0, policy_version 1680 (0.0008) -[2023-10-10 20:45:07,511][98560] Updated weights for policy 1, policy_version 1692 (0.0007) -[2023-10-10 20:45:07,769][98559] Updated weights for policy 0, policy_version 1690 (0.0009) -[2023-10-10 20:45:10,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13209.0). Total num frames: 3473408. Throughput: 0: 1671.1, 1: 1673.5. Samples: 873450. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:45:10,557][97672] Avg episode reward: [(0, '-16.740'), (1, '-15.700')] -[2023-10-10 20:45:11,476][98560] Updated weights for policy 1, policy_version 1702 (0.0009) -[2023-10-10 20:45:11,842][98560] Updated weights for policy 1, policy_version 1712 (0.0009) -[2023-10-10 20:45:11,895][98559] Updated weights for policy 0, policy_version 1700 (0.0008) -[2023-10-10 20:45:12,214][98560] Updated weights for policy 1, policy_version 1722 (0.0008) -[2023-10-10 20:45:12,272][98559] Updated weights for policy 0, policy_version 1710 (0.0008) -[2023-10-10 20:45:12,645][98559] Updated weights for policy 0, policy_version 1720 (0.0009) -[2023-10-10 20:45:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.1, 300 sec: 13207.1). Total num frames: 3538944. Throughput: 0: 1692.6, 1: 1700.5. Samples: 894200. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-10 20:45:15,557][97672] Avg episode reward: [(0, '-16.640'), (1, '-15.740')] -[2023-10-10 20:45:16,189][98560] Updated weights for policy 1, policy_version 1732 (0.0007) -[2023-10-10 20:45:16,565][98560] Updated weights for policy 1, policy_version 1742 (0.0008) -[2023-10-10 20:45:16,594][98559] Updated weights for policy 0, policy_version 1730 (0.0009) -[2023-10-10 20:45:16,932][98560] Updated weights for policy 1, policy_version 1752 (0.0008) -[2023-10-10 20:45:16,971][98559] Updated weights for policy 0, policy_version 1740 (0.0007) -[2023-10-10 20:45:17,335][98559] Updated weights for policy 0, policy_version 1750 (0.0008) -[2023-10-10 20:45:17,716][98559] Updated weights for policy 0, policy_version 1760 (0.0009) -[2023-10-10 20:45:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.1, 300 sec: 13205.2). Total num frames: 3604480. Throughput: 0: 1697.3, 1: 1703.3. Samples: 915186. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:45:20,557][97672] Avg episode reward: [(0, '-16.540'), (1, '-15.860')] -[2023-10-10 20:45:20,913][98560] Updated weights for policy 1, policy_version 1762 (0.0009) -[2023-10-10 20:45:21,288][98560] Updated weights for policy 1, policy_version 1772 (0.0011) -[2023-10-10 20:45:21,662][98560] Updated weights for policy 1, policy_version 1782 (0.0008) -[2023-10-10 20:45:21,845][98559] Updated weights for policy 0, policy_version 1770 (0.0008) -[2023-10-10 20:45:22,033][98560] Updated weights for policy 1, policy_version 1792 (0.0007) -[2023-10-10 20:45:22,214][98559] Updated weights for policy 0, policy_version 1780 (0.0009) -[2023-10-10 20:45:22,594][98559] Updated weights for policy 0, policy_version 1790 (0.0009) -[2023-10-10 20:45:25,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13203.5). Total num frames: 3670016. Throughput: 0: 1670.2, 1: 1688.2. Samples: 924188. Policy #0 lag: (min: 8.0, avg: 26.6, max: 40.0) -[2023-10-10 20:45:25,557][97672] Avg episode reward: [(0, '-16.500'), (1, '-15.940')] -[2023-10-10 20:45:26,047][98560] Updated weights for policy 1, policy_version 1802 (0.0007) -[2023-10-10 20:45:26,411][98560] Updated weights for policy 1, policy_version 1812 (0.0007) -[2023-10-10 20:45:26,642][98559] Updated weights for policy 0, policy_version 1800 (0.0008) -[2023-10-10 20:45:26,771][98560] Updated weights for policy 1, policy_version 1822 (0.0007) -[2023-10-10 20:45:27,019][98559] Updated weights for policy 0, policy_version 1810 (0.0010) -[2023-10-10 20:45:27,388][98559] Updated weights for policy 0, policy_version 1820 (0.0009) -[2023-10-10 20:45:30,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13201.8). Total num frames: 3735552. Throughput: 0: 1694.1, 1: 1701.0. Samples: 945376. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:45:30,557][97672] Avg episode reward: [(0, '-16.540'), (1, '-15.860')] -[2023-10-10 20:45:30,671][98560] Updated weights for policy 1, policy_version 1832 (0.0008) -[2023-10-10 20:45:31,036][98560] Updated weights for policy 1, policy_version 1842 (0.0007) -[2023-10-10 20:45:31,418][98560] Updated weights for policy 1, policy_version 1852 (0.0009) -[2023-10-10 20:45:31,479][98559] Updated weights for policy 0, policy_version 1830 (0.0009) -[2023-10-10 20:45:31,848][98559] Updated weights for policy 0, policy_version 1840 (0.0009) -[2023-10-10 20:45:32,226][98559] Updated weights for policy 0, policy_version 1850 (0.0007) -[2023-10-10 20:45:35,316][98560] Updated weights for policy 1, policy_version 1862 (0.0008) -[2023-10-10 20:45:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13200.1). Total num frames: 3801088. Throughput: 0: 1696.3, 1: 1701.1. Samples: 966456. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:45:35,557][97672] Avg episode reward: [(0, '-16.380'), (1, '-15.720')] -[2023-10-10 20:45:35,566][98385] Saving new best policy, reward=-16.380! -[2023-10-10 20:45:35,692][98560] Updated weights for policy 1, policy_version 1872 (0.0010) -[2023-10-10 20:45:36,060][98560] Updated weights for policy 1, policy_version 1882 (0.0007) -[2023-10-10 20:45:36,295][98559] Updated weights for policy 0, policy_version 1860 (0.0010) -[2023-10-10 20:45:36,666][98559] Updated weights for policy 0, policy_version 1870 (0.0008) -[2023-10-10 20:45:37,046][98559] Updated weights for policy 0, policy_version 1880 (0.0008) -[2023-10-10 20:45:40,167][98560] Updated weights for policy 1, policy_version 1892 (0.0008) -[2023-10-10 20:45:40,556][98560] Updated weights for policy 1, policy_version 1902 (0.0010) -[2023-10-10 20:45:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13198.5). Total num frames: 3866624. Throughput: 0: 1689.6, 1: 1700.0. Samples: 975794. Policy #0 lag: (min: 26.0, avg: 26.1, max: 33.0) -[2023-10-10 20:45:40,557][97672] Avg episode reward: [(0, '-16.280'), (1, '-15.620')] -[2023-10-10 20:45:40,557][98385] Saving new best policy, reward=-16.280! -[2023-10-10 20:45:40,935][98559] Updated weights for policy 0, policy_version 1890 (0.0009) -[2023-10-10 20:45:40,937][98560] Updated weights for policy 1, policy_version 1912 (0.0009) -[2023-10-10 20:45:41,228][98439] Saving new best policy, reward=-15.620! -[2023-10-10 20:45:41,306][98559] Updated weights for policy 0, policy_version 1900 (0.0007) -[2023-10-10 20:45:41,692][98559] Updated weights for policy 0, policy_version 1910 (0.0010) -[2023-10-10 20:45:42,068][98559] Updated weights for policy 0, policy_version 1920 (0.0010) -[2023-10-10 20:45:44,962][98560] Updated weights for policy 1, policy_version 1922 (0.0008) -[2023-10-10 20:45:45,345][98560] Updated weights for policy 1, policy_version 1932 (0.0009) -[2023-10-10 20:45:45,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 3932160. Throughput: 0: 1700.0, 1: 1703.4. Samples: 996576. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-10 20:45:45,556][97672] Avg episode reward: [(0, '-16.220'), (1, '-15.560')] -[2023-10-10 20:45:45,557][98385] Saving new best policy, reward=-16.220! -[2023-10-10 20:45:45,707][98560] Updated weights for policy 1, policy_version 1942 (0.0009) -[2023-10-10 20:45:46,075][98439] Saving new best policy, reward=-15.560! -[2023-10-10 20:45:46,076][98560] Updated weights for policy 1, policy_version 1952 (0.0008) -[2023-10-10 20:45:46,104][98559] Updated weights for policy 0, policy_version 1930 (0.0007) -[2023-10-10 20:45:46,476][98559] Updated weights for policy 0, policy_version 1940 (0.0008) -[2023-10-10 20:45:46,857][98559] Updated weights for policy 0, policy_version 1950 (0.0008) -[2023-10-10 20:45:50,207][98560] Updated weights for policy 1, policy_version 1962 (0.0008) -[2023-10-10 20:45:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 3997696. Throughput: 0: 1697.7, 1: 1698.8. Samples: 1017158. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:45:50,557][97672] Avg episode reward: [(0, '-15.880'), (1, '-15.520')] -[2023-10-10 20:45:50,564][98385] Saving new best policy, reward=-15.880! -[2023-10-10 20:45:50,574][98560] Updated weights for policy 1, policy_version 1972 (0.0008) -[2023-10-10 20:45:50,945][98560] Updated weights for policy 1, policy_version 1982 (0.0008) -[2023-10-10 20:45:51,019][98439] Saving new best policy, reward=-15.520! -[2023-10-10 20:45:51,062][98559] Updated weights for policy 0, policy_version 1960 (0.0009) -[2023-10-10 20:45:51,439][98559] Updated weights for policy 0, policy_version 1970 (0.0008) -[2023-10-10 20:45:51,827][98559] Updated weights for policy 0, policy_version 1980 (0.0008) -[2023-10-10 20:45:54,894][98560] Updated weights for policy 1, policy_version 1992 (0.0008) -[2023-10-10 20:45:55,259][98560] Updated weights for policy 1, policy_version 2002 (0.0009) -[2023-10-10 20:45:55,538][98559] Updated weights for policy 0, policy_version 1990 (0.0008) -[2023-10-10 20:45:55,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 4063232. Throughput: 0: 1699.1, 1: 1699.3. Samples: 1026380. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:45:55,556][97672] Avg episode reward: [(0, '-15.980'), (1, '-15.560')] -[2023-10-10 20:45:55,627][98560] Updated weights for policy 1, policy_version 2012 (0.0008) -[2023-10-10 20:45:55,911][98559] Updated weights for policy 0, policy_version 2000 (0.0008) -[2023-10-10 20:45:56,291][98559] Updated weights for policy 0, policy_version 2010 (0.0008) -[2023-10-10 20:45:59,706][98560] Updated weights for policy 1, policy_version 2022 (0.0009) -[2023-10-10 20:46:00,077][98560] Updated weights for policy 1, policy_version 2032 (0.0008) -[2023-10-10 20:46:00,401][98559] Updated weights for policy 0, policy_version 2020 (0.0010) -[2023-10-10 20:46:00,437][98560] Updated weights for policy 1, policy_version 2042 (0.0010) -[2023-10-10 20:46:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 4128768. Throughput: 0: 1702.3, 1: 1699.6. Samples: 1047284. Policy #0 lag: (min: 1.0, avg: 19.0, max: 33.0) -[2023-10-10 20:46:00,556][97672] Avg episode reward: [(0, '-16.040'), (1, '-15.500')] -[2023-10-10 20:46:00,664][98439] Saving new best policy, reward=-15.500! -[2023-10-10 20:46:00,767][98559] Updated weights for policy 0, policy_version 2030 (0.0009) -[2023-10-10 20:46:01,141][98559] Updated weights for policy 0, policy_version 2040 (0.0010) -[2023-10-10 20:46:04,420][98560] Updated weights for policy 1, policy_version 2052 (0.0008) -[2023-10-10 20:46:04,780][98560] Updated weights for policy 1, policy_version 2062 (0.0009) -[2023-10-10 20:46:05,150][98560] Updated weights for policy 1, policy_version 2072 (0.0009) -[2023-10-10 20:46:05,186][98559] Updated weights for policy 0, policy_version 2050 (0.0009) -[2023-10-10 20:46:05,547][98559] Updated weights for policy 0, policy_version 2060 (0.0008) -[2023-10-10 20:46:05,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 4227072. Throughput: 0: 1697.0, 1: 1688.4. Samples: 1067528. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) -[2023-10-10 20:46:05,557][97672] Avg episode reward: [(0, '-16.040'), (1, '-15.500')] -[2023-10-10 20:46:05,923][98559] Updated weights for policy 0, policy_version 2070 (0.0009) -[2023-10-10 20:46:06,304][98559] Updated weights for policy 0, policy_version 2080 (0.0009) -[2023-10-10 20:46:09,141][98560] Updated weights for policy 1, policy_version 2082 (0.0008) -[2023-10-10 20:46:09,502][98560] Updated weights for policy 1, policy_version 2092 (0.0011) -[2023-10-10 20:46:09,880][98560] Updated weights for policy 1, policy_version 2102 (0.0008) -[2023-10-10 20:46:10,222][98559] Updated weights for policy 0, policy_version 2090 (0.0007) -[2023-10-10 20:46:10,243][98560] Updated weights for policy 1, policy_version 2112 (0.0007) -[2023-10-10 20:46:10,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 4292608. Throughput: 0: 1705.6, 1: 1702.2. Samples: 1077540. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 20:46:10,557][97672] Avg episode reward: [(0, '-15.840'), (1, '-15.340')] -[2023-10-10 20:46:10,558][98439] Saving new best policy, reward=-15.340! -[2023-10-10 20:46:10,595][98559] Updated weights for policy 0, policy_version 2100 (0.0007) -[2023-10-10 20:46:10,970][98559] Updated weights for policy 0, policy_version 2110 (0.0009) -[2023-10-10 20:46:11,045][98385] Saving new best policy, reward=-15.840! -[2023-10-10 20:46:14,401][98560] Updated weights for policy 1, policy_version 2122 (0.0009) -[2023-10-10 20:46:14,764][98560] Updated weights for policy 1, policy_version 2132 (0.0010) -[2023-10-10 20:46:15,042][98559] Updated weights for policy 0, policy_version 2120 (0.0008) -[2023-10-10 20:46:15,131][98560] Updated weights for policy 1, policy_version 2142 (0.0008) -[2023-10-10 20:46:15,420][98559] Updated weights for policy 0, policy_version 2130 (0.0007) -[2023-10-10 20:46:15,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 4358144. Throughput: 0: 1700.0, 1: 1695.6. Samples: 1098178. Policy #0 lag: (min: 26.0, avg: 30.3, max: 58.0) -[2023-10-10 20:46:15,557][97672] Avg episode reward: [(0, '-15.580'), (1, '-15.280')] -[2023-10-10 20:46:15,559][98439] Saving new best policy, reward=-15.280! -[2023-10-10 20:46:15,798][98559] Updated weights for policy 0, policy_version 2140 (0.0007) -[2023-10-10 20:46:15,951][98385] Saving new best policy, reward=-15.580! -[2023-10-10 20:46:19,014][98560] Updated weights for policy 1, policy_version 2152 (0.0008) -[2023-10-10 20:46:19,383][98560] Updated weights for policy 1, policy_version 2162 (0.0008) -[2023-10-10 20:46:19,725][98559] Updated weights for policy 0, policy_version 2150 (0.0007) -[2023-10-10 20:46:19,757][98560] Updated weights for policy 1, policy_version 2172 (0.0008) -[2023-10-10 20:46:20,092][98559] Updated weights for policy 0, policy_version 2160 (0.0009) -[2023-10-10 20:46:20,462][98559] Updated weights for policy 0, policy_version 2170 (0.0008) -[2023-10-10 20:46:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 4423680. Throughput: 0: 1680.4, 1: 1676.9. Samples: 1117538. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:46:20,557][97672] Avg episode reward: [(0, '-15.520'), (1, '-15.400')] -[2023-10-10 20:46:20,689][98385] Saving new best policy, reward=-15.520! -[2023-10-10 20:46:23,698][98560] Updated weights for policy 1, policy_version 2182 (0.0007) -[2023-10-10 20:46:24,070][98560] Updated weights for policy 1, policy_version 2192 (0.0007) -[2023-10-10 20:46:24,438][98560] Updated weights for policy 1, policy_version 2202 (0.0009) -[2023-10-10 20:46:24,527][98559] Updated weights for policy 0, policy_version 2180 (0.0009) -[2023-10-10 20:46:24,904][98559] Updated weights for policy 0, policy_version 2190 (0.0009) -[2023-10-10 20:46:25,292][98559] Updated weights for policy 0, policy_version 2200 (0.0007) -[2023-10-10 20:46:25,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 4489216. Throughput: 0: 1698.3, 1: 1698.3. Samples: 1128644. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-10 20:46:25,557][97672] Avg episode reward: [(0, '-15.580'), (1, '-15.260')] -[2023-10-10 20:46:25,559][98439] Saving new best policy, reward=-15.260! -[2023-10-10 20:46:28,661][98560] Updated weights for policy 1, policy_version 2212 (0.0007) -[2023-10-10 20:46:29,062][98560] Updated weights for policy 1, policy_version 2222 (0.0007) -[2023-10-10 20:46:29,429][98560] Updated weights for policy 1, policy_version 2232 (0.0007) -[2023-10-10 20:46:29,572][98559] Updated weights for policy 0, policy_version 2210 (0.0009) -[2023-10-10 20:46:29,970][98559] Updated weights for policy 0, policy_version 2220 (0.0010) -[2023-10-10 20:46:30,346][98559] Updated weights for policy 0, policy_version 2230 (0.0008) -[2023-10-10 20:46:30,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 4554752. Throughput: 0: 1692.2, 1: 1694.3. Samples: 1148968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:46:30,557][97672] Avg episode reward: [(0, '-15.460'), (1, '-15.220')] -[2023-10-10 20:46:30,559][98439] Saving new best policy, reward=-15.220! -[2023-10-10 20:46:30,718][98385] Saving new best policy, reward=-15.460! -[2023-10-10 20:46:30,720][98559] Updated weights for policy 0, policy_version 2240 (0.0009) -[2023-10-10 20:46:33,244][98560] Updated weights for policy 1, policy_version 2242 (0.0009) -[2023-10-10 20:46:33,615][98560] Updated weights for policy 1, policy_version 2252 (0.0009) -[2023-10-10 20:46:33,993][98560] Updated weights for policy 1, policy_version 2262 (0.0009) -[2023-10-10 20:46:34,355][98560] Updated weights for policy 1, policy_version 2272 (0.0009) -[2023-10-10 20:46:34,568][98559] Updated weights for policy 0, policy_version 2250 (0.0009) -[2023-10-10 20:46:34,940][98559] Updated weights for policy 0, policy_version 2260 (0.0011) -[2023-10-10 20:46:35,324][98559] Updated weights for policy 0, policy_version 2270 (0.0007) -[2023-10-10 20:46:35,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 4653056. Throughput: 0: 1668.4, 1: 1676.4. Samples: 1167674. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:46:35,557][97672] Avg episode reward: [(0, '-15.340'), (1, '-15.180')] -[2023-10-10 20:46:35,566][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000002272_2326528.pth... -[2023-10-10 20:46:35,566][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000002272_2326528.pth... -[2023-10-10 20:46:35,603][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000000672_688128.pth -[2023-10-10 20:46:35,605][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000000672_688128.pth -[2023-10-10 20:46:35,609][98385] Saving new best policy, reward=-15.340! -[2023-10-10 20:46:35,609][98439] Saving new best policy, reward=-15.180! -[2023-10-10 20:46:38,349][98560] Updated weights for policy 1, policy_version 2282 (0.0009) -[2023-10-10 20:46:38,720][98560] Updated weights for policy 1, policy_version 2292 (0.0007) -[2023-10-10 20:46:39,097][98560] Updated weights for policy 1, policy_version 2302 (0.0007) -[2023-10-10 20:46:39,337][98559] Updated weights for policy 0, policy_version 2280 (0.0008) -[2023-10-10 20:46:39,709][98559] Updated weights for policy 0, policy_version 2290 (0.0010) -[2023-10-10 20:46:40,094][98559] Updated weights for policy 0, policy_version 2300 (0.0009) -[2023-10-10 20:46:40,556][97672] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 4718592. Throughput: 0: 1695.7, 1: 1707.7. Samples: 1179532. Policy #0 lag: (min: 9.0, avg: 15.0, max: 41.0) -[2023-10-10 20:46:40,557][97672] Avg episode reward: [(0, '-15.240'), (1, '-15.260')] -[2023-10-10 20:46:40,559][98385] Saving new best policy, reward=-15.240! -[2023-10-10 20:46:43,015][98560] Updated weights for policy 1, policy_version 2312 (0.0008) -[2023-10-10 20:46:43,392][98560] Updated weights for policy 1, policy_version 2322 (0.0008) -[2023-10-10 20:46:43,754][98560] Updated weights for policy 1, policy_version 2332 (0.0009) -[2023-10-10 20:46:44,253][98559] Updated weights for policy 0, policy_version 2310 (0.0008) -[2023-10-10 20:46:44,622][98559] Updated weights for policy 0, policy_version 2320 (0.0009) -[2023-10-10 20:46:45,001][98559] Updated weights for policy 0, policy_version 2330 (0.0009) -[2023-10-10 20:46:45,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 4784128. Throughput: 0: 1681.9, 1: 1690.0. Samples: 1199020. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:46:45,557][97672] Avg episode reward: [(0, '-15.280'), (1, '-15.060')] -[2023-10-10 20:46:45,559][98439] Saving new best policy, reward=-15.060! -[2023-10-10 20:46:47,640][98560] Updated weights for policy 1, policy_version 2342 (0.0009) -[2023-10-10 20:46:48,019][98560] Updated weights for policy 1, policy_version 2352 (0.0010) -[2023-10-10 20:46:48,381][98560] Updated weights for policy 1, policy_version 2362 (0.0011) -[2023-10-10 20:46:48,961][98559] Updated weights for policy 0, policy_version 2340 (0.0007) -[2023-10-10 20:46:49,342][98559] Updated weights for policy 0, policy_version 2350 (0.0008) -[2023-10-10 20:46:49,712][98559] Updated weights for policy 0, policy_version 2360 (0.0008) -[2023-10-10 20:46:50,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 4849664. Throughput: 0: 1667.4, 1: 1698.7. Samples: 1219004. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 20:46:50,557][97672] Avg episode reward: [(0, '-15.380'), (1, '-15.080')] -[2023-10-10 20:46:52,341][98560] Updated weights for policy 1, policy_version 2372 (0.0008) -[2023-10-10 20:46:52,724][98560] Updated weights for policy 1, policy_version 2382 (0.0008) -[2023-10-10 20:46:53,092][98560] Updated weights for policy 1, policy_version 2392 (0.0008) -[2023-10-10 20:46:53,856][98559] Updated weights for policy 0, policy_version 2370 (0.0009) -[2023-10-10 20:46:54,233][98559] Updated weights for policy 0, policy_version 2380 (0.0008) -[2023-10-10 20:46:54,598][98559] Updated weights for policy 0, policy_version 2390 (0.0010) -[2023-10-10 20:46:54,975][98559] Updated weights for policy 0, policy_version 2400 (0.0011) -[2023-10-10 20:46:55,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 4915200. Throughput: 0: 1691.5, 1: 1708.4. Samples: 1230532. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:46:55,557][97672] Avg episode reward: [(0, '-15.200'), (1, '-15.080')] -[2023-10-10 20:46:55,559][98385] Saving new best policy, reward=-15.200! -[2023-10-10 20:46:56,968][98560] Updated weights for policy 1, policy_version 2402 (0.0009) -[2023-10-10 20:46:57,345][98560] Updated weights for policy 1, policy_version 2412 (0.0009) -[2023-10-10 20:46:57,706][98560] Updated weights for policy 1, policy_version 2422 (0.0007) -[2023-10-10 20:46:58,077][98560] Updated weights for policy 1, policy_version 2432 (0.0009) -[2023-10-10 20:46:58,933][98559] Updated weights for policy 0, policy_version 2410 (0.0009) -[2023-10-10 20:46:59,313][98559] Updated weights for policy 0, policy_version 2420 (0.0010) -[2023-10-10 20:46:59,679][98559] Updated weights for policy 0, policy_version 2430 (0.0010) -[2023-10-10 20:47:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 4980736. Throughput: 0: 1671.7, 1: 1701.3. Samples: 1249960. Policy #0 lag: (min: 4.0, avg: 11.0, max: 36.0) -[2023-10-10 20:47:00,556][97672] Avg episode reward: [(0, '-15.060'), (1, '-14.920')] -[2023-10-10 20:47:00,557][98439] Saving new best policy, reward=-14.920! -[2023-10-10 20:47:00,557][98385] Saving new best policy, reward=-15.060! -[2023-10-10 20:47:02,026][98560] Updated weights for policy 1, policy_version 2442 (0.0007) -[2023-10-10 20:47:02,403][98560] Updated weights for policy 1, policy_version 2452 (0.0009) -[2023-10-10 20:47:02,779][98560] Updated weights for policy 1, policy_version 2462 (0.0010) -[2023-10-10 20:47:03,769][98559] Updated weights for policy 0, policy_version 2440 (0.0009) -[2023-10-10 20:47:04,149][98559] Updated weights for policy 0, policy_version 2450 (0.0010) -[2023-10-10 20:47:04,518][98559] Updated weights for policy 0, policy_version 2460 (0.0011) -[2023-10-10 20:47:05,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 5046272. Throughput: 0: 1673.6, 1: 1717.8. Samples: 1270148. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:47:05,557][97672] Avg episode reward: [(0, '-14.960'), (1, '-14.960')] -[2023-10-10 20:47:05,565][98385] Saving new best policy, reward=-14.960! -[2023-10-10 20:47:06,672][98560] Updated weights for policy 1, policy_version 2472 (0.0009) -[2023-10-10 20:47:07,051][98560] Updated weights for policy 1, policy_version 2482 (0.0009) -[2023-10-10 20:47:07,417][98560] Updated weights for policy 1, policy_version 2492 (0.0008) -[2023-10-10 20:47:08,654][98559] Updated weights for policy 0, policy_version 2470 (0.0009) -[2023-10-10 20:47:09,027][98559] Updated weights for policy 0, policy_version 2480 (0.0008) -[2023-10-10 20:47:09,408][98559] Updated weights for policy 0, policy_version 2490 (0.0008) -[2023-10-10 20:47:10,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 5111808. Throughput: 0: 1682.7, 1: 1696.8. Samples: 1280722. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-10 20:47:10,557][97672] Avg episode reward: [(0, '-14.980'), (1, '-14.960')] -[2023-10-10 20:47:11,560][98560] Updated weights for policy 1, policy_version 2502 (0.0008) -[2023-10-10 20:47:11,934][98560] Updated weights for policy 1, policy_version 2512 (0.0008) -[2023-10-10 20:47:12,306][98560] Updated weights for policy 1, policy_version 2522 (0.0008) -[2023-10-10 20:47:13,700][98559] Updated weights for policy 0, policy_version 2500 (0.0008) -[2023-10-10 20:47:14,094][98559] Updated weights for policy 0, policy_version 2510 (0.0007) -[2023-10-10 20:47:14,474][98559] Updated weights for policy 0, policy_version 2520 (0.0009) -[2023-10-10 20:47:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 5177344. Throughput: 0: 1663.2, 1: 1701.7. Samples: 1300388. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-10 20:47:15,556][97672] Avg episode reward: [(0, '-14.920'), (1, '-14.760')] -[2023-10-10 20:47:15,557][98385] Saving new best policy, reward=-14.920! -[2023-10-10 20:47:15,557][98439] Saving new best policy, reward=-14.760! -[2023-10-10 20:47:16,401][98560] Updated weights for policy 1, policy_version 2532 (0.0009) -[2023-10-10 20:47:16,801][98560] Updated weights for policy 1, policy_version 2542 (0.0008) -[2023-10-10 20:47:17,171][98560] Updated weights for policy 1, policy_version 2552 (0.0008) -[2023-10-10 20:47:18,363][98559] Updated weights for policy 0, policy_version 2530 (0.0010) -[2023-10-10 20:47:18,725][98559] Updated weights for policy 0, policy_version 2540 (0.0007) -[2023-10-10 20:47:19,101][98559] Updated weights for policy 0, policy_version 2550 (0.0007) -[2023-10-10 20:47:19,477][98559] Updated weights for policy 0, policy_version 2560 (0.0007) -[2023-10-10 20:47:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 5242880. Throughput: 0: 1681.4, 1: 1717.6. Samples: 1320628. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:47:20,557][97672] Avg episode reward: [(0, '-14.920'), (1, '-14.860')] -[2023-10-10 20:47:21,245][98560] Updated weights for policy 1, policy_version 2562 (0.0007) -[2023-10-10 20:47:21,615][98560] Updated weights for policy 1, policy_version 2572 (0.0011) -[2023-10-10 20:47:21,991][98560] Updated weights for policy 1, policy_version 2582 (0.0011) -[2023-10-10 20:47:22,355][98560] Updated weights for policy 1, policy_version 2592 (0.0011) -[2023-10-10 20:47:23,641][98559] Updated weights for policy 0, policy_version 2570 (0.0009) -[2023-10-10 20:47:24,015][98559] Updated weights for policy 0, policy_version 2580 (0.0008) -[2023-10-10 20:47:24,381][98559] Updated weights for policy 0, policy_version 2590 (0.0009) -[2023-10-10 20:47:25,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 5308416. Throughput: 0: 1675.9, 1: 1685.5. Samples: 1330792. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-10 20:47:25,557][97672] Avg episode reward: [(0, '-14.900'), (1, '-14.860')] -[2023-10-10 20:47:25,558][98385] Saving new best policy, reward=-14.900! -[2023-10-10 20:47:26,273][98560] Updated weights for policy 1, policy_version 2602 (0.0007) -[2023-10-10 20:47:26,632][98560] Updated weights for policy 1, policy_version 2612 (0.0007) -[2023-10-10 20:47:26,998][98560] Updated weights for policy 1, policy_version 2622 (0.0008) -[2023-10-10 20:47:28,333][98559] Updated weights for policy 0, policy_version 2600 (0.0008) -[2023-10-10 20:47:28,704][98559] Updated weights for policy 0, policy_version 2610 (0.0008) -[2023-10-10 20:47:29,079][98559] Updated weights for policy 0, policy_version 2620 (0.0008) -[2023-10-10 20:47:30,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 5373952. Throughput: 0: 1661.7, 1: 1714.1. Samples: 1350932. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:47:30,556][97672] Avg episode reward: [(0, '-14.880'), (1, '-14.840')] -[2023-10-10 20:47:30,557][98385] Saving new best policy, reward=-14.880! -[2023-10-10 20:47:30,979][98560] Updated weights for policy 1, policy_version 2632 (0.0010) -[2023-10-10 20:47:31,350][98560] Updated weights for policy 1, policy_version 2642 (0.0011) -[2023-10-10 20:47:31,717][98560] Updated weights for policy 1, policy_version 2652 (0.0008) -[2023-10-10 20:47:33,118][98559] Updated weights for policy 0, policy_version 2630 (0.0008) -[2023-10-10 20:47:33,500][98559] Updated weights for policy 0, policy_version 2640 (0.0007) -[2023-10-10 20:47:33,879][98559] Updated weights for policy 0, policy_version 2650 (0.0008) -[2023-10-10 20:47:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 5439488. Throughput: 0: 1681.3, 1: 1715.5. Samples: 1371860. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:47:35,557][97672] Avg episode reward: [(0, '-14.860'), (1, '-14.900')] -[2023-10-10 20:47:35,569][98385] Saving new best policy, reward=-14.860! -[2023-10-10 20:47:35,655][98560] Updated weights for policy 1, policy_version 2662 (0.0009) -[2023-10-10 20:47:36,021][98560] Updated weights for policy 1, policy_version 2672 (0.0009) -[2023-10-10 20:47:36,401][98560] Updated weights for policy 1, policy_version 2682 (0.0010) -[2023-10-10 20:47:37,945][98559] Updated weights for policy 0, policy_version 2660 (0.0008) -[2023-10-10 20:47:38,318][98559] Updated weights for policy 0, policy_version 2670 (0.0009) -[2023-10-10 20:47:38,692][98559] Updated weights for policy 0, policy_version 2680 (0.0010) -[2023-10-10 20:47:40,376][98560] Updated weights for policy 1, policy_version 2692 (0.0008) -[2023-10-10 20:47:40,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 5505024. Throughput: 0: 1666.1, 1: 1692.3. Samples: 1381660. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-10 20:47:40,557][97672] Avg episode reward: [(0, '-14.820'), (1, '-14.780')] -[2023-10-10 20:47:40,558][98385] Saving new best policy, reward=-14.820! -[2023-10-10 20:47:40,740][98560] Updated weights for policy 1, policy_version 2702 (0.0009) -[2023-10-10 20:47:41,116][98560] Updated weights for policy 1, policy_version 2712 (0.0009) -[2023-10-10 20:47:42,775][98559] Updated weights for policy 0, policy_version 2690 (0.0009) -[2023-10-10 20:47:43,146][98559] Updated weights for policy 0, policy_version 2700 (0.0008) -[2023-10-10 20:47:43,523][98559] Updated weights for policy 0, policy_version 2710 (0.0009) -[2023-10-10 20:47:43,892][98559] Updated weights for policy 0, policy_version 2720 (0.0008) -[2023-10-10 20:47:45,097][98560] Updated weights for policy 1, policy_version 2722 (0.0009) -[2023-10-10 20:47:45,473][98560] Updated weights for policy 1, policy_version 2732 (0.0011) -[2023-10-10 20:47:45,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 5570560. Throughput: 0: 1670.7, 1: 1707.9. Samples: 1401994. Policy #0 lag: (min: 14.0, avg: 19.7, max: 46.0) -[2023-10-10 20:47:45,556][97672] Avg episode reward: [(0, '-14.800'), (1, '-15.040')] -[2023-10-10 20:47:45,557][98385] Saving new best policy, reward=-14.800! -[2023-10-10 20:47:45,846][98560] Updated weights for policy 1, policy_version 2742 (0.0010) -[2023-10-10 20:47:46,204][98560] Updated weights for policy 1, policy_version 2752 (0.0011) -[2023-10-10 20:47:47,858][98559] Updated weights for policy 0, policy_version 2730 (0.0008) -[2023-10-10 20:47:48,228][98559] Updated weights for policy 0, policy_version 2740 (0.0010) -[2023-10-10 20:47:48,605][98559] Updated weights for policy 0, policy_version 2750 (0.0011) -[2023-10-10 20:47:50,291][98560] Updated weights for policy 1, policy_version 2762 (0.0009) -[2023-10-10 20:47:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 5636096. Throughput: 0: 1688.5, 1: 1709.1. Samples: 1423044. Policy #0 lag: (min: 15.0, avg: 15.2, max: 25.0) -[2023-10-10 20:47:50,557][97672] Avg episode reward: [(0, '-14.920'), (1, '-15.060')] -[2023-10-10 20:47:50,657][98560] Updated weights for policy 1, policy_version 2772 (0.0008) -[2023-10-10 20:47:51,031][98560] Updated weights for policy 1, policy_version 2782 (0.0009) -[2023-10-10 20:47:52,635][98559] Updated weights for policy 0, policy_version 2760 (0.0007) -[2023-10-10 20:47:53,007][98559] Updated weights for policy 0, policy_version 2770 (0.0008) -[2023-10-10 20:47:53,378][98559] Updated weights for policy 0, policy_version 2780 (0.0007) -[2023-10-10 20:47:55,208][98560] Updated weights for policy 1, policy_version 2792 (0.0007) -[2023-10-10 20:47:55,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 5701632. Throughput: 0: 1667.9, 1: 1702.1. Samples: 1432372. Policy #0 lag: (min: 25.0, avg: 27.1, max: 56.0) -[2023-10-10 20:47:55,556][97672] Avg episode reward: [(0, '-14.820'), (1, '-15.100')] -[2023-10-10 20:47:55,589][98560] Updated weights for policy 1, policy_version 2802 (0.0007) -[2023-10-10 20:47:55,958][98560] Updated weights for policy 1, policy_version 2812 (0.0008) -[2023-10-10 20:47:57,366][98559] Updated weights for policy 0, policy_version 2790 (0.0007) -[2023-10-10 20:47:57,735][98559] Updated weights for policy 0, policy_version 2800 (0.0007) -[2023-10-10 20:47:58,120][98559] Updated weights for policy 0, policy_version 2810 (0.0009) -[2023-10-10 20:47:59,902][98560] Updated weights for policy 1, policy_version 2822 (0.0009) -[2023-10-10 20:48:00,269][98560] Updated weights for policy 1, policy_version 2832 (0.0008) -[2023-10-10 20:48:00,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 5767168. Throughput: 0: 1687.5, 1: 1706.4. Samples: 1453112. Policy #0 lag: (min: 19.0, avg: 19.9, max: 39.0) -[2023-10-10 20:48:00,557][97672] Avg episode reward: [(0, '-14.800'), (1, '-15.080')] -[2023-10-10 20:48:00,634][98560] Updated weights for policy 1, policy_version 2842 (0.0008) -[2023-10-10 20:48:02,249][98559] Updated weights for policy 0, policy_version 2820 (0.0010) -[2023-10-10 20:48:02,641][98559] Updated weights for policy 0, policy_version 2830 (0.0010) -[2023-10-10 20:48:03,016][98559] Updated weights for policy 0, policy_version 2840 (0.0007) -[2023-10-10 20:48:04,630][98560] Updated weights for policy 1, policy_version 2852 (0.0009) -[2023-10-10 20:48:05,029][98560] Updated weights for policy 1, policy_version 2862 (0.0010) -[2023-10-10 20:48:05,405][98560] Updated weights for policy 1, policy_version 2872 (0.0011) -[2023-10-10 20:48:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 5832704. Throughput: 0: 1698.1, 1: 1709.2. Samples: 1473956. Policy #0 lag: (min: 31.0, avg: 41.9, max: 63.0) -[2023-10-10 20:48:05,556][97672] Avg episode reward: [(0, '-14.820'), (1, '-15.080')] -[2023-10-10 20:48:06,841][98559] Updated weights for policy 0, policy_version 2850 (0.0009) -[2023-10-10 20:48:07,210][98559] Updated weights for policy 0, policy_version 2860 (0.0007) -[2023-10-10 20:48:07,589][98559] Updated weights for policy 0, policy_version 2870 (0.0008) -[2023-10-10 20:48:07,956][98559] Updated weights for policy 0, policy_version 2880 (0.0008) -[2023-10-10 20:48:09,361][98560] Updated weights for policy 1, policy_version 2882 (0.0008) -[2023-10-10 20:48:09,726][98560] Updated weights for policy 1, policy_version 2892 (0.0010) -[2023-10-10 20:48:10,094][98560] Updated weights for policy 1, policy_version 2902 (0.0009) -[2023-10-10 20:48:10,459][98560] Updated weights for policy 1, policy_version 2912 (0.0009) -[2023-10-10 20:48:10,556][97672] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 5931008. Throughput: 0: 1679.5, 1: 1715.4. Samples: 1483562. Policy #0 lag: (min: 31.0, avg: 41.9, max: 63.0) -[2023-10-10 20:48:10,557][97672] Avg episode reward: [(0, '-14.900'), (1, '-15.140')] -[2023-10-10 20:48:11,853][98559] Updated weights for policy 0, policy_version 2890 (0.0010) -[2023-10-10 20:48:12,225][98559] Updated weights for policy 0, policy_version 2900 (0.0008) -[2023-10-10 20:48:12,596][98559] Updated weights for policy 0, policy_version 2910 (0.0007) -[2023-10-10 20:48:14,447][98560] Updated weights for policy 1, policy_version 2922 (0.0010) -[2023-10-10 20:48:14,816][98560] Updated weights for policy 1, policy_version 2932 (0.0009) -[2023-10-10 20:48:15,180][98560] Updated weights for policy 1, policy_version 2942 (0.0010) -[2023-10-10 20:48:15,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 5996544. Throughput: 0: 1708.7, 1: 1705.1. Samples: 1504552. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-10 20:48:15,557][97672] Avg episode reward: [(0, '-14.640'), (1, '-15.120')] -[2023-10-10 20:48:15,557][98385] Saving new best policy, reward=-14.640! -[2023-10-10 20:48:16,550][98559] Updated weights for policy 0, policy_version 2920 (0.0008) -[2023-10-10 20:48:16,927][98559] Updated weights for policy 0, policy_version 2930 (0.0008) -[2023-10-10 20:48:17,301][98559] Updated weights for policy 0, policy_version 2940 (0.0007) -[2023-10-10 20:48:19,221][98560] Updated weights for policy 1, policy_version 2952 (0.0007) -[2023-10-10 20:48:19,604][98560] Updated weights for policy 1, policy_version 2962 (0.0008) -[2023-10-10 20:48:19,972][98560] Updated weights for policy 1, policy_version 2972 (0.0008) -[2023-10-10 20:48:20,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 6062080. Throughput: 0: 1713.8, 1: 1687.8. Samples: 1524932. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-10 20:48:20,557][97672] Avg episode reward: [(0, '-14.640'), (1, '-15.320')] -[2023-10-10 20:48:21,297][98559] Updated weights for policy 0, policy_version 2950 (0.0010) -[2023-10-10 20:48:21,672][98559] Updated weights for policy 0, policy_version 2960 (0.0010) -[2023-10-10 20:48:22,046][98559] Updated weights for policy 0, policy_version 2970 (0.0007) -[2023-10-10 20:48:24,017][98560] Updated weights for policy 1, policy_version 2982 (0.0009) -[2023-10-10 20:48:24,387][98560] Updated weights for policy 1, policy_version 2992 (0.0010) -[2023-10-10 20:48:24,749][98560] Updated weights for policy 1, policy_version 3002 (0.0009) -[2023-10-10 20:48:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 6127616. Throughput: 0: 1698.6, 1: 1707.6. Samples: 1534942. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) -[2023-10-10 20:48:25,557][97672] Avg episode reward: [(0, '-14.520'), (1, '-15.160')] -[2023-10-10 20:48:25,558][98385] Saving new best policy, reward=-14.520! -[2023-10-10 20:48:25,931][98559] Updated weights for policy 0, policy_version 2980 (0.0008) -[2023-10-10 20:48:26,306][98559] Updated weights for policy 0, policy_version 2990 (0.0008) -[2023-10-10 20:48:26,682][98559] Updated weights for policy 0, policy_version 3000 (0.0008) -[2023-10-10 20:48:28,885][98560] Updated weights for policy 1, policy_version 3012 (0.0009) -[2023-10-10 20:48:29,262][98560] Updated weights for policy 1, policy_version 3022 (0.0008) -[2023-10-10 20:48:29,623][98560] Updated weights for policy 1, policy_version 3032 (0.0008) -[2023-10-10 20:48:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 6193152. Throughput: 0: 1714.6, 1: 1701.6. Samples: 1555724. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) -[2023-10-10 20:48:30,557][97672] Avg episode reward: [(0, '-14.500'), (1, '-15.180')] -[2023-10-10 20:48:30,714][98559] Updated weights for policy 0, policy_version 3010 (0.0008) -[2023-10-10 20:48:31,086][98559] Updated weights for policy 0, policy_version 3020 (0.0009) -[2023-10-10 20:48:31,470][98559] Updated weights for policy 0, policy_version 3030 (0.0009) -[2023-10-10 20:48:31,847][98385] Saving new best policy, reward=-14.500! -[2023-10-10 20:48:31,849][98559] Updated weights for policy 0, policy_version 3040 (0.0008) -[2023-10-10 20:48:33,856][98560] Updated weights for policy 1, policy_version 3042 (0.0008) -[2023-10-10 20:48:34,224][98560] Updated weights for policy 1, policy_version 3052 (0.0008) -[2023-10-10 20:48:34,599][98560] Updated weights for policy 1, policy_version 3062 (0.0008) -[2023-10-10 20:48:34,968][98560] Updated weights for policy 1, policy_version 3072 (0.0010) -[2023-10-10 20:48:35,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 6258688. Throughput: 0: 1712.2, 1: 1675.0. Samples: 1575468. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:48:35,557][97672] Avg episode reward: [(0, '-14.620'), (1, '-15.180')] -[2023-10-10 20:48:35,568][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000003072_3145728.pth... -[2023-10-10 20:48:35,605][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000001472_1507328.pth -[2023-10-10 20:48:35,933][98559] Updated weights for policy 0, policy_version 3050 (0.0007) -[2023-10-10 20:48:36,314][98559] Updated weights for policy 0, policy_version 3060 (0.0007) -[2023-10-10 20:48:36,686][98559] Updated weights for policy 0, policy_version 3070 (0.0007) -[2023-10-10 20:48:36,759][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000003072_3145728.pth... -[2023-10-10 20:48:36,799][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000001472_1507328.pth -[2023-10-10 20:48:38,945][98560] Updated weights for policy 1, policy_version 3082 (0.0009) -[2023-10-10 20:48:39,313][98560] Updated weights for policy 1, policy_version 3092 (0.0009) -[2023-10-10 20:48:39,684][98560] Updated weights for policy 1, policy_version 3102 (0.0009) -[2023-10-10 20:48:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 6324224. Throughput: 0: 1704.9, 1: 1699.2. Samples: 1585556. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:48:40,557][97672] Avg episode reward: [(0, '-14.480'), (1, '-15.100')] -[2023-10-10 20:48:40,722][98559] Updated weights for policy 0, policy_version 3080 (0.0008) -[2023-10-10 20:48:41,108][98559] Updated weights for policy 0, policy_version 3090 (0.0007) -[2023-10-10 20:48:41,476][98559] Updated weights for policy 0, policy_version 3100 (0.0007) -[2023-10-10 20:48:41,625][98385] Saving new best policy, reward=-14.480! -[2023-10-10 20:48:43,685][98560] Updated weights for policy 1, policy_version 3112 (0.0010) -[2023-10-10 20:48:44,057][98560] Updated weights for policy 1, policy_version 3122 (0.0008) -[2023-10-10 20:48:44,427][98560] Updated weights for policy 1, policy_version 3132 (0.0009) -[2023-10-10 20:48:45,456][98559] Updated weights for policy 0, policy_version 3110 (0.0008) -[2023-10-10 20:48:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 6389760. Throughput: 0: 1710.1, 1: 1691.9. Samples: 1606202. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-10 20:48:45,556][97672] Avg episode reward: [(0, '-14.460'), (1, '-15.180')] -[2023-10-10 20:48:45,827][98559] Updated weights for policy 0, policy_version 3120 (0.0007) -[2023-10-10 20:48:46,200][98559] Updated weights for policy 0, policy_version 3130 (0.0007) -[2023-10-10 20:48:46,427][98385] Saving new best policy, reward=-14.460! -[2023-10-10 20:48:48,328][98560] Updated weights for policy 1, policy_version 3142 (0.0008) -[2023-10-10 20:48:48,700][98560] Updated weights for policy 1, policy_version 3152 (0.0008) -[2023-10-10 20:48:49,077][98560] Updated weights for policy 1, policy_version 3162 (0.0009) -[2023-10-10 20:48:50,263][98559] Updated weights for policy 0, policy_version 3140 (0.0009) -[2023-10-10 20:48:50,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 6455296. Throughput: 0: 1702.6, 1: 1672.3. Samples: 1625830. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:48:50,557][97672] Avg episode reward: [(0, '-14.460'), (1, '-15.240')] -[2023-10-10 20:48:50,655][98559] Updated weights for policy 0, policy_version 3150 (0.0010) -[2023-10-10 20:48:51,035][98559] Updated weights for policy 0, policy_version 3160 (0.0010) -[2023-10-10 20:48:53,187][98560] Updated weights for policy 1, policy_version 3172 (0.0010) -[2023-10-10 20:48:53,593][98560] Updated weights for policy 1, policy_version 3182 (0.0010) -[2023-10-10 20:48:53,964][98560] Updated weights for policy 1, policy_version 3192 (0.0009) -[2023-10-10 20:48:55,099][98559] Updated weights for policy 0, policy_version 3170 (0.0009) -[2023-10-10 20:48:55,475][98559] Updated weights for policy 0, policy_version 3180 (0.0011) -[2023-10-10 20:48:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 6520832. Throughput: 0: 1704.1, 1: 1695.9. Samples: 1636562. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:48:55,556][97672] Avg episode reward: [(0, '-14.540'), (1, '-15.080')] -[2023-10-10 20:48:55,849][98559] Updated weights for policy 0, policy_version 3190 (0.0010) -[2023-10-10 20:48:56,220][98559] Updated weights for policy 0, policy_version 3200 (0.0010) -[2023-10-10 20:48:57,859][98560] Updated weights for policy 1, policy_version 3202 (0.0009) -[2023-10-10 20:48:58,227][98560] Updated weights for policy 1, policy_version 3212 (0.0009) -[2023-10-10 20:48:58,599][98560] Updated weights for policy 1, policy_version 3222 (0.0009) -[2023-10-10 20:48:58,967][98560] Updated weights for policy 1, policy_version 3232 (0.0009) -[2023-10-10 20:49:00,283][98559] Updated weights for policy 0, policy_version 3210 (0.0008) -[2023-10-10 20:49:00,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 6586368. Throughput: 0: 1699.4, 1: 1674.5. Samples: 1656378. Policy #0 lag: (min: 29.0, avg: 35.7, max: 61.0) -[2023-10-10 20:49:00,556][97672] Avg episode reward: [(0, '-14.540'), (1, '-15.160')] -[2023-10-10 20:49:00,666][98559] Updated weights for policy 0, policy_version 3220 (0.0010) -[2023-10-10 20:49:01,024][98559] Updated weights for policy 0, policy_version 3230 (0.0009) -[2023-10-10 20:49:02,897][98560] Updated weights for policy 1, policy_version 3242 (0.0009) -[2023-10-10 20:49:03,274][98560] Updated weights for policy 1, policy_version 3252 (0.0009) -[2023-10-10 20:49:03,637][98560] Updated weights for policy 1, policy_version 3262 (0.0009) -[2023-10-10 20:49:05,035][98559] Updated weights for policy 0, policy_version 3240 (0.0010) -[2023-10-10 20:49:05,414][98559] Updated weights for policy 0, policy_version 3250 (0.0010) -[2023-10-10 20:49:05,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 6651904. Throughput: 0: 1681.2, 1: 1683.8. Samples: 1676356. Policy #0 lag: (min: 29.0, avg: 35.7, max: 61.0) -[2023-10-10 20:49:05,557][97672] Avg episode reward: [(0, '-14.460'), (1, '-15.140')] -[2023-10-10 20:49:05,793][98559] Updated weights for policy 0, policy_version 3260 (0.0008) -[2023-10-10 20:49:07,641][98560] Updated weights for policy 1, policy_version 3272 (0.0008) -[2023-10-10 20:49:08,006][98560] Updated weights for policy 1, policy_version 3282 (0.0008) -[2023-10-10 20:49:08,383][98560] Updated weights for policy 1, policy_version 3292 (0.0007) -[2023-10-10 20:49:09,858][98559] Updated weights for policy 0, policy_version 3270 (0.0009) -[2023-10-10 20:49:10,230][98559] Updated weights for policy 0, policy_version 3280 (0.0010) -[2023-10-10 20:49:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 6717440. Throughput: 0: 1694.1, 1: 1690.6. Samples: 1687252. Policy #0 lag: (min: 19.0, avg: 25.0, max: 51.0) -[2023-10-10 20:49:10,557][97672] Avg episode reward: [(0, '-14.560'), (1, '-14.880')] -[2023-10-10 20:49:10,618][98559] Updated weights for policy 0, policy_version 3290 (0.0007) -[2023-10-10 20:49:12,502][98560] Updated weights for policy 1, policy_version 3302 (0.0009) -[2023-10-10 20:49:12,873][98560] Updated weights for policy 1, policy_version 3312 (0.0010) -[2023-10-10 20:49:13,243][98560] Updated weights for policy 1, policy_version 3322 (0.0009) -[2023-10-10 20:49:14,702][98559] Updated weights for policy 0, policy_version 3300 (0.0008) -[2023-10-10 20:49:15,077][98559] Updated weights for policy 0, policy_version 3310 (0.0008) -[2023-10-10 20:49:15,450][98559] Updated weights for policy 0, policy_version 3320 (0.0008) -[2023-10-10 20:49:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 6782976. Throughput: 0: 1694.6, 1: 1669.8. Samples: 1707122. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:49:15,557][97672] Avg episode reward: [(0, '-14.660'), (1, '-14.880')] -[2023-10-10 20:49:17,154][98560] Updated weights for policy 1, policy_version 3332 (0.0009) -[2023-10-10 20:49:17,532][98560] Updated weights for policy 1, policy_version 3342 (0.0007) -[2023-10-10 20:49:17,904][98560] Updated weights for policy 1, policy_version 3352 (0.0008) -[2023-10-10 20:49:19,314][98559] Updated weights for policy 0, policy_version 3330 (0.0008) -[2023-10-10 20:49:19,690][98559] Updated weights for policy 0, policy_version 3340 (0.0008) -[2023-10-10 20:49:20,065][98559] Updated weights for policy 0, policy_version 3350 (0.0009) -[2023-10-10 20:49:20,445][98559] Updated weights for policy 0, policy_version 3360 (0.0011) -[2023-10-10 20:49:20,556][97672] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 6881280. Throughput: 0: 1670.1, 1: 1698.9. Samples: 1727072. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:49:20,556][97672] Avg episode reward: [(0, '-14.700'), (1, '-14.700')] -[2023-10-10 20:49:20,569][98439] Saving new best policy, reward=-14.700! -[2023-10-10 20:49:22,020][98560] Updated weights for policy 1, policy_version 3362 (0.0009) -[2023-10-10 20:49:22,388][98560] Updated weights for policy 1, policy_version 3372 (0.0008) -[2023-10-10 20:49:22,763][98560] Updated weights for policy 1, policy_version 3382 (0.0007) -[2023-10-10 20:49:23,135][98560] Updated weights for policy 1, policy_version 3392 (0.0008) -[2023-10-10 20:49:24,418][98559] Updated weights for policy 0, policy_version 3370 (0.0010) -[2023-10-10 20:49:24,799][98559] Updated weights for policy 0, policy_version 3380 (0.0010) -[2023-10-10 20:49:25,179][98559] Updated weights for policy 0, policy_version 3390 (0.0008) -[2023-10-10 20:49:25,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 6946816. Throughput: 0: 1697.0, 1: 1687.5. Samples: 1737860. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:49:25,557][97672] Avg episode reward: [(0, '-14.720'), (1, '-14.700')] -[2023-10-10 20:49:27,275][98560] Updated weights for policy 1, policy_version 3402 (0.0008) -[2023-10-10 20:49:27,639][98560] Updated weights for policy 1, policy_version 3412 (0.0008) -[2023-10-10 20:49:28,017][98560] Updated weights for policy 1, policy_version 3422 (0.0009) -[2023-10-10 20:49:29,164][98559] Updated weights for policy 0, policy_version 3400 (0.0008) -[2023-10-10 20:49:29,538][98559] Updated weights for policy 0, policy_version 3410 (0.0009) -[2023-10-10 20:49:29,910][98559] Updated weights for policy 0, policy_version 3420 (0.0008) -[2023-10-10 20:49:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 7012352. Throughput: 0: 1688.6, 1: 1678.8. Samples: 1757738. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:49:30,556][97672] Avg episode reward: [(0, '-14.560'), (1, '-14.740')] -[2023-10-10 20:49:31,968][98560] Updated weights for policy 1, policy_version 3432 (0.0007) -[2023-10-10 20:49:32,341][98560] Updated weights for policy 1, policy_version 3442 (0.0007) -[2023-10-10 20:49:32,699][98560] Updated weights for policy 1, policy_version 3452 (0.0007) -[2023-10-10 20:49:33,934][98559] Updated weights for policy 0, policy_version 3430 (0.0008) -[2023-10-10 20:49:34,314][98559] Updated weights for policy 0, policy_version 3440 (0.0009) -[2023-10-10 20:49:34,690][98559] Updated weights for policy 0, policy_version 3450 (0.0010) -[2023-10-10 20:49:35,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 7077888. Throughput: 0: 1677.8, 1: 1698.6. Samples: 1777768. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:49:35,556][97672] Avg episode reward: [(0, '-14.600'), (1, '-14.760')] -[2023-10-10 20:49:36,672][98560] Updated weights for policy 1, policy_version 3462 (0.0007) -[2023-10-10 20:49:37,055][98560] Updated weights for policy 1, policy_version 3472 (0.0007) -[2023-10-10 20:49:37,413][98560] Updated weights for policy 1, policy_version 3482 (0.0007) -[2023-10-10 20:49:38,685][98559] Updated weights for policy 0, policy_version 3460 (0.0009) -[2023-10-10 20:49:39,076][98559] Updated weights for policy 0, policy_version 3470 (0.0007) -[2023-10-10 20:49:39,457][98559] Updated weights for policy 0, policy_version 3480 (0.0012) -[2023-10-10 20:49:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 7143424. Throughput: 0: 1707.8, 1: 1671.1. Samples: 1788612. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 20:49:40,556][97672] Avg episode reward: [(0, '-14.560'), (1, '-14.780')] -[2023-10-10 20:49:41,503][98560] Updated weights for policy 1, policy_version 3492 (0.0007) -[2023-10-10 20:49:41,874][98560] Updated weights for policy 1, policy_version 3502 (0.0007) -[2023-10-10 20:49:42,245][98560] Updated weights for policy 1, policy_version 3512 (0.0009) -[2023-10-10 20:49:43,379][98559] Updated weights for policy 0, policy_version 3490 (0.0010) -[2023-10-10 20:49:43,754][98559] Updated weights for policy 0, policy_version 3500 (0.0007) -[2023-10-10 20:49:44,125][98559] Updated weights for policy 0, policy_version 3510 (0.0007) -[2023-10-10 20:49:44,502][98559] Updated weights for policy 0, policy_version 3520 (0.0008) -[2023-10-10 20:49:45,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 7208960. Throughput: 0: 1685.4, 1: 1697.0. Samples: 1808586. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-10 20:49:45,556][97672] Avg episode reward: [(0, '-14.500'), (1, '-14.800')] -[2023-10-10 20:49:46,261][98560] Updated weights for policy 1, policy_version 3522 (0.0008) -[2023-10-10 20:49:46,667][98560] Updated weights for policy 1, policy_version 3532 (0.0010) -[2023-10-10 20:49:47,030][98560] Updated weights for policy 1, policy_version 3542 (0.0010) -[2023-10-10 20:49:47,403][98560] Updated weights for policy 1, policy_version 3552 (0.0010) -[2023-10-10 20:49:48,609][98559] Updated weights for policy 0, policy_version 3530 (0.0009) -[2023-10-10 20:49:48,994][98559] Updated weights for policy 0, policy_version 3540 (0.0008) -[2023-10-10 20:49:49,372][98559] Updated weights for policy 0, policy_version 3550 (0.0009) -[2023-10-10 20:49:50,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 7274496. Throughput: 0: 1692.7, 1: 1701.2. Samples: 1829080. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-10 20:49:50,557][97672] Avg episode reward: [(0, '-14.540'), (1, '-14.420')] -[2023-10-10 20:49:50,564][98439] Saving new best policy, reward=-14.420! -[2023-10-10 20:49:51,437][98560] Updated weights for policy 1, policy_version 3562 (0.0010) -[2023-10-10 20:49:51,807][98560] Updated weights for policy 1, policy_version 3572 (0.0011) -[2023-10-10 20:49:52,186][98560] Updated weights for policy 1, policy_version 3582 (0.0010) -[2023-10-10 20:49:53,352][98559] Updated weights for policy 0, policy_version 3560 (0.0010) -[2023-10-10 20:49:53,726][98559] Updated weights for policy 0, policy_version 3570 (0.0010) -[2023-10-10 20:49:54,106][98559] Updated weights for policy 0, policy_version 3580 (0.0009) -[2023-10-10 20:49:55,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 7340032. Throughput: 0: 1702.0, 1: 1676.3. Samples: 1839278. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-10 20:49:55,556][97672] Avg episode reward: [(0, '-14.500'), (1, '-14.140')] -[2023-10-10 20:49:55,557][98439] Saving new best policy, reward=-14.140! -[2023-10-10 20:49:56,084][98560] Updated weights for policy 1, policy_version 3592 (0.0008) -[2023-10-10 20:49:56,453][98560] Updated weights for policy 1, policy_version 3602 (0.0008) -[2023-10-10 20:49:56,831][98560] Updated weights for policy 1, policy_version 3612 (0.0008) -[2023-10-10 20:49:58,092][98559] Updated weights for policy 0, policy_version 3590 (0.0008) -[2023-10-10 20:49:58,455][98559] Updated weights for policy 0, policy_version 3600 (0.0008) -[2023-10-10 20:49:58,826][98559] Updated weights for policy 0, policy_version 3610 (0.0010) -[2023-10-10 20:50:00,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 7405568. Throughput: 0: 1680.7, 1: 1702.3. Samples: 1859354. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-10 20:50:00,557][97672] Avg episode reward: [(0, '-14.340'), (1, '-13.980')] -[2023-10-10 20:50:00,559][98385] Saving new best policy, reward=-14.340! -[2023-10-10 20:50:00,559][98439] Saving new best policy, reward=-13.980! -[2023-10-10 20:50:01,029][98560] Updated weights for policy 1, policy_version 3622 (0.0007) -[2023-10-10 20:50:01,400][98560] Updated weights for policy 1, policy_version 3632 (0.0007) -[2023-10-10 20:50:01,778][98560] Updated weights for policy 1, policy_version 3642 (0.0010) -[2023-10-10 20:50:02,864][98559] Updated weights for policy 0, policy_version 3620 (0.0010) -[2023-10-10 20:50:03,242][98559] Updated weights for policy 0, policy_version 3630 (0.0007) -[2023-10-10 20:50:03,624][98559] Updated weights for policy 0, policy_version 3640 (0.0009) -[2023-10-10 20:50:05,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 7471104. Throughput: 0: 1706.2, 1: 1699.4. Samples: 1880322. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-10-10 20:50:05,557][97672] Avg episode reward: [(0, '-14.320'), (1, '-13.740')] -[2023-10-10 20:50:05,567][98439] Saving new best policy, reward=-13.740! -[2023-10-10 20:50:05,567][98385] Saving new best policy, reward=-14.320! -[2023-10-10 20:50:05,852][98560] Updated weights for policy 1, policy_version 3652 (0.0007) -[2023-10-10 20:50:06,217][98560] Updated weights for policy 1, policy_version 3662 (0.0009) -[2023-10-10 20:50:06,597][98560] Updated weights for policy 1, policy_version 3672 (0.0008) -[2023-10-10 20:50:07,675][98559] Updated weights for policy 0, policy_version 3650 (0.0009) -[2023-10-10 20:50:08,044][98559] Updated weights for policy 0, policy_version 3660 (0.0010) -[2023-10-10 20:50:08,416][98559] Updated weights for policy 0, policy_version 3670 (0.0010) -[2023-10-10 20:50:08,792][98559] Updated weights for policy 0, policy_version 3680 (0.0007) -[2023-10-10 20:50:10,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 7536640. Throughput: 0: 1691.7, 1: 1687.4. Samples: 1889918. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-10-10 20:50:10,556][97672] Avg episode reward: [(0, '-14.180'), (1, '-13.600')] -[2023-10-10 20:50:10,557][98385] Saving new best policy, reward=-14.180! -[2023-10-10 20:50:10,597][98560] Updated weights for policy 1, policy_version 3682 (0.0009) -[2023-10-10 20:50:10,964][98560] Updated weights for policy 1, policy_version 3692 (0.0010) -[2023-10-10 20:50:11,337][98560] Updated weights for policy 1, policy_version 3702 (0.0008) -[2023-10-10 20:50:11,707][98560] Updated weights for policy 1, policy_version 3712 (0.0008) -[2023-10-10 20:50:11,707][98439] Saving new best policy, reward=-13.600! -[2023-10-10 20:50:12,816][98559] Updated weights for policy 0, policy_version 3690 (0.0007) -[2023-10-10 20:50:13,192][98559] Updated weights for policy 0, policy_version 3700 (0.0008) -[2023-10-10 20:50:13,559][98559] Updated weights for policy 0, policy_version 3710 (0.0009) -[2023-10-10 20:50:15,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 7602176. Throughput: 0: 1686.8, 1: 1704.9. Samples: 1910364. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 20:50:15,556][97672] Avg episode reward: [(0, '-13.880'), (1, '-13.580')] -[2023-10-10 20:50:15,557][98385] Saving new best policy, reward=-13.880! -[2023-10-10 20:50:15,687][98560] Updated weights for policy 1, policy_version 3722 (0.0008) -[2023-10-10 20:50:16,062][98560] Updated weights for policy 1, policy_version 3732 (0.0007) -[2023-10-10 20:50:16,425][98560] Updated weights for policy 1, policy_version 3742 (0.0007) -[2023-10-10 20:50:16,496][98439] Saving new best policy, reward=-13.580! -[2023-10-10 20:50:17,650][98559] Updated weights for policy 0, policy_version 3720 (0.0008) -[2023-10-10 20:50:18,032][98559] Updated weights for policy 0, policy_version 3730 (0.0007) -[2023-10-10 20:50:18,398][98559] Updated weights for policy 0, policy_version 3740 (0.0007) -[2023-10-10 20:50:20,404][98560] Updated weights for policy 1, policy_version 3752 (0.0008) -[2023-10-10 20:50:20,556][97672] Fps is (10 sec: 13106.6, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 7667712. Throughput: 0: 1703.0, 1: 1708.4. Samples: 1931282. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 20:50:20,558][97672] Avg episode reward: [(0, '-13.900'), (1, '-13.500')] -[2023-10-10 20:50:20,781][98560] Updated weights for policy 1, policy_version 3762 (0.0008) -[2023-10-10 20:50:21,156][98560] Updated weights for policy 1, policy_version 3772 (0.0008) -[2023-10-10 20:50:21,298][98439] Saving new best policy, reward=-13.500! -[2023-10-10 20:50:22,277][98559] Updated weights for policy 0, policy_version 3750 (0.0008) -[2023-10-10 20:50:22,645][98559] Updated weights for policy 0, policy_version 3760 (0.0009) -[2023-10-10 20:50:23,021][98559] Updated weights for policy 0, policy_version 3770 (0.0008) -[2023-10-10 20:50:25,257][98560] Updated weights for policy 1, policy_version 3782 (0.0008) -[2023-10-10 20:50:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 7733248. Throughput: 0: 1667.3, 1: 1708.0. Samples: 1940504. Policy #0 lag: (min: 16.0, avg: 43.4, max: 48.0) -[2023-10-10 20:50:25,556][97672] Avg episode reward: [(0, '-13.860'), (1, '-13.620')] -[2023-10-10 20:50:25,557][98385] Saving new best policy, reward=-13.860! -[2023-10-10 20:50:25,620][98560] Updated weights for policy 1, policy_version 3792 (0.0007) -[2023-10-10 20:50:25,991][98560] Updated weights for policy 1, policy_version 3802 (0.0007) -[2023-10-10 20:50:27,100][98559] Updated weights for policy 0, policy_version 3780 (0.0009) -[2023-10-10 20:50:27,483][98559] Updated weights for policy 0, policy_version 3790 (0.0007) -[2023-10-10 20:50:27,855][98559] Updated weights for policy 0, policy_version 3800 (0.0008) -[2023-10-10 20:50:30,090][98560] Updated weights for policy 1, policy_version 3812 (0.0009) -[2023-10-10 20:50:30,460][98560] Updated weights for policy 1, policy_version 3822 (0.0007) -[2023-10-10 20:50:30,556][97672] Fps is (10 sec: 13107.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 7798784. Throughput: 0: 1691.4, 1: 1705.3. Samples: 1961436. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-10 20:50:30,556][97672] Avg episode reward: [(0, '-13.880'), (1, '-13.600')] -[2023-10-10 20:50:30,824][98560] Updated weights for policy 1, policy_version 3832 (0.0008) -[2023-10-10 20:50:31,788][98559] Updated weights for policy 0, policy_version 3810 (0.0007) -[2023-10-10 20:50:32,166][98559] Updated weights for policy 0, policy_version 3820 (0.0008) -[2023-10-10 20:50:32,541][98559] Updated weights for policy 0, policy_version 3830 (0.0007) -[2023-10-10 20:50:32,913][98559] Updated weights for policy 0, policy_version 3840 (0.0010) -[2023-10-10 20:50:34,737][98560] Updated weights for policy 1, policy_version 3842 (0.0008) -[2023-10-10 20:50:35,157][98560] Updated weights for policy 1, policy_version 3852 (0.0007) -[2023-10-10 20:50:35,526][98560] Updated weights for policy 1, policy_version 3862 (0.0008) -[2023-10-10 20:50:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 7864320. Throughput: 0: 1698.9, 1: 1706.8. Samples: 1982340. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-10 20:50:35,557][97672] Avg episode reward: [(0, '-14.040'), (1, '-13.440')] -[2023-10-10 20:50:35,564][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000003840_3932160.pth... -[2023-10-10 20:50:35,597][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000002272_2326528.pth -[2023-10-10 20:50:35,885][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000003872_3964928.pth... -[2023-10-10 20:50:35,889][98560] Updated weights for policy 1, policy_version 3872 (0.0010) -[2023-10-10 20:50:35,915][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000002272_2326528.pth -[2023-10-10 20:50:35,918][98439] Saving new best policy, reward=-13.440! -[2023-10-10 20:50:36,968][98559] Updated weights for policy 0, policy_version 3850 (0.0008) -[2023-10-10 20:50:37,345][98559] Updated weights for policy 0, policy_version 3860 (0.0010) -[2023-10-10 20:50:37,715][98559] Updated weights for policy 0, policy_version 3870 (0.0009) -[2023-10-10 20:50:39,778][98560] Updated weights for policy 1, policy_version 3882 (0.0009) -[2023-10-10 20:50:40,142][98560] Updated weights for policy 1, policy_version 3892 (0.0009) -[2023-10-10 20:50:40,515][98560] Updated weights for policy 1, policy_version 3902 (0.0009) -[2023-10-10 20:50:40,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 7929856. Throughput: 0: 1676.2, 1: 1706.6. Samples: 1991504. Policy #0 lag: (min: 17.0, avg: 25.5, max: 49.0) -[2023-10-10 20:50:40,557][97672] Avg episode reward: [(0, '-14.120'), (1, '-13.440')] -[2023-10-10 20:50:41,890][98559] Updated weights for policy 0, policy_version 3880 (0.0010) -[2023-10-10 20:50:42,258][98559] Updated weights for policy 0, policy_version 3890 (0.0007) -[2023-10-10 20:50:42,634][98559] Updated weights for policy 0, policy_version 3900 (0.0007) -[2023-10-10 20:50:44,505][98560] Updated weights for policy 1, policy_version 3912 (0.0010) -[2023-10-10 20:50:44,869][98560] Updated weights for policy 1, policy_version 3922 (0.0008) -[2023-10-10 20:50:45,237][98560] Updated weights for policy 1, policy_version 3932 (0.0008) -[2023-10-10 20:50:45,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 8028160. Throughput: 0: 1694.9, 1: 1708.9. Samples: 2012526. Policy #0 lag: (min: 31.0, avg: 31.2, max: 40.0) -[2023-10-10 20:50:45,557][97672] Avg episode reward: [(0, '-14.060'), (1, '-13.420')] -[2023-10-10 20:50:45,558][98439] Saving new best policy, reward=-13.420! -[2023-10-10 20:50:46,620][98559] Updated weights for policy 0, policy_version 3910 (0.0010) -[2023-10-10 20:50:46,993][98559] Updated weights for policy 0, policy_version 3920 (0.0010) -[2023-10-10 20:50:47,365][98559] Updated weights for policy 0, policy_version 3930 (0.0010) -[2023-10-10 20:50:49,112][98560] Updated weights for policy 1, policy_version 3942 (0.0008) -[2023-10-10 20:50:49,474][98560] Updated weights for policy 1, policy_version 3952 (0.0010) -[2023-10-10 20:50:49,846][98560] Updated weights for policy 1, policy_version 3962 (0.0008) -[2023-10-10 20:50:50,556][97672] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 8093696. Throughput: 0: 1691.6, 1: 1688.9. Samples: 2032446. Policy #0 lag: (min: 31.0, avg: 31.2, max: 40.0) -[2023-10-10 20:50:50,557][97672] Avg episode reward: [(0, '-14.080'), (1, '-13.420')] -[2023-10-10 20:50:51,395][98559] Updated weights for policy 0, policy_version 3940 (0.0009) -[2023-10-10 20:50:51,768][98559] Updated weights for policy 0, policy_version 3950 (0.0010) -[2023-10-10 20:50:52,141][98559] Updated weights for policy 0, policy_version 3960 (0.0010) -[2023-10-10 20:50:54,037][98560] Updated weights for policy 1, policy_version 3972 (0.0009) -[2023-10-10 20:50:54,399][98560] Updated weights for policy 1, policy_version 3982 (0.0008) -[2023-10-10 20:50:54,765][98560] Updated weights for policy 1, policy_version 3992 (0.0010) -[2023-10-10 20:50:55,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 8159232. Throughput: 0: 1679.2, 1: 1715.2. Samples: 2042664. Policy #0 lag: (min: 31.0, avg: 32.3, max: 55.0) -[2023-10-10 20:50:55,557][97672] Avg episode reward: [(0, '-14.100'), (1, '-13.400')] -[2023-10-10 20:50:55,557][98439] Saving new best policy, reward=-13.400! -[2023-10-10 20:50:56,145][98559] Updated weights for policy 0, policy_version 3970 (0.0009) -[2023-10-10 20:50:56,529][98559] Updated weights for policy 0, policy_version 3980 (0.0011) -[2023-10-10 20:50:56,895][98559] Updated weights for policy 0, policy_version 3990 (0.0008) -[2023-10-10 20:50:57,271][98559] Updated weights for policy 0, policy_version 4000 (0.0009) -[2023-10-10 20:50:58,652][98560] Updated weights for policy 1, policy_version 4002 (0.0010) -[2023-10-10 20:50:59,025][98560] Updated weights for policy 1, policy_version 4012 (0.0009) -[2023-10-10 20:50:59,399][98560] Updated weights for policy 1, policy_version 4022 (0.0008) -[2023-10-10 20:50:59,771][98560] Updated weights for policy 1, policy_version 4032 (0.0010) -[2023-10-10 20:51:00,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 8224768. Throughput: 0: 1689.2, 1: 1709.4. Samples: 2063302. Policy #0 lag: (min: 31.0, avg: 32.3, max: 55.0) -[2023-10-10 20:51:00,556][97672] Avg episode reward: [(0, '-13.980'), (1, '-13.440')] -[2023-10-10 20:51:01,443][98559] Updated weights for policy 0, policy_version 4010 (0.0007) -[2023-10-10 20:51:01,816][98559] Updated weights for policy 0, policy_version 4020 (0.0008) -[2023-10-10 20:51:02,181][98559] Updated weights for policy 0, policy_version 4030 (0.0008) -[2023-10-10 20:51:03,598][98560] Updated weights for policy 1, policy_version 4042 (0.0008) -[2023-10-10 20:51:03,974][98560] Updated weights for policy 1, policy_version 4052 (0.0008) -[2023-10-10 20:51:04,331][98560] Updated weights for policy 1, policy_version 4062 (0.0008) -[2023-10-10 20:51:05,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 8290304. Throughput: 0: 1690.7, 1: 1682.7. Samples: 2083082. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-10 20:51:05,556][97672] Avg episode reward: [(0, '-14.000'), (1, '-13.420')] -[2023-10-10 20:51:06,168][98559] Updated weights for policy 0, policy_version 4040 (0.0008) -[2023-10-10 20:51:06,548][98559] Updated weights for policy 0, policy_version 4050 (0.0007) -[2023-10-10 20:51:06,921][98559] Updated weights for policy 0, policy_version 4060 (0.0008) -[2023-10-10 20:51:08,530][98560] Updated weights for policy 1, policy_version 4072 (0.0007) -[2023-10-10 20:51:08,897][98560] Updated weights for policy 1, policy_version 4082 (0.0007) -[2023-10-10 20:51:09,273][98560] Updated weights for policy 1, policy_version 4092 (0.0009) -[2023-10-10 20:51:10,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 8355840. Throughput: 0: 1688.3, 1: 1714.7. Samples: 2093642. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-10 20:51:10,557][97672] Avg episode reward: [(0, '-14.020'), (1, '-13.520')] -[2023-10-10 20:51:11,038][98559] Updated weights for policy 0, policy_version 4070 (0.0010) -[2023-10-10 20:51:11,424][98559] Updated weights for policy 0, policy_version 4080 (0.0009) -[2023-10-10 20:51:11,804][98559] Updated weights for policy 0, policy_version 4090 (0.0010) -[2023-10-10 20:51:13,099][98560] Updated weights for policy 1, policy_version 4102 (0.0009) -[2023-10-10 20:51:13,467][98560] Updated weights for policy 1, policy_version 4112 (0.0009) -[2023-10-10 20:51:13,838][98560] Updated weights for policy 1, policy_version 4122 (0.0007) -[2023-10-10 20:51:15,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 8421376. Throughput: 0: 1687.6, 1: 1697.7. Samples: 2113774. Policy #0 lag: (min: 2.0, avg: 10.0, max: 34.0) -[2023-10-10 20:51:15,557][97672] Avg episode reward: [(0, '-14.020'), (1, '-13.480')] -[2023-10-10 20:51:15,908][98559] Updated weights for policy 0, policy_version 4100 (0.0009) -[2023-10-10 20:51:16,314][98559] Updated weights for policy 0, policy_version 4110 (0.0008) -[2023-10-10 20:51:16,686][98559] Updated weights for policy 0, policy_version 4120 (0.0007) -[2023-10-10 20:51:17,824][98560] Updated weights for policy 1, policy_version 4132 (0.0009) -[2023-10-10 20:51:18,195][98560] Updated weights for policy 1, policy_version 4142 (0.0010) -[2023-10-10 20:51:18,559][98560] Updated weights for policy 1, policy_version 4152 (0.0009) -[2023-10-10 20:51:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 8486912. Throughput: 0: 1683.6, 1: 1689.0. Samples: 2134106. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 20:51:20,557][97672] Avg episode reward: [(0, '-13.900'), (1, '-13.400')] -[2023-10-10 20:51:20,779][98559] Updated weights for policy 0, policy_version 4130 (0.0008) -[2023-10-10 20:51:21,140][98559] Updated weights for policy 0, policy_version 4140 (0.0009) -[2023-10-10 20:51:21,518][98559] Updated weights for policy 0, policy_version 4150 (0.0007) -[2023-10-10 20:51:21,888][98559] Updated weights for policy 0, policy_version 4160 (0.0007) -[2023-10-10 20:51:22,663][98560] Updated weights for policy 1, policy_version 4162 (0.0010) -[2023-10-10 20:51:23,081][98560] Updated weights for policy 1, policy_version 4172 (0.0008) -[2023-10-10 20:51:23,464][98560] Updated weights for policy 1, policy_version 4182 (0.0010) -[2023-10-10 20:51:23,843][98560] Updated weights for policy 1, policy_version 4192 (0.0010) -[2023-10-10 20:51:25,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 8552448. Throughput: 0: 1683.8, 1: 1716.0. Samples: 2144498. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-10 20:51:25,557][97672] Avg episode reward: [(0, '-13.660'), (1, '-13.340')] -[2023-10-10 20:51:25,558][98439] Saving new best policy, reward=-13.340! -[2023-10-10 20:51:25,829][98559] Updated weights for policy 0, policy_version 4170 (0.0009) -[2023-10-10 20:51:26,206][98559] Updated weights for policy 0, policy_version 4180 (0.0009) -[2023-10-10 20:51:26,585][98559] Updated weights for policy 0, policy_version 4190 (0.0009) -[2023-10-10 20:51:26,653][98385] Saving new best policy, reward=-13.660! -[2023-10-10 20:51:27,829][98560] Updated weights for policy 1, policy_version 4202 (0.0011) -[2023-10-10 20:51:28,206][98560] Updated weights for policy 1, policy_version 4212 (0.0009) -[2023-10-10 20:51:28,578][98560] Updated weights for policy 1, policy_version 4222 (0.0008) -[2023-10-10 20:51:30,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 8617984. Throughput: 0: 1686.4, 1: 1680.1. Samples: 2164018. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-10 20:51:30,557][97672] Avg episode reward: [(0, '-13.660'), (1, '-13.280')] -[2023-10-10 20:51:30,557][98439] Saving new best policy, reward=-13.280! -[2023-10-10 20:51:30,836][98559] Updated weights for policy 0, policy_version 4200 (0.0007) -[2023-10-10 20:51:31,213][98559] Updated weights for policy 0, policy_version 4210 (0.0008) -[2023-10-10 20:51:31,589][98559] Updated weights for policy 0, policy_version 4220 (0.0010) -[2023-10-10 20:51:32,583][98560] Updated weights for policy 1, policy_version 4232 (0.0008) -[2023-10-10 20:51:32,946][98560] Updated weights for policy 1, policy_version 4242 (0.0008) -[2023-10-10 20:51:33,318][98560] Updated weights for policy 1, policy_version 4252 (0.0008) -[2023-10-10 20:51:35,517][98559] Updated weights for policy 0, policy_version 4230 (0.0008) -[2023-10-10 20:51:35,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 8683520. Throughput: 0: 1688.0, 1: 1700.5. Samples: 2184926. Policy #0 lag: (min: 31.0, avg: 32.7, max: 58.0) -[2023-10-10 20:51:35,556][97672] Avg episode reward: [(0, '-13.520'), (1, '-13.260')] -[2023-10-10 20:51:35,564][98439] Saving new best policy, reward=-13.260! -[2023-10-10 20:51:35,885][98559] Updated weights for policy 0, policy_version 4240 (0.0008) -[2023-10-10 20:51:36,266][98559] Updated weights for policy 0, policy_version 4250 (0.0007) -[2023-10-10 20:51:36,483][98385] Saving new best policy, reward=-13.520! -[2023-10-10 20:51:37,288][98560] Updated weights for policy 1, policy_version 4262 (0.0010) -[2023-10-10 20:51:37,661][98560] Updated weights for policy 1, policy_version 4272 (0.0007) -[2023-10-10 20:51:38,032][98560] Updated weights for policy 1, policy_version 4282 (0.0008) -[2023-10-10 20:51:40,199][98559] Updated weights for policy 0, policy_version 4260 (0.0008) -[2023-10-10 20:51:40,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 8749056. Throughput: 0: 1689.7, 1: 1697.5. Samples: 2195088. Policy #0 lag: (min: 31.0, avg: 32.7, max: 58.0) -[2023-10-10 20:51:40,557][97672] Avg episode reward: [(0, '-13.540'), (1, '-13.480')] -[2023-10-10 20:51:40,565][98559] Updated weights for policy 0, policy_version 4270 (0.0009) -[2023-10-10 20:51:40,949][98559] Updated weights for policy 0, policy_version 4280 (0.0008) -[2023-10-10 20:51:41,929][98560] Updated weights for policy 1, policy_version 4292 (0.0007) -[2023-10-10 20:51:42,311][98560] Updated weights for policy 1, policy_version 4302 (0.0009) -[2023-10-10 20:51:42,681][98560] Updated weights for policy 1, policy_version 4312 (0.0009) -[2023-10-10 20:51:44,860][98559] Updated weights for policy 0, policy_version 4290 (0.0008) -[2023-10-10 20:51:45,232][98559] Updated weights for policy 0, policy_version 4300 (0.0008) -[2023-10-10 20:51:45,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 8814592. Throughput: 0: 1693.1, 1: 1687.1. Samples: 2215410. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:51:45,557][97672] Avg episode reward: [(0, '-13.340'), (1, '-13.620')] -[2023-10-10 20:51:45,601][98559] Updated weights for policy 0, policy_version 4310 (0.0008) -[2023-10-10 20:51:45,975][98385] Saving new best policy, reward=-13.340! -[2023-10-10 20:51:45,977][98559] Updated weights for policy 0, policy_version 4320 (0.0007) -[2023-10-10 20:51:46,670][98560] Updated weights for policy 1, policy_version 4322 (0.0010) -[2023-10-10 20:51:47,033][98560] Updated weights for policy 1, policy_version 4332 (0.0008) -[2023-10-10 20:51:47,400][98560] Updated weights for policy 1, policy_version 4342 (0.0009) -[2023-10-10 20:51:47,776][98560] Updated weights for policy 1, policy_version 4352 (0.0008) -[2023-10-10 20:51:50,036][98559] Updated weights for policy 0, policy_version 4330 (0.0009) -[2023-10-10 20:51:50,417][98559] Updated weights for policy 0, policy_version 4340 (0.0009) -[2023-10-10 20:51:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 8880128. Throughput: 0: 1676.2, 1: 1710.9. Samples: 2235502. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:51:50,557][97672] Avg episode reward: [(0, '-13.180'), (1, '-13.620')] -[2023-10-10 20:51:50,791][98559] Updated weights for policy 0, policy_version 4350 (0.0009) -[2023-10-10 20:51:50,870][98385] Saving new best policy, reward=-13.180! -[2023-10-10 20:51:51,747][98560] Updated weights for policy 1, policy_version 4362 (0.0008) -[2023-10-10 20:51:52,118][98560] Updated weights for policy 1, policy_version 4372 (0.0007) -[2023-10-10 20:51:52,484][98560] Updated weights for policy 1, policy_version 4382 (0.0009) -[2023-10-10 20:51:54,724][98559] Updated weights for policy 0, policy_version 4360 (0.0008) -[2023-10-10 20:51:55,107][98559] Updated weights for policy 0, policy_version 4370 (0.0010) -[2023-10-10 20:51:55,478][98559] Updated weights for policy 0, policy_version 4380 (0.0007) -[2023-10-10 20:51:55,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 8945664. Throughput: 0: 1698.5, 1: 1680.8. Samples: 2245712. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-10 20:51:55,556][97672] Avg episode reward: [(0, '-13.140'), (1, '-13.620')] -[2023-10-10 20:51:55,621][98385] Saving new best policy, reward=-13.140! -[2023-10-10 20:51:56,633][98560] Updated weights for policy 1, policy_version 4392 (0.0009) -[2023-10-10 20:51:57,005][98560] Updated weights for policy 1, policy_version 4402 (0.0008) -[2023-10-10 20:51:57,371][98560] Updated weights for policy 1, policy_version 4412 (0.0007) -[2023-10-10 20:51:59,473][98559] Updated weights for policy 0, policy_version 4390 (0.0010) -[2023-10-10 20:51:59,851][98559] Updated weights for policy 0, policy_version 4400 (0.0010) -[2023-10-10 20:52:00,227][98559] Updated weights for policy 0, policy_version 4410 (0.0011) -[2023-10-10 20:52:00,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 9043968. Throughput: 0: 1699.7, 1: 1694.6. Samples: 2266516. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:52:00,557][97672] Avg episode reward: [(0, '-13.080'), (1, '-13.440')] -[2023-10-10 20:52:00,557][98385] Saving new best policy, reward=-13.080! -[2023-10-10 20:52:01,455][98560] Updated weights for policy 1, policy_version 4422 (0.0010) -[2023-10-10 20:52:01,821][98560] Updated weights for policy 1, policy_version 4432 (0.0011) -[2023-10-10 20:52:02,195][98560] Updated weights for policy 1, policy_version 4442 (0.0010) -[2023-10-10 20:52:04,339][98559] Updated weights for policy 0, policy_version 4420 (0.0009) -[2023-10-10 20:52:04,730][98559] Updated weights for policy 0, policy_version 4430 (0.0008) -[2023-10-10 20:52:05,097][98559] Updated weights for policy 0, policy_version 4440 (0.0009) -[2023-10-10 20:52:05,556][97672] Fps is (10 sec: 16383.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 9109504. Throughput: 0: 1674.2, 1: 1708.0. Samples: 2286306. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:52:05,557][97672] Avg episode reward: [(0, '-12.980'), (1, '-13.300')] -[2023-10-10 20:52:05,569][98385] Saving new best policy, reward=-12.980! -[2023-10-10 20:52:06,173][98560] Updated weights for policy 1, policy_version 4452 (0.0011) -[2023-10-10 20:52:06,531][98560] Updated weights for policy 1, policy_version 4462 (0.0010) -[2023-10-10 20:52:06,906][98560] Updated weights for policy 1, policy_version 4472 (0.0009) -[2023-10-10 20:52:08,991][98559] Updated weights for policy 0, policy_version 4450 (0.0011) -[2023-10-10 20:52:09,373][98559] Updated weights for policy 0, policy_version 4460 (0.0010) -[2023-10-10 20:52:09,739][98559] Updated weights for policy 0, policy_version 4470 (0.0009) -[2023-10-10 20:52:10,117][98559] Updated weights for policy 0, policy_version 4480 (0.0010) -[2023-10-10 20:52:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 9175040. Throughput: 0: 1701.7, 1: 1681.1. Samples: 2296724. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:52:10,557][97672] Avg episode reward: [(0, '-12.820'), (1, '-13.260')] -[2023-10-10 20:52:10,557][98385] Saving new best policy, reward=-12.820! -[2023-10-10 20:52:10,885][98560] Updated weights for policy 1, policy_version 4482 (0.0009) -[2023-10-10 20:52:11,258][98560] Updated weights for policy 1, policy_version 4492 (0.0007) -[2023-10-10 20:52:11,639][98560] Updated weights for policy 1, policy_version 4502 (0.0010) -[2023-10-10 20:52:11,999][98560] Updated weights for policy 1, policy_version 4512 (0.0007) -[2023-10-10 20:52:14,142][98559] Updated weights for policy 0, policy_version 4490 (0.0010) -[2023-10-10 20:52:14,516][98559] Updated weights for policy 0, policy_version 4500 (0.0008) -[2023-10-10 20:52:14,882][98559] Updated weights for policy 0, policy_version 4510 (0.0008) -[2023-10-10 20:52:15,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 9240576. Throughput: 0: 1687.6, 1: 1715.6. Samples: 2317164. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:52:15,557][97672] Avg episode reward: [(0, '-12.740'), (1, '-13.160')] -[2023-10-10 20:52:15,557][98385] Saving new best policy, reward=-12.740! -[2023-10-10 20:52:15,944][98560] Updated weights for policy 1, policy_version 4522 (0.0008) -[2023-10-10 20:52:16,310][98560] Updated weights for policy 1, policy_version 4532 (0.0008) -[2023-10-10 20:52:16,678][98560] Updated weights for policy 1, policy_version 4542 (0.0008) -[2023-10-10 20:52:16,746][98439] Saving new best policy, reward=-13.160! -[2023-10-10 20:52:18,752][98559] Updated weights for policy 0, policy_version 4520 (0.0009) -[2023-10-10 20:52:19,125][98559] Updated weights for policy 0, policy_version 4530 (0.0009) -[2023-10-10 20:52:19,510][98559] Updated weights for policy 0, policy_version 4540 (0.0011) -[2023-10-10 20:52:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 9306112. Throughput: 0: 1679.9, 1: 1713.6. Samples: 2337634. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:52:20,556][97672] Avg episode reward: [(0, '-12.740'), (1, '-13.300')] -[2023-10-10 20:52:20,812][98560] Updated weights for policy 1, policy_version 4552 (0.0008) -[2023-10-10 20:52:21,184][98560] Updated weights for policy 1, policy_version 4562 (0.0007) -[2023-10-10 20:52:21,559][98560] Updated weights for policy 1, policy_version 4572 (0.0007) -[2023-10-10 20:52:23,559][98559] Updated weights for policy 0, policy_version 4550 (0.0010) -[2023-10-10 20:52:23,938][98559] Updated weights for policy 0, policy_version 4560 (0.0008) -[2023-10-10 20:52:24,307][98559] Updated weights for policy 0, policy_version 4570 (0.0010) -[2023-10-10 20:52:25,506][98560] Updated weights for policy 1, policy_version 4582 (0.0009) -[2023-10-10 20:52:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 9371648. Throughput: 0: 1706.7, 1: 1693.3. Samples: 2348086. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:52:25,556][97672] Avg episode reward: [(0, '-12.800'), (1, '-13.160')] -[2023-10-10 20:52:25,877][98560] Updated weights for policy 1, policy_version 4592 (0.0008) -[2023-10-10 20:52:26,241][98560] Updated weights for policy 1, policy_version 4602 (0.0007) -[2023-10-10 20:52:28,333][98559] Updated weights for policy 0, policy_version 4580 (0.0009) -[2023-10-10 20:52:28,711][98559] Updated weights for policy 0, policy_version 4590 (0.0009) -[2023-10-10 20:52:29,093][98559] Updated weights for policy 0, policy_version 4600 (0.0011) -[2023-10-10 20:52:30,356][98560] Updated weights for policy 1, policy_version 4612 (0.0010) -[2023-10-10 20:52:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 9437184. Throughput: 0: 1680.4, 1: 1708.3. Samples: 2367898. Policy #0 lag: (min: 10.0, avg: 20.9, max: 42.0) -[2023-10-10 20:52:30,556][97672] Avg episode reward: [(0, '-12.620'), (1, '-13.300')] -[2023-10-10 20:52:30,557][98385] Saving new best policy, reward=-12.620! -[2023-10-10 20:52:30,728][98560] Updated weights for policy 1, policy_version 4622 (0.0010) -[2023-10-10 20:52:31,113][98560] Updated weights for policy 1, policy_version 4632 (0.0009) -[2023-10-10 20:52:33,249][98559] Updated weights for policy 0, policy_version 4610 (0.0010) -[2023-10-10 20:52:33,622][98559] Updated weights for policy 0, policy_version 4620 (0.0009) -[2023-10-10 20:52:33,996][98559] Updated weights for policy 0, policy_version 4630 (0.0009) -[2023-10-10 20:52:34,364][98559] Updated weights for policy 0, policy_version 4640 (0.0008) -[2023-10-10 20:52:35,039][98560] Updated weights for policy 1, policy_version 4642 (0.0009) -[2023-10-10 20:52:35,416][98560] Updated weights for policy 1, policy_version 4652 (0.0008) -[2023-10-10 20:52:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 9502720. Throughput: 0: 1692.8, 1: 1711.6. Samples: 2388700. Policy #0 lag: (min: 10.0, avg: 20.9, max: 42.0) -[2023-10-10 20:52:35,556][97672] Avg episode reward: [(0, '-12.680'), (1, '-13.440')] -[2023-10-10 20:52:35,566][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000004640_4751360.pth... -[2023-10-10 20:52:35,601][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000003072_3145728.pth -[2023-10-10 20:52:35,785][98560] Updated weights for policy 1, policy_version 4662 (0.0009) -[2023-10-10 20:52:36,155][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000004672_4784128.pth... -[2023-10-10 20:52:36,155][98560] Updated weights for policy 1, policy_version 4672 (0.0008) -[2023-10-10 20:52:36,183][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000003072_3145728.pth -[2023-10-10 20:52:38,494][98559] Updated weights for policy 0, policy_version 4650 (0.0008) -[2023-10-10 20:52:38,866][98559] Updated weights for policy 0, policy_version 4660 (0.0008) -[2023-10-10 20:52:39,251][98559] Updated weights for policy 0, policy_version 4670 (0.0009) -[2023-10-10 20:52:40,019][98560] Updated weights for policy 1, policy_version 4682 (0.0008) -[2023-10-10 20:52:40,385][98560] Updated weights for policy 1, policy_version 4692 (0.0008) -[2023-10-10 20:52:40,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 9568256. Throughput: 0: 1693.2, 1: 1710.1. Samples: 2398862. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:52:40,557][97672] Avg episode reward: [(0, '-12.680'), (1, '-13.360')] -[2023-10-10 20:52:40,756][98560] Updated weights for policy 1, policy_version 4702 (0.0009) -[2023-10-10 20:52:43,302][98559] Updated weights for policy 0, policy_version 4680 (0.0008) -[2023-10-10 20:52:43,682][98559] Updated weights for policy 0, policy_version 4690 (0.0008) -[2023-10-10 20:52:44,050][98559] Updated weights for policy 0, policy_version 4700 (0.0007) -[2023-10-10 20:52:44,805][98560] Updated weights for policy 1, policy_version 4712 (0.0008) -[2023-10-10 20:52:45,179][98560] Updated weights for policy 1, policy_version 4722 (0.0009) -[2023-10-10 20:52:45,552][98560] Updated weights for policy 1, policy_version 4732 (0.0009) -[2023-10-10 20:52:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 9633792. Throughput: 0: 1668.0, 1: 1714.0. Samples: 2418706. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:52:45,556][97672] Avg episode reward: [(0, '-12.540'), (1, '-13.360')] -[2023-10-10 20:52:45,557][98385] Saving new best policy, reward=-12.540! -[2023-10-10 20:52:48,175][98559] Updated weights for policy 0, policy_version 4710 (0.0009) -[2023-10-10 20:52:48,557][98559] Updated weights for policy 0, policy_version 4720 (0.0009) -[2023-10-10 20:52:48,937][98559] Updated weights for policy 0, policy_version 4730 (0.0007) -[2023-10-10 20:52:49,570][98560] Updated weights for policy 1, policy_version 4742 (0.0009) -[2023-10-10 20:52:49,940][98560] Updated weights for policy 1, policy_version 4752 (0.0008) -[2023-10-10 20:52:50,313][98560] Updated weights for policy 1, policy_version 4762 (0.0008) -[2023-10-10 20:52:50,556][97672] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 9732096. Throughput: 0: 1690.6, 1: 1704.3. Samples: 2439076. Policy #0 lag: (min: 31.0, avg: 32.5, max: 58.0) -[2023-10-10 20:52:50,557][97672] Avg episode reward: [(0, '-12.260'), (1, '-13.160')] -[2023-10-10 20:52:50,565][98385] Saving new best policy, reward=-12.260! -[2023-10-10 20:52:53,007][98559] Updated weights for policy 0, policy_version 4740 (0.0010) -[2023-10-10 20:52:53,410][98559] Updated weights for policy 0, policy_version 4750 (0.0009) -[2023-10-10 20:52:53,787][98559] Updated weights for policy 0, policy_version 4760 (0.0008) -[2023-10-10 20:52:54,131][98560] Updated weights for policy 1, policy_version 4772 (0.0008) -[2023-10-10 20:52:54,504][98560] Updated weights for policy 1, policy_version 4782 (0.0008) -[2023-10-10 20:52:54,873][98560] Updated weights for policy 1, policy_version 4792 (0.0008) -[2023-10-10 20:52:55,556][97672] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 9797632. Throughput: 0: 1677.4, 1: 1719.5. Samples: 2449584. Policy #0 lag: (min: 31.0, avg: 32.5, max: 58.0) -[2023-10-10 20:52:55,557][97672] Avg episode reward: [(0, '-12.200'), (1, '-12.780')] -[2023-10-10 20:52:55,558][98385] Saving new best policy, reward=-12.200! -[2023-10-10 20:52:55,559][98439] Saving new best policy, reward=-12.780! -[2023-10-10 20:52:57,870][98559] Updated weights for policy 0, policy_version 4770 (0.0008) -[2023-10-10 20:52:58,257][98559] Updated weights for policy 0, policy_version 4780 (0.0009) -[2023-10-10 20:52:58,633][98559] Updated weights for policy 0, policy_version 4790 (0.0007) -[2023-10-10 20:52:58,787][98560] Updated weights for policy 1, policy_version 4802 (0.0007) -[2023-10-10 20:52:59,015][98559] Updated weights for policy 0, policy_version 4800 (0.0008) -[2023-10-10 20:52:59,159][98560] Updated weights for policy 1, policy_version 4812 (0.0010) -[2023-10-10 20:52:59,533][98560] Updated weights for policy 1, policy_version 4822 (0.0009) -[2023-10-10 20:52:59,909][98560] Updated weights for policy 1, policy_version 4832 (0.0009) -[2023-10-10 20:53:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 9863168. Throughput: 0: 1672.7, 1: 1721.1. Samples: 2469884. Policy #0 lag: (min: 7.0, avg: 8.7, max: 36.0) -[2023-10-10 20:53:00,556][97672] Avg episode reward: [(0, '-12.200'), (1, '-12.700')] -[2023-10-10 20:53:00,557][98439] Saving new best policy, reward=-12.700! -[2023-10-10 20:53:02,988][98559] Updated weights for policy 0, policy_version 4810 (0.0010) -[2023-10-10 20:53:03,358][98559] Updated weights for policy 0, policy_version 4820 (0.0008) -[2023-10-10 20:53:03,740][98559] Updated weights for policy 0, policy_version 4830 (0.0008) -[2023-10-10 20:53:03,897][98560] Updated weights for policy 1, policy_version 4842 (0.0008) -[2023-10-10 20:53:04,259][98560] Updated weights for policy 1, policy_version 4852 (0.0008) -[2023-10-10 20:53:04,638][98560] Updated weights for policy 1, policy_version 4862 (0.0010) -[2023-10-10 20:53:05,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 9928704. Throughput: 0: 1680.7, 1: 1692.7. Samples: 2489436. Policy #0 lag: (min: 7.0, avg: 8.7, max: 36.0) -[2023-10-10 20:53:05,557][97672] Avg episode reward: [(0, '-12.240'), (1, '-12.480')] -[2023-10-10 20:53:05,566][98439] Saving new best policy, reward=-12.480! -[2023-10-10 20:53:07,800][98559] Updated weights for policy 0, policy_version 4840 (0.0009) -[2023-10-10 20:53:08,170][98559] Updated weights for policy 0, policy_version 4850 (0.0007) -[2023-10-10 20:53:08,556][98559] Updated weights for policy 0, policy_version 4860 (0.0009) -[2023-10-10 20:53:08,563][98560] Updated weights for policy 1, policy_version 4872 (0.0008) -[2023-10-10 20:53:08,937][98560] Updated weights for policy 1, policy_version 4882 (0.0007) -[2023-10-10 20:53:09,311][98560] Updated weights for policy 1, policy_version 4892 (0.0008) -[2023-10-10 20:53:10,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 9994240. Throughput: 0: 1659.9, 1: 1721.3. Samples: 2500242. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-10 20:53:10,557][97672] Avg episode reward: [(0, '-12.280'), (1, '-12.520')] -[2023-10-10 20:53:12,647][98559] Updated weights for policy 0, policy_version 4870 (0.0008) -[2023-10-10 20:53:13,025][98559] Updated weights for policy 0, policy_version 4880 (0.0008) -[2023-10-10 20:53:13,348][98560] Updated weights for policy 1, policy_version 4902 (0.0008) -[2023-10-10 20:53:13,399][98559] Updated weights for policy 0, policy_version 4890 (0.0009) -[2023-10-10 20:53:13,706][98560] Updated weights for policy 1, policy_version 4912 (0.0008) -[2023-10-10 20:53:14,082][98560] Updated weights for policy 1, policy_version 4922 (0.0007) -[2023-10-10 20:53:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 10059776. Throughput: 0: 1677.2, 1: 1701.9. Samples: 2519954. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-10 20:53:15,556][97672] Avg episode reward: [(0, '-12.100'), (1, '-12.420')] -[2023-10-10 20:53:15,557][98385] Saving new best policy, reward=-12.100! -[2023-10-10 20:53:15,557][98439] Saving new best policy, reward=-12.420! -[2023-10-10 20:53:17,318][98559] Updated weights for policy 0, policy_version 4900 (0.0009) -[2023-10-10 20:53:17,679][98559] Updated weights for policy 0, policy_version 4910 (0.0010) -[2023-10-10 20:53:18,061][98559] Updated weights for policy 0, policy_version 4920 (0.0008) -[2023-10-10 20:53:18,332][98560] Updated weights for policy 1, policy_version 4932 (0.0010) -[2023-10-10 20:53:18,697][98560] Updated weights for policy 1, policy_version 4942 (0.0009) -[2023-10-10 20:53:19,065][98560] Updated weights for policy 1, policy_version 4952 (0.0009) -[2023-10-10 20:53:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 10125312. Throughput: 0: 1678.0, 1: 1683.2. Samples: 2539956. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-10 20:53:20,557][97672] Avg episode reward: [(0, '-11.960'), (1, '-12.320')] -[2023-10-10 20:53:20,568][98385] Saving new best policy, reward=-11.960! -[2023-10-10 20:53:20,568][98439] Saving new best policy, reward=-12.320! -[2023-10-10 20:53:22,230][98559] Updated weights for policy 0, policy_version 4930 (0.0009) -[2023-10-10 20:53:22,610][98559] Updated weights for policy 0, policy_version 4940 (0.0011) -[2023-10-10 20:53:22,979][98559] Updated weights for policy 0, policy_version 4950 (0.0007) -[2023-10-10 20:53:22,995][98560] Updated weights for policy 1, policy_version 4962 (0.0009) -[2023-10-10 20:53:23,357][98559] Updated weights for policy 0, policy_version 4960 (0.0008) -[2023-10-10 20:53:23,365][98560] Updated weights for policy 1, policy_version 4972 (0.0008) -[2023-10-10 20:53:23,732][98560] Updated weights for policy 1, policy_version 4982 (0.0007) -[2023-10-10 20:53:24,102][98560] Updated weights for policy 1, policy_version 4992 (0.0007) -[2023-10-10 20:53:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 10190848. Throughput: 0: 1658.2, 1: 1711.2. Samples: 2550484. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-10 20:53:25,556][97672] Avg episode reward: [(0, '-11.980'), (1, '-12.380')] -[2023-10-10 20:53:27,291][98559] Updated weights for policy 0, policy_version 4970 (0.0009) -[2023-10-10 20:53:27,671][98559] Updated weights for policy 0, policy_version 4980 (0.0011) -[2023-10-10 20:53:28,045][98559] Updated weights for policy 0, policy_version 4990 (0.0011) -[2023-10-10 20:53:28,246][98560] Updated weights for policy 1, policy_version 5002 (0.0010) -[2023-10-10 20:53:28,618][98560] Updated weights for policy 1, policy_version 5012 (0.0009) -[2023-10-10 20:53:28,989][98560] Updated weights for policy 1, policy_version 5022 (0.0007) -[2023-10-10 20:53:30,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 10256384. Throughput: 0: 1684.8, 1: 1687.6. Samples: 2570464. Policy #0 lag: (min: 8.0, avg: 35.5, max: 40.0) -[2023-10-10 20:53:30,557][97672] Avg episode reward: [(0, '-12.000'), (1, '-12.220')] -[2023-10-10 20:53:30,557][98439] Saving new best policy, reward=-12.220! -[2023-10-10 20:53:31,987][98559] Updated weights for policy 0, policy_version 5000 (0.0010) -[2023-10-10 20:53:32,364][98559] Updated weights for policy 0, policy_version 5010 (0.0009) -[2023-10-10 20:53:32,738][98559] Updated weights for policy 0, policy_version 5020 (0.0008) -[2023-10-10 20:53:32,991][98560] Updated weights for policy 1, policy_version 5032 (0.0010) -[2023-10-10 20:53:33,359][98560] Updated weights for policy 1, policy_version 5042 (0.0011) -[2023-10-10 20:53:33,735][98560] Updated weights for policy 1, policy_version 5052 (0.0009) -[2023-10-10 20:53:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 10321920. Throughput: 0: 1691.5, 1: 1686.2. Samples: 2591074. Policy #0 lag: (min: 8.0, avg: 35.5, max: 40.0) -[2023-10-10 20:53:35,557][97672] Avg episode reward: [(0, '-12.000'), (1, '-12.020')] -[2023-10-10 20:53:35,568][98439] Saving new best policy, reward=-12.020! -[2023-10-10 20:53:36,699][98559] Updated weights for policy 0, policy_version 5030 (0.0008) -[2023-10-10 20:53:37,071][98559] Updated weights for policy 0, policy_version 5040 (0.0008) -[2023-10-10 20:53:37,452][98559] Updated weights for policy 0, policy_version 5050 (0.0010) -[2023-10-10 20:53:37,660][98560] Updated weights for policy 1, policy_version 5062 (0.0007) -[2023-10-10 20:53:38,034][98560] Updated weights for policy 1, policy_version 5072 (0.0010) -[2023-10-10 20:53:38,399][98560] Updated weights for policy 1, policy_version 5082 (0.0008) -[2023-10-10 20:53:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 10387456. Throughput: 0: 1678.7, 1: 1695.9. Samples: 2601440. Policy #0 lag: (min: 27.0, avg: 27.2, max: 36.0) -[2023-10-10 20:53:40,557][97672] Avg episode reward: [(0, '-11.740'), (1, '-11.920')] -[2023-10-10 20:53:40,558][98439] Saving new best policy, reward=-11.920! -[2023-10-10 20:53:40,558][98385] Saving new best policy, reward=-11.740! -[2023-10-10 20:53:41,504][98559] Updated weights for policy 0, policy_version 5060 (0.0007) -[2023-10-10 20:53:41,888][98559] Updated weights for policy 0, policy_version 5070 (0.0008) -[2023-10-10 20:53:42,250][98559] Updated weights for policy 0, policy_version 5080 (0.0008) -[2023-10-10 20:53:42,294][98560] Updated weights for policy 1, policy_version 5092 (0.0008) -[2023-10-10 20:53:42,664][98560] Updated weights for policy 1, policy_version 5102 (0.0009) -[2023-10-10 20:53:43,033][98560] Updated weights for policy 1, policy_version 5112 (0.0007) -[2023-10-10 20:53:45,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 10452992. Throughput: 0: 1698.6, 1: 1670.1. Samples: 2621478. Policy #0 lag: (min: 27.0, avg: 27.2, max: 36.0) -[2023-10-10 20:53:45,557][97672] Avg episode reward: [(0, '-11.720'), (1, '-11.840')] -[2023-10-10 20:53:45,558][98385] Saving new best policy, reward=-11.720! -[2023-10-10 20:53:45,558][98439] Saving new best policy, reward=-11.840! -[2023-10-10 20:53:46,230][98559] Updated weights for policy 0, policy_version 5090 (0.0009) -[2023-10-10 20:53:46,605][98559] Updated weights for policy 0, policy_version 5100 (0.0009) -[2023-10-10 20:53:46,976][98559] Updated weights for policy 0, policy_version 5110 (0.0008) -[2023-10-10 20:53:47,142][98560] Updated weights for policy 1, policy_version 5122 (0.0009) -[2023-10-10 20:53:47,348][98559] Updated weights for policy 0, policy_version 5120 (0.0007) -[2023-10-10 20:53:47,554][98560] Updated weights for policy 1, policy_version 5132 (0.0009) -[2023-10-10 20:53:47,922][98560] Updated weights for policy 1, policy_version 5142 (0.0010) -[2023-10-10 20:53:48,298][98560] Updated weights for policy 1, policy_version 5152 (0.0008) -[2023-10-10 20:53:50,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 10518528. Throughput: 0: 1696.8, 1: 1695.3. Samples: 2642078. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:53:50,557][97672] Avg episode reward: [(0, '-11.900'), (1, '-11.700')] -[2023-10-10 20:53:50,568][98439] Saving new best policy, reward=-11.700! -[2023-10-10 20:53:51,535][98559] Updated weights for policy 0, policy_version 5130 (0.0007) -[2023-10-10 20:53:51,908][98559] Updated weights for policy 0, policy_version 5140 (0.0008) -[2023-10-10 20:53:52,283][98559] Updated weights for policy 0, policy_version 5150 (0.0009) -[2023-10-10 20:53:52,316][98560] Updated weights for policy 1, policy_version 5162 (0.0007) -[2023-10-10 20:53:52,695][98560] Updated weights for policy 1, policy_version 5172 (0.0008) -[2023-10-10 20:53:53,062][98560] Updated weights for policy 1, policy_version 5182 (0.0008) -[2023-10-10 20:53:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 10584064. Throughput: 0: 1686.0, 1: 1678.7. Samples: 2651652. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:53:55,557][97672] Avg episode reward: [(0, '-11.860'), (1, '-11.460')] -[2023-10-10 20:53:55,558][98439] Saving new best policy, reward=-11.460! -[2023-10-10 20:53:56,395][98559] Updated weights for policy 0, policy_version 5160 (0.0008) -[2023-10-10 20:53:56,760][98559] Updated weights for policy 0, policy_version 5170 (0.0008) -[2023-10-10 20:53:57,077][98560] Updated weights for policy 1, policy_version 5192 (0.0009) -[2023-10-10 20:53:57,143][98559] Updated weights for policy 0, policy_version 5180 (0.0009) -[2023-10-10 20:53:57,445][98560] Updated weights for policy 1, policy_version 5202 (0.0007) -[2023-10-10 20:53:57,808][98560] Updated weights for policy 1, policy_version 5212 (0.0009) -[2023-10-10 20:54:00,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 10649600. Throughput: 0: 1693.6, 1: 1685.1. Samples: 2671994. Policy #0 lag: (min: 26.0, avg: 27.5, max: 53.0) -[2023-10-10 20:54:00,557][97672] Avg episode reward: [(0, '-11.660'), (1, '-11.500')] -[2023-10-10 20:54:00,559][98385] Saving new best policy, reward=-11.660! -[2023-10-10 20:54:01,195][98559] Updated weights for policy 0, policy_version 5190 (0.0011) -[2023-10-10 20:54:01,575][98559] Updated weights for policy 0, policy_version 5200 (0.0010) -[2023-10-10 20:54:01,868][98560] Updated weights for policy 1, policy_version 5222 (0.0010) -[2023-10-10 20:54:01,947][98559] Updated weights for policy 0, policy_version 5210 (0.0008) -[2023-10-10 20:54:02,239][98560] Updated weights for policy 1, policy_version 5232 (0.0009) -[2023-10-10 20:54:02,612][98560] Updated weights for policy 1, policy_version 5242 (0.0009) -[2023-10-10 20:54:05,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 10715136. Throughput: 0: 1697.8, 1: 1702.6. Samples: 2692972. Policy #0 lag: (min: 26.0, avg: 27.5, max: 53.0) -[2023-10-10 20:54:05,557][97672] Avg episode reward: [(0, '-11.560'), (1, '-11.360')] -[2023-10-10 20:54:05,566][98385] Saving new best policy, reward=-11.560! -[2023-10-10 20:54:05,566][98439] Saving new best policy, reward=-11.360! -[2023-10-10 20:54:05,892][98559] Updated weights for policy 0, policy_version 5220 (0.0008) -[2023-10-10 20:54:06,252][98559] Updated weights for policy 0, policy_version 5230 (0.0010) -[2023-10-10 20:54:06,637][98559] Updated weights for policy 0, policy_version 5240 (0.0009) -[2023-10-10 20:54:06,680][98560] Updated weights for policy 1, policy_version 5252 (0.0008) -[2023-10-10 20:54:07,056][98560] Updated weights for policy 1, policy_version 5262 (0.0008) -[2023-10-10 20:54:07,431][98560] Updated weights for policy 1, policy_version 5272 (0.0007) -[2023-10-10 20:54:10,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 10780672. Throughput: 0: 1693.7, 1: 1675.5. Samples: 2702098. Policy #0 lag: (min: 1.0, avg: 9.6, max: 33.0) -[2023-10-10 20:54:10,557][97672] Avg episode reward: [(0, '-11.240'), (1, '-11.300')] -[2023-10-10 20:54:10,559][98385] Saving new best policy, reward=-11.240! -[2023-10-10 20:54:10,559][98439] Saving new best policy, reward=-11.300! -[2023-10-10 20:54:10,819][98559] Updated weights for policy 0, policy_version 5250 (0.0009) -[2023-10-10 20:54:11,202][98559] Updated weights for policy 0, policy_version 5260 (0.0007) -[2023-10-10 20:54:11,536][98560] Updated weights for policy 1, policy_version 5282 (0.0009) -[2023-10-10 20:54:11,575][98559] Updated weights for policy 0, policy_version 5270 (0.0008) -[2023-10-10 20:54:11,901][98560] Updated weights for policy 1, policy_version 5292 (0.0007) -[2023-10-10 20:54:11,948][98559] Updated weights for policy 0, policy_version 5280 (0.0009) -[2023-10-10 20:54:12,279][98560] Updated weights for policy 1, policy_version 5302 (0.0008) -[2023-10-10 20:54:12,652][98560] Updated weights for policy 1, policy_version 5312 (0.0008) -[2023-10-10 20:54:15,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 10846208. Throughput: 0: 1695.5, 1: 1689.0. Samples: 2722766. Policy #0 lag: (min: 1.0, avg: 9.6, max: 33.0) -[2023-10-10 20:54:15,557][97672] Avg episode reward: [(0, '-11.260'), (1, '-10.980')] -[2023-10-10 20:54:15,557][98439] Saving new best policy, reward=-10.980! -[2023-10-10 20:54:15,843][98559] Updated weights for policy 0, policy_version 5290 (0.0011) -[2023-10-10 20:54:16,218][98559] Updated weights for policy 0, policy_version 5300 (0.0010) -[2023-10-10 20:54:16,590][98559] Updated weights for policy 0, policy_version 5310 (0.0007) -[2023-10-10 20:54:16,698][98560] Updated weights for policy 1, policy_version 5322 (0.0008) -[2023-10-10 20:54:17,058][98560] Updated weights for policy 1, policy_version 5332 (0.0007) -[2023-10-10 20:54:17,429][98560] Updated weights for policy 1, policy_version 5342 (0.0008) -[2023-10-10 20:54:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 10911744. Throughput: 0: 1692.0, 1: 1698.4. Samples: 2743646. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-10 20:54:20,557][97672] Avg episode reward: [(0, '-11.100'), (1, '-10.960')] -[2023-10-10 20:54:20,566][98439] Saving new best policy, reward=-10.960! -[2023-10-10 20:54:20,606][98559] Updated weights for policy 0, policy_version 5320 (0.0009) -[2023-10-10 20:54:20,981][98559] Updated weights for policy 0, policy_version 5330 (0.0007) -[2023-10-10 20:54:21,355][98559] Updated weights for policy 0, policy_version 5340 (0.0007) -[2023-10-10 20:54:21,440][98560] Updated weights for policy 1, policy_version 5352 (0.0007) -[2023-10-10 20:54:21,506][98385] Saving new best policy, reward=-11.100! -[2023-10-10 20:54:21,817][98560] Updated weights for policy 1, policy_version 5362 (0.0008) -[2023-10-10 20:54:22,190][98560] Updated weights for policy 1, policy_version 5372 (0.0007) -[2023-10-10 20:54:25,443][98559] Updated weights for policy 0, policy_version 5350 (0.0008) -[2023-10-10 20:54:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 10977280. Throughput: 0: 1688.8, 1: 1671.2. Samples: 2752638. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-10 20:54:25,557][97672] Avg episode reward: [(0, '-11.240'), (1, '-10.820')] -[2023-10-10 20:54:25,559][98439] Saving new best policy, reward=-10.820! -[2023-10-10 20:54:25,812][98559] Updated weights for policy 0, policy_version 5360 (0.0008) -[2023-10-10 20:54:26,185][98559] Updated weights for policy 0, policy_version 5370 (0.0008) -[2023-10-10 20:54:26,259][98560] Updated weights for policy 1, policy_version 5382 (0.0008) -[2023-10-10 20:54:26,622][98560] Updated weights for policy 1, policy_version 5392 (0.0007) -[2023-10-10 20:54:26,999][98560] Updated weights for policy 1, policy_version 5402 (0.0008) -[2023-10-10 20:54:30,294][98559] Updated weights for policy 0, policy_version 5380 (0.0008) -[2023-10-10 20:54:30,556][97672] Fps is (10 sec: 13107.7, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 11042816. Throughput: 0: 1687.1, 1: 1700.2. Samples: 2773904. Policy #0 lag: (min: 4.0, avg: 6.5, max: 36.0) -[2023-10-10 20:54:30,556][97672] Avg episode reward: [(0, '-11.000'), (1, '-10.740')] -[2023-10-10 20:54:30,557][98439] Saving new best policy, reward=-10.740! -[2023-10-10 20:54:30,692][98559] Updated weights for policy 0, policy_version 5390 (0.0009) -[2023-10-10 20:54:31,062][98559] Updated weights for policy 0, policy_version 5400 (0.0008) -[2023-10-10 20:54:31,069][98560] Updated weights for policy 1, policy_version 5412 (0.0007) -[2023-10-10 20:54:31,358][98385] Saving new best policy, reward=-11.000! -[2023-10-10 20:54:31,437][98560] Updated weights for policy 1, policy_version 5422 (0.0009) -[2023-10-10 20:54:31,805][98560] Updated weights for policy 1, policy_version 5432 (0.0009) -[2023-10-10 20:54:34,858][98559] Updated weights for policy 0, policy_version 5410 (0.0008) -[2023-10-10 20:54:35,228][98559] Updated weights for policy 0, policy_version 5420 (0.0008) -[2023-10-10 20:54:35,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 11108352. Throughput: 0: 1676.4, 1: 1699.8. Samples: 2794006. Policy #0 lag: (min: 4.0, avg: 6.5, max: 36.0) -[2023-10-10 20:54:35,557][97672] Avg episode reward: [(0, '-10.940'), (1, '-10.560')] -[2023-10-10 20:54:35,566][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000005440_5570560.pth... -[2023-10-10 20:54:35,612][98559] Updated weights for policy 0, policy_version 5430 (0.0008) -[2023-10-10 20:54:35,613][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000003872_3964928.pth -[2023-10-10 20:54:35,617][98439] Saving new best policy, reward=-10.560! -[2023-10-10 20:54:35,888][98560] Updated weights for policy 1, policy_version 5442 (0.0009) -[2023-10-10 20:54:35,987][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000005440_5570560.pth... -[2023-10-10 20:54:35,992][98559] Updated weights for policy 0, policy_version 5440 (0.0009) -[2023-10-10 20:54:36,015][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000003840_3932160.pth -[2023-10-10 20:54:36,019][98385] Saving new best policy, reward=-10.940! -[2023-10-10 20:54:36,258][98560] Updated weights for policy 1, policy_version 5452 (0.0007) -[2023-10-10 20:54:36,633][98560] Updated weights for policy 1, policy_version 5462 (0.0008) -[2023-10-10 20:54:36,999][98560] Updated weights for policy 1, policy_version 5472 (0.0008) -[2023-10-10 20:54:40,033][98559] Updated weights for policy 0, policy_version 5450 (0.0009) -[2023-10-10 20:54:40,399][98559] Updated weights for policy 0, policy_version 5460 (0.0008) -[2023-10-10 20:54:40,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 11173888. Throughput: 0: 1688.4, 1: 1688.1. Samples: 2803594. Policy #0 lag: (min: 2.0, avg: 5.1, max: 31.0) -[2023-10-10 20:54:40,557][97672] Avg episode reward: [(0, '-10.900'), (1, '-10.540')] -[2023-10-10 20:54:40,776][98559] Updated weights for policy 0, policy_version 5470 (0.0008) -[2023-10-10 20:54:40,833][98560] Updated weights for policy 1, policy_version 5482 (0.0007) -[2023-10-10 20:54:40,843][98385] Saving new best policy, reward=-10.900! -[2023-10-10 20:54:41,205][98560] Updated weights for policy 1, policy_version 5492 (0.0007) -[2023-10-10 20:54:41,567][98560] Updated weights for policy 1, policy_version 5502 (0.0007) -[2023-10-10 20:54:41,640][98439] Saving new best policy, reward=-10.540! -[2023-10-10 20:54:44,918][98559] Updated weights for policy 0, policy_version 5480 (0.0009) -[2023-10-10 20:54:45,293][98559] Updated weights for policy 0, policy_version 5490 (0.0010) -[2023-10-10 20:54:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 11239424. Throughput: 0: 1690.5, 1: 1700.9. Samples: 2824606. Policy #0 lag: (min: 2.0, avg: 5.1, max: 31.0) -[2023-10-10 20:54:45,556][97672] Avg episode reward: [(0, '-10.840'), (1, '-10.520')] -[2023-10-10 20:54:45,660][98559] Updated weights for policy 0, policy_version 5500 (0.0008) -[2023-10-10 20:54:45,661][98560] Updated weights for policy 1, policy_version 5512 (0.0007) -[2023-10-10 20:54:45,810][98385] Saving new best policy, reward=-10.840! -[2023-10-10 20:54:46,034][98560] Updated weights for policy 1, policy_version 5522 (0.0009) -[2023-10-10 20:54:46,400][98560] Updated weights for policy 1, policy_version 5532 (0.0008) -[2023-10-10 20:54:46,541][98439] Saving new best policy, reward=-10.520! -[2023-10-10 20:54:49,743][98559] Updated weights for policy 0, policy_version 5510 (0.0008) -[2023-10-10 20:54:50,117][98559] Updated weights for policy 0, policy_version 5520 (0.0007) -[2023-10-10 20:54:50,489][98559] Updated weights for policy 0, policy_version 5530 (0.0008) -[2023-10-10 20:54:50,500][98560] Updated weights for policy 1, policy_version 5542 (0.0008) -[2023-10-10 20:54:50,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 11304960. Throughput: 0: 1667.9, 1: 1695.0. Samples: 2844302. Policy #0 lag: (min: 17.0, avg: 17.6, max: 34.0) -[2023-10-10 20:54:50,556][97672] Avg episode reward: [(0, '-10.740'), (1, '-10.460')] -[2023-10-10 20:54:50,708][98385] Saving new best policy, reward=-10.740! -[2023-10-10 20:54:50,861][98560] Updated weights for policy 1, policy_version 5552 (0.0008) -[2023-10-10 20:54:51,236][98560] Updated weights for policy 1, policy_version 5562 (0.0007) -[2023-10-10 20:54:51,454][98439] Saving new best policy, reward=-10.460! -[2023-10-10 20:54:54,501][98559] Updated weights for policy 0, policy_version 5540 (0.0008) -[2023-10-10 20:54:54,871][98559] Updated weights for policy 0, policy_version 5550 (0.0008) -[2023-10-10 20:54:55,224][98560] Updated weights for policy 1, policy_version 5572 (0.0008) -[2023-10-10 20:54:55,251][98559] Updated weights for policy 0, policy_version 5560 (0.0007) -[2023-10-10 20:54:55,556][97672] Fps is (10 sec: 16383.6, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 11403264. Throughput: 0: 1688.5, 1: 1693.1. Samples: 2854270. Policy #0 lag: (min: 17.0, avg: 27.7, max: 49.0) -[2023-10-10 20:54:55,557][97672] Avg episode reward: [(0, '-10.640'), (1, '-10.200')] -[2023-10-10 20:54:55,559][98385] Saving new best policy, reward=-10.640! -[2023-10-10 20:54:55,589][98560] Updated weights for policy 1, policy_version 5582 (0.0008) -[2023-10-10 20:54:55,964][98560] Updated weights for policy 1, policy_version 5592 (0.0009) -[2023-10-10 20:54:56,251][98439] Saving new best policy, reward=-10.200! -[2023-10-10 20:54:59,193][98559] Updated weights for policy 0, policy_version 5570 (0.0007) -[2023-10-10 20:54:59,555][98559] Updated weights for policy 0, policy_version 5580 (0.0007) -[2023-10-10 20:54:59,922][98560] Updated weights for policy 1, policy_version 5602 (0.0007) -[2023-10-10 20:54:59,926][98559] Updated weights for policy 0, policy_version 5590 (0.0009) -[2023-10-10 20:55:00,295][98560] Updated weights for policy 1, policy_version 5612 (0.0008) -[2023-10-10 20:55:00,303][98559] Updated weights for policy 0, policy_version 5600 (0.0008) -[2023-10-10 20:55:00,556][97672] Fps is (10 sec: 16383.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 11468800. Throughput: 0: 1685.6, 1: 1704.7. Samples: 2875334. Policy #0 lag: (min: 17.0, avg: 27.7, max: 49.0) -[2023-10-10 20:55:00,557][97672] Avg episode reward: [(0, '-10.540'), (1, '-10.140')] -[2023-10-10 20:55:00,558][98385] Saving new best policy, reward=-10.540! -[2023-10-10 20:55:00,665][98560] Updated weights for policy 1, policy_version 5622 (0.0008) -[2023-10-10 20:55:01,034][98439] Saving new best policy, reward=-10.140! -[2023-10-10 20:55:01,035][98560] Updated weights for policy 1, policy_version 5632 (0.0009) -[2023-10-10 20:55:04,380][98559] Updated weights for policy 0, policy_version 5610 (0.0010) -[2023-10-10 20:55:04,754][98559] Updated weights for policy 0, policy_version 5620 (0.0010) -[2023-10-10 20:55:05,086][98560] Updated weights for policy 1, policy_version 5642 (0.0009) -[2023-10-10 20:55:05,132][98559] Updated weights for policy 0, policy_version 5630 (0.0008) -[2023-10-10 20:55:05,462][98560] Updated weights for policy 1, policy_version 5652 (0.0008) -[2023-10-10 20:55:05,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 11534336. Throughput: 0: 1664.2, 1: 1702.3. Samples: 2895140. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:55:05,557][97672] Avg episode reward: [(0, '-10.600'), (1, '-9.480')] -[2023-10-10 20:55:05,835][98560] Updated weights for policy 1, policy_version 5662 (0.0010) -[2023-10-10 20:55:05,909][98439] Saving new best policy, reward=-9.480! -[2023-10-10 20:55:09,265][98559] Updated weights for policy 0, policy_version 5640 (0.0008) -[2023-10-10 20:55:09,636][98559] Updated weights for policy 0, policy_version 5650 (0.0008) -[2023-10-10 20:55:09,844][98560] Updated weights for policy 1, policy_version 5672 (0.0008) -[2023-10-10 20:55:10,002][98559] Updated weights for policy 0, policy_version 5660 (0.0008) -[2023-10-10 20:55:10,219][98560] Updated weights for policy 1, policy_version 5682 (0.0008) -[2023-10-10 20:55:10,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 11599872. Throughput: 0: 1695.2, 1: 1705.2. Samples: 2905656. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:55:10,557][97672] Avg episode reward: [(0, '-10.400'), (1, '-9.360')] -[2023-10-10 20:55:10,558][98385] Saving new best policy, reward=-10.400! -[2023-10-10 20:55:10,596][98560] Updated weights for policy 1, policy_version 5692 (0.0007) -[2023-10-10 20:55:10,739][98439] Saving new best policy, reward=-9.360! -[2023-10-10 20:55:14,153][98559] Updated weights for policy 0, policy_version 5670 (0.0009) -[2023-10-10 20:55:14,531][98559] Updated weights for policy 0, policy_version 5680 (0.0009) -[2023-10-10 20:55:14,599][98560] Updated weights for policy 1, policy_version 5702 (0.0008) -[2023-10-10 20:55:14,905][98559] Updated weights for policy 0, policy_version 5690 (0.0007) -[2023-10-10 20:55:14,961][98560] Updated weights for policy 1, policy_version 5712 (0.0008) -[2023-10-10 20:55:15,335][98560] Updated weights for policy 1, policy_version 5722 (0.0008) -[2023-10-10 20:55:15,556][97672] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 11698176. Throughput: 0: 1682.4, 1: 1694.8. Samples: 2925880. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:55:15,556][97672] Avg episode reward: [(0, '-10.300'), (1, '-9.080')] -[2023-10-10 20:55:15,557][98439] Saving new best policy, reward=-9.080! -[2023-10-10 20:55:15,557][98385] Saving new best policy, reward=-10.300! -[2023-10-10 20:55:18,971][98559] Updated weights for policy 0, policy_version 5700 (0.0007) -[2023-10-10 20:55:19,188][98560] Updated weights for policy 1, policy_version 5732 (0.0009) -[2023-10-10 20:55:19,366][98559] Updated weights for policy 0, policy_version 5710 (0.0008) -[2023-10-10 20:55:19,549][98560] Updated weights for policy 1, policy_version 5742 (0.0007) -[2023-10-10 20:55:19,740][98559] Updated weights for policy 0, policy_version 5720 (0.0009) -[2023-10-10 20:55:19,922][98560] Updated weights for policy 1, policy_version 5752 (0.0007) -[2023-10-10 20:55:20,556][97672] Fps is (10 sec: 16384.4, 60 sec: 14199.6, 300 sec: 13662.6). Total num frames: 11763712. Throughput: 0: 1674.6, 1: 1686.7. Samples: 2945266. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:55:20,556][97672] Avg episode reward: [(0, '-10.280'), (1, '-9.180')] -[2023-10-10 20:55:20,565][98385] Saving new best policy, reward=-10.280! -[2023-10-10 20:55:23,847][98559] Updated weights for policy 0, policy_version 5730 (0.0009) -[2023-10-10 20:55:24,042][98560] Updated weights for policy 1, policy_version 5762 (0.0007) -[2023-10-10 20:55:24,219][98559] Updated weights for policy 0, policy_version 5740 (0.0008) -[2023-10-10 20:55:24,465][98560] Updated weights for policy 1, policy_version 5772 (0.0008) -[2023-10-10 20:55:24,593][98559] Updated weights for policy 0, policy_version 5750 (0.0007) -[2023-10-10 20:55:24,822][98560] Updated weights for policy 1, policy_version 5782 (0.0010) -[2023-10-10 20:55:24,966][98559] Updated weights for policy 0, policy_version 5760 (0.0009) -[2023-10-10 20:55:25,197][98560] Updated weights for policy 1, policy_version 5792 (0.0008) -[2023-10-10 20:55:25,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 11829248. Throughput: 0: 1690.3, 1: 1705.0. Samples: 2956384. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-10 20:55:25,557][97672] Avg episode reward: [(0, '-10.040'), (1, '-8.960')] -[2023-10-10 20:55:25,558][98439] Saving new best policy, reward=-8.960! -[2023-10-10 20:55:25,558][98385] Saving new best policy, reward=-10.040! -[2023-10-10 20:55:28,894][98559] Updated weights for policy 0, policy_version 5770 (0.0008) -[2023-10-10 20:55:29,123][98560] Updated weights for policy 1, policy_version 5802 (0.0009) -[2023-10-10 20:55:29,271][98559] Updated weights for policy 0, policy_version 5780 (0.0009) -[2023-10-10 20:55:29,497][98560] Updated weights for policy 1, policy_version 5812 (0.0009) -[2023-10-10 20:55:29,646][98559] Updated weights for policy 0, policy_version 5790 (0.0008) -[2023-10-10 20:55:29,862][98560] Updated weights for policy 1, policy_version 5822 (0.0007) -[2023-10-10 20:55:30,556][97672] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 11894784. Throughput: 0: 1669.0, 1: 1702.0. Samples: 2976304. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-10 20:55:30,557][97672] Avg episode reward: [(0, '-9.840'), (1, '-9.260')] -[2023-10-10 20:55:30,559][98385] Saving new best policy, reward=-9.840! -[2023-10-10 20:55:33,707][98559] Updated weights for policy 0, policy_version 5800 (0.0009) -[2023-10-10 20:55:33,753][98560] Updated weights for policy 1, policy_version 5832 (0.0007) -[2023-10-10 20:55:34,078][98559] Updated weights for policy 0, policy_version 5810 (0.0008) -[2023-10-10 20:55:34,115][98560] Updated weights for policy 1, policy_version 5842 (0.0009) -[2023-10-10 20:55:34,454][98559] Updated weights for policy 0, policy_version 5820 (0.0009) -[2023-10-10 20:55:34,488][98560] Updated weights for policy 1, policy_version 5852 (0.0008) -[2023-10-10 20:55:35,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 11960320. Throughput: 0: 1678.2, 1: 1680.8. Samples: 2995456. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:55:35,556][97672] Avg episode reward: [(0, '-9.680'), (1, '-9.220')] -[2023-10-10 20:55:35,563][98385] Saving new best policy, reward=-9.680! -[2023-10-10 20:55:38,547][98560] Updated weights for policy 1, policy_version 5862 (0.0009) -[2023-10-10 20:55:38,634][98559] Updated weights for policy 0, policy_version 5830 (0.0009) -[2023-10-10 20:55:38,907][98560] Updated weights for policy 1, policy_version 5872 (0.0008) -[2023-10-10 20:55:39,006][98559] Updated weights for policy 0, policy_version 5840 (0.0008) -[2023-10-10 20:55:39,280][98560] Updated weights for policy 1, policy_version 5882 (0.0008) -[2023-10-10 20:55:39,373][98559] Updated weights for policy 0, policy_version 5850 (0.0008) -[2023-10-10 20:55:40,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 12025856. Throughput: 0: 1685.0, 1: 1710.9. Samples: 3007082. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:55:40,557][97672] Avg episode reward: [(0, '-9.460'), (1, '-9.040')] -[2023-10-10 20:55:40,557][98385] Saving new best policy, reward=-9.460! -[2023-10-10 20:55:43,287][98560] Updated weights for policy 1, policy_version 5892 (0.0008) -[2023-10-10 20:55:43,443][98559] Updated weights for policy 0, policy_version 5860 (0.0008) -[2023-10-10 20:55:43,657][98560] Updated weights for policy 1, policy_version 5902 (0.0008) -[2023-10-10 20:55:43,812][98559] Updated weights for policy 0, policy_version 5870 (0.0008) -[2023-10-10 20:55:44,023][98560] Updated weights for policy 1, policy_version 5912 (0.0008) -[2023-10-10 20:55:44,183][98559] Updated weights for policy 0, policy_version 5880 (0.0009) -[2023-10-10 20:55:45,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 12091392. Throughput: 0: 1658.5, 1: 1695.8. Samples: 3026278. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-10 20:55:45,557][97672] Avg episode reward: [(0, '-9.460'), (1, '-8.900')] -[2023-10-10 20:55:45,558][98439] Saving new best policy, reward=-8.900! -[2023-10-10 20:55:47,949][98560] Updated weights for policy 1, policy_version 5922 (0.0009) -[2023-10-10 20:55:48,241][98559] Updated weights for policy 0, policy_version 5890 (0.0010) -[2023-10-10 20:55:48,314][98560] Updated weights for policy 1, policy_version 5932 (0.0008) -[2023-10-10 20:55:48,625][98559] Updated weights for policy 0, policy_version 5900 (0.0007) -[2023-10-10 20:55:48,694][98560] Updated weights for policy 1, policy_version 5942 (0.0008) -[2023-10-10 20:55:49,002][98559] Updated weights for policy 0, policy_version 5910 (0.0007) -[2023-10-10 20:55:49,063][98560] Updated weights for policy 1, policy_version 5952 (0.0007) -[2023-10-10 20:55:49,371][98559] Updated weights for policy 0, policy_version 5920 (0.0008) -[2023-10-10 20:55:50,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 12156928. Throughput: 0: 1672.7, 1: 1681.3. Samples: 3046068. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-10 20:55:50,556][97672] Avg episode reward: [(0, '-9.380'), (1, '-8.800')] -[2023-10-10 20:55:50,566][98385] Saving new best policy, reward=-9.380! -[2023-10-10 20:55:50,566][98439] Saving new best policy, reward=-8.800! -[2023-10-10 20:55:53,120][98560] Updated weights for policy 1, policy_version 5962 (0.0008) -[2023-10-10 20:55:53,346][98559] Updated weights for policy 0, policy_version 5930 (0.0009) -[2023-10-10 20:55:53,490][98560] Updated weights for policy 1, policy_version 5972 (0.0008) -[2023-10-10 20:55:53,716][98559] Updated weights for policy 0, policy_version 5940 (0.0008) -[2023-10-10 20:55:53,864][98560] Updated weights for policy 1, policy_version 5982 (0.0007) -[2023-10-10 20:55:54,095][98559] Updated weights for policy 0, policy_version 5950 (0.0007) -[2023-10-10 20:55:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 12222464. Throughput: 0: 1665.6, 1: 1710.3. Samples: 3057572. Policy #0 lag: (min: 17.0, avg: 22.5, max: 49.0) -[2023-10-10 20:55:55,557][97672] Avg episode reward: [(0, '-9.200'), (1, '-8.700')] -[2023-10-10 20:55:55,558][98439] Saving new best policy, reward=-8.700! -[2023-10-10 20:55:55,558][98385] Saving new best policy, reward=-9.200! -[2023-10-10 20:55:57,867][98560] Updated weights for policy 1, policy_version 5992 (0.0008) -[2023-10-10 20:55:58,128][98559] Updated weights for policy 0, policy_version 5960 (0.0007) -[2023-10-10 20:55:58,226][98560] Updated weights for policy 1, policy_version 6002 (0.0009) -[2023-10-10 20:55:58,503][98559] Updated weights for policy 0, policy_version 5970 (0.0009) -[2023-10-10 20:55:58,588][98560] Updated weights for policy 1, policy_version 6012 (0.0007) -[2023-10-10 20:55:58,867][98559] Updated weights for policy 0, policy_version 5980 (0.0010) -[2023-10-10 20:56:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 12288000. Throughput: 0: 1663.1, 1: 1685.7. Samples: 3076578. Policy #0 lag: (min: 17.0, avg: 22.5, max: 49.0) -[2023-10-10 20:56:00,556][97672] Avg episode reward: [(0, '-9.260'), (1, '-8.480')] -[2023-10-10 20:56:00,557][98439] Saving new best policy, reward=-8.480! -[2023-10-10 20:56:02,714][98560] Updated weights for policy 1, policy_version 6022 (0.0007) -[2023-10-10 20:56:02,824][98559] Updated weights for policy 0, policy_version 5990 (0.0009) -[2023-10-10 20:56:03,075][98560] Updated weights for policy 1, policy_version 6032 (0.0010) -[2023-10-10 20:56:03,196][98559] Updated weights for policy 0, policy_version 6000 (0.0007) -[2023-10-10 20:56:03,444][98560] Updated weights for policy 1, policy_version 6042 (0.0007) -[2023-10-10 20:56:03,564][98559] Updated weights for policy 0, policy_version 6010 (0.0007) -[2023-10-10 20:56:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 12353536. Throughput: 0: 1682.3, 1: 1697.1. Samples: 3097338. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-10 20:56:05,557][97672] Avg episode reward: [(0, '-9.120'), (1, '-8.220')] -[2023-10-10 20:56:05,570][98385] Saving new best policy, reward=-9.120! -[2023-10-10 20:56:05,570][98439] Saving new best policy, reward=-8.220! -[2023-10-10 20:56:07,303][98560] Updated weights for policy 1, policy_version 6052 (0.0007) -[2023-10-10 20:56:07,671][98560] Updated weights for policy 1, policy_version 6062 (0.0008) -[2023-10-10 20:56:07,899][98559] Updated weights for policy 0, policy_version 6020 (0.0007) -[2023-10-10 20:56:08,035][98560] Updated weights for policy 1, policy_version 6072 (0.0008) -[2023-10-10 20:56:08,288][98559] Updated weights for policy 0, policy_version 6030 (0.0007) -[2023-10-10 20:56:08,659][98559] Updated weights for policy 0, policy_version 6040 (0.0010) -[2023-10-10 20:56:10,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 12419072. Throughput: 0: 1666.5, 1: 1699.6. Samples: 3107860. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-10 20:56:10,556][97672] Avg episode reward: [(0, '-9.020'), (1, '-8.220')] -[2023-10-10 20:56:10,557][98385] Saving new best policy, reward=-9.020! -[2023-10-10 20:56:12,123][98560] Updated weights for policy 1, policy_version 6082 (0.0009) -[2023-10-10 20:56:12,489][98560] Updated weights for policy 1, policy_version 6092 (0.0007) -[2023-10-10 20:56:12,624][98559] Updated weights for policy 0, policy_version 6050 (0.0008) -[2023-10-10 20:56:12,861][98560] Updated weights for policy 1, policy_version 6102 (0.0008) -[2023-10-10 20:56:12,995][98559] Updated weights for policy 0, policy_version 6060 (0.0009) -[2023-10-10 20:56:13,221][98560] Updated weights for policy 1, policy_version 6112 (0.0009) -[2023-10-10 20:56:13,383][98559] Updated weights for policy 0, policy_version 6070 (0.0010) -[2023-10-10 20:56:13,763][98559] Updated weights for policy 0, policy_version 6080 (0.0010) -[2023-10-10 20:56:15,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 12484608. Throughput: 0: 1670.4, 1: 1685.7. Samples: 3127328. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-10 20:56:15,557][97672] Avg episode reward: [(0, '-8.840'), (1, '-8.040')] -[2023-10-10 20:56:15,557][98385] Saving new best policy, reward=-8.840! -[2023-10-10 20:56:15,557][98439] Saving new best policy, reward=-8.040! -[2023-10-10 20:56:17,247][98560] Updated weights for policy 1, policy_version 6122 (0.0009) -[2023-10-10 20:56:17,627][98560] Updated weights for policy 1, policy_version 6132 (0.0007) -[2023-10-10 20:56:17,781][98559] Updated weights for policy 0, policy_version 6090 (0.0007) -[2023-10-10 20:56:18,003][98560] Updated weights for policy 1, policy_version 6142 (0.0007) -[2023-10-10 20:56:18,161][98559] Updated weights for policy 0, policy_version 6100 (0.0009) -[2023-10-10 20:56:18,540][98559] Updated weights for policy 0, policy_version 6110 (0.0007) -[2023-10-10 20:56:20,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 12550144. Throughput: 0: 1687.1, 1: 1710.5. Samples: 3148352. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-10 20:56:20,557][97672] Avg episode reward: [(0, '-8.620'), (1, '-8.040')] -[2023-10-10 20:56:20,567][98385] Saving new best policy, reward=-8.620! -[2023-10-10 20:56:22,163][98560] Updated weights for policy 1, policy_version 6152 (0.0008) -[2023-10-10 20:56:22,534][98560] Updated weights for policy 1, policy_version 6162 (0.0008) -[2023-10-10 20:56:22,571][98559] Updated weights for policy 0, policy_version 6120 (0.0009) -[2023-10-10 20:56:22,893][98560] Updated weights for policy 1, policy_version 6172 (0.0009) -[2023-10-10 20:56:22,943][98559] Updated weights for policy 0, policy_version 6130 (0.0008) -[2023-10-10 20:56:23,311][98559] Updated weights for policy 0, policy_version 6140 (0.0008) -[2023-10-10 20:56:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 12615680. Throughput: 0: 1664.9, 1: 1688.6. Samples: 3157988. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-10 20:56:25,557][97672] Avg episode reward: [(0, '-8.520'), (1, '-8.060')] -[2023-10-10 20:56:25,557][98385] Saving new best policy, reward=-8.520! -[2023-10-10 20:56:26,721][98560] Updated weights for policy 1, policy_version 6182 (0.0008) -[2023-10-10 20:56:27,081][98560] Updated weights for policy 1, policy_version 6192 (0.0010) -[2023-10-10 20:56:27,343][98559] Updated weights for policy 0, policy_version 6150 (0.0007) -[2023-10-10 20:56:27,449][98560] Updated weights for policy 1, policy_version 6202 (0.0009) -[2023-10-10 20:56:27,716][98559] Updated weights for policy 0, policy_version 6160 (0.0007) -[2023-10-10 20:56:28,082][98559] Updated weights for policy 0, policy_version 6170 (0.0010) -[2023-10-10 20:56:30,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 12681216. Throughput: 0: 1692.0, 1: 1689.7. Samples: 3178456. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-10 20:56:30,557][97672] Avg episode reward: [(0, '-8.600'), (1, '-7.920')] -[2023-10-10 20:56:30,558][98439] Saving new best policy, reward=-7.920! -[2023-10-10 20:56:31,579][98560] Updated weights for policy 1, policy_version 6212 (0.0010) -[2023-10-10 20:56:31,948][98560] Updated weights for policy 1, policy_version 6222 (0.0007) -[2023-10-10 20:56:31,949][98559] Updated weights for policy 0, policy_version 6180 (0.0009) -[2023-10-10 20:56:32,313][98560] Updated weights for policy 1, policy_version 6232 (0.0008) -[2023-10-10 20:56:32,316][98559] Updated weights for policy 0, policy_version 6190 (0.0009) -[2023-10-10 20:56:32,687][98559] Updated weights for policy 0, policy_version 6200 (0.0009) -[2023-10-10 20:56:35,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 12746752. Throughput: 0: 1703.6, 1: 1707.6. Samples: 3199572. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-10 20:56:35,557][97672] Avg episode reward: [(0, '-8.660'), (1, '-7.980')] -[2023-10-10 20:56:35,569][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000006240_6389760.pth... -[2023-10-10 20:56:35,569][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000006208_6356992.pth... -[2023-10-10 20:56:35,600][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000004672_4784128.pth -[2023-10-10 20:56:35,601][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000004640_4751360.pth -[2023-10-10 20:56:36,397][98560] Updated weights for policy 1, policy_version 6242 (0.0009) -[2023-10-10 20:56:36,651][98559] Updated weights for policy 0, policy_version 6210 (0.0011) -[2023-10-10 20:56:36,767][98560] Updated weights for policy 1, policy_version 6252 (0.0008) -[2023-10-10 20:56:37,016][98559] Updated weights for policy 0, policy_version 6220 (0.0008) -[2023-10-10 20:56:37,134][98560] Updated weights for policy 1, policy_version 6262 (0.0007) -[2023-10-10 20:56:37,391][98559] Updated weights for policy 0, policy_version 6230 (0.0008) -[2023-10-10 20:56:37,496][98560] Updated weights for policy 1, policy_version 6272 (0.0007) -[2023-10-10 20:56:37,755][98559] Updated weights for policy 0, policy_version 6240 (0.0007) -[2023-10-10 20:56:40,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 12812288. Throughput: 0: 1681.6, 1: 1677.1. Samples: 3208710. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-10 20:56:40,557][97672] Avg episode reward: [(0, '-8.440'), (1, '-8.020')] -[2023-10-10 20:56:40,559][98385] Saving new best policy, reward=-8.440! -[2023-10-10 20:56:41,580][98560] Updated weights for policy 1, policy_version 6282 (0.0010) -[2023-10-10 20:56:41,939][98560] Updated weights for policy 1, policy_version 6292 (0.0007) -[2023-10-10 20:56:41,952][98559] Updated weights for policy 0, policy_version 6250 (0.0009) -[2023-10-10 20:56:42,309][98560] Updated weights for policy 1, policy_version 6302 (0.0008) -[2023-10-10 20:56:42,326][98559] Updated weights for policy 0, policy_version 6260 (0.0007) -[2023-10-10 20:56:42,697][98559] Updated weights for policy 0, policy_version 6270 (0.0007) -[2023-10-10 20:56:45,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 12877824. Throughput: 0: 1688.2, 1: 1707.3. Samples: 3229378. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-10 20:56:45,557][97672] Avg episode reward: [(0, '-8.160'), (1, '-7.940')] -[2023-10-10 20:56:45,558][98385] Saving new best policy, reward=-8.160! -[2023-10-10 20:56:46,184][98560] Updated weights for policy 1, policy_version 6312 (0.0007) -[2023-10-10 20:56:46,548][98560] Updated weights for policy 1, policy_version 6322 (0.0007) -[2023-10-10 20:56:46,854][98559] Updated weights for policy 0, policy_version 6280 (0.0008) -[2023-10-10 20:56:46,918][98560] Updated weights for policy 1, policy_version 6332 (0.0008) -[2023-10-10 20:56:47,223][98559] Updated weights for policy 0, policy_version 6290 (0.0010) -[2023-10-10 20:56:47,602][98559] Updated weights for policy 0, policy_version 6300 (0.0010) -[2023-10-10 20:56:50,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 12943360. Throughput: 0: 1689.1, 1: 1707.4. Samples: 3250178. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-10 20:56:50,557][97672] Avg episode reward: [(0, '-8.420'), (1, '-7.920')] -[2023-10-10 20:56:51,003][98560] Updated weights for policy 1, policy_version 6342 (0.0008) -[2023-10-10 20:56:51,362][98560] Updated weights for policy 1, policy_version 6352 (0.0007) -[2023-10-10 20:56:51,549][98559] Updated weights for policy 0, policy_version 6310 (0.0010) -[2023-10-10 20:56:51,731][98560] Updated weights for policy 1, policy_version 6362 (0.0008) -[2023-10-10 20:56:51,921][98559] Updated weights for policy 0, policy_version 6320 (0.0007) -[2023-10-10 20:56:52,295][98559] Updated weights for policy 0, policy_version 6330 (0.0010) -[2023-10-10 20:56:55,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 13008896. Throughput: 0: 1681.4, 1: 1685.9. Samples: 3259388. Policy #0 lag: (min: 31.0, avg: 36.2, max: 63.0) -[2023-10-10 20:56:55,556][97672] Avg episode reward: [(0, '-8.200'), (1, '-7.340')] -[2023-10-10 20:56:55,749][98560] Updated weights for policy 1, policy_version 6372 (0.0008) -[2023-10-10 20:56:56,105][98560] Updated weights for policy 1, policy_version 6382 (0.0007) -[2023-10-10 20:56:56,318][98559] Updated weights for policy 0, policy_version 6340 (0.0009) -[2023-10-10 20:56:56,469][98560] Updated weights for policy 1, policy_version 6392 (0.0008) -[2023-10-10 20:56:56,709][98559] Updated weights for policy 0, policy_version 6350 (0.0007) -[2023-10-10 20:56:56,769][98439] Saving new best policy, reward=-7.340! -[2023-10-10 20:56:57,070][98559] Updated weights for policy 0, policy_version 6360 (0.0009) -[2023-10-10 20:57:00,534][98560] Updated weights for policy 1, policy_version 6402 (0.0008) -[2023-10-10 20:57:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 13074432. Throughput: 0: 1694.2, 1: 1699.1. Samples: 3280026. Policy #0 lag: (min: 31.0, avg: 36.2, max: 63.0) -[2023-10-10 20:57:00,557][97672] Avg episode reward: [(0, '-8.300'), (1, '-7.400')] -[2023-10-10 20:57:00,911][98560] Updated weights for policy 1, policy_version 6412 (0.0009) -[2023-10-10 20:57:01,156][98559] Updated weights for policy 0, policy_version 6370 (0.0009) -[2023-10-10 20:57:01,290][98560] Updated weights for policy 1, policy_version 6422 (0.0009) -[2023-10-10 20:57:01,522][98559] Updated weights for policy 0, policy_version 6380 (0.0008) -[2023-10-10 20:57:01,656][98560] Updated weights for policy 1, policy_version 6432 (0.0009) -[2023-10-10 20:57:01,895][98559] Updated weights for policy 0, policy_version 6390 (0.0007) -[2023-10-10 20:57:02,265][98559] Updated weights for policy 0, policy_version 6400 (0.0010) -[2023-10-10 20:57:05,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 13139968. Throughput: 0: 1688.0, 1: 1698.4. Samples: 3300744. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-10 20:57:05,557][97672] Avg episode reward: [(0, '-8.160'), (1, '-7.220')] -[2023-10-10 20:57:05,808][98560] Updated weights for policy 1, policy_version 6442 (0.0011) -[2023-10-10 20:57:06,183][98560] Updated weights for policy 1, policy_version 6452 (0.0007) -[2023-10-10 20:57:06,277][98559] Updated weights for policy 0, policy_version 6410 (0.0007) -[2023-10-10 20:57:06,555][98560] Updated weights for policy 1, policy_version 6462 (0.0007) -[2023-10-10 20:57:06,631][98439] Saving new best policy, reward=-7.220! -[2023-10-10 20:57:06,645][98559] Updated weights for policy 0, policy_version 6420 (0.0007) -[2023-10-10 20:57:07,029][98559] Updated weights for policy 0, policy_version 6430 (0.0008) -[2023-10-10 20:57:10,546][98560] Updated weights for policy 1, policy_version 6472 (0.0008) -[2023-10-10 20:57:10,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.1, 300 sec: 13440.4). Total num frames: 13205504. Throughput: 0: 1686.4, 1: 1685.0. Samples: 3309702. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-10 20:57:10,557][97672] Avg episode reward: [(0, '-8.100'), (1, '-7.220')] -[2023-10-10 20:57:10,558][98385] Saving new best policy, reward=-8.100! -[2023-10-10 20:57:10,910][98560] Updated weights for policy 1, policy_version 6482 (0.0009) -[2023-10-10 20:57:11,029][98559] Updated weights for policy 0, policy_version 6440 (0.0008) -[2023-10-10 20:57:11,280][98560] Updated weights for policy 1, policy_version 6492 (0.0008) -[2023-10-10 20:57:11,405][98559] Updated weights for policy 0, policy_version 6450 (0.0009) -[2023-10-10 20:57:11,777][98559] Updated weights for policy 0, policy_version 6460 (0.0007) -[2023-10-10 20:57:15,335][98560] Updated weights for policy 1, policy_version 6502 (0.0008) -[2023-10-10 20:57:15,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 13271040. Throughput: 0: 1692.1, 1: 1696.6. Samples: 3330946. Policy #0 lag: (min: 31.0, avg: 31.6, max: 49.0) -[2023-10-10 20:57:15,556][97672] Avg episode reward: [(0, '-7.940'), (1, '-7.340')] -[2023-10-10 20:57:15,627][98559] Updated weights for policy 0, policy_version 6470 (0.0007) -[2023-10-10 20:57:15,703][98560] Updated weights for policy 1, policy_version 6512 (0.0008) -[2023-10-10 20:57:16,001][98559] Updated weights for policy 0, policy_version 6480 (0.0008) -[2023-10-10 20:57:16,069][98560] Updated weights for policy 1, policy_version 6522 (0.0008) -[2023-10-10 20:57:16,372][98559] Updated weights for policy 0, policy_version 6490 (0.0010) -[2023-10-10 20:57:16,598][98385] Saving new best policy, reward=-7.940! -[2023-10-10 20:57:20,167][98560] Updated weights for policy 1, policy_version 6532 (0.0007) -[2023-10-10 20:57:20,507][98559] Updated weights for policy 0, policy_version 6500 (0.0007) -[2023-10-10 20:57:20,534][98560] Updated weights for policy 1, policy_version 6542 (0.0007) -[2023-10-10 20:57:20,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 13440.4). Total num frames: 13336576. Throughput: 0: 1689.4, 1: 1691.0. Samples: 3351692. Policy #0 lag: (min: 31.0, avg: 31.6, max: 49.0) -[2023-10-10 20:57:20,556][97672] Avg episode reward: [(0, '-7.800'), (1, '-7.360')] -[2023-10-10 20:57:20,879][98559] Updated weights for policy 0, policy_version 6510 (0.0009) -[2023-10-10 20:57:20,894][98560] Updated weights for policy 1, policy_version 6552 (0.0009) -[2023-10-10 20:57:21,254][98559] Updated weights for policy 0, policy_version 6520 (0.0009) -[2023-10-10 20:57:21,555][98385] Saving new best policy, reward=-7.800! -[2023-10-10 20:57:25,079][98560] Updated weights for policy 1, policy_version 6562 (0.0008) -[2023-10-10 20:57:25,283][98559] Updated weights for policy 0, policy_version 6530 (0.0007) -[2023-10-10 20:57:25,445][98560] Updated weights for policy 1, policy_version 6572 (0.0007) -[2023-10-10 20:57:25,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 13402112. Throughput: 0: 1689.6, 1: 1689.7. Samples: 3360780. Policy #0 lag: (min: 0.0, avg: 24.8, max: 32.0) -[2023-10-10 20:57:25,557][97672] Avg episode reward: [(0, '-7.660'), (1, '-7.180')] -[2023-10-10 20:57:25,654][98559] Updated weights for policy 0, policy_version 6540 (0.0008) -[2023-10-10 20:57:25,820][98560] Updated weights for policy 1, policy_version 6582 (0.0009) -[2023-10-10 20:57:26,035][98559] Updated weights for policy 0, policy_version 6550 (0.0007) -[2023-10-10 20:57:26,184][98560] Updated weights for policy 1, policy_version 6592 (0.0009) -[2023-10-10 20:57:26,184][98439] Saving new best policy, reward=-7.180! -[2023-10-10 20:57:26,400][98385] Saving new best policy, reward=-7.660! -[2023-10-10 20:57:26,400][98559] Updated weights for policy 0, policy_version 6560 (0.0009) -[2023-10-10 20:57:30,249][98560] Updated weights for policy 1, policy_version 6602 (0.0009) -[2023-10-10 20:57:30,484][98559] Updated weights for policy 0, policy_version 6570 (0.0009) -[2023-10-10 20:57:30,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 13467648. Throughput: 0: 1699.0, 1: 1684.1. Samples: 3381620. Policy #0 lag: (min: 0.0, avg: 24.8, max: 32.0) -[2023-10-10 20:57:30,557][97672] Avg episode reward: [(0, '-7.660'), (1, '-7.080')] -[2023-10-10 20:57:30,628][98560] Updated weights for policy 1, policy_version 6612 (0.0008) -[2023-10-10 20:57:30,858][98559] Updated weights for policy 0, policy_version 6580 (0.0008) -[2023-10-10 20:57:30,995][98560] Updated weights for policy 1, policy_version 6622 (0.0009) -[2023-10-10 20:57:31,064][98439] Saving new best policy, reward=-7.080! -[2023-10-10 20:57:31,235][98559] Updated weights for policy 0, policy_version 6590 (0.0007) -[2023-10-10 20:57:34,995][98560] Updated weights for policy 1, policy_version 6632 (0.0009) -[2023-10-10 20:57:35,167][98559] Updated weights for policy 0, policy_version 6600 (0.0008) -[2023-10-10 20:57:35,371][98560] Updated weights for policy 1, policy_version 6642 (0.0008) -[2023-10-10 20:57:35,547][98559] Updated weights for policy 0, policy_version 6610 (0.0008) -[2023-10-10 20:57:35,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 13440.4). Total num frames: 13533184. Throughput: 0: 1689.1, 1: 1687.0. Samples: 3402100. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:57:35,556][97672] Avg episode reward: [(0, '-7.760'), (1, '-7.220')] -[2023-10-10 20:57:35,735][98560] Updated weights for policy 1, policy_version 6652 (0.0009) -[2023-10-10 20:57:35,916][98559] Updated weights for policy 0, policy_version 6620 (0.0007) -[2023-10-10 20:57:39,666][98560] Updated weights for policy 1, policy_version 6662 (0.0008) -[2023-10-10 20:57:39,992][98559] Updated weights for policy 0, policy_version 6630 (0.0008) -[2023-10-10 20:57:40,037][98560] Updated weights for policy 1, policy_version 6672 (0.0008) -[2023-10-10 20:57:40,364][98559] Updated weights for policy 0, policy_version 6640 (0.0009) -[2023-10-10 20:57:40,393][98560] Updated weights for policy 1, policy_version 6682 (0.0008) -[2023-10-10 20:57:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 13598720. Throughput: 0: 1698.0, 1: 1688.6. Samples: 3411786. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:57:40,557][97672] Avg episode reward: [(0, '-7.720'), (1, '-7.120')] -[2023-10-10 20:57:40,728][98559] Updated weights for policy 0, policy_version 6650 (0.0010) -[2023-10-10 20:57:44,437][98560] Updated weights for policy 1, policy_version 6692 (0.0009) -[2023-10-10 20:57:44,800][98560] Updated weights for policy 1, policy_version 6702 (0.0007) -[2023-10-10 20:57:44,874][98559] Updated weights for policy 0, policy_version 6660 (0.0009) -[2023-10-10 20:57:45,165][98560] Updated weights for policy 1, policy_version 6712 (0.0008) -[2023-10-10 20:57:45,254][98559] Updated weights for policy 0, policy_version 6670 (0.0008) -[2023-10-10 20:57:45,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 13697024. Throughput: 0: 1699.6, 1: 1690.7. Samples: 3432592. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-10 20:57:45,556][97672] Avg episode reward: [(0, '-7.760'), (1, '-7.360')] -[2023-10-10 20:57:45,629][98559] Updated weights for policy 0, policy_version 6680 (0.0008) -[2023-10-10 20:57:49,302][98560] Updated weights for policy 1, policy_version 6722 (0.0008) -[2023-10-10 20:57:49,632][98559] Updated weights for policy 0, policy_version 6690 (0.0007) -[2023-10-10 20:57:49,667][98560] Updated weights for policy 1, policy_version 6732 (0.0008) -[2023-10-10 20:57:49,999][98559] Updated weights for policy 0, policy_version 6700 (0.0009) -[2023-10-10 20:57:50,036][98560] Updated weights for policy 1, policy_version 6742 (0.0010) -[2023-10-10 20:57:50,373][98559] Updated weights for policy 0, policy_version 6710 (0.0009) -[2023-10-10 20:57:50,401][98560] Updated weights for policy 1, policy_version 6752 (0.0008) -[2023-10-10 20:57:50,556][97672] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 13762560. Throughput: 0: 1679.6, 1: 1680.9. Samples: 3451966. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-10 20:57:50,557][97672] Avg episode reward: [(0, '-7.660'), (1, '-7.380')] -[2023-10-10 20:57:50,750][98559] Updated weights for policy 0, policy_version 6720 (0.0009) -[2023-10-10 20:57:54,611][98560] Updated weights for policy 1, policy_version 6762 (0.0010) -[2023-10-10 20:57:54,846][98559] Updated weights for policy 0, policy_version 6730 (0.0010) -[2023-10-10 20:57:54,997][98560] Updated weights for policy 1, policy_version 6772 (0.0008) -[2023-10-10 20:57:55,219][98559] Updated weights for policy 0, policy_version 6740 (0.0009) -[2023-10-10 20:57:55,374][98560] Updated weights for policy 1, policy_version 6782 (0.0009) -[2023-10-10 20:57:55,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 13828096. Throughput: 0: 1700.3, 1: 1695.7. Samples: 3462522. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:57:55,557][97672] Avg episode reward: [(0, '-7.740'), (1, '-6.900')] -[2023-10-10 20:57:55,558][98439] Saving new best policy, reward=-6.900! -[2023-10-10 20:57:55,588][98559] Updated weights for policy 0, policy_version 6750 (0.0009) -[2023-10-10 20:57:59,368][98560] Updated weights for policy 1, policy_version 6792 (0.0007) -[2023-10-10 20:57:59,603][98559] Updated weights for policy 0, policy_version 6760 (0.0008) -[2023-10-10 20:57:59,738][98560] Updated weights for policy 1, policy_version 6802 (0.0007) -[2023-10-10 20:57:59,968][98559] Updated weights for policy 0, policy_version 6770 (0.0008) -[2023-10-10 20:58:00,097][98560] Updated weights for policy 1, policy_version 6812 (0.0008) -[2023-10-10 20:58:00,337][98559] Updated weights for policy 0, policy_version 6780 (0.0007) -[2023-10-10 20:58:00,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 13926400. Throughput: 0: 1693.6, 1: 1689.3. Samples: 3483178. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:58:00,556][97672] Avg episode reward: [(0, '-7.820'), (1, '-6.820')] -[2023-10-10 20:58:00,557][98439] Saving new best policy, reward=-6.820! -[2023-10-10 20:58:03,849][98560] Updated weights for policy 1, policy_version 6822 (0.0008) -[2023-10-10 20:58:04,224][98560] Updated weights for policy 1, policy_version 6832 (0.0009) -[2023-10-10 20:58:04,452][98559] Updated weights for policy 0, policy_version 6790 (0.0009) -[2023-10-10 20:58:04,587][98560] Updated weights for policy 1, policy_version 6842 (0.0008) -[2023-10-10 20:58:04,821][98559] Updated weights for policy 0, policy_version 6800 (0.0009) -[2023-10-10 20:58:05,211][98559] Updated weights for policy 0, policy_version 6810 (0.0008) -[2023-10-10 20:58:05,556][97672] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 13991936. Throughput: 0: 1672.1, 1: 1673.8. Samples: 3502256. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 20:58:05,556][97672] Avg episode reward: [(0, '-7.900'), (1, '-6.880')] -[2023-10-10 20:58:08,682][98560] Updated weights for policy 1, policy_version 6852 (0.0007) -[2023-10-10 20:58:09,048][98560] Updated weights for policy 1, policy_version 6862 (0.0009) -[2023-10-10 20:58:09,177][98559] Updated weights for policy 0, policy_version 6820 (0.0008) -[2023-10-10 20:58:09,416][98560] Updated weights for policy 1, policy_version 6872 (0.0008) -[2023-10-10 20:58:09,539][98559] Updated weights for policy 0, policy_version 6830 (0.0009) -[2023-10-10 20:58:09,917][98559] Updated weights for policy 0, policy_version 6840 (0.0008) -[2023-10-10 20:58:10,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 14057472. Throughput: 0: 1697.5, 1: 1703.4. Samples: 3513822. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 20:58:10,557][97672] Avg episode reward: [(0, '-7.740'), (1, '-6.780')] -[2023-10-10 20:58:10,558][98439] Saving new best policy, reward=-6.780! -[2023-10-10 20:58:13,320][98560] Updated weights for policy 1, policy_version 6882 (0.0009) -[2023-10-10 20:58:13,683][98560] Updated weights for policy 1, policy_version 6892 (0.0007) -[2023-10-10 20:58:13,985][98559] Updated weights for policy 0, policy_version 6850 (0.0007) -[2023-10-10 20:58:14,054][98560] Updated weights for policy 1, policy_version 6902 (0.0009) -[2023-10-10 20:58:14,356][98559] Updated weights for policy 0, policy_version 6860 (0.0007) -[2023-10-10 20:58:14,425][98560] Updated weights for policy 1, policy_version 6912 (0.0010) -[2023-10-10 20:58:14,723][98559] Updated weights for policy 0, policy_version 6870 (0.0008) -[2023-10-10 20:58:15,101][98559] Updated weights for policy 0, policy_version 6880 (0.0007) -[2023-10-10 20:58:15,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 14123008. Throughput: 0: 1686.8, 1: 1696.3. Samples: 3533856. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 20:58:15,557][97672] Avg episode reward: [(0, '-7.700'), (1, '-6.720')] -[2023-10-10 20:58:15,558][98439] Saving new best policy, reward=-6.720! -[2023-10-10 20:58:18,387][98560] Updated weights for policy 1, policy_version 6922 (0.0010) -[2023-10-10 20:58:18,758][98560] Updated weights for policy 1, policy_version 6932 (0.0009) -[2023-10-10 20:58:19,059][98559] Updated weights for policy 0, policy_version 6890 (0.0008) -[2023-10-10 20:58:19,118][98560] Updated weights for policy 1, policy_version 6942 (0.0009) -[2023-10-10 20:58:19,429][98559] Updated weights for policy 0, policy_version 6900 (0.0008) -[2023-10-10 20:58:19,795][98559] Updated weights for policy 0, policy_version 6910 (0.0009) -[2023-10-10 20:58:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 14188544. Throughput: 0: 1679.3, 1: 1676.2. Samples: 3553096. Policy #0 lag: (min: 24.0, avg: 44.7, max: 56.0) -[2023-10-10 20:58:20,557][97672] Avg episode reward: [(0, '-7.780'), (1, '-6.640')] -[2023-10-10 20:58:20,565][98439] Saving new best policy, reward=-6.640! -[2023-10-10 20:58:23,305][98560] Updated weights for policy 1, policy_version 6952 (0.0007) -[2023-10-10 20:58:23,678][98560] Updated weights for policy 1, policy_version 6962 (0.0009) -[2023-10-10 20:58:23,799][98559] Updated weights for policy 0, policy_version 6920 (0.0008) -[2023-10-10 20:58:24,047][98560] Updated weights for policy 1, policy_version 6972 (0.0008) -[2023-10-10 20:58:24,163][98559] Updated weights for policy 0, policy_version 6930 (0.0007) -[2023-10-10 20:58:24,548][98559] Updated weights for policy 0, policy_version 6940 (0.0011) -[2023-10-10 20:58:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 14254080. Throughput: 0: 1701.2, 1: 1704.8. Samples: 3565058. Policy #0 lag: (min: 24.0, avg: 44.7, max: 56.0) -[2023-10-10 20:58:25,557][97672] Avg episode reward: [(0, '-7.620'), (1, '-6.700')] -[2023-10-10 20:58:25,558][98385] Saving new best policy, reward=-7.620! -[2023-10-10 20:58:28,096][98560] Updated weights for policy 1, policy_version 6982 (0.0008) -[2023-10-10 20:58:28,450][98560] Updated weights for policy 1, policy_version 6992 (0.0008) -[2023-10-10 20:58:28,620][98559] Updated weights for policy 0, policy_version 6950 (0.0009) -[2023-10-10 20:58:28,818][98560] Updated weights for policy 1, policy_version 7002 (0.0008) -[2023-10-10 20:58:28,995][98559] Updated weights for policy 0, policy_version 6960 (0.0007) -[2023-10-10 20:58:29,360][98559] Updated weights for policy 0, policy_version 6970 (0.0008) -[2023-10-10 20:58:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 14319616. Throughput: 0: 1681.9, 1: 1685.1. Samples: 3584108. Policy #0 lag: (min: 31.0, avg: 39.9, max: 63.0) -[2023-10-10 20:58:30,557][97672] Avg episode reward: [(0, '-7.660'), (1, '-6.500')] -[2023-10-10 20:58:30,559][98439] Saving new best policy, reward=-6.500! -[2023-10-10 20:58:32,792][98560] Updated weights for policy 1, policy_version 7012 (0.0010) -[2023-10-10 20:58:33,168][98560] Updated weights for policy 1, policy_version 7022 (0.0009) -[2023-10-10 20:58:33,409][98559] Updated weights for policy 0, policy_version 6980 (0.0008) -[2023-10-10 20:58:33,529][98560] Updated weights for policy 1, policy_version 7032 (0.0009) -[2023-10-10 20:58:33,796][98559] Updated weights for policy 0, policy_version 6990 (0.0007) -[2023-10-10 20:58:34,176][98559] Updated weights for policy 0, policy_version 7000 (0.0009) -[2023-10-10 20:58:35,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 14385152. Throughput: 0: 1697.0, 1: 1683.4. Samples: 3604084. Policy #0 lag: (min: 31.0, avg: 39.9, max: 63.0) -[2023-10-10 20:58:35,557][97672] Avg episode reward: [(0, '-7.660'), (1, '-6.380')] -[2023-10-10 20:58:35,565][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000007040_7208960.pth... -[2023-10-10 20:58:35,565][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000007008_7176192.pth... -[2023-10-10 20:58:35,604][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000005440_5570560.pth -[2023-10-10 20:58:35,606][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000005440_5570560.pth -[2023-10-10 20:58:35,609][98439] Saving new best policy, reward=-6.380! -[2023-10-10 20:58:37,541][98560] Updated weights for policy 1, policy_version 7042 (0.0009) -[2023-10-10 20:58:37,912][98560] Updated weights for policy 1, policy_version 7052 (0.0008) -[2023-10-10 20:58:37,919][98559] Updated weights for policy 0, policy_version 7010 (0.0009) -[2023-10-10 20:58:38,279][98560] Updated weights for policy 1, policy_version 7062 (0.0007) -[2023-10-10 20:58:38,295][98559] Updated weights for policy 0, policy_version 7020 (0.0009) -[2023-10-10 20:58:38,646][98560] Updated weights for policy 1, policy_version 7072 (0.0008) -[2023-10-10 20:58:38,663][98559] Updated weights for policy 0, policy_version 7030 (0.0009) -[2023-10-10 20:58:39,043][98559] Updated weights for policy 0, policy_version 7040 (0.0011) -[2023-10-10 20:58:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 14450688. Throughput: 0: 1696.1, 1: 1699.8. Samples: 3615336. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-10-10 20:58:40,557][97672] Avg episode reward: [(0, '-7.620'), (1, '-6.140')] -[2023-10-10 20:58:40,558][98439] Saving new best policy, reward=-6.140! -[2023-10-10 20:58:42,716][98560] Updated weights for policy 1, policy_version 7082 (0.0011) -[2023-10-10 20:58:43,034][98559] Updated weights for policy 0, policy_version 7050 (0.0008) -[2023-10-10 20:58:43,074][98560] Updated weights for policy 1, policy_version 7092 (0.0008) -[2023-10-10 20:58:43,415][98559] Updated weights for policy 0, policy_version 7060 (0.0007) -[2023-10-10 20:58:43,448][98560] Updated weights for policy 1, policy_version 7102 (0.0007) -[2023-10-10 20:58:43,793][98559] Updated weights for policy 0, policy_version 7070 (0.0010) -[2023-10-10 20:58:45,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 14516224. Throughput: 0: 1677.5, 1: 1681.7. Samples: 3634344. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-10-10 20:58:45,557][97672] Avg episode reward: [(0, '-7.560'), (1, '-6.140')] -[2023-10-10 20:58:45,558][98385] Saving new best policy, reward=-7.560! -[2023-10-10 20:58:47,709][98560] Updated weights for policy 1, policy_version 7112 (0.0007) -[2023-10-10 20:58:47,827][98559] Updated weights for policy 0, policy_version 7080 (0.0008) -[2023-10-10 20:58:48,071][98560] Updated weights for policy 1, policy_version 7122 (0.0007) -[2023-10-10 20:58:48,200][98559] Updated weights for policy 0, policy_version 7090 (0.0010) -[2023-10-10 20:58:48,440][98560] Updated weights for policy 1, policy_version 7132 (0.0008) -[2023-10-10 20:58:48,570][98559] Updated weights for policy 0, policy_version 7100 (0.0010) -[2023-10-10 20:58:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 14581760. Throughput: 0: 1701.9, 1: 1691.1. Samples: 3654946. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-10 20:58:50,557][97672] Avg episode reward: [(0, '-7.460'), (1, '-5.960')] -[2023-10-10 20:58:50,571][98439] Saving new best policy, reward=-5.960! -[2023-10-10 20:58:50,571][98385] Saving new best policy, reward=-7.460! -[2023-10-10 20:58:52,392][98559] Updated weights for policy 0, policy_version 7110 (0.0008) -[2023-10-10 20:58:52,523][98560] Updated weights for policy 1, policy_version 7142 (0.0007) -[2023-10-10 20:58:52,771][98559] Updated weights for policy 0, policy_version 7120 (0.0009) -[2023-10-10 20:58:52,896][98560] Updated weights for policy 1, policy_version 7152 (0.0007) -[2023-10-10 20:58:53,139][98559] Updated weights for policy 0, policy_version 7130 (0.0008) -[2023-10-10 20:58:53,264][98560] Updated weights for policy 1, policy_version 7162 (0.0008) -[2023-10-10 20:58:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 14647296. Throughput: 0: 1679.9, 1: 1682.7. Samples: 3665140. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-10 20:58:55,557][97672] Avg episode reward: [(0, '-7.380'), (1, '-5.820')] -[2023-10-10 20:58:55,558][98439] Saving new best policy, reward=-5.820! -[2023-10-10 20:58:55,558][98385] Saving new best policy, reward=-7.380! -[2023-10-10 20:58:57,250][98559] Updated weights for policy 0, policy_version 7140 (0.0008) -[2023-10-10 20:58:57,338][98560] Updated weights for policy 1, policy_version 7172 (0.0007) -[2023-10-10 20:58:57,622][98559] Updated weights for policy 0, policy_version 7150 (0.0008) -[2023-10-10 20:58:57,710][98560] Updated weights for policy 1, policy_version 7182 (0.0008) -[2023-10-10 20:58:57,995][98559] Updated weights for policy 0, policy_version 7160 (0.0009) -[2023-10-10 20:58:58,081][98560] Updated weights for policy 1, policy_version 7192 (0.0007) -[2023-10-10 20:59:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 14712832. Throughput: 0: 1682.0, 1: 1672.3. Samples: 3684802. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-10 20:59:00,557][97672] Avg episode reward: [(0, '-7.380'), (1, '-5.740')] -[2023-10-10 20:59:00,558][98439] Saving new best policy, reward=-5.740! -[2023-10-10 20:59:02,073][98560] Updated weights for policy 1, policy_version 7202 (0.0008) -[2023-10-10 20:59:02,260][98559] Updated weights for policy 0, policy_version 7170 (0.0008) -[2023-10-10 20:59:02,449][98560] Updated weights for policy 1, policy_version 7212 (0.0008) -[2023-10-10 20:59:02,630][98559] Updated weights for policy 0, policy_version 7180 (0.0007) -[2023-10-10 20:59:02,823][98560] Updated weights for policy 1, policy_version 7222 (0.0008) -[2023-10-10 20:59:03,005][98559] Updated weights for policy 0, policy_version 7190 (0.0008) -[2023-10-10 20:59:03,191][98560] Updated weights for policy 1, policy_version 7232 (0.0009) -[2023-10-10 20:59:03,376][98559] Updated weights for policy 0, policy_version 7200 (0.0007) -[2023-10-10 20:59:05,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 14778368. Throughput: 0: 1696.6, 1: 1695.8. Samples: 3705756. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-10 20:59:05,556][97672] Avg episode reward: [(0, '-7.300'), (1, '-5.760')] -[2023-10-10 20:59:05,566][98385] Saving new best policy, reward=-7.300! -[2023-10-10 20:59:07,130][98560] Updated weights for policy 1, policy_version 7242 (0.0008) -[2023-10-10 20:59:07,241][98559] Updated weights for policy 0, policy_version 7210 (0.0010) -[2023-10-10 20:59:07,494][98560] Updated weights for policy 1, policy_version 7252 (0.0008) -[2023-10-10 20:59:07,614][98559] Updated weights for policy 0, policy_version 7220 (0.0009) -[2023-10-10 20:59:07,861][98560] Updated weights for policy 1, policy_version 7262 (0.0008) -[2023-10-10 20:59:07,991][98559] Updated weights for policy 0, policy_version 7230 (0.0008) -[2023-10-10 20:59:10,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 14843904. Throughput: 0: 1665.1, 1: 1674.6. Samples: 3715342. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 20:59:10,558][97672] Avg episode reward: [(0, '-7.280'), (1, '-5.520')] -[2023-10-10 20:59:10,559][98385] Saving new best policy, reward=-7.280! -[2023-10-10 20:59:10,559][98439] Saving new best policy, reward=-5.520! -[2023-10-10 20:59:11,780][98560] Updated weights for policy 1, policy_version 7272 (0.0008) -[2023-10-10 20:59:12,137][98559] Updated weights for policy 0, policy_version 7240 (0.0009) -[2023-10-10 20:59:12,150][98560] Updated weights for policy 1, policy_version 7282 (0.0009) -[2023-10-10 20:59:12,514][98560] Updated weights for policy 1, policy_version 7292 (0.0007) -[2023-10-10 20:59:12,514][98559] Updated weights for policy 0, policy_version 7250 (0.0007) -[2023-10-10 20:59:12,893][98559] Updated weights for policy 0, policy_version 7260 (0.0010) -[2023-10-10 20:59:15,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 14909440. Throughput: 0: 1687.6, 1: 1690.4. Samples: 3736114. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 20:59:15,557][97672] Avg episode reward: [(0, '-7.120'), (1, '-5.480')] -[2023-10-10 20:59:15,558][98439] Saving new best policy, reward=-5.480! -[2023-10-10 20:59:15,558][98385] Saving new best policy, reward=-7.120! -[2023-10-10 20:59:16,399][98560] Updated weights for policy 1, policy_version 7302 (0.0007) -[2023-10-10 20:59:16,769][98560] Updated weights for policy 1, policy_version 7312 (0.0009) -[2023-10-10 20:59:16,835][98559] Updated weights for policy 0, policy_version 7270 (0.0009) -[2023-10-10 20:59:17,135][98560] Updated weights for policy 1, policy_version 7322 (0.0008) -[2023-10-10 20:59:17,211][98559] Updated weights for policy 0, policy_version 7280 (0.0007) -[2023-10-10 20:59:17,574][98559] Updated weights for policy 0, policy_version 7290 (0.0009) -[2023-10-10 20:59:20,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 14974976. Throughput: 0: 1693.0, 1: 1708.7. Samples: 3757158. Policy #0 lag: (min: 1.0, avg: 6.7, max: 33.0) -[2023-10-10 20:59:20,557][97672] Avg episode reward: [(0, '-7.080'), (1, '-5.440')] -[2023-10-10 20:59:20,565][98385] Saving new best policy, reward=-7.080! -[2023-10-10 20:59:20,565][98439] Saving new best policy, reward=-5.440! -[2023-10-10 20:59:21,223][98560] Updated weights for policy 1, policy_version 7332 (0.0009) -[2023-10-10 20:59:21,592][98560] Updated weights for policy 1, policy_version 7342 (0.0009) -[2023-10-10 20:59:21,767][98559] Updated weights for policy 0, policy_version 7300 (0.0008) -[2023-10-10 20:59:21,962][98560] Updated weights for policy 1, policy_version 7352 (0.0008) -[2023-10-10 20:59:22,160][98559] Updated weights for policy 0, policy_version 7310 (0.0008) -[2023-10-10 20:59:22,525][98559] Updated weights for policy 0, policy_version 7320 (0.0008) -[2023-10-10 20:59:25,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 15040512. Throughput: 0: 1668.7, 1: 1682.5. Samples: 3766140. Policy #0 lag: (min: 1.0, avg: 6.7, max: 33.0) -[2023-10-10 20:59:25,557][97672] Avg episode reward: [(0, '-7.200'), (1, '-5.520')] -[2023-10-10 20:59:25,912][98560] Updated weights for policy 1, policy_version 7362 (0.0007) -[2023-10-10 20:59:26,279][98560] Updated weights for policy 1, policy_version 7372 (0.0007) -[2023-10-10 20:59:26,640][98559] Updated weights for policy 0, policy_version 7330 (0.0010) -[2023-10-10 20:59:26,644][98560] Updated weights for policy 1, policy_version 7382 (0.0007) -[2023-10-10 20:59:27,011][98560] Updated weights for policy 1, policy_version 7392 (0.0008) -[2023-10-10 20:59:27,015][98559] Updated weights for policy 0, policy_version 7340 (0.0008) -[2023-10-10 20:59:27,387][98559] Updated weights for policy 0, policy_version 7350 (0.0009) -[2023-10-10 20:59:27,761][98559] Updated weights for policy 0, policy_version 7360 (0.0008) -[2023-10-10 20:59:30,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 15106048. Throughput: 0: 1687.8, 1: 1709.2. Samples: 3787210. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-10 20:59:30,557][97672] Avg episode reward: [(0, '-7.260'), (1, '-5.480')] -[2023-10-10 20:59:30,968][98560] Updated weights for policy 1, policy_version 7402 (0.0008) -[2023-10-10 20:59:31,345][98560] Updated weights for policy 1, policy_version 7412 (0.0007) -[2023-10-10 20:59:31,721][98560] Updated weights for policy 1, policy_version 7422 (0.0009) -[2023-10-10 20:59:31,787][98559] Updated weights for policy 0, policy_version 7370 (0.0007) -[2023-10-10 20:59:32,167][98559] Updated weights for policy 0, policy_version 7380 (0.0008) -[2023-10-10 20:59:32,545][98559] Updated weights for policy 0, policy_version 7390 (0.0008) -[2023-10-10 20:59:35,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 15171584. Throughput: 0: 1688.3, 1: 1717.4. Samples: 3808200. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-10 20:59:35,556][97672] Avg episode reward: [(0, '-7.260'), (1, '-5.500')] -[2023-10-10 20:59:35,766][98560] Updated weights for policy 1, policy_version 7432 (0.0008) -[2023-10-10 20:59:36,139][98560] Updated weights for policy 1, policy_version 7442 (0.0007) -[2023-10-10 20:59:36,509][98560] Updated weights for policy 1, policy_version 7452 (0.0009) -[2023-10-10 20:59:36,551][98559] Updated weights for policy 0, policy_version 7400 (0.0009) -[2023-10-10 20:59:36,913][98559] Updated weights for policy 0, policy_version 7410 (0.0008) -[2023-10-10 20:59:37,284][98559] Updated weights for policy 0, policy_version 7420 (0.0007) -[2023-10-10 20:59:40,452][98560] Updated weights for policy 1, policy_version 7462 (0.0008) -[2023-10-10 20:59:40,556][97672] Fps is (10 sec: 13107.7, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 15237120. Throughput: 0: 1684.4, 1: 1695.5. Samples: 3817234. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-10 20:59:40,557][97672] Avg episode reward: [(0, '-6.820'), (1, '-5.260')] -[2023-10-10 20:59:40,557][98385] Saving new best policy, reward=-6.820! -[2023-10-10 20:59:40,821][98560] Updated weights for policy 1, policy_version 7472 (0.0009) -[2023-10-10 20:59:41,186][98560] Updated weights for policy 1, policy_version 7482 (0.0008) -[2023-10-10 20:59:41,271][98559] Updated weights for policy 0, policy_version 7430 (0.0008) -[2023-10-10 20:59:41,406][98439] Saving new best policy, reward=-5.260! -[2023-10-10 20:59:41,644][98559] Updated weights for policy 0, policy_version 7440 (0.0009) -[2023-10-10 20:59:42,009][98559] Updated weights for policy 0, policy_version 7450 (0.0007) -[2023-10-10 20:59:45,216][98560] Updated weights for policy 1, policy_version 7492 (0.0010) -[2023-10-10 20:59:45,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 15302656. Throughput: 0: 1693.3, 1: 1718.4. Samples: 3838326. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-10 20:59:45,556][97672] Avg episode reward: [(0, '-6.700'), (1, '-5.260')] -[2023-10-10 20:59:45,557][98385] Saving new best policy, reward=-6.700! -[2023-10-10 20:59:45,589][98560] Updated weights for policy 1, policy_version 7502 (0.0011) -[2023-10-10 20:59:45,961][98560] Updated weights for policy 1, policy_version 7512 (0.0011) -[2023-10-10 20:59:46,172][98559] Updated weights for policy 0, policy_version 7460 (0.0007) -[2023-10-10 20:59:46,560][98559] Updated weights for policy 0, policy_version 7470 (0.0007) -[2023-10-10 20:59:46,937][98559] Updated weights for policy 0, policy_version 7480 (0.0009) -[2023-10-10 20:59:49,851][98560] Updated weights for policy 1, policy_version 7522 (0.0008) -[2023-10-10 20:59:50,212][98560] Updated weights for policy 1, policy_version 7532 (0.0008) -[2023-10-10 20:59:50,556][97672] Fps is (10 sec: 13106.7, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 15368192. Throughput: 0: 1696.2, 1: 1717.3. Samples: 3859366. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-10-10 20:59:50,558][97672] Avg episode reward: [(0, '-6.760'), (1, '-5.280')] -[2023-10-10 20:59:50,584][98560] Updated weights for policy 1, policy_version 7542 (0.0011) -[2023-10-10 20:59:50,871][98559] Updated weights for policy 0, policy_version 7490 (0.0007) -[2023-10-10 20:59:50,949][98560] Updated weights for policy 1, policy_version 7552 (0.0010) -[2023-10-10 20:59:51,237][98559] Updated weights for policy 0, policy_version 7500 (0.0008) -[2023-10-10 20:59:51,621][98559] Updated weights for policy 0, policy_version 7510 (0.0010) -[2023-10-10 20:59:51,993][98559] Updated weights for policy 0, policy_version 7520 (0.0007) -[2023-10-10 20:59:54,936][98560] Updated weights for policy 1, policy_version 7562 (0.0007) -[2023-10-10 20:59:55,299][98560] Updated weights for policy 1, policy_version 7572 (0.0007) -[2023-10-10 20:59:55,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 15433728. Throughput: 0: 1696.1, 1: 1709.7. Samples: 3868602. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-10-10 20:59:55,557][97672] Avg episode reward: [(0, '-6.740'), (1, '-5.180')] -[2023-10-10 20:59:55,673][98560] Updated weights for policy 1, policy_version 7582 (0.0009) -[2023-10-10 20:59:55,736][98439] Saving new best policy, reward=-5.180! -[2023-10-10 20:59:55,941][98559] Updated weights for policy 0, policy_version 7530 (0.0008) -[2023-10-10 20:59:56,311][98559] Updated weights for policy 0, policy_version 7540 (0.0007) -[2023-10-10 20:59:56,689][98559] Updated weights for policy 0, policy_version 7550 (0.0010) -[2023-10-10 20:59:59,813][98560] Updated weights for policy 1, policy_version 7592 (0.0009) -[2023-10-10 21:00:00,191][98560] Updated weights for policy 1, policy_version 7602 (0.0010) -[2023-10-10 21:00:00,556][97672] Fps is (10 sec: 13107.7, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 15499264. Throughput: 0: 1695.0, 1: 1716.0. Samples: 3889610. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:00:00,557][97672] Avg episode reward: [(0, '-6.740'), (1, '-5.120')] -[2023-10-10 21:00:00,564][98560] Updated weights for policy 1, policy_version 7612 (0.0010) -[2023-10-10 21:00:00,708][98439] Saving new best policy, reward=-5.120! -[2023-10-10 21:00:00,869][98559] Updated weights for policy 0, policy_version 7560 (0.0008) -[2023-10-10 21:00:01,243][98559] Updated weights for policy 0, policy_version 7570 (0.0007) -[2023-10-10 21:00:01,620][98559] Updated weights for policy 0, policy_version 7580 (0.0008) -[2023-10-10 21:00:04,531][98560] Updated weights for policy 1, policy_version 7622 (0.0009) -[2023-10-10 21:00:04,906][98560] Updated weights for policy 1, policy_version 7632 (0.0009) -[2023-10-10 21:00:05,275][98560] Updated weights for policy 1, policy_version 7642 (0.0008) -[2023-10-10 21:00:05,513][98559] Updated weights for policy 0, policy_version 7590 (0.0007) -[2023-10-10 21:00:05,556][97672] Fps is (10 sec: 16384.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 15597568. Throughput: 0: 1696.0, 1: 1703.0. Samples: 3910112. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:00:05,557][97672] Avg episode reward: [(0, '-6.680'), (1, '-5.140')] -[2023-10-10 21:00:05,888][98559] Updated weights for policy 0, policy_version 7600 (0.0011) -[2023-10-10 21:00:06,260][98559] Updated weights for policy 0, policy_version 7610 (0.0010) -[2023-10-10 21:00:06,483][98385] Saving new best policy, reward=-6.680! -[2023-10-10 21:00:09,328][98560] Updated weights for policy 1, policy_version 7652 (0.0008) -[2023-10-10 21:00:09,698][98560] Updated weights for policy 1, policy_version 7662 (0.0008) -[2023-10-10 21:00:10,073][98560] Updated weights for policy 1, policy_version 7672 (0.0008) -[2023-10-10 21:00:10,471][98559] Updated weights for policy 0, policy_version 7620 (0.0008) -[2023-10-10 21:00:10,556][97672] Fps is (10 sec: 16383.6, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 15663104. Throughput: 0: 1700.5, 1: 1713.2. Samples: 3919758. Policy #0 lag: (min: 28.0, avg: 33.8, max: 60.0) -[2023-10-10 21:00:10,557][97672] Avg episode reward: [(0, '-6.680'), (1, '-5.020')] -[2023-10-10 21:00:10,559][98439] Saving new best policy, reward=-5.020! -[2023-10-10 21:00:10,849][98559] Updated weights for policy 0, policy_version 7630 (0.0010) -[2023-10-10 21:00:11,219][98559] Updated weights for policy 0, policy_version 7640 (0.0008) -[2023-10-10 21:00:14,115][98560] Updated weights for policy 1, policy_version 7682 (0.0009) -[2023-10-10 21:00:14,495][98560] Updated weights for policy 1, policy_version 7692 (0.0009) -[2023-10-10 21:00:14,859][98560] Updated weights for policy 1, policy_version 7702 (0.0009) -[2023-10-10 21:00:15,160][98559] Updated weights for policy 0, policy_version 7650 (0.0008) -[2023-10-10 21:00:15,234][98560] Updated weights for policy 1, policy_version 7712 (0.0008) -[2023-10-10 21:00:15,530][98559] Updated weights for policy 0, policy_version 7660 (0.0010) -[2023-10-10 21:00:15,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 15728640. Throughput: 0: 1702.7, 1: 1709.4. Samples: 3940754. Policy #0 lag: (min: 28.0, avg: 33.8, max: 60.0) -[2023-10-10 21:00:15,557][97672] Avg episode reward: [(0, '-6.680'), (1, '-5.080')] -[2023-10-10 21:00:15,904][98559] Updated weights for policy 0, policy_version 7670 (0.0010) -[2023-10-10 21:00:16,283][98559] Updated weights for policy 0, policy_version 7680 (0.0009) -[2023-10-10 21:00:19,165][98560] Updated weights for policy 1, policy_version 7722 (0.0009) -[2023-10-10 21:00:19,536][98560] Updated weights for policy 1, policy_version 7732 (0.0009) -[2023-10-10 21:00:19,900][98560] Updated weights for policy 1, policy_version 7742 (0.0008) -[2023-10-10 21:00:20,299][98559] Updated weights for policy 0, policy_version 7690 (0.0008) -[2023-10-10 21:00:20,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 15794176. Throughput: 0: 1689.1, 1: 1686.9. Samples: 3960120. Policy #0 lag: (min: 25.0, avg: 33.4, max: 57.0) -[2023-10-10 21:00:20,557][97672] Avg episode reward: [(0, '-6.700'), (1, '-5.040')] -[2023-10-10 21:00:20,673][98559] Updated weights for policy 0, policy_version 7700 (0.0008) -[2023-10-10 21:00:21,055][98559] Updated weights for policy 0, policy_version 7710 (0.0007) -[2023-10-10 21:00:24,071][98560] Updated weights for policy 1, policy_version 7752 (0.0009) -[2023-10-10 21:00:24,439][98560] Updated weights for policy 1, policy_version 7762 (0.0010) -[2023-10-10 21:00:24,804][98560] Updated weights for policy 1, policy_version 7772 (0.0008) -[2023-10-10 21:00:24,922][98559] Updated weights for policy 0, policy_version 7720 (0.0008) -[2023-10-10 21:00:25,300][98559] Updated weights for policy 0, policy_version 7730 (0.0007) -[2023-10-10 21:00:25,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 15859712. Throughput: 0: 1697.9, 1: 1709.0. Samples: 3970544. Policy #0 lag: (min: 25.0, avg: 33.4, max: 57.0) -[2023-10-10 21:00:25,557][97672] Avg episode reward: [(0, '-6.700'), (1, '-5.220')] -[2023-10-10 21:00:25,668][98559] Updated weights for policy 0, policy_version 7740 (0.0007) -[2023-10-10 21:00:28,744][98560] Updated weights for policy 1, policy_version 7782 (0.0008) -[2023-10-10 21:00:29,115][98560] Updated weights for policy 1, policy_version 7792 (0.0008) -[2023-10-10 21:00:29,493][98560] Updated weights for policy 1, policy_version 7802 (0.0008) -[2023-10-10 21:00:29,650][98559] Updated weights for policy 0, policy_version 7750 (0.0007) -[2023-10-10 21:00:30,021][98559] Updated weights for policy 0, policy_version 7760 (0.0007) -[2023-10-10 21:00:30,395][98559] Updated weights for policy 0, policy_version 7770 (0.0007) -[2023-10-10 21:00:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 15925248. Throughput: 0: 1699.4, 1: 1701.5. Samples: 3991364. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:00:30,557][97672] Avg episode reward: [(0, '-6.700'), (1, '-5.240')] -[2023-10-10 21:00:33,521][98560] Updated weights for policy 1, policy_version 7812 (0.0007) -[2023-10-10 21:00:33,887][98560] Updated weights for policy 1, policy_version 7822 (0.0007) -[2023-10-10 21:00:34,263][98560] Updated weights for policy 1, policy_version 7832 (0.0009) -[2023-10-10 21:00:34,374][98559] Updated weights for policy 0, policy_version 7780 (0.0009) -[2023-10-10 21:00:34,737][98559] Updated weights for policy 0, policy_version 7790 (0.0008) -[2023-10-10 21:00:35,113][98559] Updated weights for policy 0, policy_version 7800 (0.0008) -[2023-10-10 21:00:35,556][97672] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 16023552. Throughput: 0: 1673.4, 1: 1675.1. Samples: 4010046. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-10 21:00:35,557][97672] Avg episode reward: [(0, '-6.700'), (1, '-5.280')] -[2023-10-10 21:00:35,568][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000007840_8028160.pth... -[2023-10-10 21:00:35,569][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000007808_7995392.pth... -[2023-10-10 21:00:35,603][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000006208_6356992.pth -[2023-10-10 21:00:35,607][98385] Saving a milestone ./train_atari/atari_doubledunk_APPO/checkpoint_p0/milestones/checkpoint_000007808_7995392.pth -[2023-10-10 21:00:35,607][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000006240_6389760.pth -[2023-10-10 21:00:35,613][98439] Saving a milestone ./train_atari/atari_doubledunk_APPO/checkpoint_p1/milestones/checkpoint_000007840_8028160.pth -[2023-10-10 21:00:38,335][98560] Updated weights for policy 1, policy_version 7842 (0.0010) -[2023-10-10 21:00:38,700][98560] Updated weights for policy 1, policy_version 7852 (0.0007) -[2023-10-10 21:00:39,080][98560] Updated weights for policy 1, policy_version 7862 (0.0007) -[2023-10-10 21:00:39,197][98559] Updated weights for policy 0, policy_version 7810 (0.0008) -[2023-10-10 21:00:39,450][98560] Updated weights for policy 1, policy_version 7872 (0.0007) -[2023-10-10 21:00:39,566][98559] Updated weights for policy 0, policy_version 7820 (0.0009) -[2023-10-10 21:00:39,943][98559] Updated weights for policy 0, policy_version 7830 (0.0010) -[2023-10-10 21:00:40,309][98559] Updated weights for policy 0, policy_version 7840 (0.0008) -[2023-10-10 21:00:40,556][97672] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 16089088. Throughput: 0: 1699.3, 1: 1704.3. Samples: 4021764. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-10 21:00:40,557][97672] Avg episode reward: [(0, '-6.720'), (1, '-5.180')] -[2023-10-10 21:00:43,379][98560] Updated weights for policy 1, policy_version 7882 (0.0009) -[2023-10-10 21:00:43,752][98560] Updated weights for policy 1, policy_version 7892 (0.0007) -[2023-10-10 21:00:44,125][98560] Updated weights for policy 1, policy_version 7902 (0.0009) -[2023-10-10 21:00:44,266][98559] Updated weights for policy 0, policy_version 7850 (0.0007) -[2023-10-10 21:00:44,639][98559] Updated weights for policy 0, policy_version 7860 (0.0007) -[2023-10-10 21:00:45,013][98559] Updated weights for policy 0, policy_version 7870 (0.0008) -[2023-10-10 21:00:45,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 16154624. Throughput: 0: 1691.6, 1: 1686.4. Samples: 4041622. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:00:45,557][97672] Avg episode reward: [(0, '-6.720'), (1, '-5.160')] -[2023-10-10 21:00:48,059][98560] Updated weights for policy 1, policy_version 7912 (0.0009) -[2023-10-10 21:00:48,426][98560] Updated weights for policy 1, policy_version 7922 (0.0008) -[2023-10-10 21:00:48,796][98560] Updated weights for policy 1, policy_version 7932 (0.0007) -[2023-10-10 21:00:49,100][98559] Updated weights for policy 0, policy_version 7880 (0.0009) -[2023-10-10 21:00:49,477][98559] Updated weights for policy 0, policy_version 7890 (0.0010) -[2023-10-10 21:00:49,856][98559] Updated weights for policy 0, policy_version 7900 (0.0008) -[2023-10-10 21:00:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 16220160. Throughput: 0: 1673.5, 1: 1686.0. Samples: 4061290. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:00:50,557][97672] Avg episode reward: [(0, '-6.720'), (1, '-4.880')] -[2023-10-10 21:00:50,565][98439] Saving new best policy, reward=-4.880! -[2023-10-10 21:00:52,797][98560] Updated weights for policy 1, policy_version 7942 (0.0009) -[2023-10-10 21:00:53,158][98560] Updated weights for policy 1, policy_version 7952 (0.0008) -[2023-10-10 21:00:53,524][98560] Updated weights for policy 1, policy_version 7962 (0.0008) -[2023-10-10 21:00:53,770][98559] Updated weights for policy 0, policy_version 7910 (0.0010) -[2023-10-10 21:00:54,148][98559] Updated weights for policy 0, policy_version 7920 (0.0009) -[2023-10-10 21:00:54,519][98559] Updated weights for policy 0, policy_version 7930 (0.0010) -[2023-10-10 21:00:55,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 16285696. Throughput: 0: 1705.2, 1: 1701.8. Samples: 4073076. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:00:55,557][97672] Avg episode reward: [(0, '-6.720'), (1, '-4.920')] -[2023-10-10 21:00:57,563][98560] Updated weights for policy 1, policy_version 7972 (0.0007) -[2023-10-10 21:00:57,934][98560] Updated weights for policy 1, policy_version 7982 (0.0010) -[2023-10-10 21:00:58,287][98560] Updated weights for policy 1, policy_version 7992 (0.0009) -[2023-10-10 21:00:58,704][98559] Updated weights for policy 0, policy_version 7940 (0.0008) -[2023-10-10 21:00:59,086][98559] Updated weights for policy 0, policy_version 7950 (0.0009) -[2023-10-10 21:00:59,462][98559] Updated weights for policy 0, policy_version 7960 (0.0011) -[2023-10-10 21:01:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 16351232. Throughput: 0: 1678.5, 1: 1675.1. Samples: 4091666. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:01:00,557][97672] Avg episode reward: [(0, '-6.760'), (1, '-4.920')] -[2023-10-10 21:01:02,376][98560] Updated weights for policy 1, policy_version 8002 (0.0008) -[2023-10-10 21:01:02,750][98560] Updated weights for policy 1, policy_version 8012 (0.0010) -[2023-10-10 21:01:03,115][98560] Updated weights for policy 1, policy_version 8022 (0.0010) -[2023-10-10 21:01:03,485][98560] Updated weights for policy 1, policy_version 8032 (0.0007) -[2023-10-10 21:01:03,529][98559] Updated weights for policy 0, policy_version 7970 (0.0011) -[2023-10-10 21:01:03,899][98559] Updated weights for policy 0, policy_version 7980 (0.0007) -[2023-10-10 21:01:04,273][98559] Updated weights for policy 0, policy_version 7990 (0.0008) -[2023-10-10 21:01:04,644][98559] Updated weights for policy 0, policy_version 8000 (0.0009) -[2023-10-10 21:01:05,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 16416768. Throughput: 0: 1684.2, 1: 1697.5. Samples: 4112298. Policy #0 lag: (min: 1.0, avg: 8.4, max: 33.0) -[2023-10-10 21:01:05,557][97672] Avg episode reward: [(0, '-6.760'), (1, '-4.940')] -[2023-10-10 21:01:07,433][98560] Updated weights for policy 1, policy_version 8042 (0.0007) -[2023-10-10 21:01:07,810][98560] Updated weights for policy 1, policy_version 8052 (0.0007) -[2023-10-10 21:01:08,184][98560] Updated weights for policy 1, policy_version 8062 (0.0009) -[2023-10-10 21:01:08,644][98559] Updated weights for policy 0, policy_version 8010 (0.0009) -[2023-10-10 21:01:09,027][98559] Updated weights for policy 0, policy_version 8020 (0.0009) -[2023-10-10 21:01:09,403][98559] Updated weights for policy 0, policy_version 8030 (0.0008) -[2023-10-10 21:01:10,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 16482304. Throughput: 0: 1703.8, 1: 1693.1. Samples: 4123404. Policy #0 lag: (min: 1.0, avg: 8.4, max: 33.0) -[2023-10-10 21:01:10,556][97672] Avg episode reward: [(0, '-6.760'), (1, '-4.800')] -[2023-10-10 21:01:10,557][98439] Saving new best policy, reward=-4.800! -[2023-10-10 21:01:12,231][98560] Updated weights for policy 1, policy_version 8072 (0.0008) -[2023-10-10 21:01:12,599][98560] Updated weights for policy 1, policy_version 8082 (0.0007) -[2023-10-10 21:01:12,975][98560] Updated weights for policy 1, policy_version 8092 (0.0007) -[2023-10-10 21:01:13,282][98559] Updated weights for policy 0, policy_version 8040 (0.0009) -[2023-10-10 21:01:13,656][98559] Updated weights for policy 0, policy_version 8050 (0.0009) -[2023-10-10 21:01:14,038][98559] Updated weights for policy 0, policy_version 8060 (0.0007) -[2023-10-10 21:01:15,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 16547840. Throughput: 0: 1676.7, 1: 1684.1. Samples: 4142600. Policy #0 lag: (min: 21.0, avg: 24.7, max: 53.0) -[2023-10-10 21:01:15,556][97672] Avg episode reward: [(0, '-6.840'), (1, '-4.680')] -[2023-10-10 21:01:15,558][98439] Saving new best policy, reward=-4.680! -[2023-10-10 21:01:17,081][98560] Updated weights for policy 1, policy_version 8102 (0.0008) -[2023-10-10 21:01:17,468][98560] Updated weights for policy 1, policy_version 8112 (0.0008) -[2023-10-10 21:01:17,843][98560] Updated weights for policy 1, policy_version 8122 (0.0008) -[2023-10-10 21:01:17,879][98559] Updated weights for policy 0, policy_version 8070 (0.0011) -[2023-10-10 21:01:18,251][98559] Updated weights for policy 0, policy_version 8080 (0.0007) -[2023-10-10 21:01:18,630][98559] Updated weights for policy 0, policy_version 8090 (0.0007) -[2023-10-10 21:01:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 16613376. Throughput: 0: 1711.4, 1: 1709.8. Samples: 4163998. Policy #0 lag: (min: 21.0, avg: 24.7, max: 53.0) -[2023-10-10 21:01:20,557][97672] Avg episode reward: [(0, '-6.940'), (1, '-4.640')] -[2023-10-10 21:01:20,568][98439] Saving new best policy, reward=-4.640! -[2023-10-10 21:01:21,653][98560] Updated weights for policy 1, policy_version 8132 (0.0007) -[2023-10-10 21:01:22,029][98560] Updated weights for policy 1, policy_version 8142 (0.0007) -[2023-10-10 21:01:22,391][98560] Updated weights for policy 1, policy_version 8152 (0.0010) -[2023-10-10 21:01:22,852][98559] Updated weights for policy 0, policy_version 8100 (0.0009) -[2023-10-10 21:01:23,225][98559] Updated weights for policy 0, policy_version 8110 (0.0009) -[2023-10-10 21:01:23,594][98559] Updated weights for policy 0, policy_version 8120 (0.0008) -[2023-10-10 21:01:25,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 16678912. Throughput: 0: 1695.5, 1: 1683.5. Samples: 4173816. Policy #0 lag: (min: 2.0, avg: 2.8, max: 22.0) -[2023-10-10 21:01:25,557][97672] Avg episode reward: [(0, '-6.940'), (1, '-4.500')] -[2023-10-10 21:01:25,559][98439] Saving new best policy, reward=-4.500! -[2023-10-10 21:01:26,326][98560] Updated weights for policy 1, policy_version 8162 (0.0009) -[2023-10-10 21:01:26,696][98560] Updated weights for policy 1, policy_version 8172 (0.0008) -[2023-10-10 21:01:27,063][98560] Updated weights for policy 1, policy_version 8182 (0.0008) -[2023-10-10 21:01:27,429][98560] Updated weights for policy 1, policy_version 8192 (0.0007) -[2023-10-10 21:01:27,551][98559] Updated weights for policy 0, policy_version 8130 (0.0008) -[2023-10-10 21:01:27,917][98559] Updated weights for policy 0, policy_version 8140 (0.0010) -[2023-10-10 21:01:28,296][98559] Updated weights for policy 0, policy_version 8150 (0.0010) -[2023-10-10 21:01:28,668][98559] Updated weights for policy 0, policy_version 8160 (0.0008) -[2023-10-10 21:01:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 16744448. Throughput: 0: 1685.4, 1: 1700.8. Samples: 4194002. Policy #0 lag: (min: 2.0, avg: 2.8, max: 22.0) -[2023-10-10 21:01:30,557][97672] Avg episode reward: [(0, '-6.940'), (1, '-4.300')] -[2023-10-10 21:01:30,558][98439] Saving new best policy, reward=-4.300! -[2023-10-10 21:01:31,568][98560] Updated weights for policy 1, policy_version 8202 (0.0007) -[2023-10-10 21:01:31,932][98560] Updated weights for policy 1, policy_version 8212 (0.0007) -[2023-10-10 21:01:32,309][98560] Updated weights for policy 1, policy_version 8222 (0.0010) -[2023-10-10 21:01:32,801][98559] Updated weights for policy 0, policy_version 8170 (0.0008) -[2023-10-10 21:01:33,171][98559] Updated weights for policy 0, policy_version 8180 (0.0008) -[2023-10-10 21:01:33,560][98559] Updated weights for policy 0, policy_version 8190 (0.0009) -[2023-10-10 21:01:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 16809984. Throughput: 0: 1703.3, 1: 1708.9. Samples: 4214838. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-10 21:01:35,557][97672] Avg episode reward: [(0, '-6.860'), (1, '-4.200')] -[2023-10-10 21:01:35,568][98439] Saving new best policy, reward=-4.200! -[2023-10-10 21:01:36,329][98560] Updated weights for policy 1, policy_version 8232 (0.0008) -[2023-10-10 21:01:36,699][98560] Updated weights for policy 1, policy_version 8242 (0.0007) -[2023-10-10 21:01:37,066][98560] Updated weights for policy 1, policy_version 8252 (0.0009) -[2023-10-10 21:01:37,412][98559] Updated weights for policy 0, policy_version 8200 (0.0007) -[2023-10-10 21:01:37,781][98559] Updated weights for policy 0, policy_version 8210 (0.0007) -[2023-10-10 21:01:38,160][98559] Updated weights for policy 0, policy_version 8220 (0.0008) -[2023-10-10 21:01:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 16875520. Throughput: 0: 1675.1, 1: 1687.5. Samples: 4224392. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-10 21:01:40,557][97672] Avg episode reward: [(0, '-6.860'), (1, '-4.160')] -[2023-10-10 21:01:40,558][98439] Saving new best policy, reward=-4.160! -[2023-10-10 21:01:40,963][98560] Updated weights for policy 1, policy_version 8262 (0.0008) -[2023-10-10 21:01:41,330][98560] Updated weights for policy 1, policy_version 8272 (0.0009) -[2023-10-10 21:01:41,698][98560] Updated weights for policy 1, policy_version 8282 (0.0007) -[2023-10-10 21:01:42,251][98559] Updated weights for policy 0, policy_version 8230 (0.0009) -[2023-10-10 21:01:42,622][98559] Updated weights for policy 0, policy_version 8240 (0.0007) -[2023-10-10 21:01:42,996][98559] Updated weights for policy 0, policy_version 8250 (0.0008) -[2023-10-10 21:01:45,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 16941056. Throughput: 0: 1703.2, 1: 1719.2. Samples: 4245672. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-10 21:01:45,556][97672] Avg episode reward: [(0, '-6.860'), (1, '-4.220')] -[2023-10-10 21:01:45,658][98560] Updated weights for policy 1, policy_version 8292 (0.0007) -[2023-10-10 21:01:46,017][98560] Updated weights for policy 1, policy_version 8302 (0.0007) -[2023-10-10 21:01:46,393][98560] Updated weights for policy 1, policy_version 8312 (0.0009) -[2023-10-10 21:01:46,947][98559] Updated weights for policy 0, policy_version 8260 (0.0009) -[2023-10-10 21:01:47,332][98559] Updated weights for policy 0, policy_version 8270 (0.0007) -[2023-10-10 21:01:47,710][98559] Updated weights for policy 0, policy_version 8280 (0.0007) -[2023-10-10 21:01:50,378][98560] Updated weights for policy 1, policy_version 8322 (0.0008) -[2023-10-10 21:01:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 17006592. Throughput: 0: 1713.5, 1: 1720.1. Samples: 4266808. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-10 21:01:50,557][97672] Avg episode reward: [(0, '-6.860'), (1, '-4.020')] -[2023-10-10 21:01:50,749][98560] Updated weights for policy 1, policy_version 8332 (0.0008) -[2023-10-10 21:01:51,120][98560] Updated weights for policy 1, policy_version 8342 (0.0008) -[2023-10-10 21:01:51,479][98439] Saving new best policy, reward=-4.020! -[2023-10-10 21:01:51,483][98560] Updated weights for policy 1, policy_version 8352 (0.0009) -[2023-10-10 21:01:51,512][98559] Updated weights for policy 0, policy_version 8290 (0.0008) -[2023-10-10 21:01:51,886][98559] Updated weights for policy 0, policy_version 8300 (0.0009) -[2023-10-10 21:01:52,268][98559] Updated weights for policy 0, policy_version 8310 (0.0008) -[2023-10-10 21:01:52,636][98559] Updated weights for policy 0, policy_version 8320 (0.0008) -[2023-10-10 21:01:55,491][98560] Updated weights for policy 1, policy_version 8362 (0.0007) -[2023-10-10 21:01:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 17072128. Throughput: 0: 1686.2, 1: 1706.6. Samples: 4276080. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-10 21:01:55,556][97672] Avg episode reward: [(0, '-6.860'), (1, '-3.820')] -[2023-10-10 21:01:55,859][98560] Updated weights for policy 1, policy_version 8372 (0.0008) -[2023-10-10 21:01:56,234][98560] Updated weights for policy 1, policy_version 8382 (0.0009) -[2023-10-10 21:01:56,312][98439] Saving new best policy, reward=-3.820! -[2023-10-10 21:01:56,794][98559] Updated weights for policy 0, policy_version 8330 (0.0008) -[2023-10-10 21:01:57,159][98559] Updated weights for policy 0, policy_version 8340 (0.0009) -[2023-10-10 21:01:57,540][98559] Updated weights for policy 0, policy_version 8350 (0.0009) -[2023-10-10 21:01:59,996][98560] Updated weights for policy 1, policy_version 8392 (0.0008) -[2023-10-10 21:02:00,356][98560] Updated weights for policy 1, policy_version 8402 (0.0007) -[2023-10-10 21:02:00,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 17137664. Throughput: 0: 1712.0, 1: 1725.9. Samples: 4297308. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-10 21:02:00,556][97672] Avg episode reward: [(0, '-6.860'), (1, '-3.800')] -[2023-10-10 21:02:00,724][98560] Updated weights for policy 1, policy_version 8412 (0.0009) -[2023-10-10 21:02:00,868][98439] Saving new best policy, reward=-3.800! -[2023-10-10 21:02:01,498][98559] Updated weights for policy 0, policy_version 8360 (0.0009) -[2023-10-10 21:02:01,859][98559] Updated weights for policy 0, policy_version 8370 (0.0011) -[2023-10-10 21:02:02,232][98559] Updated weights for policy 0, policy_version 8380 (0.0007) -[2023-10-10 21:02:04,821][98560] Updated weights for policy 1, policy_version 8422 (0.0008) -[2023-10-10 21:02:05,213][98560] Updated weights for policy 1, policy_version 8432 (0.0007) -[2023-10-10 21:02:05,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 17203200. Throughput: 0: 1710.6, 1: 1717.8. Samples: 4318278. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 21:02:05,557][97672] Avg episode reward: [(0, '-6.860'), (1, '-3.980')] -[2023-10-10 21:02:05,577][98560] Updated weights for policy 1, policy_version 8442 (0.0009) -[2023-10-10 21:02:06,183][98559] Updated weights for policy 0, policy_version 8390 (0.0007) -[2023-10-10 21:02:06,550][98559] Updated weights for policy 0, policy_version 8400 (0.0011) -[2023-10-10 21:02:06,927][98559] Updated weights for policy 0, policy_version 8410 (0.0007) -[2023-10-10 21:02:09,499][98560] Updated weights for policy 1, policy_version 8452 (0.0008) -[2023-10-10 21:02:09,866][98560] Updated weights for policy 1, policy_version 8462 (0.0007) -[2023-10-10 21:02:10,229][98560] Updated weights for policy 1, policy_version 8472 (0.0008) -[2023-10-10 21:02:10,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 17301504. Throughput: 0: 1700.6, 1: 1716.7. Samples: 4327594. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 21:02:10,557][97672] Avg episode reward: [(0, '-6.860'), (1, '-3.980')] -[2023-10-10 21:02:10,927][98559] Updated weights for policy 0, policy_version 8420 (0.0009) -[2023-10-10 21:02:11,300][98559] Updated weights for policy 0, policy_version 8430 (0.0009) -[2023-10-10 21:02:11,668][98559] Updated weights for policy 0, policy_version 8440 (0.0009) -[2023-10-10 21:02:14,264][98560] Updated weights for policy 1, policy_version 8482 (0.0010) -[2023-10-10 21:02:14,631][98560] Updated weights for policy 1, policy_version 8492 (0.0010) -[2023-10-10 21:02:14,994][98560] Updated weights for policy 1, policy_version 8502 (0.0008) -[2023-10-10 21:02:15,358][98560] Updated weights for policy 1, policy_version 8512 (0.0010) -[2023-10-10 21:02:15,556][97672] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 17367040. Throughput: 0: 1722.4, 1: 1712.7. Samples: 4348584. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-10 21:02:15,557][97672] Avg episode reward: [(0, '-6.860'), (1, '-3.940')] -[2023-10-10 21:02:15,648][98559] Updated weights for policy 0, policy_version 8450 (0.0009) -[2023-10-10 21:02:16,011][98559] Updated weights for policy 0, policy_version 8460 (0.0008) -[2023-10-10 21:02:16,391][98559] Updated weights for policy 0, policy_version 8470 (0.0009) -[2023-10-10 21:02:16,765][98559] Updated weights for policy 0, policy_version 8480 (0.0008) -[2023-10-10 21:02:19,466][98560] Updated weights for policy 1, policy_version 8522 (0.0009) -[2023-10-10 21:02:19,832][98560] Updated weights for policy 1, policy_version 8532 (0.0008) -[2023-10-10 21:02:20,201][98560] Updated weights for policy 1, policy_version 8542 (0.0011) -[2023-10-10 21:02:20,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 17432576. Throughput: 0: 1722.8, 1: 1706.6. Samples: 4369160. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-10 21:02:20,557][97672] Avg episode reward: [(0, '-6.860'), (1, '-3.620')] -[2023-10-10 21:02:20,567][98439] Saving new best policy, reward=-3.620! -[2023-10-10 21:02:20,711][98559] Updated weights for policy 0, policy_version 8490 (0.0010) -[2023-10-10 21:02:21,087][98559] Updated weights for policy 0, policy_version 8500 (0.0009) -[2023-10-10 21:02:21,470][98559] Updated weights for policy 0, policy_version 8510 (0.0010) -[2023-10-10 21:02:24,120][98560] Updated weights for policy 1, policy_version 8552 (0.0009) -[2023-10-10 21:02:24,494][98560] Updated weights for policy 1, policy_version 8562 (0.0008) -[2023-10-10 21:02:24,855][98560] Updated weights for policy 1, policy_version 8572 (0.0007) -[2023-10-10 21:02:25,434][98559] Updated weights for policy 0, policy_version 8520 (0.0009) -[2023-10-10 21:02:25,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 17498112. Throughput: 0: 1719.0, 1: 1715.5. Samples: 4378942. Policy #0 lag: (min: 26.0, avg: 26.2, max: 35.0) -[2023-10-10 21:02:25,557][97672] Avg episode reward: [(0, '-6.860'), (1, '-3.660')] -[2023-10-10 21:02:25,798][98559] Updated weights for policy 0, policy_version 8530 (0.0008) -[2023-10-10 21:02:26,172][98559] Updated weights for policy 0, policy_version 8540 (0.0009) -[2023-10-10 21:02:28,982][98560] Updated weights for policy 1, policy_version 8582 (0.0011) -[2023-10-10 21:02:29,347][98560] Updated weights for policy 1, policy_version 8592 (0.0010) -[2023-10-10 21:02:29,716][98560] Updated weights for policy 1, policy_version 8602 (0.0009) -[2023-10-10 21:02:30,195][98559] Updated weights for policy 0, policy_version 8550 (0.0010) -[2023-10-10 21:02:30,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 17563648. Throughput: 0: 1719.2, 1: 1712.4. Samples: 4400090. Policy #0 lag: (min: 26.0, avg: 26.2, max: 35.0) -[2023-10-10 21:02:30,556][97672] Avg episode reward: [(0, '-6.860'), (1, '-3.560')] -[2023-10-10 21:02:30,557][98439] Saving new best policy, reward=-3.560! -[2023-10-10 21:02:30,566][98559] Updated weights for policy 0, policy_version 8560 (0.0009) -[2023-10-10 21:02:30,931][98559] Updated weights for policy 0, policy_version 8570 (0.0011) -[2023-10-10 21:02:33,742][98560] Updated weights for policy 1, policy_version 8612 (0.0008) -[2023-10-10 21:02:34,112][98560] Updated weights for policy 1, policy_version 8622 (0.0008) -[2023-10-10 21:02:34,475][98560] Updated weights for policy 1, policy_version 8632 (0.0010) -[2023-10-10 21:02:34,916][98559] Updated weights for policy 0, policy_version 8580 (0.0009) -[2023-10-10 21:02:35,291][98559] Updated weights for policy 0, policy_version 8590 (0.0008) -[2023-10-10 21:02:35,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 17629184. Throughput: 0: 1703.6, 1: 1684.2. Samples: 4419258. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:02:35,557][97672] Avg episode reward: [(0, '-6.860'), (1, '-3.380')] -[2023-10-10 21:02:35,567][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000008640_8847360.pth... -[2023-10-10 21:02:35,600][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000007040_7208960.pth -[2023-10-10 21:02:35,604][98439] Saving new best policy, reward=-3.380! -[2023-10-10 21:02:35,664][98559] Updated weights for policy 0, policy_version 8600 (0.0008) -[2023-10-10 21:02:35,959][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000008608_8814592.pth... -[2023-10-10 21:02:35,987][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000007008_7176192.pth -[2023-10-10 21:02:38,488][98560] Updated weights for policy 1, policy_version 8642 (0.0009) -[2023-10-10 21:02:38,862][98560] Updated weights for policy 1, policy_version 8652 (0.0009) -[2023-10-10 21:02:39,229][98560] Updated weights for policy 1, policy_version 8662 (0.0010) -[2023-10-10 21:02:39,588][98560] Updated weights for policy 1, policy_version 8672 (0.0007) -[2023-10-10 21:02:39,720][98559] Updated weights for policy 0, policy_version 8610 (0.0008) -[2023-10-10 21:02:40,101][98559] Updated weights for policy 0, policy_version 8620 (0.0011) -[2023-10-10 21:02:40,459][98559] Updated weights for policy 0, policy_version 8630 (0.0010) -[2023-10-10 21:02:40,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 17694720. Throughput: 0: 1715.3, 1: 1713.2. Samples: 4430364. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:02:40,557][97672] Avg episode reward: [(0, '-6.860'), (1, '-3.340')] -[2023-10-10 21:02:40,558][98439] Saving new best policy, reward=-3.340! -[2023-10-10 21:02:40,835][98559] Updated weights for policy 0, policy_version 8640 (0.0010) -[2023-10-10 21:02:43,534][98560] Updated weights for policy 1, policy_version 8682 (0.0007) -[2023-10-10 21:02:43,911][98560] Updated weights for policy 1, policy_version 8692 (0.0008) -[2023-10-10 21:02:44,291][98560] Updated weights for policy 1, policy_version 8702 (0.0009) -[2023-10-10 21:02:44,683][98559] Updated weights for policy 0, policy_version 8650 (0.0008) -[2023-10-10 21:02:45,056][98559] Updated weights for policy 0, policy_version 8660 (0.0009) -[2023-10-10 21:02:45,424][98559] Updated weights for policy 0, policy_version 8670 (0.0010) -[2023-10-10 21:02:45,556][97672] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 17793024. Throughput: 0: 1716.4, 1: 1696.3. Samples: 4450878. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-10 21:02:45,557][97672] Avg episode reward: [(0, '-6.860'), (1, '-3.260')] -[2023-10-10 21:02:45,558][98439] Saving new best policy, reward=-3.260! -[2023-10-10 21:02:48,367][98560] Updated weights for policy 1, policy_version 8712 (0.0009) -[2023-10-10 21:02:48,750][98560] Updated weights for policy 1, policy_version 8722 (0.0008) -[2023-10-10 21:02:49,119][98560] Updated weights for policy 1, policy_version 8732 (0.0007) -[2023-10-10 21:02:49,365][98559] Updated weights for policy 0, policy_version 8680 (0.0008) -[2023-10-10 21:02:49,736][98559] Updated weights for policy 0, policy_version 8690 (0.0008) -[2023-10-10 21:02:50,116][98559] Updated weights for policy 0, policy_version 8700 (0.0010) -[2023-10-10 21:02:50,556][97672] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 17858560. Throughput: 0: 1683.4, 1: 1682.9. Samples: 4469762. Policy #0 lag: (min: 15.0, avg: 16.6, max: 43.0) -[2023-10-10 21:02:50,556][97672] Avg episode reward: [(0, '-6.860'), (1, '-2.660')] -[2023-10-10 21:02:50,565][98439] Saving new best policy, reward=-2.660! -[2023-10-10 21:02:53,204][98560] Updated weights for policy 1, policy_version 8742 (0.0008) -[2023-10-10 21:02:53,593][98560] Updated weights for policy 1, policy_version 8752 (0.0009) -[2023-10-10 21:02:53,954][98560] Updated weights for policy 1, policy_version 8762 (0.0007) -[2023-10-10 21:02:54,008][98559] Updated weights for policy 0, policy_version 8710 (0.0008) -[2023-10-10 21:02:54,380][98559] Updated weights for policy 0, policy_version 8720 (0.0008) -[2023-10-10 21:02:54,750][98559] Updated weights for policy 0, policy_version 8730 (0.0007) -[2023-10-10 21:02:55,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 17924096. Throughput: 0: 1714.9, 1: 1711.4. Samples: 4481778. Policy #0 lag: (min: 15.0, avg: 16.6, max: 43.0) -[2023-10-10 21:02:55,556][97672] Avg episode reward: [(0, '-6.860'), (1, '-2.040')] -[2023-10-10 21:02:55,557][98439] Saving new best policy, reward=-2.040! -[2023-10-10 21:02:57,951][98560] Updated weights for policy 1, policy_version 8772 (0.0008) -[2023-10-10 21:02:58,318][98560] Updated weights for policy 1, policy_version 8782 (0.0011) -[2023-10-10 21:02:58,690][98560] Updated weights for policy 1, policy_version 8792 (0.0007) -[2023-10-10 21:02:58,828][98559] Updated weights for policy 0, policy_version 8740 (0.0007) -[2023-10-10 21:02:59,203][98559] Updated weights for policy 0, policy_version 8750 (0.0009) -[2023-10-10 21:02:59,567][98559] Updated weights for policy 0, policy_version 8760 (0.0011) -[2023-10-10 21:03:00,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 17989632. Throughput: 0: 1697.3, 1: 1690.6. Samples: 4501040. Policy #0 lag: (min: 9.0, avg: 16.6, max: 41.0) -[2023-10-10 21:03:00,556][97672] Avg episode reward: [(0, '-6.860'), (1, '-2.060')] -[2023-10-10 21:03:02,552][98560] Updated weights for policy 1, policy_version 8802 (0.0008) -[2023-10-10 21:03:02,918][98560] Updated weights for policy 1, policy_version 8812 (0.0008) -[2023-10-10 21:03:03,285][98560] Updated weights for policy 1, policy_version 8822 (0.0009) -[2023-10-10 21:03:03,655][98560] Updated weights for policy 1, policy_version 8832 (0.0008) -[2023-10-10 21:03:03,768][98559] Updated weights for policy 0, policy_version 8770 (0.0009) -[2023-10-10 21:03:04,149][98559] Updated weights for policy 0, policy_version 8780 (0.0007) -[2023-10-10 21:03:04,522][98559] Updated weights for policy 0, policy_version 8790 (0.0007) -[2023-10-10 21:03:04,892][98559] Updated weights for policy 0, policy_version 8800 (0.0009) -[2023-10-10 21:03:05,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 18055168. Throughput: 0: 1685.7, 1: 1692.2. Samples: 4521162. Policy #0 lag: (min: 9.0, avg: 16.6, max: 41.0) -[2023-10-10 21:03:05,556][97672] Avg episode reward: [(0, '-6.860'), (1, '-1.960')] -[2023-10-10 21:03:05,564][98439] Saving new best policy, reward=-1.960! -[2023-10-10 21:03:07,645][98560] Updated weights for policy 1, policy_version 8842 (0.0008) -[2023-10-10 21:03:08,019][98560] Updated weights for policy 1, policy_version 8852 (0.0008) -[2023-10-10 21:03:08,387][98560] Updated weights for policy 1, policy_version 8862 (0.0007) -[2023-10-10 21:03:08,880][98559] Updated weights for policy 0, policy_version 8810 (0.0009) -[2023-10-10 21:03:09,257][98559] Updated weights for policy 0, policy_version 8820 (0.0008) -[2023-10-10 21:03:09,638][98559] Updated weights for policy 0, policy_version 8830 (0.0009) -[2023-10-10 21:03:10,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 18120704. Throughput: 0: 1715.6, 1: 1698.0. Samples: 4532552. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:03:10,556][97672] Avg episode reward: [(0, '-6.860'), (1, '-1.740')] -[2023-10-10 21:03:10,557][98439] Saving new best policy, reward=-1.740! -[2023-10-10 21:03:12,430][98560] Updated weights for policy 1, policy_version 8872 (0.0007) -[2023-10-10 21:03:12,795][98560] Updated weights for policy 1, policy_version 8882 (0.0008) -[2023-10-10 21:03:13,166][98560] Updated weights for policy 1, policy_version 8892 (0.0007) -[2023-10-10 21:03:13,660][98559] Updated weights for policy 0, policy_version 8840 (0.0009) -[2023-10-10 21:03:14,050][98559] Updated weights for policy 0, policy_version 8850 (0.0009) -[2023-10-10 21:03:14,420][98559] Updated weights for policy 0, policy_version 8860 (0.0010) -[2023-10-10 21:03:15,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 18186240. Throughput: 0: 1688.2, 1: 1676.8. Samples: 4551516. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:03:15,557][97672] Avg episode reward: [(0, '-6.860'), (1, '-1.720')] -[2023-10-10 21:03:15,559][98439] Saving new best policy, reward=-1.720! -[2023-10-10 21:03:17,196][98560] Updated weights for policy 1, policy_version 8902 (0.0009) -[2023-10-10 21:03:17,562][98560] Updated weights for policy 1, policy_version 8912 (0.0011) -[2023-10-10 21:03:17,929][98560] Updated weights for policy 1, policy_version 8922 (0.0010) -[2023-10-10 21:03:18,412][98559] Updated weights for policy 0, policy_version 8870 (0.0009) -[2023-10-10 21:03:18,791][98559] Updated weights for policy 0, policy_version 8880 (0.0008) -[2023-10-10 21:03:19,169][98559] Updated weights for policy 0, policy_version 8890 (0.0010) -[2023-10-10 21:03:20,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 18251776. Throughput: 0: 1692.0, 1: 1713.2. Samples: 4572492. Policy #0 lag: (min: 17.0, avg: 17.9, max: 35.0) -[2023-10-10 21:03:20,557][97672] Avg episode reward: [(0, '-6.860'), (1, '-1.540')] -[2023-10-10 21:03:20,568][98439] Saving new best policy, reward=-1.540! -[2023-10-10 21:03:21,910][98560] Updated weights for policy 1, policy_version 8932 (0.0010) -[2023-10-10 21:03:22,285][98560] Updated weights for policy 1, policy_version 8942 (0.0008) -[2023-10-10 21:03:22,644][98560] Updated weights for policy 1, policy_version 8952 (0.0008) -[2023-10-10 21:03:23,178][98559] Updated weights for policy 0, policy_version 8900 (0.0008) -[2023-10-10 21:03:23,571][98559] Updated weights for policy 0, policy_version 8910 (0.0008) -[2023-10-10 21:03:23,949][98559] Updated weights for policy 0, policy_version 8920 (0.0008) -[2023-10-10 21:03:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 18317312. Throughput: 0: 1699.5, 1: 1687.2. Samples: 4582766. Policy #0 lag: (min: 17.0, avg: 17.9, max: 35.0) -[2023-10-10 21:03:25,557][97672] Avg episode reward: [(0, '-6.820'), (1, '-1.180')] -[2023-10-10 21:03:25,559][98439] Saving new best policy, reward=-1.180! -[2023-10-10 21:03:26,532][98560] Updated weights for policy 1, policy_version 8962 (0.0008) -[2023-10-10 21:03:26,899][98560] Updated weights for policy 1, policy_version 8972 (0.0009) -[2023-10-10 21:03:27,276][98560] Updated weights for policy 1, policy_version 8982 (0.0007) -[2023-10-10 21:03:27,639][98560] Updated weights for policy 1, policy_version 8992 (0.0008) -[2023-10-10 21:03:27,823][98559] Updated weights for policy 0, policy_version 8930 (0.0009) -[2023-10-10 21:03:28,190][98559] Updated weights for policy 0, policy_version 8940 (0.0011) -[2023-10-10 21:03:28,552][98559] Updated weights for policy 0, policy_version 8950 (0.0010) -[2023-10-10 21:03:28,926][98559] Updated weights for policy 0, policy_version 8960 (0.0009) -[2023-10-10 21:03:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 18382848. Throughput: 0: 1675.6, 1: 1694.1. Samples: 4602516. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:03:30,557][97672] Avg episode reward: [(0, '-6.880'), (1, '-1.120')] -[2023-10-10 21:03:30,559][98439] Saving new best policy, reward=-1.120! -[2023-10-10 21:03:31,816][98560] Updated weights for policy 1, policy_version 9002 (0.0007) -[2023-10-10 21:03:32,183][98560] Updated weights for policy 1, policy_version 9012 (0.0007) -[2023-10-10 21:03:32,550][98560] Updated weights for policy 1, policy_version 9022 (0.0008) -[2023-10-10 21:03:33,010][98559] Updated weights for policy 0, policy_version 8970 (0.0010) -[2023-10-10 21:03:33,396][98559] Updated weights for policy 0, policy_version 8980 (0.0010) -[2023-10-10 21:03:33,772][98559] Updated weights for policy 0, policy_version 8990 (0.0009) -[2023-10-10 21:03:35,556][97672] Fps is (10 sec: 13106.7, 60 sec: 13653.2, 300 sec: 13551.5). Total num frames: 18448384. Throughput: 0: 1707.9, 1: 1710.9. Samples: 4623610. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:03:35,558][97672] Avg episode reward: [(0, '-6.880'), (1, '-0.940')] -[2023-10-10 21:03:35,572][98439] Saving new best policy, reward=-0.940! -[2023-10-10 21:03:36,601][98560] Updated weights for policy 1, policy_version 9032 (0.0009) -[2023-10-10 21:03:36,965][98560] Updated weights for policy 1, policy_version 9042 (0.0007) -[2023-10-10 21:03:37,327][98560] Updated weights for policy 1, policy_version 9052 (0.0010) -[2023-10-10 21:03:37,762][98559] Updated weights for policy 0, policy_version 9000 (0.0007) -[2023-10-10 21:03:38,133][98559] Updated weights for policy 0, policy_version 9010 (0.0011) -[2023-10-10 21:03:38,511][98559] Updated weights for policy 0, policy_version 9020 (0.0010) -[2023-10-10 21:03:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 18513920. Throughput: 0: 1686.3, 1: 1677.5. Samples: 4633150. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:03:40,557][97672] Avg episode reward: [(0, '-6.880'), (1, '-0.640')] -[2023-10-10 21:03:40,559][98439] Saving new best policy, reward=-0.640! -[2023-10-10 21:03:41,396][98560] Updated weights for policy 1, policy_version 9062 (0.0009) -[2023-10-10 21:03:41,769][98560] Updated weights for policy 1, policy_version 9072 (0.0009) -[2023-10-10 21:03:42,138][98560] Updated weights for policy 1, policy_version 9082 (0.0008) -[2023-10-10 21:03:42,378][98559] Updated weights for policy 0, policy_version 9030 (0.0010) -[2023-10-10 21:03:42,757][98559] Updated weights for policy 0, policy_version 9040 (0.0011) -[2023-10-10 21:03:43,134][98559] Updated weights for policy 0, policy_version 9050 (0.0007) -[2023-10-10 21:03:45,556][97672] Fps is (10 sec: 13107.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 18579456. Throughput: 0: 1696.9, 1: 1699.4. Samples: 4653872. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:03:45,557][97672] Avg episode reward: [(0, '-6.880'), (1, '-0.600')] -[2023-10-10 21:03:45,557][98439] Saving new best policy, reward=-0.600! -[2023-10-10 21:03:46,053][98560] Updated weights for policy 1, policy_version 9092 (0.0008) -[2023-10-10 21:03:46,445][98560] Updated weights for policy 1, policy_version 9102 (0.0007) -[2023-10-10 21:03:46,815][98560] Updated weights for policy 1, policy_version 9112 (0.0007) -[2023-10-10 21:03:46,953][98559] Updated weights for policy 0, policy_version 9060 (0.0008) -[2023-10-10 21:03:47,328][98559] Updated weights for policy 0, policy_version 9070 (0.0007) -[2023-10-10 21:03:47,704][98559] Updated weights for policy 0, policy_version 9080 (0.0007) -[2023-10-10 21:03:50,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 18644992. Throughput: 0: 1714.6, 1: 1700.7. Samples: 4674850. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-10 21:03:50,557][97672] Avg episode reward: [(0, '-6.840'), (1, '-0.600')] -[2023-10-10 21:03:50,905][98560] Updated weights for policy 1, policy_version 9122 (0.0008) -[2023-10-10 21:03:51,276][98560] Updated weights for policy 1, policy_version 9132 (0.0007) -[2023-10-10 21:03:51,649][98560] Updated weights for policy 1, policy_version 9142 (0.0009) -[2023-10-10 21:03:51,736][98559] Updated weights for policy 0, policy_version 9090 (0.0009) -[2023-10-10 21:03:52,019][98560] Updated weights for policy 1, policy_version 9152 (0.0007) -[2023-10-10 21:03:52,106][98559] Updated weights for policy 0, policy_version 9100 (0.0010) -[2023-10-10 21:03:52,482][98559] Updated weights for policy 0, policy_version 9110 (0.0011) -[2023-10-10 21:03:52,845][98559] Updated weights for policy 0, policy_version 9120 (0.0010) -[2023-10-10 21:03:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 18710528. Throughput: 0: 1683.2, 1: 1683.7. Samples: 4684064. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-10 21:03:55,556][97672] Avg episode reward: [(0, '-6.900'), (1, '-0.440')] -[2023-10-10 21:03:55,984][98560] Updated weights for policy 1, policy_version 9162 (0.0007) -[2023-10-10 21:03:56,364][98560] Updated weights for policy 1, policy_version 9172 (0.0009) -[2023-10-10 21:03:56,724][98560] Updated weights for policy 1, policy_version 9182 (0.0008) -[2023-10-10 21:03:56,791][98439] Saving new best policy, reward=-0.440! -[2023-10-10 21:03:56,838][98559] Updated weights for policy 0, policy_version 9130 (0.0008) -[2023-10-10 21:03:57,199][98559] Updated weights for policy 0, policy_version 9140 (0.0010) -[2023-10-10 21:03:57,572][98559] Updated weights for policy 0, policy_version 9150 (0.0008) -[2023-10-10 21:04:00,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 18776064. Throughput: 0: 1706.8, 1: 1706.6. Samples: 4705122. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:04:00,557][97672] Avg episode reward: [(0, '-6.900'), (1, '0.020')] -[2023-10-10 21:04:00,757][98560] Updated weights for policy 1, policy_version 9192 (0.0009) -[2023-10-10 21:04:01,132][98560] Updated weights for policy 1, policy_version 9202 (0.0008) -[2023-10-10 21:04:01,506][98560] Updated weights for policy 1, policy_version 9212 (0.0009) -[2023-10-10 21:04:01,650][98439] Saving new best policy, reward=0.020! -[2023-10-10 21:04:01,765][98559] Updated weights for policy 0, policy_version 9160 (0.0011) -[2023-10-10 21:04:02,143][98559] Updated weights for policy 0, policy_version 9170 (0.0008) -[2023-10-10 21:04:02,520][98559] Updated weights for policy 0, policy_version 9180 (0.0009) -[2023-10-10 21:04:05,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 18841600. Throughput: 0: 1716.3, 1: 1699.1. Samples: 4726184. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:04:05,557][97672] Avg episode reward: [(0, '-6.900'), (1, '0.160')] -[2023-10-10 21:04:05,605][98560] Updated weights for policy 1, policy_version 9222 (0.0009) -[2023-10-10 21:04:05,980][98560] Updated weights for policy 1, policy_version 9232 (0.0008) -[2023-10-10 21:04:06,353][98560] Updated weights for policy 1, policy_version 9242 (0.0009) -[2023-10-10 21:04:06,381][98559] Updated weights for policy 0, policy_version 9190 (0.0008) -[2023-10-10 21:04:06,564][98439] Saving new best policy, reward=0.160! -[2023-10-10 21:04:06,746][98559] Updated weights for policy 0, policy_version 9200 (0.0007) -[2023-10-10 21:04:07,118][98559] Updated weights for policy 0, policy_version 9210 (0.0007) -[2023-10-10 21:04:10,383][98560] Updated weights for policy 1, policy_version 9252 (0.0007) -[2023-10-10 21:04:10,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 18907136. Throughput: 0: 1694.8, 1: 1695.6. Samples: 4735334. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-10 21:04:10,556][97672] Avg episode reward: [(0, '-6.880'), (1, '0.320')] -[2023-10-10 21:04:10,755][98560] Updated weights for policy 1, policy_version 9262 (0.0008) -[2023-10-10 21:04:11,124][98560] Updated weights for policy 1, policy_version 9272 (0.0008) -[2023-10-10 21:04:11,229][98559] Updated weights for policy 0, policy_version 9220 (0.0009) -[2023-10-10 21:04:11,418][98439] Saving new best policy, reward=0.320! -[2023-10-10 21:04:11,599][98559] Updated weights for policy 0, policy_version 9230 (0.0009) -[2023-10-10 21:04:11,970][98559] Updated weights for policy 0, policy_version 9240 (0.0007) -[2023-10-10 21:04:14,962][98560] Updated weights for policy 1, policy_version 9282 (0.0008) -[2023-10-10 21:04:15,327][98560] Updated weights for policy 1, policy_version 9292 (0.0008) -[2023-10-10 21:04:15,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 18972672. Throughput: 0: 1716.0, 1: 1703.8. Samples: 4756406. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-10 21:04:15,557][97672] Avg episode reward: [(0, '-6.840'), (1, '0.200')] -[2023-10-10 21:04:15,702][98560] Updated weights for policy 1, policy_version 9302 (0.0008) -[2023-10-10 21:04:16,036][98559] Updated weights for policy 0, policy_version 9250 (0.0008) -[2023-10-10 21:04:16,067][98560] Updated weights for policy 1, policy_version 9312 (0.0008) -[2023-10-10 21:04:16,404][98559] Updated weights for policy 0, policy_version 9260 (0.0009) -[2023-10-10 21:04:16,787][98559] Updated weights for policy 0, policy_version 9270 (0.0010) -[2023-10-10 21:04:17,162][98559] Updated weights for policy 0, policy_version 9280 (0.0008) -[2023-10-10 21:04:20,059][98560] Updated weights for policy 1, policy_version 9322 (0.0008) -[2023-10-10 21:04:20,429][98560] Updated weights for policy 1, policy_version 9332 (0.0007) -[2023-10-10 21:04:20,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 19038208. Throughput: 0: 1715.6, 1: 1700.3. Samples: 4777324. Policy #0 lag: (min: 31.0, avg: 45.6, max: 63.0) -[2023-10-10 21:04:20,557][97672] Avg episode reward: [(0, '-6.820'), (1, '0.340')] -[2023-10-10 21:04:20,794][98560] Updated weights for policy 1, policy_version 9342 (0.0008) -[2023-10-10 21:04:20,869][98439] Saving new best policy, reward=0.340! -[2023-10-10 21:04:21,064][98559] Updated weights for policy 0, policy_version 9290 (0.0008) -[2023-10-10 21:04:21,449][98559] Updated weights for policy 0, policy_version 9300 (0.0007) -[2023-10-10 21:04:21,822][98559] Updated weights for policy 0, policy_version 9310 (0.0009) -[2023-10-10 21:04:24,619][98560] Updated weights for policy 1, policy_version 9352 (0.0011) -[2023-10-10 21:04:25,002][98560] Updated weights for policy 1, policy_version 9362 (0.0010) -[2023-10-10 21:04:25,358][98560] Updated weights for policy 1, policy_version 9372 (0.0010) -[2023-10-10 21:04:25,556][97672] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 19136512. Throughput: 0: 1704.4, 1: 1705.1. Samples: 4786580. Policy #0 lag: (min: 31.0, avg: 45.6, max: 63.0) -[2023-10-10 21:04:25,557][97672] Avg episode reward: [(0, '-6.820'), (1, '0.440')] -[2023-10-10 21:04:25,558][98439] Saving new best policy, reward=0.440! -[2023-10-10 21:04:25,771][98559] Updated weights for policy 0, policy_version 9320 (0.0008) -[2023-10-10 21:04:26,136][98559] Updated weights for policy 0, policy_version 9330 (0.0011) -[2023-10-10 21:04:26,519][98559] Updated weights for policy 0, policy_version 9340 (0.0009) -[2023-10-10 21:04:29,383][98560] Updated weights for policy 1, policy_version 9382 (0.0008) -[2023-10-10 21:04:29,744][98560] Updated weights for policy 1, policy_version 9392 (0.0009) -[2023-10-10 21:04:30,108][98560] Updated weights for policy 1, policy_version 9402 (0.0009) -[2023-10-10 21:04:30,556][97672] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 19202048. Throughput: 0: 1711.4, 1: 1711.2. Samples: 4807890. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-10 21:04:30,557][97672] Avg episode reward: [(0, '-6.820'), (1, '0.620')] -[2023-10-10 21:04:30,558][98439] Saving new best policy, reward=0.620! -[2023-10-10 21:04:30,708][98559] Updated weights for policy 0, policy_version 9350 (0.0008) -[2023-10-10 21:04:31,072][98559] Updated weights for policy 0, policy_version 9360 (0.0009) -[2023-10-10 21:04:31,449][98559] Updated weights for policy 0, policy_version 9370 (0.0008) -[2023-10-10 21:04:34,173][98560] Updated weights for policy 1, policy_version 9412 (0.0011) -[2023-10-10 21:04:34,586][98560] Updated weights for policy 1, policy_version 9422 (0.0010) -[2023-10-10 21:04:34,951][98560] Updated weights for policy 1, policy_version 9432 (0.0010) -[2023-10-10 21:04:35,309][98559] Updated weights for policy 0, policy_version 9380 (0.0007) -[2023-10-10 21:04:35,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 19267584. Throughput: 0: 1700.1, 1: 1698.8. Samples: 4827802. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-10 21:04:35,557][97672] Avg episode reward: [(0, '-6.820'), (1, '0.680')] -[2023-10-10 21:04:35,567][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000009440_9666560.pth... -[2023-10-10 21:04:35,603][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000007840_8028160.pth -[2023-10-10 21:04:35,607][98439] Saving new best policy, reward=0.680! -[2023-10-10 21:04:35,674][98559] Updated weights for policy 0, policy_version 9390 (0.0008) -[2023-10-10 21:04:36,054][98559] Updated weights for policy 0, policy_version 9400 (0.0008) -[2023-10-10 21:04:36,348][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000009408_9633792.pth... -[2023-10-10 21:04:36,386][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000007808_7995392.pth -[2023-10-10 21:04:38,766][98560] Updated weights for policy 1, policy_version 9442 (0.0010) -[2023-10-10 21:04:39,122][98560] Updated weights for policy 1, policy_version 9452 (0.0011) -[2023-10-10 21:04:39,486][98560] Updated weights for policy 1, policy_version 9462 (0.0009) -[2023-10-10 21:04:39,860][98560] Updated weights for policy 1, policy_version 9472 (0.0008) -[2023-10-10 21:04:39,937][98559] Updated weights for policy 0, policy_version 9410 (0.0010) -[2023-10-10 21:04:40,315][98559] Updated weights for policy 0, policy_version 9420 (0.0009) -[2023-10-10 21:04:40,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 19333120. Throughput: 0: 1707.4, 1: 1714.7. Samples: 4838060. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:04:40,557][97672] Avg episode reward: [(0, '-6.720'), (1, '0.720')] -[2023-10-10 21:04:40,557][98439] Saving new best policy, reward=0.720! -[2023-10-10 21:04:40,696][98559] Updated weights for policy 0, policy_version 9430 (0.0009) -[2023-10-10 21:04:41,065][98559] Updated weights for policy 0, policy_version 9440 (0.0007) -[2023-10-10 21:04:43,929][98560] Updated weights for policy 1, policy_version 9482 (0.0008) -[2023-10-10 21:04:44,297][98560] Updated weights for policy 1, policy_version 9492 (0.0008) -[2023-10-10 21:04:44,664][98560] Updated weights for policy 1, policy_version 9502 (0.0010) -[2023-10-10 21:04:45,101][98559] Updated weights for policy 0, policy_version 9450 (0.0007) -[2023-10-10 21:04:45,477][98559] Updated weights for policy 0, policy_version 9460 (0.0007) -[2023-10-10 21:04:45,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 19398656. Throughput: 0: 1712.9, 1: 1707.9. Samples: 4859058. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:04:45,557][97672] Avg episode reward: [(0, '-6.720'), (1, '1.080')] -[2023-10-10 21:04:45,559][98439] Saving new best policy, reward=1.080! -[2023-10-10 21:04:45,839][98559] Updated weights for policy 0, policy_version 9470 (0.0007) -[2023-10-10 21:04:48,690][98560] Updated weights for policy 1, policy_version 9512 (0.0007) -[2023-10-10 21:04:49,061][98560] Updated weights for policy 1, policy_version 9522 (0.0007) -[2023-10-10 21:04:49,431][98560] Updated weights for policy 1, policy_version 9532 (0.0008) -[2023-10-10 21:04:49,756][98559] Updated weights for policy 0, policy_version 9480 (0.0009) -[2023-10-10 21:04:50,124][98559] Updated weights for policy 0, policy_version 9490 (0.0011) -[2023-10-10 21:04:50,495][98559] Updated weights for policy 0, policy_version 9500 (0.0007) -[2023-10-10 21:04:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 19464192. Throughput: 0: 1694.2, 1: 1683.0. Samples: 4878156. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:04:50,557][97672] Avg episode reward: [(0, '-6.720'), (1, '1.200')] -[2023-10-10 21:04:50,565][98439] Saving new best policy, reward=1.200! -[2023-10-10 21:04:53,421][98560] Updated weights for policy 1, policy_version 9542 (0.0007) -[2023-10-10 21:04:53,791][98560] Updated weights for policy 1, policy_version 9552 (0.0010) -[2023-10-10 21:04:54,168][98560] Updated weights for policy 1, policy_version 9562 (0.0010) -[2023-10-10 21:04:54,491][98559] Updated weights for policy 0, policy_version 9510 (0.0010) -[2023-10-10 21:04:54,877][98559] Updated weights for policy 0, policy_version 9520 (0.0010) -[2023-10-10 21:04:55,248][98559] Updated weights for policy 0, policy_version 9530 (0.0011) -[2023-10-10 21:04:55,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 19562496. Throughput: 0: 1717.1, 1: 1712.8. Samples: 4889678. Policy #0 lag: (min: 9.0, avg: 25.7, max: 41.0) -[2023-10-10 21:04:55,557][97672] Avg episode reward: [(0, '-6.760'), (1, '1.160')] -[2023-10-10 21:04:58,277][98560] Updated weights for policy 1, policy_version 9572 (0.0008) -[2023-10-10 21:04:58,631][98560] Updated weights for policy 1, policy_version 9582 (0.0007) -[2023-10-10 21:04:59,006][98560] Updated weights for policy 1, policy_version 9592 (0.0008) -[2023-10-10 21:04:59,107][98559] Updated weights for policy 0, policy_version 9540 (0.0009) -[2023-10-10 21:04:59,476][98559] Updated weights for policy 0, policy_version 9550 (0.0009) -[2023-10-10 21:04:59,854][98559] Updated weights for policy 0, policy_version 9560 (0.0009) -[2023-10-10 21:05:00,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 19628032. Throughput: 0: 1711.7, 1: 1697.7. Samples: 4909828. Policy #0 lag: (min: 9.0, avg: 25.7, max: 41.0) -[2023-10-10 21:05:00,556][97672] Avg episode reward: [(0, '-6.760'), (1, '1.320')] -[2023-10-10 21:05:00,557][98439] Saving new best policy, reward=1.320! -[2023-10-10 21:05:03,203][98560] Updated weights for policy 1, policy_version 9602 (0.0010) -[2023-10-10 21:05:03,573][98560] Updated weights for policy 1, policy_version 9612 (0.0007) -[2023-10-10 21:05:03,755][98559] Updated weights for policy 0, policy_version 9570 (0.0009) -[2023-10-10 21:05:03,955][98560] Updated weights for policy 1, policy_version 9622 (0.0008) -[2023-10-10 21:05:04,116][98559] Updated weights for policy 0, policy_version 9580 (0.0008) -[2023-10-10 21:05:04,319][98560] Updated weights for policy 1, policy_version 9632 (0.0009) -[2023-10-10 21:05:04,493][98559] Updated weights for policy 0, policy_version 9590 (0.0009) -[2023-10-10 21:05:04,864][98559] Updated weights for policy 0, policy_version 9600 (0.0009) -[2023-10-10 21:05:05,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 19693568. Throughput: 0: 1692.4, 1: 1684.4. Samples: 4929276. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-10 21:05:05,557][97672] Avg episode reward: [(0, '-6.760'), (1, '1.600')] -[2023-10-10 21:05:05,568][98439] Saving new best policy, reward=1.600! -[2023-10-10 21:05:08,346][98560] Updated weights for policy 1, policy_version 9642 (0.0011) -[2023-10-10 21:05:08,710][98560] Updated weights for policy 1, policy_version 9652 (0.0007) -[2023-10-10 21:05:08,844][98559] Updated weights for policy 0, policy_version 9610 (0.0009) -[2023-10-10 21:05:09,078][98560] Updated weights for policy 1, policy_version 9662 (0.0007) -[2023-10-10 21:05:09,225][98559] Updated weights for policy 0, policy_version 9620 (0.0009) -[2023-10-10 21:05:09,596][98559] Updated weights for policy 0, policy_version 9630 (0.0008) -[2023-10-10 21:05:10,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 19759104. Throughput: 0: 1726.3, 1: 1711.2. Samples: 4941270. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-10 21:05:10,557][97672] Avg episode reward: [(0, '-6.680'), (1, '1.460')] -[2023-10-10 21:05:13,099][98560] Updated weights for policy 1, policy_version 9672 (0.0009) -[2023-10-10 21:05:13,473][98560] Updated weights for policy 1, policy_version 9682 (0.0008) -[2023-10-10 21:05:13,620][98559] Updated weights for policy 0, policy_version 9640 (0.0010) -[2023-10-10 21:05:13,832][98560] Updated weights for policy 1, policy_version 9692 (0.0008) -[2023-10-10 21:05:13,988][98559] Updated weights for policy 0, policy_version 9650 (0.0008) -[2023-10-10 21:05:14,362][98559] Updated weights for policy 0, policy_version 9660 (0.0008) -[2023-10-10 21:05:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 19824640. Throughput: 0: 1698.9, 1: 1683.7. Samples: 4960106. Policy #0 lag: (min: 25.0, avg: 32.7, max: 57.0) -[2023-10-10 21:05:15,557][97672] Avg episode reward: [(0, '-6.680'), (1, '1.380')] -[2023-10-10 21:05:17,758][98560] Updated weights for policy 1, policy_version 9702 (0.0007) -[2023-10-10 21:05:18,134][98560] Updated weights for policy 1, policy_version 9712 (0.0011) -[2023-10-10 21:05:18,422][98559] Updated weights for policy 0, policy_version 9670 (0.0008) -[2023-10-10 21:05:18,505][98560] Updated weights for policy 1, policy_version 9722 (0.0008) -[2023-10-10 21:05:18,788][98559] Updated weights for policy 0, policy_version 9680 (0.0007) -[2023-10-10 21:05:19,160][98559] Updated weights for policy 0, policy_version 9690 (0.0008) -[2023-10-10 21:05:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 19890176. Throughput: 0: 1698.8, 1: 1693.9. Samples: 4980472. Policy #0 lag: (min: 25.0, avg: 32.7, max: 57.0) -[2023-10-10 21:05:20,557][97672] Avg episode reward: [(0, '-6.680'), (1, '1.180')] -[2023-10-10 21:05:22,571][98560] Updated weights for policy 1, policy_version 9732 (0.0009) -[2023-10-10 21:05:22,976][98560] Updated weights for policy 1, policy_version 9742 (0.0009) -[2023-10-10 21:05:23,144][98559] Updated weights for policy 0, policy_version 9700 (0.0008) -[2023-10-10 21:05:23,344][98560] Updated weights for policy 1, policy_version 9752 (0.0009) -[2023-10-10 21:05:23,521][98559] Updated weights for policy 0, policy_version 9710 (0.0010) -[2023-10-10 21:05:23,895][98559] Updated weights for policy 0, policy_version 9720 (0.0007) -[2023-10-10 21:05:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 19955712. Throughput: 0: 1714.6, 1: 1694.8. Samples: 4991484. Policy #0 lag: (min: 31.0, avg: 45.9, max: 63.0) -[2023-10-10 21:05:25,557][97672] Avg episode reward: [(0, '-6.660'), (1, '1.240')] -[2023-10-10 21:05:25,558][98385] Saving new best policy, reward=-6.660! -[2023-10-10 21:05:27,438][98560] Updated weights for policy 1, policy_version 9762 (0.0008) -[2023-10-10 21:05:27,809][98560] Updated weights for policy 1, policy_version 9772 (0.0009) -[2023-10-10 21:05:27,825][98559] Updated weights for policy 0, policy_version 9730 (0.0007) -[2023-10-10 21:05:28,180][98560] Updated weights for policy 1, policy_version 9782 (0.0009) -[2023-10-10 21:05:28,196][98559] Updated weights for policy 0, policy_version 9740 (0.0009) -[2023-10-10 21:05:28,544][98560] Updated weights for policy 1, policy_version 9792 (0.0009) -[2023-10-10 21:05:28,564][98559] Updated weights for policy 0, policy_version 9750 (0.0010) -[2023-10-10 21:05:28,933][98559] Updated weights for policy 0, policy_version 9760 (0.0008) -[2023-10-10 21:05:30,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 20021248. Throughput: 0: 1691.7, 1: 1677.7. Samples: 5010682. Policy #0 lag: (min: 31.0, avg: 45.9, max: 63.0) -[2023-10-10 21:05:30,556][97672] Avg episode reward: [(0, '-6.660'), (1, '1.240')] -[2023-10-10 21:05:32,519][98560] Updated weights for policy 1, policy_version 9802 (0.0009) -[2023-10-10 21:05:32,895][98560] Updated weights for policy 1, policy_version 9812 (0.0007) -[2023-10-10 21:05:32,943][98559] Updated weights for policy 0, policy_version 9770 (0.0008) -[2023-10-10 21:05:33,263][98560] Updated weights for policy 1, policy_version 9822 (0.0009) -[2023-10-10 21:05:33,306][98559] Updated weights for policy 0, policy_version 9780 (0.0008) -[2023-10-10 21:05:33,685][98559] Updated weights for policy 0, policy_version 9790 (0.0009) -[2023-10-10 21:05:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 20086784. Throughput: 0: 1712.8, 1: 1702.0. Samples: 5031824. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 21:05:35,557][97672] Avg episode reward: [(0, '-6.660'), (1, '1.300')] -[2023-10-10 21:05:37,285][98560] Updated weights for policy 1, policy_version 9832 (0.0009) -[2023-10-10 21:05:37,617][98559] Updated weights for policy 0, policy_version 9800 (0.0008) -[2023-10-10 21:05:37,651][98560] Updated weights for policy 1, policy_version 9842 (0.0008) -[2023-10-10 21:05:37,992][98559] Updated weights for policy 0, policy_version 9810 (0.0009) -[2023-10-10 21:05:38,018][98560] Updated weights for policy 1, policy_version 9852 (0.0008) -[2023-10-10 21:05:38,368][98559] Updated weights for policy 0, policy_version 9820 (0.0008) -[2023-10-10 21:05:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 20152320. Throughput: 0: 1697.4, 1: 1684.8. Samples: 5041876. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 21:05:40,556][97672] Avg episode reward: [(0, '-6.660'), (1, '1.500')] -[2023-10-10 21:05:42,008][98560] Updated weights for policy 1, policy_version 9862 (0.0008) -[2023-10-10 21:05:42,369][98559] Updated weights for policy 0, policy_version 9830 (0.0008) -[2023-10-10 21:05:42,373][98560] Updated weights for policy 1, policy_version 9872 (0.0009) -[2023-10-10 21:05:42,736][98559] Updated weights for policy 0, policy_version 9840 (0.0008) -[2023-10-10 21:05:42,738][98560] Updated weights for policy 1, policy_version 9882 (0.0009) -[2023-10-10 21:05:43,111][98559] Updated weights for policy 0, policy_version 9850 (0.0008) -[2023-10-10 21:05:45,556][97672] Fps is (10 sec: 13107.7, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 20217856. Throughput: 0: 1700.9, 1: 1689.0. Samples: 5062376. Policy #0 lag: (min: 3.0, avg: 3.1, max: 10.0) -[2023-10-10 21:05:45,556][97672] Avg episode reward: [(0, '-6.660'), (1, '1.480')] -[2023-10-10 21:05:46,739][98560] Updated weights for policy 1, policy_version 9892 (0.0009) -[2023-10-10 21:05:47,107][98560] Updated weights for policy 1, policy_version 9902 (0.0008) -[2023-10-10 21:05:47,167][98559] Updated weights for policy 0, policy_version 9860 (0.0009) -[2023-10-10 21:05:47,476][98560] Updated weights for policy 1, policy_version 9912 (0.0008) -[2023-10-10 21:05:47,551][98559] Updated weights for policy 0, policy_version 9870 (0.0009) -[2023-10-10 21:05:47,919][98559] Updated weights for policy 0, policy_version 9880 (0.0009) -[2023-10-10 21:05:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 20283392. Throughput: 0: 1716.6, 1: 1706.5. Samples: 5083318. Policy #0 lag: (min: 3.0, avg: 3.1, max: 10.0) -[2023-10-10 21:05:50,556][97672] Avg episode reward: [(0, '-6.560'), (1, '1.520')] -[2023-10-10 21:05:50,567][98385] Saving new best policy, reward=-6.560! -[2023-10-10 21:05:51,383][98560] Updated weights for policy 1, policy_version 9922 (0.0008) -[2023-10-10 21:05:51,749][98560] Updated weights for policy 1, policy_version 9932 (0.0009) -[2023-10-10 21:05:51,934][98559] Updated weights for policy 0, policy_version 9890 (0.0010) -[2023-10-10 21:05:52,125][98560] Updated weights for policy 1, policy_version 9942 (0.0007) -[2023-10-10 21:05:52,313][98559] Updated weights for policy 0, policy_version 9900 (0.0007) -[2023-10-10 21:05:52,488][98560] Updated weights for policy 1, policy_version 9952 (0.0008) -[2023-10-10 21:05:52,685][98559] Updated weights for policy 0, policy_version 9910 (0.0008) -[2023-10-10 21:05:53,057][98559] Updated weights for policy 0, policy_version 9920 (0.0009) -[2023-10-10 21:05:55,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 20348928. Throughput: 0: 1682.6, 1: 1677.4. Samples: 5092472. Policy #0 lag: (min: 24.0, avg: 52.2, max: 56.0) -[2023-10-10 21:05:55,557][97672] Avg episode reward: [(0, '-6.560'), (1, '1.620')] -[2023-10-10 21:05:55,557][98439] Saving new best policy, reward=1.620! -[2023-10-10 21:05:56,437][98560] Updated weights for policy 1, policy_version 9962 (0.0009) -[2023-10-10 21:05:56,810][98560] Updated weights for policy 1, policy_version 9972 (0.0007) -[2023-10-10 21:05:56,961][98559] Updated weights for policy 0, policy_version 9930 (0.0008) -[2023-10-10 21:05:57,174][98560] Updated weights for policy 1, policy_version 9982 (0.0009) -[2023-10-10 21:05:57,330][98559] Updated weights for policy 0, policy_version 9940 (0.0008) -[2023-10-10 21:05:57,713][98559] Updated weights for policy 0, policy_version 9950 (0.0008) -[2023-10-10 21:06:00,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 20414464. Throughput: 0: 1710.7, 1: 1699.5. Samples: 5113564. Policy #0 lag: (min: 24.0, avg: 52.2, max: 56.0) -[2023-10-10 21:06:00,557][97672] Avg episode reward: [(0, '-6.560'), (1, '1.560')] -[2023-10-10 21:06:01,261][98560] Updated weights for policy 1, policy_version 9992 (0.0008) -[2023-10-10 21:06:01,628][98560] Updated weights for policy 1, policy_version 10002 (0.0007) -[2023-10-10 21:06:01,684][98559] Updated weights for policy 0, policy_version 9960 (0.0008) -[2023-10-10 21:06:01,992][98560] Updated weights for policy 1, policy_version 10012 (0.0008) -[2023-10-10 21:06:02,052][98559] Updated weights for policy 0, policy_version 9970 (0.0007) -[2023-10-10 21:06:02,438][98559] Updated weights for policy 0, policy_version 9980 (0.0008) -[2023-10-10 21:06:05,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 20480000. Throughput: 0: 1715.8, 1: 1710.3. Samples: 5134648. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:06:05,556][97672] Avg episode reward: [(0, '-6.560'), (1, '1.700')] -[2023-10-10 21:06:05,567][98439] Saving new best policy, reward=1.700! -[2023-10-10 21:06:05,952][98560] Updated weights for policy 1, policy_version 10022 (0.0010) -[2023-10-10 21:06:06,327][98560] Updated weights for policy 1, policy_version 10032 (0.0008) -[2023-10-10 21:06:06,418][98559] Updated weights for policy 0, policy_version 9990 (0.0009) -[2023-10-10 21:06:06,698][98560] Updated weights for policy 1, policy_version 10042 (0.0008) -[2023-10-10 21:06:06,790][98559] Updated weights for policy 0, policy_version 10000 (0.0009) -[2023-10-10 21:06:07,152][98559] Updated weights for policy 0, policy_version 10010 (0.0009) -[2023-10-10 21:06:10,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 20545536. Throughput: 0: 1692.8, 1: 1691.4. Samples: 5143772. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:06:10,557][97672] Avg episode reward: [(0, '-6.560'), (1, '1.940')] -[2023-10-10 21:06:10,831][98560] Updated weights for policy 1, policy_version 10052 (0.0007) -[2023-10-10 21:06:11,114][98559] Updated weights for policy 0, policy_version 10020 (0.0008) -[2023-10-10 21:06:11,193][98560] Updated weights for policy 1, policy_version 10062 (0.0008) -[2023-10-10 21:06:11,492][98559] Updated weights for policy 0, policy_version 10030 (0.0010) -[2023-10-10 21:06:11,559][98560] Updated weights for policy 1, policy_version 10072 (0.0008) -[2023-10-10 21:06:11,852][98439] Saving new best policy, reward=1.940! -[2023-10-10 21:06:11,876][98559] Updated weights for policy 0, policy_version 10040 (0.0007) -[2023-10-10 21:06:15,551][98560] Updated weights for policy 1, policy_version 10082 (0.0007) -[2023-10-10 21:06:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 20611072. Throughput: 0: 1713.9, 1: 1709.4. Samples: 5164732. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-10-10 21:06:15,556][97672] Avg episode reward: [(0, '-6.580'), (1, '1.980')] -[2023-10-10 21:06:15,901][98559] Updated weights for policy 0, policy_version 10050 (0.0007) -[2023-10-10 21:06:15,925][98560] Updated weights for policy 1, policy_version 10092 (0.0008) -[2023-10-10 21:06:16,274][98559] Updated weights for policy 0, policy_version 10060 (0.0008) -[2023-10-10 21:06:16,290][98560] Updated weights for policy 1, policy_version 10102 (0.0008) -[2023-10-10 21:06:16,642][98559] Updated weights for policy 0, policy_version 10070 (0.0007) -[2023-10-10 21:06:16,652][98439] Saving new best policy, reward=1.980! -[2023-10-10 21:06:16,656][98560] Updated weights for policy 1, policy_version 10112 (0.0009) -[2023-10-10 21:06:17,018][98559] Updated weights for policy 0, policy_version 10080 (0.0007) -[2023-10-10 21:06:20,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 20676608. Throughput: 0: 1709.5, 1: 1709.5. Samples: 5185680. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-10-10 21:06:20,557][97672] Avg episode reward: [(0, '-6.580'), (1, '2.040')] -[2023-10-10 21:06:20,767][98560] Updated weights for policy 1, policy_version 10122 (0.0007) -[2023-10-10 21:06:20,900][98559] Updated weights for policy 0, policy_version 10090 (0.0008) -[2023-10-10 21:06:21,126][98560] Updated weights for policy 1, policy_version 10132 (0.0009) -[2023-10-10 21:06:21,279][98559] Updated weights for policy 0, policy_version 10100 (0.0009) -[2023-10-10 21:06:21,495][98560] Updated weights for policy 1, policy_version 10142 (0.0008) -[2023-10-10 21:06:21,567][98439] Saving new best policy, reward=2.040! -[2023-10-10 21:06:21,656][98559] Updated weights for policy 0, policy_version 10110 (0.0008) -[2023-10-10 21:06:25,514][98560] Updated weights for policy 1, policy_version 10152 (0.0008) -[2023-10-10 21:06:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 20742144. Throughput: 0: 1703.9, 1: 1693.0. Samples: 5194738. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-10 21:06:25,557][97672] Avg episode reward: [(0, '-6.580'), (1, '2.200')] -[2023-10-10 21:06:25,626][98559] Updated weights for policy 0, policy_version 10120 (0.0007) -[2023-10-10 21:06:25,879][98560] Updated weights for policy 1, policy_version 10162 (0.0008) -[2023-10-10 21:06:26,008][98559] Updated weights for policy 0, policy_version 10130 (0.0007) -[2023-10-10 21:06:26,240][98560] Updated weights for policy 1, policy_version 10172 (0.0008) -[2023-10-10 21:06:26,370][98559] Updated weights for policy 0, policy_version 10140 (0.0007) -[2023-10-10 21:06:26,390][98439] Saving new best policy, reward=2.200! -[2023-10-10 21:06:30,343][98560] Updated weights for policy 1, policy_version 10182 (0.0009) -[2023-10-10 21:06:30,458][98559] Updated weights for policy 0, policy_version 10150 (0.0008) -[2023-10-10 21:06:30,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 20807680. Throughput: 0: 1711.8, 1: 1699.0. Samples: 5215862. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-10 21:06:30,556][97672] Avg episode reward: [(0, '-6.580'), (1, '2.700')] -[2023-10-10 21:06:30,707][98560] Updated weights for policy 1, policy_version 10192 (0.0008) -[2023-10-10 21:06:30,831][98559] Updated weights for policy 0, policy_version 10160 (0.0009) -[2023-10-10 21:06:31,073][98560] Updated weights for policy 1, policy_version 10202 (0.0007) -[2023-10-10 21:06:31,201][98559] Updated weights for policy 0, policy_version 10170 (0.0011) -[2023-10-10 21:06:31,291][98439] Saving new best policy, reward=2.700! -[2023-10-10 21:06:35,158][98560] Updated weights for policy 1, policy_version 10212 (0.0007) -[2023-10-10 21:06:35,277][98559] Updated weights for policy 0, policy_version 10180 (0.0009) -[2023-10-10 21:06:35,526][98560] Updated weights for policy 1, policy_version 10222 (0.0007) -[2023-10-10 21:06:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 20873216. Throughput: 0: 1702.7, 1: 1700.4. Samples: 5236460. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-10 21:06:35,557][97672] Avg episode reward: [(0, '-6.580'), (1, '2.860')] -[2023-10-10 21:06:35,666][98559] Updated weights for policy 0, policy_version 10190 (0.0008) -[2023-10-10 21:06:35,893][98560] Updated weights for policy 1, policy_version 10232 (0.0007) -[2023-10-10 21:06:36,037][98559] Updated weights for policy 0, policy_version 10200 (0.0008) -[2023-10-10 21:06:36,184][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000010240_10485760.pth... -[2023-10-10 21:06:36,224][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000008640_8847360.pth -[2023-10-10 21:06:36,229][98439] Saving new best policy, reward=2.860! -[2023-10-10 21:06:36,327][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000010208_10452992.pth... -[2023-10-10 21:06:36,360][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000008608_8814592.pth -[2023-10-10 21:06:39,952][98560] Updated weights for policy 1, policy_version 10242 (0.0007) -[2023-10-10 21:06:39,999][98559] Updated weights for policy 0, policy_version 10210 (0.0011) -[2023-10-10 21:06:40,320][98560] Updated weights for policy 1, policy_version 10252 (0.0007) -[2023-10-10 21:06:40,365][98559] Updated weights for policy 0, policy_version 10220 (0.0010) -[2023-10-10 21:06:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 20938752. Throughput: 0: 1708.7, 1: 1701.2. Samples: 5245918. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-10 21:06:40,556][97672] Avg episode reward: [(0, '-6.580'), (1, '3.080')] -[2023-10-10 21:06:40,690][98560] Updated weights for policy 1, policy_version 10262 (0.0007) -[2023-10-10 21:06:40,743][98559] Updated weights for policy 0, policy_version 10230 (0.0009) -[2023-10-10 21:06:41,052][98439] Saving new best policy, reward=3.080! -[2023-10-10 21:06:41,055][98560] Updated weights for policy 1, policy_version 10272 (0.0008) -[2023-10-10 21:06:41,106][98559] Updated weights for policy 0, policy_version 10240 (0.0008) -[2023-10-10 21:06:44,856][98560] Updated weights for policy 1, policy_version 10282 (0.0011) -[2023-10-10 21:06:45,218][98560] Updated weights for policy 1, policy_version 10292 (0.0008) -[2023-10-10 21:06:45,237][98559] Updated weights for policy 0, policy_version 10250 (0.0010) -[2023-10-10 21:06:45,556][97672] Fps is (10 sec: 13107.7, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 21004288. Throughput: 0: 1709.4, 1: 1704.0. Samples: 5267168. Policy #0 lag: (min: 5.0, avg: 11.5, max: 37.0) -[2023-10-10 21:06:45,556][97672] Avg episode reward: [(0, '-6.580'), (1, '3.460')] -[2023-10-10 21:06:45,588][98560] Updated weights for policy 1, policy_version 10302 (0.0007) -[2023-10-10 21:06:45,603][98559] Updated weights for policy 0, policy_version 10260 (0.0007) -[2023-10-10 21:06:45,658][98439] Saving new best policy, reward=3.460! -[2023-10-10 21:06:45,978][98559] Updated weights for policy 0, policy_version 10270 (0.0009) -[2023-10-10 21:06:49,687][98560] Updated weights for policy 1, policy_version 10312 (0.0009) -[2023-10-10 21:06:49,860][98559] Updated weights for policy 0, policy_version 10280 (0.0009) -[2023-10-10 21:06:50,058][98560] Updated weights for policy 1, policy_version 10322 (0.0008) -[2023-10-10 21:06:50,227][98559] Updated weights for policy 0, policy_version 10290 (0.0007) -[2023-10-10 21:06:50,420][98560] Updated weights for policy 1, policy_version 10332 (0.0007) -[2023-10-10 21:06:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 21069824. Throughput: 0: 1693.9, 1: 1691.3. Samples: 5286982. Policy #0 lag: (min: 5.0, avg: 11.5, max: 37.0) -[2023-10-10 21:06:50,556][97672] Avg episode reward: [(0, '-6.580'), (1, '3.660')] -[2023-10-10 21:06:50,568][98439] Saving new best policy, reward=3.660! -[2023-10-10 21:06:50,609][98559] Updated weights for policy 0, policy_version 10300 (0.0009) -[2023-10-10 21:06:54,463][98560] Updated weights for policy 1, policy_version 10342 (0.0008) -[2023-10-10 21:06:54,609][98559] Updated weights for policy 0, policy_version 10310 (0.0010) -[2023-10-10 21:06:54,835][98560] Updated weights for policy 1, policy_version 10352 (0.0010) -[2023-10-10 21:06:54,976][98559] Updated weights for policy 0, policy_version 10320 (0.0008) -[2023-10-10 21:06:55,202][98560] Updated weights for policy 1, policy_version 10362 (0.0009) -[2023-10-10 21:06:55,353][98559] Updated weights for policy 0, policy_version 10330 (0.0008) -[2023-10-10 21:06:55,556][97672] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 21168128. Throughput: 0: 1710.2, 1: 1701.3. Samples: 5297290. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-10 21:06:55,557][97672] Avg episode reward: [(0, '-6.580'), (1, '3.780')] -[2023-10-10 21:06:55,558][98439] Saving new best policy, reward=3.780! -[2023-10-10 21:06:59,206][98560] Updated weights for policy 1, policy_version 10372 (0.0007) -[2023-10-10 21:06:59,326][98559] Updated weights for policy 0, policy_version 10340 (0.0008) -[2023-10-10 21:06:59,605][98560] Updated weights for policy 1, policy_version 10382 (0.0009) -[2023-10-10 21:06:59,695][98559] Updated weights for policy 0, policy_version 10350 (0.0008) -[2023-10-10 21:06:59,968][98560] Updated weights for policy 1, policy_version 10392 (0.0008) -[2023-10-10 21:07:00,056][98559] Updated weights for policy 0, policy_version 10360 (0.0008) -[2023-10-10 21:07:00,556][97672] Fps is (10 sec: 19660.9, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 21266432. Throughput: 0: 1708.8, 1: 1706.0. Samples: 5318398. Policy #0 lag: (min: 22.0, avg: 22.0, max: 26.0) -[2023-10-10 21:07:00,556][97672] Avg episode reward: [(0, '-6.580'), (1, '4.180')] -[2023-10-10 21:07:00,557][98439] Saving new best policy, reward=4.180! -[2023-10-10 21:07:03,930][98559] Updated weights for policy 0, policy_version 10370 (0.0008) -[2023-10-10 21:07:03,987][98560] Updated weights for policy 1, policy_version 10402 (0.0008) -[2023-10-10 21:07:04,298][98559] Updated weights for policy 0, policy_version 10380 (0.0009) -[2023-10-10 21:07:04,362][98560] Updated weights for policy 1, policy_version 10412 (0.0008) -[2023-10-10 21:07:04,671][98559] Updated weights for policy 0, policy_version 10390 (0.0008) -[2023-10-10 21:07:04,725][98560] Updated weights for policy 1, policy_version 10422 (0.0008) -[2023-10-10 21:07:05,044][98559] Updated weights for policy 0, policy_version 10400 (0.0009) -[2023-10-10 21:07:05,089][98560] Updated weights for policy 1, policy_version 10432 (0.0008) -[2023-10-10 21:07:05,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 21331968. Throughput: 0: 1685.5, 1: 1680.8. Samples: 5337164. Policy #0 lag: (min: 22.0, avg: 22.0, max: 26.0) -[2023-10-10 21:07:05,557][97672] Avg episode reward: [(0, '-6.580'), (1, '4.380')] -[2023-10-10 21:07:05,567][98439] Saving new best policy, reward=4.380! -[2023-10-10 21:07:09,044][98559] Updated weights for policy 0, policy_version 10410 (0.0008) -[2023-10-10 21:07:09,131][98560] Updated weights for policy 1, policy_version 10442 (0.0009) -[2023-10-10 21:07:09,409][98559] Updated weights for policy 0, policy_version 10420 (0.0009) -[2023-10-10 21:07:09,496][98560] Updated weights for policy 1, policy_version 10452 (0.0008) -[2023-10-10 21:07:09,787][98559] Updated weights for policy 0, policy_version 10430 (0.0008) -[2023-10-10 21:07:09,861][98560] Updated weights for policy 1, policy_version 10462 (0.0008) -[2023-10-10 21:07:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 21397504. Throughput: 0: 1718.3, 1: 1701.0. Samples: 5348604. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:07:10,556][97672] Avg episode reward: [(0, '-6.580'), (1, '4.460')] -[2023-10-10 21:07:10,557][98439] Saving new best policy, reward=4.460! -[2023-10-10 21:07:13,756][98560] Updated weights for policy 1, policy_version 10472 (0.0008) -[2023-10-10 21:07:13,811][98559] Updated weights for policy 0, policy_version 10440 (0.0007) -[2023-10-10 21:07:14,118][98560] Updated weights for policy 1, policy_version 10482 (0.0008) -[2023-10-10 21:07:14,180][98559] Updated weights for policy 0, policy_version 10450 (0.0007) -[2023-10-10 21:07:14,476][98560] Updated weights for policy 1, policy_version 10492 (0.0008) -[2023-10-10 21:07:14,554][98559] Updated weights for policy 0, policy_version 10460 (0.0008) -[2023-10-10 21:07:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 21463040. Throughput: 0: 1694.4, 1: 1700.3. Samples: 5368622. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:07:15,557][97672] Avg episode reward: [(0, '-6.580'), (1, '4.780')] -[2023-10-10 21:07:15,557][98439] Saving new best policy, reward=4.780! -[2023-10-10 21:07:18,476][98559] Updated weights for policy 0, policy_version 10470 (0.0008) -[2023-10-10 21:07:18,628][98560] Updated weights for policy 1, policy_version 10502 (0.0009) -[2023-10-10 21:07:18,853][98559] Updated weights for policy 0, policy_version 10480 (0.0007) -[2023-10-10 21:07:19,001][98560] Updated weights for policy 1, policy_version 10512 (0.0007) -[2023-10-10 21:07:19,219][98559] Updated weights for policy 0, policy_version 10490 (0.0007) -[2023-10-10 21:07:19,379][98560] Updated weights for policy 1, policy_version 10522 (0.0007) -[2023-10-10 21:07:20,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 21528576. Throughput: 0: 1695.6, 1: 1677.6. Samples: 5388258. Policy #0 lag: (min: 28.0, avg: 32.0, max: 60.0) -[2023-10-10 21:07:20,557][97672] Avg episode reward: [(0, '-6.580'), (1, '5.220')] -[2023-10-10 21:07:20,572][98439] Saving new best policy, reward=5.220! -[2023-10-10 21:07:23,240][98559] Updated weights for policy 0, policy_version 10500 (0.0007) -[2023-10-10 21:07:23,452][98560] Updated weights for policy 1, policy_version 10532 (0.0008) -[2023-10-10 21:07:23,607][98559] Updated weights for policy 0, policy_version 10510 (0.0007) -[2023-10-10 21:07:23,816][98560] Updated weights for policy 1, policy_version 10542 (0.0008) -[2023-10-10 21:07:23,982][98559] Updated weights for policy 0, policy_version 10520 (0.0007) -[2023-10-10 21:07:24,181][98560] Updated weights for policy 1, policy_version 10552 (0.0009) -[2023-10-10 21:07:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 21594112. Throughput: 0: 1713.9, 1: 1707.8. Samples: 5399894. Policy #0 lag: (min: 28.0, avg: 32.0, max: 60.0) -[2023-10-10 21:07:25,557][97672] Avg episode reward: [(0, '-6.580'), (1, '5.540')] -[2023-10-10 21:07:25,558][98439] Saving new best policy, reward=5.540! -[2023-10-10 21:07:28,076][98560] Updated weights for policy 1, policy_version 10562 (0.0009) -[2023-10-10 21:07:28,115][98559] Updated weights for policy 0, policy_version 10530 (0.0008) -[2023-10-10 21:07:28,451][98560] Updated weights for policy 1, policy_version 10572 (0.0009) -[2023-10-10 21:07:28,479][98559] Updated weights for policy 0, policy_version 10540 (0.0008) -[2023-10-10 21:07:28,825][98560] Updated weights for policy 1, policy_version 10582 (0.0007) -[2023-10-10 21:07:28,862][98559] Updated weights for policy 0, policy_version 10550 (0.0008) -[2023-10-10 21:07:29,194][98560] Updated weights for policy 1, policy_version 10592 (0.0008) -[2023-10-10 21:07:29,234][98559] Updated weights for policy 0, policy_version 10560 (0.0009) -[2023-10-10 21:07:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 21659648. Throughput: 0: 1680.7, 1: 1693.4. Samples: 5419002. Policy #0 lag: (min: 25.0, avg: 31.4, max: 57.0) -[2023-10-10 21:07:30,557][97672] Avg episode reward: [(0, '-6.580'), (1, '6.300')] -[2023-10-10 21:07:30,559][98439] Saving new best policy, reward=6.300! -[2023-10-10 21:07:33,164][98560] Updated weights for policy 1, policy_version 10602 (0.0009) -[2023-10-10 21:07:33,312][98559] Updated weights for policy 0, policy_version 10570 (0.0007) -[2023-10-10 21:07:33,541][98560] Updated weights for policy 1, policy_version 10612 (0.0008) -[2023-10-10 21:07:33,687][98559] Updated weights for policy 0, policy_version 10580 (0.0008) -[2023-10-10 21:07:33,908][98560] Updated weights for policy 1, policy_version 10622 (0.0007) -[2023-10-10 21:07:34,060][98559] Updated weights for policy 0, policy_version 10590 (0.0007) -[2023-10-10 21:07:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 21725184. Throughput: 0: 1695.4, 1: 1689.4. Samples: 5439298. Policy #0 lag: (min: 25.0, avg: 31.4, max: 57.0) -[2023-10-10 21:07:35,557][97672] Avg episode reward: [(0, '-6.580'), (1, '6.640')] -[2023-10-10 21:07:35,570][98439] Saving new best policy, reward=6.640! -[2023-10-10 21:07:37,898][98560] Updated weights for policy 1, policy_version 10632 (0.0008) -[2023-10-10 21:07:38,165][98559] Updated weights for policy 0, policy_version 10600 (0.0009) -[2023-10-10 21:07:38,266][98560] Updated weights for policy 1, policy_version 10642 (0.0007) -[2023-10-10 21:07:38,547][98559] Updated weights for policy 0, policy_version 10610 (0.0008) -[2023-10-10 21:07:38,638][98560] Updated weights for policy 1, policy_version 10652 (0.0008) -[2023-10-10 21:07:38,905][98559] Updated weights for policy 0, policy_version 10620 (0.0009) -[2023-10-10 21:07:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 21790720. Throughput: 0: 1698.2, 1: 1707.5. Samples: 5450544. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-10 21:07:40,557][97672] Avg episode reward: [(0, '-6.560'), (1, '6.600')] -[2023-10-10 21:07:42,644][98560] Updated weights for policy 1, policy_version 10662 (0.0008) -[2023-10-10 21:07:42,929][98559] Updated weights for policy 0, policy_version 10630 (0.0008) -[2023-10-10 21:07:43,014][98560] Updated weights for policy 1, policy_version 10672 (0.0008) -[2023-10-10 21:07:43,293][98559] Updated weights for policy 0, policy_version 10640 (0.0007) -[2023-10-10 21:07:43,385][98560] Updated weights for policy 1, policy_version 10682 (0.0007) -[2023-10-10 21:07:43,666][98559] Updated weights for policy 0, policy_version 10650 (0.0008) -[2023-10-10 21:07:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 21856256. Throughput: 0: 1681.5, 1: 1679.0. Samples: 5469622. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-10 21:07:45,557][97672] Avg episode reward: [(0, '-6.560'), (1, '7.140')] -[2023-10-10 21:07:45,558][98439] Saving new best policy, reward=7.140! -[2023-10-10 21:07:47,363][98560] Updated weights for policy 1, policy_version 10692 (0.0008) -[2023-10-10 21:07:47,537][98559] Updated weights for policy 0, policy_version 10660 (0.0008) -[2023-10-10 21:07:47,756][98560] Updated weights for policy 1, policy_version 10702 (0.0008) -[2023-10-10 21:07:47,912][98559] Updated weights for policy 0, policy_version 10670 (0.0009) -[2023-10-10 21:07:48,120][98560] Updated weights for policy 1, policy_version 10712 (0.0008) -[2023-10-10 21:07:48,280][98559] Updated weights for policy 0, policy_version 10680 (0.0009) -[2023-10-10 21:07:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 21921792. Throughput: 0: 1707.9, 1: 1702.0. Samples: 5490608. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-10 21:07:50,557][97672] Avg episode reward: [(0, '-6.560'), (1, '7.380')] -[2023-10-10 21:07:50,570][98439] Saving new best policy, reward=7.380! -[2023-10-10 21:07:52,119][98560] Updated weights for policy 1, policy_version 10722 (0.0007) -[2023-10-10 21:07:52,141][98559] Updated weights for policy 0, policy_version 10690 (0.0009) -[2023-10-10 21:07:52,490][98560] Updated weights for policy 1, policy_version 10732 (0.0008) -[2023-10-10 21:07:52,507][98559] Updated weights for policy 0, policy_version 10700 (0.0009) -[2023-10-10 21:07:52,857][98560] Updated weights for policy 1, policy_version 10742 (0.0008) -[2023-10-10 21:07:52,878][98559] Updated weights for policy 0, policy_version 10710 (0.0008) -[2023-10-10 21:07:53,223][98560] Updated weights for policy 1, policy_version 10752 (0.0010) -[2023-10-10 21:07:53,248][98559] Updated weights for policy 0, policy_version 10720 (0.0009) -[2023-10-10 21:07:55,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 21987328. Throughput: 0: 1674.5, 1: 1701.7. Samples: 5500536. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-10 21:07:55,557][97672] Avg episode reward: [(0, '-6.560'), (1, '7.580')] -[2023-10-10 21:07:55,558][98439] Saving new best policy, reward=7.580! -[2023-10-10 21:07:57,166][98560] Updated weights for policy 1, policy_version 10762 (0.0008) -[2023-10-10 21:07:57,370][98559] Updated weights for policy 0, policy_version 10730 (0.0007) -[2023-10-10 21:07:57,530][98560] Updated weights for policy 1, policy_version 10772 (0.0008) -[2023-10-10 21:07:57,743][98559] Updated weights for policy 0, policy_version 10740 (0.0008) -[2023-10-10 21:07:57,902][98560] Updated weights for policy 1, policy_version 10782 (0.0009) -[2023-10-10 21:07:58,113][98559] Updated weights for policy 0, policy_version 10750 (0.0008) -[2023-10-10 21:08:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 22052864. Throughput: 0: 1695.2, 1: 1695.0. Samples: 5521180. Policy #0 lag: (min: 2.0, avg: 2.5, max: 17.0) -[2023-10-10 21:08:00,557][97672] Avg episode reward: [(0, '-6.560'), (1, '7.760')] -[2023-10-10 21:08:00,559][98439] Saving new best policy, reward=7.760! -[2023-10-10 21:08:01,935][98560] Updated weights for policy 1, policy_version 10792 (0.0008) -[2023-10-10 21:08:02,096][98559] Updated weights for policy 0, policy_version 10760 (0.0008) -[2023-10-10 21:08:02,300][98560] Updated weights for policy 1, policy_version 10802 (0.0008) -[2023-10-10 21:08:02,466][98559] Updated weights for policy 0, policy_version 10770 (0.0007) -[2023-10-10 21:08:02,670][98560] Updated weights for policy 1, policy_version 10812 (0.0009) -[2023-10-10 21:08:02,840][98559] Updated weights for policy 0, policy_version 10780 (0.0009) -[2023-10-10 21:08:05,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 22118400. Throughput: 0: 1698.1, 1: 1713.8. Samples: 5541792. Policy #0 lag: (min: 2.0, avg: 2.5, max: 17.0) -[2023-10-10 21:08:05,558][97672] Avg episode reward: [(0, '-6.520'), (1, '7.780')] -[2023-10-10 21:08:05,571][98385] Saving new best policy, reward=-6.520! -[2023-10-10 21:08:05,571][98439] Saving new best policy, reward=7.780! -[2023-10-10 21:08:06,558][98560] Updated weights for policy 1, policy_version 10822 (0.0007) -[2023-10-10 21:08:06,819][98559] Updated weights for policy 0, policy_version 10790 (0.0009) -[2023-10-10 21:08:06,926][98560] Updated weights for policy 1, policy_version 10832 (0.0009) -[2023-10-10 21:08:07,197][98559] Updated weights for policy 0, policy_version 10800 (0.0007) -[2023-10-10 21:08:07,285][98560] Updated weights for policy 1, policy_version 10842 (0.0008) -[2023-10-10 21:08:07,566][98559] Updated weights for policy 0, policy_version 10810 (0.0009) -[2023-10-10 21:08:10,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 22183936. Throughput: 0: 1677.2, 1: 1688.0. Samples: 5551326. Policy #0 lag: (min: 29.0, avg: 36.3, max: 61.0) -[2023-10-10 21:08:10,556][97672] Avg episode reward: [(0, '-6.420'), (1, '7.840')] -[2023-10-10 21:08:10,557][98385] Saving new best policy, reward=-6.420! -[2023-10-10 21:08:10,557][98439] Saving new best policy, reward=7.840! -[2023-10-10 21:08:11,426][98560] Updated weights for policy 1, policy_version 10852 (0.0008) -[2023-10-10 21:08:11,690][98559] Updated weights for policy 0, policy_version 10820 (0.0010) -[2023-10-10 21:08:11,791][98560] Updated weights for policy 1, policy_version 10862 (0.0007) -[2023-10-10 21:08:12,061][98559] Updated weights for policy 0, policy_version 10830 (0.0009) -[2023-10-10 21:08:12,162][98560] Updated weights for policy 1, policy_version 10872 (0.0007) -[2023-10-10 21:08:12,425][98559] Updated weights for policy 0, policy_version 10840 (0.0009) -[2023-10-10 21:08:15,556][97672] Fps is (10 sec: 13107.8, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 22249472. Throughput: 0: 1704.7, 1: 1700.2. Samples: 5572222. Policy #0 lag: (min: 29.0, avg: 36.3, max: 61.0) -[2023-10-10 21:08:15,556][97672] Avg episode reward: [(0, '-6.420'), (1, '8.100')] -[2023-10-10 21:08:15,557][98439] Saving new best policy, reward=8.100! -[2023-10-10 21:08:16,142][98560] Updated weights for policy 1, policy_version 10882 (0.0008) -[2023-10-10 21:08:16,513][98560] Updated weights for policy 1, policy_version 10892 (0.0009) -[2023-10-10 21:08:16,606][98559] Updated weights for policy 0, policy_version 10850 (0.0008) -[2023-10-10 21:08:16,889][98560] Updated weights for policy 1, policy_version 10902 (0.0007) -[2023-10-10 21:08:17,002][98559] Updated weights for policy 0, policy_version 10860 (0.0008) -[2023-10-10 21:08:17,254][98560] Updated weights for policy 1, policy_version 10912 (0.0008) -[2023-10-10 21:08:17,376][98559] Updated weights for policy 0, policy_version 10870 (0.0008) -[2023-10-10 21:08:17,755][98559] Updated weights for policy 0, policy_version 10880 (0.0009) -[2023-10-10 21:08:20,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 22315008. Throughput: 0: 1704.3, 1: 1712.4. Samples: 5593048. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-10 21:08:20,557][97672] Avg episode reward: [(0, '-6.420'), (1, '8.320')] -[2023-10-10 21:08:20,564][98439] Saving new best policy, reward=8.320! -[2023-10-10 21:08:21,261][98560] Updated weights for policy 1, policy_version 10922 (0.0007) -[2023-10-10 21:08:21,629][98560] Updated weights for policy 1, policy_version 10932 (0.0007) -[2023-10-10 21:08:21,751][98559] Updated weights for policy 0, policy_version 10890 (0.0008) -[2023-10-10 21:08:21,996][98560] Updated weights for policy 1, policy_version 10942 (0.0008) -[2023-10-10 21:08:22,124][98559] Updated weights for policy 0, policy_version 10900 (0.0010) -[2023-10-10 21:08:22,488][98559] Updated weights for policy 0, policy_version 10910 (0.0009) -[2023-10-10 21:08:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 22380544. Throughput: 0: 1684.6, 1: 1689.3. Samples: 5602368. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-10 21:08:25,556][97672] Avg episode reward: [(0, '-6.460'), (1, '8.420')] -[2023-10-10 21:08:25,557][98439] Saving new best policy, reward=8.420! -[2023-10-10 21:08:26,123][98560] Updated weights for policy 1, policy_version 10952 (0.0007) -[2023-10-10 21:08:26,484][98560] Updated weights for policy 1, policy_version 10962 (0.0008) -[2023-10-10 21:08:26,663][98559] Updated weights for policy 0, policy_version 10920 (0.0007) -[2023-10-10 21:08:26,848][98560] Updated weights for policy 1, policy_version 10972 (0.0008) -[2023-10-10 21:08:27,039][98559] Updated weights for policy 0, policy_version 10930 (0.0009) -[2023-10-10 21:08:27,411][98559] Updated weights for policy 0, policy_version 10940 (0.0009) -[2023-10-10 21:08:30,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 22446080. Throughput: 0: 1697.1, 1: 1712.9. Samples: 5623070. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-10 21:08:30,556][97672] Avg episode reward: [(0, '-6.240'), (1, '8.560')] -[2023-10-10 21:08:30,557][98385] Saving new best policy, reward=-6.240! -[2023-10-10 21:08:30,810][98560] Updated weights for policy 1, policy_version 10982 (0.0008) -[2023-10-10 21:08:31,180][98560] Updated weights for policy 1, policy_version 10992 (0.0010) -[2023-10-10 21:08:31,446][98559] Updated weights for policy 0, policy_version 10950 (0.0009) -[2023-10-10 21:08:31,543][98560] Updated weights for policy 1, policy_version 11002 (0.0009) -[2023-10-10 21:08:31,764][98439] Saving new best policy, reward=8.560! -[2023-10-10 21:08:31,811][98559] Updated weights for policy 0, policy_version 10960 (0.0009) -[2023-10-10 21:08:32,186][98559] Updated weights for policy 0, policy_version 10970 (0.0008) -[2023-10-10 21:08:35,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 22511616. Throughput: 0: 1695.1, 1: 1712.8. Samples: 5643960. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-10 21:08:35,557][97672] Avg episode reward: [(0, '-6.240'), (1, '8.660')] -[2023-10-10 21:08:35,572][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000010976_11239424.pth... -[2023-10-10 21:08:35,605][98560] Updated weights for policy 1, policy_version 11012 (0.0007) -[2023-10-10 21:08:35,607][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000009408_9633792.pth -[2023-10-10 21:08:35,979][98560] Updated weights for policy 1, policy_version 11022 (0.0008) -[2023-10-10 21:08:36,186][98559] Updated weights for policy 0, policy_version 10980 (0.0007) -[2023-10-10 21:08:36,344][98560] Updated weights for policy 1, policy_version 11032 (0.0007) -[2023-10-10 21:08:36,557][98559] Updated weights for policy 0, policy_version 10990 (0.0008) -[2023-10-10 21:08:36,635][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000011040_11304960.pth... -[2023-10-10 21:08:36,667][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000009440_9666560.pth -[2023-10-10 21:08:36,670][98439] Saving new best policy, reward=8.660! -[2023-10-10 21:08:36,938][98559] Updated weights for policy 0, policy_version 11000 (0.0009) -[2023-10-10 21:08:40,338][98560] Updated weights for policy 1, policy_version 11042 (0.0008) -[2023-10-10 21:08:40,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 22577152. Throughput: 0: 1695.6, 1: 1698.3. Samples: 5653264. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:08:40,557][97672] Avg episode reward: [(0, '-6.240'), (1, '8.540')] -[2023-10-10 21:08:40,701][98560] Updated weights for policy 1, policy_version 11052 (0.0007) -[2023-10-10 21:08:40,889][98559] Updated weights for policy 0, policy_version 11010 (0.0009) -[2023-10-10 21:08:41,073][98560] Updated weights for policy 1, policy_version 11062 (0.0008) -[2023-10-10 21:08:41,254][98559] Updated weights for policy 0, policy_version 11020 (0.0008) -[2023-10-10 21:08:41,438][98560] Updated weights for policy 1, policy_version 11072 (0.0010) -[2023-10-10 21:08:41,631][98559] Updated weights for policy 0, policy_version 11030 (0.0008) -[2023-10-10 21:08:41,995][98559] Updated weights for policy 0, policy_version 11040 (0.0009) -[2023-10-10 21:08:45,378][98560] Updated weights for policy 1, policy_version 11082 (0.0008) -[2023-10-10 21:08:45,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 22642688. Throughput: 0: 1691.7, 1: 1706.2. Samples: 5674088. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:08:45,557][97672] Avg episode reward: [(0, '-6.240'), (1, '8.880')] -[2023-10-10 21:08:45,738][98560] Updated weights for policy 1, policy_version 11092 (0.0008) -[2023-10-10 21:08:45,989][98559] Updated weights for policy 0, policy_version 11050 (0.0008) -[2023-10-10 21:08:46,106][98560] Updated weights for policy 1, policy_version 11102 (0.0008) -[2023-10-10 21:08:46,177][98439] Saving new best policy, reward=8.880! -[2023-10-10 21:08:46,367][98559] Updated weights for policy 0, policy_version 11060 (0.0008) -[2023-10-10 21:08:46,737][98559] Updated weights for policy 0, policy_version 11070 (0.0008) -[2023-10-10 21:08:50,105][98560] Updated weights for policy 1, policy_version 11112 (0.0008) -[2023-10-10 21:08:50,477][98560] Updated weights for policy 1, policy_version 11122 (0.0008) -[2023-10-10 21:08:50,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 22708224. Throughput: 0: 1694.6, 1: 1713.8. Samples: 5695170. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:08:50,557][97672] Avg episode reward: [(0, '-6.240'), (1, '9.260')] -[2023-10-10 21:08:50,789][98559] Updated weights for policy 0, policy_version 11080 (0.0009) -[2023-10-10 21:08:50,846][98560] Updated weights for policy 1, policy_version 11132 (0.0008) -[2023-10-10 21:08:50,996][98439] Saving new best policy, reward=9.260! -[2023-10-10 21:08:51,159][98559] Updated weights for policy 0, policy_version 11090 (0.0009) -[2023-10-10 21:08:51,538][98559] Updated weights for policy 0, policy_version 11100 (0.0009) -[2023-10-10 21:08:54,856][98560] Updated weights for policy 1, policy_version 11142 (0.0009) -[2023-10-10 21:08:55,227][98560] Updated weights for policy 1, policy_version 11152 (0.0007) -[2023-10-10 21:08:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 22773760. Throughput: 0: 1691.4, 1: 1707.2. Samples: 5704260. Policy #0 lag: (min: 0.0, avg: 21.6, max: 32.0) -[2023-10-10 21:08:55,557][97672] Avg episode reward: [(0, '-6.220'), (1, '9.260')] -[2023-10-10 21:08:55,597][98560] Updated weights for policy 1, policy_version 11162 (0.0008) -[2023-10-10 21:08:55,619][98559] Updated weights for policy 0, policy_version 11110 (0.0008) -[2023-10-10 21:08:55,986][98559] Updated weights for policy 0, policy_version 11120 (0.0008) -[2023-10-10 21:08:56,356][98559] Updated weights for policy 0, policy_version 11130 (0.0010) -[2023-10-10 21:08:56,575][98385] Saving new best policy, reward=-6.220! -[2023-10-10 21:08:59,676][98560] Updated weights for policy 1, policy_version 11172 (0.0010) -[2023-10-10 21:09:00,046][98560] Updated weights for policy 1, policy_version 11182 (0.0009) -[2023-10-10 21:09:00,367][98559] Updated weights for policy 0, policy_version 11140 (0.0008) -[2023-10-10 21:09:00,415][98560] Updated weights for policy 1, policy_version 11192 (0.0007) -[2023-10-10 21:09:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 22839296. Throughput: 0: 1690.7, 1: 1707.4. Samples: 5725136. Policy #0 lag: (min: 0.0, avg: 21.6, max: 32.0) -[2023-10-10 21:09:00,557][97672] Avg episode reward: [(0, '-6.220'), (1, '9.200')] -[2023-10-10 21:09:00,737][98559] Updated weights for policy 0, policy_version 11150 (0.0009) -[2023-10-10 21:09:01,110][98559] Updated weights for policy 0, policy_version 11160 (0.0011) -[2023-10-10 21:09:04,326][98560] Updated weights for policy 1, policy_version 11202 (0.0007) -[2023-10-10 21:09:04,697][98560] Updated weights for policy 1, policy_version 11212 (0.0008) -[2023-10-10 21:09:05,075][98560] Updated weights for policy 1, policy_version 11222 (0.0007) -[2023-10-10 21:09:05,133][98559] Updated weights for policy 0, policy_version 11170 (0.0009) -[2023-10-10 21:09:05,433][98560] Updated weights for policy 1, policy_version 11232 (0.0009) -[2023-10-10 21:09:05,518][98559] Updated weights for policy 0, policy_version 11180 (0.0009) -[2023-10-10 21:09:05,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 22937600. Throughput: 0: 1683.8, 1: 1701.2. Samples: 5745370. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 21:09:05,556][97672] Avg episode reward: [(0, '-6.220'), (1, '9.240')] -[2023-10-10 21:09:05,878][98559] Updated weights for policy 0, policy_version 11190 (0.0009) -[2023-10-10 21:09:06,255][98559] Updated weights for policy 0, policy_version 11200 (0.0010) -[2023-10-10 21:09:09,530][98560] Updated weights for policy 1, policy_version 11242 (0.0008) -[2023-10-10 21:09:09,902][98560] Updated weights for policy 1, policy_version 11252 (0.0007) -[2023-10-10 21:09:10,271][98560] Updated weights for policy 1, policy_version 11262 (0.0008) -[2023-10-10 21:09:10,405][98559] Updated weights for policy 0, policy_version 11210 (0.0008) -[2023-10-10 21:09:10,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 23003136. Throughput: 0: 1689.3, 1: 1708.0. Samples: 5755244. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 21:09:10,556][97672] Avg episode reward: [(0, '-6.220'), (1, '9.300')] -[2023-10-10 21:09:10,557][98439] Saving new best policy, reward=9.300! -[2023-10-10 21:09:10,769][98559] Updated weights for policy 0, policy_version 11220 (0.0009) -[2023-10-10 21:09:11,143][98559] Updated weights for policy 0, policy_version 11230 (0.0007) -[2023-10-10 21:09:14,326][98560] Updated weights for policy 1, policy_version 11272 (0.0008) -[2023-10-10 21:09:14,705][98560] Updated weights for policy 1, policy_version 11282 (0.0010) -[2023-10-10 21:09:14,928][98559] Updated weights for policy 0, policy_version 11240 (0.0007) -[2023-10-10 21:09:15,067][98560] Updated weights for policy 1, policy_version 11292 (0.0007) -[2023-10-10 21:09:15,304][98559] Updated weights for policy 0, policy_version 11250 (0.0008) -[2023-10-10 21:09:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 23068672. Throughput: 0: 1698.6, 1: 1706.4. Samples: 5776296. Policy #0 lag: (min: 17.0, avg: 18.8, max: 43.0) -[2023-10-10 21:09:15,557][97672] Avg episode reward: [(0, '-6.180'), (1, '9.660')] -[2023-10-10 21:09:15,557][98439] Saving new best policy, reward=9.660! -[2023-10-10 21:09:15,678][98559] Updated weights for policy 0, policy_version 11260 (0.0010) -[2023-10-10 21:09:15,823][98385] Saving new best policy, reward=-6.180! -[2023-10-10 21:09:19,060][98560] Updated weights for policy 1, policy_version 11302 (0.0007) -[2023-10-10 21:09:19,431][98560] Updated weights for policy 1, policy_version 11312 (0.0009) -[2023-10-10 21:09:19,670][98559] Updated weights for policy 0, policy_version 11270 (0.0009) -[2023-10-10 21:09:19,802][98560] Updated weights for policy 1, policy_version 11322 (0.0007) -[2023-10-10 21:09:20,046][98559] Updated weights for policy 0, policy_version 11280 (0.0008) -[2023-10-10 21:09:20,423][98559] Updated weights for policy 0, policy_version 11290 (0.0007) -[2023-10-10 21:09:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 23134208. Throughput: 0: 1679.7, 1: 1691.8. Samples: 5795680. Policy #0 lag: (min: 17.0, avg: 18.8, max: 43.0) -[2023-10-10 21:09:20,557][97672] Avg episode reward: [(0, '-6.180'), (1, '9.900')] -[2023-10-10 21:09:20,565][98439] Saving new best policy, reward=9.900! -[2023-10-10 21:09:23,693][98560] Updated weights for policy 1, policy_version 11332 (0.0008) -[2023-10-10 21:09:24,068][98560] Updated weights for policy 1, policy_version 11342 (0.0011) -[2023-10-10 21:09:24,338][98559] Updated weights for policy 0, policy_version 11300 (0.0007) -[2023-10-10 21:09:24,447][98560] Updated weights for policy 1, policy_version 11352 (0.0010) -[2023-10-10 21:09:24,701][98559] Updated weights for policy 0, policy_version 11310 (0.0008) -[2023-10-10 21:09:25,082][98559] Updated weights for policy 0, policy_version 11320 (0.0008) -[2023-10-10 21:09:25,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 23232512. Throughput: 0: 1701.9, 1: 1712.0. Samples: 5806888. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:09:25,556][97672] Avg episode reward: [(0, '-6.180'), (1, '9.880')] -[2023-10-10 21:09:28,617][98560] Updated weights for policy 1, policy_version 11362 (0.0008) -[2023-10-10 21:09:28,989][98560] Updated weights for policy 1, policy_version 11372 (0.0008) -[2023-10-10 21:09:29,040][98559] Updated weights for policy 0, policy_version 11330 (0.0010) -[2023-10-10 21:09:29,355][98560] Updated weights for policy 1, policy_version 11382 (0.0008) -[2023-10-10 21:09:29,409][98559] Updated weights for policy 0, policy_version 11340 (0.0009) -[2023-10-10 21:09:29,730][98560] Updated weights for policy 1, policy_version 11392 (0.0008) -[2023-10-10 21:09:29,774][98559] Updated weights for policy 0, policy_version 11350 (0.0010) -[2023-10-10 21:09:30,147][98559] Updated weights for policy 0, policy_version 11360 (0.0008) -[2023-10-10 21:09:30,556][97672] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 23298048. Throughput: 0: 1695.8, 1: 1704.9. Samples: 5827120. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:09:30,557][97672] Avg episode reward: [(0, '-6.080'), (1, '9.760')] -[2023-10-10 21:09:30,557][98385] Saving new best policy, reward=-6.080! -[2023-10-10 21:09:33,529][98560] Updated weights for policy 1, policy_version 11402 (0.0010) -[2023-10-10 21:09:33,898][98560] Updated weights for policy 1, policy_version 11412 (0.0011) -[2023-10-10 21:09:34,262][98559] Updated weights for policy 0, policy_version 11370 (0.0008) -[2023-10-10 21:09:34,269][98560] Updated weights for policy 1, policy_version 11422 (0.0011) -[2023-10-10 21:09:34,642][98559] Updated weights for policy 0, policy_version 11380 (0.0009) -[2023-10-10 21:09:35,005][98559] Updated weights for policy 0, policy_version 11390 (0.0009) -[2023-10-10 21:09:35,556][97672] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 23363584. Throughput: 0: 1676.9, 1: 1676.3. Samples: 5846068. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:09:35,557][97672] Avg episode reward: [(0, '-6.080'), (1, '9.600')] -[2023-10-10 21:09:38,399][98560] Updated weights for policy 1, policy_version 11432 (0.0008) -[2023-10-10 21:09:38,775][98560] Updated weights for policy 1, policy_version 11442 (0.0010) -[2023-10-10 21:09:38,920][98559] Updated weights for policy 0, policy_version 11400 (0.0008) -[2023-10-10 21:09:39,144][98560] Updated weights for policy 1, policy_version 11452 (0.0009) -[2023-10-10 21:09:39,288][98559] Updated weights for policy 0, policy_version 11410 (0.0009) -[2023-10-10 21:09:39,660][98559] Updated weights for policy 0, policy_version 11420 (0.0008) -[2023-10-10 21:09:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 23429120. Throughput: 0: 1709.5, 1: 1703.4. Samples: 5857840. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:09:40,557][97672] Avg episode reward: [(0, '-6.000'), (1, '9.560')] -[2023-10-10 21:09:40,557][98385] Saving new best policy, reward=-6.000! -[2023-10-10 21:09:43,175][98560] Updated weights for policy 1, policy_version 11462 (0.0011) -[2023-10-10 21:09:43,537][98560] Updated weights for policy 1, policy_version 11472 (0.0008) -[2023-10-10 21:09:43,597][98559] Updated weights for policy 0, policy_version 11430 (0.0007) -[2023-10-10 21:09:43,905][98560] Updated weights for policy 1, policy_version 11482 (0.0007) -[2023-10-10 21:09:43,966][98559] Updated weights for policy 0, policy_version 11440 (0.0007) -[2023-10-10 21:09:44,337][98559] Updated weights for policy 0, policy_version 11450 (0.0008) -[2023-10-10 21:09:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 23494656. Throughput: 0: 1693.3, 1: 1685.9. Samples: 5877198. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:09:45,557][97672] Avg episode reward: [(0, '-5.920'), (1, '9.680')] -[2023-10-10 21:09:45,558][98385] Saving new best policy, reward=-5.920! -[2023-10-10 21:09:47,818][98560] Updated weights for policy 1, policy_version 11492 (0.0009) -[2023-10-10 21:09:48,185][98560] Updated weights for policy 1, policy_version 11502 (0.0009) -[2023-10-10 21:09:48,278][98559] Updated weights for policy 0, policy_version 11460 (0.0009) -[2023-10-10 21:09:48,561][98560] Updated weights for policy 1, policy_version 11512 (0.0008) -[2023-10-10 21:09:48,643][98559] Updated weights for policy 0, policy_version 11470 (0.0007) -[2023-10-10 21:09:49,011][98559] Updated weights for policy 0, policy_version 11480 (0.0007) -[2023-10-10 21:09:50,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 23560192. Throughput: 0: 1698.5, 1: 1683.2. Samples: 5897546. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:09:50,556][97672] Avg episode reward: [(0, '-5.920'), (1, '9.780')] -[2023-10-10 21:09:52,697][98560] Updated weights for policy 1, policy_version 11522 (0.0008) -[2023-10-10 21:09:53,056][98560] Updated weights for policy 1, policy_version 11532 (0.0009) -[2023-10-10 21:09:53,099][98559] Updated weights for policy 0, policy_version 11490 (0.0007) -[2023-10-10 21:09:53,440][98560] Updated weights for policy 1, policy_version 11542 (0.0008) -[2023-10-10 21:09:53,493][98559] Updated weights for policy 0, policy_version 11500 (0.0007) -[2023-10-10 21:09:53,810][98560] Updated weights for policy 1, policy_version 11552 (0.0008) -[2023-10-10 21:09:53,862][98559] Updated weights for policy 0, policy_version 11510 (0.0009) -[2023-10-10 21:09:54,240][98559] Updated weights for policy 0, policy_version 11520 (0.0008) -[2023-10-10 21:09:55,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 23625728. Throughput: 0: 1720.3, 1: 1696.5. Samples: 5909000. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:09:55,556][97672] Avg episode reward: [(0, '-5.920'), (1, '9.920')] -[2023-10-10 21:09:55,557][98439] Saving new best policy, reward=9.920! -[2023-10-10 21:09:57,835][98560] Updated weights for policy 1, policy_version 11562 (0.0007) -[2023-10-10 21:09:58,192][98560] Updated weights for policy 1, policy_version 11572 (0.0009) -[2023-10-10 21:09:58,304][98559] Updated weights for policy 0, policy_version 11530 (0.0010) -[2023-10-10 21:09:58,567][98560] Updated weights for policy 1, policy_version 11582 (0.0009) -[2023-10-10 21:09:58,680][98559] Updated weights for policy 0, policy_version 11540 (0.0008) -[2023-10-10 21:09:59,059][98559] Updated weights for policy 0, policy_version 11550 (0.0010) -[2023-10-10 21:10:00,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 23691264. Throughput: 0: 1691.5, 1: 1671.5. Samples: 5927628. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:10:00,557][97672] Avg episode reward: [(0, '-5.820'), (1, '9.980')] -[2023-10-10 21:10:00,558][98385] Saving new best policy, reward=-5.820! -[2023-10-10 21:10:00,558][98439] Saving new best policy, reward=9.980! -[2023-10-10 21:10:02,503][98560] Updated weights for policy 1, policy_version 11592 (0.0010) -[2023-10-10 21:10:02,870][98560] Updated weights for policy 1, policy_version 11602 (0.0010) -[2023-10-10 21:10:03,098][98559] Updated weights for policy 0, policy_version 11560 (0.0009) -[2023-10-10 21:10:03,239][98560] Updated weights for policy 1, policy_version 11612 (0.0009) -[2023-10-10 21:10:03,468][98559] Updated weights for policy 0, policy_version 11570 (0.0008) -[2023-10-10 21:10:03,840][98559] Updated weights for policy 0, policy_version 11580 (0.0009) -[2023-10-10 21:10:05,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 23756800. Throughput: 0: 1708.2, 1: 1690.7. Samples: 5948628. Policy #0 lag: (min: 31.0, avg: 31.4, max: 46.0) -[2023-10-10 21:10:05,557][97672] Avg episode reward: [(0, '-5.820'), (1, '10.460')] -[2023-10-10 21:10:05,566][98439] Saving new best policy, reward=10.460! -[2023-10-10 21:10:07,395][98560] Updated weights for policy 1, policy_version 11622 (0.0009) -[2023-10-10 21:10:07,772][98560] Updated weights for policy 1, policy_version 11632 (0.0008) -[2023-10-10 21:10:07,861][98559] Updated weights for policy 0, policy_version 11590 (0.0008) -[2023-10-10 21:10:08,137][98560] Updated weights for policy 1, policy_version 11642 (0.0008) -[2023-10-10 21:10:08,226][98559] Updated weights for policy 0, policy_version 11600 (0.0009) -[2023-10-10 21:10:08,607][98559] Updated weights for policy 0, policy_version 11610 (0.0009) -[2023-10-10 21:10:10,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 23822336. Throughput: 0: 1699.7, 1: 1685.1. Samples: 5959206. Policy #0 lag: (min: 31.0, avg: 31.4, max: 46.0) -[2023-10-10 21:10:10,557][97672] Avg episode reward: [(0, '-5.820'), (1, '10.380')] -[2023-10-10 21:10:12,214][98560] Updated weights for policy 1, policy_version 11652 (0.0009) -[2023-10-10 21:10:12,585][98560] Updated weights for policy 1, policy_version 11662 (0.0008) -[2023-10-10 21:10:12,680][98559] Updated weights for policy 0, policy_version 11620 (0.0009) -[2023-10-10 21:10:12,952][98560] Updated weights for policy 1, policy_version 11672 (0.0008) -[2023-10-10 21:10:13,041][98559] Updated weights for policy 0, policy_version 11630 (0.0009) -[2023-10-10 21:10:13,417][98559] Updated weights for policy 0, policy_version 11640 (0.0009) -[2023-10-10 21:10:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 23887872. Throughput: 0: 1697.4, 1: 1675.2. Samples: 5978890. Policy #0 lag: (min: 31.0, avg: 31.4, max: 46.0) -[2023-10-10 21:10:15,556][97672] Avg episode reward: [(0, '-5.820'), (1, '10.640')] -[2023-10-10 21:10:15,557][98439] Saving new best policy, reward=10.640! -[2023-10-10 21:10:16,933][98560] Updated weights for policy 1, policy_version 11682 (0.0009) -[2023-10-10 21:10:17,291][98559] Updated weights for policy 0, policy_version 11650 (0.0010) -[2023-10-10 21:10:17,304][98560] Updated weights for policy 1, policy_version 11692 (0.0010) -[2023-10-10 21:10:17,664][98559] Updated weights for policy 0, policy_version 11660 (0.0009) -[2023-10-10 21:10:17,667][98560] Updated weights for policy 1, policy_version 11702 (0.0007) -[2023-10-10 21:10:18,032][98559] Updated weights for policy 0, policy_version 11670 (0.0009) -[2023-10-10 21:10:18,039][98560] Updated weights for policy 1, policy_version 11712 (0.0008) -[2023-10-10 21:10:18,414][98559] Updated weights for policy 0, policy_version 11680 (0.0010) -[2023-10-10 21:10:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 23953408. Throughput: 0: 1714.4, 1: 1705.4. Samples: 5999956. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:10:20,557][97672] Avg episode reward: [(0, '-5.820'), (1, '11.020')] -[2023-10-10 21:10:20,566][98439] Saving new best policy, reward=11.020! -[2023-10-10 21:10:21,809][98560] Updated weights for policy 1, policy_version 11722 (0.0007) -[2023-10-10 21:10:22,173][98560] Updated weights for policy 1, policy_version 11732 (0.0007) -[2023-10-10 21:10:22,496][98559] Updated weights for policy 0, policy_version 11690 (0.0007) -[2023-10-10 21:10:22,530][98560] Updated weights for policy 1, policy_version 11742 (0.0008) -[2023-10-10 21:10:22,867][98559] Updated weights for policy 0, policy_version 11700 (0.0008) -[2023-10-10 21:10:23,230][98559] Updated weights for policy 0, policy_version 11710 (0.0009) -[2023-10-10 21:10:25,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 24018944. Throughput: 0: 1681.1, 1: 1683.4. Samples: 6009242. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:10:25,557][97672] Avg episode reward: [(0, '-5.820'), (1, '11.080')] -[2023-10-10 21:10:25,558][98439] Saving new best policy, reward=11.080! -[2023-10-10 21:10:26,547][98560] Updated weights for policy 1, policy_version 11752 (0.0009) -[2023-10-10 21:10:26,912][98560] Updated weights for policy 1, policy_version 11762 (0.0008) -[2023-10-10 21:10:27,164][98559] Updated weights for policy 0, policy_version 11720 (0.0008) -[2023-10-10 21:10:27,281][98560] Updated weights for policy 1, policy_version 11772 (0.0008) -[2023-10-10 21:10:27,533][98559] Updated weights for policy 0, policy_version 11730 (0.0008) -[2023-10-10 21:10:27,913][98559] Updated weights for policy 0, policy_version 11740 (0.0008) -[2023-10-10 21:10:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 24084480. Throughput: 0: 1705.2, 1: 1700.6. Samples: 6030458. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:10:30,557][97672] Avg episode reward: [(0, '-5.700'), (1, '11.220')] -[2023-10-10 21:10:30,558][98385] Saving new best policy, reward=-5.700! -[2023-10-10 21:10:30,558][98439] Saving new best policy, reward=11.220! -[2023-10-10 21:10:31,276][98560] Updated weights for policy 1, policy_version 11782 (0.0008) -[2023-10-10 21:10:31,638][98560] Updated weights for policy 1, policy_version 11792 (0.0008) -[2023-10-10 21:10:31,902][98559] Updated weights for policy 0, policy_version 11750 (0.0008) -[2023-10-10 21:10:32,011][98560] Updated weights for policy 1, policy_version 11802 (0.0008) -[2023-10-10 21:10:32,271][98559] Updated weights for policy 0, policy_version 11760 (0.0007) -[2023-10-10 21:10:32,642][98559] Updated weights for policy 0, policy_version 11770 (0.0007) -[2023-10-10 21:10:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 24150016. Throughput: 0: 1711.4, 1: 1713.2. Samples: 6051654. Policy #0 lag: (min: 9.0, avg: 15.9, max: 41.0) -[2023-10-10 21:10:35,557][97672] Avg episode reward: [(0, '-5.700'), (1, '11.260')] -[2023-10-10 21:10:35,570][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000011808_12091392.pth... -[2023-10-10 21:10:35,570][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000011776_12058624.pth... -[2023-10-10 21:10:35,610][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000010240_10485760.pth -[2023-10-10 21:10:35,611][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000010208_10452992.pth -[2023-10-10 21:10:35,614][98439] Saving new best policy, reward=11.260! -[2023-10-10 21:10:35,992][98560] Updated weights for policy 1, policy_version 11812 (0.0007) -[2023-10-10 21:10:36,361][98560] Updated weights for policy 1, policy_version 11822 (0.0009) -[2023-10-10 21:10:36,600][98559] Updated weights for policy 0, policy_version 11780 (0.0007) -[2023-10-10 21:10:36,731][98560] Updated weights for policy 1, policy_version 11832 (0.0008) -[2023-10-10 21:10:36,968][98559] Updated weights for policy 0, policy_version 11790 (0.0008) -[2023-10-10 21:10:37,329][98559] Updated weights for policy 0, policy_version 11800 (0.0009) -[2023-10-10 21:10:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 24215552. Throughput: 0: 1685.7, 1: 1691.5. Samples: 6060974. Policy #0 lag: (min: 9.0, avg: 15.9, max: 41.0) -[2023-10-10 21:10:40,557][97672] Avg episode reward: [(0, '-5.700'), (1, '11.340')] -[2023-10-10 21:10:40,557][98439] Saving new best policy, reward=11.340! -[2023-10-10 21:10:40,792][98560] Updated weights for policy 1, policy_version 11842 (0.0007) -[2023-10-10 21:10:41,167][98560] Updated weights for policy 1, policy_version 11852 (0.0007) -[2023-10-10 21:10:41,392][98559] Updated weights for policy 0, policy_version 11810 (0.0009) -[2023-10-10 21:10:41,539][98560] Updated weights for policy 1, policy_version 11862 (0.0007) -[2023-10-10 21:10:41,766][98559] Updated weights for policy 0, policy_version 11820 (0.0007) -[2023-10-10 21:10:41,902][98560] Updated weights for policy 1, policy_version 11872 (0.0007) -[2023-10-10 21:10:42,139][98559] Updated weights for policy 0, policy_version 11830 (0.0008) -[2023-10-10 21:10:42,512][98559] Updated weights for policy 0, policy_version 11840 (0.0008) -[2023-10-10 21:10:45,556][97672] Fps is (10 sec: 13107.7, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 24281088. Throughput: 0: 1705.4, 1: 1720.7. Samples: 6081802. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:10:45,556][97672] Avg episode reward: [(0, '-5.700'), (1, '11.460')] -[2023-10-10 21:10:45,740][98560] Updated weights for policy 1, policy_version 11882 (0.0007) -[2023-10-10 21:10:46,114][98560] Updated weights for policy 1, policy_version 11892 (0.0007) -[2023-10-10 21:10:46,490][98560] Updated weights for policy 1, policy_version 11902 (0.0008) -[2023-10-10 21:10:46,555][98439] Saving new best policy, reward=11.460! -[2023-10-10 21:10:46,574][98559] Updated weights for policy 0, policy_version 11850 (0.0007) -[2023-10-10 21:10:46,945][98559] Updated weights for policy 0, policy_version 11860 (0.0007) -[2023-10-10 21:10:47,315][98559] Updated weights for policy 0, policy_version 11870 (0.0009) -[2023-10-10 21:10:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 24346624. Throughput: 0: 1705.3, 1: 1712.9. Samples: 6102448. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:10:50,557][97672] Avg episode reward: [(0, '-5.700'), (1, '11.720')] -[2023-10-10 21:10:50,653][98560] Updated weights for policy 1, policy_version 11912 (0.0008) -[2023-10-10 21:10:51,022][98560] Updated weights for policy 1, policy_version 11922 (0.0008) -[2023-10-10 21:10:51,309][98559] Updated weights for policy 0, policy_version 11880 (0.0010) -[2023-10-10 21:10:51,395][98560] Updated weights for policy 1, policy_version 11932 (0.0008) -[2023-10-10 21:10:51,532][98439] Saving new best policy, reward=11.720! -[2023-10-10 21:10:51,676][98559] Updated weights for policy 0, policy_version 11890 (0.0007) -[2023-10-10 21:10:52,047][98559] Updated weights for policy 0, policy_version 11900 (0.0007) -[2023-10-10 21:10:55,413][98560] Updated weights for policy 1, policy_version 11942 (0.0008) -[2023-10-10 21:10:55,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 24412160. Throughput: 0: 1692.7, 1: 1696.6. Samples: 6111724. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:10:55,557][97672] Avg episode reward: [(0, '-5.700'), (1, '11.940')] -[2023-10-10 21:10:55,780][98560] Updated weights for policy 1, policy_version 11952 (0.0009) -[2023-10-10 21:10:56,050][98559] Updated weights for policy 0, policy_version 11910 (0.0008) -[2023-10-10 21:10:56,153][98560] Updated weights for policy 1, policy_version 11962 (0.0007) -[2023-10-10 21:10:56,376][98439] Saving new best policy, reward=11.940! -[2023-10-10 21:10:56,427][98559] Updated weights for policy 0, policy_version 11920 (0.0010) -[2023-10-10 21:10:56,799][98559] Updated weights for policy 0, policy_version 11930 (0.0011) -[2023-10-10 21:11:00,258][98560] Updated weights for policy 1, policy_version 11972 (0.0008) -[2023-10-10 21:11:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 24477696. Throughput: 0: 1704.3, 1: 1712.6. Samples: 6132650. Policy #0 lag: (min: 1.0, avg: 4.0, max: 32.0) -[2023-10-10 21:11:00,556][97672] Avg episode reward: [(0, '-5.700'), (1, '11.880')] -[2023-10-10 21:11:00,620][98560] Updated weights for policy 1, policy_version 11982 (0.0008) -[2023-10-10 21:11:00,827][98559] Updated weights for policy 0, policy_version 11940 (0.0010) -[2023-10-10 21:11:00,989][98560] Updated weights for policy 1, policy_version 11992 (0.0007) -[2023-10-10 21:11:01,187][98559] Updated weights for policy 0, policy_version 11950 (0.0010) -[2023-10-10 21:11:01,562][98559] Updated weights for policy 0, policy_version 11960 (0.0007) -[2023-10-10 21:11:05,070][98560] Updated weights for policy 1, policy_version 12002 (0.0007) -[2023-10-10 21:11:05,404][98559] Updated weights for policy 0, policy_version 11970 (0.0007) -[2023-10-10 21:11:05,457][98560] Updated weights for policy 1, policy_version 12012 (0.0007) -[2023-10-10 21:11:05,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 24543232. Throughput: 0: 1709.4, 1: 1709.6. Samples: 6153810. Policy #0 lag: (min: 1.0, avg: 4.0, max: 32.0) -[2023-10-10 21:11:05,557][97672] Avg episode reward: [(0, '-5.700'), (1, '11.920')] -[2023-10-10 21:11:05,767][98559] Updated weights for policy 0, policy_version 11980 (0.0008) -[2023-10-10 21:11:05,829][98560] Updated weights for policy 1, policy_version 12022 (0.0009) -[2023-10-10 21:11:06,148][98559] Updated weights for policy 0, policy_version 11990 (0.0007) -[2023-10-10 21:11:06,194][98560] Updated weights for policy 1, policy_version 12032 (0.0008) -[2023-10-10 21:11:06,521][98559] Updated weights for policy 0, policy_version 12000 (0.0009) -[2023-10-10 21:11:10,189][98560] Updated weights for policy 1, policy_version 12042 (0.0011) -[2023-10-10 21:11:10,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 24608768. Throughput: 0: 1711.2, 1: 1706.9. Samples: 6163056. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:11:10,556][97672] Avg episode reward: [(0, '-5.700'), (1, '12.140')] -[2023-10-10 21:11:10,566][98560] Updated weights for policy 1, policy_version 12052 (0.0008) -[2023-10-10 21:11:10,610][98559] Updated weights for policy 0, policy_version 12010 (0.0008) -[2023-10-10 21:11:10,927][98560] Updated weights for policy 1, policy_version 12062 (0.0008) -[2023-10-10 21:11:10,984][98559] Updated weights for policy 0, policy_version 12020 (0.0008) -[2023-10-10 21:11:11,002][98439] Saving new best policy, reward=12.140! -[2023-10-10 21:11:11,348][98559] Updated weights for policy 0, policy_version 12030 (0.0008) -[2023-10-10 21:11:14,909][98560] Updated weights for policy 1, policy_version 12072 (0.0008) -[2023-10-10 21:11:15,281][98560] Updated weights for policy 1, policy_version 12082 (0.0007) -[2023-10-10 21:11:15,366][98559] Updated weights for policy 0, policy_version 12040 (0.0009) -[2023-10-10 21:11:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 24674304. Throughput: 0: 1706.2, 1: 1708.5. Samples: 6184120. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:11:15,557][97672] Avg episode reward: [(0, '-5.700'), (1, '12.220')] -[2023-10-10 21:11:15,648][98560] Updated weights for policy 1, policy_version 12092 (0.0009) -[2023-10-10 21:11:15,734][98559] Updated weights for policy 0, policy_version 12050 (0.0008) -[2023-10-10 21:11:15,796][98439] Saving new best policy, reward=12.220! -[2023-10-10 21:11:16,108][98559] Updated weights for policy 0, policy_version 12060 (0.0009) -[2023-10-10 21:11:19,516][98560] Updated weights for policy 1, policy_version 12102 (0.0007) -[2023-10-10 21:11:19,883][98560] Updated weights for policy 1, policy_version 12112 (0.0008) -[2023-10-10 21:11:20,174][98559] Updated weights for policy 0, policy_version 12070 (0.0008) -[2023-10-10 21:11:20,249][98560] Updated weights for policy 1, policy_version 12122 (0.0007) -[2023-10-10 21:11:20,551][98559] Updated weights for policy 0, policy_version 12080 (0.0007) -[2023-10-10 21:11:20,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 24772608. Throughput: 0: 1694.1, 1: 1697.7. Samples: 6204284. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:11:20,556][97672] Avg episode reward: [(0, '-5.700'), (1, '12.320')] -[2023-10-10 21:11:20,565][98439] Saving new best policy, reward=12.320! -[2023-10-10 21:11:20,920][98559] Updated weights for policy 0, policy_version 12090 (0.0008) -[2023-10-10 21:11:24,287][98560] Updated weights for policy 1, policy_version 12132 (0.0007) -[2023-10-10 21:11:24,655][98560] Updated weights for policy 1, policy_version 12142 (0.0008) -[2023-10-10 21:11:25,024][98560] Updated weights for policy 1, policy_version 12152 (0.0011) -[2023-10-10 21:11:25,083][98559] Updated weights for policy 0, policy_version 12100 (0.0009) -[2023-10-10 21:11:25,466][98559] Updated weights for policy 0, policy_version 12110 (0.0009) -[2023-10-10 21:11:25,556][97672] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 24838144. Throughput: 0: 1703.1, 1: 1705.6. Samples: 6214362. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-10 21:11:25,556][97672] Avg episode reward: [(0, '-5.700'), (1, '12.480')] -[2023-10-10 21:11:25,557][98439] Saving new best policy, reward=12.480! -[2023-10-10 21:11:25,840][98559] Updated weights for policy 0, policy_version 12120 (0.0008) -[2023-10-10 21:11:28,951][98560] Updated weights for policy 1, policy_version 12162 (0.0008) -[2023-10-10 21:11:29,318][98560] Updated weights for policy 1, policy_version 12172 (0.0008) -[2023-10-10 21:11:29,695][98560] Updated weights for policy 1, policy_version 12182 (0.0008) -[2023-10-10 21:11:29,789][98559] Updated weights for policy 0, policy_version 12130 (0.0007) -[2023-10-10 21:11:30,059][98560] Updated weights for policy 1, policy_version 12192 (0.0008) -[2023-10-10 21:11:30,163][98559] Updated weights for policy 0, policy_version 12140 (0.0008) -[2023-10-10 21:11:30,529][98559] Updated weights for policy 0, policy_version 12150 (0.0009) -[2023-10-10 21:11:30,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 24903680. Throughput: 0: 1706.3, 1: 1709.4. Samples: 6235508. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-10 21:11:30,557][97672] Avg episode reward: [(0, '-5.700'), (1, '12.880')] -[2023-10-10 21:11:30,558][98439] Saving new best policy, reward=12.880! -[2023-10-10 21:11:30,900][98559] Updated weights for policy 0, policy_version 12160 (0.0008) -[2023-10-10 21:11:33,978][98560] Updated weights for policy 1, policy_version 12202 (0.0009) -[2023-10-10 21:11:34,340][98560] Updated weights for policy 1, policy_version 12212 (0.0007) -[2023-10-10 21:11:34,704][98560] Updated weights for policy 1, policy_version 12222 (0.0007) -[2023-10-10 21:11:34,849][98559] Updated weights for policy 0, policy_version 12170 (0.0007) -[2023-10-10 21:11:35,217][98559] Updated weights for policy 0, policy_version 12180 (0.0008) -[2023-10-10 21:11:35,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 24969216. Throughput: 0: 1687.5, 1: 1690.7. Samples: 6254464. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-10 21:11:35,557][97672] Avg episode reward: [(0, '-5.700'), (1, '12.920')] -[2023-10-10 21:11:35,567][98439] Saving new best policy, reward=12.920! -[2023-10-10 21:11:35,590][98559] Updated weights for policy 0, policy_version 12190 (0.0008) -[2023-10-10 21:11:38,689][98560] Updated weights for policy 1, policy_version 12232 (0.0008) -[2023-10-10 21:11:39,058][98560] Updated weights for policy 1, policy_version 12242 (0.0008) -[2023-10-10 21:11:39,422][98560] Updated weights for policy 1, policy_version 12252 (0.0007) -[2023-10-10 21:11:39,492][98559] Updated weights for policy 0, policy_version 12200 (0.0011) -[2023-10-10 21:11:39,871][98559] Updated weights for policy 0, policy_version 12210 (0.0008) -[2023-10-10 21:11:40,245][98559] Updated weights for policy 0, policy_version 12220 (0.0009) -[2023-10-10 21:11:40,556][97672] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 25067520. Throughput: 0: 1706.4, 1: 1717.5. Samples: 6265800. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-10 21:11:40,556][97672] Avg episode reward: [(0, '-5.700'), (1, '13.060')] -[2023-10-10 21:11:40,557][98439] Saving new best policy, reward=13.060! -[2023-10-10 21:11:43,437][98560] Updated weights for policy 1, policy_version 12262 (0.0007) -[2023-10-10 21:11:43,809][98560] Updated weights for policy 1, policy_version 12272 (0.0008) -[2023-10-10 21:11:44,180][98560] Updated weights for policy 1, policy_version 12282 (0.0008) -[2023-10-10 21:11:44,234][98559] Updated weights for policy 0, policy_version 12230 (0.0008) -[2023-10-10 21:11:44,602][98559] Updated weights for policy 0, policy_version 12240 (0.0009) -[2023-10-10 21:11:44,973][98559] Updated weights for policy 0, policy_version 12250 (0.0008) -[2023-10-10 21:11:45,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 25133056. Throughput: 0: 1701.5, 1: 1709.7. Samples: 6286156. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-10 21:11:45,557][97672] Avg episode reward: [(0, '-5.700'), (1, '13.120')] -[2023-10-10 21:11:45,559][98439] Saving new best policy, reward=13.120! -[2023-10-10 21:11:48,181][98560] Updated weights for policy 1, policy_version 12292 (0.0008) -[2023-10-10 21:11:48,551][98560] Updated weights for policy 1, policy_version 12302 (0.0007) -[2023-10-10 21:11:48,926][98560] Updated weights for policy 1, policy_version 12312 (0.0007) -[2023-10-10 21:11:48,940][98559] Updated weights for policy 0, policy_version 12260 (0.0010) -[2023-10-10 21:11:49,312][98559] Updated weights for policy 0, policy_version 12270 (0.0008) -[2023-10-10 21:11:49,680][98559] Updated weights for policy 0, policy_version 12280 (0.0007) -[2023-10-10 21:11:50,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 25198592. Throughput: 0: 1678.4, 1: 1692.3. Samples: 6305490. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:11:50,557][97672] Avg episode reward: [(0, '-5.780'), (1, '13.280')] -[2023-10-10 21:11:50,573][98439] Saving new best policy, reward=13.280! -[2023-10-10 21:11:52,970][98560] Updated weights for policy 1, policy_version 12322 (0.0007) -[2023-10-10 21:11:53,369][98560] Updated weights for policy 1, policy_version 12332 (0.0009) -[2023-10-10 21:11:53,734][98560] Updated weights for policy 1, policy_version 12342 (0.0007) -[2023-10-10 21:11:53,768][98559] Updated weights for policy 0, policy_version 12290 (0.0007) -[2023-10-10 21:11:54,104][98560] Updated weights for policy 1, policy_version 12352 (0.0009) -[2023-10-10 21:11:54,156][98559] Updated weights for policy 0, policy_version 12300 (0.0009) -[2023-10-10 21:11:54,529][98559] Updated weights for policy 0, policy_version 12310 (0.0009) -[2023-10-10 21:11:54,897][98559] Updated weights for policy 0, policy_version 12320 (0.0009) -[2023-10-10 21:11:55,556][97672] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 25264128. Throughput: 0: 1708.9, 1: 1720.3. Samples: 6317370. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:11:55,557][97672] Avg episode reward: [(0, '-5.740'), (1, '13.260')] -[2023-10-10 21:11:58,091][98560] Updated weights for policy 1, policy_version 12362 (0.0009) -[2023-10-10 21:11:58,462][98560] Updated weights for policy 1, policy_version 12372 (0.0008) -[2023-10-10 21:11:58,824][98559] Updated weights for policy 0, policy_version 12330 (0.0007) -[2023-10-10 21:11:58,837][98560] Updated weights for policy 1, policy_version 12382 (0.0008) -[2023-10-10 21:11:59,203][98559] Updated weights for policy 0, policy_version 12340 (0.0007) -[2023-10-10 21:11:59,574][98559] Updated weights for policy 0, policy_version 12350 (0.0007) -[2023-10-10 21:12:00,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 25329664. Throughput: 0: 1693.9, 1: 1693.3. Samples: 6336546. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:12:00,556][97672] Avg episode reward: [(0, '-5.740'), (1, '13.340')] -[2023-10-10 21:12:00,557][98439] Saving new best policy, reward=13.340! -[2023-10-10 21:12:02,861][98560] Updated weights for policy 1, policy_version 12392 (0.0010) -[2023-10-10 21:12:03,229][98560] Updated weights for policy 1, policy_version 12402 (0.0007) -[2023-10-10 21:12:03,375][98559] Updated weights for policy 0, policy_version 12360 (0.0008) -[2023-10-10 21:12:03,600][98560] Updated weights for policy 1, policy_version 12412 (0.0007) -[2023-10-10 21:12:03,759][98559] Updated weights for policy 0, policy_version 12370 (0.0008) -[2023-10-10 21:12:04,131][98559] Updated weights for policy 0, policy_version 12380 (0.0010) -[2023-10-10 21:12:05,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 25395200. Throughput: 0: 1696.2, 1: 1694.3. Samples: 6356858. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:12:05,557][97672] Avg episode reward: [(0, '-5.740'), (1, '13.380')] -[2023-10-10 21:12:05,570][98439] Saving new best policy, reward=13.380! -[2023-10-10 21:12:07,537][98560] Updated weights for policy 1, policy_version 12422 (0.0008) -[2023-10-10 21:12:07,912][98560] Updated weights for policy 1, policy_version 12432 (0.0008) -[2023-10-10 21:12:08,062][98559] Updated weights for policy 0, policy_version 12390 (0.0008) -[2023-10-10 21:12:08,280][98560] Updated weights for policy 1, policy_version 12442 (0.0009) -[2023-10-10 21:12:08,432][98559] Updated weights for policy 0, policy_version 12400 (0.0008) -[2023-10-10 21:12:08,812][98559] Updated weights for policy 0, policy_version 12410 (0.0009) -[2023-10-10 21:12:10,556][97672] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 25460736. Throughput: 0: 1705.5, 1: 1705.9. Samples: 6367876. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:12:10,558][97672] Avg episode reward: [(0, '-5.740'), (1, '13.400')] -[2023-10-10 21:12:10,559][98439] Saving new best policy, reward=13.400! -[2023-10-10 21:12:12,441][98560] Updated weights for policy 1, policy_version 12452 (0.0008) -[2023-10-10 21:12:12,797][98560] Updated weights for policy 1, policy_version 12462 (0.0007) -[2023-10-10 21:12:12,816][98559] Updated weights for policy 0, policy_version 12420 (0.0008) -[2023-10-10 21:12:13,171][98560] Updated weights for policy 1, policy_version 12472 (0.0008) -[2023-10-10 21:12:13,188][98559] Updated weights for policy 0, policy_version 12430 (0.0007) -[2023-10-10 21:12:13,553][98559] Updated weights for policy 0, policy_version 12440 (0.0007) -[2023-10-10 21:12:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 25526272. Throughput: 0: 1687.4, 1: 1679.2. Samples: 6387002. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:12:15,557][97672] Avg episode reward: [(0, '-5.340'), (1, '13.540')] -[2023-10-10 21:12:15,558][98385] Saving new best policy, reward=-5.340! -[2023-10-10 21:12:15,559][98439] Saving new best policy, reward=13.540! -[2023-10-10 21:12:17,075][98560] Updated weights for policy 1, policy_version 12482 (0.0008) -[2023-10-10 21:12:17,454][98560] Updated weights for policy 1, policy_version 12492 (0.0011) -[2023-10-10 21:12:17,587][98559] Updated weights for policy 0, policy_version 12450 (0.0008) -[2023-10-10 21:12:17,818][98560] Updated weights for policy 1, policy_version 12502 (0.0010) -[2023-10-10 21:12:17,954][98559] Updated weights for policy 0, policy_version 12460 (0.0008) -[2023-10-10 21:12:18,182][98560] Updated weights for policy 1, policy_version 12512 (0.0009) -[2023-10-10 21:12:18,326][98559] Updated weights for policy 0, policy_version 12470 (0.0010) -[2023-10-10 21:12:18,703][98559] Updated weights for policy 0, policy_version 12480 (0.0008) -[2023-10-10 21:12:20,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 25591808. Throughput: 0: 1709.5, 1: 1702.6. Samples: 6408008. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-10 21:12:20,557][97672] Avg episode reward: [(0, '-5.340'), (1, '13.620')] -[2023-10-10 21:12:20,566][98439] Saving new best policy, reward=13.620! -[2023-10-10 21:12:22,358][98560] Updated weights for policy 1, policy_version 12522 (0.0008) -[2023-10-10 21:12:22,731][98560] Updated weights for policy 1, policy_version 12532 (0.0008) -[2023-10-10 21:12:22,758][98559] Updated weights for policy 0, policy_version 12490 (0.0008) -[2023-10-10 21:12:23,093][98560] Updated weights for policy 1, policy_version 12542 (0.0009) -[2023-10-10 21:12:23,132][98559] Updated weights for policy 0, policy_version 12500 (0.0009) -[2023-10-10 21:12:23,503][98559] Updated weights for policy 0, policy_version 12510 (0.0009) -[2023-10-10 21:12:25,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 25657344. Throughput: 0: 1694.8, 1: 1686.8. Samples: 6417972. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-10 21:12:25,557][97672] Avg episode reward: [(0, '-5.280'), (1, '13.600')] -[2023-10-10 21:12:25,558][98385] Saving new best policy, reward=-5.280! -[2023-10-10 21:12:27,025][98560] Updated weights for policy 1, policy_version 12552 (0.0008) -[2023-10-10 21:12:27,396][98560] Updated weights for policy 1, policy_version 12562 (0.0008) -[2023-10-10 21:12:27,399][98559] Updated weights for policy 0, policy_version 12520 (0.0008) -[2023-10-10 21:12:27,764][98560] Updated weights for policy 1, policy_version 12572 (0.0009) -[2023-10-10 21:12:27,773][98559] Updated weights for policy 0, policy_version 12530 (0.0008) -[2023-10-10 21:12:28,141][98559] Updated weights for policy 0, policy_version 12540 (0.0007) -[2023-10-10 21:12:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 25722880. Throughput: 0: 1694.7, 1: 1685.7. Samples: 6438272. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-10 21:12:30,557][97672] Avg episode reward: [(0, '-5.280'), (1, '13.700')] -[2023-10-10 21:12:30,558][98439] Saving new best policy, reward=13.700! -[2023-10-10 21:12:31,796][98560] Updated weights for policy 1, policy_version 12582 (0.0009) -[2023-10-10 21:12:32,175][98560] Updated weights for policy 1, policy_version 12592 (0.0008) -[2023-10-10 21:12:32,241][98559] Updated weights for policy 0, policy_version 12550 (0.0008) -[2023-10-10 21:12:32,544][98560] Updated weights for policy 1, policy_version 12602 (0.0007) -[2023-10-10 21:12:32,618][98559] Updated weights for policy 0, policy_version 12560 (0.0008) -[2023-10-10 21:12:32,978][98559] Updated weights for policy 0, policy_version 12570 (0.0010) -[2023-10-10 21:12:35,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 25788416. Throughput: 0: 1712.4, 1: 1700.4. Samples: 6459062. Policy #0 lag: (min: 12.0, avg: 12.1, max: 18.0) -[2023-10-10 21:12:35,557][97672] Avg episode reward: [(0, '-5.280'), (1, '13.560')] -[2023-10-10 21:12:35,569][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000012608_12910592.pth... -[2023-10-10 21:12:35,570][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000012576_12877824.pth... -[2023-10-10 21:12:35,607][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000010976_11239424.pth -[2023-10-10 21:12:35,610][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000011040_11304960.pth -[2023-10-10 21:12:36,586][98560] Updated weights for policy 1, policy_version 12612 (0.0007) -[2023-10-10 21:12:36,965][98560] Updated weights for policy 1, policy_version 12622 (0.0007) -[2023-10-10 21:12:37,046][98559] Updated weights for policy 0, policy_version 12580 (0.0009) -[2023-10-10 21:12:37,332][98560] Updated weights for policy 1, policy_version 12632 (0.0008) -[2023-10-10 21:12:37,419][98559] Updated weights for policy 0, policy_version 12590 (0.0008) -[2023-10-10 21:12:37,797][98559] Updated weights for policy 0, policy_version 12600 (0.0008) -[2023-10-10 21:12:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 25853952. Throughput: 0: 1680.9, 1: 1671.5. Samples: 6468226. Policy #0 lag: (min: 12.0, avg: 12.1, max: 18.0) -[2023-10-10 21:12:40,556][97672] Avg episode reward: [(0, '-5.280'), (1, '13.700')] -[2023-10-10 21:12:41,345][98560] Updated weights for policy 1, policy_version 12642 (0.0009) -[2023-10-10 21:12:41,717][98560] Updated weights for policy 1, policy_version 12652 (0.0011) -[2023-10-10 21:12:41,881][98559] Updated weights for policy 0, policy_version 12610 (0.0010) -[2023-10-10 21:12:42,086][98560] Updated weights for policy 1, policy_version 12662 (0.0007) -[2023-10-10 21:12:42,255][98559] Updated weights for policy 0, policy_version 12620 (0.0009) -[2023-10-10 21:12:42,461][98560] Updated weights for policy 1, policy_version 12672 (0.0007) -[2023-10-10 21:12:42,629][98559] Updated weights for policy 0, policy_version 12630 (0.0007) -[2023-10-10 21:12:42,997][98559] Updated weights for policy 0, policy_version 12640 (0.0009) -[2023-10-10 21:12:45,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 25919488. Throughput: 0: 1692.2, 1: 1693.0. Samples: 6488882. Policy #0 lag: (min: 19.0, avg: 32.7, max: 51.0) -[2023-10-10 21:12:45,557][97672] Avg episode reward: [(0, '-5.080'), (1, '13.640')] -[2023-10-10 21:12:45,557][98385] Saving new best policy, reward=-5.080! -[2023-10-10 21:12:46,489][98560] Updated weights for policy 1, policy_version 12682 (0.0008) -[2023-10-10 21:12:46,863][98560] Updated weights for policy 1, policy_version 12692 (0.0007) -[2023-10-10 21:12:46,940][98559] Updated weights for policy 0, policy_version 12650 (0.0008) -[2023-10-10 21:12:47,229][98560] Updated weights for policy 1, policy_version 12702 (0.0009) -[2023-10-10 21:12:47,310][98559] Updated weights for policy 0, policy_version 12660 (0.0008) -[2023-10-10 21:12:47,680][98559] Updated weights for policy 0, policy_version 12670 (0.0008) -[2023-10-10 21:12:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 25985024. Throughput: 0: 1703.6, 1: 1696.6. Samples: 6509864. Policy #0 lag: (min: 19.0, avg: 32.7, max: 51.0) -[2023-10-10 21:12:50,556][97672] Avg episode reward: [(0, '-4.980'), (1, '13.420')] -[2023-10-10 21:12:50,565][98385] Saving new best policy, reward=-4.980! -[2023-10-10 21:12:51,310][98560] Updated weights for policy 1, policy_version 12712 (0.0008) -[2023-10-10 21:12:51,650][98559] Updated weights for policy 0, policy_version 12680 (0.0007) -[2023-10-10 21:12:51,683][98560] Updated weights for policy 1, policy_version 12722 (0.0007) -[2023-10-10 21:12:52,014][98559] Updated weights for policy 0, policy_version 12690 (0.0009) -[2023-10-10 21:12:52,059][98560] Updated weights for policy 1, policy_version 12732 (0.0009) -[2023-10-10 21:12:52,390][98559] Updated weights for policy 0, policy_version 12700 (0.0008) -[2023-10-10 21:12:55,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 26050560. Throughput: 0: 1685.0, 1: 1673.4. Samples: 6519002. Policy #0 lag: (min: 19.0, avg: 32.7, max: 51.0) -[2023-10-10 21:12:55,557][97672] Avg episode reward: [(0, '-4.980'), (1, '13.700')] -[2023-10-10 21:12:56,056][98560] Updated weights for policy 1, policy_version 12742 (0.0009) -[2023-10-10 21:12:56,380][98559] Updated weights for policy 0, policy_version 12710 (0.0008) -[2023-10-10 21:12:56,437][98560] Updated weights for policy 1, policy_version 12752 (0.0010) -[2023-10-10 21:12:56,739][98559] Updated weights for policy 0, policy_version 12720 (0.0008) -[2023-10-10 21:12:56,802][98560] Updated weights for policy 1, policy_version 12762 (0.0008) -[2023-10-10 21:12:57,101][98559] Updated weights for policy 0, policy_version 12730 (0.0011) -[2023-10-10 21:13:00,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 26116096. Throughput: 0: 1705.8, 1: 1699.8. Samples: 6540256. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:13:00,557][97672] Avg episode reward: [(0, '-4.980'), (1, '13.820')] -[2023-10-10 21:13:00,559][98439] Saving new best policy, reward=13.820! -[2023-10-10 21:13:00,894][98560] Updated weights for policy 1, policy_version 12772 (0.0009) -[2023-10-10 21:13:01,067][98559] Updated weights for policy 0, policy_version 12740 (0.0010) -[2023-10-10 21:13:01,261][98560] Updated weights for policy 1, policy_version 12782 (0.0008) -[2023-10-10 21:13:01,434][98559] Updated weights for policy 0, policy_version 12750 (0.0007) -[2023-10-10 21:13:01,629][98560] Updated weights for policy 1, policy_version 12792 (0.0007) -[2023-10-10 21:13:01,813][98559] Updated weights for policy 0, policy_version 12760 (0.0007) -[2023-10-10 21:13:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 26181632. Throughput: 0: 1708.5, 1: 1694.6. Samples: 6561148. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:13:05,556][97672] Avg episode reward: [(0, '-4.980'), (1, '13.840')] -[2023-10-10 21:13:05,591][98560] Updated weights for policy 1, policy_version 12802 (0.0009) -[2023-10-10 21:13:05,831][98559] Updated weights for policy 0, policy_version 12770 (0.0007) -[2023-10-10 21:13:05,961][98560] Updated weights for policy 1, policy_version 12812 (0.0010) -[2023-10-10 21:13:06,194][98559] Updated weights for policy 0, policy_version 12780 (0.0008) -[2023-10-10 21:13:06,330][98560] Updated weights for policy 1, policy_version 12822 (0.0008) -[2023-10-10 21:13:06,563][98559] Updated weights for policy 0, policy_version 12790 (0.0007) -[2023-10-10 21:13:06,686][98439] Saving new best policy, reward=13.840! -[2023-10-10 21:13:06,687][98560] Updated weights for policy 1, policy_version 12832 (0.0007) -[2023-10-10 21:13:06,941][98559] Updated weights for policy 0, policy_version 12800 (0.0008) -[2023-10-10 21:13:10,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 26247168. Throughput: 0: 1703.2, 1: 1680.8. Samples: 6570256. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:13:10,556][97672] Avg episode reward: [(0, '-4.980'), (1, '13.900')] -[2023-10-10 21:13:10,755][98560] Updated weights for policy 1, policy_version 12842 (0.0008) -[2023-10-10 21:13:11,078][98559] Updated weights for policy 0, policy_version 12810 (0.0009) -[2023-10-10 21:13:11,130][98560] Updated weights for policy 1, policy_version 12852 (0.0008) -[2023-10-10 21:13:11,447][98559] Updated weights for policy 0, policy_version 12820 (0.0009) -[2023-10-10 21:13:11,499][98560] Updated weights for policy 1, policy_version 12862 (0.0007) -[2023-10-10 21:13:11,569][98439] Saving new best policy, reward=13.900! -[2023-10-10 21:13:11,815][98559] Updated weights for policy 0, policy_version 12830 (0.0010) -[2023-10-10 21:13:15,547][98560] Updated weights for policy 1, policy_version 12872 (0.0007) -[2023-10-10 21:13:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 26312704. Throughput: 0: 1706.5, 1: 1691.0. Samples: 6591160. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:13:15,556][97672] Avg episode reward: [(0, '-4.880'), (1, '14.360')] -[2023-10-10 21:13:15,877][98559] Updated weights for policy 0, policy_version 12840 (0.0009) -[2023-10-10 21:13:15,914][98560] Updated weights for policy 1, policy_version 12882 (0.0008) -[2023-10-10 21:13:16,243][98559] Updated weights for policy 0, policy_version 12850 (0.0009) -[2023-10-10 21:13:16,288][98560] Updated weights for policy 1, policy_version 12892 (0.0009) -[2023-10-10 21:13:16,429][98439] Saving new best policy, reward=14.360! -[2023-10-10 21:13:16,609][98559] Updated weights for policy 0, policy_version 12860 (0.0009) -[2023-10-10 21:13:16,759][98385] Saving new best policy, reward=-4.880! -[2023-10-10 21:13:20,200][98560] Updated weights for policy 1, policy_version 12902 (0.0008) -[2023-10-10 21:13:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 26378240. Throughput: 0: 1706.4, 1: 1694.4. Samples: 6612094. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:13:20,556][97672] Avg episode reward: [(0, '-4.880'), (1, '14.380')] -[2023-10-10 21:13:20,568][98560] Updated weights for policy 1, policy_version 12912 (0.0008) -[2023-10-10 21:13:20,715][98559] Updated weights for policy 0, policy_version 12870 (0.0009) -[2023-10-10 21:13:20,939][98560] Updated weights for policy 1, policy_version 12922 (0.0009) -[2023-10-10 21:13:21,090][98559] Updated weights for policy 0, policy_version 12880 (0.0007) -[2023-10-10 21:13:21,153][98439] Saving new best policy, reward=14.380! -[2023-10-10 21:13:21,469][98559] Updated weights for policy 0, policy_version 12890 (0.0008) -[2023-10-10 21:13:25,007][98560] Updated weights for policy 1, policy_version 12932 (0.0010) -[2023-10-10 21:13:25,375][98560] Updated weights for policy 1, policy_version 12942 (0.0010) -[2023-10-10 21:13:25,476][98559] Updated weights for policy 0, policy_version 12900 (0.0008) -[2023-10-10 21:13:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 26443776. Throughput: 0: 1708.7, 1: 1695.6. Samples: 6621420. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:13:25,556][97672] Avg episode reward: [(0, '-4.880'), (1, '14.620')] -[2023-10-10 21:13:25,738][98560] Updated weights for policy 1, policy_version 12952 (0.0007) -[2023-10-10 21:13:25,850][98559] Updated weights for policy 0, policy_version 12910 (0.0007) -[2023-10-10 21:13:26,020][98439] Saving new best policy, reward=14.620! -[2023-10-10 21:13:26,213][98559] Updated weights for policy 0, policy_version 12920 (0.0008) -[2023-10-10 21:13:29,862][98560] Updated weights for policy 1, policy_version 12962 (0.0009) -[2023-10-10 21:13:30,128][98559] Updated weights for policy 0, policy_version 12930 (0.0009) -[2023-10-10 21:13:30,233][98560] Updated weights for policy 1, policy_version 12972 (0.0008) -[2023-10-10 21:13:30,506][98559] Updated weights for policy 0, policy_version 12940 (0.0008) -[2023-10-10 21:13:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 26509312. Throughput: 0: 1714.9, 1: 1700.7. Samples: 6642584. Policy #0 lag: (min: 31.0, avg: 36.2, max: 63.0) -[2023-10-10 21:13:30,557][97672] Avg episode reward: [(0, '-4.860'), (1, '14.740')] -[2023-10-10 21:13:30,600][98560] Updated weights for policy 1, policy_version 12982 (0.0007) -[2023-10-10 21:13:30,878][98559] Updated weights for policy 0, policy_version 12950 (0.0007) -[2023-10-10 21:13:30,963][98439] Saving new best policy, reward=14.740! -[2023-10-10 21:13:30,964][98560] Updated weights for policy 1, policy_version 12992 (0.0008) -[2023-10-10 21:13:31,254][98385] Saving new best policy, reward=-4.860! -[2023-10-10 21:13:31,259][98559] Updated weights for policy 0, policy_version 12960 (0.0010) -[2023-10-10 21:13:34,958][98560] Updated weights for policy 1, policy_version 13002 (0.0007) -[2023-10-10 21:13:35,270][98559] Updated weights for policy 0, policy_version 12970 (0.0008) -[2023-10-10 21:13:35,319][98560] Updated weights for policy 1, policy_version 13012 (0.0007) -[2023-10-10 21:13:35,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 26574848. Throughput: 0: 1699.0, 1: 1699.7. Samples: 6662804. Policy #0 lag: (min: 31.0, avg: 36.2, max: 63.0) -[2023-10-10 21:13:35,557][97672] Avg episode reward: [(0, '-4.860'), (1, '14.920')] -[2023-10-10 21:13:35,634][98559] Updated weights for policy 0, policy_version 12980 (0.0008) -[2023-10-10 21:13:35,693][98560] Updated weights for policy 1, policy_version 13022 (0.0007) -[2023-10-10 21:13:35,767][98439] Saving new best policy, reward=14.920! -[2023-10-10 21:13:36,009][98559] Updated weights for policy 0, policy_version 12990 (0.0009) -[2023-10-10 21:13:39,806][98560] Updated weights for policy 1, policy_version 13032 (0.0008) -[2023-10-10 21:13:40,113][98559] Updated weights for policy 0, policy_version 13000 (0.0010) -[2023-10-10 21:13:40,182][98560] Updated weights for policy 1, policy_version 13042 (0.0010) -[2023-10-10 21:13:40,485][98559] Updated weights for policy 0, policy_version 13010 (0.0008) -[2023-10-10 21:13:40,540][98560] Updated weights for policy 1, policy_version 13052 (0.0007) -[2023-10-10 21:13:40,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 26640384. Throughput: 0: 1708.4, 1: 1702.0. Samples: 6672474. Policy #0 lag: (min: 31.0, avg: 36.2, max: 63.0) -[2023-10-10 21:13:40,557][97672] Avg episode reward: [(0, '-4.860'), (1, '14.700')] -[2023-10-10 21:13:40,845][98559] Updated weights for policy 0, policy_version 13020 (0.0009) -[2023-10-10 21:13:44,629][98560] Updated weights for policy 1, policy_version 13062 (0.0008) -[2023-10-10 21:13:44,996][98560] Updated weights for policy 1, policy_version 13072 (0.0008) -[2023-10-10 21:13:45,005][98559] Updated weights for policy 0, policy_version 13030 (0.0009) -[2023-10-10 21:13:45,365][98560] Updated weights for policy 1, policy_version 13082 (0.0007) -[2023-10-10 21:13:45,377][98559] Updated weights for policy 0, policy_version 13040 (0.0008) -[2023-10-10 21:13:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 26705920. Throughput: 0: 1701.6, 1: 1698.3. Samples: 6693250. Policy #0 lag: (min: 31.0, avg: 32.0, max: 53.0) -[2023-10-10 21:13:45,557][97672] Avg episode reward: [(0, '-4.840'), (1, '14.700')] -[2023-10-10 21:13:45,757][98559] Updated weights for policy 0, policy_version 13050 (0.0009) -[2023-10-10 21:13:45,978][98385] Saving new best policy, reward=-4.840! -[2023-10-10 21:13:49,408][98560] Updated weights for policy 1, policy_version 13092 (0.0008) -[2023-10-10 21:13:49,590][98559] Updated weights for policy 0, policy_version 13060 (0.0009) -[2023-10-10 21:13:49,781][98560] Updated weights for policy 1, policy_version 13102 (0.0008) -[2023-10-10 21:13:49,973][98559] Updated weights for policy 0, policy_version 13070 (0.0009) -[2023-10-10 21:13:50,142][98560] Updated weights for policy 1, policy_version 13112 (0.0008) -[2023-10-10 21:13:50,339][98559] Updated weights for policy 0, policy_version 13080 (0.0008) -[2023-10-10 21:13:50,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 26804224. Throughput: 0: 1677.0, 1: 1693.9. Samples: 6712838. Policy #0 lag: (min: 31.0, avg: 32.0, max: 53.0) -[2023-10-10 21:13:50,557][97672] Avg episode reward: [(0, '-4.780'), (1, '14.740')] -[2023-10-10 21:13:50,630][98385] Saving new best policy, reward=-4.780! -[2023-10-10 21:13:54,242][98560] Updated weights for policy 1, policy_version 13122 (0.0007) -[2023-10-10 21:13:54,310][98559] Updated weights for policy 0, policy_version 13090 (0.0009) -[2023-10-10 21:13:54,601][98560] Updated weights for policy 1, policy_version 13132 (0.0008) -[2023-10-10 21:13:54,681][98559] Updated weights for policy 0, policy_version 13100 (0.0009) -[2023-10-10 21:13:54,968][98560] Updated weights for policy 1, policy_version 13142 (0.0008) -[2023-10-10 21:13:55,047][98559] Updated weights for policy 0, policy_version 13110 (0.0009) -[2023-10-10 21:13:55,340][98560] Updated weights for policy 1, policy_version 13152 (0.0007) -[2023-10-10 21:13:55,415][98559] Updated weights for policy 0, policy_version 13120 (0.0009) -[2023-10-10 21:13:55,556][97672] Fps is (10 sec: 19661.0, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 26902528. Throughput: 0: 1701.0, 1: 1704.8. Samples: 6723520. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:13:55,557][97672] Avg episode reward: [(0, '-4.780'), (1, '14.660')] -[2023-10-10 21:13:59,260][98560] Updated weights for policy 1, policy_version 13162 (0.0007) -[2023-10-10 21:13:59,590][98559] Updated weights for policy 0, policy_version 13130 (0.0009) -[2023-10-10 21:13:59,626][98560] Updated weights for policy 1, policy_version 13172 (0.0007) -[2023-10-10 21:13:59,967][98559] Updated weights for policy 0, policy_version 13140 (0.0008) -[2023-10-10 21:13:59,995][98560] Updated weights for policy 1, policy_version 13182 (0.0008) -[2023-10-10 21:14:00,343][98559] Updated weights for policy 0, policy_version 13150 (0.0007) -[2023-10-10 21:14:00,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 26968064. Throughput: 0: 1697.4, 1: 1705.3. Samples: 6744284. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:14:00,557][97672] Avg episode reward: [(0, '-4.640'), (1, '14.800')] -[2023-10-10 21:14:00,558][98385] Saving new best policy, reward=-4.640! -[2023-10-10 21:14:04,081][98560] Updated weights for policy 1, policy_version 13192 (0.0008) -[2023-10-10 21:14:04,213][98559] Updated weights for policy 0, policy_version 13160 (0.0009) -[2023-10-10 21:14:04,446][98560] Updated weights for policy 1, policy_version 13202 (0.0009) -[2023-10-10 21:14:04,592][98559] Updated weights for policy 0, policy_version 13170 (0.0008) -[2023-10-10 21:14:04,818][98560] Updated weights for policy 1, policy_version 13212 (0.0008) -[2023-10-10 21:14:04,970][98559] Updated weights for policy 0, policy_version 13180 (0.0008) -[2023-10-10 21:14:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 27033600. Throughput: 0: 1676.3, 1: 1678.9. Samples: 6763078. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:14:05,557][97672] Avg episode reward: [(0, '-4.640'), (1, '14.860')] -[2023-10-10 21:14:08,727][98560] Updated weights for policy 1, policy_version 13222 (0.0010) -[2023-10-10 21:14:08,896][98559] Updated weights for policy 0, policy_version 13190 (0.0007) -[2023-10-10 21:14:09,101][98560] Updated weights for policy 1, policy_version 13232 (0.0009) -[2023-10-10 21:14:09,273][98559] Updated weights for policy 0, policy_version 13200 (0.0008) -[2023-10-10 21:14:09,455][98560] Updated weights for policy 1, policy_version 13242 (0.0008) -[2023-10-10 21:14:09,643][98559] Updated weights for policy 0, policy_version 13210 (0.0009) -[2023-10-10 21:14:10,556][97672] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 27099136. Throughput: 0: 1705.9, 1: 1706.0. Samples: 6774952. Policy #0 lag: (min: 11.0, avg: 23.8, max: 43.0) -[2023-10-10 21:14:10,556][97672] Avg episode reward: [(0, '-4.640'), (1, '15.080')] -[2023-10-10 21:14:10,557][98439] Saving new best policy, reward=15.080! -[2023-10-10 21:14:13,433][98560] Updated weights for policy 1, policy_version 13252 (0.0007) -[2023-10-10 21:14:13,577][98559] Updated weights for policy 0, policy_version 13220 (0.0010) -[2023-10-10 21:14:13,799][98560] Updated weights for policy 1, policy_version 13262 (0.0008) -[2023-10-10 21:14:13,939][98559] Updated weights for policy 0, policy_version 13230 (0.0007) -[2023-10-10 21:14:14,164][98560] Updated weights for policy 1, policy_version 13272 (0.0008) -[2023-10-10 21:14:14,307][98559] Updated weights for policy 0, policy_version 13240 (0.0009) -[2023-10-10 21:14:15,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 27164672. Throughput: 0: 1680.5, 1: 1693.5. Samples: 6794416. Policy #0 lag: (min: 11.0, avg: 23.8, max: 43.0) -[2023-10-10 21:14:15,557][97672] Avg episode reward: [(0, '-4.540'), (1, '15.380')] -[2023-10-10 21:14:15,559][98385] Saving new best policy, reward=-4.540! -[2023-10-10 21:14:15,559][98439] Saving new best policy, reward=15.380! -[2023-10-10 21:14:18,062][98560] Updated weights for policy 1, policy_version 13282 (0.0009) -[2023-10-10 21:14:18,419][98560] Updated weights for policy 1, policy_version 13292 (0.0010) -[2023-10-10 21:14:18,422][98559] Updated weights for policy 0, policy_version 13250 (0.0008) -[2023-10-10 21:14:18,782][98560] Updated weights for policy 1, policy_version 13302 (0.0009) -[2023-10-10 21:14:18,788][98559] Updated weights for policy 0, policy_version 13260 (0.0007) -[2023-10-10 21:14:19,158][98559] Updated weights for policy 0, policy_version 13270 (0.0008) -[2023-10-10 21:14:19,159][98560] Updated weights for policy 1, policy_version 13312 (0.0009) -[2023-10-10 21:14:19,529][98559] Updated weights for policy 0, policy_version 13280 (0.0007) -[2023-10-10 21:14:20,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 27230208. Throughput: 0: 1685.9, 1: 1679.6. Samples: 6814252. Policy #0 lag: (min: 11.0, avg: 23.8, max: 43.0) -[2023-10-10 21:14:20,557][97672] Avg episode reward: [(0, '-4.540'), (1, '15.600')] -[2023-10-10 21:14:20,571][98439] Saving new best policy, reward=15.600! -[2023-10-10 21:14:23,317][98560] Updated weights for policy 1, policy_version 13322 (0.0008) -[2023-10-10 21:14:23,479][98559] Updated weights for policy 0, policy_version 13290 (0.0008) -[2023-10-10 21:14:23,685][98560] Updated weights for policy 1, policy_version 13332 (0.0007) -[2023-10-10 21:14:23,862][98559] Updated weights for policy 0, policy_version 13300 (0.0007) -[2023-10-10 21:14:24,049][98560] Updated weights for policy 1, policy_version 13342 (0.0009) -[2023-10-10 21:14:24,228][98559] Updated weights for policy 0, policy_version 13310 (0.0009) -[2023-10-10 21:14:25,556][97672] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 27295744. Throughput: 0: 1701.7, 1: 1706.1. Samples: 6825828. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-10 21:14:25,557][97672] Avg episode reward: [(0, '-4.540'), (1, '15.820')] -[2023-10-10 21:14:25,559][98439] Saving new best policy, reward=15.820! -[2023-10-10 21:14:28,093][98560] Updated weights for policy 1, policy_version 13352 (0.0008) -[2023-10-10 21:14:28,209][98559] Updated weights for policy 0, policy_version 13320 (0.0008) -[2023-10-10 21:14:28,463][98560] Updated weights for policy 1, policy_version 13362 (0.0007) -[2023-10-10 21:14:28,588][98559] Updated weights for policy 0, policy_version 13330 (0.0008) -[2023-10-10 21:14:28,840][98560] Updated weights for policy 1, policy_version 13372 (0.0009) -[2023-10-10 21:14:28,958][98559] Updated weights for policy 0, policy_version 13340 (0.0009) -[2023-10-10 21:14:30,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 27361280. Throughput: 0: 1683.9, 1: 1680.5. Samples: 6844648. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-10 21:14:30,556][97672] Avg episode reward: [(0, '-4.540'), (1, '15.620')] -[2023-10-10 21:14:32,830][98560] Updated weights for policy 1, policy_version 13382 (0.0009) -[2023-10-10 21:14:32,958][98559] Updated weights for policy 0, policy_version 13350 (0.0008) -[2023-10-10 21:14:33,189][98560] Updated weights for policy 1, policy_version 13392 (0.0007) -[2023-10-10 21:14:33,318][98559] Updated weights for policy 0, policy_version 13360 (0.0009) -[2023-10-10 21:14:33,562][98560] Updated weights for policy 1, policy_version 13402 (0.0008) -[2023-10-10 21:14:33,685][98559] Updated weights for policy 0, policy_version 13370 (0.0008) -[2023-10-10 21:14:35,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 27426816. Throughput: 0: 1699.8, 1: 1683.4. Samples: 6865082. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-10 21:14:35,557][97672] Avg episode reward: [(0, '-4.540'), (1, '15.480')] -[2023-10-10 21:14:35,564][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000013376_13697024.pth... -[2023-10-10 21:14:35,565][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000013408_13729792.pth... -[2023-10-10 21:14:35,603][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000011776_12058624.pth -[2023-10-10 21:14:35,605][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000011808_12091392.pth -[2023-10-10 21:14:37,532][98560] Updated weights for policy 1, policy_version 13412 (0.0009) -[2023-10-10 21:14:37,854][98559] Updated weights for policy 0, policy_version 13380 (0.0009) -[2023-10-10 21:14:37,898][98560] Updated weights for policy 1, policy_version 13422 (0.0009) -[2023-10-10 21:14:38,231][98559] Updated weights for policy 0, policy_version 13390 (0.0007) -[2023-10-10 21:14:38,268][98560] Updated weights for policy 1, policy_version 13432 (0.0009) -[2023-10-10 21:14:38,608][98559] Updated weights for policy 0, policy_version 13400 (0.0008) -[2023-10-10 21:14:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 27492352. Throughput: 0: 1690.7, 1: 1698.8. Samples: 6876046. Policy #0 lag: (min: 20.0, avg: 24.0, max: 52.0) -[2023-10-10 21:14:40,557][97672] Avg episode reward: [(0, '-4.460'), (1, '15.460')] -[2023-10-10 21:14:40,558][98385] Saving new best policy, reward=-4.460! -[2023-10-10 21:14:42,373][98560] Updated weights for policy 1, policy_version 13442 (0.0008) -[2023-10-10 21:14:42,722][98559] Updated weights for policy 0, policy_version 13410 (0.0008) -[2023-10-10 21:14:42,736][98560] Updated weights for policy 1, policy_version 13452 (0.0009) -[2023-10-10 21:14:43,095][98559] Updated weights for policy 0, policy_version 13420 (0.0009) -[2023-10-10 21:14:43,112][98560] Updated weights for policy 1, policy_version 13462 (0.0007) -[2023-10-10 21:14:43,468][98559] Updated weights for policy 0, policy_version 13430 (0.0008) -[2023-10-10 21:14:43,480][98560] Updated weights for policy 1, policy_version 13472 (0.0008) -[2023-10-10 21:14:43,839][98559] Updated weights for policy 0, policy_version 13440 (0.0008) -[2023-10-10 21:14:45,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 27557888. Throughput: 0: 1678.7, 1: 1671.8. Samples: 6895056. Policy #0 lag: (min: 20.0, avg: 24.0, max: 52.0) -[2023-10-10 21:14:45,557][97672] Avg episode reward: [(0, '-4.460'), (1, '15.440')] -[2023-10-10 21:14:47,555][98560] Updated weights for policy 1, policy_version 13482 (0.0009) -[2023-10-10 21:14:47,915][98559] Updated weights for policy 0, policy_version 13450 (0.0008) -[2023-10-10 21:14:47,917][98560] Updated weights for policy 1, policy_version 13492 (0.0008) -[2023-10-10 21:14:48,287][98559] Updated weights for policy 0, policy_version 13460 (0.0007) -[2023-10-10 21:14:48,291][98560] Updated weights for policy 1, policy_version 13502 (0.0008) -[2023-10-10 21:14:48,657][98559] Updated weights for policy 0, policy_version 13470 (0.0007) -[2023-10-10 21:14:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 27623424. Throughput: 0: 1698.6, 1: 1692.1. Samples: 6915660. Policy #0 lag: (min: 20.0, avg: 24.0, max: 52.0) -[2023-10-10 21:14:50,556][97672] Avg episode reward: [(0, '-4.460'), (1, '15.420')] -[2023-10-10 21:14:52,418][98560] Updated weights for policy 1, policy_version 13512 (0.0009) -[2023-10-10 21:14:52,722][98559] Updated weights for policy 0, policy_version 13480 (0.0008) -[2023-10-10 21:14:52,787][98560] Updated weights for policy 1, policy_version 13522 (0.0008) -[2023-10-10 21:14:53,082][98559] Updated weights for policy 0, policy_version 13490 (0.0007) -[2023-10-10 21:14:53,160][98560] Updated weights for policy 1, policy_version 13532 (0.0009) -[2023-10-10 21:14:53,456][98559] Updated weights for policy 0, policy_version 13500 (0.0008) -[2023-10-10 21:14:55,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 27688960. Throughput: 0: 1671.7, 1: 1680.0. Samples: 6925782. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:14:55,556][97672] Avg episode reward: [(0, '-4.460'), (1, '15.540')] -[2023-10-10 21:14:57,212][98560] Updated weights for policy 1, policy_version 13542 (0.0009) -[2023-10-10 21:14:57,399][98559] Updated weights for policy 0, policy_version 13510 (0.0007) -[2023-10-10 21:14:57,574][98560] Updated weights for policy 1, policy_version 13552 (0.0008) -[2023-10-10 21:14:57,775][98559] Updated weights for policy 0, policy_version 13520 (0.0008) -[2023-10-10 21:14:57,937][98560] Updated weights for policy 1, policy_version 13562 (0.0008) -[2023-10-10 21:14:58,136][98559] Updated weights for policy 0, policy_version 13530 (0.0009) -[2023-10-10 21:15:00,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 27754496. Throughput: 0: 1689.2, 1: 1676.4. Samples: 6945872. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:15:00,557][97672] Avg episode reward: [(0, '-4.460'), (1, '15.600')] -[2023-10-10 21:15:01,969][98560] Updated weights for policy 1, policy_version 13572 (0.0008) -[2023-10-10 21:15:02,217][98559] Updated weights for policy 0, policy_version 13540 (0.0009) -[2023-10-10 21:15:02,338][98560] Updated weights for policy 1, policy_version 13582 (0.0008) -[2023-10-10 21:15:02,584][98559] Updated weights for policy 0, policy_version 13550 (0.0008) -[2023-10-10 21:15:02,703][98560] Updated weights for policy 1, policy_version 13592 (0.0007) -[2023-10-10 21:15:02,949][98559] Updated weights for policy 0, policy_version 13560 (0.0007) -[2023-10-10 21:15:05,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 27820032. Throughput: 0: 1696.3, 1: 1695.0. Samples: 6966860. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:15:05,557][97672] Avg episode reward: [(0, '-4.460'), (1, '15.780')] -[2023-10-10 21:15:06,645][98560] Updated weights for policy 1, policy_version 13602 (0.0008) -[2023-10-10 21:15:06,942][98559] Updated weights for policy 0, policy_version 13570 (0.0009) -[2023-10-10 21:15:07,016][98560] Updated weights for policy 1, policy_version 13612 (0.0008) -[2023-10-10 21:15:07,323][98559] Updated weights for policy 0, policy_version 13580 (0.0009) -[2023-10-10 21:15:07,387][98560] Updated weights for policy 1, policy_version 13622 (0.0008) -[2023-10-10 21:15:07,694][98559] Updated weights for policy 0, policy_version 13590 (0.0007) -[2023-10-10 21:15:07,753][98560] Updated weights for policy 1, policy_version 13632 (0.0008) -[2023-10-10 21:15:08,060][98559] Updated weights for policy 0, policy_version 13600 (0.0011) -[2023-10-10 21:15:10,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 27885568. Throughput: 0: 1673.1, 1: 1672.5. Samples: 6976378. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:15:10,557][97672] Avg episode reward: [(0, '-4.460'), (1, '15.920')] -[2023-10-10 21:15:10,558][98439] Saving new best policy, reward=15.920! -[2023-10-10 21:15:11,864][98560] Updated weights for policy 1, policy_version 13642 (0.0008) -[2023-10-10 21:15:12,130][98559] Updated weights for policy 0, policy_version 13610 (0.0008) -[2023-10-10 21:15:12,238][98560] Updated weights for policy 1, policy_version 13652 (0.0009) -[2023-10-10 21:15:12,501][98559] Updated weights for policy 0, policy_version 13620 (0.0007) -[2023-10-10 21:15:12,601][98560] Updated weights for policy 1, policy_version 13662 (0.0007) -[2023-10-10 21:15:12,875][98559] Updated weights for policy 0, policy_version 13630 (0.0008) -[2023-10-10 21:15:15,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 27951104. Throughput: 0: 1697.2, 1: 1690.9. Samples: 6997114. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:15:15,557][97672] Avg episode reward: [(0, '-4.460'), (1, '15.940')] -[2023-10-10 21:15:15,558][98439] Saving new best policy, reward=15.940! -[2023-10-10 21:15:16,751][98559] Updated weights for policy 0, policy_version 13640 (0.0007) -[2023-10-10 21:15:16,782][98560] Updated weights for policy 1, policy_version 13672 (0.0008) -[2023-10-10 21:15:17,122][98559] Updated weights for policy 0, policy_version 13650 (0.0008) -[2023-10-10 21:15:17,161][98560] Updated weights for policy 1, policy_version 13682 (0.0008) -[2023-10-10 21:15:17,493][98559] Updated weights for policy 0, policy_version 13660 (0.0009) -[2023-10-10 21:15:17,533][98560] Updated weights for policy 1, policy_version 13692 (0.0008) -[2023-10-10 21:15:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 28016640. Throughput: 0: 1708.3, 1: 1696.9. Samples: 7018316. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:15:20,557][97672] Avg episode reward: [(0, '-4.460'), (1, '16.200')] -[2023-10-10 21:15:20,567][98439] Saving new best policy, reward=16.200! -[2023-10-10 21:15:21,338][98560] Updated weights for policy 1, policy_version 13702 (0.0009) -[2023-10-10 21:15:21,412][98559] Updated weights for policy 0, policy_version 13670 (0.0007) -[2023-10-10 21:15:21,696][98560] Updated weights for policy 1, policy_version 13712 (0.0007) -[2023-10-10 21:15:21,784][98559] Updated weights for policy 0, policy_version 13680 (0.0008) -[2023-10-10 21:15:22,068][98560] Updated weights for policy 1, policy_version 13722 (0.0009) -[2023-10-10 21:15:22,158][98559] Updated weights for policy 0, policy_version 13690 (0.0009) -[2023-10-10 21:15:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 28082176. Throughput: 0: 1694.0, 1: 1674.3. Samples: 7027622. Policy #0 lag: (min: 21.0, avg: 29.0, max: 53.0) -[2023-10-10 21:15:25,557][97672] Avg episode reward: [(0, '-4.460'), (1, '16.480')] -[2023-10-10 21:15:25,559][98439] Saving new best policy, reward=16.480! -[2023-10-10 21:15:26,074][98560] Updated weights for policy 1, policy_version 13732 (0.0008) -[2023-10-10 21:15:26,081][98559] Updated weights for policy 0, policy_version 13700 (0.0009) -[2023-10-10 21:15:26,446][98560] Updated weights for policy 1, policy_version 13742 (0.0007) -[2023-10-10 21:15:26,458][98559] Updated weights for policy 0, policy_version 13710 (0.0010) -[2023-10-10 21:15:26,809][98560] Updated weights for policy 1, policy_version 13752 (0.0007) -[2023-10-10 21:15:26,840][98559] Updated weights for policy 0, policy_version 13720 (0.0008) -[2023-10-10 21:15:30,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 28147712. Throughput: 0: 1717.1, 1: 1696.5. Samples: 7048668. Policy #0 lag: (min: 21.0, avg: 29.0, max: 53.0) -[2023-10-10 21:15:30,557][97672] Avg episode reward: [(0, '-4.460'), (1, '16.640')] -[2023-10-10 21:15:30,559][98439] Saving new best policy, reward=16.640! -[2023-10-10 21:15:30,683][98559] Updated weights for policy 0, policy_version 13730 (0.0009) -[2023-10-10 21:15:30,987][98560] Updated weights for policy 1, policy_version 13762 (0.0010) -[2023-10-10 21:15:31,052][98559] Updated weights for policy 0, policy_version 13740 (0.0007) -[2023-10-10 21:15:31,360][98560] Updated weights for policy 1, policy_version 13772 (0.0007) -[2023-10-10 21:15:31,429][98559] Updated weights for policy 0, policy_version 13750 (0.0007) -[2023-10-10 21:15:31,738][98560] Updated weights for policy 1, policy_version 13782 (0.0007) -[2023-10-10 21:15:31,804][98559] Updated weights for policy 0, policy_version 13760 (0.0007) -[2023-10-10 21:15:32,105][98560] Updated weights for policy 1, policy_version 13792 (0.0008) -[2023-10-10 21:15:35,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 28213248. Throughput: 0: 1723.5, 1: 1696.3. Samples: 7069552. Policy #0 lag: (min: 21.0, avg: 29.0, max: 53.0) -[2023-10-10 21:15:35,556][97672] Avg episode reward: [(0, '-4.460'), (1, '16.840')] -[2023-10-10 21:15:35,566][98439] Saving new best policy, reward=16.840! -[2023-10-10 21:15:35,785][98559] Updated weights for policy 0, policy_version 13770 (0.0007) -[2023-10-10 21:15:36,105][98560] Updated weights for policy 1, policy_version 13802 (0.0008) -[2023-10-10 21:15:36,171][98559] Updated weights for policy 0, policy_version 13780 (0.0007) -[2023-10-10 21:15:36,475][98560] Updated weights for policy 1, policy_version 13812 (0.0008) -[2023-10-10 21:15:36,537][98559] Updated weights for policy 0, policy_version 13790 (0.0008) -[2023-10-10 21:15:36,852][98560] Updated weights for policy 1, policy_version 13822 (0.0008) -[2023-10-10 21:15:40,521][98559] Updated weights for policy 0, policy_version 13800 (0.0009) -[2023-10-10 21:15:40,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 28278784. Throughput: 0: 1722.4, 1: 1678.8. Samples: 7078836. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-10 21:15:40,556][97672] Avg episode reward: [(0, '-4.460'), (1, '16.900')] -[2023-10-10 21:15:40,847][98560] Updated weights for policy 1, policy_version 13832 (0.0008) -[2023-10-10 21:15:40,890][98559] Updated weights for policy 0, policy_version 13810 (0.0008) -[2023-10-10 21:15:41,212][98560] Updated weights for policy 1, policy_version 13842 (0.0008) -[2023-10-10 21:15:41,257][98559] Updated weights for policy 0, policy_version 13820 (0.0008) -[2023-10-10 21:15:41,577][98560] Updated weights for policy 1, policy_version 13852 (0.0008) -[2023-10-10 21:15:41,719][98439] Saving new best policy, reward=16.900! -[2023-10-10 21:15:45,110][98559] Updated weights for policy 0, policy_version 13830 (0.0009) -[2023-10-10 21:15:45,484][98559] Updated weights for policy 0, policy_version 13840 (0.0007) -[2023-10-10 21:15:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 28344320. Throughput: 0: 1732.1, 1: 1695.1. Samples: 7100092. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-10 21:15:45,556][97672] Avg episode reward: [(0, '-4.460'), (1, '16.880')] -[2023-10-10 21:15:45,713][98560] Updated weights for policy 1, policy_version 13862 (0.0009) -[2023-10-10 21:15:45,860][98559] Updated weights for policy 0, policy_version 13850 (0.0008) -[2023-10-10 21:15:46,080][98560] Updated weights for policy 1, policy_version 13872 (0.0008) -[2023-10-10 21:15:46,458][98560] Updated weights for policy 1, policy_version 13882 (0.0007) -[2023-10-10 21:15:49,779][98559] Updated weights for policy 0, policy_version 13860 (0.0008) -[2023-10-10 21:15:50,152][98559] Updated weights for policy 0, policy_version 13870 (0.0009) -[2023-10-10 21:15:50,419][98560] Updated weights for policy 1, policy_version 13892 (0.0009) -[2023-10-10 21:15:50,521][98559] Updated weights for policy 0, policy_version 13880 (0.0007) -[2023-10-10 21:15:50,556][97672] Fps is (10 sec: 13106.6, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 28409856. Throughput: 0: 1718.8, 1: 1690.1. Samples: 7120262. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-10 21:15:50,558][97672] Avg episode reward: [(0, '-4.460'), (1, '17.100')] -[2023-10-10 21:15:50,786][98560] Updated weights for policy 1, policy_version 13902 (0.0009) -[2023-10-10 21:15:51,160][98560] Updated weights for policy 1, policy_version 13912 (0.0009) -[2023-10-10 21:15:51,453][98439] Saving new best policy, reward=17.100! -[2023-10-10 21:15:54,392][98559] Updated weights for policy 0, policy_version 13890 (0.0008) -[2023-10-10 21:15:54,756][98559] Updated weights for policy 0, policy_version 13900 (0.0008) -[2023-10-10 21:15:55,132][98559] Updated weights for policy 0, policy_version 13910 (0.0007) -[2023-10-10 21:15:55,252][98560] Updated weights for policy 1, policy_version 13922 (0.0007) -[2023-10-10 21:15:55,493][98559] Updated weights for policy 0, policy_version 13920 (0.0008) -[2023-10-10 21:15:55,556][97672] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 28508160. Throughput: 0: 1736.9, 1: 1682.0. Samples: 7130228. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-10 21:15:55,557][97672] Avg episode reward: [(0, '-4.460'), (1, '17.240')] -[2023-10-10 21:15:55,627][98560] Updated weights for policy 1, policy_version 13932 (0.0007) -[2023-10-10 21:15:56,001][98560] Updated weights for policy 1, policy_version 13942 (0.0008) -[2023-10-10 21:15:56,366][98439] Saving new best policy, reward=17.240! -[2023-10-10 21:15:56,367][98560] Updated weights for policy 1, policy_version 13952 (0.0007) -[2023-10-10 21:15:59,634][98559] Updated weights for policy 0, policy_version 13930 (0.0011) -[2023-10-10 21:15:59,999][98559] Updated weights for policy 0, policy_version 13940 (0.0009) -[2023-10-10 21:16:00,272][98560] Updated weights for policy 1, policy_version 13962 (0.0008) -[2023-10-10 21:16:00,371][98559] Updated weights for policy 0, policy_version 13950 (0.0009) -[2023-10-10 21:16:00,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 28573696. Throughput: 0: 1727.9, 1: 1690.1. Samples: 7150924. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-10 21:16:00,558][97672] Avg episode reward: [(0, '-4.480'), (1, '17.420')] -[2023-10-10 21:16:00,640][98560] Updated weights for policy 1, policy_version 13972 (0.0009) -[2023-10-10 21:16:01,006][98560] Updated weights for policy 1, policy_version 13982 (0.0009) -[2023-10-10 21:16:01,076][98439] Saving new best policy, reward=17.420! -[2023-10-10 21:16:04,301][98559] Updated weights for policy 0, policy_version 13960 (0.0009) -[2023-10-10 21:16:04,680][98559] Updated weights for policy 0, policy_version 13970 (0.0010) -[2023-10-10 21:16:05,058][98559] Updated weights for policy 0, policy_version 13980 (0.0008) -[2023-10-10 21:16:05,157][98560] Updated weights for policy 1, policy_version 13992 (0.0008) -[2023-10-10 21:16:05,529][98560] Updated weights for policy 1, policy_version 14002 (0.0009) -[2023-10-10 21:16:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 28639232. Throughput: 0: 1699.1, 1: 1692.5. Samples: 7170940. Policy #0 lag: (min: 24.0, avg: 51.9, max: 56.0) -[2023-10-10 21:16:05,557][97672] Avg episode reward: [(0, '-4.560'), (1, '17.600')] -[2023-10-10 21:16:05,893][98560] Updated weights for policy 1, policy_version 14012 (0.0010) -[2023-10-10 21:16:06,041][98439] Saving new best policy, reward=17.600! -[2023-10-10 21:16:08,894][98559] Updated weights for policy 0, policy_version 13990 (0.0008) -[2023-10-10 21:16:09,264][98559] Updated weights for policy 0, policy_version 14000 (0.0008) -[2023-10-10 21:16:09,632][98559] Updated weights for policy 0, policy_version 14010 (0.0007) -[2023-10-10 21:16:10,047][98560] Updated weights for policy 1, policy_version 14022 (0.0010) -[2023-10-10 21:16:10,420][98560] Updated weights for policy 1, policy_version 14032 (0.0008) -[2023-10-10 21:16:10,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 28704768. Throughput: 0: 1731.4, 1: 1687.9. Samples: 7181488. Policy #0 lag: (min: 24.0, avg: 51.9, max: 56.0) -[2023-10-10 21:16:10,556][97672] Avg episode reward: [(0, '-4.560'), (1, '17.740')] -[2023-10-10 21:16:10,787][98560] Updated weights for policy 1, policy_version 14042 (0.0008) -[2023-10-10 21:16:11,005][98439] Saving new best policy, reward=17.740! -[2023-10-10 21:16:13,614][98559] Updated weights for policy 0, policy_version 14020 (0.0009) -[2023-10-10 21:16:13,991][98559] Updated weights for policy 0, policy_version 14030 (0.0008) -[2023-10-10 21:16:14,360][98559] Updated weights for policy 0, policy_version 14040 (0.0008) -[2023-10-10 21:16:14,820][98560] Updated weights for policy 1, policy_version 14052 (0.0007) -[2023-10-10 21:16:15,198][98560] Updated weights for policy 1, policy_version 14062 (0.0009) -[2023-10-10 21:16:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 28770304. Throughput: 0: 1705.4, 1: 1692.9. Samples: 7201594. Policy #0 lag: (min: 24.0, avg: 51.9, max: 56.0) -[2023-10-10 21:16:15,557][97672] Avg episode reward: [(0, '-4.560'), (1, '17.940')] -[2023-10-10 21:16:15,573][98560] Updated weights for policy 1, policy_version 14072 (0.0009) -[2023-10-10 21:16:15,859][98439] Saving new best policy, reward=17.940! -[2023-10-10 21:16:18,278][98559] Updated weights for policy 0, policy_version 14050 (0.0007) -[2023-10-10 21:16:18,649][98559] Updated weights for policy 0, policy_version 14060 (0.0008) -[2023-10-10 21:16:19,031][98559] Updated weights for policy 0, policy_version 14070 (0.0010) -[2023-10-10 21:16:19,392][98559] Updated weights for policy 0, policy_version 14080 (0.0009) -[2023-10-10 21:16:19,410][98560] Updated weights for policy 1, policy_version 14082 (0.0008) -[2023-10-10 21:16:19,780][98560] Updated weights for policy 1, policy_version 14092 (0.0009) -[2023-10-10 21:16:20,144][98560] Updated weights for policy 1, policy_version 14102 (0.0007) -[2023-10-10 21:16:20,519][98560] Updated weights for policy 1, policy_version 14112 (0.0007) -[2023-10-10 21:16:20,556][97672] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 28868608. Throughput: 0: 1698.6, 1: 1692.9. Samples: 7222170. Policy #0 lag: (min: 3.0, avg: 3.4, max: 16.0) -[2023-10-10 21:16:20,556][97672] Avg episode reward: [(0, '-4.560'), (1, '17.640')] -[2023-10-10 21:16:23,450][98559] Updated weights for policy 0, policy_version 14090 (0.0008) -[2023-10-10 21:16:23,832][98559] Updated weights for policy 0, policy_version 14100 (0.0008) -[2023-10-10 21:16:24,202][98559] Updated weights for policy 0, policy_version 14110 (0.0009) -[2023-10-10 21:16:24,618][98560] Updated weights for policy 1, policy_version 14122 (0.0008) -[2023-10-10 21:16:24,982][98560] Updated weights for policy 1, policy_version 14132 (0.0009) -[2023-10-10 21:16:25,345][98560] Updated weights for policy 1, policy_version 14142 (0.0010) -[2023-10-10 21:16:25,556][97672] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 28934144. Throughput: 0: 1720.0, 1: 1700.1. Samples: 7232740. Policy #0 lag: (min: 3.0, avg: 3.4, max: 16.0) -[2023-10-10 21:16:25,556][97672] Avg episode reward: [(0, '-4.560'), (1, '17.620')] -[2023-10-10 21:16:28,152][98559] Updated weights for policy 0, policy_version 14120 (0.0011) -[2023-10-10 21:16:28,523][98559] Updated weights for policy 0, policy_version 14130 (0.0011) -[2023-10-10 21:16:28,904][98559] Updated weights for policy 0, policy_version 14140 (0.0010) -[2023-10-10 21:16:29,319][98560] Updated weights for policy 1, policy_version 14152 (0.0009) -[2023-10-10 21:16:29,699][98560] Updated weights for policy 1, policy_version 14162 (0.0011) -[2023-10-10 21:16:30,067][98560] Updated weights for policy 1, policy_version 14172 (0.0009) -[2023-10-10 21:16:30,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 28999680. Throughput: 0: 1698.1, 1: 1696.0. Samples: 7252828. Policy #0 lag: (min: 3.0, avg: 3.4, max: 16.0) -[2023-10-10 21:16:30,557][97672] Avg episode reward: [(0, '-4.440'), (1, '17.540')] -[2023-10-10 21:16:30,559][98385] Saving new best policy, reward=-4.440! -[2023-10-10 21:16:32,967][98559] Updated weights for policy 0, policy_version 14150 (0.0008) -[2023-10-10 21:16:33,344][98559] Updated weights for policy 0, policy_version 14160 (0.0008) -[2023-10-10 21:16:33,718][98559] Updated weights for policy 0, policy_version 14170 (0.0010) -[2023-10-10 21:16:34,100][98560] Updated weights for policy 1, policy_version 14182 (0.0007) -[2023-10-10 21:16:34,471][98560] Updated weights for policy 1, policy_version 14192 (0.0010) -[2023-10-10 21:16:34,840][98560] Updated weights for policy 1, policy_version 14202 (0.0008) -[2023-10-10 21:16:35,556][97672] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 29065216. Throughput: 0: 1709.6, 1: 1683.5. Samples: 7272952. Policy #0 lag: (min: 30.0, avg: 35.6, max: 62.0) -[2023-10-10 21:16:35,557][97672] Avg episode reward: [(0, '-4.440'), (1, '17.540')] -[2023-10-10 21:16:35,570][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000014176_14516224.pth... -[2023-10-10 21:16:35,570][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000014208_14548992.pth... -[2023-10-10 21:16:35,607][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000012608_12910592.pth -[2023-10-10 21:16:35,609][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000012576_12877824.pth -[2023-10-10 21:16:37,733][98559] Updated weights for policy 0, policy_version 14180 (0.0010) -[2023-10-10 21:16:38,105][98559] Updated weights for policy 0, policy_version 14190 (0.0010) -[2023-10-10 21:16:38,482][98559] Updated weights for policy 0, policy_version 14200 (0.0011) -[2023-10-10 21:16:38,901][98560] Updated weights for policy 1, policy_version 14212 (0.0010) -[2023-10-10 21:16:39,279][98560] Updated weights for policy 1, policy_version 14222 (0.0008) -[2023-10-10 21:16:39,639][98560] Updated weights for policy 1, policy_version 14232 (0.0007) -[2023-10-10 21:16:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 29130752. Throughput: 0: 1699.2, 1: 1702.9. Samples: 7283322. Policy #0 lag: (min: 30.0, avg: 35.6, max: 62.0) -[2023-10-10 21:16:40,557][97672] Avg episode reward: [(0, '-4.440'), (1, '17.500')] -[2023-10-10 21:16:42,405][98559] Updated weights for policy 0, policy_version 14210 (0.0008) -[2023-10-10 21:16:42,778][98559] Updated weights for policy 0, policy_version 14220 (0.0008) -[2023-10-10 21:16:43,143][98559] Updated weights for policy 0, policy_version 14230 (0.0009) -[2023-10-10 21:16:43,513][98559] Updated weights for policy 0, policy_version 14240 (0.0010) -[2023-10-10 21:16:43,587][98560] Updated weights for policy 1, policy_version 14242 (0.0011) -[2023-10-10 21:16:43,949][98560] Updated weights for policy 1, policy_version 14252 (0.0009) -[2023-10-10 21:16:44,320][98560] Updated weights for policy 1, policy_version 14262 (0.0007) -[2023-10-10 21:16:44,688][98560] Updated weights for policy 1, policy_version 14272 (0.0009) -[2023-10-10 21:16:45,556][97672] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 29196288. Throughput: 0: 1699.3, 1: 1702.0. Samples: 7303984. Policy #0 lag: (min: 30.0, avg: 35.6, max: 62.0) -[2023-10-10 21:16:45,556][97672] Avg episode reward: [(0, '-4.440'), (1, '17.640')] -[2023-10-10 21:16:47,514][98559] Updated weights for policy 0, policy_version 14250 (0.0007) -[2023-10-10 21:16:47,890][98559] Updated weights for policy 0, policy_version 14260 (0.0009) -[2023-10-10 21:16:48,258][98559] Updated weights for policy 0, policy_version 14270 (0.0010) -[2023-10-10 21:16:48,742][98560] Updated weights for policy 1, policy_version 14282 (0.0008) -[2023-10-10 21:16:49,116][98560] Updated weights for policy 1, policy_version 14292 (0.0009) -[2023-10-10 21:16:49,494][98560] Updated weights for policy 1, policy_version 14302 (0.0008) -[2023-10-10 21:16:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 29261824. Throughput: 0: 1726.9, 1: 1674.0. Samples: 7323982. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:16:50,557][97672] Avg episode reward: [(0, '-4.440'), (1, '17.640')] -[2023-10-10 21:16:52,165][98559] Updated weights for policy 0, policy_version 14280 (0.0008) -[2023-10-10 21:16:52,537][98559] Updated weights for policy 0, policy_version 14290 (0.0007) -[2023-10-10 21:16:52,900][98559] Updated weights for policy 0, policy_version 14300 (0.0008) -[2023-10-10 21:16:53,645][98560] Updated weights for policy 1, policy_version 14312 (0.0009) -[2023-10-10 21:16:54,023][98560] Updated weights for policy 1, policy_version 14322 (0.0010) -[2023-10-10 21:16:54,398][98560] Updated weights for policy 1, policy_version 14332 (0.0011) -[2023-10-10 21:16:55,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 29327360. Throughput: 0: 1693.1, 1: 1708.5. Samples: 7334560. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:16:55,557][97672] Avg episode reward: [(0, '-4.320'), (1, '17.660')] -[2023-10-10 21:16:55,558][98385] Saving new best policy, reward=-4.320! -[2023-10-10 21:16:56,695][98559] Updated weights for policy 0, policy_version 14310 (0.0008) -[2023-10-10 21:16:57,062][98559] Updated weights for policy 0, policy_version 14320 (0.0008) -[2023-10-10 21:16:57,438][98559] Updated weights for policy 0, policy_version 14330 (0.0008) -[2023-10-10 21:16:58,301][98560] Updated weights for policy 1, policy_version 14342 (0.0008) -[2023-10-10 21:16:58,672][98560] Updated weights for policy 1, policy_version 14352 (0.0008) -[2023-10-10 21:16:59,048][98560] Updated weights for policy 1, policy_version 14362 (0.0008) -[2023-10-10 21:17:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 29392896. Throughput: 0: 1723.6, 1: 1695.1. Samples: 7355436. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:17:00,557][97672] Avg episode reward: [(0, '-4.340'), (1, '17.900')] -[2023-10-10 21:17:01,357][98559] Updated weights for policy 0, policy_version 14340 (0.0008) -[2023-10-10 21:17:01,723][98559] Updated weights for policy 0, policy_version 14350 (0.0008) -[2023-10-10 21:17:02,090][98559] Updated weights for policy 0, policy_version 14360 (0.0009) -[2023-10-10 21:17:02,988][98560] Updated weights for policy 1, policy_version 14372 (0.0008) -[2023-10-10 21:17:03,351][98560] Updated weights for policy 1, policy_version 14382 (0.0011) -[2023-10-10 21:17:03,727][98560] Updated weights for policy 1, policy_version 14392 (0.0011) -[2023-10-10 21:17:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 29458432. Throughput: 0: 1729.9, 1: 1683.8. Samples: 7375788. Policy #0 lag: (min: 27.0, avg: 27.3, max: 39.0) -[2023-10-10 21:17:05,557][97672] Avg episode reward: [(0, '-4.260'), (1, '17.900')] -[2023-10-10 21:17:05,568][98385] Saving new best policy, reward=-4.260! -[2023-10-10 21:17:06,035][98559] Updated weights for policy 0, policy_version 14370 (0.0008) -[2023-10-10 21:17:06,410][98559] Updated weights for policy 0, policy_version 14380 (0.0010) -[2023-10-10 21:17:06,783][98559] Updated weights for policy 0, policy_version 14390 (0.0009) -[2023-10-10 21:17:07,150][98559] Updated weights for policy 0, policy_version 14400 (0.0008) -[2023-10-10 21:17:07,559][98560] Updated weights for policy 1, policy_version 14402 (0.0009) -[2023-10-10 21:17:07,931][98560] Updated weights for policy 1, policy_version 14412 (0.0007) -[2023-10-10 21:17:08,292][98560] Updated weights for policy 1, policy_version 14422 (0.0007) -[2023-10-10 21:17:08,670][98560] Updated weights for policy 1, policy_version 14432 (0.0007) -[2023-10-10 21:17:10,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 29523968. Throughput: 0: 1704.5, 1: 1705.8. Samples: 7386204. Policy #0 lag: (min: 27.0, avg: 27.3, max: 39.0) -[2023-10-10 21:17:10,557][97672] Avg episode reward: [(0, '-4.260'), (1, '17.920')] -[2023-10-10 21:17:11,279][98559] Updated weights for policy 0, policy_version 14410 (0.0010) -[2023-10-10 21:17:11,647][98559] Updated weights for policy 0, policy_version 14420 (0.0008) -[2023-10-10 21:17:12,014][98559] Updated weights for policy 0, policy_version 14430 (0.0007) -[2023-10-10 21:17:12,653][98560] Updated weights for policy 1, policy_version 14442 (0.0008) -[2023-10-10 21:17:13,027][98560] Updated weights for policy 1, policy_version 14452 (0.0007) -[2023-10-10 21:17:13,392][98560] Updated weights for policy 1, policy_version 14462 (0.0010) -[2023-10-10 21:17:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 29589504. Throughput: 0: 1721.4, 1: 1685.4. Samples: 7406134. Policy #0 lag: (min: 27.0, avg: 27.3, max: 39.0) -[2023-10-10 21:17:15,557][97672] Avg episode reward: [(0, '-4.260'), (1, '18.120')] -[2023-10-10 21:17:15,558][98439] Saving new best policy, reward=18.120! -[2023-10-10 21:17:16,071][98559] Updated weights for policy 0, policy_version 14440 (0.0008) -[2023-10-10 21:17:16,436][98559] Updated weights for policy 0, policy_version 14450 (0.0007) -[2023-10-10 21:17:16,814][98559] Updated weights for policy 0, policy_version 14460 (0.0007) -[2023-10-10 21:17:17,423][98560] Updated weights for policy 1, policy_version 14472 (0.0009) -[2023-10-10 21:17:17,789][98560] Updated weights for policy 1, policy_version 14482 (0.0009) -[2023-10-10 21:17:18,168][98560] Updated weights for policy 1, policy_version 14492 (0.0007) -[2023-10-10 21:17:20,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 29655040. Throughput: 0: 1727.2, 1: 1707.6. Samples: 7427520. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-10-10 21:17:20,557][97672] Avg episode reward: [(0, '-4.260'), (1, '18.200')] -[2023-10-10 21:17:20,567][98439] Saving new best policy, reward=18.200! -[2023-10-10 21:17:20,776][98559] Updated weights for policy 0, policy_version 14470 (0.0009) -[2023-10-10 21:17:21,151][98559] Updated weights for policy 0, policy_version 14480 (0.0008) -[2023-10-10 21:17:21,525][98559] Updated weights for policy 0, policy_version 14490 (0.0008) -[2023-10-10 21:17:22,063][98560] Updated weights for policy 1, policy_version 14502 (0.0009) -[2023-10-10 21:17:22,435][98560] Updated weights for policy 1, policy_version 14512 (0.0009) -[2023-10-10 21:17:22,809][98560] Updated weights for policy 1, policy_version 14522 (0.0009) -[2023-10-10 21:17:25,506][98559] Updated weights for policy 0, policy_version 14500 (0.0007) -[2023-10-10 21:17:25,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 29720576. Throughput: 0: 1717.0, 1: 1700.5. Samples: 7437108. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-10-10 21:17:25,557][97672] Avg episode reward: [(0, '-4.260'), (1, '18.100')] -[2023-10-10 21:17:25,883][98559] Updated weights for policy 0, policy_version 14510 (0.0007) -[2023-10-10 21:17:26,250][98559] Updated weights for policy 0, policy_version 14520 (0.0008) -[2023-10-10 21:17:27,014][98560] Updated weights for policy 1, policy_version 14532 (0.0009) -[2023-10-10 21:17:27,388][98560] Updated weights for policy 1, policy_version 14542 (0.0007) -[2023-10-10 21:17:27,762][98560] Updated weights for policy 1, policy_version 14552 (0.0009) -[2023-10-10 21:17:30,301][98559] Updated weights for policy 0, policy_version 14530 (0.0008) -[2023-10-10 21:17:30,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 29786112. Throughput: 0: 1724.1, 1: 1689.6. Samples: 7457604. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-10-10 21:17:30,557][97672] Avg episode reward: [(0, '-4.180'), (1, '17.900')] -[2023-10-10 21:17:30,662][98559] Updated weights for policy 0, policy_version 14540 (0.0009) -[2023-10-10 21:17:31,041][98559] Updated weights for policy 0, policy_version 14550 (0.0009) -[2023-10-10 21:17:31,416][98385] Saving new best policy, reward=-4.180! -[2023-10-10 21:17:31,417][98559] Updated weights for policy 0, policy_version 14560 (0.0008) -[2023-10-10 21:17:31,681][98560] Updated weights for policy 1, policy_version 14562 (0.0008) -[2023-10-10 21:17:32,051][98560] Updated weights for policy 1, policy_version 14572 (0.0007) -[2023-10-10 21:17:32,427][98560] Updated weights for policy 1, policy_version 14582 (0.0009) -[2023-10-10 21:17:32,800][98560] Updated weights for policy 1, policy_version 14592 (0.0009) -[2023-10-10 21:17:35,488][98559] Updated weights for policy 0, policy_version 14570 (0.0007) -[2023-10-10 21:17:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 29851648. Throughput: 0: 1713.5, 1: 1717.2. Samples: 7478362. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:17:35,557][97672] Avg episode reward: [(0, '-4.180'), (1, '17.800')] -[2023-10-10 21:17:35,861][98559] Updated weights for policy 0, policy_version 14580 (0.0008) -[2023-10-10 21:17:36,239][98559] Updated weights for policy 0, policy_version 14590 (0.0008) -[2023-10-10 21:17:36,705][98560] Updated weights for policy 1, policy_version 14602 (0.0009) -[2023-10-10 21:17:37,071][98560] Updated weights for policy 1, policy_version 14612 (0.0009) -[2023-10-10 21:17:37,448][98560] Updated weights for policy 1, policy_version 14622 (0.0010) -[2023-10-10 21:17:40,253][98559] Updated weights for policy 0, policy_version 14600 (0.0007) -[2023-10-10 21:17:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 29917184. Throughput: 0: 1719.5, 1: 1689.2. Samples: 7487950. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:17:40,556][97672] Avg episode reward: [(0, '-4.180'), (1, '18.000')] -[2023-10-10 21:17:40,623][98559] Updated weights for policy 0, policy_version 14610 (0.0007) -[2023-10-10 21:17:40,993][98559] Updated weights for policy 0, policy_version 14620 (0.0007) -[2023-10-10 21:17:41,374][98560] Updated weights for policy 1, policy_version 14632 (0.0007) -[2023-10-10 21:17:41,738][98560] Updated weights for policy 1, policy_version 14642 (0.0008) -[2023-10-10 21:17:42,109][98560] Updated weights for policy 1, policy_version 14652 (0.0009) -[2023-10-10 21:17:44,879][98559] Updated weights for policy 0, policy_version 14630 (0.0008) -[2023-10-10 21:17:45,265][98559] Updated weights for policy 0, policy_version 14640 (0.0008) -[2023-10-10 21:17:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 29982720. Throughput: 0: 1716.2, 1: 1702.8. Samples: 7509290. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:17:45,556][97672] Avg episode reward: [(0, '-4.180'), (1, '18.180')] -[2023-10-10 21:17:45,632][98559] Updated weights for policy 0, policy_version 14650 (0.0007) -[2023-10-10 21:17:46,202][98560] Updated weights for policy 1, policy_version 14662 (0.0009) -[2023-10-10 21:17:46,577][98560] Updated weights for policy 1, policy_version 14672 (0.0008) -[2023-10-10 21:17:46,935][98560] Updated weights for policy 1, policy_version 14682 (0.0010) -[2023-10-10 21:17:49,618][98559] Updated weights for policy 0, policy_version 14660 (0.0009) -[2023-10-10 21:17:49,982][98559] Updated weights for policy 0, policy_version 14670 (0.0007) -[2023-10-10 21:17:50,359][98559] Updated weights for policy 0, policy_version 14680 (0.0008) -[2023-10-10 21:17:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 30048256. Throughput: 0: 1692.7, 1: 1717.3. Samples: 7529234. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:17:50,556][97672] Avg episode reward: [(0, '-4.080'), (1, '18.160')] -[2023-10-10 21:17:50,657][98385] Saving new best policy, reward=-4.080! -[2023-10-10 21:17:50,877][98560] Updated weights for policy 1, policy_version 14692 (0.0007) -[2023-10-10 21:17:51,251][98560] Updated weights for policy 1, policy_version 14702 (0.0007) -[2023-10-10 21:17:51,617][98560] Updated weights for policy 1, policy_version 14712 (0.0007) -[2023-10-10 21:17:54,287][98559] Updated weights for policy 0, policy_version 14690 (0.0008) -[2023-10-10 21:17:54,661][98559] Updated weights for policy 0, policy_version 14700 (0.0008) -[2023-10-10 21:17:55,035][98559] Updated weights for policy 0, policy_version 14710 (0.0008) -[2023-10-10 21:17:55,412][98559] Updated weights for policy 0, policy_version 14720 (0.0007) -[2023-10-10 21:17:55,556][97672] Fps is (10 sec: 16383.8, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 30146560. Throughput: 0: 1718.6, 1: 1689.2. Samples: 7539558. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:17:55,557][97672] Avg episode reward: [(0, '-4.080'), (1, '18.380')] -[2023-10-10 21:17:55,699][98560] Updated weights for policy 1, policy_version 14722 (0.0008) -[2023-10-10 21:17:56,063][98560] Updated weights for policy 1, policy_version 14732 (0.0008) -[2023-10-10 21:17:56,430][98560] Updated weights for policy 1, policy_version 14742 (0.0008) -[2023-10-10 21:17:56,799][98560] Updated weights for policy 1, policy_version 14752 (0.0007) -[2023-10-10 21:17:56,799][98439] Saving new best policy, reward=18.380! -[2023-10-10 21:17:59,415][98559] Updated weights for policy 0, policy_version 14730 (0.0010) -[2023-10-10 21:17:59,786][98559] Updated weights for policy 0, policy_version 14740 (0.0009) -[2023-10-10 21:18:00,162][98559] Updated weights for policy 0, policy_version 14750 (0.0007) -[2023-10-10 21:18:00,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 30212096. Throughput: 0: 1709.8, 1: 1710.6. Samples: 7560052. Policy #0 lag: (min: 5.0, avg: 13.0, max: 37.0) -[2023-10-10 21:18:00,556][97672] Avg episode reward: [(0, '-4.000'), (1, '18.440')] -[2023-10-10 21:18:00,557][98385] Saving new best policy, reward=-4.000! -[2023-10-10 21:18:00,921][98560] Updated weights for policy 1, policy_version 14762 (0.0009) -[2023-10-10 21:18:01,290][98560] Updated weights for policy 1, policy_version 14772 (0.0011) -[2023-10-10 21:18:01,664][98560] Updated weights for policy 1, policy_version 14782 (0.0010) -[2023-10-10 21:18:01,730][98439] Saving new best policy, reward=18.440! -[2023-10-10 21:18:03,996][98559] Updated weights for policy 0, policy_version 14760 (0.0007) -[2023-10-10 21:18:04,365][98559] Updated weights for policy 0, policy_version 14770 (0.0008) -[2023-10-10 21:18:04,741][98559] Updated weights for policy 0, policy_version 14780 (0.0010) -[2023-10-10 21:18:05,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 30277632. Throughput: 0: 1687.5, 1: 1700.8. Samples: 7579992. Policy #0 lag: (min: 5.0, avg: 13.0, max: 37.0) -[2023-10-10 21:18:05,557][97672] Avg episode reward: [(0, '-4.000'), (1, '18.360')] -[2023-10-10 21:18:05,796][98560] Updated weights for policy 1, policy_version 14792 (0.0009) -[2023-10-10 21:18:06,176][98560] Updated weights for policy 1, policy_version 14802 (0.0008) -[2023-10-10 21:18:06,540][98560] Updated weights for policy 1, policy_version 14812 (0.0009) -[2023-10-10 21:18:08,812][98559] Updated weights for policy 0, policy_version 14790 (0.0010) -[2023-10-10 21:18:09,177][98559] Updated weights for policy 0, policy_version 14800 (0.0008) -[2023-10-10 21:18:09,562][98559] Updated weights for policy 0, policy_version 14810 (0.0008) -[2023-10-10 21:18:10,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 30343168. Throughput: 0: 1717.2, 1: 1691.3. Samples: 7590490. Policy #0 lag: (min: 5.0, avg: 13.0, max: 37.0) -[2023-10-10 21:18:10,557][97672] Avg episode reward: [(0, '-3.960'), (1, '18.220')] -[2023-10-10 21:18:10,557][98385] Saving new best policy, reward=-3.960! -[2023-10-10 21:18:10,579][98560] Updated weights for policy 1, policy_version 14822 (0.0010) -[2023-10-10 21:18:10,950][98560] Updated weights for policy 1, policy_version 14832 (0.0011) -[2023-10-10 21:18:11,317][98560] Updated weights for policy 1, policy_version 14842 (0.0010) -[2023-10-10 21:18:13,574][98559] Updated weights for policy 0, policy_version 14820 (0.0010) -[2023-10-10 21:18:13,952][98559] Updated weights for policy 0, policy_version 14830 (0.0009) -[2023-10-10 21:18:14,322][98559] Updated weights for policy 0, policy_version 14840 (0.0008) -[2023-10-10 21:18:15,347][98560] Updated weights for policy 1, policy_version 14852 (0.0010) -[2023-10-10 21:18:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 30408704. Throughput: 0: 1692.2, 1: 1701.3. Samples: 7610314. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:18:15,557][97672] Avg episode reward: [(0, '-3.960'), (1, '18.140')] -[2023-10-10 21:18:15,719][98560] Updated weights for policy 1, policy_version 14862 (0.0008) -[2023-10-10 21:18:16,085][98560] Updated weights for policy 1, policy_version 14872 (0.0008) -[2023-10-10 21:18:18,188][98559] Updated weights for policy 0, policy_version 14850 (0.0008) -[2023-10-10 21:18:18,561][98559] Updated weights for policy 0, policy_version 14860 (0.0011) -[2023-10-10 21:18:18,923][98559] Updated weights for policy 0, policy_version 14870 (0.0009) -[2023-10-10 21:18:19,294][98559] Updated weights for policy 0, policy_version 14880 (0.0009) -[2023-10-10 21:18:20,093][98560] Updated weights for policy 1, policy_version 14882 (0.0007) -[2023-10-10 21:18:20,462][98560] Updated weights for policy 1, policy_version 14892 (0.0008) -[2023-10-10 21:18:20,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 30474240. Throughput: 0: 1691.4, 1: 1706.2. Samples: 7631256. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:18:20,557][97672] Avg episode reward: [(0, '-3.960'), (1, '18.040')] -[2023-10-10 21:18:20,830][98560] Updated weights for policy 1, policy_version 14902 (0.0008) -[2023-10-10 21:18:21,194][98560] Updated weights for policy 1, policy_version 14912 (0.0009) -[2023-10-10 21:18:23,247][98559] Updated weights for policy 0, policy_version 14890 (0.0008) -[2023-10-10 21:18:23,615][98559] Updated weights for policy 0, policy_version 14900 (0.0010) -[2023-10-10 21:18:23,984][98559] Updated weights for policy 0, policy_version 14910 (0.0011) -[2023-10-10 21:18:25,167][98560] Updated weights for policy 1, policy_version 14922 (0.0007) -[2023-10-10 21:18:25,540][98560] Updated weights for policy 1, policy_version 14932 (0.0007) -[2023-10-10 21:18:25,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 30539776. Throughput: 0: 1707.3, 1: 1703.0. Samples: 7641416. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:18:25,557][97672] Avg episode reward: [(0, '-3.920'), (1, '17.960')] -[2023-10-10 21:18:25,557][98385] Saving new best policy, reward=-3.920! -[2023-10-10 21:18:25,900][98560] Updated weights for policy 1, policy_version 14942 (0.0007) -[2023-10-10 21:18:27,962][98559] Updated weights for policy 0, policy_version 14920 (0.0007) -[2023-10-10 21:18:28,331][98559] Updated weights for policy 0, policy_version 14930 (0.0008) -[2023-10-10 21:18:28,696][98559] Updated weights for policy 0, policy_version 14940 (0.0007) -[2023-10-10 21:18:29,949][98560] Updated weights for policy 1, policy_version 14952 (0.0007) -[2023-10-10 21:18:30,323][98560] Updated weights for policy 1, policy_version 14962 (0.0007) -[2023-10-10 21:18:30,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 30605312. Throughput: 0: 1683.6, 1: 1703.1. Samples: 7661688. Policy #0 lag: (min: 5.0, avg: 10.8, max: 37.0) -[2023-10-10 21:18:30,557][97672] Avg episode reward: [(0, '-3.920'), (1, '17.700')] -[2023-10-10 21:18:30,700][98560] Updated weights for policy 1, policy_version 14972 (0.0007) -[2023-10-10 21:18:32,850][98559] Updated weights for policy 0, policy_version 14950 (0.0007) -[2023-10-10 21:18:33,231][98559] Updated weights for policy 0, policy_version 14960 (0.0009) -[2023-10-10 21:18:33,602][98559] Updated weights for policy 0, policy_version 14970 (0.0011) -[2023-10-10 21:18:34,573][98560] Updated weights for policy 1, policy_version 14982 (0.0008) -[2023-10-10 21:18:34,952][98560] Updated weights for policy 1, policy_version 14992 (0.0008) -[2023-10-10 21:18:35,313][98560] Updated weights for policy 1, policy_version 15002 (0.0008) -[2023-10-10 21:18:35,556][97672] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 30703616. Throughput: 0: 1706.0, 1: 1698.6. Samples: 7682444. Policy #0 lag: (min: 5.0, avg: 10.8, max: 37.0) -[2023-10-10 21:18:35,556][97672] Avg episode reward: [(0, '-3.920'), (1, '17.700')] -[2023-10-10 21:18:35,565][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000015008_15368192.pth... -[2023-10-10 21:18:35,565][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000014976_15335424.pth... -[2023-10-10 21:18:35,597][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000013376_13697024.pth -[2023-10-10 21:18:35,604][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000013408_13729792.pth -[2023-10-10 21:18:37,567][98559] Updated weights for policy 0, policy_version 14980 (0.0008) -[2023-10-10 21:18:37,938][98559] Updated weights for policy 0, policy_version 14990 (0.0008) -[2023-10-10 21:18:38,309][98559] Updated weights for policy 0, policy_version 15000 (0.0008) -[2023-10-10 21:18:39,268][98560] Updated weights for policy 1, policy_version 15012 (0.0008) -[2023-10-10 21:18:39,639][98560] Updated weights for policy 1, policy_version 15022 (0.0011) -[2023-10-10 21:18:40,006][98560] Updated weights for policy 1, policy_version 15032 (0.0011) -[2023-10-10 21:18:40,556][97672] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 30769152. Throughput: 0: 1689.7, 1: 1705.8. Samples: 7692354. Policy #0 lag: (min: 5.0, avg: 10.8, max: 37.0) -[2023-10-10 21:18:40,557][97672] Avg episode reward: [(0, '-3.920'), (1, '17.700')] -[2023-10-10 21:18:42,326][98559] Updated weights for policy 0, policy_version 15010 (0.0009) -[2023-10-10 21:18:42,698][98559] Updated weights for policy 0, policy_version 15020 (0.0008) -[2023-10-10 21:18:43,069][98559] Updated weights for policy 0, policy_version 15030 (0.0010) -[2023-10-10 21:18:43,443][98559] Updated weights for policy 0, policy_version 15040 (0.0009) -[2023-10-10 21:18:44,003][98560] Updated weights for policy 1, policy_version 15042 (0.0009) -[2023-10-10 21:18:44,374][98560] Updated weights for policy 1, policy_version 15052 (0.0008) -[2023-10-10 21:18:44,739][98560] Updated weights for policy 1, policy_version 15062 (0.0009) -[2023-10-10 21:18:45,111][98560] Updated weights for policy 1, policy_version 15072 (0.0008) -[2023-10-10 21:18:45,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 30834688. Throughput: 0: 1689.1, 1: 1708.3. Samples: 7712936. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) -[2023-10-10 21:18:45,557][97672] Avg episode reward: [(0, '-3.920'), (1, '17.840')] -[2023-10-10 21:18:47,524][98559] Updated weights for policy 0, policy_version 15050 (0.0010) -[2023-10-10 21:18:47,887][98559] Updated weights for policy 0, policy_version 15060 (0.0009) -[2023-10-10 21:18:48,255][98559] Updated weights for policy 0, policy_version 15070 (0.0007) -[2023-10-10 21:18:49,149][98560] Updated weights for policy 1, policy_version 15082 (0.0012) -[2023-10-10 21:18:49,515][98560] Updated weights for policy 1, policy_version 15092 (0.0007) -[2023-10-10 21:18:49,877][98560] Updated weights for policy 1, policy_version 15102 (0.0009) -[2023-10-10 21:18:50,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 30900224. Throughput: 0: 1711.7, 1: 1689.0. Samples: 7733026. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) -[2023-10-10 21:18:50,557][97672] Avg episode reward: [(0, '-3.880'), (1, '18.160')] -[2023-10-10 21:18:50,569][98385] Saving new best policy, reward=-3.880! -[2023-10-10 21:18:52,154][98559] Updated weights for policy 0, policy_version 15080 (0.0008) -[2023-10-10 21:18:52,532][98559] Updated weights for policy 0, policy_version 15090 (0.0007) -[2023-10-10 21:18:52,903][98559] Updated weights for policy 0, policy_version 15100 (0.0009) -[2023-10-10 21:18:53,737][98560] Updated weights for policy 1, policy_version 15112 (0.0008) -[2023-10-10 21:18:54,113][98560] Updated weights for policy 1, policy_version 15122 (0.0008) -[2023-10-10 21:18:54,478][98560] Updated weights for policy 1, policy_version 15132 (0.0009) -[2023-10-10 21:18:55,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 30965760. Throughput: 0: 1680.9, 1: 1713.1. Samples: 7743218. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) -[2023-10-10 21:18:55,556][97672] Avg episode reward: [(0, '-3.880'), (1, '18.140')] -[2023-10-10 21:18:56,870][98559] Updated weights for policy 0, policy_version 15110 (0.0008) -[2023-10-10 21:18:57,231][98559] Updated weights for policy 0, policy_version 15120 (0.0011) -[2023-10-10 21:18:57,607][98559] Updated weights for policy 0, policy_version 15130 (0.0011) -[2023-10-10 21:18:58,615][98560] Updated weights for policy 1, policy_version 15142 (0.0010) -[2023-10-10 21:18:58,987][98560] Updated weights for policy 1, policy_version 15152 (0.0008) -[2023-10-10 21:18:59,359][98560] Updated weights for policy 1, policy_version 15162 (0.0007) -[2023-10-10 21:19:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 31031296. Throughput: 0: 1708.5, 1: 1706.9. Samples: 7764008. Policy #0 lag: (min: 24.0, avg: 50.8, max: 56.0) -[2023-10-10 21:19:00,557][97672] Avg episode reward: [(0, '-3.880'), (1, '18.140')] -[2023-10-10 21:19:01,671][98559] Updated weights for policy 0, policy_version 15140 (0.0010) -[2023-10-10 21:19:02,047][98559] Updated weights for policy 0, policy_version 15150 (0.0008) -[2023-10-10 21:19:02,425][98559] Updated weights for policy 0, policy_version 15160 (0.0009) -[2023-10-10 21:19:03,522][98560] Updated weights for policy 1, policy_version 15172 (0.0007) -[2023-10-10 21:19:03,901][98560] Updated weights for policy 1, policy_version 15182 (0.0009) -[2023-10-10 21:19:04,271][98560] Updated weights for policy 1, policy_version 15192 (0.0009) -[2023-10-10 21:19:05,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 31096832. Throughput: 0: 1718.1, 1: 1675.8. Samples: 7783984. Policy #0 lag: (min: 24.0, avg: 50.8, max: 56.0) -[2023-10-10 21:19:05,557][97672] Avg episode reward: [(0, '-3.880'), (1, '18.160')] -[2023-10-10 21:19:06,415][98559] Updated weights for policy 0, policy_version 15170 (0.0011) -[2023-10-10 21:19:06,793][98559] Updated weights for policy 0, policy_version 15180 (0.0008) -[2023-10-10 21:19:07,159][98559] Updated weights for policy 0, policy_version 15190 (0.0008) -[2023-10-10 21:19:07,528][98559] Updated weights for policy 0, policy_version 15200 (0.0007) -[2023-10-10 21:19:08,181][98560] Updated weights for policy 1, policy_version 15202 (0.0009) -[2023-10-10 21:19:08,544][98560] Updated weights for policy 1, policy_version 15212 (0.0010) -[2023-10-10 21:19:08,917][98560] Updated weights for policy 1, policy_version 15222 (0.0010) -[2023-10-10 21:19:09,287][98560] Updated weights for policy 1, policy_version 15232 (0.0010) -[2023-10-10 21:19:10,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 31162368. Throughput: 0: 1695.6, 1: 1708.4. Samples: 7794596. Policy #0 lag: (min: 24.0, avg: 50.8, max: 56.0) -[2023-10-10 21:19:10,556][97672] Avg episode reward: [(0, '-3.880'), (1, '18.140')] -[2023-10-10 21:19:11,566][98559] Updated weights for policy 0, policy_version 15210 (0.0007) -[2023-10-10 21:19:11,941][98559] Updated weights for policy 0, policy_version 15220 (0.0008) -[2023-10-10 21:19:12,312][98559] Updated weights for policy 0, policy_version 15230 (0.0010) -[2023-10-10 21:19:13,261][98560] Updated weights for policy 1, policy_version 15242 (0.0009) -[2023-10-10 21:19:13,637][98560] Updated weights for policy 1, policy_version 15252 (0.0009) -[2023-10-10 21:19:13,996][98560] Updated weights for policy 1, policy_version 15262 (0.0007) -[2023-10-10 21:19:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 31227904. Throughput: 0: 1715.6, 1: 1687.4. Samples: 7814822. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:19:15,557][97672] Avg episode reward: [(0, '-3.880'), (1, '18.180')] -[2023-10-10 21:19:16,310][98559] Updated weights for policy 0, policy_version 15240 (0.0010) -[2023-10-10 21:19:16,691][98559] Updated weights for policy 0, policy_version 15250 (0.0007) -[2023-10-10 21:19:17,061][98559] Updated weights for policy 0, policy_version 15260 (0.0008) -[2023-10-10 21:19:18,001][98560] Updated weights for policy 1, policy_version 15272 (0.0009) -[2023-10-10 21:19:18,370][98560] Updated weights for policy 1, policy_version 15282 (0.0008) -[2023-10-10 21:19:18,751][98560] Updated weights for policy 1, policy_version 15292 (0.0009) -[2023-10-10 21:19:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 31293440. Throughput: 0: 1718.9, 1: 1686.0. Samples: 7835664. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:19:20,557][97672] Avg episode reward: [(0, '-3.880'), (1, '18.380')] -[2023-10-10 21:19:20,933][98559] Updated weights for policy 0, policy_version 15270 (0.0010) -[2023-10-10 21:19:21,315][98559] Updated weights for policy 0, policy_version 15280 (0.0009) -[2023-10-10 21:19:21,680][98559] Updated weights for policy 0, policy_version 15290 (0.0009) -[2023-10-10 21:19:22,793][98560] Updated weights for policy 1, policy_version 15302 (0.0009) -[2023-10-10 21:19:23,181][98560] Updated weights for policy 1, policy_version 15312 (0.0007) -[2023-10-10 21:19:23,550][98560] Updated weights for policy 1, policy_version 15322 (0.0011) -[2023-10-10 21:19:25,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 31358976. Throughput: 0: 1709.5, 1: 1704.5. Samples: 7845984. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:19:25,556][97672] Avg episode reward: [(0, '-3.880'), (1, '18.360')] -[2023-10-10 21:19:25,625][98559] Updated weights for policy 0, policy_version 15300 (0.0009) -[2023-10-10 21:19:25,986][98559] Updated weights for policy 0, policy_version 15310 (0.0008) -[2023-10-10 21:19:26,359][98559] Updated weights for policy 0, policy_version 15320 (0.0008) -[2023-10-10 21:19:27,537][98560] Updated weights for policy 1, policy_version 15332 (0.0009) -[2023-10-10 21:19:27,916][98560] Updated weights for policy 1, policy_version 15342 (0.0008) -[2023-10-10 21:19:28,277][98560] Updated weights for policy 1, policy_version 15352 (0.0007) -[2023-10-10 21:19:30,417][98559] Updated weights for policy 0, policy_version 15330 (0.0009) -[2023-10-10 21:19:30,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 31424512. Throughput: 0: 1718.0, 1: 1680.5. Samples: 7865864. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:19:30,556][97672] Avg episode reward: [(0, '-3.880'), (1, '18.440')] -[2023-10-10 21:19:30,789][98559] Updated weights for policy 0, policy_version 15340 (0.0009) -[2023-10-10 21:19:31,155][98559] Updated weights for policy 0, policy_version 15350 (0.0009) -[2023-10-10 21:19:31,528][98559] Updated weights for policy 0, policy_version 15360 (0.0011) -[2023-10-10 21:19:32,243][98560] Updated weights for policy 1, policy_version 15362 (0.0008) -[2023-10-10 21:19:32,605][98560] Updated weights for policy 1, policy_version 15372 (0.0009) -[2023-10-10 21:19:32,983][98560] Updated weights for policy 1, policy_version 15382 (0.0008) -[2023-10-10 21:19:33,341][98560] Updated weights for policy 1, policy_version 15392 (0.0009) -[2023-10-10 21:19:35,522][98559] Updated weights for policy 0, policy_version 15370 (0.0008) -[2023-10-10 21:19:35,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 31490048. Throughput: 0: 1709.5, 1: 1708.0. Samples: 7886812. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:19:35,557][97672] Avg episode reward: [(0, '-3.880'), (1, '18.540')] -[2023-10-10 21:19:35,570][98439] Saving new best policy, reward=18.540! -[2023-10-10 21:19:35,898][98559] Updated weights for policy 0, policy_version 15380 (0.0009) -[2023-10-10 21:19:36,274][98559] Updated weights for policy 0, policy_version 15390 (0.0010) -[2023-10-10 21:19:37,282][98560] Updated weights for policy 1, policy_version 15402 (0.0010) -[2023-10-10 21:19:37,644][98560] Updated weights for policy 1, policy_version 15412 (0.0011) -[2023-10-10 21:19:38,009][98560] Updated weights for policy 1, policy_version 15422 (0.0009) -[2023-10-10 21:19:40,331][98559] Updated weights for policy 0, policy_version 15400 (0.0009) -[2023-10-10 21:19:40,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 31555584. Throughput: 0: 1717.2, 1: 1699.2. Samples: 7896956. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:19:40,557][97672] Avg episode reward: [(0, '-3.880'), (1, '18.640')] -[2023-10-10 21:19:40,557][98439] Saving new best policy, reward=18.640! -[2023-10-10 21:19:40,701][98559] Updated weights for policy 0, policy_version 15410 (0.0008) -[2023-10-10 21:19:41,084][98559] Updated weights for policy 0, policy_version 15420 (0.0007) -[2023-10-10 21:19:41,962][98560] Updated weights for policy 1, policy_version 15432 (0.0007) -[2023-10-10 21:19:42,324][98560] Updated weights for policy 1, policy_version 15442 (0.0008) -[2023-10-10 21:19:42,695][98560] Updated weights for policy 1, policy_version 15452 (0.0008) -[2023-10-10 21:19:44,977][98559] Updated weights for policy 0, policy_version 15430 (0.0009) -[2023-10-10 21:19:45,344][98559] Updated weights for policy 0, policy_version 15440 (0.0007) -[2023-10-10 21:19:45,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 31621120. Throughput: 0: 1716.0, 1: 1696.3. Samples: 7917562. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:19:45,556][97672] Avg episode reward: [(0, '-3.880'), (1, '18.820')] -[2023-10-10 21:19:45,557][98439] Saving new best policy, reward=18.820! -[2023-10-10 21:19:45,723][98559] Updated weights for policy 0, policy_version 15450 (0.0007) -[2023-10-10 21:19:46,804][98560] Updated weights for policy 1, policy_version 15462 (0.0008) -[2023-10-10 21:19:47,171][98560] Updated weights for policy 1, policy_version 15472 (0.0007) -[2023-10-10 21:19:47,539][98560] Updated weights for policy 1, policy_version 15482 (0.0010) -[2023-10-10 21:19:49,658][98559] Updated weights for policy 0, policy_version 15460 (0.0010) -[2023-10-10 21:19:50,026][98559] Updated weights for policy 0, policy_version 15470 (0.0009) -[2023-10-10 21:19:50,396][98559] Updated weights for policy 0, policy_version 15480 (0.0010) -[2023-10-10 21:19:50,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 31686656. Throughput: 0: 1694.0, 1: 1720.8. Samples: 7937648. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:19:50,556][97672] Avg episode reward: [(0, '-3.880'), (1, '18.640')] -[2023-10-10 21:19:51,617][98560] Updated weights for policy 1, policy_version 15492 (0.0009) -[2023-10-10 21:19:51,987][98560] Updated weights for policy 1, policy_version 15502 (0.0009) -[2023-10-10 21:19:52,350][98560] Updated weights for policy 1, policy_version 15512 (0.0007) -[2023-10-10 21:19:54,345][98559] Updated weights for policy 0, policy_version 15490 (0.0010) -[2023-10-10 21:19:54,712][98559] Updated weights for policy 0, policy_version 15500 (0.0009) -[2023-10-10 21:19:55,083][98559] Updated weights for policy 0, policy_version 15510 (0.0010) -[2023-10-10 21:19:55,451][98559] Updated weights for policy 0, policy_version 15520 (0.0009) -[2023-10-10 21:19:55,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 31784960. Throughput: 0: 1717.0, 1: 1689.2. Samples: 7947874. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:19:55,557][97672] Avg episode reward: [(0, '-3.880'), (1, '18.520')] -[2023-10-10 21:19:56,432][98560] Updated weights for policy 1, policy_version 15522 (0.0008) -[2023-10-10 21:19:56,803][98560] Updated weights for policy 1, policy_version 15532 (0.0009) -[2023-10-10 21:19:57,182][98560] Updated weights for policy 1, policy_version 15542 (0.0008) -[2023-10-10 21:19:57,554][98560] Updated weights for policy 1, policy_version 15552 (0.0010) -[2023-10-10 21:19:59,492][98559] Updated weights for policy 0, policy_version 15530 (0.0010) -[2023-10-10 21:19:59,859][98559] Updated weights for policy 0, policy_version 15540 (0.0009) -[2023-10-10 21:20:00,237][98559] Updated weights for policy 0, policy_version 15550 (0.0007) -[2023-10-10 21:20:00,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 31850496. Throughput: 0: 1709.0, 1: 1706.3. Samples: 7968510. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:20:00,557][97672] Avg episode reward: [(0, '-3.880'), (1, '18.420')] -[2023-10-10 21:20:01,523][98560] Updated weights for policy 1, policy_version 15562 (0.0008) -[2023-10-10 21:20:01,898][98560] Updated weights for policy 1, policy_version 15572 (0.0008) -[2023-10-10 21:20:02,272][98560] Updated weights for policy 1, policy_version 15582 (0.0007) -[2023-10-10 21:20:04,027][98559] Updated weights for policy 0, policy_version 15560 (0.0008) -[2023-10-10 21:20:04,398][98559] Updated weights for policy 0, policy_version 15570 (0.0009) -[2023-10-10 21:20:04,772][98559] Updated weights for policy 0, policy_version 15580 (0.0009) -[2023-10-10 21:20:05,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 31916032. Throughput: 0: 1686.2, 1: 1717.3. Samples: 7988824. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:20:05,557][97672] Avg episode reward: [(0, '-3.880'), (1, '18.360')] -[2023-10-10 21:20:06,103][98560] Updated weights for policy 1, policy_version 15592 (0.0009) -[2023-10-10 21:20:06,467][98560] Updated weights for policy 1, policy_version 15602 (0.0008) -[2023-10-10 21:20:06,832][98560] Updated weights for policy 1, policy_version 15612 (0.0007) -[2023-10-10 21:20:08,840][98559] Updated weights for policy 0, policy_version 15590 (0.0007) -[2023-10-10 21:20:09,218][98559] Updated weights for policy 0, policy_version 15600 (0.0010) -[2023-10-10 21:20:09,593][98559] Updated weights for policy 0, policy_version 15610 (0.0010) -[2023-10-10 21:20:10,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13653.2, 300 sec: 13662.6). Total num frames: 31981568. Throughput: 0: 1716.6, 1: 1691.2. Samples: 7999338. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-10 21:20:10,558][97672] Avg episode reward: [(0, '-3.880'), (1, '18.300')] -[2023-10-10 21:20:10,887][98560] Updated weights for policy 1, policy_version 15622 (0.0010) -[2023-10-10 21:20:11,271][98560] Updated weights for policy 1, policy_version 15632 (0.0009) -[2023-10-10 21:20:11,651][98560] Updated weights for policy 1, policy_version 15642 (0.0009) -[2023-10-10 21:20:13,591][98559] Updated weights for policy 0, policy_version 15620 (0.0009) -[2023-10-10 21:20:13,966][98559] Updated weights for policy 0, policy_version 15630 (0.0008) -[2023-10-10 21:20:14,329][98559] Updated weights for policy 0, policy_version 15640 (0.0008) -[2023-10-10 21:20:15,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 32047104. Throughput: 0: 1698.1, 1: 1710.3. Samples: 8019244. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-10 21:20:15,557][97672] Avg episode reward: [(0, '-3.880'), (1, '18.400')] -[2023-10-10 21:20:15,730][98560] Updated weights for policy 1, policy_version 15652 (0.0008) -[2023-10-10 21:20:16,097][98560] Updated weights for policy 1, policy_version 15662 (0.0007) -[2023-10-10 21:20:16,471][98560] Updated weights for policy 1, policy_version 15672 (0.0008) -[2023-10-10 21:20:18,295][98559] Updated weights for policy 0, policy_version 15650 (0.0010) -[2023-10-10 21:20:18,673][98559] Updated weights for policy 0, policy_version 15660 (0.0008) -[2023-10-10 21:20:19,046][98559] Updated weights for policy 0, policy_version 15670 (0.0008) -[2023-10-10 21:20:19,426][98559] Updated weights for policy 0, policy_version 15680 (0.0007) -[2023-10-10 21:20:20,364][98560] Updated weights for policy 1, policy_version 15682 (0.0009) -[2023-10-10 21:20:20,556][97672] Fps is (10 sec: 13107.7, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 32112640. Throughput: 0: 1696.1, 1: 1711.3. Samples: 8040140. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-10 21:20:20,556][97672] Avg episode reward: [(0, '-3.960'), (1, '18.160')] -[2023-10-10 21:20:20,743][98560] Updated weights for policy 1, policy_version 15692 (0.0008) -[2023-10-10 21:20:21,101][98560] Updated weights for policy 1, policy_version 15702 (0.0009) -[2023-10-10 21:20:21,475][98560] Updated weights for policy 1, policy_version 15712 (0.0008) -[2023-10-10 21:20:23,531][98559] Updated weights for policy 0, policy_version 15690 (0.0010) -[2023-10-10 21:20:23,903][98559] Updated weights for policy 0, policy_version 15700 (0.0008) -[2023-10-10 21:20:24,267][98559] Updated weights for policy 0, policy_version 15710 (0.0009) -[2023-10-10 21:20:25,522][98560] Updated weights for policy 1, policy_version 15722 (0.0007) -[2023-10-10 21:20:25,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 32178176. Throughput: 0: 1711.9, 1: 1693.7. Samples: 8050210. Policy #0 lag: (min: 1.0, avg: 11.8, max: 33.0) -[2023-10-10 21:20:25,557][97672] Avg episode reward: [(0, '-3.960'), (1, '18.240')] -[2023-10-10 21:20:25,883][98560] Updated weights for policy 1, policy_version 15732 (0.0009) -[2023-10-10 21:20:26,254][98560] Updated weights for policy 1, policy_version 15742 (0.0007) -[2023-10-10 21:20:28,234][98559] Updated weights for policy 0, policy_version 15720 (0.0007) -[2023-10-10 21:20:28,612][98559] Updated weights for policy 0, policy_version 15730 (0.0008) -[2023-10-10 21:20:28,978][98559] Updated weights for policy 0, policy_version 15740 (0.0007) -[2023-10-10 21:20:30,273][98560] Updated weights for policy 1, policy_version 15752 (0.0007) -[2023-10-10 21:20:30,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 32243712. Throughput: 0: 1686.8, 1: 1704.6. Samples: 8070176. Policy #0 lag: (min: 1.0, avg: 11.8, max: 33.0) -[2023-10-10 21:20:30,557][97672] Avg episode reward: [(0, '-3.960'), (1, '18.220')] -[2023-10-10 21:20:30,631][98560] Updated weights for policy 1, policy_version 15762 (0.0010) -[2023-10-10 21:20:31,000][98560] Updated weights for policy 1, policy_version 15772 (0.0010) -[2023-10-10 21:20:32,872][98559] Updated weights for policy 0, policy_version 15750 (0.0009) -[2023-10-10 21:20:33,241][98559] Updated weights for policy 0, policy_version 15760 (0.0009) -[2023-10-10 21:20:33,615][98559] Updated weights for policy 0, policy_version 15770 (0.0010) -[2023-10-10 21:20:34,884][98560] Updated weights for policy 1, policy_version 15782 (0.0009) -[2023-10-10 21:20:35,251][98560] Updated weights for policy 1, policy_version 15792 (0.0010) -[2023-10-10 21:20:35,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 32309248. Throughput: 0: 1709.6, 1: 1706.8. Samples: 8091386. Policy #0 lag: (min: 1.0, avg: 11.8, max: 33.0) -[2023-10-10 21:20:35,557][97672] Avg episode reward: [(0, '-3.960'), (1, '18.380')] -[2023-10-10 21:20:35,567][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000015776_16154624.pth... -[2023-10-10 21:20:35,600][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000014176_14516224.pth -[2023-10-10 21:20:35,604][98385] Saving a milestone ./train_atari/atari_doubledunk_APPO/checkpoint_p0/milestones/checkpoint_000015776_16154624.pth -[2023-10-10 21:20:35,628][98560] Updated weights for policy 1, policy_version 15802 (0.0008) -[2023-10-10 21:20:35,849][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000015808_16187392.pth... -[2023-10-10 21:20:35,889][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000014208_14548992.pth -[2023-10-10 21:20:35,894][98439] Saving a milestone ./train_atari/atari_doubledunk_APPO/checkpoint_p1/milestones/checkpoint_000015808_16187392.pth -[2023-10-10 21:20:37,578][98559] Updated weights for policy 0, policy_version 15780 (0.0009) -[2023-10-10 21:20:37,945][98559] Updated weights for policy 0, policy_version 15790 (0.0009) -[2023-10-10 21:20:38,320][98559] Updated weights for policy 0, policy_version 15800 (0.0008) -[2023-10-10 21:20:39,584][98560] Updated weights for policy 1, policy_version 15812 (0.0008) -[2023-10-10 21:20:39,946][98560] Updated weights for policy 1, policy_version 15822 (0.0008) -[2023-10-10 21:20:40,310][98560] Updated weights for policy 1, policy_version 15832 (0.0007) -[2023-10-10 21:20:40,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 32374784. Throughput: 0: 1697.8, 1: 1706.8. Samples: 8101080. Policy #0 lag: (min: 2.0, avg: 5.4, max: 32.0) -[2023-10-10 21:20:40,557][97672] Avg episode reward: [(0, '-3.840'), (1, '18.500')] -[2023-10-10 21:20:40,558][98385] Saving new best policy, reward=-3.840! -[2023-10-10 21:20:42,285][98559] Updated weights for policy 0, policy_version 15810 (0.0008) -[2023-10-10 21:20:42,659][98559] Updated weights for policy 0, policy_version 15820 (0.0008) -[2023-10-10 21:20:43,027][98559] Updated weights for policy 0, policy_version 15830 (0.0009) -[2023-10-10 21:20:43,401][98559] Updated weights for policy 0, policy_version 15840 (0.0007) -[2023-10-10 21:20:44,410][98560] Updated weights for policy 1, policy_version 15842 (0.0008) -[2023-10-10 21:20:44,775][98560] Updated weights for policy 1, policy_version 15852 (0.0011) -[2023-10-10 21:20:45,149][98560] Updated weights for policy 1, policy_version 15862 (0.0010) -[2023-10-10 21:20:45,511][98560] Updated weights for policy 1, policy_version 15872 (0.0010) -[2023-10-10 21:20:45,556][97672] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 32473088. Throughput: 0: 1695.8, 1: 1712.7. Samples: 8121896. Policy #0 lag: (min: 2.0, avg: 5.4, max: 32.0) -[2023-10-10 21:20:45,557][97672] Avg episode reward: [(0, '-3.840'), (1, '18.500')] -[2023-10-10 21:20:47,252][98559] Updated weights for policy 0, policy_version 15850 (0.0010) -[2023-10-10 21:20:47,626][98559] Updated weights for policy 0, policy_version 15860 (0.0008) -[2023-10-10 21:20:48,001][98559] Updated weights for policy 0, policy_version 15870 (0.0008) -[2023-10-10 21:20:49,626][98560] Updated weights for policy 1, policy_version 15882 (0.0008) -[2023-10-10 21:20:49,995][98560] Updated weights for policy 1, policy_version 15892 (0.0008) -[2023-10-10 21:20:50,370][98560] Updated weights for policy 1, policy_version 15902 (0.0010) -[2023-10-10 21:20:50,556][97672] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 32538624. Throughput: 0: 1719.8, 1: 1695.2. Samples: 8142500. Policy #0 lag: (min: 2.0, avg: 5.4, max: 32.0) -[2023-10-10 21:20:50,557][97672] Avg episode reward: [(0, '-3.840'), (1, '18.600')] -[2023-10-10 21:20:51,942][98559] Updated weights for policy 0, policy_version 15880 (0.0008) -[2023-10-10 21:20:52,325][98559] Updated weights for policy 0, policy_version 15890 (0.0010) -[2023-10-10 21:20:52,687][98559] Updated weights for policy 0, policy_version 15900 (0.0008) -[2023-10-10 21:20:54,392][98560] Updated weights for policy 1, policy_version 15912 (0.0011) -[2023-10-10 21:20:54,751][98560] Updated weights for policy 1, policy_version 15922 (0.0008) -[2023-10-10 21:20:55,123][98560] Updated weights for policy 1, policy_version 15932 (0.0009) -[2023-10-10 21:20:55,556][97672] Fps is (10 sec: 13107.7, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 32604160. Throughput: 0: 1691.3, 1: 1705.7. Samples: 8152198. Policy #0 lag: (min: 0.0, avg: 20.5, max: 32.0) -[2023-10-10 21:20:55,556][97672] Avg episode reward: [(0, '-3.860'), (1, '18.720')] -[2023-10-10 21:20:56,816][98559] Updated weights for policy 0, policy_version 15910 (0.0007) -[2023-10-10 21:20:57,180][98559] Updated weights for policy 0, policy_version 15920 (0.0009) -[2023-10-10 21:20:57,550][98559] Updated weights for policy 0, policy_version 15930 (0.0007) -[2023-10-10 21:20:59,296][98560] Updated weights for policy 1, policy_version 15942 (0.0009) -[2023-10-10 21:20:59,690][98560] Updated weights for policy 1, policy_version 15952 (0.0010) -[2023-10-10 21:21:00,055][98560] Updated weights for policy 1, policy_version 15962 (0.0008) -[2023-10-10 21:21:00,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 32669696. Throughput: 0: 1706.4, 1: 1708.0. Samples: 8172894. Policy #0 lag: (min: 0.0, avg: 20.5, max: 32.0) -[2023-10-10 21:21:00,558][97672] Avg episode reward: [(0, '-3.860'), (1, '18.760')] -[2023-10-10 21:21:01,557][98559] Updated weights for policy 0, policy_version 15940 (0.0008) -[2023-10-10 21:21:01,927][98559] Updated weights for policy 0, policy_version 15950 (0.0009) -[2023-10-10 21:21:02,293][98559] Updated weights for policy 0, policy_version 15960 (0.0009) -[2023-10-10 21:21:03,992][98560] Updated weights for policy 1, policy_version 15972 (0.0009) -[2023-10-10 21:21:04,354][98560] Updated weights for policy 1, policy_version 15982 (0.0008) -[2023-10-10 21:21:04,729][98560] Updated weights for policy 1, policy_version 15992 (0.0010) -[2023-10-10 21:21:05,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 32735232. Throughput: 0: 1721.4, 1: 1682.3. Samples: 8193308. Policy #0 lag: (min: 0.0, avg: 20.5, max: 32.0) -[2023-10-10 21:21:05,557][97672] Avg episode reward: [(0, '-3.860'), (1, '19.000')] -[2023-10-10 21:21:05,566][98439] Saving new best policy, reward=19.000! -[2023-10-10 21:21:06,136][98559] Updated weights for policy 0, policy_version 15970 (0.0008) -[2023-10-10 21:21:06,518][98559] Updated weights for policy 0, policy_version 15980 (0.0009) -[2023-10-10 21:21:06,890][98559] Updated weights for policy 0, policy_version 15990 (0.0007) -[2023-10-10 21:21:07,271][98559] Updated weights for policy 0, policy_version 16000 (0.0010) -[2023-10-10 21:21:08,705][98560] Updated weights for policy 1, policy_version 16002 (0.0008) -[2023-10-10 21:21:09,075][98560] Updated weights for policy 1, policy_version 16012 (0.0008) -[2023-10-10 21:21:09,451][98560] Updated weights for policy 1, policy_version 16022 (0.0007) -[2023-10-10 21:21:09,814][98560] Updated weights for policy 1, policy_version 16032 (0.0008) -[2023-10-10 21:21:10,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 32800768. Throughput: 0: 1700.4, 1: 1706.4. Samples: 8203518. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:21:10,557][97672] Avg episode reward: [(0, '-3.840'), (1, '19.080')] -[2023-10-10 21:21:10,557][98439] Saving new best policy, reward=19.080! -[2023-10-10 21:21:11,347][98559] Updated weights for policy 0, policy_version 16010 (0.0010) -[2023-10-10 21:21:11,714][98559] Updated weights for policy 0, policy_version 16020 (0.0010) -[2023-10-10 21:21:12,079][98559] Updated weights for policy 0, policy_version 16030 (0.0010) -[2023-10-10 21:21:13,720][98560] Updated weights for policy 1, policy_version 16042 (0.0009) -[2023-10-10 21:21:14,093][98560] Updated weights for policy 1, policy_version 16052 (0.0009) -[2023-10-10 21:21:14,467][98560] Updated weights for policy 1, policy_version 16062 (0.0009) -[2023-10-10 21:21:15,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 32866304. Throughput: 0: 1723.9, 1: 1698.0. Samples: 8224160. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:21:15,557][97672] Avg episode reward: [(0, '-3.860'), (1, '19.060')] -[2023-10-10 21:21:16,191][98559] Updated weights for policy 0, policy_version 16040 (0.0008) -[2023-10-10 21:21:16,561][98559] Updated weights for policy 0, policy_version 16050 (0.0009) -[2023-10-10 21:21:16,938][98559] Updated weights for policy 0, policy_version 16060 (0.0008) -[2023-10-10 21:21:18,270][98560] Updated weights for policy 1, policy_version 16072 (0.0008) -[2023-10-10 21:21:18,645][98560] Updated weights for policy 1, policy_version 16082 (0.0007) -[2023-10-10 21:21:19,010][98560] Updated weights for policy 1, policy_version 16092 (0.0008) -[2023-10-10 21:21:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 32931840. Throughput: 0: 1719.6, 1: 1680.3. Samples: 8244382. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:21:20,557][97672] Avg episode reward: [(0, '-3.920'), (1, '19.140')] -[2023-10-10 21:21:20,567][98439] Saving new best policy, reward=19.140! -[2023-10-10 21:21:21,016][98559] Updated weights for policy 0, policy_version 16070 (0.0007) -[2023-10-10 21:21:21,392][98559] Updated weights for policy 0, policy_version 16080 (0.0008) -[2023-10-10 21:21:21,755][98559] Updated weights for policy 0, policy_version 16090 (0.0010) -[2023-10-10 21:21:22,937][98560] Updated weights for policy 1, policy_version 16102 (0.0009) -[2023-10-10 21:21:23,309][98560] Updated weights for policy 1, policy_version 16112 (0.0007) -[2023-10-10 21:21:23,683][98560] Updated weights for policy 1, policy_version 16122 (0.0007) -[2023-10-10 21:21:25,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 32997376. Throughput: 0: 1708.3, 1: 1714.2. Samples: 8255092. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:21:25,556][97672] Avg episode reward: [(0, '-3.920'), (1, '19.020')] -[2023-10-10 21:21:25,690][98559] Updated weights for policy 0, policy_version 16100 (0.0008) -[2023-10-10 21:21:26,064][98559] Updated weights for policy 0, policy_version 16110 (0.0008) -[2023-10-10 21:21:26,425][98559] Updated weights for policy 0, policy_version 16120 (0.0008) -[2023-10-10 21:21:27,623][98560] Updated weights for policy 1, policy_version 16132 (0.0007) -[2023-10-10 21:21:27,982][98560] Updated weights for policy 1, policy_version 16142 (0.0007) -[2023-10-10 21:21:28,350][98560] Updated weights for policy 1, policy_version 16152 (0.0008) -[2023-10-10 21:21:30,366][98559] Updated weights for policy 0, policy_version 16130 (0.0008) -[2023-10-10 21:21:30,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 33062912. Throughput: 0: 1715.3, 1: 1685.4. Samples: 8274928. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:21:30,557][97672] Avg episode reward: [(0, '-3.920'), (1, '19.400')] -[2023-10-10 21:21:30,558][98439] Saving new best policy, reward=19.400! -[2023-10-10 21:21:30,739][98559] Updated weights for policy 0, policy_version 16140 (0.0009) -[2023-10-10 21:21:31,116][98559] Updated weights for policy 0, policy_version 16150 (0.0007) -[2023-10-10 21:21:31,487][98559] Updated weights for policy 0, policy_version 16160 (0.0007) -[2023-10-10 21:21:32,453][98560] Updated weights for policy 1, policy_version 16162 (0.0009) -[2023-10-10 21:21:32,823][98560] Updated weights for policy 1, policy_version 16172 (0.0008) -[2023-10-10 21:21:33,195][98560] Updated weights for policy 1, policy_version 16182 (0.0008) -[2023-10-10 21:21:33,562][98560] Updated weights for policy 1, policy_version 16192 (0.0008) -[2023-10-10 21:21:35,454][98559] Updated weights for policy 0, policy_version 16170 (0.0011) -[2023-10-10 21:21:35,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 33128448. Throughput: 0: 1707.3, 1: 1697.2. Samples: 8295706. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:21:35,557][97672] Avg episode reward: [(0, '-3.920'), (1, '19.480')] -[2023-10-10 21:21:35,569][98439] Saving new best policy, reward=19.480! -[2023-10-10 21:21:35,831][98559] Updated weights for policy 0, policy_version 16180 (0.0010) -[2023-10-10 21:21:36,191][98559] Updated weights for policy 0, policy_version 16190 (0.0009) -[2023-10-10 21:21:37,627][98560] Updated weights for policy 1, policy_version 16202 (0.0008) -[2023-10-10 21:21:38,003][98560] Updated weights for policy 1, policy_version 16212 (0.0008) -[2023-10-10 21:21:38,365][98560] Updated weights for policy 1, policy_version 16222 (0.0009) -[2023-10-10 21:21:40,150][98559] Updated weights for policy 0, policy_version 16200 (0.0011) -[2023-10-10 21:21:40,523][98559] Updated weights for policy 0, policy_version 16210 (0.0009) -[2023-10-10 21:21:40,556][97672] Fps is (10 sec: 13107.7, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 33193984. Throughput: 0: 1711.6, 1: 1708.4. Samples: 8306098. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:21:40,556][97672] Avg episode reward: [(0, '-3.920'), (1, '19.360')] -[2023-10-10 21:21:40,893][98559] Updated weights for policy 0, policy_version 16220 (0.0008) -[2023-10-10 21:21:42,523][98560] Updated weights for policy 1, policy_version 16232 (0.0009) -[2023-10-10 21:21:42,889][98560] Updated weights for policy 1, policy_version 16242 (0.0009) -[2023-10-10 21:21:43,263][98560] Updated weights for policy 1, policy_version 16252 (0.0009) -[2023-10-10 21:21:44,830][98559] Updated weights for policy 0, policy_version 16230 (0.0007) -[2023-10-10 21:21:45,194][98559] Updated weights for policy 0, policy_version 16240 (0.0010) -[2023-10-10 21:21:45,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 33259520. Throughput: 0: 1720.7, 1: 1690.3. Samples: 8326390. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:21:45,556][97672] Avg episode reward: [(0, '-3.820'), (1, '19.320')] -[2023-10-10 21:21:45,571][98559] Updated weights for policy 0, policy_version 16250 (0.0009) -[2023-10-10 21:21:45,786][98385] Saving new best policy, reward=-3.820! -[2023-10-10 21:21:47,254][98560] Updated weights for policy 1, policy_version 16262 (0.0010) -[2023-10-10 21:21:47,642][98560] Updated weights for policy 1, policy_version 16272 (0.0009) -[2023-10-10 21:21:48,010][98560] Updated weights for policy 1, policy_version 16282 (0.0009) -[2023-10-10 21:21:49,484][98559] Updated weights for policy 0, policy_version 16260 (0.0009) -[2023-10-10 21:21:49,860][98559] Updated weights for policy 0, policy_version 16270 (0.0007) -[2023-10-10 21:21:50,229][98559] Updated weights for policy 0, policy_version 16280 (0.0007) -[2023-10-10 21:21:50,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 33357824. Throughput: 0: 1688.9, 1: 1709.6. Samples: 8346242. Policy #0 lag: (min: 27.0, avg: 34.1, max: 59.0) -[2023-10-10 21:21:50,556][97672] Avg episode reward: [(0, '-3.820'), (1, '19.340')] -[2023-10-10 21:21:51,943][98560] Updated weights for policy 1, policy_version 16292 (0.0010) -[2023-10-10 21:21:52,305][98560] Updated weights for policy 1, policy_version 16302 (0.0009) -[2023-10-10 21:21:52,679][98560] Updated weights for policy 1, policy_version 16312 (0.0011) -[2023-10-10 21:21:54,125][98559] Updated weights for policy 0, policy_version 16290 (0.0008) -[2023-10-10 21:21:54,498][98559] Updated weights for policy 0, policy_version 16300 (0.0009) -[2023-10-10 21:21:54,870][98559] Updated weights for policy 0, policy_version 16310 (0.0012) -[2023-10-10 21:21:55,238][98559] Updated weights for policy 0, policy_version 16320 (0.0009) -[2023-10-10 21:21:55,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 33423360. Throughput: 0: 1716.9, 1: 1695.6. Samples: 8357082. Policy #0 lag: (min: 27.0, avg: 34.1, max: 59.0) -[2023-10-10 21:21:55,556][97672] Avg episode reward: [(0, '-3.820'), (1, '19.400')] -[2023-10-10 21:21:56,754][98560] Updated weights for policy 1, policy_version 16322 (0.0008) -[2023-10-10 21:21:57,130][98560] Updated weights for policy 1, policy_version 16332 (0.0007) -[2023-10-10 21:21:57,492][98560] Updated weights for policy 1, policy_version 16342 (0.0009) -[2023-10-10 21:21:57,860][98560] Updated weights for policy 1, policy_version 16352 (0.0008) -[2023-10-10 21:21:59,198][98559] Updated weights for policy 0, policy_version 16330 (0.0009) -[2023-10-10 21:21:59,567][98559] Updated weights for policy 0, policy_version 16340 (0.0008) -[2023-10-10 21:21:59,939][98559] Updated weights for policy 0, policy_version 16350 (0.0009) -[2023-10-10 21:22:00,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 33488896. Throughput: 0: 1705.5, 1: 1696.1. Samples: 8377232. Policy #0 lag: (min: 27.0, avg: 34.1, max: 59.0) -[2023-10-10 21:22:00,557][97672] Avg episode reward: [(0, '-3.820'), (1, '19.440')] -[2023-10-10 21:22:01,781][98560] Updated weights for policy 1, policy_version 16362 (0.0008) -[2023-10-10 21:22:02,153][98560] Updated weights for policy 1, policy_version 16372 (0.0008) -[2023-10-10 21:22:02,518][98560] Updated weights for policy 1, policy_version 16382 (0.0009) -[2023-10-10 21:22:04,003][98559] Updated weights for policy 0, policy_version 16360 (0.0009) -[2023-10-10 21:22:04,376][98559] Updated weights for policy 0, policy_version 16370 (0.0010) -[2023-10-10 21:22:04,753][98559] Updated weights for policy 0, policy_version 16380 (0.0009) -[2023-10-10 21:22:05,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 33554432. Throughput: 0: 1690.3, 1: 1717.1. Samples: 8397718. Policy #0 lag: (min: 8.0, avg: 27.0, max: 40.0) -[2023-10-10 21:22:05,557][97672] Avg episode reward: [(0, '-3.780'), (1, '19.260')] -[2023-10-10 21:22:05,570][98385] Saving new best policy, reward=-3.780! -[2023-10-10 21:22:06,550][98560] Updated weights for policy 1, policy_version 16392 (0.0008) -[2023-10-10 21:22:06,917][98560] Updated weights for policy 1, policy_version 16402 (0.0009) -[2023-10-10 21:22:07,279][98560] Updated weights for policy 1, policy_version 16412 (0.0010) -[2023-10-10 21:22:08,752][98559] Updated weights for policy 0, policy_version 16390 (0.0009) -[2023-10-10 21:22:09,135][98559] Updated weights for policy 0, policy_version 16400 (0.0010) -[2023-10-10 21:22:09,503][98559] Updated weights for policy 0, policy_version 16410 (0.0010) -[2023-10-10 21:22:10,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 33619968. Throughput: 0: 1719.5, 1: 1677.9. Samples: 8407974. Policy #0 lag: (min: 8.0, avg: 27.0, max: 40.0) -[2023-10-10 21:22:10,556][97672] Avg episode reward: [(0, '-3.780'), (1, '19.260')] -[2023-10-10 21:22:11,227][98560] Updated weights for policy 1, policy_version 16422 (0.0009) -[2023-10-10 21:22:11,599][98560] Updated weights for policy 1, policy_version 16432 (0.0009) -[2023-10-10 21:22:11,982][98560] Updated weights for policy 1, policy_version 16442 (0.0010) -[2023-10-10 21:22:13,578][98559] Updated weights for policy 0, policy_version 16420 (0.0010) -[2023-10-10 21:22:13,951][98559] Updated weights for policy 0, policy_version 16430 (0.0008) -[2023-10-10 21:22:14,324][98559] Updated weights for policy 0, policy_version 16440 (0.0007) -[2023-10-10 21:22:15,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 33685504. Throughput: 0: 1696.8, 1: 1709.4. Samples: 8428204. Policy #0 lag: (min: 8.0, avg: 27.0, max: 40.0) -[2023-10-10 21:22:15,557][97672] Avg episode reward: [(0, '-3.660'), (1, '19.580')] -[2023-10-10 21:22:15,558][98439] Saving new best policy, reward=19.580! -[2023-10-10 21:22:15,557][98385] Saving new best policy, reward=-3.660! -[2023-10-10 21:22:16,026][98560] Updated weights for policy 1, policy_version 16452 (0.0009) -[2023-10-10 21:22:16,399][98560] Updated weights for policy 1, policy_version 16462 (0.0008) -[2023-10-10 21:22:16,771][98560] Updated weights for policy 1, policy_version 16472 (0.0008) -[2023-10-10 21:22:18,432][98559] Updated weights for policy 0, policy_version 16450 (0.0008) -[2023-10-10 21:22:18,799][98559] Updated weights for policy 0, policy_version 16460 (0.0009) -[2023-10-10 21:22:19,172][98559] Updated weights for policy 0, policy_version 16470 (0.0008) -[2023-10-10 21:22:19,541][98559] Updated weights for policy 0, policy_version 16480 (0.0007) -[2023-10-10 21:22:20,556][97672] Fps is (10 sec: 13106.6, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 33751040. Throughput: 0: 1692.4, 1: 1712.0. Samples: 8448904. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 21:22:20,557][97672] Avg episode reward: [(0, '-3.620'), (1, '19.560')] -[2023-10-10 21:22:20,567][98385] Saving new best policy, reward=-3.620! -[2023-10-10 21:22:20,652][98560] Updated weights for policy 1, policy_version 16482 (0.0010) -[2023-10-10 21:22:21,016][98560] Updated weights for policy 1, policy_version 16492 (0.0008) -[2023-10-10 21:22:21,390][98560] Updated weights for policy 1, policy_version 16502 (0.0009) -[2023-10-10 21:22:21,758][98560] Updated weights for policy 1, policy_version 16512 (0.0009) -[2023-10-10 21:22:23,596][98559] Updated weights for policy 0, policy_version 16490 (0.0007) -[2023-10-10 21:22:23,974][98559] Updated weights for policy 0, policy_version 16500 (0.0008) -[2023-10-10 21:22:24,348][98559] Updated weights for policy 0, policy_version 16510 (0.0009) -[2023-10-10 21:22:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 33816576. Throughput: 0: 1718.6, 1: 1690.2. Samples: 8459494. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 21:22:25,556][97672] Avg episode reward: [(0, '-3.620'), (1, '19.640')] -[2023-10-10 21:22:25,875][98560] Updated weights for policy 1, policy_version 16522 (0.0009) -[2023-10-10 21:22:26,243][98560] Updated weights for policy 1, policy_version 16532 (0.0008) -[2023-10-10 21:22:26,606][98560] Updated weights for policy 1, policy_version 16542 (0.0007) -[2023-10-10 21:22:26,677][98439] Saving new best policy, reward=19.640! -[2023-10-10 21:22:28,319][98559] Updated weights for policy 0, policy_version 16520 (0.0010) -[2023-10-10 21:22:28,692][98559] Updated weights for policy 0, policy_version 16530 (0.0007) -[2023-10-10 21:22:29,061][98559] Updated weights for policy 0, policy_version 16540 (0.0009) -[2023-10-10 21:22:30,509][98560] Updated weights for policy 1, policy_version 16552 (0.0009) -[2023-10-10 21:22:30,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 33882112. Throughput: 0: 1688.4, 1: 1709.4. Samples: 8479290. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 21:22:30,557][97672] Avg episode reward: [(0, '-3.620'), (1, '19.720')] -[2023-10-10 21:22:30,875][98560] Updated weights for policy 1, policy_version 16562 (0.0007) -[2023-10-10 21:22:31,249][98560] Updated weights for policy 1, policy_version 16572 (0.0007) -[2023-10-10 21:22:31,397][98439] Saving new best policy, reward=19.720! -[2023-10-10 21:22:33,001][98559] Updated weights for policy 0, policy_version 16550 (0.0008) -[2023-10-10 21:22:33,368][98559] Updated weights for policy 0, policy_version 16560 (0.0009) -[2023-10-10 21:22:33,742][98559] Updated weights for policy 0, policy_version 16570 (0.0010) -[2023-10-10 21:22:35,409][98560] Updated weights for policy 1, policy_version 16582 (0.0009) -[2023-10-10 21:22:35,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 33947648. Throughput: 0: 1708.3, 1: 1713.1. Samples: 8500204. Policy #0 lag: (min: 9.0, avg: 28.7, max: 41.0) -[2023-10-10 21:22:35,556][97672] Avg episode reward: [(0, '-3.620'), (1, '19.780')] -[2023-10-10 21:22:35,565][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000016576_16973824.pth... -[2023-10-10 21:22:35,603][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000014976_15335424.pth -[2023-10-10 21:22:35,807][98560] Updated weights for policy 1, policy_version 16592 (0.0009) -[2023-10-10 21:22:36,179][98560] Updated weights for policy 1, policy_version 16602 (0.0010) -[2023-10-10 21:22:36,396][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000016608_17006592.pth... -[2023-10-10 21:22:36,424][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000015008_15368192.pth -[2023-10-10 21:22:36,428][98439] Saving new best policy, reward=19.780! -[2023-10-10 21:22:37,768][98559] Updated weights for policy 0, policy_version 16580 (0.0010) -[2023-10-10 21:22:38,136][98559] Updated weights for policy 0, policy_version 16590 (0.0009) -[2023-10-10 21:22:38,515][98559] Updated weights for policy 0, policy_version 16600 (0.0007) -[2023-10-10 21:22:40,092][98560] Updated weights for policy 1, policy_version 16612 (0.0009) -[2023-10-10 21:22:40,464][98560] Updated weights for policy 1, policy_version 16622 (0.0008) -[2023-10-10 21:22:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 34013184. Throughput: 0: 1696.4, 1: 1700.7. Samples: 8509950. Policy #0 lag: (min: 9.0, avg: 28.7, max: 41.0) -[2023-10-10 21:22:40,557][97672] Avg episode reward: [(0, '-3.580'), (1, '19.700')] -[2023-10-10 21:22:40,557][98385] Saving new best policy, reward=-3.580! -[2023-10-10 21:22:40,828][98560] Updated weights for policy 1, policy_version 16632 (0.0008) -[2023-10-10 21:22:42,363][98559] Updated weights for policy 0, policy_version 16610 (0.0008) -[2023-10-10 21:22:42,734][98559] Updated weights for policy 0, policy_version 16620 (0.0007) -[2023-10-10 21:22:43,100][98559] Updated weights for policy 0, policy_version 16630 (0.0009) -[2023-10-10 21:22:43,466][98559] Updated weights for policy 0, policy_version 16640 (0.0007) -[2023-10-10 21:22:44,846][98560] Updated weights for policy 1, policy_version 16642 (0.0009) -[2023-10-10 21:22:45,220][98560] Updated weights for policy 1, policy_version 16652 (0.0008) -[2023-10-10 21:22:45,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 34078720. Throughput: 0: 1695.3, 1: 1712.4. Samples: 8530580. Policy #0 lag: (min: 9.0, avg: 28.7, max: 41.0) -[2023-10-10 21:22:45,556][97672] Avg episode reward: [(0, '-3.580'), (1, '19.760')] -[2023-10-10 21:22:45,587][98560] Updated weights for policy 1, policy_version 16662 (0.0007) -[2023-10-10 21:22:45,963][98560] Updated weights for policy 1, policy_version 16672 (0.0008) -[2023-10-10 21:22:47,588][98559] Updated weights for policy 0, policy_version 16650 (0.0008) -[2023-10-10 21:22:47,962][98559] Updated weights for policy 0, policy_version 16660 (0.0008) -[2023-10-10 21:22:48,340][98559] Updated weights for policy 0, policy_version 16670 (0.0009) -[2023-10-10 21:22:49,943][98560] Updated weights for policy 1, policy_version 16682 (0.0008) -[2023-10-10 21:22:50,307][98560] Updated weights for policy 1, policy_version 16692 (0.0007) -[2023-10-10 21:22:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 34144256. Throughput: 0: 1714.9, 1: 1701.8. Samples: 8551470. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 21:22:50,557][97672] Avg episode reward: [(0, '-3.580'), (1, '19.780')] -[2023-10-10 21:22:50,678][98560] Updated weights for policy 1, policy_version 16702 (0.0009) -[2023-10-10 21:22:52,304][98559] Updated weights for policy 0, policy_version 16680 (0.0010) -[2023-10-10 21:22:52,683][98559] Updated weights for policy 0, policy_version 16690 (0.0008) -[2023-10-10 21:22:53,058][98559] Updated weights for policy 0, policy_version 16700 (0.0007) -[2023-10-10 21:22:54,760][98560] Updated weights for policy 1, policy_version 16712 (0.0008) -[2023-10-10 21:22:55,119][98560] Updated weights for policy 1, policy_version 16722 (0.0008) -[2023-10-10 21:22:55,493][98560] Updated weights for policy 1, policy_version 16732 (0.0008) -[2023-10-10 21:22:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 34209792. Throughput: 0: 1687.7, 1: 1708.6. Samples: 8560810. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 21:22:55,557][97672] Avg episode reward: [(0, '-3.580'), (1, '19.820')] -[2023-10-10 21:22:55,640][98439] Saving new best policy, reward=19.820! -[2023-10-10 21:22:57,058][98559] Updated weights for policy 0, policy_version 16710 (0.0010) -[2023-10-10 21:22:57,431][98559] Updated weights for policy 0, policy_version 16720 (0.0010) -[2023-10-10 21:22:57,810][98559] Updated weights for policy 0, policy_version 16730 (0.0010) -[2023-10-10 21:22:59,382][98560] Updated weights for policy 1, policy_version 16742 (0.0008) -[2023-10-10 21:22:59,759][98560] Updated weights for policy 1, policy_version 16752 (0.0009) -[2023-10-10 21:23:00,127][98560] Updated weights for policy 1, policy_version 16762 (0.0009) -[2023-10-10 21:23:00,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 34308096. Throughput: 0: 1712.7, 1: 1709.1. Samples: 8582182. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 21:23:00,557][97672] Avg episode reward: [(0, '-3.580'), (1, '19.700')] -[2023-10-10 21:23:01,771][98559] Updated weights for policy 0, policy_version 16740 (0.0008) -[2023-10-10 21:23:02,141][98559] Updated weights for policy 0, policy_version 16750 (0.0007) -[2023-10-10 21:23:02,516][98559] Updated weights for policy 0, policy_version 16760 (0.0008) -[2023-10-10 21:23:04,116][98560] Updated weights for policy 1, policy_version 16772 (0.0009) -[2023-10-10 21:23:04,490][98560] Updated weights for policy 1, policy_version 16782 (0.0009) -[2023-10-10 21:23:04,849][98560] Updated weights for policy 1, policy_version 16792 (0.0010) -[2023-10-10 21:23:05,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 34373632. Throughput: 0: 1722.1, 1: 1693.4. Samples: 8602602. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:23:05,556][97672] Avg episode reward: [(0, '-3.580'), (1, '19.660')] -[2023-10-10 21:23:06,471][98559] Updated weights for policy 0, policy_version 16770 (0.0007) -[2023-10-10 21:23:06,851][98559] Updated weights for policy 0, policy_version 16780 (0.0007) -[2023-10-10 21:23:07,210][98559] Updated weights for policy 0, policy_version 16790 (0.0010) -[2023-10-10 21:23:07,576][98559] Updated weights for policy 0, policy_version 16800 (0.0008) -[2023-10-10 21:23:08,824][98560] Updated weights for policy 1, policy_version 16802 (0.0008) -[2023-10-10 21:23:09,190][98560] Updated weights for policy 1, policy_version 16812 (0.0007) -[2023-10-10 21:23:09,563][98560] Updated weights for policy 1, policy_version 16822 (0.0011) -[2023-10-10 21:23:09,921][98560] Updated weights for policy 1, policy_version 16832 (0.0011) -[2023-10-10 21:23:10,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 34439168. Throughput: 0: 1689.9, 1: 1713.7. Samples: 8612656. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:23:10,557][97672] Avg episode reward: [(0, '-3.580'), (1, '19.920')] -[2023-10-10 21:23:10,558][98439] Saving new best policy, reward=19.920! -[2023-10-10 21:23:11,523][98559] Updated weights for policy 0, policy_version 16810 (0.0007) -[2023-10-10 21:23:11,907][98559] Updated weights for policy 0, policy_version 16820 (0.0008) -[2023-10-10 21:23:12,284][98559] Updated weights for policy 0, policy_version 16830 (0.0009) -[2023-10-10 21:23:13,966][98560] Updated weights for policy 1, policy_version 16842 (0.0007) -[2023-10-10 21:23:14,333][98560] Updated weights for policy 1, policy_version 16852 (0.0007) -[2023-10-10 21:23:14,711][98560] Updated weights for policy 1, policy_version 16862 (0.0008) -[2023-10-10 21:23:15,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 34504704. Throughput: 0: 1717.7, 1: 1710.0. Samples: 8633536. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:23:15,557][97672] Avg episode reward: [(0, '-3.580'), (1, '19.980')] -[2023-10-10 21:23:15,558][98439] Saving new best policy, reward=19.980! -[2023-10-10 21:23:16,197][98559] Updated weights for policy 0, policy_version 16840 (0.0009) -[2023-10-10 21:23:16,565][98559] Updated weights for policy 0, policy_version 16850 (0.0010) -[2023-10-10 21:23:16,937][98559] Updated weights for policy 0, policy_version 16860 (0.0010) -[2023-10-10 21:23:18,806][98560] Updated weights for policy 1, policy_version 16872 (0.0008) -[2023-10-10 21:23:19,172][98560] Updated weights for policy 1, policy_version 16882 (0.0011) -[2023-10-10 21:23:19,542][98560] Updated weights for policy 1, policy_version 16892 (0.0009) -[2023-10-10 21:23:20,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 34570240. Throughput: 0: 1718.9, 1: 1680.7. Samples: 8653184. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:23:20,558][97672] Avg episode reward: [(0, '-3.580'), (1, '19.840')] -[2023-10-10 21:23:20,906][98559] Updated weights for policy 0, policy_version 16870 (0.0009) -[2023-10-10 21:23:21,286][98559] Updated weights for policy 0, policy_version 16880 (0.0008) -[2023-10-10 21:23:21,654][98559] Updated weights for policy 0, policy_version 16890 (0.0009) -[2023-10-10 21:23:23,649][98560] Updated weights for policy 1, policy_version 16902 (0.0008) -[2023-10-10 21:23:24,043][98560] Updated weights for policy 1, policy_version 16912 (0.0008) -[2023-10-10 21:23:24,405][98560] Updated weights for policy 1, policy_version 16922 (0.0007) -[2023-10-10 21:23:25,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 34635776. Throughput: 0: 1702.2, 1: 1712.6. Samples: 8663614. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:23:25,557][97672] Avg episode reward: [(0, '-3.580'), (1, '19.900')] -[2023-10-10 21:23:25,611][98559] Updated weights for policy 0, policy_version 16900 (0.0007) -[2023-10-10 21:23:25,979][98559] Updated weights for policy 0, policy_version 16910 (0.0009) -[2023-10-10 21:23:26,347][98559] Updated weights for policy 0, policy_version 16920 (0.0010) -[2023-10-10 21:23:28,217][98560] Updated weights for policy 1, policy_version 16932 (0.0009) -[2023-10-10 21:23:28,585][98560] Updated weights for policy 1, policy_version 16942 (0.0009) -[2023-10-10 21:23:28,950][98560] Updated weights for policy 1, policy_version 16952 (0.0010) -[2023-10-10 21:23:30,196][98559] Updated weights for policy 0, policy_version 16930 (0.0009) -[2023-10-10 21:23:30,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 34701312. Throughput: 0: 1725.1, 1: 1692.0. Samples: 8684348. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:23:30,557][97672] Avg episode reward: [(0, '-3.580'), (1, '19.940')] -[2023-10-10 21:23:30,570][98559] Updated weights for policy 0, policy_version 16940 (0.0011) -[2023-10-10 21:23:30,937][98559] Updated weights for policy 0, policy_version 16950 (0.0008) -[2023-10-10 21:23:31,310][98559] Updated weights for policy 0, policy_version 16960 (0.0008) -[2023-10-10 21:23:32,872][98560] Updated weights for policy 1, policy_version 16962 (0.0008) -[2023-10-10 21:23:33,247][98560] Updated weights for policy 1, policy_version 16972 (0.0007) -[2023-10-10 21:23:33,625][98560] Updated weights for policy 1, policy_version 16982 (0.0008) -[2023-10-10 21:23:33,989][98560] Updated weights for policy 1, policy_version 16992 (0.0009) -[2023-10-10 21:23:35,429][98559] Updated weights for policy 0, policy_version 16970 (0.0009) -[2023-10-10 21:23:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 34766848. Throughput: 0: 1712.6, 1: 1684.7. Samples: 8704346. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-10 21:23:35,557][97672] Avg episode reward: [(0, '-3.580'), (1, '20.260')] -[2023-10-10 21:23:35,567][98439] Saving new best policy, reward=20.260! -[2023-10-10 21:23:35,787][98559] Updated weights for policy 0, policy_version 16980 (0.0011) -[2023-10-10 21:23:36,157][98559] Updated weights for policy 0, policy_version 16990 (0.0010) -[2023-10-10 21:23:38,219][98560] Updated weights for policy 1, policy_version 17002 (0.0011) -[2023-10-10 21:23:38,595][98560] Updated weights for policy 1, policy_version 17012 (0.0007) -[2023-10-10 21:23:38,970][98560] Updated weights for policy 1, policy_version 17022 (0.0008) -[2023-10-10 21:23:40,078][98559] Updated weights for policy 0, policy_version 17000 (0.0009) -[2023-10-10 21:23:40,452][98559] Updated weights for policy 0, policy_version 17010 (0.0010) -[2023-10-10 21:23:40,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 34832384. Throughput: 0: 1719.8, 1: 1714.3. Samples: 8715342. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-10 21:23:40,557][97672] Avg episode reward: [(0, '-3.580'), (1, '20.160')] -[2023-10-10 21:23:40,829][98559] Updated weights for policy 0, policy_version 17020 (0.0011) -[2023-10-10 21:23:43,008][98560] Updated weights for policy 1, policy_version 17032 (0.0009) -[2023-10-10 21:23:43,370][98560] Updated weights for policy 1, policy_version 17042 (0.0010) -[2023-10-10 21:23:43,748][98560] Updated weights for policy 1, policy_version 17052 (0.0007) -[2023-10-10 21:23:44,850][98559] Updated weights for policy 0, policy_version 17030 (0.0008) -[2023-10-10 21:23:45,223][98559] Updated weights for policy 0, policy_version 17040 (0.0010) -[2023-10-10 21:23:45,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 34897920. Throughput: 0: 1716.1, 1: 1683.8. Samples: 8735180. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-10 21:23:45,557][97672] Avg episode reward: [(0, '-3.580'), (1, '20.180')] -[2023-10-10 21:23:45,598][98559] Updated weights for policy 0, policy_version 17050 (0.0011) -[2023-10-10 21:23:47,750][98560] Updated weights for policy 1, policy_version 17062 (0.0008) -[2023-10-10 21:23:48,125][98560] Updated weights for policy 1, policy_version 17072 (0.0009) -[2023-10-10 21:23:48,491][98560] Updated weights for policy 1, policy_version 17082 (0.0008) -[2023-10-10 21:23:49,575][98559] Updated weights for policy 0, policy_version 17060 (0.0008) -[2023-10-10 21:23:49,953][98559] Updated weights for policy 0, policy_version 17070 (0.0009) -[2023-10-10 21:23:50,329][98559] Updated weights for policy 0, policy_version 17080 (0.0009) -[2023-10-10 21:23:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 34963456. Throughput: 0: 1690.6, 1: 1686.5. Samples: 8754570. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) -[2023-10-10 21:23:50,557][97672] Avg episode reward: [(0, '-3.580'), (1, '20.160')] -[2023-10-10 21:23:52,514][98560] Updated weights for policy 1, policy_version 17092 (0.0010) -[2023-10-10 21:23:52,883][98560] Updated weights for policy 1, policy_version 17102 (0.0010) -[2023-10-10 21:23:53,247][98560] Updated weights for policy 1, policy_version 17112 (0.0011) -[2023-10-10 21:23:54,408][98559] Updated weights for policy 0, policy_version 17090 (0.0009) -[2023-10-10 21:23:54,775][98559] Updated weights for policy 0, policy_version 17100 (0.0008) -[2023-10-10 21:23:55,153][98559] Updated weights for policy 0, policy_version 17110 (0.0007) -[2023-10-10 21:23:55,516][98559] Updated weights for policy 0, policy_version 17120 (0.0008) -[2023-10-10 21:23:55,556][97672] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 35061760. Throughput: 0: 1712.4, 1: 1688.5. Samples: 8765694. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) -[2023-10-10 21:23:55,556][97672] Avg episode reward: [(0, '-3.580'), (1, '20.280')] -[2023-10-10 21:23:55,557][98439] Saving new best policy, reward=20.280! -[2023-10-10 21:23:57,299][98560] Updated weights for policy 1, policy_version 17122 (0.0009) -[2023-10-10 21:23:57,677][98560] Updated weights for policy 1, policy_version 17132 (0.0008) -[2023-10-10 21:23:58,045][98560] Updated weights for policy 1, policy_version 17142 (0.0007) -[2023-10-10 21:23:58,413][98560] Updated weights for policy 1, policy_version 17152 (0.0008) -[2023-10-10 21:23:59,360][98559] Updated weights for policy 0, policy_version 17130 (0.0007) -[2023-10-10 21:23:59,736][98559] Updated weights for policy 0, policy_version 17140 (0.0008) -[2023-10-10 21:24:00,114][98559] Updated weights for policy 0, policy_version 17150 (0.0009) -[2023-10-10 21:24:00,556][97672] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 35127296. Throughput: 0: 1706.8, 1: 1670.4. Samples: 8785508. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:24:00,556][97672] Avg episode reward: [(0, '-3.580'), (1, '20.540')] -[2023-10-10 21:24:00,557][98439] Saving new best policy, reward=20.540! -[2023-10-10 21:24:02,581][98560] Updated weights for policy 1, policy_version 17162 (0.0011) -[2023-10-10 21:24:02,947][98560] Updated weights for policy 1, policy_version 17172 (0.0010) -[2023-10-10 21:24:03,315][98560] Updated weights for policy 1, policy_version 17182 (0.0007) -[2023-10-10 21:24:04,029][98559] Updated weights for policy 0, policy_version 17160 (0.0011) -[2023-10-10 21:24:04,401][98559] Updated weights for policy 0, policy_version 17170 (0.0008) -[2023-10-10 21:24:04,772][98559] Updated weights for policy 0, policy_version 17180 (0.0008) -[2023-10-10 21:24:05,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 35192832. Throughput: 0: 1690.3, 1: 1696.4. Samples: 8805584. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:24:05,557][97672] Avg episode reward: [(0, '-3.580'), (1, '20.540')] -[2023-10-10 21:24:07,254][98560] Updated weights for policy 1, policy_version 17192 (0.0010) -[2023-10-10 21:24:07,621][98560] Updated weights for policy 1, policy_version 17202 (0.0009) -[2023-10-10 21:24:07,998][98560] Updated weights for policy 1, policy_version 17212 (0.0010) -[2023-10-10 21:24:08,804][98559] Updated weights for policy 0, policy_version 17190 (0.0008) -[2023-10-10 21:24:09,171][98559] Updated weights for policy 0, policy_version 17200 (0.0009) -[2023-10-10 21:24:09,544][98559] Updated weights for policy 0, policy_version 17210 (0.0009) -[2023-10-10 21:24:10,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 35258368. Throughput: 0: 1718.8, 1: 1680.6. Samples: 8816586. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:24:10,557][97672] Avg episode reward: [(0, '-3.580'), (1, '20.580')] -[2023-10-10 21:24:10,559][98439] Saving new best policy, reward=20.580! -[2023-10-10 21:24:12,134][98560] Updated weights for policy 1, policy_version 17222 (0.0007) -[2023-10-10 21:24:12,506][98560] Updated weights for policy 1, policy_version 17232 (0.0009) -[2023-10-10 21:24:12,885][98560] Updated weights for policy 1, policy_version 17242 (0.0009) -[2023-10-10 21:24:13,566][98559] Updated weights for policy 0, policy_version 17220 (0.0009) -[2023-10-10 21:24:13,939][98559] Updated weights for policy 0, policy_version 17230 (0.0009) -[2023-10-10 21:24:14,302][98559] Updated weights for policy 0, policy_version 17240 (0.0008) -[2023-10-10 21:24:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 35323904. Throughput: 0: 1686.0, 1: 1685.2. Samples: 8836050. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-10 21:24:15,557][97672] Avg episode reward: [(0, '-3.580'), (1, '20.600')] -[2023-10-10 21:24:15,559][98439] Saving new best policy, reward=20.600! -[2023-10-10 21:24:16,956][98560] Updated weights for policy 1, policy_version 17252 (0.0008) -[2023-10-10 21:24:17,327][98560] Updated weights for policy 1, policy_version 17262 (0.0008) -[2023-10-10 21:24:17,685][98560] Updated weights for policy 1, policy_version 17272 (0.0008) -[2023-10-10 21:24:18,178][98559] Updated weights for policy 0, policy_version 17250 (0.0008) -[2023-10-10 21:24:18,540][98559] Updated weights for policy 0, policy_version 17260 (0.0007) -[2023-10-10 21:24:18,909][98559] Updated weights for policy 0, policy_version 17270 (0.0007) -[2023-10-10 21:24:19,275][98559] Updated weights for policy 0, policy_version 17280 (0.0008) -[2023-10-10 21:24:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 35389440. Throughput: 0: 1692.0, 1: 1701.2. Samples: 8857040. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-10 21:24:20,557][97672] Avg episode reward: [(0, '-3.560'), (1, '20.820')] -[2023-10-10 21:24:20,568][98385] Saving new best policy, reward=-3.560! -[2023-10-10 21:24:20,568][98439] Saving new best policy, reward=20.820! -[2023-10-10 21:24:21,641][98560] Updated weights for policy 1, policy_version 17282 (0.0009) -[2023-10-10 21:24:22,014][98560] Updated weights for policy 1, policy_version 17292 (0.0008) -[2023-10-10 21:24:22,377][98560] Updated weights for policy 1, policy_version 17302 (0.0007) -[2023-10-10 21:24:22,744][98560] Updated weights for policy 1, policy_version 17312 (0.0009) -[2023-10-10 21:24:23,307][98559] Updated weights for policy 0, policy_version 17290 (0.0008) -[2023-10-10 21:24:23,684][98559] Updated weights for policy 0, policy_version 17300 (0.0007) -[2023-10-10 21:24:24,039][98559] Updated weights for policy 0, policy_version 17310 (0.0007) -[2023-10-10 21:24:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 35454976. Throughput: 0: 1705.0, 1: 1670.6. Samples: 8867242. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-10 21:24:25,557][97672] Avg episode reward: [(0, '-3.560'), (1, '20.720')] -[2023-10-10 21:24:26,720][98560] Updated weights for policy 1, policy_version 17322 (0.0007) -[2023-10-10 21:24:27,102][98560] Updated weights for policy 1, policy_version 17332 (0.0009) -[2023-10-10 21:24:27,468][98560] Updated weights for policy 1, policy_version 17342 (0.0007) -[2023-10-10 21:24:28,109][98559] Updated weights for policy 0, policy_version 17320 (0.0011) -[2023-10-10 21:24:28,488][98559] Updated weights for policy 0, policy_version 17330 (0.0007) -[2023-10-10 21:24:28,851][98559] Updated weights for policy 0, policy_version 17340 (0.0008) -[2023-10-10 21:24:30,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 35520512. Throughput: 0: 1691.0, 1: 1692.0. Samples: 8887416. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-10 21:24:30,557][97672] Avg episode reward: [(0, '-3.540'), (1, '20.720')] -[2023-10-10 21:24:30,558][98385] Saving new best policy, reward=-3.540! -[2023-10-10 21:24:31,498][98560] Updated weights for policy 1, policy_version 17352 (0.0008) -[2023-10-10 21:24:31,866][98560] Updated weights for policy 1, policy_version 17362 (0.0008) -[2023-10-10 21:24:32,239][98560] Updated weights for policy 1, policy_version 17372 (0.0007) -[2023-10-10 21:24:32,809][98559] Updated weights for policy 0, policy_version 17350 (0.0008) -[2023-10-10 21:24:33,184][98559] Updated weights for policy 0, policy_version 17360 (0.0009) -[2023-10-10 21:24:33,555][98559] Updated weights for policy 0, policy_version 17370 (0.0008) -[2023-10-10 21:24:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 35586048. Throughput: 0: 1713.6, 1: 1704.4. Samples: 8908382. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-10 21:24:35,557][97672] Avg episode reward: [(0, '-3.540'), (1, '20.680')] -[2023-10-10 21:24:35,568][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000017376_17793024.pth... -[2023-10-10 21:24:35,569][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000017376_17793024.pth... -[2023-10-10 21:24:35,598][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000015808_16187392.pth -[2023-10-10 21:24:35,602][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000015776_16154624.pth -[2023-10-10 21:24:36,236][98560] Updated weights for policy 1, policy_version 17382 (0.0009) -[2023-10-10 21:24:36,597][98560] Updated weights for policy 1, policy_version 17392 (0.0010) -[2023-10-10 21:24:36,963][98560] Updated weights for policy 1, policy_version 17402 (0.0009) -[2023-10-10 21:24:37,574][98559] Updated weights for policy 0, policy_version 17380 (0.0008) -[2023-10-10 21:24:37,946][98559] Updated weights for policy 0, policy_version 17390 (0.0008) -[2023-10-10 21:24:38,313][98559] Updated weights for policy 0, policy_version 17400 (0.0007) -[2023-10-10 21:24:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 35651584. Throughput: 0: 1701.6, 1: 1681.2. Samples: 8917920. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-10 21:24:40,556][97672] Avg episode reward: [(0, '-3.540'), (1, '20.820')] -[2023-10-10 21:24:41,055][98560] Updated weights for policy 1, policy_version 17412 (0.0009) -[2023-10-10 21:24:41,426][98560] Updated weights for policy 1, policy_version 17422 (0.0007) -[2023-10-10 21:24:41,789][98560] Updated weights for policy 1, policy_version 17432 (0.0009) -[2023-10-10 21:24:42,234][98559] Updated weights for policy 0, policy_version 17410 (0.0008) -[2023-10-10 21:24:42,611][98559] Updated weights for policy 0, policy_version 17420 (0.0009) -[2023-10-10 21:24:42,975][98559] Updated weights for policy 0, policy_version 17430 (0.0008) -[2023-10-10 21:24:43,355][98559] Updated weights for policy 0, policy_version 17440 (0.0007) -[2023-10-10 21:24:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 35717120. Throughput: 0: 1700.7, 1: 1702.3. Samples: 8938644. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:24:45,557][97672] Avg episode reward: [(0, '-3.540'), (1, '20.720')] -[2023-10-10 21:24:45,875][98560] Updated weights for policy 1, policy_version 17442 (0.0008) -[2023-10-10 21:24:46,240][98560] Updated weights for policy 1, policy_version 17452 (0.0008) -[2023-10-10 21:24:46,609][98560] Updated weights for policy 1, policy_version 17462 (0.0009) -[2023-10-10 21:24:46,985][98560] Updated weights for policy 1, policy_version 17472 (0.0009) -[2023-10-10 21:24:47,316][98559] Updated weights for policy 0, policy_version 17450 (0.0010) -[2023-10-10 21:24:47,683][98559] Updated weights for policy 0, policy_version 17460 (0.0009) -[2023-10-10 21:24:48,051][98559] Updated weights for policy 0, policy_version 17470 (0.0008) -[2023-10-10 21:24:50,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 35782656. Throughput: 0: 1721.6, 1: 1700.0. Samples: 8959556. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:24:50,557][97672] Avg episode reward: [(0, '-3.420'), (1, '20.720')] -[2023-10-10 21:24:50,569][98385] Saving new best policy, reward=-3.420! -[2023-10-10 21:24:51,052][98560] Updated weights for policy 1, policy_version 17482 (0.0008) -[2023-10-10 21:24:51,417][98560] Updated weights for policy 1, policy_version 17492 (0.0011) -[2023-10-10 21:24:51,786][98560] Updated weights for policy 1, policy_version 17502 (0.0009) -[2023-10-10 21:24:52,178][98559] Updated weights for policy 0, policy_version 17480 (0.0008) -[2023-10-10 21:24:52,557][98559] Updated weights for policy 0, policy_version 17490 (0.0007) -[2023-10-10 21:24:52,929][98559] Updated weights for policy 0, policy_version 17500 (0.0008) -[2023-10-10 21:24:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 35848192. Throughput: 0: 1695.2, 1: 1687.6. Samples: 8968812. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:24:55,557][97672] Avg episode reward: [(0, '-3.300'), (1, '20.860')] -[2023-10-10 21:24:55,558][98385] Saving new best policy, reward=-3.300! -[2023-10-10 21:24:55,845][98560] Updated weights for policy 1, policy_version 17512 (0.0008) -[2023-10-10 21:24:56,216][98560] Updated weights for policy 1, policy_version 17522 (0.0011) -[2023-10-10 21:24:56,581][98560] Updated weights for policy 1, policy_version 17532 (0.0007) -[2023-10-10 21:24:56,706][98559] Updated weights for policy 0, policy_version 17510 (0.0007) -[2023-10-10 21:24:56,729][98439] Saving new best policy, reward=20.860! -[2023-10-10 21:24:57,077][98559] Updated weights for policy 0, policy_version 17520 (0.0007) -[2023-10-10 21:24:57,444][98559] Updated weights for policy 0, policy_version 17530 (0.0009) -[2023-10-10 21:25:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 35913728. Throughput: 0: 1724.5, 1: 1698.8. Samples: 8990098. Policy #0 lag: (min: 31.0, avg: 39.9, max: 63.0) -[2023-10-10 21:25:00,557][97672] Avg episode reward: [(0, '-3.300'), (1, '20.940')] -[2023-10-10 21:25:00,687][98560] Updated weights for policy 1, policy_version 17542 (0.0008) -[2023-10-10 21:25:01,071][98560] Updated weights for policy 1, policy_version 17552 (0.0009) -[2023-10-10 21:25:01,412][98559] Updated weights for policy 0, policy_version 17540 (0.0007) -[2023-10-10 21:25:01,446][98560] Updated weights for policy 1, policy_version 17562 (0.0010) -[2023-10-10 21:25:01,664][98439] Saving new best policy, reward=20.940! -[2023-10-10 21:25:01,788][98559] Updated weights for policy 0, policy_version 17550 (0.0009) -[2023-10-10 21:25:02,159][98559] Updated weights for policy 0, policy_version 17560 (0.0008) -[2023-10-10 21:25:05,292][98560] Updated weights for policy 1, policy_version 17572 (0.0007) -[2023-10-10 21:25:05,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 35979264. Throughput: 0: 1732.4, 1: 1694.2. Samples: 9011236. Policy #0 lag: (min: 31.0, avg: 39.9, max: 63.0) -[2023-10-10 21:25:05,556][97672] Avg episode reward: [(0, '-3.260'), (1, '20.960')] -[2023-10-10 21:25:05,567][98385] Saving new best policy, reward=-3.260! -[2023-10-10 21:25:05,658][98560] Updated weights for policy 1, policy_version 17582 (0.0008) -[2023-10-10 21:25:05,985][98559] Updated weights for policy 0, policy_version 17570 (0.0008) -[2023-10-10 21:25:06,023][98560] Updated weights for policy 1, policy_version 17592 (0.0008) -[2023-10-10 21:25:06,313][98439] Saving new best policy, reward=20.960! -[2023-10-10 21:25:06,347][98559] Updated weights for policy 0, policy_version 17580 (0.0009) -[2023-10-10 21:25:06,728][98559] Updated weights for policy 0, policy_version 17590 (0.0011) -[2023-10-10 21:25:07,089][98559] Updated weights for policy 0, policy_version 17600 (0.0010) -[2023-10-10 21:25:10,177][98560] Updated weights for policy 1, policy_version 17602 (0.0008) -[2023-10-10 21:25:10,545][98560] Updated weights for policy 1, policy_version 17612 (0.0009) -[2023-10-10 21:25:10,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 36044800. Throughput: 0: 1709.1, 1: 1690.5. Samples: 9020224. Policy #0 lag: (min: 31.0, avg: 39.9, max: 63.0) -[2023-10-10 21:25:10,557][97672] Avg episode reward: [(0, '-3.260'), (1, '20.960')] -[2023-10-10 21:25:10,905][98560] Updated weights for policy 1, policy_version 17622 (0.0009) -[2023-10-10 21:25:11,208][98559] Updated weights for policy 0, policy_version 17610 (0.0008) -[2023-10-10 21:25:11,275][98560] Updated weights for policy 1, policy_version 17632 (0.0008) -[2023-10-10 21:25:11,574][98559] Updated weights for policy 0, policy_version 17620 (0.0010) -[2023-10-10 21:25:11,948][98559] Updated weights for policy 0, policy_version 17630 (0.0011) -[2023-10-10 21:25:15,407][98560] Updated weights for policy 1, policy_version 17642 (0.0008) -[2023-10-10 21:25:15,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 36110336. Throughput: 0: 1728.5, 1: 1690.1. Samples: 9041254. Policy #0 lag: (min: 24.0, avg: 49.4, max: 56.0) -[2023-10-10 21:25:15,557][97672] Avg episode reward: [(0, '-3.260'), (1, '21.020')] -[2023-10-10 21:25:15,777][98560] Updated weights for policy 1, policy_version 17652 (0.0008) -[2023-10-10 21:25:15,835][98559] Updated weights for policy 0, policy_version 17640 (0.0008) -[2023-10-10 21:25:16,144][98560] Updated weights for policy 1, policy_version 17662 (0.0008) -[2023-10-10 21:25:16,207][98559] Updated weights for policy 0, policy_version 17650 (0.0009) -[2023-10-10 21:25:16,213][98439] Saving new best policy, reward=21.020! -[2023-10-10 21:25:16,591][98559] Updated weights for policy 0, policy_version 17660 (0.0009) -[2023-10-10 21:25:20,203][98560] Updated weights for policy 1, policy_version 17672 (0.0007) -[2023-10-10 21:25:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 36175872. Throughput: 0: 1727.9, 1: 1691.9. Samples: 9062274. Policy #0 lag: (min: 24.0, avg: 49.4, max: 56.0) -[2023-10-10 21:25:20,557][97672] Avg episode reward: [(0, '-3.280'), (1, '21.140')] -[2023-10-10 21:25:20,565][98559] Updated weights for policy 0, policy_version 17670 (0.0010) -[2023-10-10 21:25:20,565][98560] Updated weights for policy 1, policy_version 17682 (0.0007) -[2023-10-10 21:25:20,929][98559] Updated weights for policy 0, policy_version 17680 (0.0008) -[2023-10-10 21:25:20,942][98560] Updated weights for policy 1, policy_version 17692 (0.0008) -[2023-10-10 21:25:21,080][98439] Saving new best policy, reward=21.140! -[2023-10-10 21:25:21,296][98559] Updated weights for policy 0, policy_version 17690 (0.0009) -[2023-10-10 21:25:25,063][98560] Updated weights for policy 1, policy_version 17702 (0.0008) -[2023-10-10 21:25:25,430][98560] Updated weights for policy 1, policy_version 17712 (0.0009) -[2023-10-10 21:25:25,507][98559] Updated weights for policy 0, policy_version 17700 (0.0009) -[2023-10-10 21:25:25,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 36241408. Throughput: 0: 1722.2, 1: 1691.6. Samples: 9071540. Policy #0 lag: (min: 24.0, avg: 49.4, max: 56.0) -[2023-10-10 21:25:25,557][97672] Avg episode reward: [(0, '-3.280'), (1, '21.160')] -[2023-10-10 21:25:25,801][98560] Updated weights for policy 1, policy_version 17722 (0.0008) -[2023-10-10 21:25:25,882][98559] Updated weights for policy 0, policy_version 17710 (0.0008) -[2023-10-10 21:25:26,025][98439] Saving new best policy, reward=21.160! -[2023-10-10 21:25:26,256][98559] Updated weights for policy 0, policy_version 17720 (0.0007) -[2023-10-10 21:25:29,771][98560] Updated weights for policy 1, policy_version 17732 (0.0008) -[2023-10-10 21:25:30,141][98560] Updated weights for policy 1, policy_version 17742 (0.0008) -[2023-10-10 21:25:30,286][98559] Updated weights for policy 0, policy_version 17730 (0.0010) -[2023-10-10 21:25:30,511][98560] Updated weights for policy 1, policy_version 17752 (0.0008) -[2023-10-10 21:25:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 36306944. Throughput: 0: 1725.0, 1: 1684.5. Samples: 9092072. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:25:30,558][97672] Avg episode reward: [(0, '-3.280'), (1, '21.260')] -[2023-10-10 21:25:30,661][98559] Updated weights for policy 0, policy_version 17740 (0.0009) -[2023-10-10 21:25:30,799][98439] Saving new best policy, reward=21.260! -[2023-10-10 21:25:31,029][98559] Updated weights for policy 0, policy_version 17750 (0.0008) -[2023-10-10 21:25:31,409][98559] Updated weights for policy 0, policy_version 17760 (0.0009) -[2023-10-10 21:25:34,231][98560] Updated weights for policy 1, policy_version 17762 (0.0010) -[2023-10-10 21:25:34,589][98560] Updated weights for policy 1, policy_version 17772 (0.0010) -[2023-10-10 21:25:34,966][98560] Updated weights for policy 1, policy_version 17782 (0.0009) -[2023-10-10 21:25:35,290][98559] Updated weights for policy 0, policy_version 17770 (0.0010) -[2023-10-10 21:25:35,341][98560] Updated weights for policy 1, policy_version 17792 (0.0009) -[2023-10-10 21:25:35,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 36405248. Throughput: 0: 1712.1, 1: 1677.7. Samples: 9112096. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:25:35,557][97672] Avg episode reward: [(0, '-3.280'), (1, '21.240')] -[2023-10-10 21:25:35,668][98559] Updated weights for policy 0, policy_version 17780 (0.0008) -[2023-10-10 21:25:36,041][98559] Updated weights for policy 0, policy_version 17790 (0.0007) -[2023-10-10 21:25:39,477][98560] Updated weights for policy 1, policy_version 17802 (0.0008) -[2023-10-10 21:25:39,857][98560] Updated weights for policy 1, policy_version 17812 (0.0008) -[2023-10-10 21:25:40,026][98559] Updated weights for policy 0, policy_version 17800 (0.0009) -[2023-10-10 21:25:40,221][98560] Updated weights for policy 1, policy_version 17822 (0.0009) -[2023-10-10 21:25:40,383][98559] Updated weights for policy 0, policy_version 17810 (0.0009) -[2023-10-10 21:25:40,556][97672] Fps is (10 sec: 16384.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 36470784. Throughput: 0: 1720.6, 1: 1690.9. Samples: 9122330. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:25:40,557][97672] Avg episode reward: [(0, '-3.360'), (1, '21.320')] -[2023-10-10 21:25:40,558][98439] Saving new best policy, reward=21.320! -[2023-10-10 21:25:40,756][98559] Updated weights for policy 0, policy_version 17820 (0.0009) -[2023-10-10 21:25:44,357][98560] Updated weights for policy 1, policy_version 17832 (0.0009) -[2023-10-10 21:25:44,724][98560] Updated weights for policy 1, policy_version 17842 (0.0008) -[2023-10-10 21:25:44,907][98559] Updated weights for policy 0, policy_version 17830 (0.0008) -[2023-10-10 21:25:45,089][98560] Updated weights for policy 1, policy_version 17852 (0.0008) -[2023-10-10 21:25:45,269][98559] Updated weights for policy 0, policy_version 17840 (0.0007) -[2023-10-10 21:25:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 36536320. Throughput: 0: 1707.2, 1: 1686.4. Samples: 9142808. Policy #0 lag: (min: 18.0, avg: 26.0, max: 50.0) -[2023-10-10 21:25:45,556][97672] Avg episode reward: [(0, '-3.360'), (1, '21.500')] -[2023-10-10 21:25:45,557][98439] Saving new best policy, reward=21.500! -[2023-10-10 21:25:45,650][98559] Updated weights for policy 0, policy_version 17850 (0.0010) -[2023-10-10 21:25:49,353][98560] Updated weights for policy 1, policy_version 17862 (0.0010) -[2023-10-10 21:25:49,673][98559] Updated weights for policy 0, policy_version 17860 (0.0010) -[2023-10-10 21:25:49,729][98560] Updated weights for policy 1, policy_version 17872 (0.0008) -[2023-10-10 21:25:50,037][98559] Updated weights for policy 0, policy_version 17870 (0.0008) -[2023-10-10 21:25:50,085][98560] Updated weights for policy 1, policy_version 17882 (0.0007) -[2023-10-10 21:25:50,413][98559] Updated weights for policy 0, policy_version 17880 (0.0007) -[2023-10-10 21:25:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 36601856. Throughput: 0: 1682.0, 1: 1667.1. Samples: 9161946. Policy #0 lag: (min: 18.0, avg: 26.0, max: 50.0) -[2023-10-10 21:25:50,557][97672] Avg episode reward: [(0, '-3.360'), (1, '21.420')] -[2023-10-10 21:25:54,323][98560] Updated weights for policy 1, policy_version 17892 (0.0008) -[2023-10-10 21:25:54,465][98559] Updated weights for policy 0, policy_version 17890 (0.0008) -[2023-10-10 21:25:54,690][98560] Updated weights for policy 1, policy_version 17902 (0.0010) -[2023-10-10 21:25:54,834][98559] Updated weights for policy 0, policy_version 17900 (0.0009) -[2023-10-10 21:25:55,056][98560] Updated weights for policy 1, policy_version 17912 (0.0009) -[2023-10-10 21:25:55,206][98559] Updated weights for policy 0, policy_version 17910 (0.0008) -[2023-10-10 21:25:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 36667392. Throughput: 0: 1704.7, 1: 1681.3. Samples: 9172596. Policy #0 lag: (min: 18.0, avg: 26.0, max: 50.0) -[2023-10-10 21:25:55,557][97672] Avg episode reward: [(0, '-3.360'), (1, '21.340')] -[2023-10-10 21:25:55,580][98559] Updated weights for policy 0, policy_version 17920 (0.0008) -[2023-10-10 21:25:59,038][98560] Updated weights for policy 1, policy_version 17922 (0.0008) -[2023-10-10 21:25:59,404][98560] Updated weights for policy 1, policy_version 17932 (0.0008) -[2023-10-10 21:25:59,774][98559] Updated weights for policy 0, policy_version 17930 (0.0007) -[2023-10-10 21:25:59,774][98560] Updated weights for policy 1, policy_version 17942 (0.0008) -[2023-10-10 21:26:00,140][98559] Updated weights for policy 0, policy_version 17940 (0.0009) -[2023-10-10 21:26:00,141][98560] Updated weights for policy 1, policy_version 17952 (0.0009) -[2023-10-10 21:26:00,508][98559] Updated weights for policy 0, policy_version 17950 (0.0009) -[2023-10-10 21:26:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 36732928. Throughput: 0: 1696.2, 1: 1684.5. Samples: 9193386. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-10 21:26:00,557][97672] Avg episode reward: [(0, '-3.360'), (1, '21.180')] -[2023-10-10 21:26:04,125][98560] Updated weights for policy 1, policy_version 17962 (0.0009) -[2023-10-10 21:26:04,284][98559] Updated weights for policy 0, policy_version 17960 (0.0009) -[2023-10-10 21:26:04,487][98560] Updated weights for policy 1, policy_version 17972 (0.0008) -[2023-10-10 21:26:04,648][98559] Updated weights for policy 0, policy_version 17970 (0.0010) -[2023-10-10 21:26:04,858][98560] Updated weights for policy 1, policy_version 17982 (0.0008) -[2023-10-10 21:26:05,013][98559] Updated weights for policy 0, policy_version 17980 (0.0007) -[2023-10-10 21:26:05,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 36831232. Throughput: 0: 1672.5, 1: 1658.1. Samples: 9212152. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-10 21:26:05,556][97672] Avg episode reward: [(0, '-3.360'), (1, '21.180')] -[2023-10-10 21:26:08,956][98559] Updated weights for policy 0, policy_version 17990 (0.0007) -[2023-10-10 21:26:08,986][98560] Updated weights for policy 1, policy_version 17992 (0.0009) -[2023-10-10 21:26:09,321][98559] Updated weights for policy 0, policy_version 18000 (0.0009) -[2023-10-10 21:26:09,350][98560] Updated weights for policy 1, policy_version 18002 (0.0009) -[2023-10-10 21:26:09,699][98559] Updated weights for policy 0, policy_version 18010 (0.0008) -[2023-10-10 21:26:09,726][98560] Updated weights for policy 1, policy_version 18012 (0.0008) -[2023-10-10 21:26:10,556][97672] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 36896768. Throughput: 0: 1700.3, 1: 1685.0. Samples: 9223878. Policy #0 lag: (min: 24.0, avg: 41.0, max: 56.0) -[2023-10-10 21:26:10,557][97672] Avg episode reward: [(0, '-3.360'), (1, '21.060')] -[2023-10-10 21:26:13,641][98559] Updated weights for policy 0, policy_version 18020 (0.0008) -[2023-10-10 21:26:13,676][98560] Updated weights for policy 1, policy_version 18022 (0.0007) -[2023-10-10 21:26:14,013][98559] Updated weights for policy 0, policy_version 18030 (0.0008) -[2023-10-10 21:26:14,041][98560] Updated weights for policy 1, policy_version 18032 (0.0007) -[2023-10-10 21:26:14,375][98559] Updated weights for policy 0, policy_version 18040 (0.0008) -[2023-10-10 21:26:14,404][98560] Updated weights for policy 1, policy_version 18042 (0.0008) -[2023-10-10 21:26:15,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 36962304. Throughput: 0: 1683.3, 1: 1687.9. Samples: 9243776. Policy #0 lag: (min: 24.0, avg: 41.0, max: 56.0) -[2023-10-10 21:26:15,557][97672] Avg episode reward: [(0, '-3.360'), (1, '21.040')] -[2023-10-10 21:26:18,361][98560] Updated weights for policy 1, policy_version 18052 (0.0009) -[2023-10-10 21:26:18,518][98559] Updated weights for policy 0, policy_version 18050 (0.0009) -[2023-10-10 21:26:18,741][98560] Updated weights for policy 1, policy_version 18062 (0.0009) -[2023-10-10 21:26:18,890][98559] Updated weights for policy 0, policy_version 18060 (0.0007) -[2023-10-10 21:26:19,096][98560] Updated weights for policy 1, policy_version 18072 (0.0009) -[2023-10-10 21:26:19,255][98559] Updated weights for policy 0, policy_version 18070 (0.0009) -[2023-10-10 21:26:19,620][98559] Updated weights for policy 0, policy_version 18080 (0.0010) -[2023-10-10 21:26:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 37027840. Throughput: 0: 1682.4, 1: 1672.8. Samples: 9263082. Policy #0 lag: (min: 24.0, avg: 41.0, max: 56.0) -[2023-10-10 21:26:20,557][97672] Avg episode reward: [(0, '-3.200'), (1, '20.980')] -[2023-10-10 21:26:20,565][98385] Saving new best policy, reward=-3.200! -[2023-10-10 21:26:23,135][98560] Updated weights for policy 1, policy_version 18082 (0.0008) -[2023-10-10 21:26:23,507][98560] Updated weights for policy 1, policy_version 18092 (0.0009) -[2023-10-10 21:26:23,614][98559] Updated weights for policy 0, policy_version 18090 (0.0008) -[2023-10-10 21:26:23,871][98560] Updated weights for policy 1, policy_version 18102 (0.0009) -[2023-10-10 21:26:23,981][98559] Updated weights for policy 0, policy_version 18100 (0.0008) -[2023-10-10 21:26:24,244][98560] Updated weights for policy 1, policy_version 18112 (0.0008) -[2023-10-10 21:26:24,351][98559] Updated weights for policy 0, policy_version 18110 (0.0010) -[2023-10-10 21:26:25,556][97672] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 37093376. Throughput: 0: 1697.0, 1: 1691.5. Samples: 9274812. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:26:25,556][97672] Avg episode reward: [(0, '-3.060'), (1, '20.980')] -[2023-10-10 21:26:25,557][98385] Saving new best policy, reward=-3.060! -[2023-10-10 21:26:28,133][98559] Updated weights for policy 0, policy_version 18120 (0.0009) -[2023-10-10 21:26:28,370][98560] Updated weights for policy 1, policy_version 18122 (0.0009) -[2023-10-10 21:26:28,504][98559] Updated weights for policy 0, policy_version 18130 (0.0007) -[2023-10-10 21:26:28,725][98560] Updated weights for policy 1, policy_version 18132 (0.0009) -[2023-10-10 21:26:28,880][98559] Updated weights for policy 0, policy_version 18140 (0.0007) -[2023-10-10 21:26:29,091][98560] Updated weights for policy 1, policy_version 18142 (0.0010) -[2023-10-10 21:26:30,556][97672] Fps is (10 sec: 13107.4, 60 sec: 14199.6, 300 sec: 13662.6). Total num frames: 37158912. Throughput: 0: 1686.0, 1: 1674.6. Samples: 9294032. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:26:30,556][97672] Avg episode reward: [(0, '-2.980'), (1, '21.000')] -[2023-10-10 21:26:30,557][98385] Saving new best policy, reward=-2.980! -[2023-10-10 21:26:32,990][98559] Updated weights for policy 0, policy_version 18150 (0.0009) -[2023-10-10 21:26:33,148][98560] Updated weights for policy 1, policy_version 18152 (0.0007) -[2023-10-10 21:26:33,366][98559] Updated weights for policy 0, policy_version 18160 (0.0008) -[2023-10-10 21:26:33,522][98560] Updated weights for policy 1, policy_version 18162 (0.0007) -[2023-10-10 21:26:33,735][98559] Updated weights for policy 0, policy_version 18170 (0.0009) -[2023-10-10 21:26:33,887][98560] Updated weights for policy 1, policy_version 18172 (0.0008) -[2023-10-10 21:26:35,556][97672] Fps is (10 sec: 13106.7, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 37224448. Throughput: 0: 1706.8, 1: 1680.2. Samples: 9314364. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:26:35,557][97672] Avg episode reward: [(0, '-2.980'), (1, '20.880')] -[2023-10-10 21:26:35,570][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000018176_18612224.pth... -[2023-10-10 21:26:35,570][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000018176_18612224.pth... -[2023-10-10 21:26:35,606][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000016608_17006592.pth -[2023-10-10 21:26:35,609][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000016576_16973824.pth -[2023-10-10 21:26:37,716][98559] Updated weights for policy 0, policy_version 18180 (0.0008) -[2023-10-10 21:26:38,003][98560] Updated weights for policy 1, policy_version 18182 (0.0008) -[2023-10-10 21:26:38,081][98559] Updated weights for policy 0, policy_version 18190 (0.0008) -[2023-10-10 21:26:38,401][98560] Updated weights for policy 1, policy_version 18192 (0.0008) -[2023-10-10 21:26:38,447][98559] Updated weights for policy 0, policy_version 18200 (0.0007) -[2023-10-10 21:26:38,764][98560] Updated weights for policy 1, policy_version 18202 (0.0008) -[2023-10-10 21:26:40,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 37289984. Throughput: 0: 1695.7, 1: 1696.1. Samples: 9325226. Policy #0 lag: (min: 16.0, avg: 39.4, max: 48.0) -[2023-10-10 21:26:40,557][97672] Avg episode reward: [(0, '-2.980'), (1, '20.960')] -[2023-10-10 21:26:42,464][98559] Updated weights for policy 0, policy_version 18210 (0.0007) -[2023-10-10 21:26:42,837][98559] Updated weights for policy 0, policy_version 18220 (0.0008) -[2023-10-10 21:26:42,863][98560] Updated weights for policy 1, policy_version 18212 (0.0009) -[2023-10-10 21:26:43,207][98559] Updated weights for policy 0, policy_version 18230 (0.0007) -[2023-10-10 21:26:43,237][98560] Updated weights for policy 1, policy_version 18222 (0.0007) -[2023-10-10 21:26:43,584][98559] Updated weights for policy 0, policy_version 18240 (0.0009) -[2023-10-10 21:26:43,607][98560] Updated weights for policy 1, policy_version 18232 (0.0008) -[2023-10-10 21:26:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 37355520. Throughput: 0: 1689.6, 1: 1670.6. Samples: 9344596. Policy #0 lag: (min: 16.0, avg: 39.4, max: 48.0) -[2023-10-10 21:26:45,557][97672] Avg episode reward: [(0, '-2.980'), (1, '20.680')] -[2023-10-10 21:26:47,667][98560] Updated weights for policy 1, policy_version 18242 (0.0008) -[2023-10-10 21:26:47,910][98559] Updated weights for policy 0, policy_version 18250 (0.0009) -[2023-10-10 21:26:48,027][98560] Updated weights for policy 1, policy_version 18252 (0.0008) -[2023-10-10 21:26:48,283][98559] Updated weights for policy 0, policy_version 18260 (0.0008) -[2023-10-10 21:26:48,395][98560] Updated weights for policy 1, policy_version 18262 (0.0008) -[2023-10-10 21:26:48,654][98559] Updated weights for policy 0, policy_version 18270 (0.0007) -[2023-10-10 21:26:48,767][98560] Updated weights for policy 1, policy_version 18272 (0.0008) -[2023-10-10 21:26:50,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 37421056. Throughput: 0: 1708.4, 1: 1683.0. Samples: 9364764. Policy #0 lag: (min: 16.0, avg: 39.4, max: 48.0) -[2023-10-10 21:26:50,557][97672] Avg episode reward: [(0, '-2.920'), (1, '20.640')] -[2023-10-10 21:26:50,564][98385] Saving new best policy, reward=-2.920! -[2023-10-10 21:26:52,473][98559] Updated weights for policy 0, policy_version 18280 (0.0009) -[2023-10-10 21:26:52,799][98560] Updated weights for policy 1, policy_version 18282 (0.0009) -[2023-10-10 21:26:52,848][98559] Updated weights for policy 0, policy_version 18290 (0.0009) -[2023-10-10 21:26:53,164][98560] Updated weights for policy 1, policy_version 18292 (0.0007) -[2023-10-10 21:26:53,218][98559] Updated weights for policy 0, policy_version 18300 (0.0009) -[2023-10-10 21:26:53,528][98560] Updated weights for policy 1, policy_version 18302 (0.0007) -[2023-10-10 21:26:55,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 37486592. Throughput: 0: 1682.3, 1: 1680.0. Samples: 9375182. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:26:55,556][97672] Avg episode reward: [(0, '-2.920'), (1, '20.700')] -[2023-10-10 21:26:57,208][98559] Updated weights for policy 0, policy_version 18310 (0.0009) -[2023-10-10 21:26:57,388][98560] Updated weights for policy 1, policy_version 18312 (0.0008) -[2023-10-10 21:26:57,574][98559] Updated weights for policy 0, policy_version 18320 (0.0008) -[2023-10-10 21:26:57,754][98560] Updated weights for policy 1, policy_version 18322 (0.0010) -[2023-10-10 21:26:57,935][98559] Updated weights for policy 0, policy_version 18330 (0.0007) -[2023-10-10 21:26:58,125][98560] Updated weights for policy 1, policy_version 18332 (0.0009) -[2023-10-10 21:27:00,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 37552128. Throughput: 0: 1700.6, 1: 1664.9. Samples: 9395224. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:27:00,557][97672] Avg episode reward: [(0, '-2.920'), (1, '20.700')] -[2023-10-10 21:27:01,959][98559] Updated weights for policy 0, policy_version 18340 (0.0009) -[2023-10-10 21:27:02,244][98560] Updated weights for policy 1, policy_version 18342 (0.0008) -[2023-10-10 21:27:02,335][98559] Updated weights for policy 0, policy_version 18350 (0.0008) -[2023-10-10 21:27:02,616][98560] Updated weights for policy 1, policy_version 18352 (0.0008) -[2023-10-10 21:27:02,704][98559] Updated weights for policy 0, policy_version 18360 (0.0008) -[2023-10-10 21:27:02,979][98560] Updated weights for policy 1, policy_version 18362 (0.0008) -[2023-10-10 21:27:05,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 37617664. Throughput: 0: 1712.9, 1: 1688.7. Samples: 9416154. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:27:05,556][97672] Avg episode reward: [(0, '-2.920'), (1, '20.680')] -[2023-10-10 21:27:06,723][98559] Updated weights for policy 0, policy_version 18370 (0.0009) -[2023-10-10 21:27:06,984][98560] Updated weights for policy 1, policy_version 18372 (0.0008) -[2023-10-10 21:27:07,091][98559] Updated weights for policy 0, policy_version 18380 (0.0008) -[2023-10-10 21:27:07,350][98560] Updated weights for policy 1, policy_version 18382 (0.0008) -[2023-10-10 21:27:07,466][98559] Updated weights for policy 0, policy_version 18390 (0.0009) -[2023-10-10 21:27:07,716][98560] Updated weights for policy 1, policy_version 18392 (0.0007) -[2023-10-10 21:27:07,840][98559] Updated weights for policy 0, policy_version 18400 (0.0007) -[2023-10-10 21:27:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 37683200. Throughput: 0: 1685.5, 1: 1667.3. Samples: 9425688. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:27:10,557][97672] Avg episode reward: [(0, '-2.920'), (1, '20.740')] -[2023-10-10 21:27:11,676][98560] Updated weights for policy 1, policy_version 18402 (0.0007) -[2023-10-10 21:27:11,870][98559] Updated weights for policy 0, policy_version 18410 (0.0008) -[2023-10-10 21:27:12,048][98560] Updated weights for policy 1, policy_version 18412 (0.0008) -[2023-10-10 21:27:12,247][98559] Updated weights for policy 0, policy_version 18420 (0.0007) -[2023-10-10 21:27:12,417][98560] Updated weights for policy 1, policy_version 18422 (0.0007) -[2023-10-10 21:27:12,619][98559] Updated weights for policy 0, policy_version 18430 (0.0007) -[2023-10-10 21:27:12,781][98560] Updated weights for policy 1, policy_version 18432 (0.0007) -[2023-10-10 21:27:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 37748736. Throughput: 0: 1701.3, 1: 1677.0. Samples: 9446056. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:27:15,556][97672] Avg episode reward: [(0, '-2.860'), (1, '20.880')] -[2023-10-10 21:27:15,557][98385] Saving new best policy, reward=-2.860! -[2023-10-10 21:27:16,585][98559] Updated weights for policy 0, policy_version 18440 (0.0008) -[2023-10-10 21:27:16,937][98560] Updated weights for policy 1, policy_version 18442 (0.0009) -[2023-10-10 21:27:16,955][98559] Updated weights for policy 0, policy_version 18450 (0.0009) -[2023-10-10 21:27:17,309][98560] Updated weights for policy 1, policy_version 18452 (0.0007) -[2023-10-10 21:27:17,316][98559] Updated weights for policy 0, policy_version 18460 (0.0008) -[2023-10-10 21:27:17,676][98560] Updated weights for policy 1, policy_version 18462 (0.0007) -[2023-10-10 21:27:20,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 37814272. Throughput: 0: 1701.8, 1: 1687.7. Samples: 9466888. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:27:20,557][97672] Avg episode reward: [(0, '-2.860'), (1, '20.800')] -[2023-10-10 21:27:21,350][98559] Updated weights for policy 0, policy_version 18470 (0.0008) -[2023-10-10 21:27:21,693][98560] Updated weights for policy 1, policy_version 18472 (0.0008) -[2023-10-10 21:27:21,719][98559] Updated weights for policy 0, policy_version 18480 (0.0008) -[2023-10-10 21:27:22,062][98560] Updated weights for policy 1, policy_version 18482 (0.0008) -[2023-10-10 21:27:22,091][98559] Updated weights for policy 0, policy_version 18490 (0.0007) -[2023-10-10 21:27:22,429][98560] Updated weights for policy 1, policy_version 18492 (0.0009) -[2023-10-10 21:27:25,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 37879808. Throughput: 0: 1692.3, 1: 1660.0. Samples: 9476080. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:27:25,557][97672] Avg episode reward: [(0, '-2.860'), (1, '20.880')] -[2023-10-10 21:27:26,041][98559] Updated weights for policy 0, policy_version 18500 (0.0008) -[2023-10-10 21:27:26,411][98559] Updated weights for policy 0, policy_version 18510 (0.0009) -[2023-10-10 21:27:26,533][98560] Updated weights for policy 1, policy_version 18502 (0.0007) -[2023-10-10 21:27:26,774][98559] Updated weights for policy 0, policy_version 18520 (0.0008) -[2023-10-10 21:27:26,921][98560] Updated weights for policy 1, policy_version 18512 (0.0008) -[2023-10-10 21:27:27,289][98560] Updated weights for policy 1, policy_version 18522 (0.0008) -[2023-10-10 21:27:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 37945344. Throughput: 0: 1701.6, 1: 1683.5. Samples: 9496924. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:27:30,557][97672] Avg episode reward: [(0, '-2.860'), (1, '20.880')] -[2023-10-10 21:27:30,944][98559] Updated weights for policy 0, policy_version 18530 (0.0008) -[2023-10-10 21:27:31,316][98559] Updated weights for policy 0, policy_version 18540 (0.0007) -[2023-10-10 21:27:31,331][98560] Updated weights for policy 1, policy_version 18532 (0.0008) -[2023-10-10 21:27:31,693][98559] Updated weights for policy 0, policy_version 18550 (0.0007) -[2023-10-10 21:27:31,696][98560] Updated weights for policy 1, policy_version 18542 (0.0009) -[2023-10-10 21:27:32,066][98559] Updated weights for policy 0, policy_version 18560 (0.0008) -[2023-10-10 21:27:32,072][98560] Updated weights for policy 1, policy_version 18552 (0.0010) -[2023-10-10 21:27:35,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 38010880. Throughput: 0: 1709.4, 1: 1694.6. Samples: 9517942. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:27:35,557][97672] Avg episode reward: [(0, '-2.860'), (1, '21.020')] -[2023-10-10 21:27:36,100][98560] Updated weights for policy 1, policy_version 18562 (0.0009) -[2023-10-10 21:27:36,214][98559] Updated weights for policy 0, policy_version 18570 (0.0009) -[2023-10-10 21:27:36,471][98560] Updated weights for policy 1, policy_version 18572 (0.0010) -[2023-10-10 21:27:36,581][98559] Updated weights for policy 0, policy_version 18580 (0.0008) -[2023-10-10 21:27:36,833][98560] Updated weights for policy 1, policy_version 18582 (0.0007) -[2023-10-10 21:27:36,957][98559] Updated weights for policy 0, policy_version 18590 (0.0009) -[2023-10-10 21:27:37,207][98560] Updated weights for policy 1, policy_version 18592 (0.0008) -[2023-10-10 21:27:40,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 38076416. Throughput: 0: 1701.6, 1: 1674.2. Samples: 9527092. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-10 21:27:40,556][97672] Avg episode reward: [(0, '-2.860'), (1, '21.220')] -[2023-10-10 21:27:40,924][98559] Updated weights for policy 0, policy_version 18600 (0.0008) -[2023-10-10 21:27:41,217][98560] Updated weights for policy 1, policy_version 18602 (0.0009) -[2023-10-10 21:27:41,295][98559] Updated weights for policy 0, policy_version 18610 (0.0007) -[2023-10-10 21:27:41,581][98560] Updated weights for policy 1, policy_version 18612 (0.0010) -[2023-10-10 21:27:41,657][98559] Updated weights for policy 0, policy_version 18620 (0.0007) -[2023-10-10 21:27:41,954][98560] Updated weights for policy 1, policy_version 18622 (0.0008) -[2023-10-10 21:27:45,556][97672] Fps is (10 sec: 13107.7, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 38141952. Throughput: 0: 1706.6, 1: 1691.8. Samples: 9548152. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-10 21:27:45,556][97672] Avg episode reward: [(0, '-2.860'), (1, '21.380')] -[2023-10-10 21:27:45,594][98559] Updated weights for policy 0, policy_version 18630 (0.0009) -[2023-10-10 21:27:45,968][98559] Updated weights for policy 0, policy_version 18640 (0.0009) -[2023-10-10 21:27:46,144][98560] Updated weights for policy 1, policy_version 18632 (0.0009) -[2023-10-10 21:27:46,335][98559] Updated weights for policy 0, policy_version 18650 (0.0009) -[2023-10-10 21:27:46,511][98560] Updated weights for policy 1, policy_version 18642 (0.0008) -[2023-10-10 21:27:46,881][98560] Updated weights for policy 1, policy_version 18652 (0.0009) -[2023-10-10 21:27:50,265][98559] Updated weights for policy 0, policy_version 18660 (0.0008) -[2023-10-10 21:27:50,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 38207488. Throughput: 0: 1699.8, 1: 1690.6. Samples: 9568724. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-10 21:27:50,557][97672] Avg episode reward: [(0, '-2.860'), (1, '21.420')] -[2023-10-10 21:27:50,640][98559] Updated weights for policy 0, policy_version 18670 (0.0010) -[2023-10-10 21:27:51,017][98559] Updated weights for policy 0, policy_version 18680 (0.0007) -[2023-10-10 21:27:51,053][98560] Updated weights for policy 1, policy_version 18662 (0.0007) -[2023-10-10 21:27:51,428][98560] Updated weights for policy 1, policy_version 18672 (0.0008) -[2023-10-10 21:27:51,798][98560] Updated weights for policy 1, policy_version 18682 (0.0007) -[2023-10-10 21:27:54,670][98559] Updated weights for policy 0, policy_version 18690 (0.0007) -[2023-10-10 21:27:55,044][98559] Updated weights for policy 0, policy_version 18700 (0.0009) -[2023-10-10 21:27:55,424][98559] Updated weights for policy 0, policy_version 18710 (0.0007) -[2023-10-10 21:27:55,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 38273024. Throughput: 0: 1711.9, 1: 1678.0. Samples: 9578232. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 21:27:55,557][97672] Avg episode reward: [(0, '-2.860'), (1, '21.580')] -[2023-10-10 21:27:55,559][98439] Saving new best policy, reward=21.580! -[2023-10-10 21:27:55,795][98559] Updated weights for policy 0, policy_version 18720 (0.0010) -[2023-10-10 21:27:55,890][98560] Updated weights for policy 1, policy_version 18692 (0.0008) -[2023-10-10 21:27:56,256][98560] Updated weights for policy 1, policy_version 18702 (0.0007) -[2023-10-10 21:27:56,620][98560] Updated weights for policy 1, policy_version 18712 (0.0007) -[2023-10-10 21:27:59,827][98559] Updated weights for policy 0, policy_version 18730 (0.0008) -[2023-10-10 21:28:00,199][98559] Updated weights for policy 0, policy_version 18740 (0.0008) -[2023-10-10 21:28:00,539][98560] Updated weights for policy 1, policy_version 18722 (0.0007) -[2023-10-10 21:28:00,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 13440.4). Total num frames: 38338560. Throughput: 0: 1710.2, 1: 1690.0. Samples: 9599066. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 21:28:00,556][97672] Avg episode reward: [(0, '-2.860'), (1, '21.600')] -[2023-10-10 21:28:00,569][98559] Updated weights for policy 0, policy_version 18750 (0.0008) -[2023-10-10 21:28:00,905][98560] Updated weights for policy 1, policy_version 18732 (0.0009) -[2023-10-10 21:28:01,275][98560] Updated weights for policy 1, policy_version 18742 (0.0008) -[2023-10-10 21:28:01,638][98439] Saving new best policy, reward=21.600! -[2023-10-10 21:28:01,642][98560] Updated weights for policy 1, policy_version 18752 (0.0010) -[2023-10-10 21:28:04,629][98559] Updated weights for policy 0, policy_version 18760 (0.0008) -[2023-10-10 21:28:05,002][98559] Updated weights for policy 0, policy_version 18770 (0.0008) -[2023-10-10 21:28:05,381][98559] Updated weights for policy 0, policy_version 18780 (0.0007) -[2023-10-10 21:28:05,556][97672] Fps is (10 sec: 16384.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 38436864. Throughput: 0: 1684.3, 1: 1693.2. Samples: 9618876. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:28:05,557][97672] Avg episode reward: [(0, '-2.860'), (1, '21.660')] -[2023-10-10 21:28:05,732][98560] Updated weights for policy 1, policy_version 18762 (0.0007) -[2023-10-10 21:28:06,103][98560] Updated weights for policy 1, policy_version 18772 (0.0008) -[2023-10-10 21:28:06,483][98560] Updated weights for policy 1, policy_version 18782 (0.0008) -[2023-10-10 21:28:06,560][98439] Saving new best policy, reward=21.660! -[2023-10-10 21:28:09,530][98559] Updated weights for policy 0, policy_version 18790 (0.0009) -[2023-10-10 21:28:09,897][98559] Updated weights for policy 0, policy_version 18800 (0.0009) -[2023-10-10 21:28:10,261][98559] Updated weights for policy 0, policy_version 18810 (0.0008) -[2023-10-10 21:28:10,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 38502400. Throughput: 0: 1710.0, 1: 1691.7. Samples: 9629158. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:28:10,557][97672] Avg episode reward: [(0, '-2.860'), (1, '21.640')] -[2023-10-10 21:28:10,572][98560] Updated weights for policy 1, policy_version 18792 (0.0009) -[2023-10-10 21:28:10,930][98560] Updated weights for policy 1, policy_version 18802 (0.0008) -[2023-10-10 21:28:11,294][98560] Updated weights for policy 1, policy_version 18812 (0.0007) -[2023-10-10 21:28:14,324][98559] Updated weights for policy 0, policy_version 18820 (0.0010) -[2023-10-10 21:28:14,689][98559] Updated weights for policy 0, policy_version 18830 (0.0008) -[2023-10-10 21:28:15,062][98559] Updated weights for policy 0, policy_version 18840 (0.0007) -[2023-10-10 21:28:15,330][98560] Updated weights for policy 1, policy_version 18822 (0.0008) -[2023-10-10 21:28:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 38567936. Throughput: 0: 1706.8, 1: 1697.4. Samples: 9650110. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:28:15,556][97672] Avg episode reward: [(0, '-2.860'), (1, '21.660')] -[2023-10-10 21:28:15,708][98560] Updated weights for policy 1, policy_version 18832 (0.0009) -[2023-10-10 21:28:16,070][98560] Updated weights for policy 1, policy_version 18842 (0.0007) -[2023-10-10 21:28:19,025][98559] Updated weights for policy 0, policy_version 18850 (0.0007) -[2023-10-10 21:28:19,386][98559] Updated weights for policy 0, policy_version 18860 (0.0008) -[2023-10-10 21:28:19,760][98559] Updated weights for policy 0, policy_version 18870 (0.0009) -[2023-10-10 21:28:20,027][98560] Updated weights for policy 1, policy_version 18852 (0.0008) -[2023-10-10 21:28:20,123][98559] Updated weights for policy 0, policy_version 18880 (0.0007) -[2023-10-10 21:28:20,394][98560] Updated weights for policy 1, policy_version 18862 (0.0011) -[2023-10-10 21:28:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 38633472. Throughput: 0: 1685.3, 1: 1697.6. Samples: 9670170. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 21:28:20,556][97672] Avg episode reward: [(0, '-2.860'), (1, '21.560')] -[2023-10-10 21:28:20,763][98560] Updated weights for policy 1, policy_version 18872 (0.0010) -[2023-10-10 21:28:24,202][98559] Updated weights for policy 0, policy_version 18890 (0.0010) -[2023-10-10 21:28:24,551][98560] Updated weights for policy 1, policy_version 18882 (0.0009) -[2023-10-10 21:28:24,565][98559] Updated weights for policy 0, policy_version 18900 (0.0009) -[2023-10-10 21:28:24,913][98560] Updated weights for policy 1, policy_version 18892 (0.0008) -[2023-10-10 21:28:24,942][98559] Updated weights for policy 0, policy_version 18910 (0.0009) -[2023-10-10 21:28:25,280][98560] Updated weights for policy 1, policy_version 18902 (0.0008) -[2023-10-10 21:28:25,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 38699008. Throughput: 0: 1718.8, 1: 1697.6. Samples: 9680828. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 21:28:25,556][97672] Avg episode reward: [(0, '-2.860'), (1, '21.440')] -[2023-10-10 21:28:25,649][98560] Updated weights for policy 1, policy_version 18912 (0.0010) -[2023-10-10 21:28:28,989][98559] Updated weights for policy 0, policy_version 18920 (0.0008) -[2023-10-10 21:28:29,359][98559] Updated weights for policy 0, policy_version 18930 (0.0009) -[2023-10-10 21:28:29,682][98560] Updated weights for policy 1, policy_version 18922 (0.0008) -[2023-10-10 21:28:29,723][98559] Updated weights for policy 0, policy_version 18940 (0.0009) -[2023-10-10 21:28:30,057][98560] Updated weights for policy 1, policy_version 18932 (0.0009) -[2023-10-10 21:28:30,418][98560] Updated weights for policy 1, policy_version 18942 (0.0008) -[2023-10-10 21:28:30,556][97672] Fps is (10 sec: 16383.4, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 38797312. Throughput: 0: 1699.0, 1: 1694.6. Samples: 9700862. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 21:28:30,558][97672] Avg episode reward: [(0, '-2.860'), (1, '21.480')] -[2023-10-10 21:28:33,701][98559] Updated weights for policy 0, policy_version 18950 (0.0008) -[2023-10-10 21:28:34,067][98559] Updated weights for policy 0, policy_version 18960 (0.0009) -[2023-10-10 21:28:34,381][98560] Updated weights for policy 1, policy_version 18952 (0.0007) -[2023-10-10 21:28:34,440][98559] Updated weights for policy 0, policy_version 18970 (0.0007) -[2023-10-10 21:28:34,740][98560] Updated weights for policy 1, policy_version 18962 (0.0010) -[2023-10-10 21:28:35,108][98560] Updated weights for policy 1, policy_version 18972 (0.0007) -[2023-10-10 21:28:35,556][97672] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 38862848. Throughput: 0: 1688.8, 1: 1684.8. Samples: 9720534. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-10 21:28:35,557][97672] Avg episode reward: [(0, '-2.820'), (1, '21.520')] -[2023-10-10 21:28:35,566][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000018976_19431424.pth... -[2023-10-10 21:28:35,566][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000018976_19431424.pth... -[2023-10-10 21:28:35,601][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000017376_17793024.pth -[2023-10-10 21:28:35,603][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000017376_17793024.pth -[2023-10-10 21:28:35,605][98385] Saving new best policy, reward=-2.820! -[2023-10-10 21:28:38,523][98559] Updated weights for policy 0, policy_version 18980 (0.0008) -[2023-10-10 21:28:38,887][98559] Updated weights for policy 0, policy_version 18990 (0.0008) -[2023-10-10 21:28:39,259][98559] Updated weights for policy 0, policy_version 19000 (0.0008) -[2023-10-10 21:28:39,302][98560] Updated weights for policy 1, policy_version 18982 (0.0009) -[2023-10-10 21:28:39,662][98560] Updated weights for policy 1, policy_version 18992 (0.0008) -[2023-10-10 21:28:40,040][98560] Updated weights for policy 1, policy_version 19002 (0.0008) -[2023-10-10 21:28:40,556][97672] Fps is (10 sec: 13107.6, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 38928384. Throughput: 0: 1709.4, 1: 1700.8. Samples: 9731690. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-10 21:28:40,557][97672] Avg episode reward: [(0, '-2.820'), (1, '21.560')] -[2023-10-10 21:28:43,226][98559] Updated weights for policy 0, policy_version 19010 (0.0009) -[2023-10-10 21:28:43,595][98559] Updated weights for policy 0, policy_version 19020 (0.0009) -[2023-10-10 21:28:43,956][98559] Updated weights for policy 0, policy_version 19030 (0.0009) -[2023-10-10 21:28:44,167][98560] Updated weights for policy 1, policy_version 19012 (0.0008) -[2023-10-10 21:28:44,323][98559] Updated weights for policy 0, policy_version 19040 (0.0009) -[2023-10-10 21:28:44,526][98560] Updated weights for policy 1, policy_version 19022 (0.0008) -[2023-10-10 21:28:44,899][98560] Updated weights for policy 1, policy_version 19032 (0.0010) -[2023-10-10 21:28:45,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 38993920. Throughput: 0: 1683.7, 1: 1697.3. Samples: 9751214. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-10 21:28:45,557][97672] Avg episode reward: [(0, '-2.700'), (1, '21.560')] -[2023-10-10 21:28:45,558][98385] Saving new best policy, reward=-2.700! -[2023-10-10 21:28:48,268][98559] Updated weights for policy 0, policy_version 19050 (0.0011) -[2023-10-10 21:28:48,647][98559] Updated weights for policy 0, policy_version 19060 (0.0009) -[2023-10-10 21:28:48,988][98560] Updated weights for policy 1, policy_version 19042 (0.0007) -[2023-10-10 21:28:49,015][98559] Updated weights for policy 0, policy_version 19070 (0.0009) -[2023-10-10 21:28:49,362][98560] Updated weights for policy 1, policy_version 19052 (0.0008) -[2023-10-10 21:28:49,723][98560] Updated weights for policy 1, policy_version 19062 (0.0010) -[2023-10-10 21:28:50,092][98560] Updated weights for policy 1, policy_version 19072 (0.0011) -[2023-10-10 21:28:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 39059456. Throughput: 0: 1712.2, 1: 1678.9. Samples: 9771474. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:28:50,557][97672] Avg episode reward: [(0, '-2.700'), (1, '21.500')] -[2023-10-10 21:28:52,962][98559] Updated weights for policy 0, policy_version 19080 (0.0009) -[2023-10-10 21:28:53,333][98559] Updated weights for policy 0, policy_version 19090 (0.0009) -[2023-10-10 21:28:53,706][98559] Updated weights for policy 0, policy_version 19100 (0.0008) -[2023-10-10 21:28:54,152][98560] Updated weights for policy 1, policy_version 19082 (0.0008) -[2023-10-10 21:28:54,527][98560] Updated weights for policy 1, policy_version 19092 (0.0008) -[2023-10-10 21:28:54,894][98560] Updated weights for policy 1, policy_version 19102 (0.0007) -[2023-10-10 21:28:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 39124992. Throughput: 0: 1701.2, 1: 1697.6. Samples: 9782106. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:28:55,557][97672] Avg episode reward: [(0, '-2.700'), (1, '21.540')] -[2023-10-10 21:28:57,744][98559] Updated weights for policy 0, policy_version 19110 (0.0009) -[2023-10-10 21:28:58,106][98559] Updated weights for policy 0, policy_version 19120 (0.0010) -[2023-10-10 21:28:58,471][98559] Updated weights for policy 0, policy_version 19130 (0.0010) -[2023-10-10 21:28:58,737][98560] Updated weights for policy 1, policy_version 19112 (0.0008) -[2023-10-10 21:28:59,108][98560] Updated weights for policy 1, policy_version 19122 (0.0008) -[2023-10-10 21:28:59,471][98560] Updated weights for policy 1, policy_version 19132 (0.0010) -[2023-10-10 21:29:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 39190528. Throughput: 0: 1693.2, 1: 1693.3. Samples: 9802500. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:29:00,556][97672] Avg episode reward: [(0, '-2.640'), (1, '21.520')] -[2023-10-10 21:29:00,557][98385] Saving new best policy, reward=-2.640! -[2023-10-10 21:29:02,499][98559] Updated weights for policy 0, policy_version 19140 (0.0009) -[2023-10-10 21:29:02,875][98559] Updated weights for policy 0, policy_version 19150 (0.0010) -[2023-10-10 21:29:03,234][98559] Updated weights for policy 0, policy_version 19160 (0.0011) -[2023-10-10 21:29:03,678][98560] Updated weights for policy 1, policy_version 19142 (0.0008) -[2023-10-10 21:29:04,056][98560] Updated weights for policy 1, policy_version 19152 (0.0011) -[2023-10-10 21:29:04,434][98560] Updated weights for policy 1, policy_version 19162 (0.0009) -[2023-10-10 21:29:05,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 39256064. Throughput: 0: 1716.7, 1: 1664.7. Samples: 9822338. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:29:05,557][97672] Avg episode reward: [(0, '-2.520'), (1, '21.580')] -[2023-10-10 21:29:05,569][98385] Saving new best policy, reward=-2.520! -[2023-10-10 21:29:07,090][98559] Updated weights for policy 0, policy_version 19170 (0.0009) -[2023-10-10 21:29:07,463][98559] Updated weights for policy 0, policy_version 19180 (0.0008) -[2023-10-10 21:29:07,826][98559] Updated weights for policy 0, policy_version 19190 (0.0009) -[2023-10-10 21:29:08,200][98559] Updated weights for policy 0, policy_version 19200 (0.0011) -[2023-10-10 21:29:08,291][98560] Updated weights for policy 1, policy_version 19172 (0.0008) -[2023-10-10 21:29:08,661][98560] Updated weights for policy 1, policy_version 19182 (0.0009) -[2023-10-10 21:29:09,029][98560] Updated weights for policy 1, policy_version 19192 (0.0008) -[2023-10-10 21:29:10,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 39321600. Throughput: 0: 1688.1, 1: 1693.8. Samples: 9833012. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:29:10,557][97672] Avg episode reward: [(0, '-2.520'), (1, '21.720')] -[2023-10-10 21:29:10,559][98439] Saving new best policy, reward=21.720! -[2023-10-10 21:29:12,235][98559] Updated weights for policy 0, policy_version 19210 (0.0011) -[2023-10-10 21:29:12,617][98559] Updated weights for policy 0, policy_version 19220 (0.0011) -[2023-10-10 21:29:12,989][98559] Updated weights for policy 0, policy_version 19230 (0.0010) -[2023-10-10 21:29:13,140][98560] Updated weights for policy 1, policy_version 19202 (0.0008) -[2023-10-10 21:29:13,506][98560] Updated weights for policy 1, policy_version 19212 (0.0008) -[2023-10-10 21:29:13,873][98560] Updated weights for policy 1, policy_version 19222 (0.0008) -[2023-10-10 21:29:14,246][98560] Updated weights for policy 1, policy_version 19232 (0.0010) -[2023-10-10 21:29:15,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 39387136. Throughput: 0: 1704.7, 1: 1685.0. Samples: 9853396. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:29:15,557][97672] Avg episode reward: [(0, '-2.520'), (1, '21.880')] -[2023-10-10 21:29:15,559][98439] Saving new best policy, reward=21.880! -[2023-10-10 21:29:16,943][98559] Updated weights for policy 0, policy_version 19240 (0.0008) -[2023-10-10 21:29:17,309][98559] Updated weights for policy 0, policy_version 19250 (0.0007) -[2023-10-10 21:29:17,682][98559] Updated weights for policy 0, policy_version 19260 (0.0007) -[2023-10-10 21:29:18,257][98560] Updated weights for policy 1, policy_version 19242 (0.0009) -[2023-10-10 21:29:18,630][98560] Updated weights for policy 1, policy_version 19252 (0.0008) -[2023-10-10 21:29:19,009][98560] Updated weights for policy 1, policy_version 19262 (0.0008) -[2023-10-10 21:29:20,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 39452672. Throughput: 0: 1719.9, 1: 1679.5. Samples: 9873506. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:29:20,557][97672] Avg episode reward: [(0, '-2.460'), (1, '22.000')] -[2023-10-10 21:29:20,565][98385] Saving new best policy, reward=-2.460! -[2023-10-10 21:29:20,565][98439] Saving new best policy, reward=22.000! -[2023-10-10 21:29:21,675][98559] Updated weights for policy 0, policy_version 19270 (0.0010) -[2023-10-10 21:29:22,047][98559] Updated weights for policy 0, policy_version 19280 (0.0008) -[2023-10-10 21:29:22,417][98559] Updated weights for policy 0, policy_version 19290 (0.0008) -[2023-10-10 21:29:22,983][98560] Updated weights for policy 1, policy_version 19272 (0.0007) -[2023-10-10 21:29:23,342][98560] Updated weights for policy 1, policy_version 19282 (0.0008) -[2023-10-10 21:29:23,711][98560] Updated weights for policy 1, policy_version 19292 (0.0007) -[2023-10-10 21:29:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 39518208. Throughput: 0: 1690.1, 1: 1694.5. Samples: 9883996. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-10 21:29:25,557][97672] Avg episode reward: [(0, '-2.460'), (1, '21.940')] -[2023-10-10 21:29:26,374][98559] Updated weights for policy 0, policy_version 19300 (0.0007) -[2023-10-10 21:29:26,747][98559] Updated weights for policy 0, policy_version 19310 (0.0007) -[2023-10-10 21:29:27,120][98559] Updated weights for policy 0, policy_version 19320 (0.0009) -[2023-10-10 21:29:27,823][98560] Updated weights for policy 1, policy_version 19302 (0.0009) -[2023-10-10 21:29:28,187][98560] Updated weights for policy 1, policy_version 19312 (0.0008) -[2023-10-10 21:29:28,554][98560] Updated weights for policy 1, policy_version 19322 (0.0007) -[2023-10-10 21:29:30,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 39583744. Throughput: 0: 1717.0, 1: 1671.9. Samples: 9903716. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-10 21:29:30,557][97672] Avg episode reward: [(0, '-2.460'), (1, '21.960')] -[2023-10-10 21:29:31,141][98559] Updated weights for policy 0, policy_version 19330 (0.0008) -[2023-10-10 21:29:31,505][98559] Updated weights for policy 0, policy_version 19340 (0.0007) -[2023-10-10 21:29:31,873][98559] Updated weights for policy 0, policy_version 19350 (0.0008) -[2023-10-10 21:29:32,242][98559] Updated weights for policy 0, policy_version 19360 (0.0008) -[2023-10-10 21:29:32,598][98560] Updated weights for policy 1, policy_version 19332 (0.0008) -[2023-10-10 21:29:32,973][98560] Updated weights for policy 1, policy_version 19342 (0.0008) -[2023-10-10 21:29:33,340][98560] Updated weights for policy 1, policy_version 19352 (0.0009) -[2023-10-10 21:29:35,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 39649280. Throughput: 0: 1717.0, 1: 1688.7. Samples: 9924730. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-10 21:29:35,556][97672] Avg episode reward: [(0, '-2.340'), (1, '21.940')] -[2023-10-10 21:29:35,564][98385] Saving new best policy, reward=-2.340! -[2023-10-10 21:29:36,213][98559] Updated weights for policy 0, policy_version 19370 (0.0007) -[2023-10-10 21:29:36,585][98559] Updated weights for policy 0, policy_version 19380 (0.0008) -[2023-10-10 21:29:36,948][98559] Updated weights for policy 0, policy_version 19390 (0.0007) -[2023-10-10 21:29:37,454][98560] Updated weights for policy 1, policy_version 19362 (0.0009) -[2023-10-10 21:29:37,823][98560] Updated weights for policy 1, policy_version 19372 (0.0010) -[2023-10-10 21:29:38,186][98560] Updated weights for policy 1, policy_version 19382 (0.0009) -[2023-10-10 21:29:38,546][98560] Updated weights for policy 1, policy_version 19392 (0.0010) -[2023-10-10 21:29:40,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 39714816. Throughput: 0: 1705.6, 1: 1695.1. Samples: 9935136. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-10 21:29:40,556][97672] Avg episode reward: [(0, '-2.340'), (1, '22.040')] -[2023-10-10 21:29:40,557][98439] Saving new best policy, reward=22.040! -[2023-10-10 21:29:40,753][98559] Updated weights for policy 0, policy_version 19400 (0.0007) -[2023-10-10 21:29:41,134][98559] Updated weights for policy 0, policy_version 19410 (0.0007) -[2023-10-10 21:29:41,494][98559] Updated weights for policy 0, policy_version 19420 (0.0011) -[2023-10-10 21:29:42,634][98560] Updated weights for policy 1, policy_version 19402 (0.0007) -[2023-10-10 21:29:43,005][98560] Updated weights for policy 1, policy_version 19412 (0.0008) -[2023-10-10 21:29:43,381][98560] Updated weights for policy 1, policy_version 19422 (0.0008) -[2023-10-10 21:29:45,394][98559] Updated weights for policy 0, policy_version 19430 (0.0008) -[2023-10-10 21:29:45,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 39780352. Throughput: 0: 1726.3, 1: 1673.1. Samples: 9955474. Policy #0 lag: (min: 31.0, avg: 32.8, max: 60.0) -[2023-10-10 21:29:45,557][97672] Avg episode reward: [(0, '-2.340'), (1, '22.060')] -[2023-10-10 21:29:45,559][98439] Saving new best policy, reward=22.060! -[2023-10-10 21:29:45,764][98559] Updated weights for policy 0, policy_version 19440 (0.0009) -[2023-10-10 21:29:46,138][98559] Updated weights for policy 0, policy_version 19450 (0.0007) -[2023-10-10 21:29:47,360][98560] Updated weights for policy 1, policy_version 19432 (0.0010) -[2023-10-10 21:29:47,736][98560] Updated weights for policy 1, policy_version 19442 (0.0011) -[2023-10-10 21:29:48,091][98560] Updated weights for policy 1, policy_version 19452 (0.0010) -[2023-10-10 21:29:50,071][98559] Updated weights for policy 0, policy_version 19460 (0.0008) -[2023-10-10 21:29:50,454][98559] Updated weights for policy 0, policy_version 19470 (0.0008) -[2023-10-10 21:29:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 39845888. Throughput: 0: 1716.2, 1: 1702.6. Samples: 9976184. Policy #0 lag: (min: 31.0, avg: 32.8, max: 60.0) -[2023-10-10 21:29:50,556][97672] Avg episode reward: [(0, '-2.380'), (1, '22.060')] -[2023-10-10 21:29:50,824][98559] Updated weights for policy 0, policy_version 19480 (0.0008) -[2023-10-10 21:29:52,165][98560] Updated weights for policy 1, policy_version 19462 (0.0009) -[2023-10-10 21:29:52,553][98560] Updated weights for policy 1, policy_version 19472 (0.0007) -[2023-10-10 21:29:52,928][98560] Updated weights for policy 1, policy_version 19482 (0.0007) -[2023-10-10 21:29:54,776][98559] Updated weights for policy 0, policy_version 19490 (0.0011) -[2023-10-10 21:29:55,150][98559] Updated weights for policy 0, policy_version 19500 (0.0009) -[2023-10-10 21:29:55,515][98559] Updated weights for policy 0, policy_version 19510 (0.0008) -[2023-10-10 21:29:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 39911424. Throughput: 0: 1727.5, 1: 1684.3. Samples: 9986542. Policy #0 lag: (min: 31.0, avg: 32.8, max: 60.0) -[2023-10-10 21:29:55,557][97672] Avg episode reward: [(0, '-2.320'), (1, '21.920')] -[2023-10-10 21:29:55,888][98385] Saving new best policy, reward=-2.320! -[2023-10-10 21:29:55,894][98559] Updated weights for policy 0, policy_version 19520 (0.0008) -[2023-10-10 21:29:56,795][98560] Updated weights for policy 1, policy_version 19492 (0.0008) -[2023-10-10 21:29:57,170][98560] Updated weights for policy 1, policy_version 19502 (0.0009) -[2023-10-10 21:29:57,536][98560] Updated weights for policy 1, policy_version 19512 (0.0008) -[2023-10-10 21:29:59,844][98559] Updated weights for policy 0, policy_version 19530 (0.0008) -[2023-10-10 21:30:00,216][98559] Updated weights for policy 0, policy_version 19540 (0.0008) -[2023-10-10 21:30:00,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 39976960. Throughput: 0: 1726.0, 1: 1689.0. Samples: 10007070. Policy #0 lag: (min: 31.0, avg: 32.8, max: 60.0) -[2023-10-10 21:30:00,557][97672] Avg episode reward: [(0, '-2.320'), (1, '21.980')] -[2023-10-10 21:30:00,585][98559] Updated weights for policy 0, policy_version 19550 (0.0011) -[2023-10-10 21:30:01,594][98560] Updated weights for policy 1, policy_version 19522 (0.0008) -[2023-10-10 21:30:01,957][98560] Updated weights for policy 1, policy_version 19532 (0.0010) -[2023-10-10 21:30:02,334][98560] Updated weights for policy 1, policy_version 19542 (0.0009) -[2023-10-10 21:30:02,706][98560] Updated weights for policy 1, policy_version 19552 (0.0008) -[2023-10-10 21:30:04,572][98559] Updated weights for policy 0, policy_version 19560 (0.0010) -[2023-10-10 21:30:04,950][98559] Updated weights for policy 0, policy_version 19570 (0.0010) -[2023-10-10 21:30:05,312][98559] Updated weights for policy 0, policy_version 19580 (0.0007) -[2023-10-10 21:30:05,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 40075264. Throughput: 0: 1702.0, 1: 1707.4. Samples: 10026932. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:30:05,557][97672] Avg episode reward: [(0, '-2.320'), (1, '22.000')] -[2023-10-10 21:30:06,728][98560] Updated weights for policy 1, policy_version 19562 (0.0008) -[2023-10-10 21:30:07,096][98560] Updated weights for policy 1, policy_version 19572 (0.0009) -[2023-10-10 21:30:07,454][98560] Updated weights for policy 1, policy_version 19582 (0.0008) -[2023-10-10 21:30:09,209][98559] Updated weights for policy 0, policy_version 19590 (0.0010) -[2023-10-10 21:30:09,576][98559] Updated weights for policy 0, policy_version 19600 (0.0010) -[2023-10-10 21:30:09,950][98559] Updated weights for policy 0, policy_version 19610 (0.0007) -[2023-10-10 21:30:10,556][97672] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 40140800. Throughput: 0: 1728.0, 1: 1679.4. Samples: 10037326. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:30:10,557][97672] Avg episode reward: [(0, '-2.320'), (1, '21.860')] -[2023-10-10 21:30:11,519][98560] Updated weights for policy 1, policy_version 19592 (0.0009) -[2023-10-10 21:30:11,884][98560] Updated weights for policy 1, policy_version 19602 (0.0009) -[2023-10-10 21:30:12,256][98560] Updated weights for policy 1, policy_version 19612 (0.0010) -[2023-10-10 21:30:13,845][98559] Updated weights for policy 0, policy_version 19620 (0.0008) -[2023-10-10 21:30:14,230][98559] Updated weights for policy 0, policy_version 19630 (0.0008) -[2023-10-10 21:30:14,595][98559] Updated weights for policy 0, policy_version 19640 (0.0009) -[2023-10-10 21:30:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 40206336. Throughput: 0: 1718.6, 1: 1702.0. Samples: 10057642. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:30:15,557][97672] Avg episode reward: [(0, '-2.320'), (1, '21.920')] -[2023-10-10 21:30:16,153][98560] Updated weights for policy 1, policy_version 19622 (0.0009) -[2023-10-10 21:30:16,520][98560] Updated weights for policy 1, policy_version 19632 (0.0010) -[2023-10-10 21:30:16,887][98560] Updated weights for policy 1, policy_version 19642 (0.0009) -[2023-10-10 21:30:18,664][98559] Updated weights for policy 0, policy_version 19650 (0.0008) -[2023-10-10 21:30:19,040][98559] Updated weights for policy 0, policy_version 19660 (0.0008) -[2023-10-10 21:30:19,412][98559] Updated weights for policy 0, policy_version 19670 (0.0010) -[2023-10-10 21:30:19,782][98559] Updated weights for policy 0, policy_version 19680 (0.0009) -[2023-10-10 21:30:20,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 40271872. Throughput: 0: 1699.9, 1: 1703.3. Samples: 10077878. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-10 21:30:20,557][97672] Avg episode reward: [(0, '-2.240'), (1, '21.980')] -[2023-10-10 21:30:20,567][98385] Saving new best policy, reward=-2.240! -[2023-10-10 21:30:20,920][98560] Updated weights for policy 1, policy_version 19652 (0.0009) -[2023-10-10 21:30:21,282][98560] Updated weights for policy 1, policy_version 19662 (0.0010) -[2023-10-10 21:30:21,647][98560] Updated weights for policy 1, policy_version 19672 (0.0009) -[2023-10-10 21:30:23,787][98559] Updated weights for policy 0, policy_version 19690 (0.0007) -[2023-10-10 21:30:24,149][98559] Updated weights for policy 0, policy_version 19700 (0.0008) -[2023-10-10 21:30:24,519][98559] Updated weights for policy 0, policy_version 19710 (0.0009) -[2023-10-10 21:30:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 40337408. Throughput: 0: 1731.8, 1: 1677.9. Samples: 10088574. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-10 21:30:25,557][97672] Avg episode reward: [(0, '-2.240'), (1, '21.960')] -[2023-10-10 21:30:25,757][98560] Updated weights for policy 1, policy_version 19682 (0.0009) -[2023-10-10 21:30:26,127][98560] Updated weights for policy 1, policy_version 19692 (0.0009) -[2023-10-10 21:30:26,504][98560] Updated weights for policy 1, policy_version 19702 (0.0011) -[2023-10-10 21:30:26,870][98560] Updated weights for policy 1, policy_version 19712 (0.0010) -[2023-10-10 21:30:28,447][98559] Updated weights for policy 0, policy_version 19720 (0.0008) -[2023-10-10 21:30:28,811][98559] Updated weights for policy 0, policy_version 19730 (0.0007) -[2023-10-10 21:30:29,187][98559] Updated weights for policy 0, policy_version 19740 (0.0008) -[2023-10-10 21:30:30,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 40402944. Throughput: 0: 1698.0, 1: 1698.7. Samples: 10108326. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-10 21:30:30,556][97672] Avg episode reward: [(0, '-2.240'), (1, '21.960')] -[2023-10-10 21:30:30,935][98560] Updated weights for policy 1, policy_version 19722 (0.0008) -[2023-10-10 21:30:31,309][98560] Updated weights for policy 1, policy_version 19732 (0.0010) -[2023-10-10 21:30:31,671][98560] Updated weights for policy 1, policy_version 19742 (0.0008) -[2023-10-10 21:30:33,201][98559] Updated weights for policy 0, policy_version 19750 (0.0008) -[2023-10-10 21:30:33,565][98559] Updated weights for policy 0, policy_version 19760 (0.0010) -[2023-10-10 21:30:33,935][98559] Updated weights for policy 0, policy_version 19770 (0.0008) -[2023-10-10 21:30:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 40468480. Throughput: 0: 1710.4, 1: 1706.3. Samples: 10129940. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-10 21:30:35,557][97672] Avg episode reward: [(0, '-2.160'), (1, '21.900')] -[2023-10-10 21:30:35,559][98560] Updated weights for policy 1, policy_version 19752 (0.0009) -[2023-10-10 21:30:35,571][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000019776_20250624.pth... -[2023-10-10 21:30:35,605][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000018176_18612224.pth -[2023-10-10 21:30:35,609][98385] Saving new best policy, reward=-2.160! -[2023-10-10 21:30:35,936][98560] Updated weights for policy 1, policy_version 19762 (0.0008) -[2023-10-10 21:30:36,297][98560] Updated weights for policy 1, policy_version 19772 (0.0008) -[2023-10-10 21:30:36,443][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000019776_20250624.pth... -[2023-10-10 21:30:36,472][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000018176_18612224.pth -[2023-10-10 21:30:37,866][98559] Updated weights for policy 0, policy_version 19780 (0.0010) -[2023-10-10 21:30:38,236][98559] Updated weights for policy 0, policy_version 19790 (0.0009) -[2023-10-10 21:30:38,610][98559] Updated weights for policy 0, policy_version 19800 (0.0011) -[2023-10-10 21:30:40,407][98560] Updated weights for policy 1, policy_version 19782 (0.0007) -[2023-10-10 21:30:40,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 40534016. Throughput: 0: 1714.2, 1: 1693.2. Samples: 10139874. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 21:30:40,557][97672] Avg episode reward: [(0, '-2.200'), (1, '21.960')] -[2023-10-10 21:30:40,800][98560] Updated weights for policy 1, policy_version 19792 (0.0008) -[2023-10-10 21:30:41,171][98560] Updated weights for policy 1, policy_version 19802 (0.0007) -[2023-10-10 21:30:42,604][98559] Updated weights for policy 0, policy_version 19810 (0.0010) -[2023-10-10 21:30:42,971][98559] Updated weights for policy 0, policy_version 19820 (0.0008) -[2023-10-10 21:30:43,341][98559] Updated weights for policy 0, policy_version 19830 (0.0008) -[2023-10-10 21:30:43,717][98559] Updated weights for policy 0, policy_version 19840 (0.0009) -[2023-10-10 21:30:45,079][98560] Updated weights for policy 1, policy_version 19812 (0.0010) -[2023-10-10 21:30:45,449][98560] Updated weights for policy 1, policy_version 19822 (0.0007) -[2023-10-10 21:30:45,556][97672] Fps is (10 sec: 13107.7, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 40599552. Throughput: 0: 1697.2, 1: 1706.9. Samples: 10160252. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 21:30:45,556][97672] Avg episode reward: [(0, '-2.200'), (1, '21.960')] -[2023-10-10 21:30:45,816][98560] Updated weights for policy 1, policy_version 19832 (0.0009) -[2023-10-10 21:30:47,661][98559] Updated weights for policy 0, policy_version 19850 (0.0010) -[2023-10-10 21:30:48,028][98559] Updated weights for policy 0, policy_version 19860 (0.0010) -[2023-10-10 21:30:48,407][98559] Updated weights for policy 0, policy_version 19870 (0.0007) -[2023-10-10 21:30:49,897][98560] Updated weights for policy 1, policy_version 19842 (0.0007) -[2023-10-10 21:30:50,261][98560] Updated weights for policy 1, policy_version 19852 (0.0009) -[2023-10-10 21:30:50,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 40665088. Throughput: 0: 1722.9, 1: 1704.8. Samples: 10181182. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 21:30:50,557][97672] Avg episode reward: [(0, '-2.200'), (1, '22.000')] -[2023-10-10 21:30:50,628][98560] Updated weights for policy 1, policy_version 19862 (0.0007) -[2023-10-10 21:30:50,989][98560] Updated weights for policy 1, policy_version 19872 (0.0007) -[2023-10-10 21:30:52,391][98559] Updated weights for policy 0, policy_version 19880 (0.0010) -[2023-10-10 21:30:52,757][98559] Updated weights for policy 0, policy_version 19890 (0.0009) -[2023-10-10 21:30:53,129][98559] Updated weights for policy 0, policy_version 19900 (0.0008) -[2023-10-10 21:30:54,904][98560] Updated weights for policy 1, policy_version 19882 (0.0009) -[2023-10-10 21:30:55,266][98560] Updated weights for policy 1, policy_version 19892 (0.0007) -[2023-10-10 21:30:55,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 40730624. Throughput: 0: 1694.3, 1: 1706.2. Samples: 10190350. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 21:30:55,557][97672] Avg episode reward: [(0, '-2.200'), (1, '21.960')] -[2023-10-10 21:30:55,640][98560] Updated weights for policy 1, policy_version 19902 (0.0007) -[2023-10-10 21:30:57,037][98559] Updated weights for policy 0, policy_version 19910 (0.0008) -[2023-10-10 21:30:57,408][98559] Updated weights for policy 0, policy_version 19920 (0.0007) -[2023-10-10 21:30:57,780][98559] Updated weights for policy 0, policy_version 19930 (0.0008) -[2023-10-10 21:30:59,805][98560] Updated weights for policy 1, policy_version 19912 (0.0010) -[2023-10-10 21:31:00,189][98560] Updated weights for policy 1, policy_version 19922 (0.0009) -[2023-10-10 21:31:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 40796160. Throughput: 0: 1711.6, 1: 1708.7. Samples: 10211558. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-10 21:31:00,557][97672] Avg episode reward: [(0, '-2.120'), (1, '21.900')] -[2023-10-10 21:31:00,558][98560] Updated weights for policy 1, policy_version 19932 (0.0008) -[2023-10-10 21:31:00,559][98385] Saving new best policy, reward=-2.120! -[2023-10-10 21:31:01,665][98559] Updated weights for policy 0, policy_version 19940 (0.0008) -[2023-10-10 21:31:02,027][98559] Updated weights for policy 0, policy_version 19950 (0.0009) -[2023-10-10 21:31:02,403][98559] Updated weights for policy 0, policy_version 19960 (0.0007) -[2023-10-10 21:31:04,650][98560] Updated weights for policy 1, policy_version 19942 (0.0009) -[2023-10-10 21:31:05,020][98560] Updated weights for policy 1, policy_version 19952 (0.0008) -[2023-10-10 21:31:05,390][98560] Updated weights for policy 1, policy_version 19962 (0.0008) -[2023-10-10 21:31:05,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 13440.4). Total num frames: 40861696. Throughput: 0: 1732.8, 1: 1697.6. Samples: 10232246. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-10 21:31:05,556][97672] Avg episode reward: [(0, '-2.120'), (1, '21.940')] -[2023-10-10 21:31:06,329][98559] Updated weights for policy 0, policy_version 19970 (0.0007) -[2023-10-10 21:31:06,703][98559] Updated weights for policy 0, policy_version 19980 (0.0007) -[2023-10-10 21:31:07,070][98559] Updated weights for policy 0, policy_version 19990 (0.0007) -[2023-10-10 21:31:07,432][98559] Updated weights for policy 0, policy_version 20000 (0.0008) -[2023-10-10 21:31:09,366][98560] Updated weights for policy 1, policy_version 19972 (0.0009) -[2023-10-10 21:31:09,748][98560] Updated weights for policy 1, policy_version 19982 (0.0008) -[2023-10-10 21:31:10,116][98560] Updated weights for policy 1, policy_version 19992 (0.0008) -[2023-10-10 21:31:10,556][97672] Fps is (10 sec: 16384.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 40960000. Throughput: 0: 1701.0, 1: 1709.5. Samples: 10242046. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-10 21:31:10,556][97672] Avg episode reward: [(0, '-2.120'), (1, '21.860')] -[2023-10-10 21:31:11,453][98559] Updated weights for policy 0, policy_version 20010 (0.0008) -[2023-10-10 21:31:11,826][98559] Updated weights for policy 0, policy_version 20020 (0.0007) -[2023-10-10 21:31:12,191][98559] Updated weights for policy 0, policy_version 20030 (0.0008) -[2023-10-10 21:31:14,309][98560] Updated weights for policy 1, policy_version 20002 (0.0007) -[2023-10-10 21:31:14,677][98560] Updated weights for policy 1, policy_version 20012 (0.0011) -[2023-10-10 21:31:15,044][98560] Updated weights for policy 1, policy_version 20022 (0.0007) -[2023-10-10 21:31:15,408][98560] Updated weights for policy 1, policy_version 20032 (0.0007) -[2023-10-10 21:31:15,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 41025536. Throughput: 0: 1726.4, 1: 1711.9. Samples: 10263046. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-10 21:31:15,556][97672] Avg episode reward: [(0, '-2.120'), (1, '21.840')] -[2023-10-10 21:31:16,163][98559] Updated weights for policy 0, policy_version 20040 (0.0008) -[2023-10-10 21:31:16,534][98559] Updated weights for policy 0, policy_version 20050 (0.0009) -[2023-10-10 21:31:16,903][98559] Updated weights for policy 0, policy_version 20060 (0.0011) -[2023-10-10 21:31:19,366][98560] Updated weights for policy 1, policy_version 20042 (0.0008) -[2023-10-10 21:31:19,732][98560] Updated weights for policy 1, policy_version 20052 (0.0010) -[2023-10-10 21:31:20,098][98560] Updated weights for policy 1, policy_version 20062 (0.0010) -[2023-10-10 21:31:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 41091072. Throughput: 0: 1723.1, 1: 1690.2. Samples: 10283540. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:31:20,556][97672] Avg episode reward: [(0, '-2.120'), (1, '21.880')] -[2023-10-10 21:31:20,872][98559] Updated weights for policy 0, policy_version 20070 (0.0011) -[2023-10-10 21:31:21,252][98559] Updated weights for policy 0, policy_version 20080 (0.0011) -[2023-10-10 21:31:21,620][98559] Updated weights for policy 0, policy_version 20090 (0.0010) -[2023-10-10 21:31:24,040][98560] Updated weights for policy 1, policy_version 20072 (0.0009) -[2023-10-10 21:31:24,409][98560] Updated weights for policy 1, policy_version 20082 (0.0010) -[2023-10-10 21:31:24,787][98560] Updated weights for policy 1, policy_version 20092 (0.0009) -[2023-10-10 21:31:25,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 41156608. Throughput: 0: 1702.6, 1: 1707.7. Samples: 10293336. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:31:25,557][97672] Avg episode reward: [(0, '-2.120'), (1, '21.980')] -[2023-10-10 21:31:25,603][98559] Updated weights for policy 0, policy_version 20100 (0.0010) -[2023-10-10 21:31:25,982][98559] Updated weights for policy 0, policy_version 20110 (0.0010) -[2023-10-10 21:31:26,352][98559] Updated weights for policy 0, policy_version 20120 (0.0009) -[2023-10-10 21:31:28,694][98560] Updated weights for policy 1, policy_version 20102 (0.0008) -[2023-10-10 21:31:29,078][98560] Updated weights for policy 1, policy_version 20112 (0.0008) -[2023-10-10 21:31:29,451][98560] Updated weights for policy 1, policy_version 20122 (0.0008) -[2023-10-10 21:31:30,438][98559] Updated weights for policy 0, policy_version 20130 (0.0008) -[2023-10-10 21:31:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 41222144. Throughput: 0: 1722.2, 1: 1697.9. Samples: 10314156. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:31:30,557][97672] Avg episode reward: [(0, '-2.120'), (1, '21.880')] -[2023-10-10 21:31:30,805][98559] Updated weights for policy 0, policy_version 20140 (0.0007) -[2023-10-10 21:31:31,167][98559] Updated weights for policy 0, policy_version 20150 (0.0007) -[2023-10-10 21:31:31,539][98559] Updated weights for policy 0, policy_version 20160 (0.0007) -[2023-10-10 21:31:33,349][98560] Updated weights for policy 1, policy_version 20132 (0.0008) -[2023-10-10 21:31:33,731][98560] Updated weights for policy 1, policy_version 20142 (0.0008) -[2023-10-10 21:31:34,095][98560] Updated weights for policy 1, policy_version 20152 (0.0011) -[2023-10-10 21:31:35,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 41287680. Throughput: 0: 1719.0, 1: 1675.4. Samples: 10333928. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:31:35,557][97672] Avg episode reward: [(0, '-2.120'), (1, '21.920')] -[2023-10-10 21:31:35,609][98559] Updated weights for policy 0, policy_version 20170 (0.0007) -[2023-10-10 21:31:35,986][98559] Updated weights for policy 0, policy_version 20180 (0.0007) -[2023-10-10 21:31:36,367][98559] Updated weights for policy 0, policy_version 20190 (0.0007) -[2023-10-10 21:31:38,121][98560] Updated weights for policy 1, policy_version 20162 (0.0008) -[2023-10-10 21:31:38,500][98560] Updated weights for policy 1, policy_version 20172 (0.0008) -[2023-10-10 21:31:38,867][98560] Updated weights for policy 1, policy_version 20182 (0.0007) -[2023-10-10 21:31:39,229][98560] Updated weights for policy 1, policy_version 20192 (0.0008) -[2023-10-10 21:31:40,354][98559] Updated weights for policy 0, policy_version 20200 (0.0010) -[2023-10-10 21:31:40,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 41353216. Throughput: 0: 1725.0, 1: 1704.6. Samples: 10344682. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-10 21:31:40,558][97672] Avg episode reward: [(0, '-2.120'), (1, '21.880')] -[2023-10-10 21:31:40,736][98559] Updated weights for policy 0, policy_version 20210 (0.0009) -[2023-10-10 21:31:41,099][98559] Updated weights for policy 0, policy_version 20220 (0.0008) -[2023-10-10 21:31:43,466][98560] Updated weights for policy 1, policy_version 20202 (0.0007) -[2023-10-10 21:31:43,829][98560] Updated weights for policy 1, policy_version 20212 (0.0008) -[2023-10-10 21:31:44,207][98560] Updated weights for policy 1, policy_version 20222 (0.0009) -[2023-10-10 21:31:44,929][98559] Updated weights for policy 0, policy_version 20230 (0.0008) -[2023-10-10 21:31:45,306][98559] Updated weights for policy 0, policy_version 20240 (0.0009) -[2023-10-10 21:31:45,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 41418752. Throughput: 0: 1722.8, 1: 1690.2. Samples: 10365144. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-10 21:31:45,556][97672] Avg episode reward: [(0, '-2.120'), (1, '21.860')] -[2023-10-10 21:31:45,675][98559] Updated weights for policy 0, policy_version 20250 (0.0008) -[2023-10-10 21:31:48,393][98560] Updated weights for policy 1, policy_version 20232 (0.0007) -[2023-10-10 21:31:48,760][98560] Updated weights for policy 1, policy_version 20242 (0.0007) -[2023-10-10 21:31:49,115][98560] Updated weights for policy 1, policy_version 20252 (0.0008) -[2023-10-10 21:31:49,779][98559] Updated weights for policy 0, policy_version 20260 (0.0010) -[2023-10-10 21:31:50,138][98559] Updated weights for policy 0, policy_version 20270 (0.0011) -[2023-10-10 21:31:50,510][98559] Updated weights for policy 0, policy_version 20280 (0.0010) -[2023-10-10 21:31:50,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 41484288. Throughput: 0: 1696.0, 1: 1684.1. Samples: 10384352. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-10 21:31:50,557][97672] Avg episode reward: [(0, '-2.120'), (1, '21.940')] -[2023-10-10 21:31:52,969][98560] Updated weights for policy 1, policy_version 20262 (0.0009) -[2023-10-10 21:31:53,343][98560] Updated weights for policy 1, policy_version 20272 (0.0008) -[2023-10-10 21:31:53,714][98560] Updated weights for policy 1, policy_version 20282 (0.0008) -[2023-10-10 21:31:54,641][98559] Updated weights for policy 0, policy_version 20290 (0.0011) -[2023-10-10 21:31:55,016][98559] Updated weights for policy 0, policy_version 20300 (0.0009) -[2023-10-10 21:31:55,384][98559] Updated weights for policy 0, policy_version 20310 (0.0009) -[2023-10-10 21:31:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 41549824. Throughput: 0: 1709.1, 1: 1703.2. Samples: 10395600. Policy #0 lag: (min: 7.0, avg: 10.7, max: 39.0) -[2023-10-10 21:31:55,556][97672] Avg episode reward: [(0, '-2.120'), (1, '21.880')] -[2023-10-10 21:31:55,755][98559] Updated weights for policy 0, policy_version 20320 (0.0009) -[2023-10-10 21:31:57,987][98560] Updated weights for policy 1, policy_version 20292 (0.0009) -[2023-10-10 21:31:58,356][98560] Updated weights for policy 1, policy_version 20302 (0.0009) -[2023-10-10 21:31:58,728][98560] Updated weights for policy 1, policy_version 20312 (0.0008) -[2023-10-10 21:31:59,499][98559] Updated weights for policy 0, policy_version 20330 (0.0009) -[2023-10-10 21:31:59,876][98559] Updated weights for policy 0, policy_version 20340 (0.0007) -[2023-10-10 21:32:00,248][98559] Updated weights for policy 0, policy_version 20350 (0.0008) -[2023-10-10 21:32:00,556][97672] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 41648128. Throughput: 0: 1709.0, 1: 1679.0. Samples: 10415508. Policy #0 lag: (min: 7.0, avg: 10.7, max: 39.0) -[2023-10-10 21:32:00,557][97672] Avg episode reward: [(0, '-2.120'), (1, '22.040')] -[2023-10-10 21:32:02,686][98560] Updated weights for policy 1, policy_version 20322 (0.0010) -[2023-10-10 21:32:03,064][98560] Updated weights for policy 1, policy_version 20332 (0.0007) -[2023-10-10 21:32:03,430][98560] Updated weights for policy 1, policy_version 20342 (0.0007) -[2023-10-10 21:32:03,798][98560] Updated weights for policy 1, policy_version 20352 (0.0007) -[2023-10-10 21:32:04,172][98559] Updated weights for policy 0, policy_version 20360 (0.0008) -[2023-10-10 21:32:04,540][98559] Updated weights for policy 0, policy_version 20370 (0.0011) -[2023-10-10 21:32:04,923][98559] Updated weights for policy 0, policy_version 20380 (0.0009) -[2023-10-10 21:32:05,556][97672] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 41713664. Throughput: 0: 1684.4, 1: 1683.4. Samples: 10435094. Policy #0 lag: (min: 18.0, avg: 25.0, max: 50.0) -[2023-10-10 21:32:05,557][97672] Avg episode reward: [(0, '-2.120'), (1, '21.980')] -[2023-10-10 21:32:07,816][98560] Updated weights for policy 1, policy_version 20362 (0.0010) -[2023-10-10 21:32:08,188][98560] Updated weights for policy 1, policy_version 20372 (0.0009) -[2023-10-10 21:32:08,544][98560] Updated weights for policy 1, policy_version 20382 (0.0009) -[2023-10-10 21:32:08,780][98559] Updated weights for policy 0, policy_version 20390 (0.0007) -[2023-10-10 21:32:09,149][98559] Updated weights for policy 0, policy_version 20400 (0.0007) -[2023-10-10 21:32:09,518][98559] Updated weights for policy 0, policy_version 20410 (0.0010) -[2023-10-10 21:32:10,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 41779200. Throughput: 0: 1722.1, 1: 1687.0. Samples: 10446746. Policy #0 lag: (min: 18.0, avg: 25.0, max: 50.0) -[2023-10-10 21:32:10,557][97672] Avg episode reward: [(0, '-2.120'), (1, '21.980')] -[2023-10-10 21:32:12,472][98560] Updated weights for policy 1, policy_version 20392 (0.0009) -[2023-10-10 21:32:12,831][98560] Updated weights for policy 1, policy_version 20402 (0.0008) -[2023-10-10 21:32:13,205][98560] Updated weights for policy 1, policy_version 20412 (0.0007) -[2023-10-10 21:32:13,584][98559] Updated weights for policy 0, policy_version 20420 (0.0009) -[2023-10-10 21:32:13,948][98559] Updated weights for policy 0, policy_version 20430 (0.0008) -[2023-10-10 21:32:14,317][98559] Updated weights for policy 0, policy_version 20440 (0.0008) -[2023-10-10 21:32:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 41844736. Throughput: 0: 1700.8, 1: 1670.9. Samples: 10465882. Policy #0 lag: (min: 18.0, avg: 25.0, max: 50.0) -[2023-10-10 21:32:15,557][97672] Avg episode reward: [(0, '-2.120'), (1, '21.920')] -[2023-10-10 21:32:17,159][98560] Updated weights for policy 1, policy_version 20422 (0.0009) -[2023-10-10 21:32:17,547][98560] Updated weights for policy 1, policy_version 20432 (0.0008) -[2023-10-10 21:32:17,912][98560] Updated weights for policy 1, policy_version 20442 (0.0009) -[2023-10-10 21:32:18,381][98559] Updated weights for policy 0, policy_version 20450 (0.0009) -[2023-10-10 21:32:18,755][98559] Updated weights for policy 0, policy_version 20460 (0.0009) -[2023-10-10 21:32:19,138][98559] Updated weights for policy 0, policy_version 20470 (0.0008) -[2023-10-10 21:32:19,510][98559] Updated weights for policy 0, policy_version 20480 (0.0007) -[2023-10-10 21:32:20,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 41910272. Throughput: 0: 1700.2, 1: 1696.8. Samples: 10486792. Policy #0 lag: (min: 18.0, avg: 25.0, max: 50.0) -[2023-10-10 21:32:20,557][97672] Avg episode reward: [(0, '-2.120'), (1, '21.820')] -[2023-10-10 21:32:21,909][98560] Updated weights for policy 1, policy_version 20452 (0.0008) -[2023-10-10 21:32:22,278][98560] Updated weights for policy 1, policy_version 20462 (0.0008) -[2023-10-10 21:32:22,653][98560] Updated weights for policy 1, policy_version 20472 (0.0011) -[2023-10-10 21:32:23,394][98559] Updated weights for policy 0, policy_version 20490 (0.0010) -[2023-10-10 21:32:23,765][98559] Updated weights for policy 0, policy_version 20500 (0.0009) -[2023-10-10 21:32:24,140][98559] Updated weights for policy 0, policy_version 20510 (0.0007) -[2023-10-10 21:32:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 41975808. Throughput: 0: 1721.0, 1: 1671.5. Samples: 10497346. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-10 21:32:25,557][97672] Avg episode reward: [(0, '-2.120'), (1, '21.820')] -[2023-10-10 21:32:26,553][98560] Updated weights for policy 1, policy_version 20482 (0.0009) -[2023-10-10 21:32:26,926][98560] Updated weights for policy 1, policy_version 20492 (0.0007) -[2023-10-10 21:32:27,291][98560] Updated weights for policy 1, policy_version 20502 (0.0010) -[2023-10-10 21:32:27,663][98560] Updated weights for policy 1, policy_version 20512 (0.0009) -[2023-10-10 21:32:28,256][98559] Updated weights for policy 0, policy_version 20520 (0.0011) -[2023-10-10 21:32:28,624][98559] Updated weights for policy 0, policy_version 20530 (0.0007) -[2023-10-10 21:32:29,001][98559] Updated weights for policy 0, policy_version 20540 (0.0009) -[2023-10-10 21:32:30,556][97672] Fps is (10 sec: 13107.7, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 42041344. Throughput: 0: 1690.1, 1: 1683.7. Samples: 10516966. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-10 21:32:30,556][97672] Avg episode reward: [(0, '-2.120'), (1, '21.780')] -[2023-10-10 21:32:31,659][98560] Updated weights for policy 1, policy_version 20522 (0.0007) -[2023-10-10 21:32:32,037][98560] Updated weights for policy 1, policy_version 20532 (0.0008) -[2023-10-10 21:32:32,420][98560] Updated weights for policy 1, policy_version 20542 (0.0010) -[2023-10-10 21:32:32,864][98559] Updated weights for policy 0, policy_version 20550 (0.0010) -[2023-10-10 21:32:33,228][98559] Updated weights for policy 0, policy_version 20560 (0.0009) -[2023-10-10 21:32:33,592][98559] Updated weights for policy 0, policy_version 20570 (0.0009) -[2023-10-10 21:32:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 42106880. Throughput: 0: 1710.2, 1: 1708.1. Samples: 10538178. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-10 21:32:35,557][97672] Avg episode reward: [(0, '-2.120'), (1, '21.760')] -[2023-10-10 21:32:35,567][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000020544_21037056.pth... -[2023-10-10 21:32:35,567][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000020576_21069824.pth... -[2023-10-10 21:32:35,597][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000018976_19431424.pth -[2023-10-10 21:32:35,605][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000018976_19431424.pth -[2023-10-10 21:32:36,500][98560] Updated weights for policy 1, policy_version 20552 (0.0009) -[2023-10-10 21:32:36,875][98560] Updated weights for policy 1, policy_version 20562 (0.0008) -[2023-10-10 21:32:37,244][98560] Updated weights for policy 1, policy_version 20572 (0.0010) -[2023-10-10 21:32:37,563][98559] Updated weights for policy 0, policy_version 20580 (0.0009) -[2023-10-10 21:32:37,929][98559] Updated weights for policy 0, policy_version 20590 (0.0007) -[2023-10-10 21:32:38,296][98559] Updated weights for policy 0, policy_version 20600 (0.0007) -[2023-10-10 21:32:40,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 42172416. Throughput: 0: 1703.3, 1: 1680.1. Samples: 10547854. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-10 21:32:40,557][97672] Avg episode reward: [(0, '-2.120'), (1, '21.820')] -[2023-10-10 21:32:41,257][98560] Updated weights for policy 1, policy_version 20582 (0.0009) -[2023-10-10 21:32:41,630][98560] Updated weights for policy 1, policy_version 20592 (0.0008) -[2023-10-10 21:32:42,001][98560] Updated weights for policy 1, policy_version 20602 (0.0008) -[2023-10-10 21:32:42,460][98559] Updated weights for policy 0, policy_version 20610 (0.0009) -[2023-10-10 21:32:42,831][98559] Updated weights for policy 0, policy_version 20620 (0.0007) -[2023-10-10 21:32:43,196][98559] Updated weights for policy 0, policy_version 20630 (0.0008) -[2023-10-10 21:32:43,569][98559] Updated weights for policy 0, policy_version 20640 (0.0010) -[2023-10-10 21:32:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 42237952. Throughput: 0: 1694.8, 1: 1706.3. Samples: 10568556. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-10 21:32:45,557][97672] Avg episode reward: [(0, '-2.080'), (1, '21.820')] -[2023-10-10 21:32:45,558][98385] Saving new best policy, reward=-2.080! -[2023-10-10 21:32:45,881][98560] Updated weights for policy 1, policy_version 20612 (0.0008) -[2023-10-10 21:32:46,256][98560] Updated weights for policy 1, policy_version 20622 (0.0010) -[2023-10-10 21:32:46,626][98560] Updated weights for policy 1, policy_version 20632 (0.0007) -[2023-10-10 21:32:47,436][98559] Updated weights for policy 0, policy_version 20650 (0.0010) -[2023-10-10 21:32:47,809][98559] Updated weights for policy 0, policy_version 20660 (0.0009) -[2023-10-10 21:32:48,173][98559] Updated weights for policy 0, policy_version 20670 (0.0010) -[2023-10-10 21:32:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 42303488. Throughput: 0: 1716.7, 1: 1713.2. Samples: 10589440. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-10 21:32:50,557][97672] Avg episode reward: [(0, '-2.080'), (1, '21.700')] -[2023-10-10 21:32:50,672][98560] Updated weights for policy 1, policy_version 20642 (0.0009) -[2023-10-10 21:32:51,034][98560] Updated weights for policy 1, policy_version 20652 (0.0011) -[2023-10-10 21:32:51,400][98560] Updated weights for policy 1, policy_version 20662 (0.0010) -[2023-10-10 21:32:51,771][98560] Updated weights for policy 1, policy_version 20672 (0.0010) -[2023-10-10 21:32:52,150][98559] Updated weights for policy 0, policy_version 20680 (0.0010) -[2023-10-10 21:32:52,524][98559] Updated weights for policy 0, policy_version 20690 (0.0009) -[2023-10-10 21:32:52,891][98559] Updated weights for policy 0, policy_version 20700 (0.0008) -[2023-10-10 21:32:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 42369024. Throughput: 0: 1686.0, 1: 1693.1. Samples: 10598808. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-10 21:32:55,557][97672] Avg episode reward: [(0, '-1.980'), (1, '21.800')] -[2023-10-10 21:32:55,558][98385] Saving new best policy, reward=-1.980! -[2023-10-10 21:32:55,702][98560] Updated weights for policy 1, policy_version 20682 (0.0011) -[2023-10-10 21:32:56,067][98560] Updated weights for policy 1, policy_version 20692 (0.0009) -[2023-10-10 21:32:56,439][98560] Updated weights for policy 1, policy_version 20702 (0.0011) -[2023-10-10 21:32:56,898][98559] Updated weights for policy 0, policy_version 20710 (0.0008) -[2023-10-10 21:32:57,271][98559] Updated weights for policy 0, policy_version 20720 (0.0008) -[2023-10-10 21:32:57,643][98559] Updated weights for policy 0, policy_version 20730 (0.0010) -[2023-10-10 21:33:00,434][98560] Updated weights for policy 1, policy_version 20712 (0.0007) -[2023-10-10 21:33:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 42434560. Throughput: 0: 1705.8, 1: 1716.6. Samples: 10619890. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-10 21:33:00,557][97672] Avg episode reward: [(0, '-1.980'), (1, '21.700')] -[2023-10-10 21:33:00,802][98560] Updated weights for policy 1, policy_version 20722 (0.0009) -[2023-10-10 21:33:01,180][98560] Updated weights for policy 1, policy_version 20732 (0.0009) -[2023-10-10 21:33:01,762][98559] Updated weights for policy 0, policy_version 20740 (0.0009) -[2023-10-10 21:33:02,133][98559] Updated weights for policy 0, policy_version 20750 (0.0007) -[2023-10-10 21:33:02,495][98559] Updated weights for policy 0, policy_version 20760 (0.0009) -[2023-10-10 21:33:05,230][98560] Updated weights for policy 1, policy_version 20742 (0.0007) -[2023-10-10 21:33:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 42500096. Throughput: 0: 1710.0, 1: 1721.2. Samples: 10641192. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:33:05,557][97672] Avg episode reward: [(0, '-1.980'), (1, '21.640')] -[2023-10-10 21:33:05,616][98560] Updated weights for policy 1, policy_version 20752 (0.0009) -[2023-10-10 21:33:05,993][98560] Updated weights for policy 1, policy_version 20762 (0.0007) -[2023-10-10 21:33:06,420][98559] Updated weights for policy 0, policy_version 20770 (0.0009) -[2023-10-10 21:33:06,789][98559] Updated weights for policy 0, policy_version 20780 (0.0009) -[2023-10-10 21:33:07,165][98559] Updated weights for policy 0, policy_version 20790 (0.0009) -[2023-10-10 21:33:07,523][98559] Updated weights for policy 0, policy_version 20800 (0.0010) -[2023-10-10 21:33:10,022][98560] Updated weights for policy 1, policy_version 20772 (0.0008) -[2023-10-10 21:33:10,393][98560] Updated weights for policy 1, policy_version 20782 (0.0010) -[2023-10-10 21:33:10,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 42565632. Throughput: 0: 1684.6, 1: 1712.3. Samples: 10650204. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:33:10,556][97672] Avg episode reward: [(0, '-2.040'), (1, '21.700')] -[2023-10-10 21:33:10,767][98560] Updated weights for policy 1, policy_version 20792 (0.0010) -[2023-10-10 21:33:11,822][98559] Updated weights for policy 0, policy_version 20810 (0.0008) -[2023-10-10 21:33:12,202][98559] Updated weights for policy 0, policy_version 20820 (0.0009) -[2023-10-10 21:33:12,584][98559] Updated weights for policy 0, policy_version 20830 (0.0011) -[2023-10-10 21:33:14,817][98560] Updated weights for policy 1, policy_version 20802 (0.0009) -[2023-10-10 21:33:15,192][98560] Updated weights for policy 1, policy_version 20812 (0.0008) -[2023-10-10 21:33:15,552][98560] Updated weights for policy 1, policy_version 20822 (0.0009) -[2023-10-10 21:33:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 42631168. Throughput: 0: 1716.1, 1: 1713.5. Samples: 10671300. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:33:15,557][97672] Avg episode reward: [(0, '-1.880'), (1, '21.740')] -[2023-10-10 21:33:15,558][98385] Saving new best policy, reward=-1.880! -[2023-10-10 21:33:15,920][98560] Updated weights for policy 1, policy_version 20832 (0.0011) -[2023-10-10 21:33:16,439][98559] Updated weights for policy 0, policy_version 20840 (0.0010) -[2023-10-10 21:33:16,814][98559] Updated weights for policy 0, policy_version 20850 (0.0010) -[2023-10-10 21:33:17,169][98559] Updated weights for policy 0, policy_version 20860 (0.0011) -[2023-10-10 21:33:20,012][98560] Updated weights for policy 1, policy_version 20842 (0.0010) -[2023-10-10 21:33:20,378][98560] Updated weights for policy 1, policy_version 20852 (0.0009) -[2023-10-10 21:33:20,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 42696704. Throughput: 0: 1721.7, 1: 1707.5. Samples: 10692488. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:33:20,557][97672] Avg episode reward: [(0, '-1.880'), (1, '21.760')] -[2023-10-10 21:33:20,757][98560] Updated weights for policy 1, policy_version 20862 (0.0009) -[2023-10-10 21:33:21,000][98559] Updated weights for policy 0, policy_version 20870 (0.0009) -[2023-10-10 21:33:21,370][98559] Updated weights for policy 0, policy_version 20880 (0.0008) -[2023-10-10 21:33:21,749][98559] Updated weights for policy 0, policy_version 20890 (0.0009) -[2023-10-10 21:33:24,670][98560] Updated weights for policy 1, policy_version 20872 (0.0008) -[2023-10-10 21:33:25,034][98560] Updated weights for policy 1, policy_version 20882 (0.0009) -[2023-10-10 21:33:25,396][98560] Updated weights for policy 1, policy_version 20892 (0.0007) -[2023-10-10 21:33:25,556][97672] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 42795008. Throughput: 0: 1710.2, 1: 1708.0. Samples: 10701672. Policy #0 lag: (min: 3.0, avg: 10.9, max: 35.0) -[2023-10-10 21:33:25,557][97672] Avg episode reward: [(0, '-1.880'), (1, '21.820')] -[2023-10-10 21:33:25,780][98559] Updated weights for policy 0, policy_version 20900 (0.0008) -[2023-10-10 21:33:26,152][98559] Updated weights for policy 0, policy_version 20910 (0.0008) -[2023-10-10 21:33:26,521][98559] Updated weights for policy 0, policy_version 20920 (0.0009) -[2023-10-10 21:33:29,284][98560] Updated weights for policy 1, policy_version 20902 (0.0008) -[2023-10-10 21:33:29,646][98560] Updated weights for policy 1, policy_version 20912 (0.0008) -[2023-10-10 21:33:30,008][98560] Updated weights for policy 1, policy_version 20922 (0.0009) -[2023-10-10 21:33:30,331][98559] Updated weights for policy 0, policy_version 20930 (0.0009) -[2023-10-10 21:33:30,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 42860544. Throughput: 0: 1722.7, 1: 1708.0. Samples: 10722936. Policy #0 lag: (min: 3.0, avg: 10.9, max: 35.0) -[2023-10-10 21:33:30,556][97672] Avg episode reward: [(0, '-1.880'), (1, '21.860')] -[2023-10-10 21:33:30,694][98559] Updated weights for policy 0, policy_version 20940 (0.0012) -[2023-10-10 21:33:31,066][98559] Updated weights for policy 0, policy_version 20950 (0.0008) -[2023-10-10 21:33:31,434][98559] Updated weights for policy 0, policy_version 20960 (0.0008) -[2023-10-10 21:33:34,015][98560] Updated weights for policy 1, policy_version 20932 (0.0010) -[2023-10-10 21:33:34,387][98560] Updated weights for policy 1, policy_version 20942 (0.0008) -[2023-10-10 21:33:34,752][98560] Updated weights for policy 1, policy_version 20952 (0.0011) -[2023-10-10 21:33:35,400][98559] Updated weights for policy 0, policy_version 20970 (0.0007) -[2023-10-10 21:33:35,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 42926080. Throughput: 0: 1717.0, 1: 1693.5. Samples: 10742912. Policy #0 lag: (min: 3.0, avg: 10.9, max: 35.0) -[2023-10-10 21:33:35,557][97672] Avg episode reward: [(0, '-1.840'), (1, '21.800')] -[2023-10-10 21:33:35,776][98559] Updated weights for policy 0, policy_version 20980 (0.0008) -[2023-10-10 21:33:36,150][98559] Updated weights for policy 0, policy_version 20990 (0.0008) -[2023-10-10 21:33:36,217][98385] Saving new best policy, reward=-1.840! -[2023-10-10 21:33:38,898][98560] Updated weights for policy 1, policy_version 20962 (0.0007) -[2023-10-10 21:33:39,267][98560] Updated weights for policy 1, policy_version 20972 (0.0007) -[2023-10-10 21:33:39,638][98560] Updated weights for policy 1, policy_version 20982 (0.0007) -[2023-10-10 21:33:39,996][98560] Updated weights for policy 1, policy_version 20992 (0.0011) -[2023-10-10 21:33:40,101][98559] Updated weights for policy 0, policy_version 21000 (0.0008) -[2023-10-10 21:33:40,468][98559] Updated weights for policy 0, policy_version 21010 (0.0008) -[2023-10-10 21:33:40,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 42991616. Throughput: 0: 1722.8, 1: 1709.6. Samples: 10753264. Policy #0 lag: (min: 3.0, avg: 10.9, max: 35.0) -[2023-10-10 21:33:40,557][97672] Avg episode reward: [(0, '-1.840'), (1, '21.880')] -[2023-10-10 21:33:40,841][98559] Updated weights for policy 0, policy_version 21020 (0.0007) -[2023-10-10 21:33:44,101][98560] Updated weights for policy 1, policy_version 21002 (0.0007) -[2023-10-10 21:33:44,477][98560] Updated weights for policy 1, policy_version 21012 (0.0009) -[2023-10-10 21:33:44,846][98560] Updated weights for policy 1, policy_version 21022 (0.0008) -[2023-10-10 21:33:44,867][98559] Updated weights for policy 0, policy_version 21030 (0.0008) -[2023-10-10 21:33:45,226][98559] Updated weights for policy 0, policy_version 21040 (0.0009) -[2023-10-10 21:33:45,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 43057152. Throughput: 0: 1722.9, 1: 1704.9. Samples: 10774142. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:33:45,557][97672] Avg episode reward: [(0, '-1.840'), (1, '21.880')] -[2023-10-10 21:33:45,593][98559] Updated weights for policy 0, policy_version 21050 (0.0008) -[2023-10-10 21:33:48,892][98560] Updated weights for policy 1, policy_version 21032 (0.0007) -[2023-10-10 21:33:49,268][98560] Updated weights for policy 1, policy_version 21042 (0.0007) -[2023-10-10 21:33:49,618][98559] Updated weights for policy 0, policy_version 21060 (0.0007) -[2023-10-10 21:33:49,631][98560] Updated weights for policy 1, policy_version 21052 (0.0008) -[2023-10-10 21:33:49,979][98559] Updated weights for policy 0, policy_version 21070 (0.0008) -[2023-10-10 21:33:50,351][98559] Updated weights for policy 0, policy_version 21080 (0.0010) -[2023-10-10 21:33:50,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 43122688. Throughput: 0: 1697.8, 1: 1672.6. Samples: 10792860. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:33:50,556][97672] Avg episode reward: [(0, '-1.840'), (1, '21.960')] -[2023-10-10 21:33:53,731][98560] Updated weights for policy 1, policy_version 21062 (0.0007) -[2023-10-10 21:33:54,129][98560] Updated weights for policy 1, policy_version 21072 (0.0008) -[2023-10-10 21:33:54,417][98559] Updated weights for policy 0, policy_version 21090 (0.0009) -[2023-10-10 21:33:54,499][98560] Updated weights for policy 1, policy_version 21082 (0.0008) -[2023-10-10 21:33:54,791][98559] Updated weights for policy 0, policy_version 21100 (0.0008) -[2023-10-10 21:33:55,153][98559] Updated weights for policy 0, policy_version 21110 (0.0009) -[2023-10-10 21:33:55,520][98559] Updated weights for policy 0, policy_version 21120 (0.0009) -[2023-10-10 21:33:55,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 43220992. Throughput: 0: 1716.8, 1: 1699.2. Samples: 10803924. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:33:55,557][97672] Avg episode reward: [(0, '-1.840'), (1, '22.080')] -[2023-10-10 21:33:55,558][98439] Saving new best policy, reward=22.080! -[2023-10-10 21:33:58,464][98560] Updated weights for policy 1, policy_version 21092 (0.0009) -[2023-10-10 21:33:58,834][98560] Updated weights for policy 1, policy_version 21102 (0.0008) -[2023-10-10 21:33:59,209][98560] Updated weights for policy 1, policy_version 21112 (0.0008) -[2023-10-10 21:33:59,320][98559] Updated weights for policy 0, policy_version 21130 (0.0009) -[2023-10-10 21:33:59,693][98559] Updated weights for policy 0, policy_version 21140 (0.0010) -[2023-10-10 21:34:00,056][98559] Updated weights for policy 0, policy_version 21150 (0.0011) -[2023-10-10 21:34:00,556][97672] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 43286528. Throughput: 0: 1706.3, 1: 1686.2. Samples: 10823964. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-10 21:34:00,557][97672] Avg episode reward: [(0, '-1.840'), (1, '22.140')] -[2023-10-10 21:34:00,557][98439] Saving new best policy, reward=22.140! -[2023-10-10 21:34:03,226][98560] Updated weights for policy 1, policy_version 21122 (0.0008) -[2023-10-10 21:34:03,598][98560] Updated weights for policy 1, policy_version 21132 (0.0008) -[2023-10-10 21:34:03,955][98560] Updated weights for policy 1, policy_version 21142 (0.0008) -[2023-10-10 21:34:04,179][98559] Updated weights for policy 0, policy_version 21160 (0.0007) -[2023-10-10 21:34:04,328][98560] Updated weights for policy 1, policy_version 21152 (0.0007) -[2023-10-10 21:34:04,543][98559] Updated weights for policy 0, policy_version 21170 (0.0008) -[2023-10-10 21:34:04,912][98559] Updated weights for policy 0, policy_version 21180 (0.0009) -[2023-10-10 21:34:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 43352064. Throughput: 0: 1683.8, 1: 1664.4. Samples: 10843156. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-10 21:34:05,556][97672] Avg episode reward: [(0, '-1.840'), (1, '22.200')] -[2023-10-10 21:34:05,566][98439] Saving new best policy, reward=22.200! -[2023-10-10 21:34:08,419][98560] Updated weights for policy 1, policy_version 21162 (0.0008) -[2023-10-10 21:34:08,777][98560] Updated weights for policy 1, policy_version 21172 (0.0007) -[2023-10-10 21:34:08,890][98559] Updated weights for policy 0, policy_version 21190 (0.0008) -[2023-10-10 21:34:09,152][98560] Updated weights for policy 1, policy_version 21182 (0.0008) -[2023-10-10 21:34:09,247][98559] Updated weights for policy 0, policy_version 21200 (0.0007) -[2023-10-10 21:34:09,624][98559] Updated weights for policy 0, policy_version 21210 (0.0007) -[2023-10-10 21:34:10,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 43417600. Throughput: 0: 1716.9, 1: 1692.1. Samples: 10855080. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-10 21:34:10,557][97672] Avg episode reward: [(0, '-1.820'), (1, '22.200')] -[2023-10-10 21:34:10,559][98385] Saving new best policy, reward=-1.820! -[2023-10-10 21:34:13,269][98560] Updated weights for policy 1, policy_version 21192 (0.0010) -[2023-10-10 21:34:13,530][98559] Updated weights for policy 0, policy_version 21220 (0.0007) -[2023-10-10 21:34:13,642][98560] Updated weights for policy 1, policy_version 21202 (0.0008) -[2023-10-10 21:34:13,907][98559] Updated weights for policy 0, policy_version 21230 (0.0007) -[2023-10-10 21:34:14,005][98560] Updated weights for policy 1, policy_version 21212 (0.0008) -[2023-10-10 21:34:14,277][98559] Updated weights for policy 0, policy_version 21240 (0.0009) -[2023-10-10 21:34:15,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 43483136. Throughput: 0: 1696.2, 1: 1670.3. Samples: 10874428. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-10 21:34:15,557][97672] Avg episode reward: [(0, '-1.760'), (1, '22.200')] -[2023-10-10 21:34:15,557][98385] Saving new best policy, reward=-1.760! -[2023-10-10 21:34:17,945][98560] Updated weights for policy 1, policy_version 21222 (0.0008) -[2023-10-10 21:34:18,058][98559] Updated weights for policy 0, policy_version 21250 (0.0008) -[2023-10-10 21:34:18,308][98560] Updated weights for policy 1, policy_version 21232 (0.0007) -[2023-10-10 21:34:18,426][98559] Updated weights for policy 0, policy_version 21260 (0.0008) -[2023-10-10 21:34:18,669][98560] Updated weights for policy 1, policy_version 21242 (0.0007) -[2023-10-10 21:34:18,790][98559] Updated weights for policy 0, policy_version 21270 (0.0008) -[2023-10-10 21:34:19,165][98559] Updated weights for policy 0, policy_version 21280 (0.0008) -[2023-10-10 21:34:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 43548672. Throughput: 0: 1701.5, 1: 1673.5. Samples: 10894784. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-10 21:34:20,557][97672] Avg episode reward: [(0, '-1.760'), (1, '22.240')] -[2023-10-10 21:34:20,569][98439] Saving new best policy, reward=22.240! -[2023-10-10 21:34:22,803][98560] Updated weights for policy 1, policy_version 21252 (0.0007) -[2023-10-10 21:34:23,170][98560] Updated weights for policy 1, policy_version 21262 (0.0009) -[2023-10-10 21:34:23,210][98559] Updated weights for policy 0, policy_version 21290 (0.0009) -[2023-10-10 21:34:23,545][98560] Updated weights for policy 1, policy_version 21272 (0.0009) -[2023-10-10 21:34:23,580][98559] Updated weights for policy 0, policy_version 21300 (0.0007) -[2023-10-10 21:34:23,949][98559] Updated weights for policy 0, policy_version 21310 (0.0007) -[2023-10-10 21:34:25,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 43614208. Throughput: 0: 1707.9, 1: 1685.5. Samples: 10905966. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-10 21:34:25,556][97672] Avg episode reward: [(0, '-1.760'), (1, '22.200')] -[2023-10-10 21:34:27,690][98560] Updated weights for policy 1, policy_version 21282 (0.0009) -[2023-10-10 21:34:27,804][98559] Updated weights for policy 0, policy_version 21320 (0.0010) -[2023-10-10 21:34:28,060][98560] Updated weights for policy 1, policy_version 21292 (0.0010) -[2023-10-10 21:34:28,174][98559] Updated weights for policy 0, policy_version 21330 (0.0007) -[2023-10-10 21:34:28,428][98560] Updated weights for policy 1, policy_version 21302 (0.0009) -[2023-10-10 21:34:28,538][98559] Updated weights for policy 0, policy_version 21340 (0.0007) -[2023-10-10 21:34:28,792][98560] Updated weights for policy 1, policy_version 21312 (0.0007) -[2023-10-10 21:34:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 43679744. Throughput: 0: 1693.1, 1: 1662.3. Samples: 10925136. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-10 21:34:30,557][97672] Avg episode reward: [(0, '-1.760'), (1, '22.180')] -[2023-10-10 21:34:32,649][98559] Updated weights for policy 0, policy_version 21350 (0.0009) -[2023-10-10 21:34:32,774][98560] Updated weights for policy 1, policy_version 21322 (0.0007) -[2023-10-10 21:34:33,012][98559] Updated weights for policy 0, policy_version 21360 (0.0009) -[2023-10-10 21:34:33,136][98560] Updated weights for policy 1, policy_version 21332 (0.0008) -[2023-10-10 21:34:33,376][98559] Updated weights for policy 0, policy_version 21370 (0.0007) -[2023-10-10 21:34:33,506][98560] Updated weights for policy 1, policy_version 21342 (0.0008) -[2023-10-10 21:34:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 43745280. Throughput: 0: 1714.7, 1: 1686.0. Samples: 10945890. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-10 21:34:35,557][97672] Avg episode reward: [(0, '-1.840'), (1, '22.180')] -[2023-10-10 21:34:35,566][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000021376_21889024.pth... -[2023-10-10 21:34:35,567][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000021344_21856256.pth... -[2023-10-10 21:34:35,602][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000019776_20250624.pth -[2023-10-10 21:34:35,605][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000019776_20250624.pth -[2023-10-10 21:34:37,447][98559] Updated weights for policy 0, policy_version 21380 (0.0009) -[2023-10-10 21:34:37,564][98560] Updated weights for policy 1, policy_version 21352 (0.0009) -[2023-10-10 21:34:37,810][98559] Updated weights for policy 0, policy_version 21390 (0.0007) -[2023-10-10 21:34:37,931][98560] Updated weights for policy 1, policy_version 21362 (0.0008) -[2023-10-10 21:34:38,184][98559] Updated weights for policy 0, policy_version 21400 (0.0009) -[2023-10-10 21:34:38,292][98560] Updated weights for policy 1, policy_version 21372 (0.0009) -[2023-10-10 21:34:40,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 43810816. Throughput: 0: 1701.2, 1: 1679.4. Samples: 10956054. Policy #0 lag: (min: 12.0, avg: 18.0, max: 44.0) -[2023-10-10 21:34:40,557][97672] Avg episode reward: [(0, '-1.840'), (1, '22.240')] -[2023-10-10 21:34:42,121][98559] Updated weights for policy 0, policy_version 21410 (0.0007) -[2023-10-10 21:34:42,356][98560] Updated weights for policy 1, policy_version 21382 (0.0007) -[2023-10-10 21:34:42,495][98559] Updated weights for policy 0, policy_version 21420 (0.0008) -[2023-10-10 21:34:42,717][98560] Updated weights for policy 1, policy_version 21392 (0.0008) -[2023-10-10 21:34:42,855][98559] Updated weights for policy 0, policy_version 21430 (0.0009) -[2023-10-10 21:34:43,095][98560] Updated weights for policy 1, policy_version 21402 (0.0008) -[2023-10-10 21:34:43,226][98559] Updated weights for policy 0, policy_version 21440 (0.0009) -[2023-10-10 21:34:45,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 43876352. Throughput: 0: 1704.8, 1: 1673.3. Samples: 10975978. Policy #0 lag: (min: 12.0, avg: 18.0, max: 44.0) -[2023-10-10 21:34:45,557][97672] Avg episode reward: [(0, '-1.840'), (1, '22.180')] -[2023-10-10 21:34:47,223][98560] Updated weights for policy 1, policy_version 21412 (0.0008) -[2023-10-10 21:34:47,289][98559] Updated weights for policy 0, policy_version 21450 (0.0007) -[2023-10-10 21:34:47,616][98560] Updated weights for policy 1, policy_version 21422 (0.0008) -[2023-10-10 21:34:47,655][98559] Updated weights for policy 0, policy_version 21460 (0.0007) -[2023-10-10 21:34:47,988][98560] Updated weights for policy 1, policy_version 21432 (0.0009) -[2023-10-10 21:34:48,022][98559] Updated weights for policy 0, policy_version 21470 (0.0009) -[2023-10-10 21:34:50,556][97672] Fps is (10 sec: 13107.7, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 43941888. Throughput: 0: 1722.4, 1: 1691.6. Samples: 10996788. Policy #0 lag: (min: 12.0, avg: 18.0, max: 44.0) -[2023-10-10 21:34:50,556][97672] Avg episode reward: [(0, '-1.860'), (1, '22.120')] -[2023-10-10 21:34:51,912][98560] Updated weights for policy 1, policy_version 21442 (0.0007) -[2023-10-10 21:34:52,268][98560] Updated weights for policy 1, policy_version 21452 (0.0007) -[2023-10-10 21:34:52,315][98559] Updated weights for policy 0, policy_version 21480 (0.0010) -[2023-10-10 21:34:52,647][98560] Updated weights for policy 1, policy_version 21462 (0.0007) -[2023-10-10 21:34:52,697][98559] Updated weights for policy 0, policy_version 21490 (0.0007) -[2023-10-10 21:34:53,004][98560] Updated weights for policy 1, policy_version 21472 (0.0007) -[2023-10-10 21:34:53,054][98559] Updated weights for policy 0, policy_version 21500 (0.0009) -[2023-10-10 21:34:55,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.1, 300 sec: 13662.6). Total num frames: 44007424. Throughput: 0: 1685.8, 1: 1667.5. Samples: 11005976. Policy #0 lag: (min: 12.0, avg: 18.0, max: 44.0) -[2023-10-10 21:34:55,557][97672] Avg episode reward: [(0, '-1.860'), (1, '22.080')] -[2023-10-10 21:34:57,069][98560] Updated weights for policy 1, policy_version 21482 (0.0010) -[2023-10-10 21:34:57,214][98559] Updated weights for policy 0, policy_version 21510 (0.0008) -[2023-10-10 21:34:57,451][98560] Updated weights for policy 1, policy_version 21492 (0.0010) -[2023-10-10 21:34:57,576][98559] Updated weights for policy 0, policy_version 21520 (0.0008) -[2023-10-10 21:34:57,816][98560] Updated weights for policy 1, policy_version 21502 (0.0009) -[2023-10-10 21:34:57,941][98559] Updated weights for policy 0, policy_version 21530 (0.0008) -[2023-10-10 21:35:00,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 44072960. Throughput: 0: 1700.2, 1: 1681.0. Samples: 11026582. Policy #0 lag: (min: 10.0, avg: 17.7, max: 42.0) -[2023-10-10 21:35:00,557][97672] Avg episode reward: [(0, '-1.860'), (1, '22.040')] -[2023-10-10 21:35:01,853][98560] Updated weights for policy 1, policy_version 21512 (0.0009) -[2023-10-10 21:35:01,863][98559] Updated weights for policy 0, policy_version 21540 (0.0011) -[2023-10-10 21:35:02,228][98559] Updated weights for policy 0, policy_version 21550 (0.0008) -[2023-10-10 21:35:02,228][98560] Updated weights for policy 1, policy_version 21522 (0.0007) -[2023-10-10 21:35:02,599][98559] Updated weights for policy 0, policy_version 21560 (0.0008) -[2023-10-10 21:35:02,604][98560] Updated weights for policy 1, policy_version 21532 (0.0007) -[2023-10-10 21:35:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 44138496. Throughput: 0: 1708.8, 1: 1687.8. Samples: 11047632. Policy #0 lag: (min: 10.0, avg: 17.7, max: 42.0) -[2023-10-10 21:35:05,557][97672] Avg episode reward: [(0, '-1.860'), (1, '22.160')] -[2023-10-10 21:35:06,517][98559] Updated weights for policy 0, policy_version 21570 (0.0009) -[2023-10-10 21:35:06,699][98560] Updated weights for policy 1, policy_version 21542 (0.0007) -[2023-10-10 21:35:06,884][98559] Updated weights for policy 0, policy_version 21580 (0.0010) -[2023-10-10 21:35:07,071][98560] Updated weights for policy 1, policy_version 21552 (0.0008) -[2023-10-10 21:35:07,251][98559] Updated weights for policy 0, policy_version 21590 (0.0009) -[2023-10-10 21:35:07,441][98560] Updated weights for policy 1, policy_version 21562 (0.0008) -[2023-10-10 21:35:07,624][98559] Updated weights for policy 0, policy_version 21600 (0.0007) -[2023-10-10 21:35:10,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 44204032. Throughput: 0: 1691.3, 1: 1661.7. Samples: 11056854. Policy #0 lag: (min: 10.0, avg: 17.7, max: 42.0) -[2023-10-10 21:35:10,557][97672] Avg episode reward: [(0, '-1.860'), (1, '22.080')] -[2023-10-10 21:35:11,470][98560] Updated weights for policy 1, policy_version 21572 (0.0007) -[2023-10-10 21:35:11,675][98559] Updated weights for policy 0, policy_version 21610 (0.0008) -[2023-10-10 21:35:11,839][98560] Updated weights for policy 1, policy_version 21582 (0.0007) -[2023-10-10 21:35:12,045][98559] Updated weights for policy 0, policy_version 21620 (0.0007) -[2023-10-10 21:35:12,215][98560] Updated weights for policy 1, policy_version 21592 (0.0009) -[2023-10-10 21:35:12,415][98559] Updated weights for policy 0, policy_version 21630 (0.0007) -[2023-10-10 21:35:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 44269568. Throughput: 0: 1705.7, 1: 1687.9. Samples: 11077846. Policy #0 lag: (min: 10.0, avg: 17.7, max: 42.0) -[2023-10-10 21:35:15,557][97672] Avg episode reward: [(0, '-1.840'), (1, '22.020')] -[2023-10-10 21:35:16,329][98560] Updated weights for policy 1, policy_version 21602 (0.0008) -[2023-10-10 21:35:16,368][98559] Updated weights for policy 0, policy_version 21640 (0.0008) -[2023-10-10 21:35:16,702][98560] Updated weights for policy 1, policy_version 21612 (0.0007) -[2023-10-10 21:35:16,724][98559] Updated weights for policy 0, policy_version 21650 (0.0007) -[2023-10-10 21:35:17,059][98560] Updated weights for policy 1, policy_version 21622 (0.0009) -[2023-10-10 21:35:17,103][98559] Updated weights for policy 0, policy_version 21660 (0.0007) -[2023-10-10 21:35:17,429][98560] Updated weights for policy 1, policy_version 21632 (0.0011) -[2023-10-10 21:35:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 44335104. Throughput: 0: 1712.6, 1: 1683.1. Samples: 11098696. Policy #0 lag: (min: 28.0, avg: 29.3, max: 53.0) -[2023-10-10 21:35:20,558][97672] Avg episode reward: [(0, '-1.840'), (1, '22.060')] -[2023-10-10 21:35:21,162][98559] Updated weights for policy 0, policy_version 21670 (0.0008) -[2023-10-10 21:35:21,531][98559] Updated weights for policy 0, policy_version 21680 (0.0008) -[2023-10-10 21:35:21,592][98560] Updated weights for policy 1, policy_version 21642 (0.0008) -[2023-10-10 21:35:21,899][98559] Updated weights for policy 0, policy_version 21690 (0.0007) -[2023-10-10 21:35:21,955][98560] Updated weights for policy 1, policy_version 21652 (0.0009) -[2023-10-10 21:35:22,316][98560] Updated weights for policy 1, policy_version 21662 (0.0007) -[2023-10-10 21:35:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 44400640. Throughput: 0: 1706.9, 1: 1664.1. Samples: 11107748. Policy #0 lag: (min: 28.0, avg: 29.3, max: 53.0) -[2023-10-10 21:35:25,557][97672] Avg episode reward: [(0, '-1.840'), (1, '22.060')] -[2023-10-10 21:35:25,811][98559] Updated weights for policy 0, policy_version 21700 (0.0008) -[2023-10-10 21:35:26,179][98559] Updated weights for policy 0, policy_version 21710 (0.0007) -[2023-10-10 21:35:26,291][98560] Updated weights for policy 1, policy_version 21672 (0.0007) -[2023-10-10 21:35:26,551][98559] Updated weights for policy 0, policy_version 21720 (0.0007) -[2023-10-10 21:35:26,662][98560] Updated weights for policy 1, policy_version 21682 (0.0007) -[2023-10-10 21:35:27,017][98560] Updated weights for policy 1, policy_version 21692 (0.0008) -[2023-10-10 21:35:30,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 44466176. Throughput: 0: 1713.2, 1: 1684.8. Samples: 11128888. Policy #0 lag: (min: 28.0, avg: 29.3, max: 53.0) -[2023-10-10 21:35:30,557][97672] Avg episode reward: [(0, '-1.840'), (1, '22.060')] -[2023-10-10 21:35:30,612][98559] Updated weights for policy 0, policy_version 21730 (0.0009) -[2023-10-10 21:35:30,976][98559] Updated weights for policy 0, policy_version 21740 (0.0009) -[2023-10-10 21:35:31,109][98560] Updated weights for policy 1, policy_version 21702 (0.0007) -[2023-10-10 21:35:31,352][98559] Updated weights for policy 0, policy_version 21750 (0.0009) -[2023-10-10 21:35:31,473][98560] Updated weights for policy 1, policy_version 21712 (0.0007) -[2023-10-10 21:35:31,711][98559] Updated weights for policy 0, policy_version 21760 (0.0007) -[2023-10-10 21:35:31,846][98560] Updated weights for policy 1, policy_version 21722 (0.0009) -[2023-10-10 21:35:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 44531712. Throughput: 0: 1707.0, 1: 1692.7. Samples: 11149776. Policy #0 lag: (min: 28.0, avg: 29.3, max: 53.0) -[2023-10-10 21:35:35,557][97672] Avg episode reward: [(0, '-1.840'), (1, '21.980')] -[2023-10-10 21:35:35,662][98559] Updated weights for policy 0, policy_version 21770 (0.0011) -[2023-10-10 21:35:35,852][98560] Updated weights for policy 1, policy_version 21732 (0.0008) -[2023-10-10 21:35:36,032][98559] Updated weights for policy 0, policy_version 21780 (0.0007) -[2023-10-10 21:35:36,248][98560] Updated weights for policy 1, policy_version 21742 (0.0007) -[2023-10-10 21:35:36,404][98559] Updated weights for policy 0, policy_version 21790 (0.0008) -[2023-10-10 21:35:36,620][98560] Updated weights for policy 1, policy_version 21752 (0.0008) -[2023-10-10 21:35:40,436][98559] Updated weights for policy 0, policy_version 21800 (0.0009) -[2023-10-10 21:35:40,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 44597248. Throughput: 0: 1714.9, 1: 1682.8. Samples: 11158872. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:35:40,557][97672] Avg episode reward: [(0, '-1.860'), (1, '22.020')] -[2023-10-10 21:35:40,802][98560] Updated weights for policy 1, policy_version 21762 (0.0010) -[2023-10-10 21:35:40,813][98559] Updated weights for policy 0, policy_version 21810 (0.0010) -[2023-10-10 21:35:41,172][98560] Updated weights for policy 1, policy_version 21772 (0.0007) -[2023-10-10 21:35:41,176][98559] Updated weights for policy 0, policy_version 21820 (0.0010) -[2023-10-10 21:35:41,532][98560] Updated weights for policy 1, policy_version 21782 (0.0009) -[2023-10-10 21:35:41,906][98560] Updated weights for policy 1, policy_version 21792 (0.0008) -[2023-10-10 21:35:45,147][98559] Updated weights for policy 0, policy_version 21830 (0.0009) -[2023-10-10 21:35:45,523][98559] Updated weights for policy 0, policy_version 21840 (0.0009) -[2023-10-10 21:35:45,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 44662784. Throughput: 0: 1716.5, 1: 1684.1. Samples: 11179606. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:35:45,556][97672] Avg episode reward: [(0, '-1.860'), (1, '22.040')] -[2023-10-10 21:35:45,882][98559] Updated weights for policy 0, policy_version 21850 (0.0008) -[2023-10-10 21:35:45,915][98560] Updated weights for policy 1, policy_version 21802 (0.0008) -[2023-10-10 21:35:46,276][98560] Updated weights for policy 1, policy_version 21812 (0.0010) -[2023-10-10 21:35:46,659][98560] Updated weights for policy 1, policy_version 21822 (0.0009) -[2023-10-10 21:35:49,877][98559] Updated weights for policy 0, policy_version 21860 (0.0008) -[2023-10-10 21:35:50,249][98559] Updated weights for policy 0, policy_version 21870 (0.0007) -[2023-10-10 21:35:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 44728320. Throughput: 0: 1692.9, 1: 1688.5. Samples: 11199796. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:35:50,557][97672] Avg episode reward: [(0, '-1.860'), (1, '22.060')] -[2023-10-10 21:35:50,617][98559] Updated weights for policy 0, policy_version 21880 (0.0008) -[2023-10-10 21:35:50,759][98560] Updated weights for policy 1, policy_version 21832 (0.0007) -[2023-10-10 21:35:51,129][98560] Updated weights for policy 1, policy_version 21842 (0.0008) -[2023-10-10 21:35:51,505][98560] Updated weights for policy 1, policy_version 21852 (0.0011) -[2023-10-10 21:35:54,622][98559] Updated weights for policy 0, policy_version 21890 (0.0009) -[2023-10-10 21:35:54,994][98559] Updated weights for policy 0, policy_version 21900 (0.0008) -[2023-10-10 21:35:55,359][98559] Updated weights for policy 0, policy_version 21910 (0.0008) -[2023-10-10 21:35:55,473][98560] Updated weights for policy 1, policy_version 21862 (0.0007) -[2023-10-10 21:35:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 44793856. Throughput: 0: 1716.4, 1: 1685.0. Samples: 11209914. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:35:55,557][97672] Avg episode reward: [(0, '-1.860'), (1, '21.900')] -[2023-10-10 21:35:55,732][98559] Updated weights for policy 0, policy_version 21920 (0.0008) -[2023-10-10 21:35:55,837][98560] Updated weights for policy 1, policy_version 21872 (0.0008) -[2023-10-10 21:35:56,214][98560] Updated weights for policy 1, policy_version 21882 (0.0008) -[2023-10-10 21:35:59,671][98559] Updated weights for policy 0, policy_version 21930 (0.0008) -[2023-10-10 21:36:00,040][98559] Updated weights for policy 0, policy_version 21940 (0.0007) -[2023-10-10 21:36:00,406][98559] Updated weights for policy 0, policy_version 21950 (0.0009) -[2023-10-10 21:36:00,423][98560] Updated weights for policy 1, policy_version 21892 (0.0008) -[2023-10-10 21:36:00,556][97672] Fps is (10 sec: 16384.4, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 44892160. Throughput: 0: 1716.7, 1: 1679.4. Samples: 11230670. Policy #0 lag: (min: 6.0, avg: 10.0, max: 38.0) -[2023-10-10 21:36:00,556][97672] Avg episode reward: [(0, '-1.860'), (1, '21.820')] -[2023-10-10 21:36:00,787][98560] Updated weights for policy 1, policy_version 21902 (0.0010) -[2023-10-10 21:36:01,158][98560] Updated weights for policy 1, policy_version 21912 (0.0008) -[2023-10-10 21:36:04,377][98559] Updated weights for policy 0, policy_version 21960 (0.0009) -[2023-10-10 21:36:04,762][98559] Updated weights for policy 0, policy_version 21970 (0.0009) -[2023-10-10 21:36:05,125][98559] Updated weights for policy 0, policy_version 21980 (0.0007) -[2023-10-10 21:36:05,159][98560] Updated weights for policy 1, policy_version 21922 (0.0007) -[2023-10-10 21:36:05,538][98560] Updated weights for policy 1, policy_version 21932 (0.0009) -[2023-10-10 21:36:05,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 44957696. Throughput: 0: 1691.6, 1: 1685.3. Samples: 11250656. Policy #0 lag: (min: 6.0, avg: 10.0, max: 38.0) -[2023-10-10 21:36:05,557][97672] Avg episode reward: [(0, '-1.860'), (1, '21.840')] -[2023-10-10 21:36:05,919][98560] Updated weights for policy 1, policy_version 21942 (0.0009) -[2023-10-10 21:36:06,289][98560] Updated weights for policy 1, policy_version 21952 (0.0009) -[2023-10-10 21:36:09,001][98559] Updated weights for policy 0, policy_version 21990 (0.0009) -[2023-10-10 21:36:09,371][98559] Updated weights for policy 0, policy_version 22000 (0.0007) -[2023-10-10 21:36:09,751][98559] Updated weights for policy 0, policy_version 22010 (0.0008) -[2023-10-10 21:36:10,319][98560] Updated weights for policy 1, policy_version 21962 (0.0010) -[2023-10-10 21:36:10,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 45023232. Throughput: 0: 1723.2, 1: 1687.8. Samples: 11261246. Policy #0 lag: (min: 6.0, avg: 10.0, max: 38.0) -[2023-10-10 21:36:10,557][97672] Avg episode reward: [(0, '-1.860'), (1, '21.900')] -[2023-10-10 21:36:10,692][98560] Updated weights for policy 1, policy_version 21972 (0.0010) -[2023-10-10 21:36:11,055][98560] Updated weights for policy 1, policy_version 21982 (0.0009) -[2023-10-10 21:36:13,749][98559] Updated weights for policy 0, policy_version 22020 (0.0008) -[2023-10-10 21:36:14,112][98559] Updated weights for policy 0, policy_version 22030 (0.0008) -[2023-10-10 21:36:14,482][98559] Updated weights for policy 0, policy_version 22040 (0.0008) -[2023-10-10 21:36:15,079][98560] Updated weights for policy 1, policy_version 21992 (0.0008) -[2023-10-10 21:36:15,448][98560] Updated weights for policy 1, policy_version 22002 (0.0007) -[2023-10-10 21:36:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 45088768. Throughput: 0: 1702.1, 1: 1685.9. Samples: 11281350. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-10 21:36:15,557][97672] Avg episode reward: [(0, '-1.860'), (1, '21.900')] -[2023-10-10 21:36:15,821][98560] Updated weights for policy 1, policy_version 22012 (0.0008) -[2023-10-10 21:36:18,467][98559] Updated weights for policy 0, policy_version 22050 (0.0008) -[2023-10-10 21:36:18,849][98559] Updated weights for policy 0, policy_version 22060 (0.0008) -[2023-10-10 21:36:19,208][98559] Updated weights for policy 0, policy_version 22070 (0.0008) -[2023-10-10 21:36:19,580][98559] Updated weights for policy 0, policy_version 22080 (0.0012) -[2023-10-10 21:36:19,877][98560] Updated weights for policy 1, policy_version 22022 (0.0010) -[2023-10-10 21:36:20,242][98560] Updated weights for policy 1, policy_version 22032 (0.0009) -[2023-10-10 21:36:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 45154304. Throughput: 0: 1696.4, 1: 1682.2. Samples: 11301816. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-10 21:36:20,557][97672] Avg episode reward: [(0, '-1.860'), (1, '21.880')] -[2023-10-10 21:36:20,619][98560] Updated weights for policy 1, policy_version 22042 (0.0007) -[2023-10-10 21:36:23,596][98559] Updated weights for policy 0, policy_version 22090 (0.0008) -[2023-10-10 21:36:23,966][98559] Updated weights for policy 0, policy_version 22100 (0.0010) -[2023-10-10 21:36:24,341][98559] Updated weights for policy 0, policy_version 22110 (0.0010) -[2023-10-10 21:36:24,660][98560] Updated weights for policy 1, policy_version 22052 (0.0008) -[2023-10-10 21:36:25,065][98560] Updated weights for policy 1, policy_version 22062 (0.0009) -[2023-10-10 21:36:25,437][98560] Updated weights for policy 1, policy_version 22072 (0.0008) -[2023-10-10 21:36:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 45219840. Throughput: 0: 1720.0, 1: 1688.5. Samples: 11312256. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-10 21:36:25,557][97672] Avg episode reward: [(0, '-1.860'), (1, '21.880')] -[2023-10-10 21:36:28,174][98559] Updated weights for policy 0, policy_version 22120 (0.0009) -[2023-10-10 21:36:28,556][98559] Updated weights for policy 0, policy_version 22130 (0.0009) -[2023-10-10 21:36:28,921][98559] Updated weights for policy 0, policy_version 22140 (0.0009) -[2023-10-10 21:36:29,378][98560] Updated weights for policy 1, policy_version 22082 (0.0008) -[2023-10-10 21:36:29,749][98560] Updated weights for policy 1, policy_version 22092 (0.0008) -[2023-10-10 21:36:30,113][98560] Updated weights for policy 1, policy_version 22102 (0.0007) -[2023-10-10 21:36:30,484][98560] Updated weights for policy 1, policy_version 22112 (0.0008) -[2023-10-10 21:36:30,556][97672] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 45318144. Throughput: 0: 1695.8, 1: 1691.0. Samples: 11332012. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-10 21:36:30,556][97672] Avg episode reward: [(0, '-1.860'), (1, '22.020')] -[2023-10-10 21:36:32,897][98559] Updated weights for policy 0, policy_version 22150 (0.0008) -[2023-10-10 21:36:33,259][98559] Updated weights for policy 0, policy_version 22160 (0.0008) -[2023-10-10 21:36:33,630][98559] Updated weights for policy 0, policy_version 22170 (0.0008) -[2023-10-10 21:36:34,472][98560] Updated weights for policy 1, policy_version 22122 (0.0009) -[2023-10-10 21:36:34,848][98560] Updated weights for policy 1, policy_version 22132 (0.0007) -[2023-10-10 21:36:35,218][98560] Updated weights for policy 1, policy_version 22142 (0.0008) -[2023-10-10 21:36:35,556][97672] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 45383680. Throughput: 0: 1719.3, 1: 1678.0. Samples: 11352676. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:36:35,557][97672] Avg episode reward: [(0, '-1.860'), (1, '22.020')] -[2023-10-10 21:36:35,566][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000022144_22675456.pth... -[2023-10-10 21:36:35,566][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000022176_22708224.pth... -[2023-10-10 21:36:35,604][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000020576_21069824.pth -[2023-10-10 21:36:35,612][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000020544_21037056.pth -[2023-10-10 21:36:37,647][98559] Updated weights for policy 0, policy_version 22180 (0.0010) -[2023-10-10 21:36:38,018][98559] Updated weights for policy 0, policy_version 22190 (0.0009) -[2023-10-10 21:36:38,392][98559] Updated weights for policy 0, policy_version 22200 (0.0009) -[2023-10-10 21:36:39,108][98560] Updated weights for policy 1, policy_version 22152 (0.0009) -[2023-10-10 21:36:39,473][98560] Updated weights for policy 1, policy_version 22162 (0.0010) -[2023-10-10 21:36:39,843][98560] Updated weights for policy 1, policy_version 22172 (0.0010) -[2023-10-10 21:36:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 45449216. Throughput: 0: 1704.9, 1: 1694.5. Samples: 11362888. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:36:40,556][97672] Avg episode reward: [(0, '-1.860'), (1, '22.040')] -[2023-10-10 21:36:42,305][98559] Updated weights for policy 0, policy_version 22210 (0.0007) -[2023-10-10 21:36:42,682][98559] Updated weights for policy 0, policy_version 22220 (0.0009) -[2023-10-10 21:36:43,056][98559] Updated weights for policy 0, policy_version 22230 (0.0008) -[2023-10-10 21:36:43,428][98559] Updated weights for policy 0, policy_version 22240 (0.0007) -[2023-10-10 21:36:43,894][98560] Updated weights for policy 1, policy_version 22182 (0.0007) -[2023-10-10 21:36:44,260][98560] Updated weights for policy 1, policy_version 22192 (0.0008) -[2023-10-10 21:36:44,634][98560] Updated weights for policy 1, policy_version 22202 (0.0008) -[2023-10-10 21:36:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 45514752. Throughput: 0: 1695.9, 1: 1701.1. Samples: 11383536. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:36:45,557][97672] Avg episode reward: [(0, '-1.860'), (1, '22.080')] -[2023-10-10 21:36:47,491][98559] Updated weights for policy 0, policy_version 22250 (0.0009) -[2023-10-10 21:36:47,867][98559] Updated weights for policy 0, policy_version 22260 (0.0011) -[2023-10-10 21:36:48,222][98559] Updated weights for policy 0, policy_version 22270 (0.0010) -[2023-10-10 21:36:48,533][98560] Updated weights for policy 1, policy_version 22212 (0.0007) -[2023-10-10 21:36:48,911][98560] Updated weights for policy 1, policy_version 22222 (0.0008) -[2023-10-10 21:36:49,276][98560] Updated weights for policy 1, policy_version 22232 (0.0008) -[2023-10-10 21:36:50,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 45580288. Throughput: 0: 1717.8, 1: 1676.9. Samples: 11403416. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:36:50,557][97672] Avg episode reward: [(0, '-1.860'), (1, '22.220')] -[2023-10-10 21:36:52,115][98559] Updated weights for policy 0, policy_version 22280 (0.0008) -[2023-10-10 21:36:52,488][98559] Updated weights for policy 0, policy_version 22290 (0.0008) -[2023-10-10 21:36:52,870][98559] Updated weights for policy 0, policy_version 22300 (0.0010) -[2023-10-10 21:36:53,293][98560] Updated weights for policy 1, policy_version 22242 (0.0009) -[2023-10-10 21:36:53,664][98560] Updated weights for policy 1, policy_version 22252 (0.0007) -[2023-10-10 21:36:54,031][98560] Updated weights for policy 1, policy_version 22262 (0.0009) -[2023-10-10 21:36:54,408][98560] Updated weights for policy 1, policy_version 22272 (0.0010) -[2023-10-10 21:36:55,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 45645824. Throughput: 0: 1689.6, 1: 1705.8. Samples: 11414040. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-10 21:36:55,557][97672] Avg episode reward: [(0, '-1.860'), (1, '22.160')] -[2023-10-10 21:36:56,883][98559] Updated weights for policy 0, policy_version 22310 (0.0009) -[2023-10-10 21:36:57,265][98559] Updated weights for policy 0, policy_version 22320 (0.0007) -[2023-10-10 21:36:57,632][98559] Updated weights for policy 0, policy_version 22330 (0.0007) -[2023-10-10 21:36:58,433][98560] Updated weights for policy 1, policy_version 22282 (0.0007) -[2023-10-10 21:36:58,796][98560] Updated weights for policy 1, policy_version 22292 (0.0007) -[2023-10-10 21:36:59,165][98560] Updated weights for policy 1, policy_version 22302 (0.0007) -[2023-10-10 21:37:00,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 45711360. Throughput: 0: 1708.4, 1: 1693.3. Samples: 11434428. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-10 21:37:00,556][97672] Avg episode reward: [(0, '-1.860'), (1, '22.160')] -[2023-10-10 21:37:01,707][98559] Updated weights for policy 0, policy_version 22340 (0.0008) -[2023-10-10 21:37:02,072][98559] Updated weights for policy 0, policy_version 22350 (0.0009) -[2023-10-10 21:37:02,438][98559] Updated weights for policy 0, policy_version 22360 (0.0009) -[2023-10-10 21:37:03,046][98560] Updated weights for policy 1, policy_version 22312 (0.0007) -[2023-10-10 21:37:03,410][98560] Updated weights for policy 1, policy_version 22322 (0.0007) -[2023-10-10 21:37:03,769][98560] Updated weights for policy 1, policy_version 22332 (0.0007) -[2023-10-10 21:37:05,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 45776896. Throughput: 0: 1715.5, 1: 1680.9. Samples: 11454654. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-10 21:37:05,557][97672] Avg episode reward: [(0, '-1.860'), (1, '22.180')] -[2023-10-10 21:37:06,557][98559] Updated weights for policy 0, policy_version 22370 (0.0008) -[2023-10-10 21:37:06,931][98559] Updated weights for policy 0, policy_version 22380 (0.0010) -[2023-10-10 21:37:07,308][98559] Updated weights for policy 0, policy_version 22390 (0.0008) -[2023-10-10 21:37:07,664][98559] Updated weights for policy 0, policy_version 22400 (0.0007) -[2023-10-10 21:37:08,017][98560] Updated weights for policy 1, policy_version 22342 (0.0009) -[2023-10-10 21:37:08,380][98560] Updated weights for policy 1, policy_version 22352 (0.0010) -[2023-10-10 21:37:08,753][98560] Updated weights for policy 1, policy_version 22362 (0.0010) -[2023-10-10 21:37:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 45842432. Throughput: 0: 1689.4, 1: 1710.8. Samples: 11465266. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-10 21:37:10,556][97672] Avg episode reward: [(0, '-1.860'), (1, '22.260')] -[2023-10-10 21:37:10,557][98439] Saving new best policy, reward=22.260! -[2023-10-10 21:37:11,490][98559] Updated weights for policy 0, policy_version 22410 (0.0007) -[2023-10-10 21:37:11,860][98559] Updated weights for policy 0, policy_version 22420 (0.0008) -[2023-10-10 21:37:12,239][98559] Updated weights for policy 0, policy_version 22430 (0.0009) -[2023-10-10 21:37:12,663][98560] Updated weights for policy 1, policy_version 22372 (0.0010) -[2023-10-10 21:37:13,038][98560] Updated weights for policy 1, policy_version 22382 (0.0007) -[2023-10-10 21:37:13,404][98560] Updated weights for policy 1, policy_version 22392 (0.0008) -[2023-10-10 21:37:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 45907968. Throughput: 0: 1718.9, 1: 1685.7. Samples: 11485220. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 21:37:15,557][97672] Avg episode reward: [(0, '-1.860'), (1, '22.320')] -[2023-10-10 21:37:15,559][98439] Saving new best policy, reward=22.320! -[2023-10-10 21:37:16,216][98559] Updated weights for policy 0, policy_version 22440 (0.0007) -[2023-10-10 21:37:16,586][98559] Updated weights for policy 0, policy_version 22450 (0.0007) -[2023-10-10 21:37:16,946][98559] Updated weights for policy 0, policy_version 22460 (0.0009) -[2023-10-10 21:37:17,475][98560] Updated weights for policy 1, policy_version 22402 (0.0008) -[2023-10-10 21:37:17,904][98560] Updated weights for policy 1, policy_version 22412 (0.0008) -[2023-10-10 21:37:18,268][98560] Updated weights for policy 1, policy_version 22422 (0.0009) -[2023-10-10 21:37:18,636][98560] Updated weights for policy 1, policy_version 22432 (0.0008) -[2023-10-10 21:37:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 45973504. Throughput: 0: 1719.7, 1: 1693.2. Samples: 11506256. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 21:37:20,556][97672] Avg episode reward: [(0, '-1.880'), (1, '22.140')] -[2023-10-10 21:37:20,928][98559] Updated weights for policy 0, policy_version 22470 (0.0010) -[2023-10-10 21:37:21,299][98559] Updated weights for policy 0, policy_version 22480 (0.0009) -[2023-10-10 21:37:21,674][98559] Updated weights for policy 0, policy_version 22490 (0.0009) -[2023-10-10 21:37:22,513][98560] Updated weights for policy 1, policy_version 22442 (0.0007) -[2023-10-10 21:37:22,880][98560] Updated weights for policy 1, policy_version 22452 (0.0008) -[2023-10-10 21:37:23,256][98560] Updated weights for policy 1, policy_version 22462 (0.0008) -[2023-10-10 21:37:25,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 46039040. Throughput: 0: 1711.5, 1: 1697.0. Samples: 11516272. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 21:37:25,557][97672] Avg episode reward: [(0, '-1.880'), (1, '22.160')] -[2023-10-10 21:37:25,727][98559] Updated weights for policy 0, policy_version 22500 (0.0010) -[2023-10-10 21:37:26,097][98559] Updated weights for policy 0, policy_version 22510 (0.0009) -[2023-10-10 21:37:26,465][98559] Updated weights for policy 0, policy_version 22520 (0.0009) -[2023-10-10 21:37:27,273][98560] Updated weights for policy 1, policy_version 22472 (0.0008) -[2023-10-10 21:37:27,639][98560] Updated weights for policy 1, policy_version 22482 (0.0007) -[2023-10-10 21:37:28,013][98560] Updated weights for policy 1, policy_version 22492 (0.0009) -[2023-10-10 21:37:30,314][98559] Updated weights for policy 0, policy_version 22530 (0.0011) -[2023-10-10 21:37:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 46104576. Throughput: 0: 1719.8, 1: 1680.2. Samples: 11536538. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 21:37:30,557][97672] Avg episode reward: [(0, '-1.760'), (1, '22.100')] -[2023-10-10 21:37:30,682][98559] Updated weights for policy 0, policy_version 22540 (0.0008) -[2023-10-10 21:37:31,053][98559] Updated weights for policy 0, policy_version 22550 (0.0009) -[2023-10-10 21:37:31,420][98559] Updated weights for policy 0, policy_version 22560 (0.0007) -[2023-10-10 21:37:32,053][98560] Updated weights for policy 1, policy_version 22502 (0.0009) -[2023-10-10 21:37:32,410][98560] Updated weights for policy 1, policy_version 22512 (0.0010) -[2023-10-10 21:37:32,779][98560] Updated weights for policy 1, policy_version 22522 (0.0008) -[2023-10-10 21:37:35,473][98559] Updated weights for policy 0, policy_version 22570 (0.0007) -[2023-10-10 21:37:35,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 46170112. Throughput: 0: 1712.3, 1: 1707.7. Samples: 11557318. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:37:35,556][97672] Avg episode reward: [(0, '-1.760'), (1, '22.160')] -[2023-10-10 21:37:35,841][98559] Updated weights for policy 0, policy_version 22580 (0.0010) -[2023-10-10 21:37:36,223][98559] Updated weights for policy 0, policy_version 22590 (0.0007) -[2023-10-10 21:37:36,786][98560] Updated weights for policy 1, policy_version 22532 (0.0010) -[2023-10-10 21:37:37,163][98560] Updated weights for policy 1, policy_version 22542 (0.0008) -[2023-10-10 21:37:37,527][98560] Updated weights for policy 1, policy_version 22552 (0.0009) -[2023-10-10 21:37:40,304][98559] Updated weights for policy 0, policy_version 22600 (0.0007) -[2023-10-10 21:37:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 46235648. Throughput: 0: 1716.2, 1: 1684.7. Samples: 11567082. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:37:40,556][97672] Avg episode reward: [(0, '-1.760'), (1, '22.140')] -[2023-10-10 21:37:40,675][98559] Updated weights for policy 0, policy_version 22610 (0.0008) -[2023-10-10 21:37:41,040][98559] Updated weights for policy 0, policy_version 22620 (0.0010) -[2023-10-10 21:37:41,646][98560] Updated weights for policy 1, policy_version 22562 (0.0008) -[2023-10-10 21:37:42,021][98560] Updated weights for policy 1, policy_version 22572 (0.0008) -[2023-10-10 21:37:42,383][98560] Updated weights for policy 1, policy_version 22582 (0.0010) -[2023-10-10 21:37:42,753][98560] Updated weights for policy 1, policy_version 22592 (0.0008) -[2023-10-10 21:37:44,976][98559] Updated weights for policy 0, policy_version 22630 (0.0009) -[2023-10-10 21:37:45,343][98559] Updated weights for policy 0, policy_version 22640 (0.0009) -[2023-10-10 21:37:45,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 46301184. Throughput: 0: 1712.3, 1: 1696.7. Samples: 11587832. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:37:45,556][97672] Avg episode reward: [(0, '-1.760'), (1, '22.120')] -[2023-10-10 21:37:45,717][98559] Updated weights for policy 0, policy_version 22650 (0.0010) -[2023-10-10 21:37:46,729][98560] Updated weights for policy 1, policy_version 22602 (0.0009) -[2023-10-10 21:37:47,095][98560] Updated weights for policy 1, policy_version 22612 (0.0009) -[2023-10-10 21:37:47,458][98560] Updated weights for policy 1, policy_version 22622 (0.0009) -[2023-10-10 21:37:49,701][98559] Updated weights for policy 0, policy_version 22660 (0.0011) -[2023-10-10 21:37:50,076][98559] Updated weights for policy 0, policy_version 22670 (0.0010) -[2023-10-10 21:37:50,438][98559] Updated weights for policy 0, policy_version 22680 (0.0008) -[2023-10-10 21:37:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 46366720. Throughput: 0: 1698.1, 1: 1708.8. Samples: 11607964. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:37:50,557][97672] Avg episode reward: [(0, '-1.760'), (1, '22.200')] -[2023-10-10 21:37:51,561][98560] Updated weights for policy 1, policy_version 22632 (0.0008) -[2023-10-10 21:37:51,925][98560] Updated weights for policy 1, policy_version 22642 (0.0009) -[2023-10-10 21:37:52,293][98560] Updated weights for policy 1, policy_version 22652 (0.0008) -[2023-10-10 21:37:54,534][98559] Updated weights for policy 0, policy_version 22690 (0.0008) -[2023-10-10 21:37:54,896][98559] Updated weights for policy 0, policy_version 22700 (0.0010) -[2023-10-10 21:37:55,262][98559] Updated weights for policy 0, policy_version 22710 (0.0007) -[2023-10-10 21:37:55,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 46432256. Throughput: 0: 1716.4, 1: 1675.9. Samples: 11617920. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:37:55,557][97672] Avg episode reward: [(0, '-1.680'), (1, '22.160')] -[2023-10-10 21:37:55,630][98385] Saving new best policy, reward=-1.680! -[2023-10-10 21:37:55,635][98559] Updated weights for policy 0, policy_version 22720 (0.0008) -[2023-10-10 21:37:56,178][98560] Updated weights for policy 1, policy_version 22662 (0.0009) -[2023-10-10 21:37:56,544][98560] Updated weights for policy 1, policy_version 22672 (0.0007) -[2023-10-10 21:37:56,910][98560] Updated weights for policy 1, policy_version 22682 (0.0007) -[2023-10-10 21:37:59,651][98559] Updated weights for policy 0, policy_version 22730 (0.0008) -[2023-10-10 21:38:00,024][98559] Updated weights for policy 0, policy_version 22740 (0.0010) -[2023-10-10 21:38:00,393][98559] Updated weights for policy 0, policy_version 22750 (0.0008) -[2023-10-10 21:38:00,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 46530560. Throughput: 0: 1711.5, 1: 1708.6. Samples: 11639126. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:38:00,557][97672] Avg episode reward: [(0, '-1.680'), (1, '22.000')] -[2023-10-10 21:38:00,839][98560] Updated weights for policy 1, policy_version 22692 (0.0008) -[2023-10-10 21:38:01,208][98560] Updated weights for policy 1, policy_version 22702 (0.0008) -[2023-10-10 21:38:01,567][98560] Updated weights for policy 1, policy_version 22712 (0.0007) -[2023-10-10 21:38:04,449][98559] Updated weights for policy 0, policy_version 22760 (0.0009) -[2023-10-10 21:38:04,822][98559] Updated weights for policy 0, policy_version 22770 (0.0009) -[2023-10-10 21:38:05,185][98559] Updated weights for policy 0, policy_version 22780 (0.0010) -[2023-10-10 21:38:05,556][97672] Fps is (10 sec: 16384.4, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 46596096. Throughput: 0: 1678.0, 1: 1721.8. Samples: 11659250. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:38:05,556][97672] Avg episode reward: [(0, '-1.680'), (1, '21.920')] -[2023-10-10 21:38:05,570][98560] Updated weights for policy 1, policy_version 22722 (0.0007) -[2023-10-10 21:38:05,983][98560] Updated weights for policy 1, policy_version 22732 (0.0010) -[2023-10-10 21:38:06,346][98560] Updated weights for policy 1, policy_version 22742 (0.0007) -[2023-10-10 21:38:06,722][98560] Updated weights for policy 1, policy_version 22752 (0.0009) -[2023-10-10 21:38:09,085][98559] Updated weights for policy 0, policy_version 22790 (0.0008) -[2023-10-10 21:38:09,451][98559] Updated weights for policy 0, policy_version 22800 (0.0007) -[2023-10-10 21:38:09,823][98559] Updated weights for policy 0, policy_version 22810 (0.0007) -[2023-10-10 21:38:10,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 46661632. Throughput: 0: 1711.5, 1: 1697.2. Samples: 11669664. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-10 21:38:10,556][97672] Avg episode reward: [(0, '-1.680'), (1, '21.940')] -[2023-10-10 21:38:10,788][98560] Updated weights for policy 1, policy_version 22762 (0.0008) -[2023-10-10 21:38:11,162][98560] Updated weights for policy 1, policy_version 22772 (0.0008) -[2023-10-10 21:38:11,534][98560] Updated weights for policy 1, policy_version 22782 (0.0010) -[2023-10-10 21:38:13,536][98559] Updated weights for policy 0, policy_version 22820 (0.0009) -[2023-10-10 21:38:13,915][98559] Updated weights for policy 0, policy_version 22830 (0.0011) -[2023-10-10 21:38:14,271][98559] Updated weights for policy 0, policy_version 22840 (0.0010) -[2023-10-10 21:38:15,450][98560] Updated weights for policy 1, policy_version 22792 (0.0007) -[2023-10-10 21:38:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 46727168. Throughput: 0: 1689.0, 1: 1711.1. Samples: 11689542. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-10 21:38:15,556][97672] Avg episode reward: [(0, '-1.680'), (1, '21.900')] -[2023-10-10 21:38:15,814][98560] Updated weights for policy 1, policy_version 22802 (0.0008) -[2023-10-10 21:38:16,196][98560] Updated weights for policy 1, policy_version 22812 (0.0008) -[2023-10-10 21:38:18,317][98559] Updated weights for policy 0, policy_version 22850 (0.0010) -[2023-10-10 21:38:18,692][98559] Updated weights for policy 0, policy_version 22860 (0.0011) -[2023-10-10 21:38:19,063][98559] Updated weights for policy 0, policy_version 22870 (0.0010) -[2023-10-10 21:38:19,423][98559] Updated weights for policy 0, policy_version 22880 (0.0011) -[2023-10-10 21:38:20,206][98560] Updated weights for policy 1, policy_version 22822 (0.0010) -[2023-10-10 21:38:20,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 46792704. Throughput: 0: 1691.1, 1: 1709.8. Samples: 11710358. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-10 21:38:20,557][97672] Avg episode reward: [(0, '-1.680'), (1, '22.020')] -[2023-10-10 21:38:20,577][98560] Updated weights for policy 1, policy_version 22832 (0.0010) -[2023-10-10 21:38:20,955][98560] Updated weights for policy 1, policy_version 22842 (0.0009) -[2023-10-10 21:38:23,526][98559] Updated weights for policy 0, policy_version 22890 (0.0007) -[2023-10-10 21:38:23,897][98559] Updated weights for policy 0, policy_version 22900 (0.0007) -[2023-10-10 21:38:24,255][98559] Updated weights for policy 0, policy_version 22910 (0.0007) -[2023-10-10 21:38:24,854][98560] Updated weights for policy 1, policy_version 22852 (0.0009) -[2023-10-10 21:38:25,228][98560] Updated weights for policy 1, policy_version 22862 (0.0010) -[2023-10-10 21:38:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 46858240. Throughput: 0: 1708.8, 1: 1703.2. Samples: 11720624. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-10 21:38:25,557][97672] Avg episode reward: [(0, '-1.660'), (1, '22.020')] -[2023-10-10 21:38:25,558][98385] Saving new best policy, reward=-1.660! -[2023-10-10 21:38:25,598][98560] Updated weights for policy 1, policy_version 22872 (0.0010) -[2023-10-10 21:38:28,072][98559] Updated weights for policy 0, policy_version 22920 (0.0009) -[2023-10-10 21:38:28,442][98559] Updated weights for policy 0, policy_version 22930 (0.0009) -[2023-10-10 21:38:28,818][98559] Updated weights for policy 0, policy_version 22940 (0.0007) -[2023-10-10 21:38:29,529][98560] Updated weights for policy 1, policy_version 22882 (0.0008) -[2023-10-10 21:38:29,903][98560] Updated weights for policy 1, policy_version 22892 (0.0009) -[2023-10-10 21:38:30,272][98560] Updated weights for policy 1, policy_version 22902 (0.0009) -[2023-10-10 21:38:30,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 46923776. Throughput: 0: 1692.0, 1: 1712.9. Samples: 11741054. Policy #0 lag: (min: 13.0, avg: 13.7, max: 31.0) -[2023-10-10 21:38:30,556][97672] Avg episode reward: [(0, '-1.740'), (1, '22.040')] -[2023-10-10 21:38:30,647][98560] Updated weights for policy 1, policy_version 22912 (0.0010) -[2023-10-10 21:38:32,833][98559] Updated weights for policy 0, policy_version 22950 (0.0008) -[2023-10-10 21:38:33,200][98559] Updated weights for policy 0, policy_version 22960 (0.0007) -[2023-10-10 21:38:33,557][98559] Updated weights for policy 0, policy_version 22970 (0.0007) -[2023-10-10 21:38:34,588][98560] Updated weights for policy 1, policy_version 22922 (0.0009) -[2023-10-10 21:38:34,951][98560] Updated weights for policy 1, policy_version 22932 (0.0009) -[2023-10-10 21:38:35,327][98560] Updated weights for policy 1, policy_version 22942 (0.0009) -[2023-10-10 21:38:35,556][97672] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 47022080. Throughput: 0: 1715.8, 1: 1701.6. Samples: 11761750. Policy #0 lag: (min: 13.0, avg: 13.7, max: 31.0) -[2023-10-10 21:38:35,557][97672] Avg episode reward: [(0, '-1.740'), (1, '22.120')] -[2023-10-10 21:38:35,570][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000022944_23494656.pth... -[2023-10-10 21:38:35,570][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000022976_23527424.pth... -[2023-10-10 21:38:35,606][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000021344_21856256.pth -[2023-10-10 21:38:35,607][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000021376_21889024.pth -[2023-10-10 21:38:37,596][98559] Updated weights for policy 0, policy_version 22980 (0.0008) -[2023-10-10 21:38:37,961][98559] Updated weights for policy 0, policy_version 22990 (0.0007) -[2023-10-10 21:38:38,329][98559] Updated weights for policy 0, policy_version 23000 (0.0008) -[2023-10-10 21:38:39,280][98560] Updated weights for policy 1, policy_version 22952 (0.0007) -[2023-10-10 21:38:39,645][98560] Updated weights for policy 1, policy_version 22962 (0.0009) -[2023-10-10 21:38:40,011][98560] Updated weights for policy 1, policy_version 22972 (0.0010) -[2023-10-10 21:38:40,556][97672] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 47087616. Throughput: 0: 1707.3, 1: 1717.3. Samples: 11772028. Policy #0 lag: (min: 13.0, avg: 13.7, max: 31.0) -[2023-10-10 21:38:40,556][97672] Avg episode reward: [(0, '-1.740'), (1, '22.120')] -[2023-10-10 21:38:42,219][98559] Updated weights for policy 0, policy_version 23010 (0.0010) -[2023-10-10 21:38:42,594][98559] Updated weights for policy 0, policy_version 23020 (0.0010) -[2023-10-10 21:38:42,957][98559] Updated weights for policy 0, policy_version 23030 (0.0010) -[2023-10-10 21:38:43,335][98559] Updated weights for policy 0, policy_version 23040 (0.0009) -[2023-10-10 21:38:44,179][98560] Updated weights for policy 1, policy_version 22982 (0.0010) -[2023-10-10 21:38:44,547][98560] Updated weights for policy 1, policy_version 22992 (0.0011) -[2023-10-10 21:38:44,922][98560] Updated weights for policy 1, policy_version 23002 (0.0010) -[2023-10-10 21:38:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 47153152. Throughput: 0: 1706.3, 1: 1711.1. Samples: 11792908. Policy #0 lag: (min: 13.0, avg: 13.7, max: 31.0) -[2023-10-10 21:38:45,557][97672] Avg episode reward: [(0, '-1.740'), (1, '22.140')] -[2023-10-10 21:38:47,311][98559] Updated weights for policy 0, policy_version 23050 (0.0008) -[2023-10-10 21:38:47,686][98559] Updated weights for policy 0, policy_version 23060 (0.0008) -[2023-10-10 21:38:48,053][98559] Updated weights for policy 0, policy_version 23070 (0.0009) -[2023-10-10 21:38:49,034][98560] Updated weights for policy 1, policy_version 23012 (0.0009) -[2023-10-10 21:38:49,397][98560] Updated weights for policy 1, policy_version 23022 (0.0008) -[2023-10-10 21:38:49,764][98560] Updated weights for policy 1, policy_version 23032 (0.0011) -[2023-10-10 21:38:50,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 47218688. Throughput: 0: 1731.9, 1: 1684.0. Samples: 11812962. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:38:50,557][97672] Avg episode reward: [(0, '-1.720'), (1, '22.240')] -[2023-10-10 21:38:52,138][98559] Updated weights for policy 0, policy_version 23080 (0.0010) -[2023-10-10 21:38:52,512][98559] Updated weights for policy 0, policy_version 23090 (0.0008) -[2023-10-10 21:38:52,882][98559] Updated weights for policy 0, policy_version 23100 (0.0007) -[2023-10-10 21:38:53,794][98560] Updated weights for policy 1, policy_version 23042 (0.0010) -[2023-10-10 21:38:54,201][98560] Updated weights for policy 1, policy_version 23052 (0.0008) -[2023-10-10 21:38:54,571][98560] Updated weights for policy 1, policy_version 23062 (0.0010) -[2023-10-10 21:38:54,934][98560] Updated weights for policy 1, policy_version 23072 (0.0009) -[2023-10-10 21:38:55,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 47284224. Throughput: 0: 1694.7, 1: 1710.2. Samples: 11822886. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:38:55,557][97672] Avg episode reward: [(0, '-1.720'), (1, '22.260')] -[2023-10-10 21:38:56,719][98559] Updated weights for policy 0, policy_version 23110 (0.0008) -[2023-10-10 21:38:57,093][98559] Updated weights for policy 0, policy_version 23120 (0.0010) -[2023-10-10 21:38:57,453][98559] Updated weights for policy 0, policy_version 23130 (0.0011) -[2023-10-10 21:38:58,869][98560] Updated weights for policy 1, policy_version 23082 (0.0009) -[2023-10-10 21:38:59,241][98560] Updated weights for policy 1, policy_version 23092 (0.0010) -[2023-10-10 21:38:59,607][98560] Updated weights for policy 1, policy_version 23102 (0.0007) -[2023-10-10 21:39:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 47349760. Throughput: 0: 1725.8, 1: 1705.9. Samples: 11843966. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:39:00,557][97672] Avg episode reward: [(0, '-1.800'), (1, '22.360')] -[2023-10-10 21:39:00,558][98439] Saving new best policy, reward=22.360! -[2023-10-10 21:39:01,464][98559] Updated weights for policy 0, policy_version 23140 (0.0011) -[2023-10-10 21:39:01,843][98559] Updated weights for policy 0, policy_version 23150 (0.0012) -[2023-10-10 21:39:02,206][98559] Updated weights for policy 0, policy_version 23160 (0.0011) -[2023-10-10 21:39:03,619][98560] Updated weights for policy 1, policy_version 23112 (0.0010) -[2023-10-10 21:39:03,996][98560] Updated weights for policy 1, policy_version 23122 (0.0008) -[2023-10-10 21:39:04,361][98560] Updated weights for policy 1, policy_version 23132 (0.0007) -[2023-10-10 21:39:05,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 47415296. Throughput: 0: 1731.3, 1: 1680.4. Samples: 11863884. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:39:05,557][97672] Avg episode reward: [(0, '-1.780'), (1, '22.400')] -[2023-10-10 21:39:05,569][98439] Saving new best policy, reward=22.400! -[2023-10-10 21:39:06,141][98559] Updated weights for policy 0, policy_version 23170 (0.0008) -[2023-10-10 21:39:06,507][98559] Updated weights for policy 0, policy_version 23180 (0.0011) -[2023-10-10 21:39:06,867][98559] Updated weights for policy 0, policy_version 23190 (0.0010) -[2023-10-10 21:39:07,241][98559] Updated weights for policy 0, policy_version 23200 (0.0011) -[2023-10-10 21:39:08,257][98560] Updated weights for policy 1, policy_version 23142 (0.0009) -[2023-10-10 21:39:08,612][98560] Updated weights for policy 1, policy_version 23152 (0.0010) -[2023-10-10 21:39:08,983][98560] Updated weights for policy 1, policy_version 23162 (0.0009) -[2023-10-10 21:39:10,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 47480832. Throughput: 0: 1704.5, 1: 1715.1. Samples: 11874506. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-10 21:39:10,557][97672] Avg episode reward: [(0, '-1.740'), (1, '22.360')] -[2023-10-10 21:39:11,273][98559] Updated weights for policy 0, policy_version 23210 (0.0011) -[2023-10-10 21:39:11,642][98559] Updated weights for policy 0, policy_version 23220 (0.0011) -[2023-10-10 21:39:12,012][98559] Updated weights for policy 0, policy_version 23230 (0.0011) -[2023-10-10 21:39:12,915][98560] Updated weights for policy 1, policy_version 23172 (0.0010) -[2023-10-10 21:39:13,288][98560] Updated weights for policy 1, policy_version 23182 (0.0007) -[2023-10-10 21:39:13,649][98560] Updated weights for policy 1, policy_version 23192 (0.0009) -[2023-10-10 21:39:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 47546368. Throughput: 0: 1721.9, 1: 1688.3. Samples: 11894510. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-10 21:39:15,557][97672] Avg episode reward: [(0, '-1.740'), (1, '22.340')] -[2023-10-10 21:39:16,098][98559] Updated weights for policy 0, policy_version 23240 (0.0007) -[2023-10-10 21:39:16,474][98559] Updated weights for policy 0, policy_version 23250 (0.0009) -[2023-10-10 21:39:16,850][98559] Updated weights for policy 0, policy_version 23260 (0.0008) -[2023-10-10 21:39:17,657][98560] Updated weights for policy 1, policy_version 23202 (0.0009) -[2023-10-10 21:39:18,029][98560] Updated weights for policy 1, policy_version 23212 (0.0009) -[2023-10-10 21:39:18,397][98560] Updated weights for policy 1, policy_version 23222 (0.0011) -[2023-10-10 21:39:18,768][98560] Updated weights for policy 1, policy_version 23232 (0.0010) -[2023-10-10 21:39:20,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 47611904. Throughput: 0: 1715.7, 1: 1689.2. Samples: 11914968. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-10 21:39:20,557][97672] Avg episode reward: [(0, '-1.740'), (1, '22.340')] -[2023-10-10 21:39:20,852][98559] Updated weights for policy 0, policy_version 23270 (0.0008) -[2023-10-10 21:39:21,208][98559] Updated weights for policy 0, policy_version 23280 (0.0009) -[2023-10-10 21:39:21,580][98559] Updated weights for policy 0, policy_version 23290 (0.0009) -[2023-10-10 21:39:22,965][98560] Updated weights for policy 1, policy_version 23242 (0.0007) -[2023-10-10 21:39:23,343][98560] Updated weights for policy 1, policy_version 23252 (0.0007) -[2023-10-10 21:39:23,704][98560] Updated weights for policy 1, policy_version 23262 (0.0007) -[2023-10-10 21:39:25,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 47677440. Throughput: 0: 1705.5, 1: 1702.7. Samples: 11925398. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-10 21:39:25,557][97672] Avg episode reward: [(0, '-1.660'), (1, '22.240')] -[2023-10-10 21:39:25,689][98559] Updated weights for policy 0, policy_version 23300 (0.0011) -[2023-10-10 21:39:26,053][98559] Updated weights for policy 0, policy_version 23310 (0.0011) -[2023-10-10 21:39:26,423][98559] Updated weights for policy 0, policy_version 23320 (0.0011) -[2023-10-10 21:39:27,636][98560] Updated weights for policy 1, policy_version 23272 (0.0009) -[2023-10-10 21:39:28,003][98560] Updated weights for policy 1, policy_version 23282 (0.0009) -[2023-10-10 21:39:28,379][98560] Updated weights for policy 1, policy_version 23292 (0.0010) -[2023-10-10 21:39:30,480][98559] Updated weights for policy 0, policy_version 23330 (0.0009) -[2023-10-10 21:39:30,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 47742976. Throughput: 0: 1708.2, 1: 1679.6. Samples: 11945358. Policy #0 lag: (min: 6.0, avg: 10.6, max: 38.0) -[2023-10-10 21:39:30,557][97672] Avg episode reward: [(0, '-1.660'), (1, '22.240')] -[2023-10-10 21:39:30,853][98559] Updated weights for policy 0, policy_version 23340 (0.0008) -[2023-10-10 21:39:31,230][98559] Updated weights for policy 0, policy_version 23350 (0.0009) -[2023-10-10 21:39:31,607][98559] Updated weights for policy 0, policy_version 23360 (0.0009) -[2023-10-10 21:39:32,419][98560] Updated weights for policy 1, policy_version 23302 (0.0008) -[2023-10-10 21:39:32,793][98560] Updated weights for policy 1, policy_version 23312 (0.0007) -[2023-10-10 21:39:33,160][98560] Updated weights for policy 1, policy_version 23322 (0.0007) -[2023-10-10 21:39:35,491][98559] Updated weights for policy 0, policy_version 23370 (0.0009) -[2023-10-10 21:39:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 47808512. Throughput: 0: 1703.0, 1: 1703.2. Samples: 11966244. Policy #0 lag: (min: 6.0, avg: 10.6, max: 38.0) -[2023-10-10 21:39:35,557][97672] Avg episode reward: [(0, '-1.660'), (1, '22.300')] -[2023-10-10 21:39:35,867][98559] Updated weights for policy 0, policy_version 23380 (0.0010) -[2023-10-10 21:39:36,227][98559] Updated weights for policy 0, policy_version 23390 (0.0008) -[2023-10-10 21:39:37,137][98560] Updated weights for policy 1, policy_version 23332 (0.0009) -[2023-10-10 21:39:37,505][98560] Updated weights for policy 1, policy_version 23342 (0.0009) -[2023-10-10 21:39:37,881][98560] Updated weights for policy 1, policy_version 23352 (0.0009) -[2023-10-10 21:39:40,219][98559] Updated weights for policy 0, policy_version 23400 (0.0007) -[2023-10-10 21:39:40,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 47874048. Throughput: 0: 1713.3, 1: 1699.5. Samples: 11976464. Policy #0 lag: (min: 6.0, avg: 10.6, max: 38.0) -[2023-10-10 21:39:40,557][97672] Avg episode reward: [(0, '-1.660'), (1, '22.300')] -[2023-10-10 21:39:40,577][98559] Updated weights for policy 0, policy_version 23410 (0.0008) -[2023-10-10 21:39:40,947][98559] Updated weights for policy 0, policy_version 23420 (0.0008) -[2023-10-10 21:39:41,981][98560] Updated weights for policy 1, policy_version 23362 (0.0009) -[2023-10-10 21:39:42,350][98560] Updated weights for policy 1, policy_version 23372 (0.0007) -[2023-10-10 21:39:42,722][98560] Updated weights for policy 1, policy_version 23382 (0.0008) -[2023-10-10 21:39:43,087][98560] Updated weights for policy 1, policy_version 23392 (0.0009) -[2023-10-10 21:39:44,875][98559] Updated weights for policy 0, policy_version 23430 (0.0008) -[2023-10-10 21:39:45,245][98559] Updated weights for policy 0, policy_version 23440 (0.0009) -[2023-10-10 21:39:45,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 47939584. Throughput: 0: 1707.2, 1: 1691.4. Samples: 11996904. Policy #0 lag: (min: 6.0, avg: 10.6, max: 38.0) -[2023-10-10 21:39:45,557][97672] Avg episode reward: [(0, '-1.660'), (1, '22.300')] -[2023-10-10 21:39:45,619][98559] Updated weights for policy 0, policy_version 23450 (0.0009) -[2023-10-10 21:39:46,913][98560] Updated weights for policy 1, policy_version 23402 (0.0007) -[2023-10-10 21:39:47,282][98560] Updated weights for policy 1, policy_version 23412 (0.0009) -[2023-10-10 21:39:47,652][98560] Updated weights for policy 1, policy_version 23422 (0.0009) -[2023-10-10 21:39:49,708][98559] Updated weights for policy 0, policy_version 23460 (0.0009) -[2023-10-10 21:39:50,073][98559] Updated weights for policy 0, policy_version 23470 (0.0009) -[2023-10-10 21:39:50,439][98559] Updated weights for policy 0, policy_version 23480 (0.0007) -[2023-10-10 21:39:50,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 48005120. Throughput: 0: 1684.4, 1: 1718.8. Samples: 12017026. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 21:39:50,557][97672] Avg episode reward: [(0, '-1.660'), (1, '22.280')] -[2023-10-10 21:39:51,698][98560] Updated weights for policy 1, policy_version 23432 (0.0009) -[2023-10-10 21:39:52,062][98560] Updated weights for policy 1, policy_version 23442 (0.0007) -[2023-10-10 21:39:52,434][98560] Updated weights for policy 1, policy_version 23452 (0.0007) -[2023-10-10 21:39:54,381][98559] Updated weights for policy 0, policy_version 23490 (0.0008) -[2023-10-10 21:39:54,756][98559] Updated weights for policy 0, policy_version 23500 (0.0009) -[2023-10-10 21:39:55,121][98559] Updated weights for policy 0, policy_version 23510 (0.0008) -[2023-10-10 21:39:55,484][98559] Updated weights for policy 0, policy_version 23520 (0.0008) -[2023-10-10 21:39:55,556][97672] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 48103424. Throughput: 0: 1707.5, 1: 1684.3. Samples: 12027138. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 21:39:55,557][97672] Avg episode reward: [(0, '-1.660'), (1, '22.260')] -[2023-10-10 21:39:56,327][98560] Updated weights for policy 1, policy_version 23462 (0.0011) -[2023-10-10 21:39:56,692][98560] Updated weights for policy 1, policy_version 23472 (0.0010) -[2023-10-10 21:39:57,055][98560] Updated weights for policy 1, policy_version 23482 (0.0009) -[2023-10-10 21:39:59,451][98559] Updated weights for policy 0, policy_version 23530 (0.0008) -[2023-10-10 21:39:59,825][98559] Updated weights for policy 0, policy_version 23540 (0.0009) -[2023-10-10 21:40:00,198][98559] Updated weights for policy 0, policy_version 23550 (0.0010) -[2023-10-10 21:40:00,556][97672] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 48168960. Throughput: 0: 1706.0, 1: 1707.3. Samples: 12048106. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 21:40:00,557][97672] Avg episode reward: [(0, '-1.660'), (1, '22.300')] -[2023-10-10 21:40:01,296][98560] Updated weights for policy 1, policy_version 23492 (0.0007) -[2023-10-10 21:40:01,664][98560] Updated weights for policy 1, policy_version 23502 (0.0008) -[2023-10-10 21:40:02,024][98560] Updated weights for policy 1, policy_version 23512 (0.0007) -[2023-10-10 21:40:03,998][98559] Updated weights for policy 0, policy_version 23560 (0.0010) -[2023-10-10 21:40:04,371][98559] Updated weights for policy 0, policy_version 23570 (0.0008) -[2023-10-10 21:40:04,743][98559] Updated weights for policy 0, policy_version 23580 (0.0010) -[2023-10-10 21:40:05,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 48234496. Throughput: 0: 1693.1, 1: 1718.9. Samples: 12068508. Policy #0 lag: (min: 26.0, avg: 34.0, max: 58.0) -[2023-10-10 21:40:05,556][97672] Avg episode reward: [(0, '-1.660'), (1, '22.320')] -[2023-10-10 21:40:05,854][98560] Updated weights for policy 1, policy_version 23522 (0.0008) -[2023-10-10 21:40:06,216][98560] Updated weights for policy 1, policy_version 23532 (0.0009) -[2023-10-10 21:40:06,587][98560] Updated weights for policy 1, policy_version 23542 (0.0007) -[2023-10-10 21:40:06,951][98560] Updated weights for policy 1, policy_version 23552 (0.0009) -[2023-10-10 21:40:08,621][98559] Updated weights for policy 0, policy_version 23590 (0.0008) -[2023-10-10 21:40:08,992][98559] Updated weights for policy 0, policy_version 23600 (0.0007) -[2023-10-10 21:40:09,360][98559] Updated weights for policy 0, policy_version 23610 (0.0010) -[2023-10-10 21:40:10,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 48300032. Throughput: 0: 1726.8, 1: 1692.9. Samples: 12079284. Policy #0 lag: (min: 26.0, avg: 34.0, max: 58.0) -[2023-10-10 21:40:10,556][97672] Avg episode reward: [(0, '-1.660'), (1, '22.300')] -[2023-10-10 21:40:11,088][98560] Updated weights for policy 1, policy_version 23562 (0.0009) -[2023-10-10 21:40:11,462][98560] Updated weights for policy 1, policy_version 23572 (0.0008) -[2023-10-10 21:40:11,836][98560] Updated weights for policy 1, policy_version 23582 (0.0009) -[2023-10-10 21:40:13,438][98559] Updated weights for policy 0, policy_version 23620 (0.0008) -[2023-10-10 21:40:13,813][98559] Updated weights for policy 0, policy_version 23630 (0.0010) -[2023-10-10 21:40:14,186][98559] Updated weights for policy 0, policy_version 23640 (0.0010) -[2023-10-10 21:40:15,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 48365568. Throughput: 0: 1701.3, 1: 1715.4. Samples: 12099110. Policy #0 lag: (min: 26.0, avg: 34.0, max: 58.0) -[2023-10-10 21:40:15,557][97672] Avg episode reward: [(0, '-1.660'), (1, '22.320')] -[2023-10-10 21:40:15,875][98560] Updated weights for policy 1, policy_version 23592 (0.0008) -[2023-10-10 21:40:16,251][98560] Updated weights for policy 1, policy_version 23602 (0.0009) -[2023-10-10 21:40:16,632][98560] Updated weights for policy 1, policy_version 23612 (0.0010) -[2023-10-10 21:40:18,149][98559] Updated weights for policy 0, policy_version 23650 (0.0010) -[2023-10-10 21:40:18,518][98559] Updated weights for policy 0, policy_version 23660 (0.0009) -[2023-10-10 21:40:18,886][98559] Updated weights for policy 0, policy_version 23670 (0.0008) -[2023-10-10 21:40:19,257][98559] Updated weights for policy 0, policy_version 23680 (0.0008) -[2023-10-10 21:40:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 48431104. Throughput: 0: 1705.1, 1: 1711.4. Samples: 12119984. Policy #0 lag: (min: 26.0, avg: 34.0, max: 58.0) -[2023-10-10 21:40:20,556][97672] Avg episode reward: [(0, '-1.660'), (1, '22.320')] -[2023-10-10 21:40:20,700][98560] Updated weights for policy 1, policy_version 23622 (0.0010) -[2023-10-10 21:40:21,066][98560] Updated weights for policy 1, policy_version 23632 (0.0009) -[2023-10-10 21:40:21,435][98560] Updated weights for policy 1, policy_version 23642 (0.0009) -[2023-10-10 21:40:23,205][98559] Updated weights for policy 0, policy_version 23690 (0.0009) -[2023-10-10 21:40:23,569][98559] Updated weights for policy 0, policy_version 23700 (0.0008) -[2023-10-10 21:40:23,943][98559] Updated weights for policy 0, policy_version 23710 (0.0008) -[2023-10-10 21:40:25,506][98560] Updated weights for policy 1, policy_version 23652 (0.0008) -[2023-10-10 21:40:25,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 48496640. Throughput: 0: 1715.1, 1: 1691.6. Samples: 12129762. Policy #0 lag: (min: 31.0, avg: 32.7, max: 59.0) -[2023-10-10 21:40:25,556][97672] Avg episode reward: [(0, '-1.660'), (1, '22.300')] -[2023-10-10 21:40:25,868][98560] Updated weights for policy 1, policy_version 23662 (0.0007) -[2023-10-10 21:40:26,231][98560] Updated weights for policy 1, policy_version 23672 (0.0007) -[2023-10-10 21:40:28,040][98559] Updated weights for policy 0, policy_version 23720 (0.0011) -[2023-10-10 21:40:28,419][98559] Updated weights for policy 0, policy_version 23730 (0.0009) -[2023-10-10 21:40:28,796][98559] Updated weights for policy 0, policy_version 23740 (0.0008) -[2023-10-10 21:40:30,354][98560] Updated weights for policy 1, policy_version 23682 (0.0007) -[2023-10-10 21:40:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 48562176. Throughput: 0: 1690.9, 1: 1704.4. Samples: 12149696. Policy #0 lag: (min: 31.0, avg: 32.7, max: 59.0) -[2023-10-10 21:40:30,557][97672] Avg episode reward: [(0, '-1.660'), (1, '22.280')] -[2023-10-10 21:40:30,729][98560] Updated weights for policy 1, policy_version 23692 (0.0008) -[2023-10-10 21:40:31,087][98560] Updated weights for policy 1, policy_version 23702 (0.0008) -[2023-10-10 21:40:31,454][98560] Updated weights for policy 1, policy_version 23712 (0.0009) -[2023-10-10 21:40:32,630][98559] Updated weights for policy 0, policy_version 23750 (0.0008) -[2023-10-10 21:40:33,007][98559] Updated weights for policy 0, policy_version 23760 (0.0011) -[2023-10-10 21:40:33,366][98559] Updated weights for policy 0, policy_version 23770 (0.0011) -[2023-10-10 21:40:35,475][98560] Updated weights for policy 1, policy_version 23722 (0.0011) -[2023-10-10 21:40:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 48627712. Throughput: 0: 1714.5, 1: 1704.5. Samples: 12170882. Policy #0 lag: (min: 31.0, avg: 32.7, max: 59.0) -[2023-10-10 21:40:35,556][97672] Avg episode reward: [(0, '-1.660'), (1, '22.240')] -[2023-10-10 21:40:35,563][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000023776_24346624.pth... -[2023-10-10 21:40:35,604][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000022176_22708224.pth -[2023-10-10 21:40:35,608][98385] Saving a milestone ./train_atari/atari_doubledunk_APPO/checkpoint_p0/milestones/checkpoint_000023776_24346624.pth -[2023-10-10 21:40:35,842][98560] Updated weights for policy 1, policy_version 23732 (0.0011) -[2023-10-10 21:40:36,222][98560] Updated weights for policy 1, policy_version 23742 (0.0010) -[2023-10-10 21:40:36,289][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000023744_24313856.pth... -[2023-10-10 21:40:36,331][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000022144_22675456.pth -[2023-10-10 21:40:36,337][98439] Saving a milestone ./train_atari/atari_doubledunk_APPO/checkpoint_p1/milestones/checkpoint_000023744_24313856.pth -[2023-10-10 21:40:37,535][98559] Updated weights for policy 0, policy_version 23780 (0.0009) -[2023-10-10 21:40:37,902][98559] Updated weights for policy 0, policy_version 23790 (0.0007) -[2023-10-10 21:40:38,266][98559] Updated weights for policy 0, policy_version 23800 (0.0007) -[2023-10-10 21:40:40,221][98560] Updated weights for policy 1, policy_version 23752 (0.0008) -[2023-10-10 21:40:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 48693248. Throughput: 0: 1702.2, 1: 1701.1. Samples: 12180288. Policy #0 lag: (min: 31.0, avg: 32.7, max: 59.0) -[2023-10-10 21:40:40,556][97672] Avg episode reward: [(0, '-1.660'), (1, '22.220')] -[2023-10-10 21:40:40,578][98560] Updated weights for policy 1, policy_version 23762 (0.0008) -[2023-10-10 21:40:40,946][98560] Updated weights for policy 1, policy_version 23772 (0.0009) -[2023-10-10 21:40:42,186][98559] Updated weights for policy 0, policy_version 23810 (0.0007) -[2023-10-10 21:40:42,559][98559] Updated weights for policy 0, policy_version 23820 (0.0007) -[2023-10-10 21:40:42,922][98559] Updated weights for policy 0, policy_version 23830 (0.0007) -[2023-10-10 21:40:43,288][98559] Updated weights for policy 0, policy_version 23840 (0.0008) -[2023-10-10 21:40:44,979][98560] Updated weights for policy 1, policy_version 23782 (0.0010) -[2023-10-10 21:40:45,341][98560] Updated weights for policy 1, policy_version 23792 (0.0010) -[2023-10-10 21:40:45,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 48758784. Throughput: 0: 1699.3, 1: 1696.7. Samples: 12200924. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:40:45,556][97672] Avg episode reward: [(0, '-1.660'), (1, '22.140')] -[2023-10-10 21:40:45,718][98560] Updated weights for policy 1, policy_version 23802 (0.0010) -[2023-10-10 21:40:47,265][98559] Updated weights for policy 0, policy_version 23850 (0.0010) -[2023-10-10 21:40:47,633][98559] Updated weights for policy 0, policy_version 23860 (0.0010) -[2023-10-10 21:40:48,004][98559] Updated weights for policy 0, policy_version 23870 (0.0008) -[2023-10-10 21:40:49,728][98560] Updated weights for policy 1, policy_version 23812 (0.0008) -[2023-10-10 21:40:50,099][98560] Updated weights for policy 1, policy_version 23822 (0.0008) -[2023-10-10 21:40:50,466][98560] Updated weights for policy 1, policy_version 23832 (0.0008) -[2023-10-10 21:40:50,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 48824320. Throughput: 0: 1721.9, 1: 1688.5. Samples: 12221974. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:40:50,557][97672] Avg episode reward: [(0, '-1.660'), (1, '22.200')] -[2023-10-10 21:40:51,822][98559] Updated weights for policy 0, policy_version 23880 (0.0007) -[2023-10-10 21:40:52,185][98559] Updated weights for policy 0, policy_version 23890 (0.0010) -[2023-10-10 21:40:52,561][98559] Updated weights for policy 0, policy_version 23900 (0.0009) -[2023-10-10 21:40:54,641][98560] Updated weights for policy 1, policy_version 23842 (0.0011) -[2023-10-10 21:40:55,006][98560] Updated weights for policy 1, policy_version 23852 (0.0008) -[2023-10-10 21:40:55,377][98560] Updated weights for policy 1, policy_version 23862 (0.0007) -[2023-10-10 21:40:55,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 48889856. Throughput: 0: 1689.8, 1: 1689.0. Samples: 12231328. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:40:55,557][97672] Avg episode reward: [(0, '-1.660'), (1, '22.140')] -[2023-10-10 21:40:55,743][98560] Updated weights for policy 1, policy_version 23872 (0.0007) -[2023-10-10 21:40:56,577][98559] Updated weights for policy 0, policy_version 23910 (0.0007) -[2023-10-10 21:40:56,946][98559] Updated weights for policy 0, policy_version 23920 (0.0007) -[2023-10-10 21:40:57,321][98559] Updated weights for policy 0, policy_version 23930 (0.0008) -[2023-10-10 21:40:59,747][98560] Updated weights for policy 1, policy_version 23882 (0.0009) -[2023-10-10 21:41:00,116][98560] Updated weights for policy 1, policy_version 23892 (0.0009) -[2023-10-10 21:41:00,484][98560] Updated weights for policy 1, policy_version 23902 (0.0008) -[2023-10-10 21:41:00,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 48955392. Throughput: 0: 1712.2, 1: 1692.2. Samples: 12252310. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:41:00,556][97672] Avg episode reward: [(0, '-1.640'), (1, '22.140')] -[2023-10-10 21:41:00,557][98385] Saving new best policy, reward=-1.640! -[2023-10-10 21:41:01,263][98559] Updated weights for policy 0, policy_version 23940 (0.0009) -[2023-10-10 21:41:01,626][98559] Updated weights for policy 0, policy_version 23950 (0.0009) -[2023-10-10 21:41:01,991][98559] Updated weights for policy 0, policy_version 23960 (0.0010) -[2023-10-10 21:41:04,402][98560] Updated weights for policy 1, policy_version 23912 (0.0008) -[2023-10-10 21:41:04,773][98560] Updated weights for policy 1, policy_version 23922 (0.0009) -[2023-10-10 21:41:05,136][98560] Updated weights for policy 1, policy_version 23932 (0.0008) -[2023-10-10 21:41:05,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 49053696. Throughput: 0: 1717.5, 1: 1680.9. Samples: 12272912. Policy #0 lag: (min: 30.0, avg: 33.1, max: 62.0) -[2023-10-10 21:41:05,557][97672] Avg episode reward: [(0, '-1.640'), (1, '22.120')] -[2023-10-10 21:41:06,005][98559] Updated weights for policy 0, policy_version 23970 (0.0011) -[2023-10-10 21:41:06,370][98559] Updated weights for policy 0, policy_version 23980 (0.0011) -[2023-10-10 21:41:06,740][98559] Updated weights for policy 0, policy_version 23990 (0.0008) -[2023-10-10 21:41:07,103][98559] Updated weights for policy 0, policy_version 24000 (0.0009) -[2023-10-10 21:41:09,153][98560] Updated weights for policy 1, policy_version 23942 (0.0007) -[2023-10-10 21:41:09,521][98560] Updated weights for policy 1, policy_version 23952 (0.0010) -[2023-10-10 21:41:09,883][98560] Updated weights for policy 1, policy_version 23962 (0.0009) -[2023-10-10 21:41:10,556][97672] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 49119232. Throughput: 0: 1700.7, 1: 1697.2. Samples: 12282670. Policy #0 lag: (min: 30.0, avg: 33.1, max: 62.0) -[2023-10-10 21:41:10,557][97672] Avg episode reward: [(0, '-1.640'), (1, '22.120')] -[2023-10-10 21:41:11,176][98559] Updated weights for policy 0, policy_version 24010 (0.0008) -[2023-10-10 21:41:11,541][98559] Updated weights for policy 0, policy_version 24020 (0.0008) -[2023-10-10 21:41:11,906][98559] Updated weights for policy 0, policy_version 24030 (0.0008) -[2023-10-10 21:41:14,036][98560] Updated weights for policy 1, policy_version 23972 (0.0010) -[2023-10-10 21:41:14,409][98560] Updated weights for policy 1, policy_version 23982 (0.0011) -[2023-10-10 21:41:14,776][98560] Updated weights for policy 1, policy_version 23992 (0.0007) -[2023-10-10 21:41:15,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 49184768. Throughput: 0: 1726.0, 1: 1695.8. Samples: 12303676. Policy #0 lag: (min: 30.0, avg: 33.1, max: 62.0) -[2023-10-10 21:41:15,557][97672] Avg episode reward: [(0, '-1.640'), (1, '22.020')] -[2023-10-10 21:41:15,990][98559] Updated weights for policy 0, policy_version 24040 (0.0007) -[2023-10-10 21:41:16,359][98559] Updated weights for policy 0, policy_version 24050 (0.0008) -[2023-10-10 21:41:16,720][98559] Updated weights for policy 0, policy_version 24060 (0.0011) -[2023-10-10 21:41:18,818][98560] Updated weights for policy 1, policy_version 24002 (0.0010) -[2023-10-10 21:41:19,184][98560] Updated weights for policy 1, policy_version 24012 (0.0008) -[2023-10-10 21:41:19,564][98560] Updated weights for policy 1, policy_version 24022 (0.0007) -[2023-10-10 21:41:19,932][98560] Updated weights for policy 1, policy_version 24032 (0.0010) -[2023-10-10 21:41:20,549][98559] Updated weights for policy 0, policy_version 24070 (0.0009) -[2023-10-10 21:41:20,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 49250304. Throughput: 0: 1726.8, 1: 1669.7. Samples: 12323726. Policy #0 lag: (min: 30.0, avg: 33.1, max: 62.0) -[2023-10-10 21:41:20,556][97672] Avg episode reward: [(0, '-1.640'), (1, '22.040')] -[2023-10-10 21:41:20,916][98559] Updated weights for policy 0, policy_version 24080 (0.0008) -[2023-10-10 21:41:21,287][98559] Updated weights for policy 0, policy_version 24090 (0.0008) -[2023-10-10 21:41:24,043][98560] Updated weights for policy 1, policy_version 24042 (0.0010) -[2023-10-10 21:41:24,415][98560] Updated weights for policy 1, policy_version 24052 (0.0008) -[2023-10-10 21:41:24,783][98560] Updated weights for policy 1, policy_version 24062 (0.0010) -[2023-10-10 21:41:25,216][98559] Updated weights for policy 0, policy_version 24100 (0.0009) -[2023-10-10 21:41:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 49315840. Throughput: 0: 1720.3, 1: 1697.1. Samples: 12334070. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-10 21:41:25,556][97672] Avg episode reward: [(0, '-1.640'), (1, '22.020')] -[2023-10-10 21:41:25,582][98559] Updated weights for policy 0, policy_version 24110 (0.0010) -[2023-10-10 21:41:25,953][98559] Updated weights for policy 0, policy_version 24120 (0.0009) -[2023-10-10 21:41:28,693][98560] Updated weights for policy 1, policy_version 24072 (0.0008) -[2023-10-10 21:41:29,059][98560] Updated weights for policy 1, policy_version 24082 (0.0009) -[2023-10-10 21:41:29,432][98560] Updated weights for policy 1, policy_version 24092 (0.0009) -[2023-10-10 21:41:29,986][98559] Updated weights for policy 0, policy_version 24130 (0.0008) -[2023-10-10 21:41:30,353][98559] Updated weights for policy 0, policy_version 24140 (0.0007) -[2023-10-10 21:41:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 49381376. Throughput: 0: 1728.9, 1: 1686.4. Samples: 12354614. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-10 21:41:30,557][97672] Avg episode reward: [(0, '-1.720'), (1, '22.040')] -[2023-10-10 21:41:30,713][98559] Updated weights for policy 0, policy_version 24150 (0.0009) -[2023-10-10 21:41:31,084][98559] Updated weights for policy 0, policy_version 24160 (0.0009) -[2023-10-10 21:41:33,510][98560] Updated weights for policy 1, policy_version 24102 (0.0007) -[2023-10-10 21:41:33,872][98560] Updated weights for policy 1, policy_version 24112 (0.0007) -[2023-10-10 21:41:34,245][98560] Updated weights for policy 1, policy_version 24122 (0.0008) -[2023-10-10 21:41:34,991][98559] Updated weights for policy 0, policy_version 24170 (0.0008) -[2023-10-10 21:41:35,359][98559] Updated weights for policy 0, policy_version 24180 (0.0010) -[2023-10-10 21:41:35,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 49446912. Throughput: 0: 1705.9, 1: 1672.0. Samples: 12373982. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-10 21:41:35,557][97672] Avg episode reward: [(0, '-1.740'), (1, '22.120')] -[2023-10-10 21:41:35,729][98559] Updated weights for policy 0, policy_version 24190 (0.0007) -[2023-10-10 21:41:38,309][98560] Updated weights for policy 1, policy_version 24132 (0.0010) -[2023-10-10 21:41:38,680][98560] Updated weights for policy 1, policy_version 24142 (0.0007) -[2023-10-10 21:41:39,052][98560] Updated weights for policy 1, policy_version 24152 (0.0007) -[2023-10-10 21:41:39,726][98559] Updated weights for policy 0, policy_version 24200 (0.0008) -[2023-10-10 21:41:40,102][98559] Updated weights for policy 0, policy_version 24210 (0.0007) -[2023-10-10 21:41:40,466][98559] Updated weights for policy 0, policy_version 24220 (0.0007) -[2023-10-10 21:41:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 49512448. Throughput: 0: 1725.9, 1: 1701.1. Samples: 12385540. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-10 21:41:40,556][97672] Avg episode reward: [(0, '-1.740'), (1, '22.080')] -[2023-10-10 21:41:42,866][98560] Updated weights for policy 1, policy_version 24162 (0.0009) -[2023-10-10 21:41:43,225][98560] Updated weights for policy 1, policy_version 24172 (0.0007) -[2023-10-10 21:41:43,599][98560] Updated weights for policy 1, policy_version 24182 (0.0007) -[2023-10-10 21:41:43,962][98560] Updated weights for policy 1, policy_version 24192 (0.0008) -[2023-10-10 21:41:44,409][98559] Updated weights for policy 0, policy_version 24230 (0.0009) -[2023-10-10 21:41:44,778][98559] Updated weights for policy 0, policy_version 24240 (0.0010) -[2023-10-10 21:41:45,146][98559] Updated weights for policy 0, policy_version 24250 (0.0008) -[2023-10-10 21:41:45,556][97672] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 49610752. Throughput: 0: 1727.5, 1: 1681.2. Samples: 12405704. Policy #0 lag: (min: 0.0, avg: 16.1, max: 32.0) -[2023-10-10 21:41:45,557][97672] Avg episode reward: [(0, '-1.740'), (1, '22.120')] -[2023-10-10 21:41:48,020][98560] Updated weights for policy 1, policy_version 24202 (0.0009) -[2023-10-10 21:41:48,386][98560] Updated weights for policy 1, policy_version 24212 (0.0007) -[2023-10-10 21:41:48,754][98560] Updated weights for policy 1, policy_version 24222 (0.0007) -[2023-10-10 21:41:49,211][98559] Updated weights for policy 0, policy_version 24260 (0.0009) -[2023-10-10 21:41:49,584][98559] Updated weights for policy 0, policy_version 24270 (0.0009) -[2023-10-10 21:41:49,950][98559] Updated weights for policy 0, policy_version 24280 (0.0009) -[2023-10-10 21:41:50,556][97672] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 49676288. Throughput: 0: 1699.3, 1: 1686.1. Samples: 12425254. Policy #0 lag: (min: 0.0, avg: 16.1, max: 32.0) -[2023-10-10 21:41:50,556][97672] Avg episode reward: [(0, '-1.740'), (1, '22.200')] -[2023-10-10 21:41:52,735][98560] Updated weights for policy 1, policy_version 24232 (0.0008) -[2023-10-10 21:41:53,097][98560] Updated weights for policy 1, policy_version 24242 (0.0011) -[2023-10-10 21:41:53,461][98560] Updated weights for policy 1, policy_version 24252 (0.0010) -[2023-10-10 21:41:53,811][98559] Updated weights for policy 0, policy_version 24290 (0.0010) -[2023-10-10 21:41:54,174][98559] Updated weights for policy 0, policy_version 24300 (0.0010) -[2023-10-10 21:41:54,549][98559] Updated weights for policy 0, policy_version 24310 (0.0010) -[2023-10-10 21:41:54,913][98559] Updated weights for policy 0, policy_version 24320 (0.0011) -[2023-10-10 21:41:55,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 49741824. Throughput: 0: 1733.9, 1: 1697.7. Samples: 12437092. Policy #0 lag: (min: 0.0, avg: 16.1, max: 32.0) -[2023-10-10 21:41:55,557][97672] Avg episode reward: [(0, '-1.740'), (1, '22.220')] -[2023-10-10 21:41:57,428][98560] Updated weights for policy 1, policy_version 24262 (0.0009) -[2023-10-10 21:41:57,793][98560] Updated weights for policy 1, policy_version 24272 (0.0007) -[2023-10-10 21:41:58,172][98560] Updated weights for policy 1, policy_version 24282 (0.0007) -[2023-10-10 21:41:59,087][98559] Updated weights for policy 0, policy_version 24330 (0.0008) -[2023-10-10 21:41:59,451][98559] Updated weights for policy 0, policy_version 24340 (0.0010) -[2023-10-10 21:41:59,825][98559] Updated weights for policy 0, policy_version 24350 (0.0012) -[2023-10-10 21:42:00,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 49807360. Throughput: 0: 1710.0, 1: 1676.8. Samples: 12456082. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 21:42:00,557][97672] Avg episode reward: [(0, '-1.740'), (1, '22.220')] -[2023-10-10 21:42:02,252][98560] Updated weights for policy 1, policy_version 24292 (0.0008) -[2023-10-10 21:42:02,625][98560] Updated weights for policy 1, policy_version 24302 (0.0010) -[2023-10-10 21:42:02,984][98560] Updated weights for policy 1, policy_version 24312 (0.0010) -[2023-10-10 21:42:03,825][98559] Updated weights for policy 0, policy_version 24360 (0.0008) -[2023-10-10 21:42:04,199][98559] Updated weights for policy 0, policy_version 24370 (0.0008) -[2023-10-10 21:42:04,560][98559] Updated weights for policy 0, policy_version 24380 (0.0009) -[2023-10-10 21:42:05,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 49872896. Throughput: 0: 1690.8, 1: 1702.0. Samples: 12476402. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 21:42:05,557][97672] Avg episode reward: [(0, '-1.600'), (1, '22.320')] -[2023-10-10 21:42:05,570][98385] Saving new best policy, reward=-1.600! -[2023-10-10 21:42:06,907][98560] Updated weights for policy 1, policy_version 24322 (0.0010) -[2023-10-10 21:42:07,266][98560] Updated weights for policy 1, policy_version 24332 (0.0009) -[2023-10-10 21:42:07,639][98560] Updated weights for policy 1, policy_version 24342 (0.0009) -[2023-10-10 21:42:08,003][98560] Updated weights for policy 1, policy_version 24352 (0.0008) -[2023-10-10 21:42:08,577][98559] Updated weights for policy 0, policy_version 24390 (0.0008) -[2023-10-10 21:42:08,945][98559] Updated weights for policy 0, policy_version 24400 (0.0007) -[2023-10-10 21:42:09,319][98559] Updated weights for policy 0, policy_version 24410 (0.0008) -[2023-10-10 21:42:10,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 49938432. Throughput: 0: 1720.0, 1: 1688.8. Samples: 12487466. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 21:42:10,556][97672] Avg episode reward: [(0, '-1.620'), (1, '22.360')] -[2023-10-10 21:42:12,135][98560] Updated weights for policy 1, policy_version 24362 (0.0007) -[2023-10-10 21:42:12,512][98560] Updated weights for policy 1, policy_version 24372 (0.0009) -[2023-10-10 21:42:12,880][98560] Updated weights for policy 1, policy_version 24382 (0.0010) -[2023-10-10 21:42:13,149][98559] Updated weights for policy 0, policy_version 24420 (0.0008) -[2023-10-10 21:42:13,513][98559] Updated weights for policy 0, policy_version 24430 (0.0009) -[2023-10-10 21:42:13,889][98559] Updated weights for policy 0, policy_version 24440 (0.0007) -[2023-10-10 21:42:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 50003968. Throughput: 0: 1691.4, 1: 1694.0. Samples: 12506958. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 21:42:15,557][97672] Avg episode reward: [(0, '-1.620'), (1, '22.360')] -[2023-10-10 21:42:17,052][98560] Updated weights for policy 1, policy_version 24392 (0.0009) -[2023-10-10 21:42:17,435][98560] Updated weights for policy 1, policy_version 24402 (0.0007) -[2023-10-10 21:42:17,798][98560] Updated weights for policy 1, policy_version 24412 (0.0009) -[2023-10-10 21:42:17,911][98559] Updated weights for policy 0, policy_version 24450 (0.0010) -[2023-10-10 21:42:18,272][98559] Updated weights for policy 0, policy_version 24460 (0.0011) -[2023-10-10 21:42:18,638][98559] Updated weights for policy 0, policy_version 24470 (0.0007) -[2023-10-10 21:42:19,005][98559] Updated weights for policy 0, policy_version 24480 (0.0009) -[2023-10-10 21:42:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 50069504. Throughput: 0: 1705.3, 1: 1711.2. Samples: 12527728. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-10 21:42:20,556][97672] Avg episode reward: [(0, '-1.620'), (1, '22.340')] -[2023-10-10 21:42:21,786][98560] Updated weights for policy 1, policy_version 24422 (0.0007) -[2023-10-10 21:42:22,149][98560] Updated weights for policy 1, policy_version 24432 (0.0008) -[2023-10-10 21:42:22,519][98560] Updated weights for policy 1, policy_version 24442 (0.0008) -[2023-10-10 21:42:22,938][98559] Updated weights for policy 0, policy_version 24490 (0.0010) -[2023-10-10 21:42:23,312][98559] Updated weights for policy 0, policy_version 24500 (0.0010) -[2023-10-10 21:42:23,678][98559] Updated weights for policy 0, policy_version 24510 (0.0009) -[2023-10-10 21:42:25,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 50135040. Throughput: 0: 1698.6, 1: 1680.8. Samples: 12537616. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-10 21:42:25,556][97672] Avg episode reward: [(0, '-1.620'), (1, '22.340')] -[2023-10-10 21:42:26,459][98560] Updated weights for policy 1, policy_version 24452 (0.0009) -[2023-10-10 21:42:26,817][98560] Updated weights for policy 1, policy_version 24462 (0.0008) -[2023-10-10 21:42:27,181][98560] Updated weights for policy 1, policy_version 24472 (0.0008) -[2023-10-10 21:42:27,840][98559] Updated weights for policy 0, policy_version 24520 (0.0010) -[2023-10-10 21:42:28,207][98559] Updated weights for policy 0, policy_version 24530 (0.0011) -[2023-10-10 21:42:28,586][98559] Updated weights for policy 0, policy_version 24540 (0.0011) -[2023-10-10 21:42:30,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 50200576. Throughput: 0: 1686.0, 1: 1702.1. Samples: 12558166. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-10 21:42:30,557][97672] Avg episode reward: [(0, '-1.620'), (1, '22.360')] -[2023-10-10 21:42:31,017][98560] Updated weights for policy 1, policy_version 24482 (0.0008) -[2023-10-10 21:42:31,390][98560] Updated weights for policy 1, policy_version 24492 (0.0010) -[2023-10-10 21:42:31,750][98560] Updated weights for policy 1, policy_version 24502 (0.0009) -[2023-10-10 21:42:32,121][98560] Updated weights for policy 1, policy_version 24512 (0.0008) -[2023-10-10 21:42:32,641][98559] Updated weights for policy 0, policy_version 24550 (0.0008) -[2023-10-10 21:42:33,018][98559] Updated weights for policy 0, policy_version 24560 (0.0011) -[2023-10-10 21:42:33,398][98559] Updated weights for policy 0, policy_version 24570 (0.0009) -[2023-10-10 21:42:35,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 50266112. Throughput: 0: 1710.8, 1: 1713.1. Samples: 12579328. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-10 21:42:35,557][97672] Avg episode reward: [(0, '-1.620'), (1, '22.320')] -[2023-10-10 21:42:35,567][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000024512_25100288.pth... -[2023-10-10 21:42:35,567][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000024576_25165824.pth... -[2023-10-10 21:42:35,603][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000022976_23527424.pth -[2023-10-10 21:42:35,609][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000022944_23494656.pth -[2023-10-10 21:42:36,122][98560] Updated weights for policy 1, policy_version 24522 (0.0007) -[2023-10-10 21:42:36,491][98560] Updated weights for policy 1, policy_version 24532 (0.0008) -[2023-10-10 21:42:36,853][98560] Updated weights for policy 1, policy_version 24542 (0.0007) -[2023-10-10 21:42:37,402][98559] Updated weights for policy 0, policy_version 24580 (0.0009) -[2023-10-10 21:42:37,782][98559] Updated weights for policy 0, policy_version 24590 (0.0009) -[2023-10-10 21:42:38,153][98559] Updated weights for policy 0, policy_version 24600 (0.0007) -[2023-10-10 21:42:40,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 50331648. Throughput: 0: 1685.0, 1: 1685.6. Samples: 12588770. Policy #0 lag: (min: 19.0, avg: 20.0, max: 42.0) -[2023-10-10 21:42:40,557][97672] Avg episode reward: [(0, '-1.600'), (1, '22.340')] -[2023-10-10 21:42:40,751][98560] Updated weights for policy 1, policy_version 24552 (0.0011) -[2023-10-10 21:42:41,113][98560] Updated weights for policy 1, policy_version 24562 (0.0009) -[2023-10-10 21:42:41,479][98560] Updated weights for policy 1, policy_version 24572 (0.0009) -[2023-10-10 21:42:42,161][98559] Updated weights for policy 0, policy_version 24610 (0.0007) -[2023-10-10 21:42:42,526][98559] Updated weights for policy 0, policy_version 24620 (0.0009) -[2023-10-10 21:42:42,893][98559] Updated weights for policy 0, policy_version 24630 (0.0010) -[2023-10-10 21:42:43,263][98559] Updated weights for policy 0, policy_version 24640 (0.0008) -[2023-10-10 21:42:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13662.6). Total num frames: 50397184. Throughput: 0: 1703.6, 1: 1712.1. Samples: 12609790. Policy #0 lag: (min: 19.0, avg: 20.0, max: 42.0) -[2023-10-10 21:42:45,556][97672] Avg episode reward: [(0, '-1.600'), (1, '22.340')] -[2023-10-10 21:42:45,648][98560] Updated weights for policy 1, policy_version 24582 (0.0007) -[2023-10-10 21:42:46,026][98560] Updated weights for policy 1, policy_version 24592 (0.0009) -[2023-10-10 21:42:46,391][98560] Updated weights for policy 1, policy_version 24602 (0.0007) -[2023-10-10 21:42:47,143][98559] Updated weights for policy 0, policy_version 24650 (0.0007) -[2023-10-10 21:42:47,521][98559] Updated weights for policy 0, policy_version 24660 (0.0009) -[2023-10-10 21:42:47,884][98559] Updated weights for policy 0, policy_version 24670 (0.0009) -[2023-10-10 21:42:50,523][98560] Updated weights for policy 1, policy_version 24612 (0.0008) -[2023-10-10 21:42:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 50462720. Throughput: 0: 1721.0, 1: 1709.2. Samples: 12630758. Policy #0 lag: (min: 19.0, avg: 20.0, max: 42.0) -[2023-10-10 21:42:50,556][97672] Avg episode reward: [(0, '-1.620'), (1, '22.260')] -[2023-10-10 21:42:50,897][98560] Updated weights for policy 1, policy_version 24622 (0.0011) -[2023-10-10 21:42:51,255][98560] Updated weights for policy 1, policy_version 24632 (0.0009) -[2023-10-10 21:42:51,909][98559] Updated weights for policy 0, policy_version 24680 (0.0010) -[2023-10-10 21:42:52,283][98559] Updated weights for policy 0, policy_version 24690 (0.0009) -[2023-10-10 21:42:52,648][98559] Updated weights for policy 0, policy_version 24700 (0.0009) -[2023-10-10 21:42:55,332][98560] Updated weights for policy 1, policy_version 24642 (0.0008) -[2023-10-10 21:42:55,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 50528256. Throughput: 0: 1687.7, 1: 1696.9. Samples: 12639776. Policy #0 lag: (min: 19.0, avg: 20.0, max: 42.0) -[2023-10-10 21:42:55,556][97672] Avg episode reward: [(0, '-1.620'), (1, '22.260')] -[2023-10-10 21:42:55,701][98560] Updated weights for policy 1, policy_version 24652 (0.0007) -[2023-10-10 21:42:56,065][98560] Updated weights for policy 1, policy_version 24662 (0.0008) -[2023-10-10 21:42:56,434][98560] Updated weights for policy 1, policy_version 24672 (0.0007) -[2023-10-10 21:42:56,647][98559] Updated weights for policy 0, policy_version 24710 (0.0008) -[2023-10-10 21:42:57,017][98559] Updated weights for policy 0, policy_version 24720 (0.0008) -[2023-10-10 21:42:57,386][98559] Updated weights for policy 0, policy_version 24730 (0.0008) -[2023-10-10 21:43:00,490][98560] Updated weights for policy 1, policy_version 24682 (0.0011) -[2023-10-10 21:43:00,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 50593792. Throughput: 0: 1711.7, 1: 1704.0. Samples: 12660666. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-10 21:43:00,556][97672] Avg episode reward: [(0, '-1.620'), (1, '22.280')] -[2023-10-10 21:43:00,867][98560] Updated weights for policy 1, policy_version 24692 (0.0009) -[2023-10-10 21:43:01,234][98560] Updated weights for policy 1, policy_version 24702 (0.0011) -[2023-10-10 21:43:01,456][98559] Updated weights for policy 0, policy_version 24740 (0.0008) -[2023-10-10 21:43:01,819][98559] Updated weights for policy 0, policy_version 24750 (0.0007) -[2023-10-10 21:43:02,192][98559] Updated weights for policy 0, policy_version 24760 (0.0009) -[2023-10-10 21:43:05,294][98560] Updated weights for policy 1, policy_version 24712 (0.0007) -[2023-10-10 21:43:05,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 50659328. Throughput: 0: 1706.8, 1: 1708.8. Samples: 12681434. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-10 21:43:05,557][97672] Avg episode reward: [(0, '-1.580'), (1, '22.260')] -[2023-10-10 21:43:05,568][98385] Saving new best policy, reward=-1.580! -[2023-10-10 21:43:05,672][98560] Updated weights for policy 1, policy_version 24722 (0.0008) -[2023-10-10 21:43:06,047][98560] Updated weights for policy 1, policy_version 24732 (0.0008) -[2023-10-10 21:43:06,171][98559] Updated weights for policy 0, policy_version 24770 (0.0008) -[2023-10-10 21:43:06,545][98559] Updated weights for policy 0, policy_version 24780 (0.0008) -[2023-10-10 21:43:06,917][98559] Updated weights for policy 0, policy_version 24790 (0.0008) -[2023-10-10 21:43:07,285][98559] Updated weights for policy 0, policy_version 24800 (0.0009) -[2023-10-10 21:43:10,079][98560] Updated weights for policy 1, policy_version 24742 (0.0008) -[2023-10-10 21:43:10,448][98560] Updated weights for policy 1, policy_version 24752 (0.0007) -[2023-10-10 21:43:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 50724864. Throughput: 0: 1693.2, 1: 1706.9. Samples: 12690620. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-10 21:43:10,557][97672] Avg episode reward: [(0, '-1.640'), (1, '22.240')] -[2023-10-10 21:43:10,813][98560] Updated weights for policy 1, policy_version 24762 (0.0007) -[2023-10-10 21:43:11,246][98559] Updated weights for policy 0, policy_version 24810 (0.0007) -[2023-10-10 21:43:11,616][98559] Updated weights for policy 0, policy_version 24820 (0.0011) -[2023-10-10 21:43:11,976][98559] Updated weights for policy 0, policy_version 24830 (0.0010) -[2023-10-10 21:43:14,802][98560] Updated weights for policy 1, policy_version 24772 (0.0008) -[2023-10-10 21:43:15,170][98560] Updated weights for policy 1, policy_version 24782 (0.0009) -[2023-10-10 21:43:15,534][98560] Updated weights for policy 1, policy_version 24792 (0.0007) -[2023-10-10 21:43:15,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 50790400. Throughput: 0: 1706.5, 1: 1702.6. Samples: 12711576. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-10 21:43:15,557][97672] Avg episode reward: [(0, '-1.600'), (1, '22.180')] -[2023-10-10 21:43:16,103][98559] Updated weights for policy 0, policy_version 24840 (0.0009) -[2023-10-10 21:43:16,468][98559] Updated weights for policy 0, policy_version 24850 (0.0007) -[2023-10-10 21:43:16,836][98559] Updated weights for policy 0, policy_version 24860 (0.0007) -[2023-10-10 21:43:19,390][98560] Updated weights for policy 1, policy_version 24802 (0.0008) -[2023-10-10 21:43:19,755][98560] Updated weights for policy 1, policy_version 24812 (0.0010) -[2023-10-10 21:43:20,123][98560] Updated weights for policy 1, policy_version 24822 (0.0011) -[2023-10-10 21:43:20,494][98560] Updated weights for policy 1, policy_version 24832 (0.0009) -[2023-10-10 21:43:20,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 50888704. Throughput: 0: 1708.7, 1: 1691.1. Samples: 12732318. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:43:20,557][97672] Avg episode reward: [(0, '-1.600'), (1, '22.180')] -[2023-10-10 21:43:20,739][98559] Updated weights for policy 0, policy_version 24870 (0.0009) -[2023-10-10 21:43:21,106][98559] Updated weights for policy 0, policy_version 24880 (0.0009) -[2023-10-10 21:43:21,486][98559] Updated weights for policy 0, policy_version 24890 (0.0008) -[2023-10-10 21:43:24,336][98560] Updated weights for policy 1, policy_version 24842 (0.0008) -[2023-10-10 21:43:24,703][98560] Updated weights for policy 1, policy_version 24852 (0.0009) -[2023-10-10 21:43:25,074][98560] Updated weights for policy 1, policy_version 24862 (0.0009) -[2023-10-10 21:43:25,500][98559] Updated weights for policy 0, policy_version 24900 (0.0008) -[2023-10-10 21:43:25,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 50954240. Throughput: 0: 1700.1, 1: 1703.2. Samples: 12741920. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:43:25,557][97672] Avg episode reward: [(0, '-1.620'), (1, '22.220')] -[2023-10-10 21:43:25,878][98559] Updated weights for policy 0, policy_version 24910 (0.0010) -[2023-10-10 21:43:26,256][98559] Updated weights for policy 0, policy_version 24920 (0.0008) -[2023-10-10 21:43:29,069][98560] Updated weights for policy 1, policy_version 24872 (0.0008) -[2023-10-10 21:43:29,436][98560] Updated weights for policy 1, policy_version 24882 (0.0009) -[2023-10-10 21:43:29,802][98560] Updated weights for policy 1, policy_version 24892 (0.0010) -[2023-10-10 21:43:30,336][98559] Updated weights for policy 0, policy_version 24930 (0.0010) -[2023-10-10 21:43:30,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 51019776. Throughput: 0: 1704.7, 1: 1705.5. Samples: 12763246. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:43:30,557][97672] Avg episode reward: [(0, '-1.620'), (1, '22.220')] -[2023-10-10 21:43:30,707][98559] Updated weights for policy 0, policy_version 24940 (0.0008) -[2023-10-10 21:43:31,073][98559] Updated weights for policy 0, policy_version 24950 (0.0008) -[2023-10-10 21:43:31,444][98559] Updated weights for policy 0, policy_version 24960 (0.0009) -[2023-10-10 21:43:33,883][98560] Updated weights for policy 1, policy_version 24902 (0.0010) -[2023-10-10 21:43:34,260][98560] Updated weights for policy 1, policy_version 24912 (0.0009) -[2023-10-10 21:43:34,626][98560] Updated weights for policy 1, policy_version 24922 (0.0009) -[2023-10-10 21:43:35,288][98559] Updated weights for policy 0, policy_version 24970 (0.0007) -[2023-10-10 21:43:35,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 51085312. Throughput: 0: 1691.9, 1: 1683.0. Samples: 12782626. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:43:35,556][97672] Avg episode reward: [(0, '-1.620'), (1, '22.160')] -[2023-10-10 21:43:35,655][98559] Updated weights for policy 0, policy_version 24980 (0.0008) -[2023-10-10 21:43:36,033][98559] Updated weights for policy 0, policy_version 24990 (0.0008) -[2023-10-10 21:43:38,489][98560] Updated weights for policy 1, policy_version 24932 (0.0008) -[2023-10-10 21:43:38,865][98560] Updated weights for policy 1, policy_version 24942 (0.0007) -[2023-10-10 21:43:39,234][98560] Updated weights for policy 1, policy_version 24952 (0.0008) -[2023-10-10 21:43:40,187][98559] Updated weights for policy 0, policy_version 25000 (0.0009) -[2023-10-10 21:43:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 51150848. Throughput: 0: 1701.6, 1: 1714.0. Samples: 12793478. Policy #0 lag: (min: 14.0, avg: 21.7, max: 46.0) -[2023-10-10 21:43:40,556][97672] Avg episode reward: [(0, '-1.620'), (1, '22.240')] -[2023-10-10 21:43:40,573][98559] Updated weights for policy 0, policy_version 25010 (0.0009) -[2023-10-10 21:43:40,934][98559] Updated weights for policy 0, policy_version 25020 (0.0007) -[2023-10-10 21:43:43,022][98560] Updated weights for policy 1, policy_version 24962 (0.0008) -[2023-10-10 21:43:43,390][98560] Updated weights for policy 1, policy_version 24972 (0.0007) -[2023-10-10 21:43:43,756][98560] Updated weights for policy 1, policy_version 24982 (0.0007) -[2023-10-10 21:43:44,128][98560] Updated weights for policy 1, policy_version 24992 (0.0009) -[2023-10-10 21:43:45,011][98559] Updated weights for policy 0, policy_version 25030 (0.0011) -[2023-10-10 21:43:45,384][98559] Updated weights for policy 0, policy_version 25040 (0.0009) -[2023-10-10 21:43:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 51216384. Throughput: 0: 1706.8, 1: 1698.9. Samples: 12813922. Policy #0 lag: (min: 14.0, avg: 21.7, max: 46.0) -[2023-10-10 21:43:45,556][97672] Avg episode reward: [(0, '-1.620'), (1, '22.260')] -[2023-10-10 21:43:45,760][98559] Updated weights for policy 0, policy_version 25050 (0.0009) -[2023-10-10 21:43:48,223][98560] Updated weights for policy 1, policy_version 25002 (0.0010) -[2023-10-10 21:43:48,584][98560] Updated weights for policy 1, policy_version 25012 (0.0011) -[2023-10-10 21:43:48,947][98560] Updated weights for policy 1, policy_version 25022 (0.0011) -[2023-10-10 21:43:49,664][98559] Updated weights for policy 0, policy_version 25060 (0.0009) -[2023-10-10 21:43:50,028][98559] Updated weights for policy 0, policy_version 25070 (0.0009) -[2023-10-10 21:43:50,391][98559] Updated weights for policy 0, policy_version 25080 (0.0010) -[2023-10-10 21:43:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 51281920. Throughput: 0: 1693.1, 1: 1686.3. Samples: 12833508. Policy #0 lag: (min: 14.0, avg: 21.7, max: 46.0) -[2023-10-10 21:43:50,557][97672] Avg episode reward: [(0, '-1.620'), (1, '22.200')] -[2023-10-10 21:43:53,171][98560] Updated weights for policy 1, policy_version 25032 (0.0010) -[2023-10-10 21:43:53,543][98560] Updated weights for policy 1, policy_version 25042 (0.0009) -[2023-10-10 21:43:53,913][98560] Updated weights for policy 1, policy_version 25052 (0.0009) -[2023-10-10 21:43:54,205][98559] Updated weights for policy 0, policy_version 25090 (0.0009) -[2023-10-10 21:43:54,578][98559] Updated weights for policy 0, policy_version 25100 (0.0009) -[2023-10-10 21:43:54,947][98559] Updated weights for policy 0, policy_version 25110 (0.0010) -[2023-10-10 21:43:55,318][98559] Updated weights for policy 0, policy_version 25120 (0.0009) -[2023-10-10 21:43:55,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 51380224. Throughput: 0: 1717.9, 1: 1717.9. Samples: 12845230. Policy #0 lag: (min: 10.0, avg: 12.2, max: 42.0) -[2023-10-10 21:43:55,557][97672] Avg episode reward: [(0, '-1.620'), (1, '22.180')] -[2023-10-10 21:43:57,880][98560] Updated weights for policy 1, policy_version 25062 (0.0008) -[2023-10-10 21:43:58,249][98560] Updated weights for policy 1, policy_version 25072 (0.0008) -[2023-10-10 21:43:58,621][98560] Updated weights for policy 1, policy_version 25082 (0.0008) -[2023-10-10 21:43:59,310][98559] Updated weights for policy 0, policy_version 25130 (0.0008) -[2023-10-10 21:43:59,677][98559] Updated weights for policy 0, policy_version 25140 (0.0008) -[2023-10-10 21:44:00,044][98559] Updated weights for policy 0, policy_version 25150 (0.0008) -[2023-10-10 21:44:00,556][97672] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 51445760. Throughput: 0: 1709.1, 1: 1691.3. Samples: 12864594. Policy #0 lag: (min: 10.0, avg: 12.2, max: 42.0) -[2023-10-10 21:44:00,557][97672] Avg episode reward: [(0, '-1.640'), (1, '22.200')] -[2023-10-10 21:44:02,646][98560] Updated weights for policy 1, policy_version 25092 (0.0007) -[2023-10-10 21:44:03,018][98560] Updated weights for policy 1, policy_version 25102 (0.0008) -[2023-10-10 21:44:03,390][98560] Updated weights for policy 1, policy_version 25112 (0.0008) -[2023-10-10 21:44:04,017][98559] Updated weights for policy 0, policy_version 25160 (0.0008) -[2023-10-10 21:44:04,377][98559] Updated weights for policy 0, policy_version 25170 (0.0008) -[2023-10-10 21:44:04,747][98559] Updated weights for policy 0, policy_version 25180 (0.0009) -[2023-10-10 21:44:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 51511296. Throughput: 0: 1690.3, 1: 1695.5. Samples: 12884678. Policy #0 lag: (min: 10.0, avg: 12.2, max: 42.0) -[2023-10-10 21:44:05,556][97672] Avg episode reward: [(0, '-1.640'), (1, '22.280')] -[2023-10-10 21:44:07,509][98560] Updated weights for policy 1, policy_version 25122 (0.0010) -[2023-10-10 21:44:07,887][98560] Updated weights for policy 1, policy_version 25132 (0.0010) -[2023-10-10 21:44:08,257][98560] Updated weights for policy 1, policy_version 25142 (0.0011) -[2023-10-10 21:44:08,632][98560] Updated weights for policy 1, policy_version 25152 (0.0009) -[2023-10-10 21:44:08,781][98559] Updated weights for policy 0, policy_version 25190 (0.0009) -[2023-10-10 21:44:09,148][98559] Updated weights for policy 0, policy_version 25200 (0.0010) -[2023-10-10 21:44:09,520][98559] Updated weights for policy 0, policy_version 25210 (0.0007) -[2023-10-10 21:44:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 51576832. Throughput: 0: 1719.9, 1: 1707.3. Samples: 12896144. Policy #0 lag: (min: 10.0, avg: 12.2, max: 42.0) -[2023-10-10 21:44:10,557][97672] Avg episode reward: [(0, '-1.640'), (1, '22.260')] -[2023-10-10 21:44:12,806][98560] Updated weights for policy 1, policy_version 25162 (0.0009) -[2023-10-10 21:44:13,173][98560] Updated weights for policy 1, policy_version 25172 (0.0007) -[2023-10-10 21:44:13,548][98560] Updated weights for policy 1, policy_version 25182 (0.0008) -[2023-10-10 21:44:13,560][98559] Updated weights for policy 0, policy_version 25220 (0.0008) -[2023-10-10 21:44:13,930][98559] Updated weights for policy 0, policy_version 25230 (0.0008) -[2023-10-10 21:44:14,290][98559] Updated weights for policy 0, policy_version 25240 (0.0008) -[2023-10-10 21:44:15,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 51642368. Throughput: 0: 1692.8, 1: 1676.7. Samples: 12914876. Policy #0 lag: (min: 25.0, avg: 25.3, max: 39.0) -[2023-10-10 21:44:15,557][97672] Avg episode reward: [(0, '-1.640'), (1, '22.280')] -[2023-10-10 21:44:17,586][98560] Updated weights for policy 1, policy_version 25192 (0.0008) -[2023-10-10 21:44:17,953][98560] Updated weights for policy 1, policy_version 25202 (0.0007) -[2023-10-10 21:44:18,272][98559] Updated weights for policy 0, policy_version 25250 (0.0009) -[2023-10-10 21:44:18,316][98560] Updated weights for policy 1, policy_version 25212 (0.0009) -[2023-10-10 21:44:18,639][98559] Updated weights for policy 0, policy_version 25260 (0.0009) -[2023-10-10 21:44:19,007][98559] Updated weights for policy 0, policy_version 25270 (0.0008) -[2023-10-10 21:44:19,386][98559] Updated weights for policy 0, policy_version 25280 (0.0008) -[2023-10-10 21:44:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 51707904. Throughput: 0: 1700.5, 1: 1699.4. Samples: 12935622. Policy #0 lag: (min: 25.0, avg: 25.3, max: 39.0) -[2023-10-10 21:44:20,557][97672] Avg episode reward: [(0, '-1.640'), (1, '22.300')] -[2023-10-10 21:44:22,374][98560] Updated weights for policy 1, policy_version 25222 (0.0007) -[2023-10-10 21:44:22,734][98560] Updated weights for policy 1, policy_version 25232 (0.0009) -[2023-10-10 21:44:23,107][98560] Updated weights for policy 1, policy_version 25242 (0.0009) -[2023-10-10 21:44:23,320][98559] Updated weights for policy 0, policy_version 25290 (0.0007) -[2023-10-10 21:44:23,682][98559] Updated weights for policy 0, policy_version 25300 (0.0010) -[2023-10-10 21:44:24,053][98559] Updated weights for policy 0, policy_version 25310 (0.0010) -[2023-10-10 21:44:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 51773440. Throughput: 0: 1712.7, 1: 1685.5. Samples: 12946402. Policy #0 lag: (min: 25.0, avg: 25.3, max: 39.0) -[2023-10-10 21:44:25,557][97672] Avg episode reward: [(0, '-1.640'), (1, '22.360')] -[2023-10-10 21:44:27,021][98560] Updated weights for policy 1, policy_version 25252 (0.0009) -[2023-10-10 21:44:27,391][98560] Updated weights for policy 1, policy_version 25262 (0.0008) -[2023-10-10 21:44:27,753][98560] Updated weights for policy 1, policy_version 25272 (0.0007) -[2023-10-10 21:44:28,127][98559] Updated weights for policy 0, policy_version 25320 (0.0009) -[2023-10-10 21:44:28,496][98559] Updated weights for policy 0, policy_version 25330 (0.0007) -[2023-10-10 21:44:28,867][98559] Updated weights for policy 0, policy_version 25340 (0.0007) -[2023-10-10 21:44:30,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 51838976. Throughput: 0: 1691.1, 1: 1685.3. Samples: 12965858. Policy #0 lag: (min: 25.0, avg: 25.3, max: 39.0) -[2023-10-10 21:44:30,558][97672] Avg episode reward: [(0, '-1.640'), (1, '22.340')] -[2023-10-10 21:44:31,818][98560] Updated weights for policy 1, policy_version 25282 (0.0007) -[2023-10-10 21:44:32,184][98560] Updated weights for policy 1, policy_version 25292 (0.0007) -[2023-10-10 21:44:32,553][98560] Updated weights for policy 1, policy_version 25302 (0.0009) -[2023-10-10 21:44:32,680][98559] Updated weights for policy 0, policy_version 25350 (0.0008) -[2023-10-10 21:44:32,913][98560] Updated weights for policy 1, policy_version 25312 (0.0009) -[2023-10-10 21:44:33,050][98559] Updated weights for policy 0, policy_version 25360 (0.0008) -[2023-10-10 21:44:33,427][98559] Updated weights for policy 0, policy_version 25370 (0.0010) -[2023-10-10 21:44:35,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 51904512. Throughput: 0: 1713.6, 1: 1698.1. Samples: 12987034. Policy #0 lag: (min: 18.0, avg: 24.4, max: 50.0) -[2023-10-10 21:44:35,557][97672] Avg episode reward: [(0, '-1.640'), (1, '22.300')] -[2023-10-10 21:44:35,568][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000025376_25985024.pth... -[2023-10-10 21:44:35,569][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000025312_25919488.pth... -[2023-10-10 21:44:35,608][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000023776_24346624.pth -[2023-10-10 21:44:35,611][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000023744_24313856.pth -[2023-10-10 21:44:36,887][98560] Updated weights for policy 1, policy_version 25322 (0.0011) -[2023-10-10 21:44:37,256][98560] Updated weights for policy 1, policy_version 25332 (0.0008) -[2023-10-10 21:44:37,303][98559] Updated weights for policy 0, policy_version 25380 (0.0008) -[2023-10-10 21:44:37,624][98560] Updated weights for policy 1, policy_version 25342 (0.0008) -[2023-10-10 21:44:37,666][98559] Updated weights for policy 0, policy_version 25390 (0.0009) -[2023-10-10 21:44:38,031][98559] Updated weights for policy 0, policy_version 25400 (0.0009) -[2023-10-10 21:44:40,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 51970048. Throughput: 0: 1694.4, 1: 1668.6. Samples: 12996566. Policy #0 lag: (min: 18.0, avg: 24.4, max: 50.0) -[2023-10-10 21:44:40,557][97672] Avg episode reward: [(0, '-1.640'), (1, '22.260')] -[2023-10-10 21:44:41,724][98560] Updated weights for policy 1, policy_version 25352 (0.0008) -[2023-10-10 21:44:42,051][98559] Updated weights for policy 0, policy_version 25410 (0.0008) -[2023-10-10 21:44:42,095][98560] Updated weights for policy 1, policy_version 25362 (0.0008) -[2023-10-10 21:44:42,428][98559] Updated weights for policy 0, policy_version 25420 (0.0007) -[2023-10-10 21:44:42,464][98560] Updated weights for policy 1, policy_version 25372 (0.0008) -[2023-10-10 21:44:42,787][98559] Updated weights for policy 0, policy_version 25430 (0.0009) -[2023-10-10 21:44:43,157][98559] Updated weights for policy 0, policy_version 25440 (0.0010) -[2023-10-10 21:44:45,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 52035584. Throughput: 0: 1704.9, 1: 1694.8. Samples: 13017580. Policy #0 lag: (min: 18.0, avg: 24.4, max: 50.0) -[2023-10-10 21:44:45,557][97672] Avg episode reward: [(0, '-1.640'), (1, '22.300')] -[2023-10-10 21:44:46,493][98560] Updated weights for policy 1, policy_version 25382 (0.0007) -[2023-10-10 21:44:46,884][98560] Updated weights for policy 1, policy_version 25392 (0.0009) -[2023-10-10 21:44:47,162][98559] Updated weights for policy 0, policy_version 25450 (0.0009) -[2023-10-10 21:44:47,254][98560] Updated weights for policy 1, policy_version 25402 (0.0010) -[2023-10-10 21:44:47,537][98559] Updated weights for policy 0, policy_version 25460 (0.0007) -[2023-10-10 21:44:47,901][98559] Updated weights for policy 0, policy_version 25470 (0.0009) -[2023-10-10 21:44:50,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 52101120. Throughput: 0: 1724.4, 1: 1693.6. Samples: 13038484. Policy #0 lag: (min: 18.0, avg: 24.4, max: 50.0) -[2023-10-10 21:44:50,557][97672] Avg episode reward: [(0, '-1.640'), (1, '22.120')] -[2023-10-10 21:44:51,382][98560] Updated weights for policy 1, policy_version 25412 (0.0009) -[2023-10-10 21:44:51,760][98560] Updated weights for policy 1, policy_version 25422 (0.0009) -[2023-10-10 21:44:51,879][98559] Updated weights for policy 0, policy_version 25480 (0.0008) -[2023-10-10 21:44:52,130][98560] Updated weights for policy 1, policy_version 25432 (0.0008) -[2023-10-10 21:44:52,241][98559] Updated weights for policy 0, policy_version 25490 (0.0007) -[2023-10-10 21:44:52,610][98559] Updated weights for policy 0, policy_version 25500 (0.0010) -[2023-10-10 21:44:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 52166656. Throughput: 0: 1695.8, 1: 1669.6. Samples: 13047588. Policy #0 lag: (min: 29.0, avg: 36.8, max: 61.0) -[2023-10-10 21:44:55,557][97672] Avg episode reward: [(0, '-1.640'), (1, '22.100')] -[2023-10-10 21:44:56,308][98560] Updated weights for policy 1, policy_version 25442 (0.0008) -[2023-10-10 21:44:56,362][98559] Updated weights for policy 0, policy_version 25510 (0.0008) -[2023-10-10 21:44:56,682][98560] Updated weights for policy 1, policy_version 25452 (0.0009) -[2023-10-10 21:44:56,724][98559] Updated weights for policy 0, policy_version 25520 (0.0008) -[2023-10-10 21:44:57,047][98560] Updated weights for policy 1, policy_version 25462 (0.0008) -[2023-10-10 21:44:57,087][98559] Updated weights for policy 0, policy_version 25530 (0.0008) -[2023-10-10 21:44:57,403][98560] Updated weights for policy 1, policy_version 25472 (0.0008) -[2023-10-10 21:45:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 52232192. Throughput: 0: 1724.3, 1: 1691.5. Samples: 13068588. Policy #0 lag: (min: 29.0, avg: 36.8, max: 61.0) -[2023-10-10 21:45:00,557][97672] Avg episode reward: [(0, '-1.640'), (1, '22.040')] -[2023-10-10 21:45:01,159][98559] Updated weights for policy 0, policy_version 25540 (0.0008) -[2023-10-10 21:45:01,457][98560] Updated weights for policy 1, policy_version 25482 (0.0008) -[2023-10-10 21:45:01,524][98559] Updated weights for policy 0, policy_version 25550 (0.0008) -[2023-10-10 21:45:01,821][98560] Updated weights for policy 1, policy_version 25492 (0.0009) -[2023-10-10 21:45:01,890][98559] Updated weights for policy 0, policy_version 25560 (0.0007) -[2023-10-10 21:45:02,193][98560] Updated weights for policy 1, policy_version 25502 (0.0009) -[2023-10-10 21:45:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 52297728. Throughput: 0: 1731.9, 1: 1692.1. Samples: 13089702. Policy #0 lag: (min: 29.0, avg: 36.8, max: 61.0) -[2023-10-10 21:45:05,556][97672] Avg episode reward: [(0, '-1.640'), (1, '22.080')] -[2023-10-10 21:45:05,881][98559] Updated weights for policy 0, policy_version 25570 (0.0007) -[2023-10-10 21:45:06,146][98560] Updated weights for policy 1, policy_version 25512 (0.0009) -[2023-10-10 21:45:06,246][98559] Updated weights for policy 0, policy_version 25580 (0.0008) -[2023-10-10 21:45:06,515][98560] Updated weights for policy 1, policy_version 25522 (0.0007) -[2023-10-10 21:45:06,625][98559] Updated weights for policy 0, policy_version 25590 (0.0010) -[2023-10-10 21:45:06,888][98560] Updated weights for policy 1, policy_version 25532 (0.0007) -[2023-10-10 21:45:06,985][98559] Updated weights for policy 0, policy_version 25600 (0.0009) -[2023-10-10 21:45:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 52363264. Throughput: 0: 1712.8, 1: 1678.3. Samples: 13099002. Policy #0 lag: (min: 29.0, avg: 36.8, max: 61.0) -[2023-10-10 21:45:10,557][97672] Avg episode reward: [(0, '-1.600'), (1, '21.980')] -[2023-10-10 21:45:10,912][98560] Updated weights for policy 1, policy_version 25542 (0.0008) -[2023-10-10 21:45:10,934][98559] Updated weights for policy 0, policy_version 25610 (0.0009) -[2023-10-10 21:45:11,277][98560] Updated weights for policy 1, policy_version 25552 (0.0007) -[2023-10-10 21:45:11,301][98559] Updated weights for policy 0, policy_version 25620 (0.0008) -[2023-10-10 21:45:11,647][98560] Updated weights for policy 1, policy_version 25562 (0.0007) -[2023-10-10 21:45:11,681][98559] Updated weights for policy 0, policy_version 25630 (0.0009) -[2023-10-10 21:45:15,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 52428800. Throughput: 0: 1732.5, 1: 1693.3. Samples: 13120020. Policy #0 lag: (min: 17.0, avg: 22.6, max: 49.0) -[2023-10-10 21:45:15,557][97672] Avg episode reward: [(0, '-1.600'), (1, '21.920')] -[2023-10-10 21:45:15,703][98560] Updated weights for policy 1, policy_version 25572 (0.0008) -[2023-10-10 21:45:15,850][98559] Updated weights for policy 0, policy_version 25640 (0.0008) -[2023-10-10 21:45:16,082][98560] Updated weights for policy 1, policy_version 25582 (0.0007) -[2023-10-10 21:45:16,227][98559] Updated weights for policy 0, policy_version 25650 (0.0007) -[2023-10-10 21:45:16,448][98560] Updated weights for policy 1, policy_version 25592 (0.0009) -[2023-10-10 21:45:16,595][98559] Updated weights for policy 0, policy_version 25660 (0.0007) -[2023-10-10 21:45:20,519][98560] Updated weights for policy 1, policy_version 25602 (0.0008) -[2023-10-10 21:45:20,550][98559] Updated weights for policy 0, policy_version 25670 (0.0008) -[2023-10-10 21:45:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 52494336. Throughput: 0: 1725.1, 1: 1692.1. Samples: 13140810. Policy #0 lag: (min: 17.0, avg: 22.6, max: 49.0) -[2023-10-10 21:45:20,557][97672] Avg episode reward: [(0, '-1.600'), (1, '21.940')] -[2023-10-10 21:45:20,883][98560] Updated weights for policy 1, policy_version 25612 (0.0009) -[2023-10-10 21:45:20,917][98559] Updated weights for policy 0, policy_version 25680 (0.0009) -[2023-10-10 21:45:21,253][98560] Updated weights for policy 1, policy_version 25622 (0.0008) -[2023-10-10 21:45:21,280][98559] Updated weights for policy 0, policy_version 25690 (0.0010) -[2023-10-10 21:45:21,618][98560] Updated weights for policy 1, policy_version 25632 (0.0008) -[2023-10-10 21:45:25,200][98559] Updated weights for policy 0, policy_version 25700 (0.0011) -[2023-10-10 21:45:25,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 52559872. Throughput: 0: 1720.1, 1: 1689.0. Samples: 13149976. Policy #0 lag: (min: 17.0, avg: 22.6, max: 49.0) -[2023-10-10 21:45:25,556][97672] Avg episode reward: [(0, '-1.600'), (1, '22.020')] -[2023-10-10 21:45:25,561][98559] Updated weights for policy 0, policy_version 25710 (0.0007) -[2023-10-10 21:45:25,632][98560] Updated weights for policy 1, policy_version 25642 (0.0007) -[2023-10-10 21:45:25,931][98559] Updated weights for policy 0, policy_version 25720 (0.0008) -[2023-10-10 21:45:25,989][98560] Updated weights for policy 1, policy_version 25652 (0.0008) -[2023-10-10 21:45:26,356][98560] Updated weights for policy 1, policy_version 25662 (0.0010) -[2023-10-10 21:45:29,920][98559] Updated weights for policy 0, policy_version 25730 (0.0008) -[2023-10-10 21:45:30,294][98559] Updated weights for policy 0, policy_version 25740 (0.0007) -[2023-10-10 21:45:30,333][98560] Updated weights for policy 1, policy_version 25672 (0.0007) -[2023-10-10 21:45:30,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 52625408. Throughput: 0: 1720.1, 1: 1688.9. Samples: 13170986. Policy #0 lag: (min: 17.0, avg: 22.6, max: 49.0) -[2023-10-10 21:45:30,556][97672] Avg episode reward: [(0, '-1.620'), (1, '22.200')] -[2023-10-10 21:45:30,660][98559] Updated weights for policy 0, policy_version 25750 (0.0008) -[2023-10-10 21:45:30,704][98560] Updated weights for policy 1, policy_version 25682 (0.0007) -[2023-10-10 21:45:31,024][98559] Updated weights for policy 0, policy_version 25760 (0.0008) -[2023-10-10 21:45:31,068][98560] Updated weights for policy 1, policy_version 25692 (0.0008) -[2023-10-10 21:45:34,929][98559] Updated weights for policy 0, policy_version 25770 (0.0009) -[2023-10-10 21:45:35,152][98560] Updated weights for policy 1, policy_version 25702 (0.0008) -[2023-10-10 21:45:35,292][98559] Updated weights for policy 0, policy_version 25780 (0.0007) -[2023-10-10 21:45:35,537][98560] Updated weights for policy 1, policy_version 25712 (0.0008) -[2023-10-10 21:45:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 52690944. Throughput: 0: 1700.0, 1: 1693.9. Samples: 13191208. Policy #0 lag: (min: 17.0, avg: 23.6, max: 49.0) -[2023-10-10 21:45:35,557][97672] Avg episode reward: [(0, '-1.620'), (1, '22.280')] -[2023-10-10 21:45:35,655][98559] Updated weights for policy 0, policy_version 25790 (0.0009) -[2023-10-10 21:45:35,895][98560] Updated weights for policy 1, policy_version 25722 (0.0010) -[2023-10-10 21:45:39,656][98559] Updated weights for policy 0, policy_version 25800 (0.0009) -[2023-10-10 21:45:39,825][98560] Updated weights for policy 1, policy_version 25732 (0.0009) -[2023-10-10 21:45:40,013][98559] Updated weights for policy 0, policy_version 25810 (0.0008) -[2023-10-10 21:45:40,190][98560] Updated weights for policy 1, policy_version 25742 (0.0008) -[2023-10-10 21:45:40,376][98559] Updated weights for policy 0, policy_version 25820 (0.0008) -[2023-10-10 21:45:40,552][98560] Updated weights for policy 1, policy_version 25752 (0.0008) -[2023-10-10 21:45:40,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 52789248. Throughput: 0: 1717.2, 1: 1692.8. Samples: 13201040. Policy #0 lag: (min: 17.0, avg: 23.6, max: 49.0) -[2023-10-10 21:45:40,556][97672] Avg episode reward: [(0, '-1.580'), (1, '22.320')] -[2023-10-10 21:45:44,495][98559] Updated weights for policy 0, policy_version 25830 (0.0012) -[2023-10-10 21:45:44,570][98560] Updated weights for policy 1, policy_version 25762 (0.0009) -[2023-10-10 21:45:44,868][98559] Updated weights for policy 0, policy_version 25840 (0.0008) -[2023-10-10 21:45:44,935][98560] Updated weights for policy 1, policy_version 25772 (0.0008) -[2023-10-10 21:45:45,228][98559] Updated weights for policy 0, policy_version 25850 (0.0007) -[2023-10-10 21:45:45,304][98560] Updated weights for policy 1, policy_version 25782 (0.0009) -[2023-10-10 21:45:45,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 52854784. Throughput: 0: 1713.2, 1: 1703.6. Samples: 13222342. Policy #0 lag: (min: 17.0, avg: 23.6, max: 49.0) -[2023-10-10 21:45:45,557][97672] Avg episode reward: [(0, '-1.520'), (1, '22.340')] -[2023-10-10 21:45:45,557][98385] Saving new best policy, reward=-1.520! -[2023-10-10 21:45:45,668][98560] Updated weights for policy 1, policy_version 25792 (0.0010) -[2023-10-10 21:45:49,135][98559] Updated weights for policy 0, policy_version 25860 (0.0009) -[2023-10-10 21:45:49,494][98559] Updated weights for policy 0, policy_version 25870 (0.0010) -[2023-10-10 21:45:49,866][98559] Updated weights for policy 0, policy_version 25880 (0.0009) -[2023-10-10 21:45:49,887][98560] Updated weights for policy 1, policy_version 25802 (0.0009) -[2023-10-10 21:45:50,246][98560] Updated weights for policy 1, policy_version 25812 (0.0008) -[2023-10-10 21:45:50,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 52920320. Throughput: 0: 1684.4, 1: 1695.0. Samples: 13241774. Policy #0 lag: (min: 20.0, avg: 20.1, max: 27.0) -[2023-10-10 21:45:50,557][97672] Avg episode reward: [(0, '-1.520'), (1, '22.360')] -[2023-10-10 21:45:50,623][98560] Updated weights for policy 1, policy_version 25822 (0.0009) -[2023-10-10 21:45:53,829][98559] Updated weights for policy 0, policy_version 25890 (0.0008) -[2023-10-10 21:45:54,194][98559] Updated weights for policy 0, policy_version 25900 (0.0011) -[2023-10-10 21:45:54,573][98559] Updated weights for policy 0, policy_version 25910 (0.0008) -[2023-10-10 21:45:54,702][98560] Updated weights for policy 1, policy_version 25832 (0.0008) -[2023-10-10 21:45:54,936][98559] Updated weights for policy 0, policy_version 25920 (0.0008) -[2023-10-10 21:45:55,070][98560] Updated weights for policy 1, policy_version 25842 (0.0007) -[2023-10-10 21:45:55,433][98560] Updated weights for policy 1, policy_version 25852 (0.0008) -[2023-10-10 21:45:55,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 52985856. Throughput: 0: 1713.8, 1: 1698.3. Samples: 13252544. Policy #0 lag: (min: 20.0, avg: 20.1, max: 27.0) -[2023-10-10 21:45:55,556][97672] Avg episode reward: [(0, '-1.520'), (1, '22.340')] -[2023-10-10 21:45:59,100][98559] Updated weights for policy 0, policy_version 25930 (0.0007) -[2023-10-10 21:45:59,352][98560] Updated weights for policy 1, policy_version 25862 (0.0009) -[2023-10-10 21:45:59,468][98559] Updated weights for policy 0, policy_version 25940 (0.0007) -[2023-10-10 21:45:59,714][98560] Updated weights for policy 1, policy_version 25872 (0.0009) -[2023-10-10 21:45:59,827][98559] Updated weights for policy 0, policy_version 25950 (0.0007) -[2023-10-10 21:46:00,085][98560] Updated weights for policy 1, policy_version 25882 (0.0009) -[2023-10-10 21:46:00,556][97672] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 53084160. Throughput: 0: 1698.1, 1: 1700.7. Samples: 13272968. Policy #0 lag: (min: 20.0, avg: 20.1, max: 27.0) -[2023-10-10 21:46:00,557][97672] Avg episode reward: [(0, '-1.520'), (1, '22.480')] -[2023-10-10 21:46:00,558][98439] Saving new best policy, reward=22.480! -[2023-10-10 21:46:03,842][98559] Updated weights for policy 0, policy_version 25960 (0.0008) -[2023-10-10 21:46:04,081][98560] Updated weights for policy 1, policy_version 25892 (0.0008) -[2023-10-10 21:46:04,207][98559] Updated weights for policy 0, policy_version 25970 (0.0009) -[2023-10-10 21:46:04,456][98560] Updated weights for policy 1, policy_version 25902 (0.0009) -[2023-10-10 21:46:04,571][98559] Updated weights for policy 0, policy_version 25980 (0.0009) -[2023-10-10 21:46:04,815][98560] Updated weights for policy 1, policy_version 25912 (0.0007) -[2023-10-10 21:46:05,556][97672] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 53149696. Throughput: 0: 1690.2, 1: 1685.9. Samples: 13292732. Policy #0 lag: (min: 20.0, avg: 20.1, max: 27.0) -[2023-10-10 21:46:05,557][97672] Avg episode reward: [(0, '-1.520'), (1, '22.500')] -[2023-10-10 21:46:05,567][98439] Saving new best policy, reward=22.500! -[2023-10-10 21:46:08,578][98559] Updated weights for policy 0, policy_version 25990 (0.0008) -[2023-10-10 21:46:08,921][98560] Updated weights for policy 1, policy_version 25922 (0.0008) -[2023-10-10 21:46:08,952][98559] Updated weights for policy 0, policy_version 26000 (0.0008) -[2023-10-10 21:46:09,280][98560] Updated weights for policy 1, policy_version 25932 (0.0008) -[2023-10-10 21:46:09,316][98559] Updated weights for policy 0, policy_version 26010 (0.0008) -[2023-10-10 21:46:09,642][98560] Updated weights for policy 1, policy_version 25942 (0.0009) -[2023-10-10 21:46:10,013][98560] Updated weights for policy 1, policy_version 25952 (0.0008) -[2023-10-10 21:46:10,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 53215232. Throughput: 0: 1719.6, 1: 1704.9. Samples: 13304082. Policy #0 lag: (min: 1.0, avg: 8.7, max: 33.0) -[2023-10-10 21:46:10,557][97672] Avg episode reward: [(0, '-1.520'), (1, '22.460')] -[2023-10-10 21:46:13,324][98559] Updated weights for policy 0, policy_version 26020 (0.0009) -[2023-10-10 21:46:13,693][98559] Updated weights for policy 0, policy_version 26030 (0.0008) -[2023-10-10 21:46:14,017][98560] Updated weights for policy 1, policy_version 25962 (0.0009) -[2023-10-10 21:46:14,062][98559] Updated weights for policy 0, policy_version 26040 (0.0007) -[2023-10-10 21:46:14,386][98560] Updated weights for policy 1, policy_version 25972 (0.0007) -[2023-10-10 21:46:14,752][98560] Updated weights for policy 1, policy_version 25982 (0.0007) -[2023-10-10 21:46:15,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 53280768. Throughput: 0: 1690.1, 1: 1706.3. Samples: 13323828. Policy #0 lag: (min: 1.0, avg: 8.7, max: 33.0) -[2023-10-10 21:46:15,557][97672] Avg episode reward: [(0, '-1.520'), (1, '22.380')] -[2023-10-10 21:46:18,000][98559] Updated weights for policy 0, policy_version 26050 (0.0007) -[2023-10-10 21:46:18,370][98559] Updated weights for policy 0, policy_version 26060 (0.0007) -[2023-10-10 21:46:18,589][98560] Updated weights for policy 1, policy_version 25992 (0.0008) -[2023-10-10 21:46:18,733][98559] Updated weights for policy 0, policy_version 26070 (0.0008) -[2023-10-10 21:46:18,952][98560] Updated weights for policy 1, policy_version 26002 (0.0007) -[2023-10-10 21:46:19,095][98559] Updated weights for policy 0, policy_version 26080 (0.0009) -[2023-10-10 21:46:19,320][98560] Updated weights for policy 1, policy_version 26012 (0.0009) -[2023-10-10 21:46:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 53346304. Throughput: 0: 1704.3, 1: 1686.0. Samples: 13343772. Policy #0 lag: (min: 1.0, avg: 8.7, max: 33.0) -[2023-10-10 21:46:20,557][97672] Avg episode reward: [(0, '-1.380'), (1, '22.300')] -[2023-10-10 21:46:20,568][98385] Saving new best policy, reward=-1.380! -[2023-10-10 21:46:23,180][98559] Updated weights for policy 0, policy_version 26090 (0.0008) -[2023-10-10 21:46:23,431][98560] Updated weights for policy 1, policy_version 26022 (0.0008) -[2023-10-10 21:46:23,552][98559] Updated weights for policy 0, policy_version 26100 (0.0009) -[2023-10-10 21:46:23,819][98560] Updated weights for policy 1, policy_version 26032 (0.0008) -[2023-10-10 21:46:23,925][98559] Updated weights for policy 0, policy_version 26110 (0.0007) -[2023-10-10 21:46:24,198][98560] Updated weights for policy 1, policy_version 26042 (0.0008) -[2023-10-10 21:46:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 53411840. Throughput: 0: 1705.4, 1: 1719.2. Samples: 13355146. Policy #0 lag: (min: 1.0, avg: 8.7, max: 33.0) -[2023-10-10 21:46:25,557][97672] Avg episode reward: [(0, '-1.340'), (1, '22.340')] -[2023-10-10 21:46:25,558][98385] Saving new best policy, reward=-1.340! -[2023-10-10 21:46:27,804][98559] Updated weights for policy 0, policy_version 26120 (0.0008) -[2023-10-10 21:46:28,173][98559] Updated weights for policy 0, policy_version 26130 (0.0008) -[2023-10-10 21:46:28,286][98560] Updated weights for policy 1, policy_version 26052 (0.0009) -[2023-10-10 21:46:28,546][98559] Updated weights for policy 0, policy_version 26140 (0.0008) -[2023-10-10 21:46:28,654][98560] Updated weights for policy 1, policy_version 26062 (0.0009) -[2023-10-10 21:46:29,024][98560] Updated weights for policy 1, policy_version 26072 (0.0008) -[2023-10-10 21:46:30,556][97672] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 53477376. Throughput: 0: 1696.6, 1: 1694.8. Samples: 13374958. Policy #0 lag: (min: 28.0, avg: 28.8, max: 47.0) -[2023-10-10 21:46:30,557][97672] Avg episode reward: [(0, '-1.340'), (1, '22.340')] -[2023-10-10 21:46:32,592][98559] Updated weights for policy 0, policy_version 26150 (0.0008) -[2023-10-10 21:46:32,827][98560] Updated weights for policy 1, policy_version 26082 (0.0008) -[2023-10-10 21:46:32,956][98559] Updated weights for policy 0, policy_version 26160 (0.0009) -[2023-10-10 21:46:33,192][98560] Updated weights for policy 1, policy_version 26092 (0.0007) -[2023-10-10 21:46:33,328][98559] Updated weights for policy 0, policy_version 26170 (0.0008) -[2023-10-10 21:46:33,568][98560] Updated weights for policy 1, policy_version 26102 (0.0008) -[2023-10-10 21:46:33,930][98560] Updated weights for policy 1, policy_version 26112 (0.0008) -[2023-10-10 21:46:35,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 53542912. Throughput: 0: 1724.0, 1: 1687.6. Samples: 13395298. Policy #0 lag: (min: 28.0, avg: 28.8, max: 47.0) -[2023-10-10 21:46:35,557][97672] Avg episode reward: [(0, '-1.340'), (1, '22.400')] -[2023-10-10 21:46:35,572][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000026112_26738688.pth... -[2023-10-10 21:46:35,572][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000026176_26804224.pth... -[2023-10-10 21:46:35,605][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000024512_25100288.pth -[2023-10-10 21:46:35,613][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000024576_25165824.pth -[2023-10-10 21:46:37,180][98559] Updated weights for policy 0, policy_version 26180 (0.0008) -[2023-10-10 21:46:37,543][98559] Updated weights for policy 0, policy_version 26190 (0.0007) -[2023-10-10 21:46:37,913][98559] Updated weights for policy 0, policy_version 26200 (0.0009) -[2023-10-10 21:46:38,008][98560] Updated weights for policy 1, policy_version 26122 (0.0007) -[2023-10-10 21:46:38,371][98560] Updated weights for policy 1, policy_version 26132 (0.0010) -[2023-10-10 21:46:38,739][98560] Updated weights for policy 1, policy_version 26142 (0.0008) -[2023-10-10 21:46:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 53608448. Throughput: 0: 1693.5, 1: 1710.2. Samples: 13405712. Policy #0 lag: (min: 28.0, avg: 28.8, max: 47.0) -[2023-10-10 21:46:40,556][97672] Avg episode reward: [(0, '-1.340'), (1, '22.440')] -[2023-10-10 21:46:41,958][98559] Updated weights for policy 0, policy_version 26210 (0.0007) -[2023-10-10 21:46:42,329][98559] Updated weights for policy 0, policy_version 26220 (0.0008) -[2023-10-10 21:46:42,700][98559] Updated weights for policy 0, policy_version 26230 (0.0008) -[2023-10-10 21:46:42,859][98560] Updated weights for policy 1, policy_version 26152 (0.0009) -[2023-10-10 21:46:43,071][98559] Updated weights for policy 0, policy_version 26240 (0.0008) -[2023-10-10 21:46:43,222][98560] Updated weights for policy 1, policy_version 26162 (0.0008) -[2023-10-10 21:46:43,593][98560] Updated weights for policy 1, policy_version 26172 (0.0010) -[2023-10-10 21:46:45,556][97672] Fps is (10 sec: 13107.7, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 53673984. Throughput: 0: 1713.2, 1: 1680.1. Samples: 13425668. Policy #0 lag: (min: 28.0, avg: 28.8, max: 47.0) -[2023-10-10 21:46:45,557][97672] Avg episode reward: [(0, '-1.340'), (1, '22.420')] -[2023-10-10 21:46:47,109][98559] Updated weights for policy 0, policy_version 26250 (0.0010) -[2023-10-10 21:46:47,479][98559] Updated weights for policy 0, policy_version 26260 (0.0009) -[2023-10-10 21:46:47,706][98560] Updated weights for policy 1, policy_version 26182 (0.0009) -[2023-10-10 21:46:47,848][98559] Updated weights for policy 0, policy_version 26270 (0.0009) -[2023-10-10 21:46:48,071][98560] Updated weights for policy 1, policy_version 26192 (0.0009) -[2023-10-10 21:46:48,438][98560] Updated weights for policy 1, policy_version 26202 (0.0008) -[2023-10-10 21:46:50,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 53739520. Throughput: 0: 1727.6, 1: 1693.4. Samples: 13446678. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:46:50,557][97672] Avg episode reward: [(0, '-1.340'), (1, '22.440')] -[2023-10-10 21:46:51,751][98559] Updated weights for policy 0, policy_version 26280 (0.0009) -[2023-10-10 21:46:52,123][98559] Updated weights for policy 0, policy_version 26290 (0.0007) -[2023-10-10 21:46:52,474][98560] Updated weights for policy 1, policy_version 26212 (0.0008) -[2023-10-10 21:46:52,500][98559] Updated weights for policy 0, policy_version 26300 (0.0008) -[2023-10-10 21:46:52,839][98560] Updated weights for policy 1, policy_version 26222 (0.0009) -[2023-10-10 21:46:53,220][98560] Updated weights for policy 1, policy_version 26232 (0.0010) -[2023-10-10 21:46:55,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 53805056. Throughput: 0: 1696.9, 1: 1695.4. Samples: 13456736. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:46:55,557][97672] Avg episode reward: [(0, '-1.340'), (1, '22.400')] -[2023-10-10 21:46:56,365][98559] Updated weights for policy 0, policy_version 26310 (0.0010) -[2023-10-10 21:46:56,726][98559] Updated weights for policy 0, policy_version 26320 (0.0009) -[2023-10-10 21:46:57,094][98560] Updated weights for policy 1, policy_version 26242 (0.0009) -[2023-10-10 21:46:57,105][98559] Updated weights for policy 0, policy_version 26330 (0.0009) -[2023-10-10 21:46:57,464][98560] Updated weights for policy 1, policy_version 26252 (0.0008) -[2023-10-10 21:46:57,834][98560] Updated weights for policy 1, policy_version 26262 (0.0009) -[2023-10-10 21:46:58,196][98560] Updated weights for policy 1, policy_version 26272 (0.0008) -[2023-10-10 21:47:00,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 53870592. Throughput: 0: 1720.8, 1: 1679.5. Samples: 13476844. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:47:00,557][97672] Avg episode reward: [(0, '-1.340'), (1, '22.400')] -[2023-10-10 21:47:01,220][98559] Updated weights for policy 0, policy_version 26340 (0.0007) -[2023-10-10 21:47:01,588][98559] Updated weights for policy 0, policy_version 26350 (0.0008) -[2023-10-10 21:47:01,964][98559] Updated weights for policy 0, policy_version 26360 (0.0008) -[2023-10-10 21:47:02,206][98560] Updated weights for policy 1, policy_version 26282 (0.0007) -[2023-10-10 21:47:02,571][98560] Updated weights for policy 1, policy_version 26292 (0.0008) -[2023-10-10 21:47:02,934][98560] Updated weights for policy 1, policy_version 26302 (0.0008) -[2023-10-10 21:47:05,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 53936128. Throughput: 0: 1719.9, 1: 1694.1. Samples: 13497400. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:47:05,556][97672] Avg episode reward: [(0, '-1.220'), (1, '22.400')] -[2023-10-10 21:47:05,564][98385] Saving new best policy, reward=-1.220! -[2023-10-10 21:47:05,855][98559] Updated weights for policy 0, policy_version 26370 (0.0008) -[2023-10-10 21:47:06,219][98559] Updated weights for policy 0, policy_version 26380 (0.0009) -[2023-10-10 21:47:06,589][98559] Updated weights for policy 0, policy_version 26390 (0.0007) -[2023-10-10 21:47:06,960][98559] Updated weights for policy 0, policy_version 26400 (0.0007) -[2023-10-10 21:47:07,077][98560] Updated weights for policy 1, policy_version 26312 (0.0008) -[2023-10-10 21:47:07,449][98560] Updated weights for policy 1, policy_version 26322 (0.0008) -[2023-10-10 21:47:07,817][98560] Updated weights for policy 1, policy_version 26332 (0.0008) -[2023-10-10 21:47:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 54001664. Throughput: 0: 1701.4, 1: 1672.5. Samples: 13506970. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:47:10,557][97672] Avg episode reward: [(0, '-1.220'), (1, '22.400')] -[2023-10-10 21:47:11,116][98559] Updated weights for policy 0, policy_version 26410 (0.0007) -[2023-10-10 21:47:11,491][98559] Updated weights for policy 0, policy_version 26420 (0.0009) -[2023-10-10 21:47:11,772][98560] Updated weights for policy 1, policy_version 26342 (0.0009) -[2023-10-10 21:47:11,866][98559] Updated weights for policy 0, policy_version 26430 (0.0007) -[2023-10-10 21:47:12,129][98560] Updated weights for policy 1, policy_version 26352 (0.0010) -[2023-10-10 21:47:12,492][98560] Updated weights for policy 1, policy_version 26362 (0.0008) -[2023-10-10 21:47:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 54067200. Throughput: 0: 1712.1, 1: 1684.0. Samples: 13527784. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:47:15,556][97672] Avg episode reward: [(0, '-1.220'), (1, '22.440')] -[2023-10-10 21:47:15,722][98559] Updated weights for policy 0, policy_version 26440 (0.0008) -[2023-10-10 21:47:16,097][98559] Updated weights for policy 0, policy_version 26450 (0.0009) -[2023-10-10 21:47:16,465][98559] Updated weights for policy 0, policy_version 26460 (0.0007) -[2023-10-10 21:47:16,631][98560] Updated weights for policy 1, policy_version 26372 (0.0009) -[2023-10-10 21:47:17,026][98560] Updated weights for policy 1, policy_version 26382 (0.0007) -[2023-10-10 21:47:17,394][98560] Updated weights for policy 1, policy_version 26392 (0.0008) -[2023-10-10 21:47:20,459][98559] Updated weights for policy 0, policy_version 26470 (0.0009) -[2023-10-10 21:47:20,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 54132736. Throughput: 0: 1710.5, 1: 1699.7. Samples: 13548756. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:47:20,557][97672] Avg episode reward: [(0, '-1.160'), (1, '22.400')] -[2023-10-10 21:47:20,816][98559] Updated weights for policy 0, policy_version 26480 (0.0007) -[2023-10-10 21:47:21,182][98559] Updated weights for policy 0, policy_version 26490 (0.0007) -[2023-10-10 21:47:21,388][98560] Updated weights for policy 1, policy_version 26402 (0.0008) -[2023-10-10 21:47:21,403][98385] Saving new best policy, reward=-1.160! -[2023-10-10 21:47:21,756][98560] Updated weights for policy 1, policy_version 26412 (0.0009) -[2023-10-10 21:47:22,119][98560] Updated weights for policy 1, policy_version 26422 (0.0008) -[2023-10-10 21:47:22,477][98560] Updated weights for policy 1, policy_version 26432 (0.0008) -[2023-10-10 21:47:25,344][98559] Updated weights for policy 0, policy_version 26500 (0.0008) -[2023-10-10 21:47:25,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 54198272. Throughput: 0: 1715.7, 1: 1674.0. Samples: 13558250. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:47:25,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.360')] -[2023-10-10 21:47:25,714][98559] Updated weights for policy 0, policy_version 26510 (0.0011) -[2023-10-10 21:47:26,076][98559] Updated weights for policy 0, policy_version 26520 (0.0011) -[2023-10-10 21:47:26,367][98385] Saving new best policy, reward=-1.100! -[2023-10-10 21:47:26,492][98560] Updated weights for policy 1, policy_version 26442 (0.0010) -[2023-10-10 21:47:26,871][98560] Updated weights for policy 1, policy_version 26452 (0.0011) -[2023-10-10 21:47:27,249][98560] Updated weights for policy 1, policy_version 26462 (0.0008) -[2023-10-10 21:47:30,119][98559] Updated weights for policy 0, policy_version 26530 (0.0008) -[2023-10-10 21:47:30,498][98559] Updated weights for policy 0, policy_version 26540 (0.0011) -[2023-10-10 21:47:30,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 54263808. Throughput: 0: 1711.7, 1: 1696.7. Samples: 13579046. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-10 21:47:30,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.400')] -[2023-10-10 21:47:30,860][98559] Updated weights for policy 0, policy_version 26550 (0.0010) -[2023-10-10 21:47:31,232][98559] Updated weights for policy 0, policy_version 26560 (0.0009) -[2023-10-10 21:47:31,352][98560] Updated weights for policy 1, policy_version 26472 (0.0011) -[2023-10-10 21:47:31,722][98560] Updated weights for policy 1, policy_version 26482 (0.0008) -[2023-10-10 21:47:32,083][98560] Updated weights for policy 1, policy_version 26492 (0.0010) -[2023-10-10 21:47:35,068][98559] Updated weights for policy 0, policy_version 26570 (0.0010) -[2023-10-10 21:47:35,437][98559] Updated weights for policy 0, policy_version 26580 (0.0008) -[2023-10-10 21:47:35,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 54329344. Throughput: 0: 1696.2, 1: 1695.9. Samples: 13599320. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-10 21:47:35,556][97672] Avg episode reward: [(0, '-1.100'), (1, '22.380')] -[2023-10-10 21:47:35,805][98559] Updated weights for policy 0, policy_version 26590 (0.0009) -[2023-10-10 21:47:36,152][98560] Updated weights for policy 1, policy_version 26502 (0.0009) -[2023-10-10 21:47:36,512][98560] Updated weights for policy 1, policy_version 26512 (0.0008) -[2023-10-10 21:47:36,876][98560] Updated weights for policy 1, policy_version 26522 (0.0008) -[2023-10-10 21:47:39,844][98559] Updated weights for policy 0, policy_version 26600 (0.0010) -[2023-10-10 21:47:40,210][98559] Updated weights for policy 0, policy_version 26610 (0.0009) -[2023-10-10 21:47:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 54394880. Throughput: 0: 1715.7, 1: 1677.1. Samples: 13609414. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-10 21:47:40,557][97672] Avg episode reward: [(0, '-1.120'), (1, '22.400')] -[2023-10-10 21:47:40,591][98559] Updated weights for policy 0, policy_version 26620 (0.0010) -[2023-10-10 21:47:41,010][98560] Updated weights for policy 1, policy_version 26532 (0.0008) -[2023-10-10 21:47:41,369][98560] Updated weights for policy 1, policy_version 26542 (0.0009) -[2023-10-10 21:47:41,744][98560] Updated weights for policy 1, policy_version 26552 (0.0009) -[2023-10-10 21:47:44,481][98559] Updated weights for policy 0, policy_version 26630 (0.0009) -[2023-10-10 21:47:44,845][98559] Updated weights for policy 0, policy_version 26640 (0.0010) -[2023-10-10 21:47:45,218][98559] Updated weights for policy 0, policy_version 26650 (0.0008) -[2023-10-10 21:47:45,556][97672] Fps is (10 sec: 16383.6, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 54493184. Throughput: 0: 1714.5, 1: 1691.7. Samples: 13630124. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-10 21:47:45,557][97672] Avg episode reward: [(0, '-1.120'), (1, '22.420')] -[2023-10-10 21:47:45,737][98560] Updated weights for policy 1, policy_version 26562 (0.0011) -[2023-10-10 21:47:46,108][98560] Updated weights for policy 1, policy_version 26572 (0.0007) -[2023-10-10 21:47:46,472][98560] Updated weights for policy 1, policy_version 26582 (0.0009) -[2023-10-10 21:47:46,838][98560] Updated weights for policy 1, policy_version 26592 (0.0008) -[2023-10-10 21:47:49,243][98559] Updated weights for policy 0, policy_version 26660 (0.0010) -[2023-10-10 21:47:49,623][98559] Updated weights for policy 0, policy_version 26670 (0.0009) -[2023-10-10 21:47:49,986][98559] Updated weights for policy 0, policy_version 26680 (0.0009) -[2023-10-10 21:47:50,556][97672] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 54558720. Throughput: 0: 1690.7, 1: 1700.3. Samples: 13649992. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-10 21:47:50,556][97672] Avg episode reward: [(0, '-1.160'), (1, '22.440')] -[2023-10-10 21:47:50,853][98560] Updated weights for policy 1, policy_version 26602 (0.0009) -[2023-10-10 21:47:51,225][98560] Updated weights for policy 1, policy_version 26612 (0.0010) -[2023-10-10 21:47:51,605][98560] Updated weights for policy 1, policy_version 26622 (0.0008) -[2023-10-10 21:47:53,884][98559] Updated weights for policy 0, policy_version 26690 (0.0009) -[2023-10-10 21:47:54,258][98559] Updated weights for policy 0, policy_version 26700 (0.0008) -[2023-10-10 21:47:54,629][98559] Updated weights for policy 0, policy_version 26710 (0.0009) -[2023-10-10 21:47:54,984][98559] Updated weights for policy 0, policy_version 26720 (0.0008) -[2023-10-10 21:47:55,522][98560] Updated weights for policy 1, policy_version 26632 (0.0008) -[2023-10-10 21:47:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 54624256. Throughput: 0: 1722.9, 1: 1694.0. Samples: 13660728. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-10 21:47:55,557][97672] Avg episode reward: [(0, '-1.160'), (1, '22.380')] -[2023-10-10 21:47:55,885][98560] Updated weights for policy 1, policy_version 26642 (0.0009) -[2023-10-10 21:47:56,263][98560] Updated weights for policy 1, policy_version 26652 (0.0007) -[2023-10-10 21:47:58,939][98559] Updated weights for policy 0, policy_version 26730 (0.0009) -[2023-10-10 21:47:59,311][98559] Updated weights for policy 0, policy_version 26740 (0.0009) -[2023-10-10 21:47:59,679][98559] Updated weights for policy 0, policy_version 26750 (0.0009) -[2023-10-10 21:48:00,010][98560] Updated weights for policy 1, policy_version 26662 (0.0009) -[2023-10-10 21:48:00,383][98560] Updated weights for policy 1, policy_version 26672 (0.0008) -[2023-10-10 21:48:00,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 54689792. Throughput: 0: 1704.1, 1: 1707.8. Samples: 13681320. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-10 21:48:00,557][97672] Avg episode reward: [(0, '-1.160'), (1, '22.420')] -[2023-10-10 21:48:00,759][98560] Updated weights for policy 1, policy_version 26682 (0.0008) -[2023-10-10 21:48:03,690][98559] Updated weights for policy 0, policy_version 26760 (0.0008) -[2023-10-10 21:48:04,057][98559] Updated weights for policy 0, policy_version 26770 (0.0007) -[2023-10-10 21:48:04,424][98559] Updated weights for policy 0, policy_version 26780 (0.0008) -[2023-10-10 21:48:04,871][98560] Updated weights for policy 1, policy_version 26692 (0.0010) -[2023-10-10 21:48:05,245][98560] Updated weights for policy 1, policy_version 26702 (0.0010) -[2023-10-10 21:48:05,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 54755328. Throughput: 0: 1694.5, 1: 1704.4. Samples: 13701704. Policy #0 lag: (min: 28.0, avg: 34.4, max: 60.0) -[2023-10-10 21:48:05,557][97672] Avg episode reward: [(0, '-1.160'), (1, '22.380')] -[2023-10-10 21:48:05,625][98560] Updated weights for policy 1, policy_version 26712 (0.0009) -[2023-10-10 21:48:08,410][98559] Updated weights for policy 0, policy_version 26790 (0.0008) -[2023-10-10 21:48:08,766][98559] Updated weights for policy 0, policy_version 26800 (0.0007) -[2023-10-10 21:48:09,128][98559] Updated weights for policy 0, policy_version 26810 (0.0009) -[2023-10-10 21:48:09,596][98560] Updated weights for policy 1, policy_version 26722 (0.0008) -[2023-10-10 21:48:09,953][98560] Updated weights for policy 1, policy_version 26732 (0.0008) -[2023-10-10 21:48:10,313][98560] Updated weights for policy 1, policy_version 26742 (0.0010) -[2023-10-10 21:48:10,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 54820864. Throughput: 0: 1710.7, 1: 1699.3. Samples: 13711700. Policy #0 lag: (min: 28.0, avg: 34.4, max: 60.0) -[2023-10-10 21:48:10,557][97672] Avg episode reward: [(0, '-1.140'), (1, '22.280')] -[2023-10-10 21:48:10,681][98560] Updated weights for policy 1, policy_version 26752 (0.0010) -[2023-10-10 21:48:13,156][98559] Updated weights for policy 0, policy_version 26820 (0.0011) -[2023-10-10 21:48:13,515][98559] Updated weights for policy 0, policy_version 26830 (0.0011) -[2023-10-10 21:48:13,891][98559] Updated weights for policy 0, policy_version 26840 (0.0009) -[2023-10-10 21:48:14,662][98560] Updated weights for policy 1, policy_version 26762 (0.0007) -[2023-10-10 21:48:15,029][98560] Updated weights for policy 1, policy_version 26772 (0.0007) -[2023-10-10 21:48:15,398][98560] Updated weights for policy 1, policy_version 26782 (0.0007) -[2023-10-10 21:48:15,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 54919168. Throughput: 0: 1683.8, 1: 1707.9. Samples: 13731670. Policy #0 lag: (min: 28.0, avg: 34.4, max: 60.0) -[2023-10-10 21:48:15,557][97672] Avg episode reward: [(0, '-1.140'), (1, '22.280')] -[2023-10-10 21:48:17,917][98559] Updated weights for policy 0, policy_version 26850 (0.0010) -[2023-10-10 21:48:18,280][98559] Updated weights for policy 0, policy_version 26860 (0.0008) -[2023-10-10 21:48:18,656][98559] Updated weights for policy 0, policy_version 26870 (0.0007) -[2023-10-10 21:48:19,014][98559] Updated weights for policy 0, policy_version 26880 (0.0009) -[2023-10-10 21:48:19,449][98560] Updated weights for policy 1, policy_version 26792 (0.0007) -[2023-10-10 21:48:19,829][98560] Updated weights for policy 1, policy_version 26802 (0.0008) -[2023-10-10 21:48:20,195][98560] Updated weights for policy 1, policy_version 26812 (0.0010) -[2023-10-10 21:48:20,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 54984704. Throughput: 0: 1700.4, 1: 1700.7. Samples: 13752370. Policy #0 lag: (min: 28.0, avg: 34.4, max: 60.0) -[2023-10-10 21:48:20,557][97672] Avg episode reward: [(0, '-1.140'), (1, '22.240')] -[2023-10-10 21:48:22,999][98559] Updated weights for policy 0, policy_version 26890 (0.0010) -[2023-10-10 21:48:23,370][98559] Updated weights for policy 0, policy_version 26900 (0.0008) -[2023-10-10 21:48:23,733][98559] Updated weights for policy 0, policy_version 26910 (0.0009) -[2023-10-10 21:48:24,094][98560] Updated weights for policy 1, policy_version 26822 (0.0009) -[2023-10-10 21:48:24,452][98560] Updated weights for policy 1, policy_version 26832 (0.0007) -[2023-10-10 21:48:24,825][98560] Updated weights for policy 1, policy_version 26842 (0.0009) -[2023-10-10 21:48:25,556][97672] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 55050240. Throughput: 0: 1692.9, 1: 1716.3. Samples: 13762828. Policy #0 lag: (min: 24.0, avg: 52.0, max: 56.0) -[2023-10-10 21:48:25,557][97672] Avg episode reward: [(0, '-1.140'), (1, '22.260')] -[2023-10-10 21:48:27,667][98559] Updated weights for policy 0, policy_version 26920 (0.0008) -[2023-10-10 21:48:28,041][98559] Updated weights for policy 0, policy_version 26930 (0.0009) -[2023-10-10 21:48:28,409][98559] Updated weights for policy 0, policy_version 26940 (0.0008) -[2023-10-10 21:48:28,727][98560] Updated weights for policy 1, policy_version 26852 (0.0008) -[2023-10-10 21:48:29,101][98560] Updated weights for policy 1, policy_version 26862 (0.0009) -[2023-10-10 21:48:29,475][98560] Updated weights for policy 1, policy_version 26872 (0.0009) -[2023-10-10 21:48:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 55115776. Throughput: 0: 1688.5, 1: 1716.8. Samples: 13783362. Policy #0 lag: (min: 24.0, avg: 52.0, max: 56.0) -[2023-10-10 21:48:30,557][97672] Avg episode reward: [(0, '-1.140'), (1, '22.240')] -[2023-10-10 21:48:32,341][98559] Updated weights for policy 0, policy_version 26950 (0.0008) -[2023-10-10 21:48:32,708][98559] Updated weights for policy 0, policy_version 26960 (0.0008) -[2023-10-10 21:48:33,079][98559] Updated weights for policy 0, policy_version 26970 (0.0008) -[2023-10-10 21:48:33,534][98560] Updated weights for policy 1, policy_version 26882 (0.0007) -[2023-10-10 21:48:33,905][98560] Updated weights for policy 1, policy_version 26892 (0.0008) -[2023-10-10 21:48:34,275][98560] Updated weights for policy 1, policy_version 26902 (0.0009) -[2023-10-10 21:48:34,639][98560] Updated weights for policy 1, policy_version 26912 (0.0009) -[2023-10-10 21:48:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 55181312. Throughput: 0: 1718.2, 1: 1692.4. Samples: 13803468. Policy #0 lag: (min: 24.0, avg: 52.0, max: 56.0) -[2023-10-10 21:48:35,557][97672] Avg episode reward: [(0, '-1.140'), (1, '22.220')] -[2023-10-10 21:48:35,565][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000026912_27557888.pth... -[2023-10-10 21:48:35,565][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000026976_27623424.pth... -[2023-10-10 21:48:35,601][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000025376_25985024.pth -[2023-10-10 21:48:35,605][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000025312_25919488.pth -[2023-10-10 21:48:37,096][98559] Updated weights for policy 0, policy_version 26980 (0.0009) -[2023-10-10 21:48:37,459][98559] Updated weights for policy 0, policy_version 26990 (0.0009) -[2023-10-10 21:48:37,825][98559] Updated weights for policy 0, policy_version 27000 (0.0009) -[2023-10-10 21:48:38,468][98560] Updated weights for policy 1, policy_version 26922 (0.0010) -[2023-10-10 21:48:38,838][98560] Updated weights for policy 1, policy_version 26932 (0.0009) -[2023-10-10 21:48:39,206][98560] Updated weights for policy 1, policy_version 26942 (0.0008) -[2023-10-10 21:48:40,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 55246848. Throughput: 0: 1688.3, 1: 1721.7. Samples: 13814176. Policy #0 lag: (min: 24.0, avg: 52.0, max: 56.0) -[2023-10-10 21:48:40,557][97672] Avg episode reward: [(0, '-1.140'), (1, '22.280')] -[2023-10-10 21:48:41,789][98559] Updated weights for policy 0, policy_version 27010 (0.0008) -[2023-10-10 21:48:42,165][98559] Updated weights for policy 0, policy_version 27020 (0.0009) -[2023-10-10 21:48:42,534][98559] Updated weights for policy 0, policy_version 27030 (0.0010) -[2023-10-10 21:48:42,905][98559] Updated weights for policy 0, policy_version 27040 (0.0008) -[2023-10-10 21:48:43,295][98560] Updated weights for policy 1, policy_version 26952 (0.0007) -[2023-10-10 21:48:43,664][98560] Updated weights for policy 1, policy_version 26962 (0.0010) -[2023-10-10 21:48:44,027][98560] Updated weights for policy 1, policy_version 26972 (0.0007) -[2023-10-10 21:48:45,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 55312384. Throughput: 0: 1703.8, 1: 1694.0. Samples: 13834220. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-10 21:48:45,557][97672] Avg episode reward: [(0, '-1.140'), (1, '22.260')] -[2023-10-10 21:48:46,927][98559] Updated weights for policy 0, policy_version 27050 (0.0007) -[2023-10-10 21:48:47,296][98559] Updated weights for policy 0, policy_version 27060 (0.0007) -[2023-10-10 21:48:47,667][98559] Updated weights for policy 0, policy_version 27070 (0.0008) -[2023-10-10 21:48:48,202][98560] Updated weights for policy 1, policy_version 26982 (0.0007) -[2023-10-10 21:48:48,562][98560] Updated weights for policy 1, policy_version 26992 (0.0009) -[2023-10-10 21:48:48,937][98560] Updated weights for policy 1, policy_version 27002 (0.0008) -[2023-10-10 21:48:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 55377920. Throughput: 0: 1708.9, 1: 1682.8. Samples: 13854326. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-10 21:48:50,556][97672] Avg episode reward: [(0, '-1.140'), (1, '22.260')] -[2023-10-10 21:48:51,792][98559] Updated weights for policy 0, policy_version 27080 (0.0008) -[2023-10-10 21:48:52,154][98559] Updated weights for policy 0, policy_version 27090 (0.0009) -[2023-10-10 21:48:52,529][98559] Updated weights for policy 0, policy_version 27100 (0.0007) -[2023-10-10 21:48:52,934][98560] Updated weights for policy 1, policy_version 27012 (0.0009) -[2023-10-10 21:48:53,326][98560] Updated weights for policy 1, policy_version 27022 (0.0010) -[2023-10-10 21:48:53,695][98560] Updated weights for policy 1, policy_version 27032 (0.0010) -[2023-10-10 21:48:55,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 55443456. Throughput: 0: 1687.8, 1: 1713.3. Samples: 13864750. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-10 21:48:55,557][97672] Avg episode reward: [(0, '-1.140'), (1, '22.300')] -[2023-10-10 21:48:56,612][98559] Updated weights for policy 0, policy_version 27110 (0.0008) -[2023-10-10 21:48:56,981][98559] Updated weights for policy 0, policy_version 27120 (0.0007) -[2023-10-10 21:48:57,337][98559] Updated weights for policy 0, policy_version 27130 (0.0009) -[2023-10-10 21:48:57,658][98560] Updated weights for policy 1, policy_version 27042 (0.0008) -[2023-10-10 21:48:58,020][98560] Updated weights for policy 1, policy_version 27052 (0.0010) -[2023-10-10 21:48:58,385][98560] Updated weights for policy 1, policy_version 27062 (0.0010) -[2023-10-10 21:48:58,752][98560] Updated weights for policy 1, policy_version 27072 (0.0007) -[2023-10-10 21:49:00,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 55508992. Throughput: 0: 1719.6, 1: 1681.4. Samples: 13884712. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-10 21:49:00,557][97672] Avg episode reward: [(0, '-1.140'), (1, '22.340')] -[2023-10-10 21:49:01,247][98559] Updated weights for policy 0, policy_version 27140 (0.0008) -[2023-10-10 21:49:01,616][98559] Updated weights for policy 0, policy_version 27150 (0.0007) -[2023-10-10 21:49:01,983][98559] Updated weights for policy 0, policy_version 27160 (0.0009) -[2023-10-10 21:49:02,712][98560] Updated weights for policy 1, policy_version 27082 (0.0009) -[2023-10-10 21:49:03,075][98560] Updated weights for policy 1, policy_version 27092 (0.0009) -[2023-10-10 21:49:03,451][98560] Updated weights for policy 1, policy_version 27102 (0.0009) -[2023-10-10 21:49:05,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 55574528. Throughput: 0: 1719.4, 1: 1689.3. Samples: 13905762. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:49:05,557][97672] Avg episode reward: [(0, '-1.140'), (1, '22.420')] -[2023-10-10 21:49:05,980][98559] Updated weights for policy 0, policy_version 27170 (0.0009) -[2023-10-10 21:49:06,345][98559] Updated weights for policy 0, policy_version 27180 (0.0008) -[2023-10-10 21:49:06,718][98559] Updated weights for policy 0, policy_version 27190 (0.0010) -[2023-10-10 21:49:07,085][98559] Updated weights for policy 0, policy_version 27200 (0.0008) -[2023-10-10 21:49:07,378][98560] Updated weights for policy 1, policy_version 27112 (0.0011) -[2023-10-10 21:49:07,750][98560] Updated weights for policy 1, policy_version 27122 (0.0008) -[2023-10-10 21:49:08,112][98560] Updated weights for policy 1, policy_version 27132 (0.0010) -[2023-10-10 21:49:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 55640064. Throughput: 0: 1708.0, 1: 1689.6. Samples: 13915724. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:49:10,557][97672] Avg episode reward: [(0, '-1.140'), (1, '22.440')] -[2023-10-10 21:49:11,179][98559] Updated weights for policy 0, policy_version 27210 (0.0007) -[2023-10-10 21:49:11,545][98559] Updated weights for policy 0, policy_version 27220 (0.0007) -[2023-10-10 21:49:11,912][98559] Updated weights for policy 0, policy_version 27230 (0.0007) -[2023-10-10 21:49:12,261][98560] Updated weights for policy 1, policy_version 27142 (0.0009) -[2023-10-10 21:49:12,634][98560] Updated weights for policy 1, policy_version 27152 (0.0008) -[2023-10-10 21:49:13,002][98560] Updated weights for policy 1, policy_version 27162 (0.0007) -[2023-10-10 21:49:15,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 55705600. Throughput: 0: 1719.9, 1: 1672.7. Samples: 13936026. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:49:15,557][97672] Avg episode reward: [(0, '-1.140'), (1, '22.480')] -[2023-10-10 21:49:15,834][98559] Updated weights for policy 0, policy_version 27240 (0.0008) -[2023-10-10 21:49:16,215][98559] Updated weights for policy 0, policy_version 27250 (0.0007) -[2023-10-10 21:49:16,577][98559] Updated weights for policy 0, policy_version 27260 (0.0007) -[2023-10-10 21:49:17,108][98560] Updated weights for policy 1, policy_version 27172 (0.0008) -[2023-10-10 21:49:17,483][98560] Updated weights for policy 1, policy_version 27182 (0.0010) -[2023-10-10 21:49:17,846][98560] Updated weights for policy 1, policy_version 27192 (0.0009) -[2023-10-10 21:49:20,454][98559] Updated weights for policy 0, policy_version 27270 (0.0010) -[2023-10-10 21:49:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 55771136. Throughput: 0: 1717.7, 1: 1694.4. Samples: 13957014. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:49:20,557][97672] Avg episode reward: [(0, '-1.240'), (1, '22.540')] -[2023-10-10 21:49:20,567][98439] Saving new best policy, reward=22.540! -[2023-10-10 21:49:20,832][98559] Updated weights for policy 0, policy_version 27280 (0.0010) -[2023-10-10 21:49:21,194][98559] Updated weights for policy 0, policy_version 27290 (0.0008) -[2023-10-10 21:49:22,042][98560] Updated weights for policy 1, policy_version 27202 (0.0008) -[2023-10-10 21:49:22,417][98560] Updated weights for policy 1, policy_version 27212 (0.0008) -[2023-10-10 21:49:22,777][98560] Updated weights for policy 1, policy_version 27222 (0.0008) -[2023-10-10 21:49:23,144][98560] Updated weights for policy 1, policy_version 27232 (0.0008) -[2023-10-10 21:49:25,133][98559] Updated weights for policy 0, policy_version 27300 (0.0012) -[2023-10-10 21:49:25,492][98559] Updated weights for policy 0, policy_version 27310 (0.0011) -[2023-10-10 21:49:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 55836672. Throughput: 0: 1721.9, 1: 1676.3. Samples: 13967096. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-10 21:49:25,556][97672] Avg episode reward: [(0, '-1.240'), (1, '22.500')] -[2023-10-10 21:49:25,859][98559] Updated weights for policy 0, policy_version 27320 (0.0011) -[2023-10-10 21:49:26,963][98560] Updated weights for policy 1, policy_version 27242 (0.0008) -[2023-10-10 21:49:27,336][98560] Updated weights for policy 1, policy_version 27252 (0.0007) -[2023-10-10 21:49:27,692][98560] Updated weights for policy 1, policy_version 27262 (0.0008) -[2023-10-10 21:49:29,912][98559] Updated weights for policy 0, policy_version 27330 (0.0010) -[2023-10-10 21:49:30,288][98559] Updated weights for policy 0, policy_version 27340 (0.0010) -[2023-10-10 21:49:30,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 55902208. Throughput: 0: 1723.1, 1: 1691.4. Samples: 13987872. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-10 21:49:30,557][97672] Avg episode reward: [(0, '-1.240'), (1, '22.520')] -[2023-10-10 21:49:30,654][98559] Updated weights for policy 0, policy_version 27350 (0.0008) -[2023-10-10 21:49:31,021][98559] Updated weights for policy 0, policy_version 27360 (0.0007) -[2023-10-10 21:49:31,552][98560] Updated weights for policy 1, policy_version 27272 (0.0008) -[2023-10-10 21:49:31,919][98560] Updated weights for policy 1, policy_version 27282 (0.0008) -[2023-10-10 21:49:32,283][98560] Updated weights for policy 1, policy_version 27292 (0.0008) -[2023-10-10 21:49:34,832][98559] Updated weights for policy 0, policy_version 27370 (0.0011) -[2023-10-10 21:49:35,199][98559] Updated weights for policy 0, policy_version 27380 (0.0011) -[2023-10-10 21:49:35,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 55967744. Throughput: 0: 1709.8, 1: 1708.7. Samples: 14008158. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-10 21:49:35,556][97672] Avg episode reward: [(0, '-1.240'), (1, '22.560')] -[2023-10-10 21:49:35,564][98439] Saving new best policy, reward=22.560! -[2023-10-10 21:49:35,565][98559] Updated weights for policy 0, policy_version 27390 (0.0008) -[2023-10-10 21:49:36,278][98560] Updated weights for policy 1, policy_version 27302 (0.0009) -[2023-10-10 21:49:36,652][98560] Updated weights for policy 1, policy_version 27312 (0.0009) -[2023-10-10 21:49:37,029][98560] Updated weights for policy 1, policy_version 27322 (0.0011) -[2023-10-10 21:49:39,566][98559] Updated weights for policy 0, policy_version 27400 (0.0011) -[2023-10-10 21:49:39,926][98559] Updated weights for policy 0, policy_version 27410 (0.0009) -[2023-10-10 21:49:40,297][98559] Updated weights for policy 0, policy_version 27420 (0.0009) -[2023-10-10 21:49:40,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 56066048. Throughput: 0: 1736.0, 1: 1682.3. Samples: 14018574. Policy #0 lag: (min: 31.0, avg: 32.3, max: 55.0) -[2023-10-10 21:49:40,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.520')] -[2023-10-10 21:49:41,233][98560] Updated weights for policy 1, policy_version 27332 (0.0008) -[2023-10-10 21:49:41,598][98560] Updated weights for policy 1, policy_version 27342 (0.0009) -[2023-10-10 21:49:41,962][98560] Updated weights for policy 1, policy_version 27352 (0.0007) -[2023-10-10 21:49:44,236][98559] Updated weights for policy 0, policy_version 27430 (0.0009) -[2023-10-10 21:49:44,610][98559] Updated weights for policy 0, policy_version 27440 (0.0011) -[2023-10-10 21:49:44,973][98559] Updated weights for policy 0, policy_version 27450 (0.0007) -[2023-10-10 21:49:45,556][97672] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 56131584. Throughput: 0: 1724.1, 1: 1708.1. Samples: 14039162. Policy #0 lag: (min: 31.0, avg: 32.3, max: 55.0) -[2023-10-10 21:49:45,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.460')] -[2023-10-10 21:49:45,875][98560] Updated weights for policy 1, policy_version 27362 (0.0007) -[2023-10-10 21:49:46,248][98560] Updated weights for policy 1, policy_version 27372 (0.0007) -[2023-10-10 21:49:46,617][98560] Updated weights for policy 1, policy_version 27382 (0.0010) -[2023-10-10 21:49:46,983][98560] Updated weights for policy 1, policy_version 27392 (0.0009) -[2023-10-10 21:49:48,989][98559] Updated weights for policy 0, policy_version 27460 (0.0010) -[2023-10-10 21:49:49,365][98559] Updated weights for policy 0, policy_version 27470 (0.0010) -[2023-10-10 21:49:49,739][98559] Updated weights for policy 0, policy_version 27480 (0.0008) -[2023-10-10 21:49:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 56197120. Throughput: 0: 1701.5, 1: 1713.7. Samples: 14059444. Policy #0 lag: (min: 31.0, avg: 32.3, max: 55.0) -[2023-10-10 21:49:50,557][97672] Avg episode reward: [(0, '-1.220'), (1, '22.440')] -[2023-10-10 21:49:50,957][98560] Updated weights for policy 1, policy_version 27402 (0.0007) -[2023-10-10 21:49:51,311][98560] Updated weights for policy 1, policy_version 27412 (0.0008) -[2023-10-10 21:49:51,678][98560] Updated weights for policy 1, policy_version 27422 (0.0009) -[2023-10-10 21:49:53,738][98559] Updated weights for policy 0, policy_version 27490 (0.0010) -[2023-10-10 21:49:54,094][98559] Updated weights for policy 0, policy_version 27500 (0.0007) -[2023-10-10 21:49:54,463][98559] Updated weights for policy 0, policy_version 27510 (0.0008) -[2023-10-10 21:49:54,837][98559] Updated weights for policy 0, policy_version 27520 (0.0010) -[2023-10-10 21:49:55,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 56262656. Throughput: 0: 1734.9, 1: 1698.1. Samples: 14070204. Policy #0 lag: (min: 31.0, avg: 32.3, max: 55.0) -[2023-10-10 21:49:55,556][97672] Avg episode reward: [(0, '-1.220'), (1, '22.420')] -[2023-10-10 21:49:55,811][98560] Updated weights for policy 1, policy_version 27432 (0.0008) -[2023-10-10 21:49:56,182][98560] Updated weights for policy 1, policy_version 27442 (0.0008) -[2023-10-10 21:49:56,541][98560] Updated weights for policy 1, policy_version 27452 (0.0007) -[2023-10-10 21:49:58,766][98559] Updated weights for policy 0, policy_version 27530 (0.0008) -[2023-10-10 21:49:59,131][98559] Updated weights for policy 0, policy_version 27540 (0.0008) -[2023-10-10 21:49:59,502][98559] Updated weights for policy 0, policy_version 27550 (0.0010) -[2023-10-10 21:50:00,520][98560] Updated weights for policy 1, policy_version 27462 (0.0008) -[2023-10-10 21:50:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 56328192. Throughput: 0: 1712.5, 1: 1715.4. Samples: 14090284. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:50:00,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.320')] -[2023-10-10 21:50:00,896][98560] Updated weights for policy 1, policy_version 27472 (0.0009) -[2023-10-10 21:50:01,262][98560] Updated weights for policy 1, policy_version 27482 (0.0009) -[2023-10-10 21:50:03,435][98559] Updated weights for policy 0, policy_version 27560 (0.0010) -[2023-10-10 21:50:03,798][98559] Updated weights for policy 0, policy_version 27570 (0.0009) -[2023-10-10 21:50:04,164][98559] Updated weights for policy 0, policy_version 27580 (0.0008) -[2023-10-10 21:50:05,043][98560] Updated weights for policy 1, policy_version 27492 (0.0009) -[2023-10-10 21:50:05,425][98560] Updated weights for policy 1, policy_version 27502 (0.0008) -[2023-10-10 21:50:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 56393728. Throughput: 0: 1702.1, 1: 1721.3. Samples: 14111066. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:50:05,557][97672] Avg episode reward: [(0, '-1.140'), (1, '22.280')] -[2023-10-10 21:50:05,783][98560] Updated weights for policy 1, policy_version 27512 (0.0008) -[2023-10-10 21:50:08,249][98559] Updated weights for policy 0, policy_version 27590 (0.0010) -[2023-10-10 21:50:08,620][98559] Updated weights for policy 0, policy_version 27600 (0.0009) -[2023-10-10 21:50:09,000][98559] Updated weights for policy 0, policy_version 27610 (0.0008) -[2023-10-10 21:50:09,813][98560] Updated weights for policy 1, policy_version 27522 (0.0008) -[2023-10-10 21:50:10,183][98560] Updated weights for policy 1, policy_version 27532 (0.0010) -[2023-10-10 21:50:10,549][98560] Updated weights for policy 1, policy_version 27542 (0.0009) -[2023-10-10 21:50:10,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 56459264. Throughput: 0: 1716.2, 1: 1706.9. Samples: 14121138. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:50:10,556][97672] Avg episode reward: [(0, '-1.140'), (1, '22.220')] -[2023-10-10 21:50:10,916][98560] Updated weights for policy 1, policy_version 27552 (0.0008) -[2023-10-10 21:50:13,016][98559] Updated weights for policy 0, policy_version 27620 (0.0009) -[2023-10-10 21:50:13,389][98559] Updated weights for policy 0, policy_version 27630 (0.0007) -[2023-10-10 21:50:13,755][98559] Updated weights for policy 0, policy_version 27640 (0.0007) -[2023-10-10 21:50:15,078][98560] Updated weights for policy 1, policy_version 27562 (0.0009) -[2023-10-10 21:50:15,454][98560] Updated weights for policy 1, policy_version 27572 (0.0010) -[2023-10-10 21:50:15,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 56524800. Throughput: 0: 1691.0, 1: 1713.9. Samples: 14141090. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:50:15,557][97672] Avg episode reward: [(0, '-1.140'), (1, '22.240')] -[2023-10-10 21:50:15,825][98560] Updated weights for policy 1, policy_version 27582 (0.0009) -[2023-10-10 21:50:17,785][98559] Updated weights for policy 0, policy_version 27650 (0.0008) -[2023-10-10 21:50:18,163][98559] Updated weights for policy 0, policy_version 27660 (0.0008) -[2023-10-10 21:50:18,527][98559] Updated weights for policy 0, policy_version 27670 (0.0008) -[2023-10-10 21:50:18,888][98559] Updated weights for policy 0, policy_version 27680 (0.0009) -[2023-10-10 21:50:19,854][98560] Updated weights for policy 1, policy_version 27592 (0.0008) -[2023-10-10 21:50:20,229][98560] Updated weights for policy 1, policy_version 27602 (0.0010) -[2023-10-10 21:50:20,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 56590336. Throughput: 0: 1704.7, 1: 1708.9. Samples: 14161774. Policy #0 lag: (min: 20.0, avg: 26.0, max: 52.0) -[2023-10-10 21:50:20,557][97672] Avg episode reward: [(0, '-1.140'), (1, '22.180')] -[2023-10-10 21:50:20,596][98560] Updated weights for policy 1, policy_version 27612 (0.0009) -[2023-10-10 21:50:22,850][98559] Updated weights for policy 0, policy_version 27690 (0.0008) -[2023-10-10 21:50:23,229][98559] Updated weights for policy 0, policy_version 27700 (0.0007) -[2023-10-10 21:50:23,592][98559] Updated weights for policy 0, policy_version 27710 (0.0007) -[2023-10-10 21:50:24,588][98560] Updated weights for policy 1, policy_version 27622 (0.0008) -[2023-10-10 21:50:24,953][98560] Updated weights for policy 1, policy_version 27632 (0.0008) -[2023-10-10 21:50:25,323][98560] Updated weights for policy 1, policy_version 27642 (0.0009) -[2023-10-10 21:50:25,556][97672] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 56688640. Throughput: 0: 1688.3, 1: 1712.0. Samples: 14171588. Policy #0 lag: (min: 20.0, avg: 26.0, max: 52.0) -[2023-10-10 21:50:25,557][97672] Avg episode reward: [(0, '-1.140'), (1, '22.140')] -[2023-10-10 21:50:27,721][98559] Updated weights for policy 0, policy_version 27720 (0.0008) -[2023-10-10 21:50:28,096][98559] Updated weights for policy 0, policy_version 27730 (0.0007) -[2023-10-10 21:50:28,463][98559] Updated weights for policy 0, policy_version 27740 (0.0008) -[2023-10-10 21:50:29,496][98560] Updated weights for policy 1, policy_version 27652 (0.0008) -[2023-10-10 21:50:29,897][98560] Updated weights for policy 1, policy_version 27662 (0.0009) -[2023-10-10 21:50:30,258][98560] Updated weights for policy 1, policy_version 27672 (0.0008) -[2023-10-10 21:50:30,556][97672] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 56754176. Throughput: 0: 1689.1, 1: 1715.0. Samples: 14192344. Policy #0 lag: (min: 20.0, avg: 26.0, max: 52.0) -[2023-10-10 21:50:30,556][97672] Avg episode reward: [(0, '-1.140'), (1, '22.240')] -[2023-10-10 21:50:32,281][98559] Updated weights for policy 0, policy_version 27750 (0.0007) -[2023-10-10 21:50:32,653][98559] Updated weights for policy 0, policy_version 27760 (0.0008) -[2023-10-10 21:50:33,020][98559] Updated weights for policy 0, policy_version 27770 (0.0009) -[2023-10-10 21:50:34,203][98560] Updated weights for policy 1, policy_version 27682 (0.0010) -[2023-10-10 21:50:34,565][98560] Updated weights for policy 1, policy_version 27692 (0.0008) -[2023-10-10 21:50:34,940][98560] Updated weights for policy 1, policy_version 27702 (0.0007) -[2023-10-10 21:50:35,308][98560] Updated weights for policy 1, policy_version 27712 (0.0007) -[2023-10-10 21:50:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 56819712. Throughput: 0: 1709.4, 1: 1692.0. Samples: 14212510. Policy #0 lag: (min: 20.0, avg: 26.0, max: 52.0) -[2023-10-10 21:50:35,557][97672] Avg episode reward: [(0, '-1.060'), (1, '22.280')] -[2023-10-10 21:50:35,569][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000027776_28442624.pth... -[2023-10-10 21:50:35,569][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000027712_28377088.pth... -[2023-10-10 21:50:35,608][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000026176_26804224.pth -[2023-10-10 21:50:35,610][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000026112_26738688.pth -[2023-10-10 21:50:35,613][98385] Saving new best policy, reward=-1.060! -[2023-10-10 21:50:37,072][98559] Updated weights for policy 0, policy_version 27780 (0.0009) -[2023-10-10 21:50:37,450][98559] Updated weights for policy 0, policy_version 27790 (0.0008) -[2023-10-10 21:50:37,823][98559] Updated weights for policy 0, policy_version 27800 (0.0010) -[2023-10-10 21:50:39,103][98560] Updated weights for policy 1, policy_version 27722 (0.0010) -[2023-10-10 21:50:39,472][98560] Updated weights for policy 1, policy_version 27732 (0.0010) -[2023-10-10 21:50:39,841][98560] Updated weights for policy 1, policy_version 27742 (0.0009) -[2023-10-10 21:50:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 56885248. Throughput: 0: 1673.5, 1: 1711.5. Samples: 14222528. Policy #0 lag: (min: 9.0, avg: 22.8, max: 41.0) -[2023-10-10 21:50:40,557][97672] Avg episode reward: [(0, '-1.060'), (1, '22.280')] -[2023-10-10 21:50:41,745][98559] Updated weights for policy 0, policy_version 27810 (0.0010) -[2023-10-10 21:50:42,108][98559] Updated weights for policy 0, policy_version 27820 (0.0010) -[2023-10-10 21:50:42,478][98559] Updated weights for policy 0, policy_version 27830 (0.0009) -[2023-10-10 21:50:42,841][98559] Updated weights for policy 0, policy_version 27840 (0.0008) -[2023-10-10 21:50:43,874][98560] Updated weights for policy 1, policy_version 27752 (0.0009) -[2023-10-10 21:50:44,240][98560] Updated weights for policy 1, policy_version 27762 (0.0009) -[2023-10-10 21:50:44,609][98560] Updated weights for policy 1, policy_version 27772 (0.0009) -[2023-10-10 21:50:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 56950784. Throughput: 0: 1695.1, 1: 1708.1. Samples: 14243428. Policy #0 lag: (min: 9.0, avg: 22.8, max: 41.0) -[2023-10-10 21:50:45,557][97672] Avg episode reward: [(0, '-1.060'), (1, '22.260')] -[2023-10-10 21:50:46,870][98559] Updated weights for policy 0, policy_version 27850 (0.0010) -[2023-10-10 21:50:47,231][98559] Updated weights for policy 0, policy_version 27860 (0.0010) -[2023-10-10 21:50:47,614][98559] Updated weights for policy 0, policy_version 27870 (0.0009) -[2023-10-10 21:50:48,593][98560] Updated weights for policy 1, policy_version 27782 (0.0007) -[2023-10-10 21:50:48,958][98560] Updated weights for policy 1, policy_version 27792 (0.0009) -[2023-10-10 21:50:49,331][98560] Updated weights for policy 1, policy_version 27802 (0.0010) -[2023-10-10 21:50:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 57016320. Throughput: 0: 1706.1, 1: 1678.8. Samples: 14263386. Policy #0 lag: (min: 9.0, avg: 22.8, max: 41.0) -[2023-10-10 21:50:50,557][97672] Avg episode reward: [(0, '-1.060'), (1, '22.340')] -[2023-10-10 21:50:51,663][98559] Updated weights for policy 0, policy_version 27880 (0.0008) -[2023-10-10 21:50:52,046][98559] Updated weights for policy 0, policy_version 27890 (0.0010) -[2023-10-10 21:50:52,412][98559] Updated weights for policy 0, policy_version 27900 (0.0007) -[2023-10-10 21:50:53,312][98560] Updated weights for policy 1, policy_version 27812 (0.0009) -[2023-10-10 21:50:53,676][98560] Updated weights for policy 1, policy_version 27822 (0.0009) -[2023-10-10 21:50:54,040][98560] Updated weights for policy 1, policy_version 27832 (0.0011) -[2023-10-10 21:50:55,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 57081856. Throughput: 0: 1684.1, 1: 1710.9. Samples: 14273914. Policy #0 lag: (min: 9.0, avg: 22.8, max: 41.0) -[2023-10-10 21:50:55,557][97672] Avg episode reward: [(0, '-1.060'), (1, '22.420')] -[2023-10-10 21:50:56,361][98559] Updated weights for policy 0, policy_version 27910 (0.0007) -[2023-10-10 21:50:56,718][98559] Updated weights for policy 0, policy_version 27920 (0.0007) -[2023-10-10 21:50:57,091][98559] Updated weights for policy 0, policy_version 27930 (0.0007) -[2023-10-10 21:50:58,149][98560] Updated weights for policy 1, policy_version 27842 (0.0009) -[2023-10-10 21:50:58,521][98560] Updated weights for policy 1, policy_version 27852 (0.0008) -[2023-10-10 21:50:58,894][98560] Updated weights for policy 1, policy_version 27862 (0.0007) -[2023-10-10 21:50:59,262][98560] Updated weights for policy 1, policy_version 27872 (0.0009) -[2023-10-10 21:51:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 57147392. Throughput: 0: 1719.1, 1: 1692.2. Samples: 14294596. Policy #0 lag: (min: 31.0, avg: 50.8, max: 63.0) -[2023-10-10 21:51:00,557][97672] Avg episode reward: [(0, '-1.060'), (1, '22.420')] -[2023-10-10 21:51:01,228][98559] Updated weights for policy 0, policy_version 27940 (0.0008) -[2023-10-10 21:51:01,585][98559] Updated weights for policy 0, policy_version 27950 (0.0010) -[2023-10-10 21:51:01,958][98559] Updated weights for policy 0, policy_version 27960 (0.0011) -[2023-10-10 21:51:03,185][98560] Updated weights for policy 1, policy_version 27882 (0.0011) -[2023-10-10 21:51:03,558][98560] Updated weights for policy 1, policy_version 27892 (0.0011) -[2023-10-10 21:51:03,930][98560] Updated weights for policy 1, policy_version 27902 (0.0008) -[2023-10-10 21:51:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 57212928. Throughput: 0: 1724.1, 1: 1681.9. Samples: 14315042. Policy #0 lag: (min: 31.0, avg: 50.8, max: 63.0) -[2023-10-10 21:51:05,556][97672] Avg episode reward: [(0, '-1.060'), (1, '22.400')] -[2023-10-10 21:51:05,681][98559] Updated weights for policy 0, policy_version 27970 (0.0009) -[2023-10-10 21:51:06,059][98559] Updated weights for policy 0, policy_version 27980 (0.0008) -[2023-10-10 21:51:06,427][98559] Updated weights for policy 0, policy_version 27990 (0.0007) -[2023-10-10 21:51:06,793][98559] Updated weights for policy 0, policy_version 28000 (0.0008) -[2023-10-10 21:51:08,053][98560] Updated weights for policy 1, policy_version 27912 (0.0008) -[2023-10-10 21:51:08,421][98560] Updated weights for policy 1, policy_version 27922 (0.0008) -[2023-10-10 21:51:08,793][98560] Updated weights for policy 1, policy_version 27932 (0.0007) -[2023-10-10 21:51:10,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 57278464. Throughput: 0: 1716.4, 1: 1705.8. Samples: 14325586. Policy #0 lag: (min: 31.0, avg: 50.8, max: 63.0) -[2023-10-10 21:51:10,558][97672] Avg episode reward: [(0, '-1.060'), (1, '22.360')] -[2023-10-10 21:51:10,839][98559] Updated weights for policy 0, policy_version 28010 (0.0007) -[2023-10-10 21:51:11,211][98559] Updated weights for policy 0, policy_version 28020 (0.0011) -[2023-10-10 21:51:11,591][98559] Updated weights for policy 0, policy_version 28030 (0.0010) -[2023-10-10 21:51:12,817][98560] Updated weights for policy 1, policy_version 27942 (0.0008) -[2023-10-10 21:51:13,192][98560] Updated weights for policy 1, policy_version 27952 (0.0008) -[2023-10-10 21:51:13,557][98560] Updated weights for policy 1, policy_version 27962 (0.0007) -[2023-10-10 21:51:15,462][98559] Updated weights for policy 0, policy_version 28040 (0.0008) -[2023-10-10 21:51:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 57344000. Throughput: 0: 1728.0, 1: 1678.8. Samples: 14345650. Policy #0 lag: (min: 31.0, avg: 50.8, max: 63.0) -[2023-10-10 21:51:15,557][97672] Avg episode reward: [(0, '-1.080'), (1, '22.360')] -[2023-10-10 21:51:15,827][98559] Updated weights for policy 0, policy_version 28050 (0.0008) -[2023-10-10 21:51:16,202][98559] Updated weights for policy 0, policy_version 28060 (0.0009) -[2023-10-10 21:51:17,650][98560] Updated weights for policy 1, policy_version 27972 (0.0008) -[2023-10-10 21:51:18,046][98560] Updated weights for policy 1, policy_version 27982 (0.0010) -[2023-10-10 21:51:18,414][98560] Updated weights for policy 1, policy_version 27992 (0.0010) -[2023-10-10 21:51:20,152][98559] Updated weights for policy 0, policy_version 28070 (0.0009) -[2023-10-10 21:51:20,508][98559] Updated weights for policy 0, policy_version 28080 (0.0008) -[2023-10-10 21:51:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 57409536. Throughput: 0: 1723.8, 1: 1691.1. Samples: 14366180. Policy #0 lag: (min: 31.0, avg: 50.8, max: 63.0) -[2023-10-10 21:51:20,557][97672] Avg episode reward: [(0, '-1.080'), (1, '22.420')] -[2023-10-10 21:51:20,877][98559] Updated weights for policy 0, policy_version 28090 (0.0009) -[2023-10-10 21:51:22,454][98560] Updated weights for policy 1, policy_version 28002 (0.0010) -[2023-10-10 21:51:22,827][98560] Updated weights for policy 1, policy_version 28012 (0.0008) -[2023-10-10 21:51:23,195][98560] Updated weights for policy 1, policy_version 28022 (0.0009) -[2023-10-10 21:51:23,562][98560] Updated weights for policy 1, policy_version 28032 (0.0007) -[2023-10-10 21:51:24,949][98559] Updated weights for policy 0, policy_version 28100 (0.0009) -[2023-10-10 21:51:25,314][98559] Updated weights for policy 0, policy_version 28110 (0.0009) -[2023-10-10 21:51:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 57475072. Throughput: 0: 1734.5, 1: 1692.2. Samples: 14376730. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-10 21:51:25,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.340')] -[2023-10-10 21:51:25,682][98559] Updated weights for policy 0, policy_version 28120 (0.0007) -[2023-10-10 21:51:27,444][98560] Updated weights for policy 1, policy_version 28042 (0.0009) -[2023-10-10 21:51:27,804][98560] Updated weights for policy 1, policy_version 28052 (0.0009) -[2023-10-10 21:51:28,183][98560] Updated weights for policy 1, policy_version 28062 (0.0008) -[2023-10-10 21:51:29,657][98559] Updated weights for policy 0, policy_version 28130 (0.0008) -[2023-10-10 21:51:30,019][98559] Updated weights for policy 0, policy_version 28140 (0.0008) -[2023-10-10 21:51:30,389][98559] Updated weights for policy 0, policy_version 28150 (0.0008) -[2023-10-10 21:51:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 57540608. Throughput: 0: 1734.8, 1: 1673.7. Samples: 14396810. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-10 21:51:30,557][97672] Avg episode reward: [(0, '-1.120'), (1, '22.360')] -[2023-10-10 21:51:30,761][98559] Updated weights for policy 0, policy_version 28160 (0.0008) -[2023-10-10 21:51:32,184][98560] Updated weights for policy 1, policy_version 28072 (0.0010) -[2023-10-10 21:51:32,553][98560] Updated weights for policy 1, policy_version 28082 (0.0011) -[2023-10-10 21:51:32,926][98560] Updated weights for policy 1, policy_version 28092 (0.0009) -[2023-10-10 21:51:34,508][98559] Updated weights for policy 0, policy_version 28170 (0.0008) -[2023-10-10 21:51:34,881][98559] Updated weights for policy 0, policy_version 28180 (0.0007) -[2023-10-10 21:51:35,254][98559] Updated weights for policy 0, policy_version 28190 (0.0007) -[2023-10-10 21:51:35,556][97672] Fps is (10 sec: 16383.6, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 57638912. Throughput: 0: 1712.6, 1: 1696.0. Samples: 14416774. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-10 21:51:35,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.420')] -[2023-10-10 21:51:37,062][98560] Updated weights for policy 1, policy_version 28102 (0.0010) -[2023-10-10 21:51:37,429][98560] Updated weights for policy 1, policy_version 28112 (0.0007) -[2023-10-10 21:51:37,803][98560] Updated weights for policy 1, policy_version 28122 (0.0007) -[2023-10-10 21:51:39,079][98559] Updated weights for policy 0, policy_version 28200 (0.0010) -[2023-10-10 21:51:39,440][98559] Updated weights for policy 0, policy_version 28210 (0.0010) -[2023-10-10 21:51:39,815][98559] Updated weights for policy 0, policy_version 28220 (0.0007) -[2023-10-10 21:51:40,556][97672] Fps is (10 sec: 16384.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 57704448. Throughput: 0: 1745.3, 1: 1673.9. Samples: 14427778. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-10 21:51:40,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.340')] -[2023-10-10 21:51:41,974][98560] Updated weights for policy 1, policy_version 28132 (0.0010) -[2023-10-10 21:51:42,342][98560] Updated weights for policy 1, policy_version 28142 (0.0010) -[2023-10-10 21:51:42,717][98560] Updated weights for policy 1, policy_version 28152 (0.0008) -[2023-10-10 21:51:43,721][98559] Updated weights for policy 0, policy_version 28230 (0.0010) -[2023-10-10 21:51:44,087][98559] Updated weights for policy 0, policy_version 28240 (0.0007) -[2023-10-10 21:51:44,461][98559] Updated weights for policy 0, policy_version 28250 (0.0008) -[2023-10-10 21:51:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 57769984. Throughput: 0: 1716.6, 1: 1683.0. Samples: 14447576. Policy #0 lag: (min: 26.0, avg: 29.8, max: 58.0) -[2023-10-10 21:51:45,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.360')] -[2023-10-10 21:51:46,722][98560] Updated weights for policy 1, policy_version 28162 (0.0008) -[2023-10-10 21:51:47,085][98560] Updated weights for policy 1, policy_version 28172 (0.0010) -[2023-10-10 21:51:47,447][98560] Updated weights for policy 1, policy_version 28182 (0.0010) -[2023-10-10 21:51:47,818][98560] Updated weights for policy 1, policy_version 28192 (0.0009) -[2023-10-10 21:51:48,449][98559] Updated weights for policy 0, policy_version 28260 (0.0009) -[2023-10-10 21:51:48,820][98559] Updated weights for policy 0, policy_version 28270 (0.0007) -[2023-10-10 21:51:49,183][98559] Updated weights for policy 0, policy_version 28280 (0.0009) -[2023-10-10 21:51:50,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 57835520. Throughput: 0: 1709.2, 1: 1696.0. Samples: 14468276. Policy #0 lag: (min: 26.0, avg: 29.8, max: 58.0) -[2023-10-10 21:51:50,556][97672] Avg episode reward: [(0, '-1.100'), (1, '22.360')] -[2023-10-10 21:51:51,972][98560] Updated weights for policy 1, policy_version 28202 (0.0007) -[2023-10-10 21:51:52,344][98560] Updated weights for policy 1, policy_version 28212 (0.0008) -[2023-10-10 21:51:52,708][98560] Updated weights for policy 1, policy_version 28222 (0.0007) -[2023-10-10 21:51:53,105][98559] Updated weights for policy 0, policy_version 28290 (0.0009) -[2023-10-10 21:51:53,477][98559] Updated weights for policy 0, policy_version 28300 (0.0008) -[2023-10-10 21:51:53,838][98559] Updated weights for policy 0, policy_version 28310 (0.0008) -[2023-10-10 21:51:54,204][98559] Updated weights for policy 0, policy_version 28320 (0.0008) -[2023-10-10 21:51:55,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 57901056. Throughput: 0: 1733.8, 1: 1669.7. Samples: 14478744. Policy #0 lag: (min: 26.0, avg: 29.8, max: 58.0) -[2023-10-10 21:51:55,556][97672] Avg episode reward: [(0, '-1.120'), (1, '22.360')] -[2023-10-10 21:51:56,729][98560] Updated weights for policy 1, policy_version 28232 (0.0010) -[2023-10-10 21:51:57,098][98560] Updated weights for policy 1, policy_version 28242 (0.0010) -[2023-10-10 21:51:57,462][98560] Updated weights for policy 1, policy_version 28252 (0.0007) -[2023-10-10 21:51:58,152][98559] Updated weights for policy 0, policy_version 28330 (0.0011) -[2023-10-10 21:51:58,512][98559] Updated weights for policy 0, policy_version 28340 (0.0010) -[2023-10-10 21:51:58,888][98559] Updated weights for policy 0, policy_version 28350 (0.0010) -[2023-10-10 21:52:00,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 57966592. Throughput: 0: 1704.4, 1: 1696.0. Samples: 14498666. Policy #0 lag: (min: 26.0, avg: 29.8, max: 58.0) -[2023-10-10 21:52:00,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.360')] -[2023-10-10 21:52:01,334][98560] Updated weights for policy 1, policy_version 28262 (0.0009) -[2023-10-10 21:52:01,701][98560] Updated weights for policy 1, policy_version 28272 (0.0008) -[2023-10-10 21:52:02,072][98560] Updated weights for policy 1, policy_version 28282 (0.0009) -[2023-10-10 21:52:02,897][98559] Updated weights for policy 0, policy_version 28360 (0.0010) -[2023-10-10 21:52:03,273][98559] Updated weights for policy 0, policy_version 28370 (0.0007) -[2023-10-10 21:52:03,651][98559] Updated weights for policy 0, policy_version 28380 (0.0008) -[2023-10-10 21:52:05,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 58032128. Throughput: 0: 1708.5, 1: 1708.0. Samples: 14519920. Policy #0 lag: (min: 26.0, avg: 29.8, max: 58.0) -[2023-10-10 21:52:05,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.340')] -[2023-10-10 21:52:06,220][98560] Updated weights for policy 1, policy_version 28292 (0.0008) -[2023-10-10 21:52:06,618][98560] Updated weights for policy 1, policy_version 28302 (0.0009) -[2023-10-10 21:52:06,978][98560] Updated weights for policy 1, policy_version 28312 (0.0009) -[2023-10-10 21:52:07,726][98559] Updated weights for policy 0, policy_version 28390 (0.0007) -[2023-10-10 21:52:08,099][98559] Updated weights for policy 0, policy_version 28400 (0.0009) -[2023-10-10 21:52:08,472][98559] Updated weights for policy 0, policy_version 28410 (0.0010) -[2023-10-10 21:52:10,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 58097664. Throughput: 0: 1712.2, 1: 1682.9. Samples: 14529508. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:52:10,556][97672] Avg episode reward: [(0, '-1.100'), (1, '22.320')] -[2023-10-10 21:52:10,873][98560] Updated weights for policy 1, policy_version 28322 (0.0008) -[2023-10-10 21:52:11,249][98560] Updated weights for policy 1, policy_version 28332 (0.0008) -[2023-10-10 21:52:11,622][98560] Updated weights for policy 1, policy_version 28342 (0.0007) -[2023-10-10 21:52:11,992][98560] Updated weights for policy 1, policy_version 28352 (0.0007) -[2023-10-10 21:52:12,649][98559] Updated weights for policy 0, policy_version 28420 (0.0010) -[2023-10-10 21:52:13,015][98559] Updated weights for policy 0, policy_version 28430 (0.0007) -[2023-10-10 21:52:13,379][98559] Updated weights for policy 0, policy_version 28440 (0.0007) -[2023-10-10 21:52:15,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 58163200. Throughput: 0: 1699.0, 1: 1706.9. Samples: 14550078. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:52:15,556][97672] Avg episode reward: [(0, '-1.100'), (1, '22.280')] -[2023-10-10 21:52:15,972][98560] Updated weights for policy 1, policy_version 28362 (0.0008) -[2023-10-10 21:52:16,339][98560] Updated weights for policy 1, policy_version 28372 (0.0007) -[2023-10-10 21:52:16,705][98560] Updated weights for policy 1, policy_version 28382 (0.0008) -[2023-10-10 21:52:17,391][98559] Updated weights for policy 0, policy_version 28450 (0.0008) -[2023-10-10 21:52:17,755][98559] Updated weights for policy 0, policy_version 28460 (0.0008) -[2023-10-10 21:52:18,121][98559] Updated weights for policy 0, policy_version 28470 (0.0010) -[2023-10-10 21:52:18,486][98559] Updated weights for policy 0, policy_version 28480 (0.0009) -[2023-10-10 21:52:20,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 58228736. Throughput: 0: 1718.1, 1: 1708.5. Samples: 14570966. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:52:20,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.240')] -[2023-10-10 21:52:20,737][98560] Updated weights for policy 1, policy_version 28392 (0.0009) -[2023-10-10 21:52:21,101][98560] Updated weights for policy 1, policy_version 28402 (0.0008) -[2023-10-10 21:52:21,472][98560] Updated weights for policy 1, policy_version 28412 (0.0009) -[2023-10-10 21:52:22,521][98559] Updated weights for policy 0, policy_version 28490 (0.0009) -[2023-10-10 21:52:22,890][98559] Updated weights for policy 0, policy_version 28500 (0.0007) -[2023-10-10 21:52:23,260][98559] Updated weights for policy 0, policy_version 28510 (0.0007) -[2023-10-10 21:52:25,431][98560] Updated weights for policy 1, policy_version 28422 (0.0010) -[2023-10-10 21:52:25,556][97672] Fps is (10 sec: 13106.7, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 58294272. Throughput: 0: 1689.2, 1: 1701.9. Samples: 14580378. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:52:25,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.100')] -[2023-10-10 21:52:25,788][98560] Updated weights for policy 1, policy_version 28432 (0.0009) -[2023-10-10 21:52:26,149][98560] Updated weights for policy 1, policy_version 28442 (0.0010) -[2023-10-10 21:52:27,375][98559] Updated weights for policy 0, policy_version 28520 (0.0010) -[2023-10-10 21:52:27,750][98559] Updated weights for policy 0, policy_version 28530 (0.0010) -[2023-10-10 21:52:28,119][98559] Updated weights for policy 0, policy_version 28540 (0.0008) -[2023-10-10 21:52:29,978][98560] Updated weights for policy 1, policy_version 28452 (0.0011) -[2023-10-10 21:52:30,335][98560] Updated weights for policy 1, policy_version 28462 (0.0009) -[2023-10-10 21:52:30,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 58359808. Throughput: 0: 1710.3, 1: 1708.3. Samples: 14601410. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:52:30,556][97672] Avg episode reward: [(0, '-1.100'), (1, '22.140')] -[2023-10-10 21:52:30,702][98560] Updated weights for policy 1, policy_version 28472 (0.0009) -[2023-10-10 21:52:32,005][98559] Updated weights for policy 0, policy_version 28550 (0.0008) -[2023-10-10 21:52:32,381][98559] Updated weights for policy 0, policy_version 28560 (0.0007) -[2023-10-10 21:52:32,748][98559] Updated weights for policy 0, policy_version 28570 (0.0007) -[2023-10-10 21:52:34,674][98560] Updated weights for policy 1, policy_version 28482 (0.0009) -[2023-10-10 21:52:35,051][98560] Updated weights for policy 1, policy_version 28492 (0.0009) -[2023-10-10 21:52:35,415][98560] Updated weights for policy 1, policy_version 28502 (0.0010) -[2023-10-10 21:52:35,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 58425344. Throughput: 0: 1716.3, 1: 1713.9. Samples: 14622632. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) -[2023-10-10 21:52:35,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.040')] -[2023-10-10 21:52:35,564][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000028576_29261824.pth... -[2023-10-10 21:52:35,595][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000026976_27623424.pth -[2023-10-10 21:52:35,771][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000028512_29196288.pth... -[2023-10-10 21:52:35,772][98560] Updated weights for policy 1, policy_version 28512 (0.0009) -[2023-10-10 21:52:35,800][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000026912_27557888.pth -[2023-10-10 21:52:36,751][98559] Updated weights for policy 0, policy_version 28580 (0.0007) -[2023-10-10 21:52:37,121][98559] Updated weights for policy 0, policy_version 28590 (0.0008) -[2023-10-10 21:52:37,497][98559] Updated weights for policy 0, policy_version 28600 (0.0010) -[2023-10-10 21:52:39,864][98560] Updated weights for policy 1, policy_version 28522 (0.0008) -[2023-10-10 21:52:40,230][98560] Updated weights for policy 1, policy_version 28532 (0.0008) -[2023-10-10 21:52:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 58490880. Throughput: 0: 1692.6, 1: 1715.6. Samples: 14632114. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) -[2023-10-10 21:52:40,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.040')] -[2023-10-10 21:52:40,598][98560] Updated weights for policy 1, policy_version 28542 (0.0008) -[2023-10-10 21:52:41,462][98559] Updated weights for policy 0, policy_version 28610 (0.0008) -[2023-10-10 21:52:41,830][98559] Updated weights for policy 0, policy_version 28620 (0.0008) -[2023-10-10 21:52:42,194][98559] Updated weights for policy 0, policy_version 28630 (0.0007) -[2023-10-10 21:52:42,566][98559] Updated weights for policy 0, policy_version 28640 (0.0007) -[2023-10-10 21:52:44,641][98560] Updated weights for policy 1, policy_version 28552 (0.0010) -[2023-10-10 21:52:45,004][98560] Updated weights for policy 1, policy_version 28562 (0.0010) -[2023-10-10 21:52:45,380][98560] Updated weights for policy 1, policy_version 28572 (0.0010) -[2023-10-10 21:52:45,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 58589184. Throughput: 0: 1718.3, 1: 1716.5. Samples: 14653234. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) -[2023-10-10 21:52:45,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.020')] -[2023-10-10 21:52:46,463][98559] Updated weights for policy 0, policy_version 28650 (0.0008) -[2023-10-10 21:52:46,847][98559] Updated weights for policy 0, policy_version 28660 (0.0007) -[2023-10-10 21:52:47,217][98559] Updated weights for policy 0, policy_version 28670 (0.0009) -[2023-10-10 21:52:49,397][98560] Updated weights for policy 1, policy_version 28582 (0.0008) -[2023-10-10 21:52:49,766][98560] Updated weights for policy 1, policy_version 28592 (0.0009) -[2023-10-10 21:52:50,129][98560] Updated weights for policy 1, policy_version 28602 (0.0008) -[2023-10-10 21:52:50,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 58654720. Throughput: 0: 1720.1, 1: 1700.7. Samples: 14673858. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) -[2023-10-10 21:52:50,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.020')] -[2023-10-10 21:52:51,208][98559] Updated weights for policy 0, policy_version 28680 (0.0009) -[2023-10-10 21:52:51,577][98559] Updated weights for policy 0, policy_version 28690 (0.0007) -[2023-10-10 21:52:51,953][98559] Updated weights for policy 0, policy_version 28700 (0.0007) -[2023-10-10 21:52:54,273][98560] Updated weights for policy 1, policy_version 28612 (0.0008) -[2023-10-10 21:52:54,672][98560] Updated weights for policy 1, policy_version 28622 (0.0009) -[2023-10-10 21:52:55,029][98560] Updated weights for policy 1, policy_version 28632 (0.0008) -[2023-10-10 21:52:55,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 58720256. Throughput: 0: 1705.7, 1: 1716.7. Samples: 14683518. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:52:55,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.000')] -[2023-10-10 21:52:55,733][98559] Updated weights for policy 0, policy_version 28710 (0.0007) -[2023-10-10 21:52:56,105][98559] Updated weights for policy 0, policy_version 28720 (0.0009) -[2023-10-10 21:52:56,479][98559] Updated weights for policy 0, policy_version 28730 (0.0007) -[2023-10-10 21:52:59,069][98560] Updated weights for policy 1, policy_version 28642 (0.0010) -[2023-10-10 21:52:59,435][98560] Updated weights for policy 1, policy_version 28652 (0.0009) -[2023-10-10 21:52:59,791][98560] Updated weights for policy 1, policy_version 28662 (0.0011) -[2023-10-10 21:53:00,163][98560] Updated weights for policy 1, policy_version 28672 (0.0010) -[2023-10-10 21:53:00,238][98559] Updated weights for policy 0, policy_version 28740 (0.0008) -[2023-10-10 21:53:00,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 58785792. Throughput: 0: 1720.9, 1: 1710.7. Samples: 14704500. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:53:00,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.020')] -[2023-10-10 21:53:00,608][98559] Updated weights for policy 0, policy_version 28750 (0.0008) -[2023-10-10 21:53:00,975][98559] Updated weights for policy 0, policy_version 28760 (0.0010) -[2023-10-10 21:53:04,072][98560] Updated weights for policy 1, policy_version 28682 (0.0008) -[2023-10-10 21:53:04,440][98560] Updated weights for policy 1, policy_version 28692 (0.0009) -[2023-10-10 21:53:04,811][98560] Updated weights for policy 1, policy_version 28702 (0.0008) -[2023-10-10 21:53:05,004][98559] Updated weights for policy 0, policy_version 28770 (0.0008) -[2023-10-10 21:53:05,379][98559] Updated weights for policy 0, policy_version 28780 (0.0007) -[2023-10-10 21:53:05,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 58851328. Throughput: 0: 1716.2, 1: 1689.0. Samples: 14724200. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:53:05,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.040')] -[2023-10-10 21:53:05,741][98559] Updated weights for policy 0, policy_version 28790 (0.0007) -[2023-10-10 21:53:06,110][98559] Updated weights for policy 0, policy_version 28800 (0.0009) -[2023-10-10 21:53:08,707][98560] Updated weights for policy 1, policy_version 28712 (0.0009) -[2023-10-10 21:53:09,086][98560] Updated weights for policy 1, policy_version 28722 (0.0009) -[2023-10-10 21:53:09,451][98560] Updated weights for policy 1, policy_version 28732 (0.0008) -[2023-10-10 21:53:10,040][98559] Updated weights for policy 0, policy_version 28810 (0.0007) -[2023-10-10 21:53:10,413][98559] Updated weights for policy 0, policy_version 28820 (0.0007) -[2023-10-10 21:53:10,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 58916864. Throughput: 0: 1725.6, 1: 1711.3. Samples: 14735040. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:53:10,556][97672] Avg episode reward: [(0, '-1.100'), (1, '22.040')] -[2023-10-10 21:53:10,777][98559] Updated weights for policy 0, policy_version 28830 (0.0009) -[2023-10-10 21:53:13,564][98560] Updated weights for policy 1, policy_version 28742 (0.0007) -[2023-10-10 21:53:13,924][98560] Updated weights for policy 1, policy_version 28752 (0.0007) -[2023-10-10 21:53:14,296][98560] Updated weights for policy 1, policy_version 28762 (0.0009) -[2023-10-10 21:53:14,673][98559] Updated weights for policy 0, policy_version 28840 (0.0008) -[2023-10-10 21:53:15,049][98559] Updated weights for policy 0, policy_version 28850 (0.0008) -[2023-10-10 21:53:15,421][98559] Updated weights for policy 0, policy_version 28860 (0.0007) -[2023-10-10 21:53:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 58982400. Throughput: 0: 1731.0, 1: 1701.5. Samples: 14755872. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:53:15,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.120')] -[2023-10-10 21:53:18,457][98560] Updated weights for policy 1, policy_version 28772 (0.0007) -[2023-10-10 21:53:18,823][98560] Updated weights for policy 1, policy_version 28782 (0.0008) -[2023-10-10 21:53:19,198][98560] Updated weights for policy 1, policy_version 28792 (0.0007) -[2023-10-10 21:53:19,344][98559] Updated weights for policy 0, policy_version 28870 (0.0010) -[2023-10-10 21:53:19,705][98559] Updated weights for policy 0, policy_version 28880 (0.0007) -[2023-10-10 21:53:20,082][98559] Updated weights for policy 0, policy_version 28890 (0.0007) -[2023-10-10 21:53:20,556][97672] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 59080704. Throughput: 0: 1702.4, 1: 1673.5. Samples: 14774544. Policy #0 lag: (min: 15.0, avg: 24.9, max: 47.0) -[2023-10-10 21:53:20,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.100')] -[2023-10-10 21:53:23,220][98560] Updated weights for policy 1, policy_version 28802 (0.0010) -[2023-10-10 21:53:23,585][98560] Updated weights for policy 1, policy_version 28812 (0.0010) -[2023-10-10 21:53:23,954][98559] Updated weights for policy 0, policy_version 28900 (0.0007) -[2023-10-10 21:53:23,962][98560] Updated weights for policy 1, policy_version 28822 (0.0010) -[2023-10-10 21:53:24,329][98559] Updated weights for policy 0, policy_version 28910 (0.0007) -[2023-10-10 21:53:24,329][98560] Updated weights for policy 1, policy_version 28832 (0.0007) -[2023-10-10 21:53:24,694][98559] Updated weights for policy 0, policy_version 28920 (0.0008) -[2023-10-10 21:53:25,556][97672] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 59146240. Throughput: 0: 1736.0, 1: 1703.8. Samples: 14786904. Policy #0 lag: (min: 15.0, avg: 24.9, max: 47.0) -[2023-10-10 21:53:25,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.180')] -[2023-10-10 21:53:28,359][98560] Updated weights for policy 1, policy_version 28842 (0.0007) -[2023-10-10 21:53:28,719][98560] Updated weights for policy 1, policy_version 28852 (0.0007) -[2023-10-10 21:53:28,765][98559] Updated weights for policy 0, policy_version 28930 (0.0009) -[2023-10-10 21:53:29,097][98560] Updated weights for policy 1, policy_version 28862 (0.0008) -[2023-10-10 21:53:29,141][98559] Updated weights for policy 0, policy_version 28940 (0.0008) -[2023-10-10 21:53:29,509][98559] Updated weights for policy 0, policy_version 28950 (0.0008) -[2023-10-10 21:53:29,873][98559] Updated weights for policy 0, policy_version 28960 (0.0009) -[2023-10-10 21:53:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 59211776. Throughput: 0: 1721.2, 1: 1688.9. Samples: 14806686. Policy #0 lag: (min: 15.0, avg: 24.9, max: 47.0) -[2023-10-10 21:53:30,557][97672] Avg episode reward: [(0, '-1.080'), (1, '22.180')] -[2023-10-10 21:53:33,056][98560] Updated weights for policy 1, policy_version 28872 (0.0007) -[2023-10-10 21:53:33,422][98560] Updated weights for policy 1, policy_version 28882 (0.0010) -[2023-10-10 21:53:33,797][98560] Updated weights for policy 1, policy_version 28892 (0.0007) -[2023-10-10 21:53:33,986][98559] Updated weights for policy 0, policy_version 28970 (0.0007) -[2023-10-10 21:53:34,350][98559] Updated weights for policy 0, policy_version 28980 (0.0009) -[2023-10-10 21:53:34,714][98559] Updated weights for policy 0, policy_version 28990 (0.0009) -[2023-10-10 21:53:35,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 59277312. Throughput: 0: 1701.3, 1: 1686.7. Samples: 14826318. Policy #0 lag: (min: 15.0, avg: 24.9, max: 47.0) -[2023-10-10 21:53:35,556][97672] Avg episode reward: [(0, '-1.080'), (1, '22.180')] -[2023-10-10 21:53:37,875][98560] Updated weights for policy 1, policy_version 28902 (0.0008) -[2023-10-10 21:53:38,241][98560] Updated weights for policy 1, policy_version 28912 (0.0009) -[2023-10-10 21:53:38,619][98560] Updated weights for policy 1, policy_version 28922 (0.0007) -[2023-10-10 21:53:38,885][98559] Updated weights for policy 0, policy_version 29000 (0.0009) -[2023-10-10 21:53:39,251][98559] Updated weights for policy 0, policy_version 29010 (0.0010) -[2023-10-10 21:53:39,624][98559] Updated weights for policy 0, policy_version 29020 (0.0009) -[2023-10-10 21:53:40,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 59342848. Throughput: 0: 1730.2, 1: 1701.3. Samples: 14837936. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:53:40,557][97672] Avg episode reward: [(0, '-1.080'), (1, '22.240')] -[2023-10-10 21:53:42,684][98560] Updated weights for policy 1, policy_version 28932 (0.0007) -[2023-10-10 21:53:43,049][98560] Updated weights for policy 1, policy_version 28942 (0.0008) -[2023-10-10 21:53:43,418][98560] Updated weights for policy 1, policy_version 28952 (0.0008) -[2023-10-10 21:53:43,611][98559] Updated weights for policy 0, policy_version 29030 (0.0008) -[2023-10-10 21:53:43,980][98559] Updated weights for policy 0, policy_version 29040 (0.0007) -[2023-10-10 21:53:44,356][98559] Updated weights for policy 0, policy_version 29050 (0.0008) -[2023-10-10 21:53:45,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 59408384. Throughput: 0: 1701.1, 1: 1679.0. Samples: 14856604. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:53:45,557][97672] Avg episode reward: [(0, '-1.080'), (1, '22.240')] -[2023-10-10 21:53:47,472][98560] Updated weights for policy 1, policy_version 28962 (0.0008) -[2023-10-10 21:53:47,840][98560] Updated weights for policy 1, policy_version 28972 (0.0008) -[2023-10-10 21:53:48,205][98560] Updated weights for policy 1, policy_version 28982 (0.0008) -[2023-10-10 21:53:48,457][98559] Updated weights for policy 0, policy_version 29060 (0.0009) -[2023-10-10 21:53:48,580][98560] Updated weights for policy 1, policy_version 28992 (0.0010) -[2023-10-10 21:53:48,832][98559] Updated weights for policy 0, policy_version 29070 (0.0010) -[2023-10-10 21:53:49,190][98559] Updated weights for policy 0, policy_version 29080 (0.0009) -[2023-10-10 21:53:50,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 59473920. Throughput: 0: 1701.4, 1: 1698.7. Samples: 14877204. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:53:50,558][97672] Avg episode reward: [(0, '-1.100'), (1, '22.260')] -[2023-10-10 21:53:52,560][98560] Updated weights for policy 1, policy_version 29002 (0.0008) -[2023-10-10 21:53:52,926][98560] Updated weights for policy 1, policy_version 29012 (0.0009) -[2023-10-10 21:53:53,095][98559] Updated weights for policy 0, policy_version 29090 (0.0009) -[2023-10-10 21:53:53,301][98560] Updated weights for policy 1, policy_version 29022 (0.0007) -[2023-10-10 21:53:53,452][98559] Updated weights for policy 0, policy_version 29100 (0.0009) -[2023-10-10 21:53:53,834][98559] Updated weights for policy 0, policy_version 29110 (0.0008) -[2023-10-10 21:53:54,201][98559] Updated weights for policy 0, policy_version 29120 (0.0011) -[2023-10-10 21:53:55,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 59539456. Throughput: 0: 1712.0, 1: 1690.8. Samples: 14888170. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:53:55,556][97672] Avg episode reward: [(0, '-1.100'), (1, '22.200')] -[2023-10-10 21:53:57,218][98560] Updated weights for policy 1, policy_version 29032 (0.0008) -[2023-10-10 21:53:57,584][98560] Updated weights for policy 1, policy_version 29042 (0.0007) -[2023-10-10 21:53:57,955][98560] Updated weights for policy 1, policy_version 29052 (0.0008) -[2023-10-10 21:53:58,247][98559] Updated weights for policy 0, policy_version 29130 (0.0008) -[2023-10-10 21:53:58,609][98559] Updated weights for policy 0, policy_version 29140 (0.0007) -[2023-10-10 21:53:58,978][98559] Updated weights for policy 0, policy_version 29150 (0.0007) -[2023-10-10 21:54:00,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 59604992. Throughput: 0: 1681.8, 1: 1686.6. Samples: 14907450. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:54:00,556][97672] Avg episode reward: [(0, '-1.120'), (1, '22.160')] -[2023-10-10 21:54:01,868][98560] Updated weights for policy 1, policy_version 29062 (0.0008) -[2023-10-10 21:54:02,237][98560] Updated weights for policy 1, policy_version 29072 (0.0010) -[2023-10-10 21:54:02,612][98560] Updated weights for policy 1, policy_version 29082 (0.0010) -[2023-10-10 21:54:03,032][98559] Updated weights for policy 0, policy_version 29160 (0.0010) -[2023-10-10 21:54:03,399][98559] Updated weights for policy 0, policy_version 29170 (0.0010) -[2023-10-10 21:54:03,764][98559] Updated weights for policy 0, policy_version 29180 (0.0009) -[2023-10-10 21:54:05,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 59670528. Throughput: 0: 1710.7, 1: 1707.8. Samples: 14928376. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:54:05,557][97672] Avg episode reward: [(0, '-1.120'), (1, '22.180')] -[2023-10-10 21:54:06,667][98560] Updated weights for policy 1, policy_version 29092 (0.0007) -[2023-10-10 21:54:07,034][98560] Updated weights for policy 1, policy_version 29102 (0.0008) -[2023-10-10 21:54:07,397][98560] Updated weights for policy 1, policy_version 29112 (0.0008) -[2023-10-10 21:54:07,742][98559] Updated weights for policy 0, policy_version 29190 (0.0009) -[2023-10-10 21:54:08,110][98559] Updated weights for policy 0, policy_version 29200 (0.0010) -[2023-10-10 21:54:08,479][98559] Updated weights for policy 0, policy_version 29210 (0.0008) -[2023-10-10 21:54:10,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 59736064. Throughput: 0: 1686.7, 1: 1677.6. Samples: 14938298. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:54:10,557][97672] Avg episode reward: [(0, '-1.080'), (1, '22.240')] -[2023-10-10 21:54:11,611][98560] Updated weights for policy 1, policy_version 29122 (0.0009) -[2023-10-10 21:54:11,977][98560] Updated weights for policy 1, policy_version 29132 (0.0008) -[2023-10-10 21:54:12,343][98560] Updated weights for policy 1, policy_version 29142 (0.0007) -[2023-10-10 21:54:12,406][98559] Updated weights for policy 0, policy_version 29220 (0.0007) -[2023-10-10 21:54:12,709][98560] Updated weights for policy 1, policy_version 29152 (0.0007) -[2023-10-10 21:54:12,770][98559] Updated weights for policy 0, policy_version 29230 (0.0008) -[2023-10-10 21:54:13,137][98559] Updated weights for policy 0, policy_version 29240 (0.0009) -[2023-10-10 21:54:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 59801600. Throughput: 0: 1692.3, 1: 1685.1. Samples: 14958668. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:54:15,556][97672] Avg episode reward: [(0, '-1.080'), (1, '22.240')] -[2023-10-10 21:54:16,620][98560] Updated weights for policy 1, policy_version 29162 (0.0010) -[2023-10-10 21:54:16,999][98560] Updated weights for policy 1, policy_version 29172 (0.0010) -[2023-10-10 21:54:17,088][98559] Updated weights for policy 0, policy_version 29250 (0.0008) -[2023-10-10 21:54:17,368][98560] Updated weights for policy 1, policy_version 29182 (0.0008) -[2023-10-10 21:54:17,459][98559] Updated weights for policy 0, policy_version 29260 (0.0008) -[2023-10-10 21:54:17,837][98559] Updated weights for policy 0, policy_version 29270 (0.0008) -[2023-10-10 21:54:18,213][98559] Updated weights for policy 0, policy_version 29280 (0.0007) -[2023-10-10 21:54:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 59867136. Throughput: 0: 1713.5, 1: 1695.2. Samples: 14979712. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:54:20,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.260')] -[2023-10-10 21:54:21,318][98560] Updated weights for policy 1, policy_version 29192 (0.0008) -[2023-10-10 21:54:21,698][98560] Updated weights for policy 1, policy_version 29202 (0.0008) -[2023-10-10 21:54:22,055][98560] Updated weights for policy 1, policy_version 29212 (0.0008) -[2023-10-10 21:54:22,078][98559] Updated weights for policy 0, policy_version 29290 (0.0008) -[2023-10-10 21:54:22,453][98559] Updated weights for policy 0, policy_version 29300 (0.0010) -[2023-10-10 21:54:22,823][98559] Updated weights for policy 0, policy_version 29310 (0.0010) -[2023-10-10 21:54:25,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 59932672. Throughput: 0: 1687.6, 1: 1666.9. Samples: 14988884. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:54:25,556][97672] Avg episode reward: [(0, '-1.100'), (1, '22.240')] -[2023-10-10 21:54:26,121][98560] Updated weights for policy 1, policy_version 29222 (0.0010) -[2023-10-10 21:54:26,491][98560] Updated weights for policy 1, policy_version 29232 (0.0010) -[2023-10-10 21:54:26,788][98559] Updated weights for policy 0, policy_version 29320 (0.0008) -[2023-10-10 21:54:26,863][98560] Updated weights for policy 1, policy_version 29242 (0.0008) -[2023-10-10 21:54:27,145][98559] Updated weights for policy 0, policy_version 29330 (0.0009) -[2023-10-10 21:54:27,513][98559] Updated weights for policy 0, policy_version 29340 (0.0009) -[2023-10-10 21:54:30,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 59998208. Throughput: 0: 1717.6, 1: 1694.1. Samples: 15010130. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 21:54:30,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.280')] -[2023-10-10 21:54:31,122][98560] Updated weights for policy 1, policy_version 29252 (0.0009) -[2023-10-10 21:54:31,527][98559] Updated weights for policy 0, policy_version 29350 (0.0008) -[2023-10-10 21:54:31,527][98560] Updated weights for policy 1, policy_version 29262 (0.0009) -[2023-10-10 21:54:31,893][98559] Updated weights for policy 0, policy_version 29360 (0.0009) -[2023-10-10 21:54:31,898][98560] Updated weights for policy 1, policy_version 29272 (0.0010) -[2023-10-10 21:54:32,261][98559] Updated weights for policy 0, policy_version 29370 (0.0007) -[2023-10-10 21:54:35,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 60063744. Throughput: 0: 1725.8, 1: 1690.8. Samples: 15030948. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 21:54:35,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.320')] -[2023-10-10 21:54:35,570][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000029280_29982720.pth... -[2023-10-10 21:54:35,570][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000029376_30081024.pth... -[2023-10-10 21:54:35,609][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000027712_28377088.pth -[2023-10-10 21:54:35,612][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000027776_28442624.pth -[2023-10-10 21:54:35,858][98560] Updated weights for policy 1, policy_version 29282 (0.0010) -[2023-10-10 21:54:36,228][98560] Updated weights for policy 1, policy_version 29292 (0.0009) -[2023-10-10 21:54:36,299][98559] Updated weights for policy 0, policy_version 29380 (0.0007) -[2023-10-10 21:54:36,596][98560] Updated weights for policy 1, policy_version 29302 (0.0007) -[2023-10-10 21:54:36,657][98559] Updated weights for policy 0, policy_version 29390 (0.0008) -[2023-10-10 21:54:36,950][98560] Updated weights for policy 1, policy_version 29312 (0.0009) -[2023-10-10 21:54:37,019][98559] Updated weights for policy 0, policy_version 29400 (0.0008) -[2023-10-10 21:54:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 60129280. Throughput: 0: 1700.6, 1: 1674.6. Samples: 15040054. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 21:54:40,556][97672] Avg episode reward: [(0, '-1.100'), (1, '22.300')] -[2023-10-10 21:54:40,999][98559] Updated weights for policy 0, policy_version 29410 (0.0009) -[2023-10-10 21:54:41,030][98560] Updated weights for policy 1, policy_version 29322 (0.0008) -[2023-10-10 21:54:41,362][98559] Updated weights for policy 0, policy_version 29420 (0.0007) -[2023-10-10 21:54:41,388][98560] Updated weights for policy 1, policy_version 29332 (0.0007) -[2023-10-10 21:54:41,730][98559] Updated weights for policy 0, policy_version 29430 (0.0008) -[2023-10-10 21:54:41,758][98560] Updated weights for policy 1, policy_version 29342 (0.0007) -[2023-10-10 21:54:42,092][98559] Updated weights for policy 0, policy_version 29440 (0.0009) -[2023-10-10 21:54:45,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 60194816. Throughput: 0: 1723.1, 1: 1691.7. Samples: 15061118. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 21:54:45,556][97672] Avg episode reward: [(0, '-1.100'), (1, '22.420')] -[2023-10-10 21:54:45,867][98560] Updated weights for policy 1, policy_version 29352 (0.0007) -[2023-10-10 21:54:46,234][98560] Updated weights for policy 1, policy_version 29362 (0.0007) -[2023-10-10 21:54:46,247][98559] Updated weights for policy 0, policy_version 29450 (0.0008) -[2023-10-10 21:54:46,609][98560] Updated weights for policy 1, policy_version 29372 (0.0009) -[2023-10-10 21:54:46,609][98559] Updated weights for policy 0, policy_version 29460 (0.0008) -[2023-10-10 21:54:46,985][98559] Updated weights for policy 0, policy_version 29470 (0.0007) -[2023-10-10 21:54:50,509][98560] Updated weights for policy 1, policy_version 29382 (0.0009) -[2023-10-10 21:54:50,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 60260352. Throughput: 0: 1723.5, 1: 1693.2. Samples: 15082128. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 21:54:50,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.440')] -[2023-10-10 21:54:50,882][98560] Updated weights for policy 1, policy_version 29392 (0.0009) -[2023-10-10 21:54:51,115][98559] Updated weights for policy 0, policy_version 29480 (0.0007) -[2023-10-10 21:54:51,250][98560] Updated weights for policy 1, policy_version 29402 (0.0009) -[2023-10-10 21:54:51,476][98559] Updated weights for policy 0, policy_version 29490 (0.0007) -[2023-10-10 21:54:51,851][98559] Updated weights for policy 0, policy_version 29500 (0.0008) -[2023-10-10 21:54:55,208][98560] Updated weights for policy 1, policy_version 29412 (0.0008) -[2023-10-10 21:54:55,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 60325888. Throughput: 0: 1711.5, 1: 1687.8. Samples: 15091264. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-10 21:54:55,557][97672] Avg episode reward: [(0, '-1.120'), (1, '22.500')] -[2023-10-10 21:54:55,576][98560] Updated weights for policy 1, policy_version 29422 (0.0007) -[2023-10-10 21:54:55,765][98559] Updated weights for policy 0, policy_version 29510 (0.0007) -[2023-10-10 21:54:55,938][98560] Updated weights for policy 1, policy_version 29432 (0.0007) -[2023-10-10 21:54:56,122][98559] Updated weights for policy 0, policy_version 29520 (0.0007) -[2023-10-10 21:54:56,493][98559] Updated weights for policy 0, policy_version 29530 (0.0009) -[2023-10-10 21:54:59,939][98560] Updated weights for policy 1, policy_version 29442 (0.0008) -[2023-10-10 21:55:00,313][98560] Updated weights for policy 1, policy_version 29452 (0.0008) -[2023-10-10 21:55:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 60391424. Throughput: 0: 1717.5, 1: 1695.1. Samples: 15112236. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-10 21:55:00,557][97672] Avg episode reward: [(0, '-1.120'), (1, '22.500')] -[2023-10-10 21:55:00,609][98559] Updated weights for policy 0, policy_version 29540 (0.0007) -[2023-10-10 21:55:00,673][98560] Updated weights for policy 1, policy_version 29462 (0.0007) -[2023-10-10 21:55:00,979][98559] Updated weights for policy 0, policy_version 29550 (0.0008) -[2023-10-10 21:55:01,042][98560] Updated weights for policy 1, policy_version 29472 (0.0009) -[2023-10-10 21:55:01,357][98559] Updated weights for policy 0, policy_version 29560 (0.0008) -[2023-10-10 21:55:05,084][98560] Updated weights for policy 1, policy_version 29482 (0.0007) -[2023-10-10 21:55:05,223][98559] Updated weights for policy 0, policy_version 29570 (0.0007) -[2023-10-10 21:55:05,453][98560] Updated weights for policy 1, policy_version 29492 (0.0009) -[2023-10-10 21:55:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 60456960. Throughput: 0: 1708.1, 1: 1693.1. Samples: 15132766. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-10 21:55:05,557][97672] Avg episode reward: [(0, '-1.120'), (1, '22.500')] -[2023-10-10 21:55:05,586][98559] Updated weights for policy 0, policy_version 29580 (0.0007) -[2023-10-10 21:55:05,818][98560] Updated weights for policy 1, policy_version 29502 (0.0008) -[2023-10-10 21:55:05,961][98559] Updated weights for policy 0, policy_version 29590 (0.0008) -[2023-10-10 21:55:06,325][98559] Updated weights for policy 0, policy_version 29600 (0.0008) -[2023-10-10 21:55:09,926][98560] Updated weights for policy 1, policy_version 29512 (0.0008) -[2023-10-10 21:55:10,255][98559] Updated weights for policy 0, policy_version 29610 (0.0008) -[2023-10-10 21:55:10,294][98560] Updated weights for policy 1, policy_version 29522 (0.0009) -[2023-10-10 21:55:10,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 60522496. Throughput: 0: 1714.4, 1: 1695.6. Samples: 15142336. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-10 21:55:10,556][97672] Avg episode reward: [(0, '-1.120'), (1, '22.520')] -[2023-10-10 21:55:10,627][98559] Updated weights for policy 0, policy_version 29620 (0.0009) -[2023-10-10 21:55:10,657][98560] Updated weights for policy 1, policy_version 29532 (0.0010) -[2023-10-10 21:55:10,992][98559] Updated weights for policy 0, policy_version 29630 (0.0007) -[2023-10-10 21:55:14,734][98560] Updated weights for policy 1, policy_version 29542 (0.0010) -[2023-10-10 21:55:14,980][98559] Updated weights for policy 0, policy_version 29640 (0.0008) -[2023-10-10 21:55:15,100][98560] Updated weights for policy 1, policy_version 29552 (0.0009) -[2023-10-10 21:55:15,344][98559] Updated weights for policy 0, policy_version 29650 (0.0007) -[2023-10-10 21:55:15,461][98560] Updated weights for policy 1, policy_version 29562 (0.0008) -[2023-10-10 21:55:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 60588032. Throughput: 0: 1708.1, 1: 1689.6. Samples: 15163028. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-10 21:55:15,557][97672] Avg episode reward: [(0, '-1.120'), (1, '22.500')] -[2023-10-10 21:55:15,716][98559] Updated weights for policy 0, policy_version 29660 (0.0007) -[2023-10-10 21:55:19,553][98560] Updated weights for policy 1, policy_version 29572 (0.0009) -[2023-10-10 21:55:19,576][98559] Updated weights for policy 0, policy_version 29670 (0.0007) -[2023-10-10 21:55:19,942][98559] Updated weights for policy 0, policy_version 29680 (0.0009) -[2023-10-10 21:55:19,957][98560] Updated weights for policy 1, policy_version 29582 (0.0008) -[2023-10-10 21:55:20,316][98559] Updated weights for policy 0, policy_version 29690 (0.0008) -[2023-10-10 21:55:20,317][98560] Updated weights for policy 1, policy_version 29592 (0.0008) -[2023-10-10 21:55:20,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 60686336. Throughput: 0: 1685.2, 1: 1688.2. Samples: 15182752. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:55:20,556][97672] Avg episode reward: [(0, '-1.120'), (1, '22.460')] -[2023-10-10 21:55:24,295][98559] Updated weights for policy 0, policy_version 29700 (0.0007) -[2023-10-10 21:55:24,492][98560] Updated weights for policy 1, policy_version 29602 (0.0009) -[2023-10-10 21:55:24,659][98559] Updated weights for policy 0, policy_version 29710 (0.0007) -[2023-10-10 21:55:24,850][98560] Updated weights for policy 1, policy_version 29612 (0.0009) -[2023-10-10 21:55:25,016][98559] Updated weights for policy 0, policy_version 29720 (0.0007) -[2023-10-10 21:55:25,225][98560] Updated weights for policy 1, policy_version 29622 (0.0009) -[2023-10-10 21:55:25,556][97672] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 60751872. Throughput: 0: 1710.3, 1: 1689.6. Samples: 15193052. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:55:25,557][97672] Avg episode reward: [(0, '-1.120'), (1, '22.420')] -[2023-10-10 21:55:25,583][98560] Updated weights for policy 1, policy_version 29632 (0.0009) -[2023-10-10 21:55:29,146][98559] Updated weights for policy 0, policy_version 29730 (0.0008) -[2023-10-10 21:55:29,519][98559] Updated weights for policy 0, policy_version 29740 (0.0008) -[2023-10-10 21:55:29,784][98560] Updated weights for policy 1, policy_version 29642 (0.0009) -[2023-10-10 21:55:29,884][98559] Updated weights for policy 0, policy_version 29750 (0.0008) -[2023-10-10 21:55:30,145][98560] Updated weights for policy 1, policy_version 29652 (0.0008) -[2023-10-10 21:55:30,254][98559] Updated weights for policy 0, policy_version 29760 (0.0008) -[2023-10-10 21:55:30,515][98560] Updated weights for policy 1, policy_version 29662 (0.0009) -[2023-10-10 21:55:30,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 60817408. Throughput: 0: 1704.5, 1: 1686.0. Samples: 15213692. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:55:30,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.440')] -[2023-10-10 21:55:34,310][98559] Updated weights for policy 0, policy_version 29770 (0.0007) -[2023-10-10 21:55:34,580][98560] Updated weights for policy 1, policy_version 29672 (0.0008) -[2023-10-10 21:55:34,681][98559] Updated weights for policy 0, policy_version 29780 (0.0009) -[2023-10-10 21:55:34,937][98560] Updated weights for policy 1, policy_version 29682 (0.0007) -[2023-10-10 21:55:35,046][98559] Updated weights for policy 0, policy_version 29790 (0.0008) -[2023-10-10 21:55:35,306][98560] Updated weights for policy 1, policy_version 29692 (0.0007) -[2023-10-10 21:55:35,556][97672] Fps is (10 sec: 16383.4, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 60915712. Throughput: 0: 1678.7, 1: 1674.6. Samples: 15233026. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:55:35,558][97672] Avg episode reward: [(0, '-1.100'), (1, '22.420')] -[2023-10-10 21:55:39,047][98559] Updated weights for policy 0, policy_version 29800 (0.0008) -[2023-10-10 21:55:39,228][98560] Updated weights for policy 1, policy_version 29702 (0.0008) -[2023-10-10 21:55:39,425][98559] Updated weights for policy 0, policy_version 29810 (0.0009) -[2023-10-10 21:55:39,598][98560] Updated weights for policy 1, policy_version 29712 (0.0008) -[2023-10-10 21:55:39,784][98559] Updated weights for policy 0, policy_version 29820 (0.0009) -[2023-10-10 21:55:39,961][98560] Updated weights for policy 1, policy_version 29722 (0.0008) -[2023-10-10 21:55:40,556][97672] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 60981248. Throughput: 0: 1708.9, 1: 1688.6. Samples: 15244152. Policy #0 lag: (min: 1.0, avg: 8.8, max: 33.0) -[2023-10-10 21:55:40,557][97672] Avg episode reward: [(0, '-1.140'), (1, '22.360')] -[2023-10-10 21:55:43,832][98559] Updated weights for policy 0, policy_version 29830 (0.0008) -[2023-10-10 21:55:44,070][98560] Updated weights for policy 1, policy_version 29732 (0.0010) -[2023-10-10 21:55:44,216][98559] Updated weights for policy 0, policy_version 29840 (0.0009) -[2023-10-10 21:55:44,436][98560] Updated weights for policy 1, policy_version 29742 (0.0008) -[2023-10-10 21:55:44,579][98559] Updated weights for policy 0, policy_version 29850 (0.0008) -[2023-10-10 21:55:44,809][98560] Updated weights for policy 1, policy_version 29752 (0.0008) -[2023-10-10 21:55:45,556][97672] Fps is (10 sec: 13107.6, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 61046784. Throughput: 0: 1691.0, 1: 1686.3. Samples: 15264212. Policy #0 lag: (min: 1.0, avg: 8.8, max: 33.0) -[2023-10-10 21:55:45,557][97672] Avg episode reward: [(0, '-1.140'), (1, '22.320')] -[2023-10-10 21:55:48,502][98559] Updated weights for policy 0, policy_version 29860 (0.0008) -[2023-10-10 21:55:48,796][98560] Updated weights for policy 1, policy_version 29762 (0.0008) -[2023-10-10 21:55:48,873][98559] Updated weights for policy 0, policy_version 29870 (0.0010) -[2023-10-10 21:55:49,159][98560] Updated weights for policy 1, policy_version 29772 (0.0009) -[2023-10-10 21:55:49,232][98559] Updated weights for policy 0, policy_version 29880 (0.0009) -[2023-10-10 21:55:49,537][98560] Updated weights for policy 1, policy_version 29782 (0.0009) -[2023-10-10 21:55:49,901][98560] Updated weights for policy 1, policy_version 29792 (0.0010) -[2023-10-10 21:55:50,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 61112320. Throughput: 0: 1684.7, 1: 1668.4. Samples: 15283656. Policy #0 lag: (min: 1.0, avg: 8.8, max: 33.0) -[2023-10-10 21:55:50,556][97672] Avg episode reward: [(0, '-1.140'), (1, '22.340')] -[2023-10-10 21:55:53,203][98559] Updated weights for policy 0, policy_version 29890 (0.0007) -[2023-10-10 21:55:53,566][98559] Updated weights for policy 0, policy_version 29900 (0.0010) -[2023-10-10 21:55:53,842][98560] Updated weights for policy 1, policy_version 29802 (0.0007) -[2023-10-10 21:55:53,936][98559] Updated weights for policy 0, policy_version 29910 (0.0009) -[2023-10-10 21:55:54,210][98560] Updated weights for policy 1, policy_version 29812 (0.0009) -[2023-10-10 21:55:54,302][98559] Updated weights for policy 0, policy_version 29920 (0.0009) -[2023-10-10 21:55:54,568][98560] Updated weights for policy 1, policy_version 29822 (0.0010) -[2023-10-10 21:55:55,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 61177856. Throughput: 0: 1701.3, 1: 1693.1. Samples: 15295084. Policy #0 lag: (min: 1.0, avg: 8.8, max: 33.0) -[2023-10-10 21:55:55,557][97672] Avg episode reward: [(0, '-1.120'), (1, '22.320')] -[2023-10-10 21:55:58,428][98559] Updated weights for policy 0, policy_version 29930 (0.0008) -[2023-10-10 21:55:58,706][98560] Updated weights for policy 1, policy_version 29832 (0.0009) -[2023-10-10 21:55:58,793][98559] Updated weights for policy 0, policy_version 29940 (0.0008) -[2023-10-10 21:55:59,068][98560] Updated weights for policy 1, policy_version 29842 (0.0008) -[2023-10-10 21:55:59,158][98559] Updated weights for policy 0, policy_version 29950 (0.0007) -[2023-10-10 21:55:59,430][98560] Updated weights for policy 1, policy_version 29852 (0.0008) -[2023-10-10 21:56:00,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 61243392. Throughput: 0: 1679.7, 1: 1688.1. Samples: 15314580. Policy #0 lag: (min: 1.0, avg: 8.8, max: 33.0) -[2023-10-10 21:56:00,557][97672] Avg episode reward: [(0, '-1.120'), (1, '22.360')] -[2023-10-10 21:56:03,042][98559] Updated weights for policy 0, policy_version 29960 (0.0007) -[2023-10-10 21:56:03,394][98560] Updated weights for policy 1, policy_version 29862 (0.0007) -[2023-10-10 21:56:03,420][98559] Updated weights for policy 0, policy_version 29970 (0.0007) -[2023-10-10 21:56:03,764][98560] Updated weights for policy 1, policy_version 29872 (0.0009) -[2023-10-10 21:56:03,778][98559] Updated weights for policy 0, policy_version 29980 (0.0007) -[2023-10-10 21:56:04,136][98560] Updated weights for policy 1, policy_version 29882 (0.0007) -[2023-10-10 21:56:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 61308928. Throughput: 0: 1709.4, 1: 1677.5. Samples: 15335166. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-10 21:56:05,557][97672] Avg episode reward: [(0, '-1.120'), (1, '22.400')] -[2023-10-10 21:56:07,821][98559] Updated weights for policy 0, policy_version 29990 (0.0007) -[2023-10-10 21:56:08,143][98560] Updated weights for policy 1, policy_version 29892 (0.0007) -[2023-10-10 21:56:08,191][98559] Updated weights for policy 0, policy_version 30000 (0.0007) -[2023-10-10 21:56:08,540][98560] Updated weights for policy 1, policy_version 29902 (0.0009) -[2023-10-10 21:56:08,559][98559] Updated weights for policy 0, policy_version 30010 (0.0007) -[2023-10-10 21:56:08,906][98560] Updated weights for policy 1, policy_version 29912 (0.0008) -[2023-10-10 21:56:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 61374464. Throughput: 0: 1698.1, 1: 1707.1. Samples: 15346284. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-10 21:56:10,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.460')] -[2023-10-10 21:56:12,442][98559] Updated weights for policy 0, policy_version 30020 (0.0009) -[2023-10-10 21:56:12,800][98559] Updated weights for policy 0, policy_version 30030 (0.0010) -[2023-10-10 21:56:12,849][98560] Updated weights for policy 1, policy_version 29922 (0.0009) -[2023-10-10 21:56:13,174][98559] Updated weights for policy 0, policy_version 30040 (0.0007) -[2023-10-10 21:56:13,204][98560] Updated weights for policy 1, policy_version 29932 (0.0008) -[2023-10-10 21:56:13,574][98560] Updated weights for policy 1, policy_version 29942 (0.0009) -[2023-10-10 21:56:13,935][98560] Updated weights for policy 1, policy_version 29952 (0.0008) -[2023-10-10 21:56:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 61440000. Throughput: 0: 1694.5, 1: 1687.5. Samples: 15365882. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-10 21:56:15,557][97672] Avg episode reward: [(0, '-1.240'), (1, '22.440')] -[2023-10-10 21:56:17,191][98559] Updated weights for policy 0, policy_version 30050 (0.0008) -[2023-10-10 21:56:17,559][98559] Updated weights for policy 0, policy_version 30060 (0.0009) -[2023-10-10 21:56:17,922][98559] Updated weights for policy 0, policy_version 30070 (0.0007) -[2023-10-10 21:56:18,030][98560] Updated weights for policy 1, policy_version 29962 (0.0010) -[2023-10-10 21:56:18,286][98559] Updated weights for policy 0, policy_version 30080 (0.0008) -[2023-10-10 21:56:18,402][98560] Updated weights for policy 1, policy_version 29972 (0.0008) -[2023-10-10 21:56:18,784][98560] Updated weights for policy 1, policy_version 29982 (0.0007) -[2023-10-10 21:56:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 61505536. Throughput: 0: 1718.4, 1: 1690.8. Samples: 15386440. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-10 21:56:20,556][97672] Avg episode reward: [(0, '-1.240'), (1, '22.440')] -[2023-10-10 21:56:22,410][98559] Updated weights for policy 0, policy_version 30090 (0.0009) -[2023-10-10 21:56:22,768][98559] Updated weights for policy 0, policy_version 30100 (0.0007) -[2023-10-10 21:56:22,784][98560] Updated weights for policy 1, policy_version 29992 (0.0008) -[2023-10-10 21:56:23,129][98559] Updated weights for policy 0, policy_version 30110 (0.0008) -[2023-10-10 21:56:23,157][98560] Updated weights for policy 1, policy_version 30002 (0.0007) -[2023-10-10 21:56:23,521][98560] Updated weights for policy 1, policy_version 30012 (0.0007) -[2023-10-10 21:56:25,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 61571072. Throughput: 0: 1687.7, 1: 1703.5. Samples: 15396754. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-10 21:56:25,557][97672] Avg episode reward: [(0, '-1.240'), (1, '22.460')] -[2023-10-10 21:56:27,268][98559] Updated weights for policy 0, policy_version 30120 (0.0007) -[2023-10-10 21:56:27,422][98560] Updated weights for policy 1, policy_version 30022 (0.0008) -[2023-10-10 21:56:27,641][98559] Updated weights for policy 0, policy_version 30130 (0.0008) -[2023-10-10 21:56:27,792][98560] Updated weights for policy 1, policy_version 30032 (0.0009) -[2023-10-10 21:56:28,013][98559] Updated weights for policy 0, policy_version 30140 (0.0008) -[2023-10-10 21:56:28,153][98560] Updated weights for policy 1, policy_version 30042 (0.0008) -[2023-10-10 21:56:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 61636608. Throughput: 0: 1702.5, 1: 1685.2. Samples: 15416654. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:56:30,556][97672] Avg episode reward: [(0, '-1.200'), (1, '22.500')] -[2023-10-10 21:56:31,902][98559] Updated weights for policy 0, policy_version 30150 (0.0008) -[2023-10-10 21:56:32,275][98559] Updated weights for policy 0, policy_version 30160 (0.0008) -[2023-10-10 21:56:32,285][98560] Updated weights for policy 1, policy_version 30052 (0.0007) -[2023-10-10 21:56:32,646][98559] Updated weights for policy 0, policy_version 30170 (0.0009) -[2023-10-10 21:56:32,664][98560] Updated weights for policy 1, policy_version 30062 (0.0009) -[2023-10-10 21:56:33,036][98560] Updated weights for policy 1, policy_version 30072 (0.0009) -[2023-10-10 21:56:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 61702144. Throughput: 0: 1717.4, 1: 1701.8. Samples: 15437520. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:56:35,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.420')] -[2023-10-10 21:56:35,566][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000030080_30801920.pth... -[2023-10-10 21:56:35,566][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000030176_30900224.pth... -[2023-10-10 21:56:35,596][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000028512_29196288.pth -[2023-10-10 21:56:35,611][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000028576_29261824.pth -[2023-10-10 21:56:36,478][98559] Updated weights for policy 0, policy_version 30180 (0.0009) -[2023-10-10 21:56:36,844][98559] Updated weights for policy 0, policy_version 30190 (0.0008) -[2023-10-10 21:56:37,090][98560] Updated weights for policy 1, policy_version 30082 (0.0009) -[2023-10-10 21:56:37,221][98559] Updated weights for policy 0, policy_version 30200 (0.0009) -[2023-10-10 21:56:37,456][98560] Updated weights for policy 1, policy_version 30092 (0.0007) -[2023-10-10 21:56:37,820][98560] Updated weights for policy 1, policy_version 30102 (0.0009) -[2023-10-10 21:56:38,194][98560] Updated weights for policy 1, policy_version 30112 (0.0008) -[2023-10-10 21:56:40,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 61767680. Throughput: 0: 1695.7, 1: 1689.5. Samples: 15447418. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:56:40,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.360')] -[2023-10-10 21:56:41,305][98559] Updated weights for policy 0, policy_version 30210 (0.0008) -[2023-10-10 21:56:41,680][98559] Updated weights for policy 0, policy_version 30220 (0.0010) -[2023-10-10 21:56:42,034][98559] Updated weights for policy 0, policy_version 30230 (0.0009) -[2023-10-10 21:56:42,256][98560] Updated weights for policy 1, policy_version 30122 (0.0007) -[2023-10-10 21:56:42,401][98559] Updated weights for policy 0, policy_version 30240 (0.0009) -[2023-10-10 21:56:42,615][98560] Updated weights for policy 1, policy_version 30132 (0.0008) -[2023-10-10 21:56:42,981][98560] Updated weights for policy 1, policy_version 30142 (0.0009) -[2023-10-10 21:56:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 61833216. Throughput: 0: 1718.7, 1: 1689.9. Samples: 15467964. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:56:45,556][97672] Avg episode reward: [(0, '-1.200'), (1, '22.340')] -[2023-10-10 21:56:46,343][98559] Updated weights for policy 0, policy_version 30250 (0.0008) -[2023-10-10 21:56:46,703][98559] Updated weights for policy 0, policy_version 30260 (0.0009) -[2023-10-10 21:56:46,887][98560] Updated weights for policy 1, policy_version 30152 (0.0008) -[2023-10-10 21:56:47,067][98559] Updated weights for policy 0, policy_version 30270 (0.0008) -[2023-10-10 21:56:47,247][98560] Updated weights for policy 1, policy_version 30162 (0.0009) -[2023-10-10 21:56:47,617][98560] Updated weights for policy 1, policy_version 30172 (0.0008) -[2023-10-10 21:56:50,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 61898752. Throughput: 0: 1711.3, 1: 1710.6. Samples: 15489150. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:56:50,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.220')] -[2023-10-10 21:56:51,095][98559] Updated weights for policy 0, policy_version 30280 (0.0009) -[2023-10-10 21:56:51,453][98560] Updated weights for policy 1, policy_version 30182 (0.0007) -[2023-10-10 21:56:51,459][98559] Updated weights for policy 0, policy_version 30290 (0.0007) -[2023-10-10 21:56:51,819][98560] Updated weights for policy 1, policy_version 30192 (0.0009) -[2023-10-10 21:56:51,823][98559] Updated weights for policy 0, policy_version 30300 (0.0007) -[2023-10-10 21:56:52,172][98560] Updated weights for policy 1, policy_version 30202 (0.0008) -[2023-10-10 21:56:55,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 61964288. Throughput: 0: 1701.6, 1: 1680.2. Samples: 15498468. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-10 21:56:55,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.240')] -[2023-10-10 21:56:55,809][98559] Updated weights for policy 0, policy_version 30310 (0.0007) -[2023-10-10 21:56:56,177][98559] Updated weights for policy 0, policy_version 30320 (0.0008) -[2023-10-10 21:56:56,361][98560] Updated weights for policy 1, policy_version 30212 (0.0007) -[2023-10-10 21:56:56,541][98559] Updated weights for policy 0, policy_version 30330 (0.0007) -[2023-10-10 21:56:56,738][98560] Updated weights for policy 1, policy_version 30222 (0.0008) -[2023-10-10 21:56:57,103][98560] Updated weights for policy 1, policy_version 30232 (0.0009) -[2023-10-10 21:57:00,465][98559] Updated weights for policy 0, policy_version 30340 (0.0007) -[2023-10-10 21:57:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 62029824. Throughput: 0: 1711.1, 1: 1698.3. Samples: 15519304. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-10 21:57:00,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.220')] -[2023-10-10 21:57:00,831][98559] Updated weights for policy 0, policy_version 30350 (0.0007) -[2023-10-10 21:57:01,186][98560] Updated weights for policy 1, policy_version 30242 (0.0008) -[2023-10-10 21:57:01,206][98559] Updated weights for policy 0, policy_version 30360 (0.0007) -[2023-10-10 21:57:01,548][98560] Updated weights for policy 1, policy_version 30252 (0.0007) -[2023-10-10 21:57:01,906][98560] Updated weights for policy 1, policy_version 30262 (0.0008) -[2023-10-10 21:57:02,268][98560] Updated weights for policy 1, policy_version 30272 (0.0008) -[2023-10-10 21:57:05,313][98559] Updated weights for policy 0, policy_version 30370 (0.0008) -[2023-10-10 21:57:05,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 62095360. Throughput: 0: 1708.4, 1: 1704.5. Samples: 15540020. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-10 21:57:05,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.260')] -[2023-10-10 21:57:05,687][98559] Updated weights for policy 0, policy_version 30380 (0.0007) -[2023-10-10 21:57:06,053][98559] Updated weights for policy 0, policy_version 30390 (0.0009) -[2023-10-10 21:57:06,319][98560] Updated weights for policy 1, policy_version 30282 (0.0007) -[2023-10-10 21:57:06,427][98559] Updated weights for policy 0, policy_version 30400 (0.0009) -[2023-10-10 21:57:06,688][98560] Updated weights for policy 1, policy_version 30292 (0.0008) -[2023-10-10 21:57:07,057][98560] Updated weights for policy 1, policy_version 30302 (0.0008) -[2023-10-10 21:57:10,483][98559] Updated weights for policy 0, policy_version 30410 (0.0007) -[2023-10-10 21:57:10,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 62160896. Throughput: 0: 1711.1, 1: 1677.0. Samples: 15549218. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-10 21:57:10,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.340')] -[2023-10-10 21:57:10,853][98559] Updated weights for policy 0, policy_version 30420 (0.0008) -[2023-10-10 21:57:11,138][98560] Updated weights for policy 1, policy_version 30312 (0.0009) -[2023-10-10 21:57:11,215][98559] Updated weights for policy 0, policy_version 30430 (0.0009) -[2023-10-10 21:57:11,509][98560] Updated weights for policy 1, policy_version 30322 (0.0009) -[2023-10-10 21:57:11,884][98560] Updated weights for policy 1, policy_version 30332 (0.0009) -[2023-10-10 21:57:15,340][98559] Updated weights for policy 0, policy_version 30440 (0.0007) -[2023-10-10 21:57:15,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 62226432. Throughput: 0: 1717.3, 1: 1692.4. Samples: 15570092. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-10 21:57:15,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.380')] -[2023-10-10 21:57:15,706][98559] Updated weights for policy 0, policy_version 30450 (0.0010) -[2023-10-10 21:57:15,854][98560] Updated weights for policy 1, policy_version 30342 (0.0009) -[2023-10-10 21:57:16,082][98559] Updated weights for policy 0, policy_version 30460 (0.0009) -[2023-10-10 21:57:16,228][98560] Updated weights for policy 1, policy_version 30352 (0.0008) -[2023-10-10 21:57:16,592][98560] Updated weights for policy 1, policy_version 30362 (0.0009) -[2023-10-10 21:57:20,017][98559] Updated weights for policy 0, policy_version 30470 (0.0009) -[2023-10-10 21:57:20,399][98559] Updated weights for policy 0, policy_version 30480 (0.0009) -[2023-10-10 21:57:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 62291968. Throughput: 0: 1698.6, 1: 1698.9. Samples: 15590406. Policy #0 lag: (min: 12.0, avg: 19.6, max: 44.0) -[2023-10-10 21:57:20,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.420')] -[2023-10-10 21:57:20,596][98560] Updated weights for policy 1, policy_version 30372 (0.0008) -[2023-10-10 21:57:20,765][98559] Updated weights for policy 0, policy_version 30490 (0.0010) -[2023-10-10 21:57:20,958][98560] Updated weights for policy 1, policy_version 30382 (0.0007) -[2023-10-10 21:57:21,328][98560] Updated weights for policy 1, policy_version 30392 (0.0010) -[2023-10-10 21:57:24,483][98559] Updated weights for policy 0, policy_version 30500 (0.0007) -[2023-10-10 21:57:24,856][98559] Updated weights for policy 0, policy_version 30510 (0.0007) -[2023-10-10 21:57:25,222][98559] Updated weights for policy 0, policy_version 30520 (0.0007) -[2023-10-10 21:57:25,297][98560] Updated weights for policy 1, policy_version 30402 (0.0009) -[2023-10-10 21:57:25,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 62390272. Throughput: 0: 1713.6, 1: 1684.2. Samples: 15600322. Policy #0 lag: (min: 12.0, avg: 19.6, max: 44.0) -[2023-10-10 21:57:25,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.380')] -[2023-10-10 21:57:25,662][98560] Updated weights for policy 1, policy_version 30412 (0.0008) -[2023-10-10 21:57:26,022][98560] Updated weights for policy 1, policy_version 30422 (0.0010) -[2023-10-10 21:57:26,394][98560] Updated weights for policy 1, policy_version 30432 (0.0010) -[2023-10-10 21:57:29,076][98559] Updated weights for policy 0, policy_version 30530 (0.0007) -[2023-10-10 21:57:29,439][98559] Updated weights for policy 0, policy_version 30540 (0.0010) -[2023-10-10 21:57:29,806][98559] Updated weights for policy 0, policy_version 30550 (0.0008) -[2023-10-10 21:57:30,184][98559] Updated weights for policy 0, policy_version 30560 (0.0010) -[2023-10-10 21:57:30,457][98560] Updated weights for policy 1, policy_version 30442 (0.0008) -[2023-10-10 21:57:30,556][97672] Fps is (10 sec: 16383.6, 60 sec: 13653.2, 300 sec: 13662.6). Total num frames: 62455808. Throughput: 0: 1712.6, 1: 1694.2. Samples: 15621272. Policy #0 lag: (min: 12.0, avg: 19.6, max: 44.0) -[2023-10-10 21:57:30,558][97672] Avg episode reward: [(0, '-1.200'), (1, '22.460')] -[2023-10-10 21:57:30,818][98560] Updated weights for policy 1, policy_version 30452 (0.0009) -[2023-10-10 21:57:31,188][98560] Updated weights for policy 1, policy_version 30462 (0.0011) -[2023-10-10 21:57:34,199][98559] Updated weights for policy 0, policy_version 30570 (0.0009) -[2023-10-10 21:57:34,566][98559] Updated weights for policy 0, policy_version 30580 (0.0010) -[2023-10-10 21:57:34,937][98559] Updated weights for policy 0, policy_version 30590 (0.0008) -[2023-10-10 21:57:35,224][98560] Updated weights for policy 1, policy_version 30472 (0.0007) -[2023-10-10 21:57:35,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 62521344. Throughput: 0: 1693.6, 1: 1689.6. Samples: 15641396. Policy #0 lag: (min: 12.0, avg: 19.6, max: 44.0) -[2023-10-10 21:57:35,556][97672] Avg episode reward: [(0, '-1.200'), (1, '22.360')] -[2023-10-10 21:57:35,593][98560] Updated weights for policy 1, policy_version 30482 (0.0008) -[2023-10-10 21:57:35,962][98560] Updated weights for policy 1, policy_version 30492 (0.0010) -[2023-10-10 21:57:38,905][98559] Updated weights for policy 0, policy_version 30600 (0.0008) -[2023-10-10 21:57:39,280][98559] Updated weights for policy 0, policy_version 30610 (0.0007) -[2023-10-10 21:57:39,644][98559] Updated weights for policy 0, policy_version 30620 (0.0008) -[2023-10-10 21:57:39,840][98560] Updated weights for policy 1, policy_version 30502 (0.0010) -[2023-10-10 21:57:40,208][98560] Updated weights for policy 1, policy_version 30512 (0.0009) -[2023-10-10 21:57:40,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 62586880. Throughput: 0: 1725.6, 1: 1693.3. Samples: 15652320. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-10 21:57:40,557][97672] Avg episode reward: [(0, '-1.140'), (1, '22.420')] -[2023-10-10 21:57:40,571][98560] Updated weights for policy 1, policy_version 30522 (0.0007) -[2023-10-10 21:57:43,694][98559] Updated weights for policy 0, policy_version 30630 (0.0010) -[2023-10-10 21:57:44,065][98559] Updated weights for policy 0, policy_version 30640 (0.0009) -[2023-10-10 21:57:44,429][98559] Updated weights for policy 0, policy_version 30650 (0.0009) -[2023-10-10 21:57:44,727][98560] Updated weights for policy 1, policy_version 30532 (0.0008) -[2023-10-10 21:57:45,120][98560] Updated weights for policy 1, policy_version 30542 (0.0009) -[2023-10-10 21:57:45,491][98560] Updated weights for policy 1, policy_version 30552 (0.0008) -[2023-10-10 21:57:45,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 62652416. Throughput: 0: 1703.3, 1: 1696.5. Samples: 15672296. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-10 21:57:45,557][97672] Avg episode reward: [(0, '-1.140'), (1, '22.400')] -[2023-10-10 21:57:48,387][98559] Updated weights for policy 0, policy_version 30660 (0.0009) -[2023-10-10 21:57:48,754][98559] Updated weights for policy 0, policy_version 30670 (0.0008) -[2023-10-10 21:57:49,124][98559] Updated weights for policy 0, policy_version 30680 (0.0008) -[2023-10-10 21:57:49,493][98560] Updated weights for policy 1, policy_version 30562 (0.0008) -[2023-10-10 21:57:49,858][98560] Updated weights for policy 1, policy_version 30572 (0.0008) -[2023-10-10 21:57:50,232][98560] Updated weights for policy 1, policy_version 30582 (0.0008) -[2023-10-10 21:57:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 62717952. Throughput: 0: 1702.4, 1: 1686.7. Samples: 15692528. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-10 21:57:50,557][97672] Avg episode reward: [(0, '-1.340'), (1, '22.360')] -[2023-10-10 21:57:50,589][98560] Updated weights for policy 1, policy_version 30592 (0.0007) -[2023-10-10 21:57:53,209][98559] Updated weights for policy 0, policy_version 30690 (0.0009) -[2023-10-10 21:57:53,566][98559] Updated weights for policy 0, policy_version 30700 (0.0010) -[2023-10-10 21:57:53,931][98559] Updated weights for policy 0, policy_version 30710 (0.0009) -[2023-10-10 21:57:54,309][98559] Updated weights for policy 0, policy_version 30720 (0.0010) -[2023-10-10 21:57:54,625][98560] Updated weights for policy 1, policy_version 30602 (0.0009) -[2023-10-10 21:57:54,983][98560] Updated weights for policy 1, policy_version 30612 (0.0008) -[2023-10-10 21:57:55,357][98560] Updated weights for policy 1, policy_version 30622 (0.0008) -[2023-10-10 21:57:55,556][97672] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 62816256. Throughput: 0: 1721.2, 1: 1700.6. Samples: 15703196. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-10 21:57:55,557][97672] Avg episode reward: [(0, '-1.340'), (1, '22.200')] -[2023-10-10 21:57:58,097][98559] Updated weights for policy 0, policy_version 30730 (0.0009) -[2023-10-10 21:57:58,463][98559] Updated weights for policy 0, policy_version 30740 (0.0009) -[2023-10-10 21:57:58,833][98559] Updated weights for policy 0, policy_version 30750 (0.0009) -[2023-10-10 21:57:59,573][98560] Updated weights for policy 1, policy_version 30632 (0.0011) -[2023-10-10 21:57:59,933][98560] Updated weights for policy 1, policy_version 30642 (0.0008) -[2023-10-10 21:58:00,309][98560] Updated weights for policy 1, policy_version 30652 (0.0010) -[2023-10-10 21:58:00,556][97672] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 62881792. Throughput: 0: 1703.8, 1: 1701.6. Samples: 15723332. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-10 21:58:00,557][97672] Avg episode reward: [(0, '-1.340'), (1, '22.140')] -[2023-10-10 21:58:02,763][98559] Updated weights for policy 0, policy_version 30760 (0.0007) -[2023-10-10 21:58:03,139][98559] Updated weights for policy 0, policy_version 30770 (0.0008) -[2023-10-10 21:58:03,520][98559] Updated weights for policy 0, policy_version 30780 (0.0009) -[2023-10-10 21:58:04,272][98560] Updated weights for policy 1, policy_version 30662 (0.0007) -[2023-10-10 21:58:04,632][98560] Updated weights for policy 1, policy_version 30672 (0.0009) -[2023-10-10 21:58:05,012][98560] Updated weights for policy 1, policy_version 30682 (0.0007) -[2023-10-10 21:58:05,556][97672] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 62947328. Throughput: 0: 1720.2, 1: 1683.7. Samples: 15743580. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 21:58:05,556][97672] Avg episode reward: [(0, '-1.360'), (1, '22.100')] -[2023-10-10 21:58:07,660][98559] Updated weights for policy 0, policy_version 30790 (0.0010) -[2023-10-10 21:58:08,018][98559] Updated weights for policy 0, policy_version 30800 (0.0010) -[2023-10-10 21:58:08,387][98559] Updated weights for policy 0, policy_version 30810 (0.0011) -[2023-10-10 21:58:09,154][98560] Updated weights for policy 1, policy_version 30692 (0.0008) -[2023-10-10 21:58:09,525][98560] Updated weights for policy 1, policy_version 30702 (0.0009) -[2023-10-10 21:58:09,889][98560] Updated weights for policy 1, policy_version 30712 (0.0009) -[2023-10-10 21:58:10,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 63012864. Throughput: 0: 1711.3, 1: 1697.0. Samples: 15753696. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 21:58:10,557][97672] Avg episode reward: [(0, '-1.360'), (1, '22.060')] -[2023-10-10 21:58:12,311][98559] Updated weights for policy 0, policy_version 30820 (0.0008) -[2023-10-10 21:58:12,678][98559] Updated weights for policy 0, policy_version 30830 (0.0009) -[2023-10-10 21:58:13,049][98559] Updated weights for policy 0, policy_version 30840 (0.0007) -[2023-10-10 21:58:14,142][98560] Updated weights for policy 1, policy_version 30722 (0.0009) -[2023-10-10 21:58:14,504][98560] Updated weights for policy 1, policy_version 30732 (0.0008) -[2023-10-10 21:58:14,880][98560] Updated weights for policy 1, policy_version 30742 (0.0007) -[2023-10-10 21:58:15,247][98560] Updated weights for policy 1, policy_version 30752 (0.0008) -[2023-10-10 21:58:15,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 63078400. Throughput: 0: 1710.1, 1: 1699.0. Samples: 15774678. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 21:58:15,557][97672] Avg episode reward: [(0, '-1.360'), (1, '22.120')] -[2023-10-10 21:58:16,966][98559] Updated weights for policy 0, policy_version 30850 (0.0007) -[2023-10-10 21:58:17,332][98559] Updated weights for policy 0, policy_version 30860 (0.0007) -[2023-10-10 21:58:17,699][98559] Updated weights for policy 0, policy_version 30870 (0.0008) -[2023-10-10 21:58:18,071][98559] Updated weights for policy 0, policy_version 30880 (0.0008) -[2023-10-10 21:58:19,175][98560] Updated weights for policy 1, policy_version 30762 (0.0011) -[2023-10-10 21:58:19,548][98560] Updated weights for policy 1, policy_version 30772 (0.0010) -[2023-10-10 21:58:19,920][98560] Updated weights for policy 1, policy_version 30782 (0.0009) -[2023-10-10 21:58:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 63143936. Throughput: 0: 1734.4, 1: 1675.1. Samples: 15794824. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 21:58:20,557][97672] Avg episode reward: [(0, '-1.360'), (1, '22.120')] -[2023-10-10 21:58:22,109][98559] Updated weights for policy 0, policy_version 30890 (0.0008) -[2023-10-10 21:58:22,471][98559] Updated weights for policy 0, policy_version 30900 (0.0008) -[2023-10-10 21:58:22,842][98559] Updated weights for policy 0, policy_version 30910 (0.0010) -[2023-10-10 21:58:24,143][98560] Updated weights for policy 1, policy_version 30792 (0.0011) -[2023-10-10 21:58:24,519][98560] Updated weights for policy 1, policy_version 30802 (0.0009) -[2023-10-10 21:58:24,889][98560] Updated weights for policy 1, policy_version 30812 (0.0009) -[2023-10-10 21:58:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 63209472. Throughput: 0: 1701.0, 1: 1690.3. Samples: 15804928. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 21:58:25,557][97672] Avg episode reward: [(0, '-1.360'), (1, '22.180')] -[2023-10-10 21:58:26,695][98559] Updated weights for policy 0, policy_version 30920 (0.0009) -[2023-10-10 21:58:27,057][98559] Updated weights for policy 0, policy_version 30930 (0.0010) -[2023-10-10 21:58:27,423][98559] Updated weights for policy 0, policy_version 30940 (0.0008) -[2023-10-10 21:58:28,938][98560] Updated weights for policy 1, policy_version 30822 (0.0008) -[2023-10-10 21:58:29,314][98560] Updated weights for policy 1, policy_version 30832 (0.0007) -[2023-10-10 21:58:29,687][98560] Updated weights for policy 1, policy_version 30842 (0.0007) -[2023-10-10 21:58:30,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 63275008. Throughput: 0: 1730.2, 1: 1686.7. Samples: 15826054. Policy #0 lag: (min: 4.0, avg: 25.9, max: 36.0) -[2023-10-10 21:58:30,557][97672] Avg episode reward: [(0, '-1.360'), (1, '22.140')] -[2023-10-10 21:58:31,231][98559] Updated weights for policy 0, policy_version 30950 (0.0010) -[2023-10-10 21:58:31,595][98559] Updated weights for policy 0, policy_version 30960 (0.0009) -[2023-10-10 21:58:31,965][98559] Updated weights for policy 0, policy_version 30970 (0.0009) -[2023-10-10 21:58:33,759][98560] Updated weights for policy 1, policy_version 30852 (0.0009) -[2023-10-10 21:58:34,131][98560] Updated weights for policy 1, policy_version 30862 (0.0009) -[2023-10-10 21:58:34,501][98560] Updated weights for policy 1, policy_version 30872 (0.0008) -[2023-10-10 21:58:35,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 63340544. Throughput: 0: 1738.3, 1: 1671.9. Samples: 15845988. Policy #0 lag: (min: 4.0, avg: 25.9, max: 36.0) -[2023-10-10 21:58:35,557][97672] Avg episode reward: [(0, '-1.360'), (1, '22.200')] -[2023-10-10 21:58:35,567][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000030880_31621120.pth... -[2023-10-10 21:58:35,568][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000030976_31719424.pth... -[2023-10-10 21:58:35,597][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000029280_29982720.pth -[2023-10-10 21:58:35,604][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000029376_30081024.pth -[2023-10-10 21:58:35,910][98559] Updated weights for policy 0, policy_version 30980 (0.0010) -[2023-10-10 21:58:36,284][98559] Updated weights for policy 0, policy_version 30990 (0.0008) -[2023-10-10 21:58:36,657][98559] Updated weights for policy 0, policy_version 31000 (0.0009) -[2023-10-10 21:58:38,424][98560] Updated weights for policy 1, policy_version 30882 (0.0008) -[2023-10-10 21:58:38,796][98560] Updated weights for policy 1, policy_version 30892 (0.0010) -[2023-10-10 21:58:39,167][98560] Updated weights for policy 1, policy_version 30902 (0.0010) -[2023-10-10 21:58:39,533][98560] Updated weights for policy 1, policy_version 30912 (0.0010) -[2023-10-10 21:58:40,499][98559] Updated weights for policy 0, policy_version 31010 (0.0008) -[2023-10-10 21:58:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 63406080. Throughput: 0: 1717.8, 1: 1688.0. Samples: 15856458. Policy #0 lag: (min: 4.0, avg: 25.9, max: 36.0) -[2023-10-10 21:58:40,556][97672] Avg episode reward: [(0, '-1.360'), (1, '22.220')] -[2023-10-10 21:58:40,870][98559] Updated weights for policy 0, policy_version 31020 (0.0009) -[2023-10-10 21:58:41,246][98559] Updated weights for policy 0, policy_version 31030 (0.0007) -[2023-10-10 21:58:41,607][98559] Updated weights for policy 0, policy_version 31040 (0.0008) -[2023-10-10 21:58:43,509][98560] Updated weights for policy 1, policy_version 30922 (0.0007) -[2023-10-10 21:58:43,881][98560] Updated weights for policy 1, policy_version 30932 (0.0008) -[2023-10-10 21:58:44,253][98560] Updated weights for policy 1, policy_version 30942 (0.0009) -[2023-10-10 21:58:45,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 63471616. Throughput: 0: 1742.0, 1: 1681.2. Samples: 15877376. Policy #0 lag: (min: 4.0, avg: 25.9, max: 36.0) -[2023-10-10 21:58:45,557][97672] Avg episode reward: [(0, '-1.360'), (1, '22.340')] -[2023-10-10 21:58:45,587][98559] Updated weights for policy 0, policy_version 31050 (0.0009) -[2023-10-10 21:58:45,964][98559] Updated weights for policy 0, policy_version 31060 (0.0012) -[2023-10-10 21:58:46,337][98559] Updated weights for policy 0, policy_version 31070 (0.0009) -[2023-10-10 21:58:48,240][98560] Updated weights for policy 1, policy_version 30952 (0.0008) -[2023-10-10 21:58:48,611][98560] Updated weights for policy 1, policy_version 30962 (0.0010) -[2023-10-10 21:58:48,983][98560] Updated weights for policy 1, policy_version 30972 (0.0007) -[2023-10-10 21:58:50,444][98559] Updated weights for policy 0, policy_version 31080 (0.0010) -[2023-10-10 21:58:50,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 63537152. Throughput: 0: 1731.0, 1: 1685.8. Samples: 15897336. Policy #0 lag: (min: 4.0, avg: 25.9, max: 36.0) -[2023-10-10 21:58:50,557][97672] Avg episode reward: [(0, '-1.360'), (1, '22.280')] -[2023-10-10 21:58:50,816][98559] Updated weights for policy 0, policy_version 31090 (0.0010) -[2023-10-10 21:58:51,182][98559] Updated weights for policy 0, policy_version 31100 (0.0009) -[2023-10-10 21:58:52,892][98560] Updated weights for policy 1, policy_version 30982 (0.0009) -[2023-10-10 21:58:53,269][98560] Updated weights for policy 1, policy_version 30992 (0.0008) -[2023-10-10 21:58:53,643][98560] Updated weights for policy 1, policy_version 31002 (0.0010) -[2023-10-10 21:58:55,219][98559] Updated weights for policy 0, policy_version 31110 (0.0009) -[2023-10-10 21:58:55,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 63602688. Throughput: 0: 1726.1, 1: 1703.4. Samples: 15908022. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 21:58:55,556][97672] Avg episode reward: [(0, '-1.300'), (1, '22.320')] -[2023-10-10 21:58:55,590][98559] Updated weights for policy 0, policy_version 31120 (0.0007) -[2023-10-10 21:58:55,971][98559] Updated weights for policy 0, policy_version 31130 (0.0008) -[2023-10-10 21:58:57,557][98560] Updated weights for policy 1, policy_version 31012 (0.0009) -[2023-10-10 21:58:57,927][98560] Updated weights for policy 1, policy_version 31022 (0.0008) -[2023-10-10 21:58:58,291][98560] Updated weights for policy 1, policy_version 31032 (0.0011) -[2023-10-10 21:58:59,910][98559] Updated weights for policy 0, policy_version 31140 (0.0007) -[2023-10-10 21:59:00,288][98559] Updated weights for policy 0, policy_version 31150 (0.0010) -[2023-10-10 21:59:00,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 63668224. Throughput: 0: 1730.6, 1: 1673.6. Samples: 15927868. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 21:59:00,556][97672] Avg episode reward: [(0, '-1.300'), (1, '22.340')] -[2023-10-10 21:59:00,661][98559] Updated weights for policy 0, policy_version 31160 (0.0008) -[2023-10-10 21:59:02,172][98560] Updated weights for policy 1, policy_version 31042 (0.0010) -[2023-10-10 21:59:02,545][98560] Updated weights for policy 1, policy_version 31052 (0.0007) -[2023-10-10 21:59:02,905][98560] Updated weights for policy 1, policy_version 31062 (0.0008) -[2023-10-10 21:59:03,272][98560] Updated weights for policy 1, policy_version 31072 (0.0009) -[2023-10-10 21:59:04,605][98559] Updated weights for policy 0, policy_version 31170 (0.0009) -[2023-10-10 21:59:04,983][98559] Updated weights for policy 0, policy_version 31180 (0.0008) -[2023-10-10 21:59:05,356][98559] Updated weights for policy 0, policy_version 31190 (0.0008) -[2023-10-10 21:59:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 63733760. Throughput: 0: 1707.4, 1: 1700.5. Samples: 15948182. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 21:59:05,556][97672] Avg episode reward: [(0, '-1.300'), (1, '22.280')] -[2023-10-10 21:59:05,722][98559] Updated weights for policy 0, policy_version 31200 (0.0007) -[2023-10-10 21:59:07,356][98560] Updated weights for policy 1, policy_version 31082 (0.0009) -[2023-10-10 21:59:07,723][98560] Updated weights for policy 1, policy_version 31092 (0.0008) -[2023-10-10 21:59:08,091][98560] Updated weights for policy 1, policy_version 31102 (0.0009) -[2023-10-10 21:59:09,877][98559] Updated weights for policy 0, policy_version 31210 (0.0008) -[2023-10-10 21:59:10,252][98559] Updated weights for policy 0, policy_version 31220 (0.0008) -[2023-10-10 21:59:10,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 63799296. Throughput: 0: 1729.4, 1: 1694.0. Samples: 15958982. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 21:59:10,556][97672] Avg episode reward: [(0, '-1.320'), (1, '22.300')] -[2023-10-10 21:59:10,616][98559] Updated weights for policy 0, policy_version 31230 (0.0008) -[2023-10-10 21:59:11,919][98560] Updated weights for policy 1, policy_version 31112 (0.0009) -[2023-10-10 21:59:12,296][98560] Updated weights for policy 1, policy_version 31122 (0.0009) -[2023-10-10 21:59:12,656][98560] Updated weights for policy 1, policy_version 31132 (0.0007) -[2023-10-10 21:59:14,537][98559] Updated weights for policy 0, policy_version 31240 (0.0009) -[2023-10-10 21:59:14,906][98559] Updated weights for policy 0, policy_version 31250 (0.0009) -[2023-10-10 21:59:15,270][98559] Updated weights for policy 0, policy_version 31260 (0.0009) -[2023-10-10 21:59:15,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 63897600. Throughput: 0: 1725.5, 1: 1691.6. Samples: 15979826. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:59:15,557][97672] Avg episode reward: [(0, '-1.320'), (1, '22.320')] -[2023-10-10 21:59:16,565][98560] Updated weights for policy 1, policy_version 31142 (0.0009) -[2023-10-10 21:59:16,924][98560] Updated weights for policy 1, policy_version 31152 (0.0008) -[2023-10-10 21:59:17,288][98560] Updated weights for policy 1, policy_version 31162 (0.0011) -[2023-10-10 21:59:19,100][98559] Updated weights for policy 0, policy_version 31270 (0.0009) -[2023-10-10 21:59:19,465][98559] Updated weights for policy 0, policy_version 31280 (0.0010) -[2023-10-10 21:59:19,838][98559] Updated weights for policy 0, policy_version 31290 (0.0008) -[2023-10-10 21:59:20,556][97672] Fps is (10 sec: 16383.6, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 63963136. Throughput: 0: 1700.9, 1: 1715.8. Samples: 15999742. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:59:20,557][97672] Avg episode reward: [(0, '-1.320'), (1, '22.200')] -[2023-10-10 21:59:21,480][98560] Updated weights for policy 1, policy_version 31172 (0.0010) -[2023-10-10 21:59:21,877][98560] Updated weights for policy 1, policy_version 31182 (0.0008) -[2023-10-10 21:59:22,251][98560] Updated weights for policy 1, policy_version 31192 (0.0007) -[2023-10-10 21:59:23,683][98559] Updated weights for policy 0, policy_version 31300 (0.0009) -[2023-10-10 21:59:24,049][98559] Updated weights for policy 0, policy_version 31310 (0.0008) -[2023-10-10 21:59:24,412][98559] Updated weights for policy 0, policy_version 31320 (0.0009) -[2023-10-10 21:59:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 64028672. Throughput: 0: 1733.0, 1: 1683.5. Samples: 16010202. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:59:25,557][97672] Avg episode reward: [(0, '-1.320'), (1, '22.160')] -[2023-10-10 21:59:26,111][98560] Updated weights for policy 1, policy_version 31202 (0.0009) -[2023-10-10 21:59:26,474][98560] Updated weights for policy 1, policy_version 31212 (0.0008) -[2023-10-10 21:59:26,836][98560] Updated weights for policy 1, policy_version 31222 (0.0011) -[2023-10-10 21:59:27,198][98560] Updated weights for policy 1, policy_version 31232 (0.0010) -[2023-10-10 21:59:28,193][98559] Updated weights for policy 0, policy_version 31330 (0.0007) -[2023-10-10 21:59:28,553][98559] Updated weights for policy 0, policy_version 31340 (0.0007) -[2023-10-10 21:59:28,927][98559] Updated weights for policy 0, policy_version 31350 (0.0007) -[2023-10-10 21:59:29,294][98559] Updated weights for policy 0, policy_version 31360 (0.0009) -[2023-10-10 21:59:30,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 64094208. Throughput: 0: 1699.9, 1: 1699.1. Samples: 16030332. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:59:30,556][97672] Avg episode reward: [(0, '-1.320'), (1, '22.180')] -[2023-10-10 21:59:31,310][98560] Updated weights for policy 1, policy_version 31242 (0.0009) -[2023-10-10 21:59:31,685][98560] Updated weights for policy 1, policy_version 31252 (0.0010) -[2023-10-10 21:59:32,055][98560] Updated weights for policy 1, policy_version 31262 (0.0011) -[2023-10-10 21:59:33,352][98559] Updated weights for policy 0, policy_version 31370 (0.0009) -[2023-10-10 21:59:33,730][98559] Updated weights for policy 0, policy_version 31380 (0.0008) -[2023-10-10 21:59:34,097][98559] Updated weights for policy 0, policy_version 31390 (0.0008) -[2023-10-10 21:59:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 64159744. Throughput: 0: 1711.6, 1: 1712.4. Samples: 16051418. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 21:59:35,557][97672] Avg episode reward: [(0, '-1.320'), (1, '22.200')] -[2023-10-10 21:59:36,197][98560] Updated weights for policy 1, policy_version 31272 (0.0008) -[2023-10-10 21:59:36,564][98560] Updated weights for policy 1, policy_version 31282 (0.0008) -[2023-10-10 21:59:36,942][98560] Updated weights for policy 1, policy_version 31292 (0.0010) -[2023-10-10 21:59:38,156][98559] Updated weights for policy 0, policy_version 31400 (0.0011) -[2023-10-10 21:59:38,524][98559] Updated weights for policy 0, policy_version 31410 (0.0009) -[2023-10-10 21:59:38,898][98559] Updated weights for policy 0, policy_version 31420 (0.0007) -[2023-10-10 21:59:40,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 64225280. Throughput: 0: 1722.9, 1: 1678.9. Samples: 16061104. Policy #0 lag: (min: 12.0, avg: 14.3, max: 44.0) -[2023-10-10 21:59:40,556][97672] Avg episode reward: [(0, '-1.320'), (1, '22.220')] -[2023-10-10 21:59:41,042][98560] Updated weights for policy 1, policy_version 31302 (0.0010) -[2023-10-10 21:59:41,412][98560] Updated weights for policy 1, policy_version 31312 (0.0008) -[2023-10-10 21:59:41,782][98560] Updated weights for policy 1, policy_version 31322 (0.0007) -[2023-10-10 21:59:42,885][98559] Updated weights for policy 0, policy_version 31430 (0.0008) -[2023-10-10 21:59:43,261][98559] Updated weights for policy 0, policy_version 31440 (0.0009) -[2023-10-10 21:59:43,626][98559] Updated weights for policy 0, policy_version 31450 (0.0008) -[2023-10-10 21:59:45,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 64290816. Throughput: 0: 1706.0, 1: 1707.2. Samples: 16081462. Policy #0 lag: (min: 12.0, avg: 14.3, max: 44.0) -[2023-10-10 21:59:45,556][97672] Avg episode reward: [(0, '-1.320'), (1, '22.200')] -[2023-10-10 21:59:45,790][98560] Updated weights for policy 1, policy_version 31332 (0.0008) -[2023-10-10 21:59:46,157][98560] Updated weights for policy 1, policy_version 31342 (0.0009) -[2023-10-10 21:59:46,523][98560] Updated weights for policy 1, policy_version 31352 (0.0008) -[2023-10-10 21:59:47,532][98559] Updated weights for policy 0, policy_version 31460 (0.0008) -[2023-10-10 21:59:47,906][98559] Updated weights for policy 0, policy_version 31470 (0.0010) -[2023-10-10 21:59:48,267][98559] Updated weights for policy 0, policy_version 31480 (0.0010) -[2023-10-10 21:59:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 64356352. Throughput: 0: 1722.2, 1: 1701.6. Samples: 16102254. Policy #0 lag: (min: 12.0, avg: 14.3, max: 44.0) -[2023-10-10 21:59:50,557][97672] Avg episode reward: [(0, '-1.300'), (1, '22.280')] -[2023-10-10 21:59:50,613][98560] Updated weights for policy 1, policy_version 31362 (0.0009) -[2023-10-10 21:59:50,979][98560] Updated weights for policy 1, policy_version 31372 (0.0010) -[2023-10-10 21:59:51,348][98560] Updated weights for policy 1, policy_version 31382 (0.0010) -[2023-10-10 21:59:51,718][98560] Updated weights for policy 1, policy_version 31392 (0.0009) -[2023-10-10 21:59:52,299][98559] Updated weights for policy 0, policy_version 31490 (0.0008) -[2023-10-10 21:59:52,662][98559] Updated weights for policy 0, policy_version 31500 (0.0009) -[2023-10-10 21:59:53,034][98559] Updated weights for policy 0, policy_version 31510 (0.0007) -[2023-10-10 21:59:53,397][98559] Updated weights for policy 0, policy_version 31520 (0.0007) -[2023-10-10 21:59:55,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 64421888. Throughput: 0: 1701.9, 1: 1687.0. Samples: 16111482. Policy #0 lag: (min: 12.0, avg: 14.3, max: 44.0) -[2023-10-10 21:59:55,557][97672] Avg episode reward: [(0, '-1.360'), (1, '22.320')] -[2023-10-10 21:59:55,826][98560] Updated weights for policy 1, policy_version 31402 (0.0007) -[2023-10-10 21:59:56,194][98560] Updated weights for policy 1, policy_version 31412 (0.0007) -[2023-10-10 21:59:56,558][98560] Updated weights for policy 1, policy_version 31422 (0.0007) -[2023-10-10 21:59:57,274][98559] Updated weights for policy 0, policy_version 31530 (0.0008) -[2023-10-10 21:59:57,656][98559] Updated weights for policy 0, policy_version 31540 (0.0008) -[2023-10-10 21:59:58,018][98559] Updated weights for policy 0, policy_version 31550 (0.0009) -[2023-10-10 22:00:00,398][98560] Updated weights for policy 1, policy_version 31432 (0.0008) -[2023-10-10 22:00:00,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 64487424. Throughput: 0: 1702.6, 1: 1697.5. Samples: 16132832. Policy #0 lag: (min: 12.0, avg: 14.3, max: 44.0) -[2023-10-10 22:00:00,558][97672] Avg episode reward: [(0, '-1.360'), (1, '22.260')] -[2023-10-10 22:00:00,767][98560] Updated weights for policy 1, policy_version 31442 (0.0007) -[2023-10-10 22:00:01,131][98560] Updated weights for policy 1, policy_version 31452 (0.0007) -[2023-10-10 22:00:01,901][98559] Updated weights for policy 0, policy_version 31560 (0.0009) -[2023-10-10 22:00:02,269][98559] Updated weights for policy 0, policy_version 31570 (0.0009) -[2023-10-10 22:00:02,637][98559] Updated weights for policy 0, policy_version 31580 (0.0008) -[2023-10-10 22:00:05,065][98560] Updated weights for policy 1, policy_version 31462 (0.0007) -[2023-10-10 22:00:05,426][98560] Updated weights for policy 1, policy_version 31472 (0.0007) -[2023-10-10 22:00:05,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 64552960. Throughput: 0: 1729.3, 1: 1702.9. Samples: 16154194. Policy #0 lag: (min: 31.0, avg: 42.7, max: 63.0) -[2023-10-10 22:00:05,557][97672] Avg episode reward: [(0, '-1.360'), (1, '22.220')] -[2023-10-10 22:00:05,799][98560] Updated weights for policy 1, policy_version 31482 (0.0011) -[2023-10-10 22:00:06,572][98559] Updated weights for policy 0, policy_version 31590 (0.0007) -[2023-10-10 22:00:06,938][98559] Updated weights for policy 0, policy_version 31600 (0.0007) -[2023-10-10 22:00:07,306][98559] Updated weights for policy 0, policy_version 31610 (0.0008) -[2023-10-10 22:00:09,920][98560] Updated weights for policy 1, policy_version 31492 (0.0009) -[2023-10-10 22:00:10,311][98560] Updated weights for policy 1, policy_version 31502 (0.0010) -[2023-10-10 22:00:10,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 64618496. Throughput: 0: 1699.2, 1: 1710.3. Samples: 16163630. Policy #0 lag: (min: 31.0, avg: 42.7, max: 63.0) -[2023-10-10 22:00:10,557][97672] Avg episode reward: [(0, '-1.360'), (1, '22.360')] -[2023-10-10 22:00:10,676][98560] Updated weights for policy 1, policy_version 31512 (0.0010) -[2023-10-10 22:00:11,137][98559] Updated weights for policy 0, policy_version 31620 (0.0008) -[2023-10-10 22:00:11,509][98559] Updated weights for policy 0, policy_version 31630 (0.0010) -[2023-10-10 22:00:11,868][98559] Updated weights for policy 0, policy_version 31640 (0.0008) -[2023-10-10 22:00:14,769][98560] Updated weights for policy 1, policy_version 31522 (0.0010) -[2023-10-10 22:00:15,147][98560] Updated weights for policy 1, policy_version 31532 (0.0009) -[2023-10-10 22:00:15,518][98560] Updated weights for policy 1, policy_version 31542 (0.0008) -[2023-10-10 22:00:15,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 64684032. Throughput: 0: 1725.2, 1: 1703.2. Samples: 16184608. Policy #0 lag: (min: 31.0, avg: 42.7, max: 63.0) -[2023-10-10 22:00:15,556][97672] Avg episode reward: [(0, '-1.360'), (1, '22.400')] -[2023-10-10 22:00:15,886][98560] Updated weights for policy 1, policy_version 31552 (0.0007) -[2023-10-10 22:00:15,944][98559] Updated weights for policy 0, policy_version 31650 (0.0009) -[2023-10-10 22:00:16,313][98559] Updated weights for policy 0, policy_version 31660 (0.0009) -[2023-10-10 22:00:16,690][98559] Updated weights for policy 0, policy_version 31670 (0.0009) -[2023-10-10 22:00:17,069][98559] Updated weights for policy 0, policy_version 31680 (0.0007) -[2023-10-10 22:00:19,840][98560] Updated weights for policy 1, policy_version 31562 (0.0008) -[2023-10-10 22:00:20,210][98560] Updated weights for policy 1, policy_version 31572 (0.0009) -[2023-10-10 22:00:20,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 64749568. Throughput: 0: 1727.0, 1: 1699.8. Samples: 16205622. Policy #0 lag: (min: 31.0, avg: 42.7, max: 63.0) -[2023-10-10 22:00:20,556][97672] Avg episode reward: [(0, '-1.320'), (1, '22.360')] -[2023-10-10 22:00:20,584][98560] Updated weights for policy 1, policy_version 31582 (0.0008) -[2023-10-10 22:00:21,163][98559] Updated weights for policy 0, policy_version 31690 (0.0009) -[2023-10-10 22:00:21,532][98559] Updated weights for policy 0, policy_version 31700 (0.0009) -[2023-10-10 22:00:21,896][98559] Updated weights for policy 0, policy_version 31710 (0.0008) -[2023-10-10 22:00:24,424][98560] Updated weights for policy 1, policy_version 31592 (0.0008) -[2023-10-10 22:00:24,794][98560] Updated weights for policy 1, policy_version 31602 (0.0008) -[2023-10-10 22:00:25,169][98560] Updated weights for policy 1, policy_version 31612 (0.0007) -[2023-10-10 22:00:25,556][97672] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 64847872. Throughput: 0: 1711.6, 1: 1708.8. Samples: 16215018. Policy #0 lag: (min: 31.0, avg: 42.7, max: 63.0) -[2023-10-10 22:00:25,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.380')] -[2023-10-10 22:00:25,955][98559] Updated weights for policy 0, policy_version 31720 (0.0008) -[2023-10-10 22:00:26,323][98559] Updated weights for policy 0, policy_version 31730 (0.0007) -[2023-10-10 22:00:26,689][98559] Updated weights for policy 0, policy_version 31740 (0.0009) -[2023-10-10 22:00:29,141][98560] Updated weights for policy 1, policy_version 31622 (0.0007) -[2023-10-10 22:00:29,506][98560] Updated weights for policy 1, policy_version 31632 (0.0010) -[2023-10-10 22:00:29,882][98560] Updated weights for policy 1, policy_version 31642 (0.0008) -[2023-10-10 22:00:30,556][97672] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 64913408. Throughput: 0: 1723.4, 1: 1710.6. Samples: 16235990. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-10-10 22:00:30,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.380')] -[2023-10-10 22:00:30,743][98559] Updated weights for policy 0, policy_version 31750 (0.0008) -[2023-10-10 22:00:31,111][98559] Updated weights for policy 0, policy_version 31760 (0.0011) -[2023-10-10 22:00:31,469][98559] Updated weights for policy 0, policy_version 31770 (0.0008) -[2023-10-10 22:00:33,844][98560] Updated weights for policy 1, policy_version 31652 (0.0007) -[2023-10-10 22:00:34,207][98560] Updated weights for policy 1, policy_version 31662 (0.0008) -[2023-10-10 22:00:34,579][98560] Updated weights for policy 1, policy_version 31672 (0.0009) -[2023-10-10 22:00:35,472][98559] Updated weights for policy 0, policy_version 31780 (0.0010) -[2023-10-10 22:00:35,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 64978944. Throughput: 0: 1724.4, 1: 1694.0. Samples: 16256080. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-10-10 22:00:35,556][97672] Avg episode reward: [(0, '-1.260'), (1, '22.360')] -[2023-10-10 22:00:35,568][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000031680_32440320.pth... -[2023-10-10 22:00:35,598][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000030080_30801920.pth -[2023-10-10 22:00:35,602][98439] Saving a milestone ./train_atari/atari_doubledunk_APPO/checkpoint_p1/milestones/checkpoint_000031680_32440320.pth -[2023-10-10 22:00:35,841][98559] Updated weights for policy 0, policy_version 31790 (0.0007) -[2023-10-10 22:00:36,214][98559] Updated weights for policy 0, policy_version 31800 (0.0007) -[2023-10-10 22:00:36,503][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000031808_32571392.pth... -[2023-10-10 22:00:36,546][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000030176_30900224.pth -[2023-10-10 22:00:36,550][98385] Saving a milestone ./train_atari/atari_doubledunk_APPO/checkpoint_p0/milestones/checkpoint_000031808_32571392.pth -[2023-10-10 22:00:38,545][98560] Updated weights for policy 1, policy_version 31682 (0.0010) -[2023-10-10 22:00:38,913][98560] Updated weights for policy 1, policy_version 31692 (0.0008) -[2023-10-10 22:00:39,276][98560] Updated weights for policy 1, policy_version 31702 (0.0007) -[2023-10-10 22:00:39,643][98560] Updated weights for policy 1, policy_version 31712 (0.0009) -[2023-10-10 22:00:40,169][98559] Updated weights for policy 0, policy_version 31810 (0.0008) -[2023-10-10 22:00:40,542][98559] Updated weights for policy 0, policy_version 31820 (0.0008) -[2023-10-10 22:00:40,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 65044480. Throughput: 0: 1724.1, 1: 1721.4. Samples: 16266532. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-10-10 22:00:40,557][97672] Avg episode reward: [(0, '-1.280'), (1, '22.300')] -[2023-10-10 22:00:40,904][98559] Updated weights for policy 0, policy_version 31830 (0.0010) -[2023-10-10 22:00:41,274][98559] Updated weights for policy 0, policy_version 31840 (0.0007) -[2023-10-10 22:00:43,669][98560] Updated weights for policy 1, policy_version 31722 (0.0008) -[2023-10-10 22:00:44,042][98560] Updated weights for policy 1, policy_version 31732 (0.0009) -[2023-10-10 22:00:44,404][98560] Updated weights for policy 1, policy_version 31742 (0.0010) -[2023-10-10 22:00:45,240][98559] Updated weights for policy 0, policy_version 31850 (0.0009) -[2023-10-10 22:00:45,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 65110016. Throughput: 0: 1725.3, 1: 1704.1. Samples: 16287158. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-10-10 22:00:45,557][97672] Avg episode reward: [(0, '-1.280'), (1, '22.280')] -[2023-10-10 22:00:45,608][98559] Updated weights for policy 0, policy_version 31860 (0.0009) -[2023-10-10 22:00:45,984][98559] Updated weights for policy 0, policy_version 31870 (0.0010) -[2023-10-10 22:00:48,350][98560] Updated weights for policy 1, policy_version 31752 (0.0007) -[2023-10-10 22:00:48,727][98560] Updated weights for policy 1, policy_version 31762 (0.0008) -[2023-10-10 22:00:49,095][98560] Updated weights for policy 1, policy_version 31772 (0.0007) -[2023-10-10 22:00:49,874][98559] Updated weights for policy 0, policy_version 31880 (0.0009) -[2023-10-10 22:00:50,255][98559] Updated weights for policy 0, policy_version 31890 (0.0010) -[2023-10-10 22:00:50,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 65175552. Throughput: 0: 1697.4, 1: 1685.2. Samples: 16306408. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-10-10 22:00:50,557][97672] Avg episode reward: [(0, '-1.280'), (1, '22.340')] -[2023-10-10 22:00:50,621][98559] Updated weights for policy 0, policy_version 31900 (0.0008) -[2023-10-10 22:00:53,013][98560] Updated weights for policy 1, policy_version 31782 (0.0008) -[2023-10-10 22:00:53,383][98560] Updated weights for policy 1, policy_version 31792 (0.0009) -[2023-10-10 22:00:53,758][98560] Updated weights for policy 1, policy_version 31802 (0.0010) -[2023-10-10 22:00:54,671][98559] Updated weights for policy 0, policy_version 31910 (0.0008) -[2023-10-10 22:00:55,039][98559] Updated weights for policy 0, policy_version 31920 (0.0008) -[2023-10-10 22:00:55,407][98559] Updated weights for policy 0, policy_version 31930 (0.0009) -[2023-10-10 22:00:55,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 65241088. Throughput: 0: 1715.4, 1: 1711.2. Samples: 16317828. Policy #0 lag: (min: 12.0, avg: 14.6, max: 44.0) -[2023-10-10 22:00:55,556][97672] Avg episode reward: [(0, '-1.280'), (1, '22.300')] -[2023-10-10 22:00:57,862][98560] Updated weights for policy 1, policy_version 31812 (0.0008) -[2023-10-10 22:00:58,257][98560] Updated weights for policy 1, policy_version 31822 (0.0008) -[2023-10-10 22:00:58,625][98560] Updated weights for policy 1, policy_version 31832 (0.0009) -[2023-10-10 22:00:59,261][98559] Updated weights for policy 0, policy_version 31940 (0.0010) -[2023-10-10 22:00:59,632][98559] Updated weights for policy 0, policy_version 31950 (0.0007) -[2023-10-10 22:00:59,995][98559] Updated weights for policy 0, policy_version 31960 (0.0011) -[2023-10-10 22:01:00,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 65339392. Throughput: 0: 1712.8, 1: 1688.4. Samples: 16337664. Policy #0 lag: (min: 12.0, avg: 14.6, max: 44.0) -[2023-10-10 22:01:00,557][97672] Avg episode reward: [(0, '-1.280'), (1, '22.280')] -[2023-10-10 22:01:02,802][98560] Updated weights for policy 1, policy_version 31842 (0.0008) -[2023-10-10 22:01:03,169][98560] Updated weights for policy 1, policy_version 31852 (0.0011) -[2023-10-10 22:01:03,542][98560] Updated weights for policy 1, policy_version 31862 (0.0011) -[2023-10-10 22:01:03,917][98560] Updated weights for policy 1, policy_version 31872 (0.0010) -[2023-10-10 22:01:03,974][98559] Updated weights for policy 0, policy_version 31970 (0.0009) -[2023-10-10 22:01:04,348][98559] Updated weights for policy 0, policy_version 31980 (0.0008) -[2023-10-10 22:01:04,717][98559] Updated weights for policy 0, policy_version 31990 (0.0008) -[2023-10-10 22:01:05,076][98559] Updated weights for policy 0, policy_version 32000 (0.0008) -[2023-10-10 22:01:05,556][97672] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 65404928. Throughput: 0: 1683.5, 1: 1683.9. Samples: 16357154. Policy #0 lag: (min: 12.0, avg: 14.6, max: 44.0) -[2023-10-10 22:01:05,557][97672] Avg episode reward: [(0, '-1.280'), (1, '22.240')] -[2023-10-10 22:01:07,874][98560] Updated weights for policy 1, policy_version 31882 (0.0008) -[2023-10-10 22:01:08,248][98560] Updated weights for policy 1, policy_version 31892 (0.0007) -[2023-10-10 22:01:08,626][98560] Updated weights for policy 1, policy_version 31902 (0.0010) -[2023-10-10 22:01:09,154][98559] Updated weights for policy 0, policy_version 32010 (0.0009) -[2023-10-10 22:01:09,516][98559] Updated weights for policy 0, policy_version 32020 (0.0007) -[2023-10-10 22:01:09,881][98559] Updated weights for policy 0, policy_version 32030 (0.0010) -[2023-10-10 22:01:10,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 65470464. Throughput: 0: 1713.5, 1: 1701.8. Samples: 16368706. Policy #0 lag: (min: 12.0, avg: 14.6, max: 44.0) -[2023-10-10 22:01:10,557][97672] Avg episode reward: [(0, '-1.280'), (1, '22.220')] -[2023-10-10 22:01:12,718][98560] Updated weights for policy 1, policy_version 31912 (0.0009) -[2023-10-10 22:01:13,084][98560] Updated weights for policy 1, policy_version 31922 (0.0009) -[2023-10-10 22:01:13,451][98560] Updated weights for policy 1, policy_version 31932 (0.0010) -[2023-10-10 22:01:14,021][98559] Updated weights for policy 0, policy_version 32040 (0.0008) -[2023-10-10 22:01:14,380][98559] Updated weights for policy 0, policy_version 32050 (0.0009) -[2023-10-10 22:01:14,760][98559] Updated weights for policy 0, policy_version 32060 (0.0009) -[2023-10-10 22:01:15,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 65536000. Throughput: 0: 1701.9, 1: 1670.1. Samples: 16387730. Policy #0 lag: (min: 25.0, avg: 35.3, max: 57.0) -[2023-10-10 22:01:15,557][97672] Avg episode reward: [(0, '-1.280'), (1, '22.140')] -[2023-10-10 22:01:17,580][98560] Updated weights for policy 1, policy_version 31942 (0.0009) -[2023-10-10 22:01:17,952][98560] Updated weights for policy 1, policy_version 31952 (0.0009) -[2023-10-10 22:01:18,308][98560] Updated weights for policy 1, policy_version 31962 (0.0008) -[2023-10-10 22:01:18,756][98559] Updated weights for policy 0, policy_version 32070 (0.0010) -[2023-10-10 22:01:19,120][98559] Updated weights for policy 0, policy_version 32080 (0.0007) -[2023-10-10 22:01:19,482][98559] Updated weights for policy 0, policy_version 32090 (0.0010) -[2023-10-10 22:01:20,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 65601536. Throughput: 0: 1684.4, 1: 1692.6. Samples: 16408046. Policy #0 lag: (min: 25.0, avg: 35.3, max: 57.0) -[2023-10-10 22:01:20,558][97672] Avg episode reward: [(0, '-1.280'), (1, '22.060')] -[2023-10-10 22:01:22,241][98560] Updated weights for policy 1, policy_version 31972 (0.0008) -[2023-10-10 22:01:22,612][98560] Updated weights for policy 1, policy_version 31982 (0.0010) -[2023-10-10 22:01:22,978][98560] Updated weights for policy 1, policy_version 31992 (0.0007) -[2023-10-10 22:01:23,497][98559] Updated weights for policy 0, policy_version 32100 (0.0009) -[2023-10-10 22:01:23,861][98559] Updated weights for policy 0, policy_version 32110 (0.0008) -[2023-10-10 22:01:24,240][98559] Updated weights for policy 0, policy_version 32120 (0.0009) -[2023-10-10 22:01:25,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 65667072. Throughput: 0: 1714.5, 1: 1682.6. Samples: 16419404. Policy #0 lag: (min: 25.0, avg: 35.3, max: 57.0) -[2023-10-10 22:01:25,556][97672] Avg episode reward: [(0, '-1.280'), (1, '22.080')] -[2023-10-10 22:01:26,966][98560] Updated weights for policy 1, policy_version 32002 (0.0008) -[2023-10-10 22:01:27,343][98560] Updated weights for policy 1, policy_version 32012 (0.0009) -[2023-10-10 22:01:27,707][98560] Updated weights for policy 1, policy_version 32022 (0.0008) -[2023-10-10 22:01:28,071][98560] Updated weights for policy 1, policy_version 32032 (0.0009) -[2023-10-10 22:01:28,279][98559] Updated weights for policy 0, policy_version 32130 (0.0009) -[2023-10-10 22:01:28,649][98559] Updated weights for policy 0, policy_version 32140 (0.0009) -[2023-10-10 22:01:29,012][98559] Updated weights for policy 0, policy_version 32150 (0.0007) -[2023-10-10 22:01:29,380][98559] Updated weights for policy 0, policy_version 32160 (0.0008) -[2023-10-10 22:01:30,556][97672] Fps is (10 sec: 13107.7, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 65732608. Throughput: 0: 1683.6, 1: 1683.1. Samples: 16438660. Policy #0 lag: (min: 25.0, avg: 35.3, max: 57.0) -[2023-10-10 22:01:30,557][97672] Avg episode reward: [(0, '-1.280'), (1, '22.120')] -[2023-10-10 22:01:32,205][98560] Updated weights for policy 1, policy_version 32042 (0.0008) -[2023-10-10 22:01:32,563][98560] Updated weights for policy 1, policy_version 32052 (0.0009) -[2023-10-10 22:01:32,927][98560] Updated weights for policy 1, policy_version 32062 (0.0009) -[2023-10-10 22:01:33,137][98559] Updated weights for policy 0, policy_version 32170 (0.0008) -[2023-10-10 22:01:33,497][98559] Updated weights for policy 0, policy_version 32180 (0.0007) -[2023-10-10 22:01:33,858][98559] Updated weights for policy 0, policy_version 32190 (0.0007) -[2023-10-10 22:01:35,557][97672] Fps is (10 sec: 13105.1, 60 sec: 13653.0, 300 sec: 13662.5). Total num frames: 65798144. Throughput: 0: 1707.9, 1: 1697.7. Samples: 16459666. Policy #0 lag: (min: 25.0, avg: 35.3, max: 57.0) -[2023-10-10 22:01:35,558][97672] Avg episode reward: [(0, '-1.280'), (1, '22.080')] -[2023-10-10 22:01:36,907][98560] Updated weights for policy 1, policy_version 32072 (0.0008) -[2023-10-10 22:01:37,275][98560] Updated weights for policy 1, policy_version 32082 (0.0010) -[2023-10-10 22:01:37,646][98560] Updated weights for policy 1, policy_version 32092 (0.0009) -[2023-10-10 22:01:37,977][98559] Updated weights for policy 0, policy_version 32200 (0.0009) -[2023-10-10 22:01:38,347][98559] Updated weights for policy 0, policy_version 32210 (0.0011) -[2023-10-10 22:01:38,715][98559] Updated weights for policy 0, policy_version 32220 (0.0010) -[2023-10-10 22:01:40,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 65863680. Throughput: 0: 1705.2, 1: 1673.2. Samples: 16469860. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-10 22:01:40,556][97672] Avg episode reward: [(0, '-1.280'), (1, '22.080')] -[2023-10-10 22:01:41,609][98560] Updated weights for policy 1, policy_version 32102 (0.0008) -[2023-10-10 22:01:41,984][98560] Updated weights for policy 1, policy_version 32112 (0.0008) -[2023-10-10 22:01:42,345][98560] Updated weights for policy 1, policy_version 32122 (0.0010) -[2023-10-10 22:01:42,727][98559] Updated weights for policy 0, policy_version 32230 (0.0008) -[2023-10-10 22:01:43,101][98559] Updated weights for policy 0, policy_version 32240 (0.0008) -[2023-10-10 22:01:43,458][98559] Updated weights for policy 0, policy_version 32250 (0.0007) -[2023-10-10 22:01:45,556][97672] Fps is (10 sec: 13109.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 65929216. Throughput: 0: 1692.0, 1: 1696.8. Samples: 16490162. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-10 22:01:45,557][97672] Avg episode reward: [(0, '-1.280'), (1, '22.120')] -[2023-10-10 22:01:46,553][98560] Updated weights for policy 1, policy_version 32132 (0.0007) -[2023-10-10 22:01:46,945][98560] Updated weights for policy 1, policy_version 32142 (0.0007) -[2023-10-10 22:01:47,297][98559] Updated weights for policy 0, policy_version 32260 (0.0007) -[2023-10-10 22:01:47,309][98560] Updated weights for policy 1, policy_version 32152 (0.0009) -[2023-10-10 22:01:47,664][98559] Updated weights for policy 0, policy_version 32270 (0.0008) -[2023-10-10 22:01:48,022][98559] Updated weights for policy 0, policy_version 32280 (0.0010) -[2023-10-10 22:01:50,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 65994752. Throughput: 0: 1715.4, 1: 1700.5. Samples: 16510868. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-10 22:01:50,557][97672] Avg episode reward: [(0, '-1.320'), (1, '22.140')] -[2023-10-10 22:01:51,394][98560] Updated weights for policy 1, policy_version 32162 (0.0007) -[2023-10-10 22:01:51,765][98560] Updated weights for policy 1, policy_version 32172 (0.0010) -[2023-10-10 22:01:52,126][98560] Updated weights for policy 1, policy_version 32182 (0.0008) -[2023-10-10 22:01:52,140][98559] Updated weights for policy 0, policy_version 32290 (0.0010) -[2023-10-10 22:01:52,489][98560] Updated weights for policy 1, policy_version 32192 (0.0008) -[2023-10-10 22:01:52,515][98559] Updated weights for policy 0, policy_version 32300 (0.0008) -[2023-10-10 22:01:52,884][98559] Updated weights for policy 0, policy_version 32310 (0.0008) -[2023-10-10 22:01:53,249][98559] Updated weights for policy 0, policy_version 32320 (0.0010) -[2023-10-10 22:01:55,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 66060288. Throughput: 0: 1686.0, 1: 1674.4. Samples: 16519926. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-10 22:01:55,557][97672] Avg episode reward: [(0, '-1.320'), (1, '22.160')] -[2023-10-10 22:01:56,601][98560] Updated weights for policy 1, policy_version 32202 (0.0011) -[2023-10-10 22:01:56,969][98560] Updated weights for policy 1, policy_version 32212 (0.0010) -[2023-10-10 22:01:57,267][98559] Updated weights for policy 0, policy_version 32330 (0.0008) -[2023-10-10 22:01:57,340][98560] Updated weights for policy 1, policy_version 32222 (0.0007) -[2023-10-10 22:01:57,641][98559] Updated weights for policy 0, policy_version 32340 (0.0008) -[2023-10-10 22:01:58,008][98559] Updated weights for policy 0, policy_version 32350 (0.0010) -[2023-10-10 22:02:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 66125824. Throughput: 0: 1700.5, 1: 1700.6. Samples: 16540776. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-10 22:02:00,557][97672] Avg episode reward: [(0, '-1.320'), (1, '22.220')] -[2023-10-10 22:02:01,489][98560] Updated weights for policy 1, policy_version 32232 (0.0007) -[2023-10-10 22:02:01,865][98560] Updated weights for policy 1, policy_version 32242 (0.0008) -[2023-10-10 22:02:01,951][98559] Updated weights for policy 0, policy_version 32360 (0.0009) -[2023-10-10 22:02:02,232][98560] Updated weights for policy 1, policy_version 32252 (0.0009) -[2023-10-10 22:02:02,332][98559] Updated weights for policy 0, policy_version 32370 (0.0008) -[2023-10-10 22:02:02,695][98559] Updated weights for policy 0, policy_version 32380 (0.0009) -[2023-10-10 22:02:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 66191360. Throughput: 0: 1714.0, 1: 1700.2. Samples: 16561682. Policy #0 lag: (min: 27.0, avg: 29.6, max: 59.0) -[2023-10-10 22:02:05,557][97672] Avg episode reward: [(0, '-1.340'), (1, '22.220')] -[2023-10-10 22:02:06,168][98560] Updated weights for policy 1, policy_version 32262 (0.0009) -[2023-10-10 22:02:06,535][98560] Updated weights for policy 1, policy_version 32272 (0.0010) -[2023-10-10 22:02:06,802][98559] Updated weights for policy 0, policy_version 32390 (0.0008) -[2023-10-10 22:02:06,898][98560] Updated weights for policy 1, policy_version 32282 (0.0009) -[2023-10-10 22:02:07,163][98559] Updated weights for policy 0, policy_version 32400 (0.0007) -[2023-10-10 22:02:07,535][98559] Updated weights for policy 0, policy_version 32410 (0.0007) -[2023-10-10 22:02:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 66256896. Throughput: 0: 1685.2, 1: 1680.8. Samples: 16570874. Policy #0 lag: (min: 27.0, avg: 29.6, max: 59.0) -[2023-10-10 22:02:10,557][97672] Avg episode reward: [(0, '-1.340'), (1, '22.240')] -[2023-10-10 22:02:10,921][98560] Updated weights for policy 1, policy_version 32292 (0.0010) -[2023-10-10 22:02:11,285][98560] Updated weights for policy 1, policy_version 32302 (0.0009) -[2023-10-10 22:02:11,488][98559] Updated weights for policy 0, policy_version 32420 (0.0009) -[2023-10-10 22:02:11,660][98560] Updated weights for policy 1, policy_version 32312 (0.0009) -[2023-10-10 22:02:11,860][98559] Updated weights for policy 0, policy_version 32430 (0.0007) -[2023-10-10 22:02:12,232][98559] Updated weights for policy 0, policy_version 32440 (0.0009) -[2023-10-10 22:02:15,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 13662.6). Total num frames: 66322432. Throughput: 0: 1711.1, 1: 1694.9. Samples: 16591928. Policy #0 lag: (min: 27.0, avg: 29.6, max: 59.0) -[2023-10-10 22:02:15,556][97672] Avg episode reward: [(0, '-1.380'), (1, '22.240')] -[2023-10-10 22:02:15,597][98560] Updated weights for policy 1, policy_version 32322 (0.0008) -[2023-10-10 22:02:15,964][98560] Updated weights for policy 1, policy_version 32332 (0.0008) -[2023-10-10 22:02:16,129][98559] Updated weights for policy 0, policy_version 32450 (0.0009) -[2023-10-10 22:02:16,319][98560] Updated weights for policy 1, policy_version 32342 (0.0010) -[2023-10-10 22:02:16,506][98559] Updated weights for policy 0, policy_version 32460 (0.0007) -[2023-10-10 22:02:16,685][98560] Updated weights for policy 1, policy_version 32352 (0.0008) -[2023-10-10 22:02:16,865][98559] Updated weights for policy 0, policy_version 32470 (0.0009) -[2023-10-10 22:02:17,240][98559] Updated weights for policy 0, policy_version 32480 (0.0010) -[2023-10-10 22:02:20,556][97672] Fps is (10 sec: 13106.7, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 66387968. Throughput: 0: 1712.0, 1: 1697.2. Samples: 16613072. Policy #0 lag: (min: 27.0, avg: 29.6, max: 59.0) -[2023-10-10 22:02:20,558][97672] Avg episode reward: [(0, '-1.380'), (1, '22.140')] -[2023-10-10 22:02:20,608][98560] Updated weights for policy 1, policy_version 32362 (0.0009) -[2023-10-10 22:02:20,974][98560] Updated weights for policy 1, policy_version 32372 (0.0009) -[2023-10-10 22:02:21,124][98559] Updated weights for policy 0, policy_version 32490 (0.0008) -[2023-10-10 22:02:21,334][98560] Updated weights for policy 1, policy_version 32382 (0.0008) -[2023-10-10 22:02:21,489][98559] Updated weights for policy 0, policy_version 32500 (0.0008) -[2023-10-10 22:02:21,864][98559] Updated weights for policy 0, policy_version 32510 (0.0008) -[2023-10-10 22:02:25,472][98560] Updated weights for policy 1, policy_version 32392 (0.0009) -[2023-10-10 22:02:25,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 66453504. Throughput: 0: 1694.3, 1: 1692.0. Samples: 16622246. Policy #0 lag: (min: 27.0, avg: 29.6, max: 59.0) -[2023-10-10 22:02:25,557][97672] Avg episode reward: [(0, '-1.380'), (1, '22.240')] -[2023-10-10 22:02:25,841][98560] Updated weights for policy 1, policy_version 32402 (0.0008) -[2023-10-10 22:02:25,903][98559] Updated weights for policy 0, policy_version 32520 (0.0007) -[2023-10-10 22:02:26,201][98560] Updated weights for policy 1, policy_version 32412 (0.0010) -[2023-10-10 22:02:26,265][98559] Updated weights for policy 0, policy_version 32530 (0.0008) -[2023-10-10 22:02:26,635][98559] Updated weights for policy 0, policy_version 32540 (0.0007) -[2023-10-10 22:02:30,218][98560] Updated weights for policy 1, policy_version 32422 (0.0009) -[2023-10-10 22:02:30,556][97672] Fps is (10 sec: 13107.7, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 66519040. Throughput: 0: 1707.3, 1: 1695.1. Samples: 16643268. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:02:30,557][97672] Avg episode reward: [(0, '-1.380'), (1, '22.220')] -[2023-10-10 22:02:30,580][98560] Updated weights for policy 1, policy_version 32432 (0.0008) -[2023-10-10 22:02:30,747][98559] Updated weights for policy 0, policy_version 32550 (0.0011) -[2023-10-10 22:02:30,956][98560] Updated weights for policy 1, policy_version 32442 (0.0008) -[2023-10-10 22:02:31,114][98559] Updated weights for policy 0, policy_version 32560 (0.0008) -[2023-10-10 22:02:31,481][98559] Updated weights for policy 0, policy_version 32570 (0.0009) -[2023-10-10 22:02:34,891][98560] Updated weights for policy 1, policy_version 32452 (0.0008) -[2023-10-10 22:02:35,291][98560] Updated weights for policy 1, policy_version 32462 (0.0009) -[2023-10-10 22:02:35,420][98559] Updated weights for policy 0, policy_version 32580 (0.0007) -[2023-10-10 22:02:35,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.5, 300 sec: 13551.5). Total num frames: 66584576. Throughput: 0: 1712.2, 1: 1698.4. Samples: 16664346. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:02:35,556][97672] Avg episode reward: [(0, '-1.380'), (1, '22.220')] -[2023-10-10 22:02:35,670][98560] Updated weights for policy 1, policy_version 32472 (0.0009) -[2023-10-10 22:02:35,789][98559] Updated weights for policy 0, policy_version 32590 (0.0009) -[2023-10-10 22:02:35,952][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000032480_33259520.pth... -[2023-10-10 22:02:35,980][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000030880_31621120.pth -[2023-10-10 22:02:36,143][98559] Updated weights for policy 0, policy_version 32600 (0.0008) -[2023-10-10 22:02:36,433][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000032608_33390592.pth... -[2023-10-10 22:02:36,462][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000030976_31719424.pth -[2023-10-10 22:02:39,640][98560] Updated weights for policy 1, policy_version 32482 (0.0008) -[2023-10-10 22:02:40,008][98560] Updated weights for policy 1, policy_version 32492 (0.0007) -[2023-10-10 22:02:40,324][98559] Updated weights for policy 0, policy_version 32610 (0.0010) -[2023-10-10 22:02:40,370][98560] Updated weights for policy 1, policy_version 32502 (0.0008) -[2023-10-10 22:02:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 66650112. Throughput: 0: 1715.3, 1: 1699.9. Samples: 16673610. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:02:40,557][97672] Avg episode reward: [(0, '-1.380'), (1, '22.220')] -[2023-10-10 22:02:40,683][98559] Updated weights for policy 0, policy_version 32620 (0.0007) -[2023-10-10 22:02:40,738][98560] Updated weights for policy 1, policy_version 32512 (0.0007) -[2023-10-10 22:02:41,046][98559] Updated weights for policy 0, policy_version 32630 (0.0009) -[2023-10-10 22:02:41,421][98559] Updated weights for policy 0, policy_version 32640 (0.0011) -[2023-10-10 22:02:44,965][98560] Updated weights for policy 1, policy_version 32522 (0.0007) -[2023-10-10 22:02:45,336][98560] Updated weights for policy 1, policy_version 32532 (0.0008) -[2023-10-10 22:02:45,449][98559] Updated weights for policy 0, policy_version 32650 (0.0009) -[2023-10-10 22:02:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 66715648. Throughput: 0: 1716.0, 1: 1698.2. Samples: 16694414. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:02:45,556][97672] Avg episode reward: [(0, '-1.380'), (1, '22.240')] -[2023-10-10 22:02:45,699][98560] Updated weights for policy 1, policy_version 32542 (0.0007) -[2023-10-10 22:02:45,808][98559] Updated weights for policy 0, policy_version 32660 (0.0008) -[2023-10-10 22:02:46,173][98559] Updated weights for policy 0, policy_version 32670 (0.0010) -[2023-10-10 22:02:49,611][98560] Updated weights for policy 1, policy_version 32552 (0.0010) -[2023-10-10 22:02:49,983][98560] Updated weights for policy 1, policy_version 32562 (0.0011) -[2023-10-10 22:02:50,352][98560] Updated weights for policy 1, policy_version 32572 (0.0008) -[2023-10-10 22:02:50,392][98559] Updated weights for policy 0, policy_version 32680 (0.0009) -[2023-10-10 22:02:50,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 66813952. Throughput: 0: 1706.2, 1: 1690.1. Samples: 16714516. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:02:50,556][97672] Avg episode reward: [(0, '-1.380'), (1, '22.320')] -[2023-10-10 22:02:50,764][98559] Updated weights for policy 0, policy_version 32690 (0.0010) -[2023-10-10 22:02:51,139][98559] Updated weights for policy 0, policy_version 32700 (0.0011) -[2023-10-10 22:02:54,433][98560] Updated weights for policy 1, policy_version 32582 (0.0009) -[2023-10-10 22:02:54,805][98560] Updated weights for policy 1, policy_version 32592 (0.0011) -[2023-10-10 22:02:55,137][98559] Updated weights for policy 0, policy_version 32710 (0.0008) -[2023-10-10 22:02:55,170][98560] Updated weights for policy 1, policy_version 32602 (0.0009) -[2023-10-10 22:02:55,515][98559] Updated weights for policy 0, policy_version 32720 (0.0008) -[2023-10-10 22:02:55,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 66879488. Throughput: 0: 1706.2, 1: 1699.6. Samples: 16724132. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-10-10 22:02:55,556][97672] Avg episode reward: [(0, '-1.380'), (1, '22.340')] -[2023-10-10 22:02:55,883][98559] Updated weights for policy 0, policy_version 32730 (0.0008) -[2023-10-10 22:02:59,168][98560] Updated weights for policy 1, policy_version 32612 (0.0009) -[2023-10-10 22:02:59,533][98560] Updated weights for policy 1, policy_version 32622 (0.0008) -[2023-10-10 22:02:59,740][98559] Updated weights for policy 0, policy_version 32740 (0.0008) -[2023-10-10 22:02:59,897][98560] Updated weights for policy 1, policy_version 32632 (0.0009) -[2023-10-10 22:03:00,103][98559] Updated weights for policy 0, policy_version 32750 (0.0007) -[2023-10-10 22:03:00,466][98559] Updated weights for policy 0, policy_version 32760 (0.0009) -[2023-10-10 22:03:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 66945024. Throughput: 0: 1712.4, 1: 1699.1. Samples: 16745444. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-10-10 22:03:00,557][97672] Avg episode reward: [(0, '-1.380'), (1, '22.380')] -[2023-10-10 22:03:03,848][98560] Updated weights for policy 1, policy_version 32642 (0.0008) -[2023-10-10 22:03:04,208][98560] Updated weights for policy 1, policy_version 32652 (0.0010) -[2023-10-10 22:03:04,426][98559] Updated weights for policy 0, policy_version 32770 (0.0011) -[2023-10-10 22:03:04,568][98560] Updated weights for policy 1, policy_version 32662 (0.0009) -[2023-10-10 22:03:04,790][98559] Updated weights for policy 0, policy_version 32780 (0.0007) -[2023-10-10 22:03:04,931][98560] Updated weights for policy 1, policy_version 32672 (0.0009) -[2023-10-10 22:03:05,147][98559] Updated weights for policy 0, policy_version 32790 (0.0008) -[2023-10-10 22:03:05,515][98559] Updated weights for policy 0, policy_version 32800 (0.0007) -[2023-10-10 22:03:05,556][97672] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 67043328. Throughput: 0: 1687.6, 1: 1679.2. Samples: 16764574. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-10-10 22:03:05,557][97672] Avg episode reward: [(0, '-1.380'), (1, '22.380')] -[2023-10-10 22:03:08,966][98560] Updated weights for policy 1, policy_version 32682 (0.0008) -[2023-10-10 22:03:09,329][98560] Updated weights for policy 1, policy_version 32692 (0.0007) -[2023-10-10 22:03:09,551][98559] Updated weights for policy 0, policy_version 32810 (0.0008) -[2023-10-10 22:03:09,698][98560] Updated weights for policy 1, policy_version 32702 (0.0008) -[2023-10-10 22:03:09,915][98559] Updated weights for policy 0, policy_version 32820 (0.0010) -[2023-10-10 22:03:10,282][98559] Updated weights for policy 0, policy_version 32830 (0.0009) -[2023-10-10 22:03:10,556][97672] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 67108864. Throughput: 0: 1709.7, 1: 1702.7. Samples: 16775804. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-10-10 22:03:10,557][97672] Avg episode reward: [(0, '-1.380'), (1, '22.480')] -[2023-10-10 22:03:13,728][98560] Updated weights for policy 1, policy_version 32712 (0.0009) -[2023-10-10 22:03:14,092][98560] Updated weights for policy 1, policy_version 32722 (0.0008) -[2023-10-10 22:03:14,305][98559] Updated weights for policy 0, policy_version 32840 (0.0008) -[2023-10-10 22:03:14,461][98560] Updated weights for policy 1, policy_version 32732 (0.0008) -[2023-10-10 22:03:14,663][98559] Updated weights for policy 0, policy_version 32850 (0.0007) -[2023-10-10 22:03:15,039][98559] Updated weights for policy 0, policy_version 32860 (0.0008) -[2023-10-10 22:03:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 67174400. Throughput: 0: 1706.6, 1: 1694.6. Samples: 16796322. Policy #0 lag: (min: 11.0, avg: 15.7, max: 43.0) -[2023-10-10 22:03:15,556][97672] Avg episode reward: [(0, '-1.380'), (1, '22.460')] -[2023-10-10 22:03:18,540][98560] Updated weights for policy 1, policy_version 32742 (0.0009) -[2023-10-10 22:03:18,910][98560] Updated weights for policy 1, policy_version 32752 (0.0007) -[2023-10-10 22:03:18,963][98559] Updated weights for policy 0, policy_version 32870 (0.0008) -[2023-10-10 22:03:19,276][98560] Updated weights for policy 1, policy_version 32762 (0.0007) -[2023-10-10 22:03:19,330][98559] Updated weights for policy 0, policy_version 32880 (0.0009) -[2023-10-10 22:03:19,695][98559] Updated weights for policy 0, policy_version 32890 (0.0009) -[2023-10-10 22:03:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.6, 300 sec: 13662.6). Total num frames: 67239936. Throughput: 0: 1683.6, 1: 1672.1. Samples: 16815352. Policy #0 lag: (min: 11.0, avg: 15.7, max: 43.0) -[2023-10-10 22:03:20,556][97672] Avg episode reward: [(0, '-1.380'), (1, '22.500')] -[2023-10-10 22:03:23,385][98560] Updated weights for policy 1, policy_version 32772 (0.0009) -[2023-10-10 22:03:23,675][98559] Updated weights for policy 0, policy_version 32900 (0.0009) -[2023-10-10 22:03:23,792][98560] Updated weights for policy 1, policy_version 32782 (0.0008) -[2023-10-10 22:03:24,031][98559] Updated weights for policy 0, policy_version 32910 (0.0008) -[2023-10-10 22:03:24,157][98560] Updated weights for policy 1, policy_version 32792 (0.0007) -[2023-10-10 22:03:24,405][98559] Updated weights for policy 0, policy_version 32920 (0.0008) -[2023-10-10 22:03:25,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 67305472. Throughput: 0: 1710.0, 1: 1703.3. Samples: 16827206. Policy #0 lag: (min: 11.0, avg: 15.7, max: 43.0) -[2023-10-10 22:03:25,557][97672] Avg episode reward: [(0, '-1.380'), (1, '22.500')] -[2023-10-10 22:03:28,116][98560] Updated weights for policy 1, policy_version 32802 (0.0008) -[2023-10-10 22:03:28,441][98559] Updated weights for policy 0, policy_version 32930 (0.0008) -[2023-10-10 22:03:28,480][98560] Updated weights for policy 1, policy_version 32812 (0.0007) -[2023-10-10 22:03:28,816][98559] Updated weights for policy 0, policy_version 32940 (0.0007) -[2023-10-10 22:03:28,848][98560] Updated weights for policy 1, policy_version 32822 (0.0008) -[2023-10-10 22:03:29,175][98559] Updated weights for policy 0, policy_version 32950 (0.0008) -[2023-10-10 22:03:29,211][98560] Updated weights for policy 1, policy_version 32832 (0.0007) -[2023-10-10 22:03:29,548][98559] Updated weights for policy 0, policy_version 32960 (0.0009) -[2023-10-10 22:03:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 67371008. Throughput: 0: 1685.2, 1: 1690.7. Samples: 16846330. Policy #0 lag: (min: 11.0, avg: 15.7, max: 43.0) -[2023-10-10 22:03:30,557][97672] Avg episode reward: [(0, '-1.380'), (1, '22.520')] -[2023-10-10 22:03:33,214][98560] Updated weights for policy 1, policy_version 32842 (0.0008) -[2023-10-10 22:03:33,488][98559] Updated weights for policy 0, policy_version 32970 (0.0007) -[2023-10-10 22:03:33,584][98560] Updated weights for policy 1, policy_version 32852 (0.0007) -[2023-10-10 22:03:33,849][98559] Updated weights for policy 0, policy_version 32980 (0.0007) -[2023-10-10 22:03:33,948][98560] Updated weights for policy 1, policy_version 32862 (0.0007) -[2023-10-10 22:03:34,212][98559] Updated weights for policy 0, policy_version 32990 (0.0009) -[2023-10-10 22:03:35,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 67436544. Throughput: 0: 1696.2, 1: 1682.0. Samples: 16866536. Policy #0 lag: (min: 11.0, avg: 15.7, max: 43.0) -[2023-10-10 22:03:35,556][97672] Avg episode reward: [(0, '-1.380'), (1, '22.540')] -[2023-10-10 22:03:37,929][98560] Updated weights for policy 1, policy_version 32872 (0.0009) -[2023-10-10 22:03:38,299][98560] Updated weights for policy 1, policy_version 32882 (0.0008) -[2023-10-10 22:03:38,302][98559] Updated weights for policy 0, policy_version 33000 (0.0010) -[2023-10-10 22:03:38,658][98560] Updated weights for policy 1, policy_version 32892 (0.0008) -[2023-10-10 22:03:38,673][98559] Updated weights for policy 0, policy_version 33010 (0.0008) -[2023-10-10 22:03:39,043][98559] Updated weights for policy 0, policy_version 33020 (0.0009) -[2023-10-10 22:03:40,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 67502080. Throughput: 0: 1712.7, 1: 1704.5. Samples: 16877910. Policy #0 lag: (min: 13.0, avg: 21.0, max: 45.0) -[2023-10-10 22:03:40,558][97672] Avg episode reward: [(0, '-1.380'), (1, '22.480')] -[2023-10-10 22:03:42,777][98560] Updated weights for policy 1, policy_version 32902 (0.0009) -[2023-10-10 22:03:43,009][98559] Updated weights for policy 0, policy_version 33030 (0.0009) -[2023-10-10 22:03:43,142][98560] Updated weights for policy 1, policy_version 32912 (0.0009) -[2023-10-10 22:03:43,381][98559] Updated weights for policy 0, policy_version 33040 (0.0007) -[2023-10-10 22:03:43,513][98560] Updated weights for policy 1, policy_version 32922 (0.0009) -[2023-10-10 22:03:43,748][98559] Updated weights for policy 0, policy_version 33050 (0.0008) -[2023-10-10 22:03:45,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 67567616. Throughput: 0: 1686.3, 1: 1676.9. Samples: 16896788. Policy #0 lag: (min: 13.0, avg: 21.0, max: 45.0) -[2023-10-10 22:03:45,557][97672] Avg episode reward: [(0, '-1.380'), (1, '22.460')] -[2023-10-10 22:03:47,404][98560] Updated weights for policy 1, policy_version 32932 (0.0007) -[2023-10-10 22:03:47,634][98559] Updated weights for policy 0, policy_version 33060 (0.0010) -[2023-10-10 22:03:47,765][98560] Updated weights for policy 1, policy_version 32942 (0.0008) -[2023-10-10 22:03:47,995][98559] Updated weights for policy 0, policy_version 33070 (0.0009) -[2023-10-10 22:03:48,132][98560] Updated weights for policy 1, policy_version 32952 (0.0009) -[2023-10-10 22:03:48,371][98559] Updated weights for policy 0, policy_version 33080 (0.0007) -[2023-10-10 22:03:50,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 67633152. Throughput: 0: 1711.0, 1: 1698.0. Samples: 16917978. Policy #0 lag: (min: 13.0, avg: 21.0, max: 45.0) -[2023-10-10 22:03:50,557][97672] Avg episode reward: [(0, '-1.380'), (1, '22.460')] -[2023-10-10 22:03:52,201][98560] Updated weights for policy 1, policy_version 32962 (0.0008) -[2023-10-10 22:03:52,319][98559] Updated weights for policy 0, policy_version 33090 (0.0009) -[2023-10-10 22:03:52,578][98560] Updated weights for policy 1, policy_version 32972 (0.0008) -[2023-10-10 22:03:52,687][98559] Updated weights for policy 0, policy_version 33100 (0.0008) -[2023-10-10 22:03:52,938][98560] Updated weights for policy 1, policy_version 32982 (0.0009) -[2023-10-10 22:03:53,054][98559] Updated weights for policy 0, policy_version 33110 (0.0008) -[2023-10-10 22:03:53,309][98560] Updated weights for policy 1, policy_version 32992 (0.0008) -[2023-10-10 22:03:53,425][98559] Updated weights for policy 0, policy_version 33120 (0.0007) -[2023-10-10 22:03:55,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 67698688. Throughput: 0: 1692.6, 1: 1691.2. Samples: 16928074. Policy #0 lag: (min: 13.0, avg: 21.0, max: 45.0) -[2023-10-10 22:03:55,556][97672] Avg episode reward: [(0, '-1.380'), (1, '22.400')] -[2023-10-10 22:03:57,284][98560] Updated weights for policy 1, policy_version 33002 (0.0009) -[2023-10-10 22:03:57,472][98559] Updated weights for policy 0, policy_version 33130 (0.0008) -[2023-10-10 22:03:57,657][98560] Updated weights for policy 1, policy_version 33012 (0.0007) -[2023-10-10 22:03:57,840][98559] Updated weights for policy 0, policy_version 33140 (0.0008) -[2023-10-10 22:03:58,020][98560] Updated weights for policy 1, policy_version 33022 (0.0008) -[2023-10-10 22:03:58,205][98559] Updated weights for policy 0, policy_version 33150 (0.0009) -[2023-10-10 22:04:00,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 67764224. Throughput: 0: 1694.2, 1: 1680.9. Samples: 16948202. Policy #0 lag: (min: 13.0, avg: 21.0, max: 45.0) -[2023-10-10 22:04:00,557][97672] Avg episode reward: [(0, '-1.380'), (1, '22.340')] -[2023-10-10 22:04:02,134][98560] Updated weights for policy 1, policy_version 33032 (0.0010) -[2023-10-10 22:04:02,268][98559] Updated weights for policy 0, policy_version 33160 (0.0008) -[2023-10-10 22:04:02,490][98560] Updated weights for policy 1, policy_version 33042 (0.0008) -[2023-10-10 22:04:02,640][98559] Updated weights for policy 0, policy_version 33170 (0.0008) -[2023-10-10 22:04:02,862][98560] Updated weights for policy 1, policy_version 33052 (0.0008) -[2023-10-10 22:04:03,002][98559] Updated weights for policy 0, policy_version 33180 (0.0008) -[2023-10-10 22:04:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 67829760. Throughput: 0: 1712.7, 1: 1707.1. Samples: 16969242. Policy #0 lag: (min: 19.0, avg: 25.3, max: 51.0) -[2023-10-10 22:04:05,556][97672] Avg episode reward: [(0, '-1.420'), (1, '22.320')] -[2023-10-10 22:04:06,777][98560] Updated weights for policy 1, policy_version 33062 (0.0008) -[2023-10-10 22:04:06,921][98559] Updated weights for policy 0, policy_version 33190 (0.0007) -[2023-10-10 22:04:07,144][98560] Updated weights for policy 1, policy_version 33072 (0.0008) -[2023-10-10 22:04:07,283][98559] Updated weights for policy 0, policy_version 33200 (0.0009) -[2023-10-10 22:04:07,511][98560] Updated weights for policy 1, policy_version 33082 (0.0008) -[2023-10-10 22:04:07,653][98559] Updated weights for policy 0, policy_version 33210 (0.0008) -[2023-10-10 22:04:10,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 67895296. Throughput: 0: 1684.5, 1: 1682.7. Samples: 16978730. Policy #0 lag: (min: 19.0, avg: 25.3, max: 51.0) -[2023-10-10 22:04:10,556][97672] Avg episode reward: [(0, '-1.420'), (1, '22.260')] -[2023-10-10 22:04:11,616][98559] Updated weights for policy 0, policy_version 33220 (0.0008) -[2023-10-10 22:04:11,668][98560] Updated weights for policy 1, policy_version 33092 (0.0008) -[2023-10-10 22:04:11,987][98559] Updated weights for policy 0, policy_version 33230 (0.0007) -[2023-10-10 22:04:12,033][98560] Updated weights for policy 1, policy_version 33102 (0.0008) -[2023-10-10 22:04:12,352][98559] Updated weights for policy 0, policy_version 33240 (0.0007) -[2023-10-10 22:04:12,400][98560] Updated weights for policy 1, policy_version 33112 (0.0010) -[2023-10-10 22:04:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 67960832. Throughput: 0: 1706.9, 1: 1696.7. Samples: 16999492. Policy #0 lag: (min: 19.0, avg: 25.3, max: 51.0) -[2023-10-10 22:04:15,556][97672] Avg episode reward: [(0, '-1.400'), (1, '22.200')] -[2023-10-10 22:04:16,399][98560] Updated weights for policy 1, policy_version 33122 (0.0009) -[2023-10-10 22:04:16,415][98559] Updated weights for policy 0, policy_version 33250 (0.0009) -[2023-10-10 22:04:16,784][98559] Updated weights for policy 0, policy_version 33260 (0.0007) -[2023-10-10 22:04:16,817][98560] Updated weights for policy 1, policy_version 33132 (0.0007) -[2023-10-10 22:04:17,141][98559] Updated weights for policy 0, policy_version 33270 (0.0008) -[2023-10-10 22:04:17,183][98560] Updated weights for policy 1, policy_version 33142 (0.0007) -[2023-10-10 22:04:17,511][98559] Updated weights for policy 0, policy_version 33280 (0.0008) -[2023-10-10 22:04:17,545][98560] Updated weights for policy 1, policy_version 33152 (0.0008) -[2023-10-10 22:04:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 68026368. Throughput: 0: 1711.8, 1: 1707.1. Samples: 17020386. Policy #0 lag: (min: 19.0, avg: 25.3, max: 51.0) -[2023-10-10 22:04:20,556][97672] Avg episode reward: [(0, '-1.400'), (1, '22.180')] -[2023-10-10 22:04:21,518][98560] Updated weights for policy 1, policy_version 33162 (0.0008) -[2023-10-10 22:04:21,613][98559] Updated weights for policy 0, policy_version 33290 (0.0008) -[2023-10-10 22:04:21,878][98560] Updated weights for policy 1, policy_version 33172 (0.0009) -[2023-10-10 22:04:21,987][98559] Updated weights for policy 0, policy_version 33300 (0.0008) -[2023-10-10 22:04:22,247][98560] Updated weights for policy 1, policy_version 33182 (0.0009) -[2023-10-10 22:04:22,351][98559] Updated weights for policy 0, policy_version 33310 (0.0008) -[2023-10-10 22:04:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 68091904. Throughput: 0: 1692.3, 1: 1679.7. Samples: 17029650. Policy #0 lag: (min: 19.0, avg: 25.3, max: 51.0) -[2023-10-10 22:04:25,556][97672] Avg episode reward: [(0, '-1.400'), (1, '22.180')] -[2023-10-10 22:04:26,241][98560] Updated weights for policy 1, policy_version 33192 (0.0008) -[2023-10-10 22:04:26,276][98559] Updated weights for policy 0, policy_version 33320 (0.0008) -[2023-10-10 22:04:26,608][98560] Updated weights for policy 1, policy_version 33202 (0.0007) -[2023-10-10 22:04:26,648][98559] Updated weights for policy 0, policy_version 33330 (0.0008) -[2023-10-10 22:04:26,979][98560] Updated weights for policy 1, policy_version 33212 (0.0009) -[2023-10-10 22:04:27,018][98559] Updated weights for policy 0, policy_version 33340 (0.0007) -[2023-10-10 22:04:30,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 68157440. Throughput: 0: 1715.0, 1: 1702.8. Samples: 17050590. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:04:30,557][97672] Avg episode reward: [(0, '-1.420'), (1, '22.220')] -[2023-10-10 22:04:31,053][98560] Updated weights for policy 1, policy_version 33222 (0.0008) -[2023-10-10 22:04:31,169][98559] Updated weights for policy 0, policy_version 33350 (0.0009) -[2023-10-10 22:04:31,415][98560] Updated weights for policy 1, policy_version 33232 (0.0008) -[2023-10-10 22:04:31,538][98559] Updated weights for policy 0, policy_version 33360 (0.0007) -[2023-10-10 22:04:31,789][98560] Updated weights for policy 1, policy_version 33242 (0.0007) -[2023-10-10 22:04:31,898][98559] Updated weights for policy 0, policy_version 33370 (0.0007) -[2023-10-10 22:04:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 68222976. Throughput: 0: 1707.4, 1: 1697.6. Samples: 17071204. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:04:35,557][97672] Avg episode reward: [(0, '-1.320'), (1, '22.160')] -[2023-10-10 22:04:35,568][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000033248_34045952.pth... -[2023-10-10 22:04:35,569][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000033376_34177024.pth... -[2023-10-10 22:04:35,606][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000031680_32440320.pth -[2023-10-10 22:04:35,607][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000031808_32571392.pth -[2023-10-10 22:04:36,005][98560] Updated weights for policy 1, policy_version 33252 (0.0008) -[2023-10-10 22:04:36,021][98559] Updated weights for policy 0, policy_version 33380 (0.0007) -[2023-10-10 22:04:36,377][98559] Updated weights for policy 0, policy_version 33390 (0.0008) -[2023-10-10 22:04:36,377][98560] Updated weights for policy 1, policy_version 33262 (0.0009) -[2023-10-10 22:04:36,739][98560] Updated weights for policy 1, policy_version 33272 (0.0007) -[2023-10-10 22:04:36,751][98559] Updated weights for policy 0, policy_version 33400 (0.0008) -[2023-10-10 22:04:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 68288512. Throughput: 0: 1702.7, 1: 1681.5. Samples: 17080364. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:04:40,557][97672] Avg episode reward: [(0, '-1.320'), (1, '22.060')] -[2023-10-10 22:04:40,640][98559] Updated weights for policy 0, policy_version 33410 (0.0008) -[2023-10-10 22:04:40,785][98560] Updated weights for policy 1, policy_version 33282 (0.0008) -[2023-10-10 22:04:41,003][98559] Updated weights for policy 0, policy_version 33420 (0.0007) -[2023-10-10 22:04:41,145][98560] Updated weights for policy 1, policy_version 33292 (0.0008) -[2023-10-10 22:04:41,373][98559] Updated weights for policy 0, policy_version 33430 (0.0007) -[2023-10-10 22:04:41,511][98560] Updated weights for policy 1, policy_version 33302 (0.0007) -[2023-10-10 22:04:41,739][98559] Updated weights for policy 0, policy_version 33440 (0.0007) -[2023-10-10 22:04:41,876][98560] Updated weights for policy 1, policy_version 33312 (0.0007) -[2023-10-10 22:04:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 68354048. Throughput: 0: 1709.7, 1: 1698.7. Samples: 17101578. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:04:45,557][97672] Avg episode reward: [(0, '-1.320'), (1, '22.100')] -[2023-10-10 22:04:45,645][98559] Updated weights for policy 0, policy_version 33450 (0.0008) -[2023-10-10 22:04:45,894][98560] Updated weights for policy 1, policy_version 33322 (0.0008) -[2023-10-10 22:04:46,024][98559] Updated weights for policy 0, policy_version 33460 (0.0009) -[2023-10-10 22:04:46,264][98560] Updated weights for policy 1, policy_version 33332 (0.0009) -[2023-10-10 22:04:46,383][98559] Updated weights for policy 0, policy_version 33470 (0.0009) -[2023-10-10 22:04:46,631][98560] Updated weights for policy 1, policy_version 33342 (0.0009) -[2023-10-10 22:04:50,472][98559] Updated weights for policy 0, policy_version 33480 (0.0009) -[2023-10-10 22:04:50,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 68419584. Throughput: 0: 1704.6, 1: 1693.0. Samples: 17122134. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:04:50,556][97672] Avg episode reward: [(0, '-1.320'), (1, '22.060')] -[2023-10-10 22:04:50,717][98560] Updated weights for policy 1, policy_version 33352 (0.0008) -[2023-10-10 22:04:50,834][98559] Updated weights for policy 0, policy_version 33490 (0.0008) -[2023-10-10 22:04:51,089][98560] Updated weights for policy 1, policy_version 33362 (0.0008) -[2023-10-10 22:04:51,198][98559] Updated weights for policy 0, policy_version 33500 (0.0010) -[2023-10-10 22:04:51,459][98560] Updated weights for policy 1, policy_version 33372 (0.0009) -[2023-10-10 22:04:55,253][98559] Updated weights for policy 0, policy_version 33510 (0.0009) -[2023-10-10 22:04:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 68485120. Throughput: 0: 1709.4, 1: 1685.8. Samples: 17131514. Policy #0 lag: (min: 17.0, avg: 34.2, max: 49.0) -[2023-10-10 22:04:55,557][97672] Avg episode reward: [(0, '-1.320'), (1, '22.080')] -[2023-10-10 22:04:55,609][98560] Updated weights for policy 1, policy_version 33382 (0.0008) -[2023-10-10 22:04:55,613][98559] Updated weights for policy 0, policy_version 33520 (0.0009) -[2023-10-10 22:04:55,977][98559] Updated weights for policy 0, policy_version 33530 (0.0008) -[2023-10-10 22:04:55,986][98560] Updated weights for policy 1, policy_version 33392 (0.0008) -[2023-10-10 22:04:56,351][98560] Updated weights for policy 1, policy_version 33402 (0.0009) -[2023-10-10 22:05:00,130][98559] Updated weights for policy 0, policy_version 33540 (0.0008) -[2023-10-10 22:05:00,355][98560] Updated weights for policy 1, policy_version 33412 (0.0008) -[2023-10-10 22:05:00,499][98559] Updated weights for policy 0, policy_version 33550 (0.0008) -[2023-10-10 22:05:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 68550656. Throughput: 0: 1707.1, 1: 1685.0. Samples: 17152134. Policy #0 lag: (min: 17.0, avg: 34.2, max: 49.0) -[2023-10-10 22:05:00,556][97672] Avg episode reward: [(0, '-1.320'), (1, '22.140')] -[2023-10-10 22:05:00,721][98560] Updated weights for policy 1, policy_version 33422 (0.0008) -[2023-10-10 22:05:00,865][98559] Updated weights for policy 0, policy_version 33560 (0.0009) -[2023-10-10 22:05:01,096][98560] Updated weights for policy 1, policy_version 33432 (0.0007) -[2023-10-10 22:05:04,875][98559] Updated weights for policy 0, policy_version 33570 (0.0007) -[2023-10-10 22:05:05,175][98560] Updated weights for policy 1, policy_version 33442 (0.0008) -[2023-10-10 22:05:05,236][98559] Updated weights for policy 0, policy_version 33580 (0.0008) -[2023-10-10 22:05:05,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 68616192. Throughput: 0: 1692.0, 1: 1689.6. Samples: 17172558. Policy #0 lag: (min: 17.0, avg: 34.2, max: 49.0) -[2023-10-10 22:05:05,556][97672] Avg episode reward: [(0, '-1.320'), (1, '22.160')] -[2023-10-10 22:05:05,582][98560] Updated weights for policy 1, policy_version 33452 (0.0008) -[2023-10-10 22:05:05,611][98559] Updated weights for policy 0, policy_version 33590 (0.0010) -[2023-10-10 22:05:05,938][98560] Updated weights for policy 1, policy_version 33462 (0.0008) -[2023-10-10 22:05:05,973][98559] Updated weights for policy 0, policy_version 33600 (0.0009) -[2023-10-10 22:05:06,311][98560] Updated weights for policy 1, policy_version 33472 (0.0008) -[2023-10-10 22:05:09,982][98559] Updated weights for policy 0, policy_version 33610 (0.0009) -[2023-10-10 22:05:10,280][98560] Updated weights for policy 1, policy_version 33482 (0.0009) -[2023-10-10 22:05:10,357][98559] Updated weights for policy 0, policy_version 33620 (0.0009) -[2023-10-10 22:05:10,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 68681728. Throughput: 0: 1705.1, 1: 1686.6. Samples: 17182274. Policy #0 lag: (min: 17.0, avg: 34.2, max: 49.0) -[2023-10-10 22:05:10,557][97672] Avg episode reward: [(0, '-1.320'), (1, '22.160')] -[2023-10-10 22:05:10,646][98560] Updated weights for policy 1, policy_version 33492 (0.0008) -[2023-10-10 22:05:10,732][98559] Updated weights for policy 0, policy_version 33630 (0.0010) -[2023-10-10 22:05:11,008][98560] Updated weights for policy 1, policy_version 33502 (0.0009) -[2023-10-10 22:05:14,760][98559] Updated weights for policy 0, policy_version 33640 (0.0009) -[2023-10-10 22:05:15,097][98560] Updated weights for policy 1, policy_version 33512 (0.0008) -[2023-10-10 22:05:15,134][98559] Updated weights for policy 0, policy_version 33650 (0.0008) -[2023-10-10 22:05:15,463][98560] Updated weights for policy 1, policy_version 33522 (0.0009) -[2023-10-10 22:05:15,516][98559] Updated weights for policy 0, policy_version 33660 (0.0008) -[2023-10-10 22:05:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 68747264. Throughput: 0: 1701.1, 1: 1687.8. Samples: 17203090. Policy #0 lag: (min: 17.0, avg: 34.2, max: 49.0) -[2023-10-10 22:05:15,556][97672] Avg episode reward: [(0, '-1.320'), (1, '22.180')] -[2023-10-10 22:05:15,837][98560] Updated weights for policy 1, policy_version 33532 (0.0007) -[2023-10-10 22:05:19,275][98559] Updated weights for policy 0, policy_version 33670 (0.0009) -[2023-10-10 22:05:19,642][98559] Updated weights for policy 0, policy_version 33680 (0.0007) -[2023-10-10 22:05:19,947][98560] Updated weights for policy 1, policy_version 33542 (0.0007) -[2023-10-10 22:05:20,005][98559] Updated weights for policy 0, policy_version 33690 (0.0009) -[2023-10-10 22:05:20,323][98560] Updated weights for policy 1, policy_version 33552 (0.0007) -[2023-10-10 22:05:20,556][97672] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 68845568. Throughput: 0: 1679.9, 1: 1684.8. Samples: 17222614. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:05:20,557][97672] Avg episode reward: [(0, '-1.320'), (1, '22.160')] -[2023-10-10 22:05:20,699][98560] Updated weights for policy 1, policy_version 33562 (0.0007) -[2023-10-10 22:05:24,239][98559] Updated weights for policy 0, policy_version 33700 (0.0010) -[2023-10-10 22:05:24,612][98559] Updated weights for policy 0, policy_version 33710 (0.0009) -[2023-10-10 22:05:24,691][98560] Updated weights for policy 1, policy_version 33572 (0.0007) -[2023-10-10 22:05:24,980][98559] Updated weights for policy 0, policy_version 33720 (0.0009) -[2023-10-10 22:05:25,051][98560] Updated weights for policy 1, policy_version 33582 (0.0007) -[2023-10-10 22:05:25,424][98560] Updated weights for policy 1, policy_version 33592 (0.0007) -[2023-10-10 22:05:25,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 68911104. Throughput: 0: 1706.0, 1: 1685.2. Samples: 17232966. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:05:25,556][97672] Avg episode reward: [(0, '-1.320'), (1, '22.200')] -[2023-10-10 22:05:28,939][98559] Updated weights for policy 0, policy_version 33730 (0.0008) -[2023-10-10 22:05:29,310][98559] Updated weights for policy 0, policy_version 33740 (0.0010) -[2023-10-10 22:05:29,570][98560] Updated weights for policy 1, policy_version 33602 (0.0007) -[2023-10-10 22:05:29,676][98559] Updated weights for policy 0, policy_version 33750 (0.0008) -[2023-10-10 22:05:29,948][98560] Updated weights for policy 1, policy_version 33612 (0.0008) -[2023-10-10 22:05:30,043][98559] Updated weights for policy 0, policy_version 33760 (0.0009) -[2023-10-10 22:05:30,305][98560] Updated weights for policy 1, policy_version 33622 (0.0008) -[2023-10-10 22:05:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 68976640. Throughput: 0: 1687.5, 1: 1688.4. Samples: 17253492. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:05:30,557][97672] Avg episode reward: [(0, '-1.320'), (1, '22.300')] -[2023-10-10 22:05:30,670][98560] Updated weights for policy 1, policy_version 33632 (0.0008) -[2023-10-10 22:05:34,065][98559] Updated weights for policy 0, policy_version 33770 (0.0008) -[2023-10-10 22:05:34,435][98559] Updated weights for policy 0, policy_version 33780 (0.0008) -[2023-10-10 22:05:34,555][98560] Updated weights for policy 1, policy_version 33642 (0.0008) -[2023-10-10 22:05:34,793][98559] Updated weights for policy 0, policy_version 33790 (0.0007) -[2023-10-10 22:05:34,923][98560] Updated weights for policy 1, policy_version 33652 (0.0009) -[2023-10-10 22:05:35,285][98560] Updated weights for policy 1, policy_version 33662 (0.0009) -[2023-10-10 22:05:35,556][97672] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 69074944. Throughput: 0: 1676.8, 1: 1685.0. Samples: 17273412. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:05:35,557][97672] Avg episode reward: [(0, '-1.320'), (1, '22.360')] -[2023-10-10 22:05:38,850][98559] Updated weights for policy 0, policy_version 33800 (0.0008) -[2023-10-10 22:05:39,214][98559] Updated weights for policy 0, policy_version 33810 (0.0010) -[2023-10-10 22:05:39,288][98560] Updated weights for policy 1, policy_version 33672 (0.0009) -[2023-10-10 22:05:39,590][98559] Updated weights for policy 0, policy_version 33820 (0.0009) -[2023-10-10 22:05:39,644][98560] Updated weights for policy 1, policy_version 33682 (0.0008) -[2023-10-10 22:05:40,015][98560] Updated weights for policy 1, policy_version 33692 (0.0010) -[2023-10-10 22:05:40,556][97672] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 69140480. Throughput: 0: 1703.2, 1: 1698.8. Samples: 17284600. Policy #0 lag: (min: 21.0, avg: 45.5, max: 48.0) -[2023-10-10 22:05:40,556][97672] Avg episode reward: [(0, '-1.320'), (1, '22.380')] -[2023-10-10 22:05:43,800][98559] Updated weights for policy 0, policy_version 33830 (0.0008) -[2023-10-10 22:05:44,001][98560] Updated weights for policy 1, policy_version 33702 (0.0008) -[2023-10-10 22:05:44,167][98559] Updated weights for policy 0, policy_version 33840 (0.0009) -[2023-10-10 22:05:44,375][98560] Updated weights for policy 1, policy_version 33712 (0.0008) -[2023-10-10 22:05:44,525][98559] Updated weights for policy 0, policy_version 33850 (0.0009) -[2023-10-10 22:05:44,738][98560] Updated weights for policy 1, policy_version 33722 (0.0008) -[2023-10-10 22:05:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 69206016. Throughput: 0: 1684.1, 1: 1702.8. Samples: 17304546. Policy #0 lag: (min: 21.0, avg: 45.5, max: 48.0) -[2023-10-10 22:05:45,556][97672] Avg episode reward: [(0, '-1.320'), (1, '22.400')] -[2023-10-10 22:05:48,569][98560] Updated weights for policy 1, policy_version 33732 (0.0007) -[2023-10-10 22:05:48,593][98559] Updated weights for policy 0, policy_version 33860 (0.0009) -[2023-10-10 22:05:48,937][98560] Updated weights for policy 1, policy_version 33742 (0.0007) -[2023-10-10 22:05:48,963][98559] Updated weights for policy 0, policy_version 33870 (0.0008) -[2023-10-10 22:05:49,297][98560] Updated weights for policy 1, policy_version 33752 (0.0007) -[2023-10-10 22:05:49,338][98559] Updated weights for policy 0, policy_version 33880 (0.0009) -[2023-10-10 22:05:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 69271552. Throughput: 0: 1685.0, 1: 1677.5. Samples: 17323870. Policy #0 lag: (min: 21.0, avg: 45.5, max: 48.0) -[2023-10-10 22:05:50,557][97672] Avg episode reward: [(0, '-1.320'), (1, '22.380')] -[2023-10-10 22:05:53,274][98559] Updated weights for policy 0, policy_version 33890 (0.0009) -[2023-10-10 22:05:53,368][98560] Updated weights for policy 1, policy_version 33762 (0.0008) -[2023-10-10 22:05:53,639][98559] Updated weights for policy 0, policy_version 33900 (0.0007) -[2023-10-10 22:05:53,725][98560] Updated weights for policy 1, policy_version 33772 (0.0007) -[2023-10-10 22:05:54,007][98559] Updated weights for policy 0, policy_version 33910 (0.0008) -[2023-10-10 22:05:54,103][98560] Updated weights for policy 1, policy_version 33782 (0.0008) -[2023-10-10 22:05:54,381][98559] Updated weights for policy 0, policy_version 33920 (0.0008) -[2023-10-10 22:05:54,464][98560] Updated weights for policy 1, policy_version 33792 (0.0008) -[2023-10-10 22:05:55,556][97672] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 69337088. Throughput: 0: 1699.4, 1: 1709.2. Samples: 17335662. Policy #0 lag: (min: 21.0, avg: 45.5, max: 48.0) -[2023-10-10 22:05:55,557][97672] Avg episode reward: [(0, '-1.320'), (1, '22.420')] -[2023-10-10 22:05:58,213][98559] Updated weights for policy 0, policy_version 33930 (0.0009) -[2023-10-10 22:05:58,571][98560] Updated weights for policy 1, policy_version 33802 (0.0007) -[2023-10-10 22:05:58,576][98559] Updated weights for policy 0, policy_version 33940 (0.0009) -[2023-10-10 22:05:58,946][98559] Updated weights for policy 0, policy_version 33950 (0.0009) -[2023-10-10 22:05:58,949][98560] Updated weights for policy 1, policy_version 33812 (0.0009) -[2023-10-10 22:05:59,315][98560] Updated weights for policy 1, policy_version 33822 (0.0009) -[2023-10-10 22:06:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 69402624. Throughput: 0: 1675.4, 1: 1697.6. Samples: 17354878. Policy #0 lag: (min: 21.0, avg: 45.5, max: 48.0) -[2023-10-10 22:06:00,557][97672] Avg episode reward: [(0, '-1.340'), (1, '22.400')] -[2023-10-10 22:06:02,895][98559] Updated weights for policy 0, policy_version 33960 (0.0007) -[2023-10-10 22:06:03,267][98560] Updated weights for policy 1, policy_version 33832 (0.0008) -[2023-10-10 22:06:03,269][98559] Updated weights for policy 0, policy_version 33970 (0.0009) -[2023-10-10 22:06:03,636][98559] Updated weights for policy 0, policy_version 33980 (0.0009) -[2023-10-10 22:06:03,645][98560] Updated weights for policy 1, policy_version 33842 (0.0007) -[2023-10-10 22:06:04,011][98560] Updated weights for policy 1, policy_version 33852 (0.0007) -[2023-10-10 22:06:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 69468160. Throughput: 0: 1699.5, 1: 1688.4. Samples: 17375068. Policy #0 lag: (min: 29.0, avg: 41.8, max: 61.0) -[2023-10-10 22:06:05,557][97672] Avg episode reward: [(0, '-1.340'), (1, '22.320')] -[2023-10-10 22:06:07,731][98559] Updated weights for policy 0, policy_version 33990 (0.0009) -[2023-10-10 22:06:08,099][98559] Updated weights for policy 0, policy_version 34000 (0.0007) -[2023-10-10 22:06:08,182][98560] Updated weights for policy 1, policy_version 33862 (0.0007) -[2023-10-10 22:06:08,459][98559] Updated weights for policy 0, policy_version 34010 (0.0010) -[2023-10-10 22:06:08,543][98560] Updated weights for policy 1, policy_version 33872 (0.0007) -[2023-10-10 22:06:08,904][98560] Updated weights for policy 1, policy_version 33882 (0.0008) -[2023-10-10 22:06:10,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 69533696. Throughput: 0: 1686.9, 1: 1713.4. Samples: 17385980. Policy #0 lag: (min: 29.0, avg: 41.8, max: 61.0) -[2023-10-10 22:06:10,557][97672] Avg episode reward: [(0, '-1.340'), (1, '22.380')] -[2023-10-10 22:06:12,443][98559] Updated weights for policy 0, policy_version 34020 (0.0010) -[2023-10-10 22:06:12,802][98559] Updated weights for policy 0, policy_version 34030 (0.0011) -[2023-10-10 22:06:13,140][98560] Updated weights for policy 1, policy_version 33892 (0.0008) -[2023-10-10 22:06:13,170][98559] Updated weights for policy 0, policy_version 34040 (0.0009) -[2023-10-10 22:06:13,511][98560] Updated weights for policy 1, policy_version 33902 (0.0008) -[2023-10-10 22:06:13,874][98560] Updated weights for policy 1, policy_version 33912 (0.0008) -[2023-10-10 22:06:15,556][97672] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 69599232. Throughput: 0: 1693.4, 1: 1686.6. Samples: 17405592. Policy #0 lag: (min: 29.0, avg: 41.8, max: 61.0) -[2023-10-10 22:06:15,557][97672] Avg episode reward: [(0, '-1.340'), (1, '22.360')] -[2023-10-10 22:06:17,156][98559] Updated weights for policy 0, policy_version 34050 (0.0008) -[2023-10-10 22:06:17,518][98559] Updated weights for policy 0, policy_version 34060 (0.0010) -[2023-10-10 22:06:17,710][98560] Updated weights for policy 1, policy_version 33922 (0.0007) -[2023-10-10 22:06:17,891][98559] Updated weights for policy 0, policy_version 34070 (0.0007) -[2023-10-10 22:06:18,078][98560] Updated weights for policy 1, policy_version 33932 (0.0010) -[2023-10-10 22:06:18,258][98559] Updated weights for policy 0, policy_version 34080 (0.0008) -[2023-10-10 22:06:18,450][98560] Updated weights for policy 1, policy_version 33942 (0.0009) -[2023-10-10 22:06:18,817][98560] Updated weights for policy 1, policy_version 33952 (0.0010) -[2023-10-10 22:06:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 69664768. Throughput: 0: 1710.4, 1: 1682.8. Samples: 17426108. Policy #0 lag: (min: 29.0, avg: 41.8, max: 61.0) -[2023-10-10 22:06:20,557][97672] Avg episode reward: [(0, '-1.340'), (1, '22.280')] -[2023-10-10 22:06:22,350][98559] Updated weights for policy 0, policy_version 34090 (0.0009) -[2023-10-10 22:06:22,708][98559] Updated weights for policy 0, policy_version 34100 (0.0007) -[2023-10-10 22:06:22,783][98560] Updated weights for policy 1, policy_version 33962 (0.0007) -[2023-10-10 22:06:23,084][98559] Updated weights for policy 0, policy_version 34110 (0.0008) -[2023-10-10 22:06:23,153][98560] Updated weights for policy 1, policy_version 33972 (0.0008) -[2023-10-10 22:06:23,524][98560] Updated weights for policy 1, policy_version 33982 (0.0008) -[2023-10-10 22:06:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 69730304. Throughput: 0: 1678.2, 1: 1696.4. Samples: 17436460. Policy #0 lag: (min: 29.0, avg: 41.8, max: 61.0) -[2023-10-10 22:06:25,557][97672] Avg episode reward: [(0, '-1.340'), (1, '22.140')] -[2023-10-10 22:06:27,191][98559] Updated weights for policy 0, policy_version 34120 (0.0008) -[2023-10-10 22:06:27,558][98559] Updated weights for policy 0, policy_version 34130 (0.0008) -[2023-10-10 22:06:27,623][98560] Updated weights for policy 1, policy_version 33992 (0.0008) -[2023-10-10 22:06:27,912][98559] Updated weights for policy 0, policy_version 34140 (0.0008) -[2023-10-10 22:06:27,988][98560] Updated weights for policy 1, policy_version 34002 (0.0009) -[2023-10-10 22:06:28,362][98560] Updated weights for policy 1, policy_version 34012 (0.0010) -[2023-10-10 22:06:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.6). Total num frames: 69795840. Throughput: 0: 1699.5, 1: 1673.8. Samples: 17456344. Policy #0 lag: (min: 1.0, avg: 4.0, max: 31.0) -[2023-10-10 22:06:30,557][97672] Avg episode reward: [(0, '-1.320'), (1, '22.080')] -[2023-10-10 22:06:31,997][98559] Updated weights for policy 0, policy_version 34150 (0.0009) -[2023-10-10 22:06:32,285][98560] Updated weights for policy 1, policy_version 34022 (0.0008) -[2023-10-10 22:06:32,362][98559] Updated weights for policy 0, policy_version 34160 (0.0008) -[2023-10-10 22:06:32,654][98560] Updated weights for policy 1, policy_version 34032 (0.0008) -[2023-10-10 22:06:32,733][98559] Updated weights for policy 0, policy_version 34170 (0.0010) -[2023-10-10 22:06:33,016][98560] Updated weights for policy 1, policy_version 34042 (0.0008) -[2023-10-10 22:06:35,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 69861376. Throughput: 0: 1712.8, 1: 1696.0. Samples: 17477262. Policy #0 lag: (min: 1.0, avg: 4.0, max: 31.0) -[2023-10-10 22:06:35,556][97672] Avg episode reward: [(0, '-1.320'), (1, '22.120')] -[2023-10-10 22:06:35,567][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000034176_34996224.pth... -[2023-10-10 22:06:35,567][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000034048_34865152.pth... -[2023-10-10 22:06:35,602][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000032480_33259520.pth -[2023-10-10 22:06:35,606][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000032608_33390592.pth -[2023-10-10 22:06:36,566][98559] Updated weights for policy 0, policy_version 34180 (0.0009) -[2023-10-10 22:06:36,936][98559] Updated weights for policy 0, policy_version 34190 (0.0008) -[2023-10-10 22:06:37,079][98560] Updated weights for policy 1, policy_version 34052 (0.0008) -[2023-10-10 22:06:37,306][98559] Updated weights for policy 0, policy_version 34200 (0.0007) -[2023-10-10 22:06:37,458][98560] Updated weights for policy 1, policy_version 34062 (0.0007) -[2023-10-10 22:06:37,835][98560] Updated weights for policy 1, policy_version 34072 (0.0007) -[2023-10-10 22:06:40,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 69926912. Throughput: 0: 1684.3, 1: 1678.6. Samples: 17486994. Policy #0 lag: (min: 1.0, avg: 4.0, max: 31.0) -[2023-10-10 22:06:40,556][97672] Avg episode reward: [(0, '-1.320'), (1, '22.140')] -[2023-10-10 22:06:41,242][98559] Updated weights for policy 0, policy_version 34210 (0.0008) -[2023-10-10 22:06:41,612][98559] Updated weights for policy 0, policy_version 34220 (0.0010) -[2023-10-10 22:06:41,744][98560] Updated weights for policy 1, policy_version 34082 (0.0007) -[2023-10-10 22:06:41,977][98559] Updated weights for policy 0, policy_version 34230 (0.0009) -[2023-10-10 22:06:42,115][98560] Updated weights for policy 1, policy_version 34092 (0.0007) -[2023-10-10 22:06:42,336][98559] Updated weights for policy 0, policy_version 34240 (0.0009) -[2023-10-10 22:06:42,490][98560] Updated weights for policy 1, policy_version 34102 (0.0008) -[2023-10-10 22:06:42,848][98560] Updated weights for policy 1, policy_version 34112 (0.0009) -[2023-10-10 22:06:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 69992448. Throughput: 0: 1715.9, 1: 1680.7. Samples: 17507726. Policy #0 lag: (min: 1.0, avg: 4.0, max: 31.0) -[2023-10-10 22:06:45,556][97672] Avg episode reward: [(0, '-1.320'), (1, '22.140')] -[2023-10-10 22:06:46,359][98559] Updated weights for policy 0, policy_version 34250 (0.0008) -[2023-10-10 22:06:46,728][98559] Updated weights for policy 0, policy_version 34260 (0.0007) -[2023-10-10 22:06:47,023][98560] Updated weights for policy 1, policy_version 34122 (0.0007) -[2023-10-10 22:06:47,096][98559] Updated weights for policy 0, policy_version 34270 (0.0009) -[2023-10-10 22:06:47,388][98560] Updated weights for policy 1, policy_version 34132 (0.0007) -[2023-10-10 22:06:47,760][98560] Updated weights for policy 1, policy_version 34142 (0.0009) -[2023-10-10 22:06:50,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 70057984. Throughput: 0: 1719.4, 1: 1693.3. Samples: 17528642. Policy #0 lag: (min: 1.0, avg: 4.0, max: 31.0) -[2023-10-10 22:06:50,557][97672] Avg episode reward: [(0, '-1.340'), (1, '22.160')] -[2023-10-10 22:06:51,008][98559] Updated weights for policy 0, policy_version 34280 (0.0008) -[2023-10-10 22:06:51,381][98559] Updated weights for policy 0, policy_version 34290 (0.0009) -[2023-10-10 22:06:51,620][98560] Updated weights for policy 1, policy_version 34152 (0.0007) -[2023-10-10 22:06:51,750][98559] Updated weights for policy 0, policy_version 34300 (0.0008) -[2023-10-10 22:06:51,983][98560] Updated weights for policy 1, policy_version 34162 (0.0007) -[2023-10-10 22:06:52,358][98560] Updated weights for policy 1, policy_version 34172 (0.0007) -[2023-10-10 22:06:55,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 70123520. Throughput: 0: 1703.3, 1: 1671.5. Samples: 17537846. Policy #0 lag: (min: 23.0, avg: 27.8, max: 55.0) -[2023-10-10 22:06:55,557][97672] Avg episode reward: [(0, '-1.340'), (1, '22.120')] -[2023-10-10 22:06:55,776][98559] Updated weights for policy 0, policy_version 34310 (0.0009) -[2023-10-10 22:06:56,142][98559] Updated weights for policy 0, policy_version 34320 (0.0008) -[2023-10-10 22:06:56,501][98560] Updated weights for policy 1, policy_version 34182 (0.0009) -[2023-10-10 22:06:56,510][98559] Updated weights for policy 0, policy_version 34330 (0.0008) -[2023-10-10 22:06:56,865][98560] Updated weights for policy 1, policy_version 34192 (0.0008) -[2023-10-10 22:06:57,240][98560] Updated weights for policy 1, policy_version 34202 (0.0007) -[2023-10-10 22:07:00,512][98559] Updated weights for policy 0, policy_version 34340 (0.0008) -[2023-10-10 22:07:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 70189056. Throughput: 0: 1712.1, 1: 1697.8. Samples: 17559038. Policy #0 lag: (min: 23.0, avg: 27.8, max: 55.0) -[2023-10-10 22:07:00,557][97672] Avg episode reward: [(0, '-1.340'), (1, '22.120')] -[2023-10-10 22:07:00,884][98559] Updated weights for policy 0, policy_version 34350 (0.0010) -[2023-10-10 22:07:01,114][98560] Updated weights for policy 1, policy_version 34212 (0.0007) -[2023-10-10 22:07:01,256][98559] Updated weights for policy 0, policy_version 34360 (0.0008) -[2023-10-10 22:07:01,484][98560] Updated weights for policy 1, policy_version 34222 (0.0008) -[2023-10-10 22:07:01,849][98560] Updated weights for policy 1, policy_version 34232 (0.0007) -[2023-10-10 22:07:05,294][98559] Updated weights for policy 0, policy_version 34370 (0.0009) -[2023-10-10 22:07:05,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 70254592. Throughput: 0: 1709.7, 1: 1707.0. Samples: 17579860. Policy #0 lag: (min: 23.0, avg: 27.8, max: 55.0) -[2023-10-10 22:07:05,557][97672] Avg episode reward: [(0, '-1.340'), (1, '22.180')] -[2023-10-10 22:07:05,664][98559] Updated weights for policy 0, policy_version 34380 (0.0010) -[2023-10-10 22:07:05,892][98560] Updated weights for policy 1, policy_version 34242 (0.0008) -[2023-10-10 22:07:06,038][98559] Updated weights for policy 0, policy_version 34390 (0.0009) -[2023-10-10 22:07:06,259][98560] Updated weights for policy 1, policy_version 34252 (0.0009) -[2023-10-10 22:07:06,399][98559] Updated weights for policy 0, policy_version 34400 (0.0008) -[2023-10-10 22:07:06,631][98560] Updated weights for policy 1, policy_version 34262 (0.0009) -[2023-10-10 22:07:06,992][98560] Updated weights for policy 1, policy_version 34272 (0.0007) -[2023-10-10 22:07:10,436][98559] Updated weights for policy 0, policy_version 34410 (0.0007) -[2023-10-10 22:07:10,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 70320128. Throughput: 0: 1713.4, 1: 1680.0. Samples: 17589164. Policy #0 lag: (min: 23.0, avg: 27.8, max: 55.0) -[2023-10-10 22:07:10,557][97672] Avg episode reward: [(0, '-1.340'), (1, '22.380')] -[2023-10-10 22:07:10,804][98559] Updated weights for policy 0, policy_version 34420 (0.0009) -[2023-10-10 22:07:11,002][98560] Updated weights for policy 1, policy_version 34282 (0.0010) -[2023-10-10 22:07:11,175][98559] Updated weights for policy 0, policy_version 34430 (0.0007) -[2023-10-10 22:07:11,364][98560] Updated weights for policy 1, policy_version 34292 (0.0008) -[2023-10-10 22:07:11,739][98560] Updated weights for policy 1, policy_version 34302 (0.0008) -[2023-10-10 22:07:15,111][98559] Updated weights for policy 0, policy_version 34440 (0.0009) -[2023-10-10 22:07:15,479][98559] Updated weights for policy 0, policy_version 34450 (0.0009) -[2023-10-10 22:07:15,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 70385664. Throughput: 0: 1719.9, 1: 1702.6. Samples: 17610358. Policy #0 lag: (min: 23.0, avg: 27.8, max: 55.0) -[2023-10-10 22:07:15,556][97672] Avg episode reward: [(0, '-1.340'), (1, '22.440')] -[2023-10-10 22:07:15,757][98560] Updated weights for policy 1, policy_version 34312 (0.0008) -[2023-10-10 22:07:15,846][98559] Updated weights for policy 0, policy_version 34460 (0.0009) -[2023-10-10 22:07:16,120][98560] Updated weights for policy 1, policy_version 34322 (0.0009) -[2023-10-10 22:07:16,491][98560] Updated weights for policy 1, policy_version 34332 (0.0008) -[2023-10-10 22:07:19,877][98559] Updated weights for policy 0, policy_version 34470 (0.0008) -[2023-10-10 22:07:20,249][98559] Updated weights for policy 0, policy_version 34480 (0.0008) -[2023-10-10 22:07:20,501][98560] Updated weights for policy 1, policy_version 34342 (0.0007) -[2023-10-10 22:07:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 70451200. Throughput: 0: 1703.2, 1: 1708.9. Samples: 17630808. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 22:07:20,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.480')] -[2023-10-10 22:07:20,622][98559] Updated weights for policy 0, policy_version 34490 (0.0009) -[2023-10-10 22:07:20,867][98560] Updated weights for policy 1, policy_version 34352 (0.0008) -[2023-10-10 22:07:21,241][98560] Updated weights for policy 1, policy_version 34362 (0.0008) -[2023-10-10 22:07:24,633][98559] Updated weights for policy 0, policy_version 34500 (0.0008) -[2023-10-10 22:07:24,998][98559] Updated weights for policy 0, policy_version 34510 (0.0010) -[2023-10-10 22:07:25,197][98560] Updated weights for policy 1, policy_version 34372 (0.0008) -[2023-10-10 22:07:25,377][98559] Updated weights for policy 0, policy_version 34520 (0.0009) -[2023-10-10 22:07:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 70516736. Throughput: 0: 1719.3, 1: 1697.9. Samples: 17640766. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 22:07:25,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.460')] -[2023-10-10 22:07:25,566][98560] Updated weights for policy 1, policy_version 34382 (0.0008) -[2023-10-10 22:07:25,938][98560] Updated weights for policy 1, policy_version 34392 (0.0008) -[2023-10-10 22:07:29,299][98559] Updated weights for policy 0, policy_version 34530 (0.0008) -[2023-10-10 22:07:29,667][98559] Updated weights for policy 0, policy_version 34540 (0.0008) -[2023-10-10 22:07:29,965][98560] Updated weights for policy 1, policy_version 34402 (0.0008) -[2023-10-10 22:07:30,034][98559] Updated weights for policy 0, policy_version 34550 (0.0008) -[2023-10-10 22:07:30,337][98560] Updated weights for policy 1, policy_version 34412 (0.0007) -[2023-10-10 22:07:30,409][98559] Updated weights for policy 0, policy_version 34560 (0.0009) -[2023-10-10 22:07:30,556][97672] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 70615040. Throughput: 0: 1710.5, 1: 1711.1. Samples: 17661698. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 22:07:30,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.440')] -[2023-10-10 22:07:30,705][98560] Updated weights for policy 1, policy_version 34422 (0.0008) -[2023-10-10 22:07:31,066][98560] Updated weights for policy 1, policy_version 34432 (0.0008) -[2023-10-10 22:07:34,395][98559] Updated weights for policy 0, policy_version 34570 (0.0007) -[2023-10-10 22:07:34,756][98559] Updated weights for policy 0, policy_version 34580 (0.0009) -[2023-10-10 22:07:35,078][98560] Updated weights for policy 1, policy_version 34442 (0.0007) -[2023-10-10 22:07:35,118][98559] Updated weights for policy 0, policy_version 34590 (0.0007) -[2023-10-10 22:07:35,442][98560] Updated weights for policy 1, policy_version 34452 (0.0009) -[2023-10-10 22:07:35,556][97672] Fps is (10 sec: 16384.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 70680576. Throughput: 0: 1686.3, 1: 1713.7. Samples: 17681644. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 22:07:35,556][97672] Avg episode reward: [(0, '-1.260'), (1, '22.460')] -[2023-10-10 22:07:35,806][98560] Updated weights for policy 1, policy_version 34462 (0.0010) -[2023-10-10 22:07:39,232][98559] Updated weights for policy 0, policy_version 34600 (0.0007) -[2023-10-10 22:07:39,600][98559] Updated weights for policy 0, policy_version 34610 (0.0008) -[2023-10-10 22:07:39,815][98560] Updated weights for policy 1, policy_version 34472 (0.0010) -[2023-10-10 22:07:39,966][98559] Updated weights for policy 0, policy_version 34620 (0.0007) -[2023-10-10 22:07:40,181][98560] Updated weights for policy 1, policy_version 34482 (0.0009) -[2023-10-10 22:07:40,553][98560] Updated weights for policy 1, policy_version 34492 (0.0008) -[2023-10-10 22:07:40,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 70746112. Throughput: 0: 1717.0, 1: 1710.9. Samples: 17692104. Policy #0 lag: (min: 18.0, avg: 19.4, max: 39.0) -[2023-10-10 22:07:40,557][97672] Avg episode reward: [(0, '-1.240'), (1, '22.420')] -[2023-10-10 22:07:43,952][98559] Updated weights for policy 0, policy_version 34630 (0.0009) -[2023-10-10 22:07:44,320][98559] Updated weights for policy 0, policy_version 34640 (0.0008) -[2023-10-10 22:07:44,453][98560] Updated weights for policy 1, policy_version 34502 (0.0008) -[2023-10-10 22:07:44,693][98559] Updated weights for policy 0, policy_version 34650 (0.0009) -[2023-10-10 22:07:44,815][98560] Updated weights for policy 1, policy_version 34512 (0.0008) -[2023-10-10 22:07:45,185][98560] Updated weights for policy 1, policy_version 34522 (0.0009) -[2023-10-10 22:07:45,556][97672] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 70844416. Throughput: 0: 1703.0, 1: 1712.2. Samples: 17712720. Policy #0 lag: (min: 18.0, avg: 19.4, max: 39.0) -[2023-10-10 22:07:45,557][97672] Avg episode reward: [(0, '-1.240'), (1, '22.480')] -[2023-10-10 22:07:48,741][98559] Updated weights for policy 0, policy_version 34660 (0.0008) -[2023-10-10 22:07:49,057][98560] Updated weights for policy 1, policy_version 34532 (0.0008) -[2023-10-10 22:07:49,098][98559] Updated weights for policy 0, policy_version 34670 (0.0008) -[2023-10-10 22:07:49,430][98560] Updated weights for policy 1, policy_version 34542 (0.0008) -[2023-10-10 22:07:49,471][98559] Updated weights for policy 0, policy_version 34680 (0.0009) -[2023-10-10 22:07:49,794][98560] Updated weights for policy 1, policy_version 34552 (0.0008) -[2023-10-10 22:07:50,556][97672] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 70909952. Throughput: 0: 1691.0, 1: 1700.1. Samples: 17732458. Policy #0 lag: (min: 18.0, avg: 19.4, max: 39.0) -[2023-10-10 22:07:50,556][97672] Avg episode reward: [(0, '-1.240'), (1, '22.420')] -[2023-10-10 22:07:53,354][98559] Updated weights for policy 0, policy_version 34690 (0.0009) -[2023-10-10 22:07:53,734][98559] Updated weights for policy 0, policy_version 34700 (0.0009) -[2023-10-10 22:07:53,802][98560] Updated weights for policy 1, policy_version 34562 (0.0008) -[2023-10-10 22:07:54,094][98559] Updated weights for policy 0, policy_version 34710 (0.0008) -[2023-10-10 22:07:54,175][98560] Updated weights for policy 1, policy_version 34572 (0.0008) -[2023-10-10 22:07:54,451][98559] Updated weights for policy 0, policy_version 34720 (0.0008) -[2023-10-10 22:07:54,530][98560] Updated weights for policy 1, policy_version 34582 (0.0009) -[2023-10-10 22:07:54,897][98560] Updated weights for policy 1, policy_version 34592 (0.0011) -[2023-10-10 22:07:55,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 70975488. Throughput: 0: 1715.3, 1: 1721.0. Samples: 17743798. Policy #0 lag: (min: 18.0, avg: 19.4, max: 39.0) -[2023-10-10 22:07:55,557][97672] Avg episode reward: [(0, '-1.240'), (1, '22.360')] -[2023-10-10 22:07:58,308][98559] Updated weights for policy 0, policy_version 34730 (0.0008) -[2023-10-10 22:07:58,668][98559] Updated weights for policy 0, policy_version 34740 (0.0007) -[2023-10-10 22:07:58,925][98560] Updated weights for policy 1, policy_version 34602 (0.0009) -[2023-10-10 22:07:59,030][98559] Updated weights for policy 0, policy_version 34750 (0.0009) -[2023-10-10 22:07:59,297][98560] Updated weights for policy 1, policy_version 34612 (0.0008) -[2023-10-10 22:07:59,671][98560] Updated weights for policy 1, policy_version 34622 (0.0008) -[2023-10-10 22:08:00,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 71041024. Throughput: 0: 1686.1, 1: 1718.7. Samples: 17763576. Policy #0 lag: (min: 18.0, avg: 19.4, max: 39.0) -[2023-10-10 22:08:00,557][97672] Avg episode reward: [(0, '-1.240'), (1, '22.360')] -[2023-10-10 22:08:03,068][98559] Updated weights for policy 0, policy_version 34760 (0.0008) -[2023-10-10 22:08:03,436][98559] Updated weights for policy 0, policy_version 34770 (0.0007) -[2023-10-10 22:08:03,725][98560] Updated weights for policy 1, policy_version 34632 (0.0009) -[2023-10-10 22:08:03,807][98559] Updated weights for policy 0, policy_version 34780 (0.0007) -[2023-10-10 22:08:04,083][98560] Updated weights for policy 1, policy_version 34642 (0.0009) -[2023-10-10 22:08:04,450][98560] Updated weights for policy 1, policy_version 34652 (0.0008) -[2023-10-10 22:08:05,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 71106560. Throughput: 0: 1703.6, 1: 1689.1. Samples: 17783482. Policy #0 lag: (min: 27.0, avg: 33.8, max: 59.0) -[2023-10-10 22:08:05,557][97672] Avg episode reward: [(0, '-1.240'), (1, '22.320')] -[2023-10-10 22:08:07,769][98559] Updated weights for policy 0, policy_version 34790 (0.0008) -[2023-10-10 22:08:08,136][98559] Updated weights for policy 0, policy_version 34800 (0.0009) -[2023-10-10 22:08:08,469][98560] Updated weights for policy 1, policy_version 34662 (0.0008) -[2023-10-10 22:08:08,500][98559] Updated weights for policy 0, policy_version 34810 (0.0008) -[2023-10-10 22:08:08,831][98560] Updated weights for policy 1, policy_version 34672 (0.0008) -[2023-10-10 22:08:09,200][98560] Updated weights for policy 1, policy_version 34682 (0.0010) -[2023-10-10 22:08:10,556][97672] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 71172096. Throughput: 0: 1697.6, 1: 1719.1. Samples: 17794514. Policy #0 lag: (min: 27.0, avg: 33.8, max: 59.0) -[2023-10-10 22:08:10,556][97672] Avg episode reward: [(0, '-1.240'), (1, '22.220')] -[2023-10-10 22:08:12,482][98559] Updated weights for policy 0, policy_version 34820 (0.0007) -[2023-10-10 22:08:12,836][98559] Updated weights for policy 0, policy_version 34830 (0.0010) -[2023-10-10 22:08:13,038][98560] Updated weights for policy 1, policy_version 34692 (0.0009) -[2023-10-10 22:08:13,206][98559] Updated weights for policy 0, policy_version 34840 (0.0007) -[2023-10-10 22:08:13,409][98560] Updated weights for policy 1, policy_version 34702 (0.0009) -[2023-10-10 22:08:13,779][98560] Updated weights for policy 1, policy_version 34712 (0.0007) -[2023-10-10 22:08:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 71237632. Throughput: 0: 1688.2, 1: 1703.1. Samples: 17814308. Policy #0 lag: (min: 27.0, avg: 33.8, max: 59.0) -[2023-10-10 22:08:15,557][97672] Avg episode reward: [(0, '-1.240'), (1, '22.280')] -[2023-10-10 22:08:17,361][98559] Updated weights for policy 0, policy_version 34850 (0.0010) -[2023-10-10 22:08:17,730][98559] Updated weights for policy 0, policy_version 34860 (0.0008) -[2023-10-10 22:08:17,930][98560] Updated weights for policy 1, policy_version 34722 (0.0008) -[2023-10-10 22:08:18,095][98559] Updated weights for policy 0, policy_version 34870 (0.0007) -[2023-10-10 22:08:18,292][98560] Updated weights for policy 1, policy_version 34732 (0.0008) -[2023-10-10 22:08:18,465][98559] Updated weights for policy 0, policy_version 34880 (0.0008) -[2023-10-10 22:08:18,660][98560] Updated weights for policy 1, policy_version 34742 (0.0008) -[2023-10-10 22:08:19,040][98560] Updated weights for policy 1, policy_version 34752 (0.0008) -[2023-10-10 22:08:20,556][97672] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 71303168. Throughput: 0: 1710.4, 1: 1693.3. Samples: 17834814. Policy #0 lag: (min: 27.0, avg: 33.8, max: 59.0) -[2023-10-10 22:08:20,557][97672] Avg episode reward: [(0, '-1.320'), (1, '22.200')] -[2023-10-10 22:08:22,564][98559] Updated weights for policy 0, policy_version 34890 (0.0008) -[2023-10-10 22:08:22,937][98559] Updated weights for policy 0, policy_version 34900 (0.0007) -[2023-10-10 22:08:23,024][98560] Updated weights for policy 1, policy_version 34762 (0.0008) -[2023-10-10 22:08:23,294][98559] Updated weights for policy 0, policy_version 34910 (0.0008) -[2023-10-10 22:08:23,391][98560] Updated weights for policy 1, policy_version 34772 (0.0007) -[2023-10-10 22:08:23,754][98560] Updated weights for policy 1, policy_version 34782 (0.0011) -[2023-10-10 22:08:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 71368704. Throughput: 0: 1682.7, 1: 1720.0. Samples: 17845228. Policy #0 lag: (min: 27.0, avg: 33.8, max: 59.0) -[2023-10-10 22:08:25,557][97672] Avg episode reward: [(0, '-1.320'), (1, '22.220')] -[2023-10-10 22:08:27,407][98559] Updated weights for policy 0, policy_version 34920 (0.0008) -[2023-10-10 22:08:27,781][98559] Updated weights for policy 0, policy_version 34930 (0.0009) -[2023-10-10 22:08:27,887][98560] Updated weights for policy 1, policy_version 34792 (0.0008) -[2023-10-10 22:08:28,152][98559] Updated weights for policy 0, policy_version 34940 (0.0009) -[2023-10-10 22:08:28,254][98560] Updated weights for policy 1, policy_version 34802 (0.0008) -[2023-10-10 22:08:28,634][98560] Updated weights for policy 1, policy_version 34812 (0.0010) -[2023-10-10 22:08:30,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 71434240. Throughput: 0: 1694.4, 1: 1688.1. Samples: 17864934. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:08:30,557][97672] Avg episode reward: [(0, '-1.280'), (1, '22.280')] -[2023-10-10 22:08:32,224][98559] Updated weights for policy 0, policy_version 34950 (0.0009) -[2023-10-10 22:08:32,590][98559] Updated weights for policy 0, policy_version 34960 (0.0008) -[2023-10-10 22:08:32,640][98560] Updated weights for policy 1, policy_version 34822 (0.0007) -[2023-10-10 22:08:32,959][98559] Updated weights for policy 0, policy_version 34970 (0.0007) -[2023-10-10 22:08:32,999][98560] Updated weights for policy 1, policy_version 34832 (0.0007) -[2023-10-10 22:08:33,361][98560] Updated weights for policy 1, policy_version 34842 (0.0007) -[2023-10-10 22:08:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 71499776. Throughput: 0: 1703.5, 1: 1698.8. Samples: 17885562. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:08:35,557][97672] Avg episode reward: [(0, '-1.280'), (1, '22.260')] -[2023-10-10 22:08:35,569][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000034848_35684352.pth... -[2023-10-10 22:08:35,569][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000034976_35815424.pth... -[2023-10-10 22:08:35,605][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000033376_34177024.pth -[2023-10-10 22:08:35,608][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000033248_34045952.pth -[2023-10-10 22:08:36,909][98559] Updated weights for policy 0, policy_version 34980 (0.0007) -[2023-10-10 22:08:37,272][98559] Updated weights for policy 0, policy_version 34990 (0.0007) -[2023-10-10 22:08:37,380][98560] Updated weights for policy 1, policy_version 34852 (0.0007) -[2023-10-10 22:08:37,640][98559] Updated weights for policy 0, policy_version 35000 (0.0007) -[2023-10-10 22:08:37,737][98560] Updated weights for policy 1, policy_version 34862 (0.0010) -[2023-10-10 22:08:38,107][98560] Updated weights for policy 1, policy_version 34872 (0.0010) -[2023-10-10 22:08:40,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 71565312. Throughput: 0: 1678.3, 1: 1694.9. Samples: 17895590. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:08:40,556][97672] Avg episode reward: [(0, '-1.280'), (1, '22.240')] -[2023-10-10 22:08:41,318][98559] Updated weights for policy 0, policy_version 35010 (0.0008) -[2023-10-10 22:08:41,685][98559] Updated weights for policy 0, policy_version 35020 (0.0010) -[2023-10-10 22:08:42,057][98559] Updated weights for policy 0, policy_version 35030 (0.0008) -[2023-10-10 22:08:42,132][98560] Updated weights for policy 1, policy_version 34882 (0.0009) -[2023-10-10 22:08:42,420][98559] Updated weights for policy 0, policy_version 35040 (0.0007) -[2023-10-10 22:08:42,495][98560] Updated weights for policy 1, policy_version 34892 (0.0007) -[2023-10-10 22:08:42,861][98560] Updated weights for policy 1, policy_version 34902 (0.0009) -[2023-10-10 22:08:43,227][98560] Updated weights for policy 1, policy_version 34912 (0.0008) -[2023-10-10 22:08:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 71630848. Throughput: 0: 1710.1, 1: 1679.9. Samples: 17916126. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:08:45,557][97672] Avg episode reward: [(0, '-1.280'), (1, '22.280')] -[2023-10-10 22:08:46,493][98559] Updated weights for policy 0, policy_version 35050 (0.0008) -[2023-10-10 22:08:46,863][98559] Updated weights for policy 0, policy_version 35060 (0.0008) -[2023-10-10 22:08:47,203][98560] Updated weights for policy 1, policy_version 34922 (0.0008) -[2023-10-10 22:08:47,223][98559] Updated weights for policy 0, policy_version 35070 (0.0008) -[2023-10-10 22:08:47,569][98560] Updated weights for policy 1, policy_version 34932 (0.0009) -[2023-10-10 22:08:47,942][98560] Updated weights for policy 1, policy_version 34942 (0.0009) -[2023-10-10 22:08:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 71696384. Throughput: 0: 1712.1, 1: 1708.4. Samples: 17937406. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:08:50,556][97672] Avg episode reward: [(0, '-1.260'), (1, '22.220')] -[2023-10-10 22:08:51,251][98559] Updated weights for policy 0, policy_version 35080 (0.0008) -[2023-10-10 22:08:51,622][98559] Updated weights for policy 0, policy_version 35090 (0.0009) -[2023-10-10 22:08:51,997][98559] Updated weights for policy 0, policy_version 35100 (0.0009) -[2023-10-10 22:08:52,069][98560] Updated weights for policy 1, policy_version 34952 (0.0008) -[2023-10-10 22:08:52,430][98560] Updated weights for policy 1, policy_version 34962 (0.0007) -[2023-10-10 22:08:52,798][98560] Updated weights for policy 1, policy_version 34972 (0.0008) -[2023-10-10 22:08:55,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 71761920. Throughput: 0: 1705.9, 1: 1680.7. Samples: 17946910. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:08:55,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.260')] -[2023-10-10 22:08:55,895][98559] Updated weights for policy 0, policy_version 35110 (0.0008) -[2023-10-10 22:08:56,270][98559] Updated weights for policy 0, policy_version 35120 (0.0007) -[2023-10-10 22:08:56,642][98559] Updated weights for policy 0, policy_version 35130 (0.0009) -[2023-10-10 22:08:56,948][98560] Updated weights for policy 1, policy_version 34982 (0.0009) -[2023-10-10 22:08:57,315][98560] Updated weights for policy 1, policy_version 34992 (0.0010) -[2023-10-10 22:08:57,675][98560] Updated weights for policy 1, policy_version 35002 (0.0009) -[2023-10-10 22:09:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 71827456. Throughput: 0: 1720.6, 1: 1687.4. Samples: 17967668. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:09:00,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.260')] -[2023-10-10 22:09:00,693][98559] Updated weights for policy 0, policy_version 35140 (0.0008) -[2023-10-10 22:09:01,057][98559] Updated weights for policy 0, policy_version 35150 (0.0008) -[2023-10-10 22:09:01,424][98559] Updated weights for policy 0, policy_version 35160 (0.0010) -[2023-10-10 22:09:01,585][98560] Updated weights for policy 1, policy_version 35012 (0.0008) -[2023-10-10 22:09:01,958][98560] Updated weights for policy 1, policy_version 35022 (0.0008) -[2023-10-10 22:09:02,320][98560] Updated weights for policy 1, policy_version 35032 (0.0007) -[2023-10-10 22:09:05,351][98559] Updated weights for policy 0, policy_version 35170 (0.0009) -[2023-10-10 22:09:05,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 71892992. Throughput: 0: 1718.4, 1: 1699.0. Samples: 17988596. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:09:05,556][97672] Avg episode reward: [(0, '-1.200'), (1, '22.260')] -[2023-10-10 22:09:05,711][98559] Updated weights for policy 0, policy_version 35180 (0.0010) -[2023-10-10 22:09:06,080][98559] Updated weights for policy 0, policy_version 35190 (0.0008) -[2023-10-10 22:09:06,449][98559] Updated weights for policy 0, policy_version 35200 (0.0008) -[2023-10-10 22:09:06,536][98560] Updated weights for policy 1, policy_version 35042 (0.0009) -[2023-10-10 22:09:06,911][98560] Updated weights for policy 1, policy_version 35052 (0.0009) -[2023-10-10 22:09:07,275][98560] Updated weights for policy 1, policy_version 35062 (0.0008) -[2023-10-10 22:09:07,643][98560] Updated weights for policy 1, policy_version 35072 (0.0009) -[2023-10-10 22:09:10,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 71958528. Throughput: 0: 1720.2, 1: 1670.0. Samples: 17997790. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:09:10,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.320')] -[2023-10-10 22:09:10,585][98559] Updated weights for policy 0, policy_version 35210 (0.0010) -[2023-10-10 22:09:10,950][98559] Updated weights for policy 0, policy_version 35220 (0.0011) -[2023-10-10 22:09:11,311][98559] Updated weights for policy 0, policy_version 35230 (0.0010) -[2023-10-10 22:09:11,686][98560] Updated weights for policy 1, policy_version 35082 (0.0007) -[2023-10-10 22:09:12,056][98560] Updated weights for policy 1, policy_version 35092 (0.0009) -[2023-10-10 22:09:12,420][98560] Updated weights for policy 1, policy_version 35102 (0.0010) -[2023-10-10 22:09:15,286][98559] Updated weights for policy 0, policy_version 35240 (0.0008) -[2023-10-10 22:09:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 72024064. Throughput: 0: 1721.4, 1: 1695.1. Samples: 18018678. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:09:15,556][97672] Avg episode reward: [(0, '-1.200'), (1, '22.320')] -[2023-10-10 22:09:15,658][98559] Updated weights for policy 0, policy_version 35250 (0.0007) -[2023-10-10 22:09:16,030][98559] Updated weights for policy 0, policy_version 35260 (0.0008) -[2023-10-10 22:09:16,612][98560] Updated weights for policy 1, policy_version 35112 (0.0009) -[2023-10-10 22:09:16,986][98560] Updated weights for policy 1, policy_version 35122 (0.0008) -[2023-10-10 22:09:17,357][98560] Updated weights for policy 1, policy_version 35132 (0.0007) -[2023-10-10 22:09:19,940][98559] Updated weights for policy 0, policy_version 35270 (0.0008) -[2023-10-10 22:09:20,305][98559] Updated weights for policy 0, policy_version 35280 (0.0009) -[2023-10-10 22:09:20,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 72089600. Throughput: 0: 1712.3, 1: 1695.6. Samples: 18038918. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-10 22:09:20,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.280')] -[2023-10-10 22:09:20,659][98559] Updated weights for policy 0, policy_version 35290 (0.0007) -[2023-10-10 22:09:21,317][98560] Updated weights for policy 1, policy_version 35142 (0.0008) -[2023-10-10 22:09:21,696][98560] Updated weights for policy 1, policy_version 35152 (0.0009) -[2023-10-10 22:09:22,073][98560] Updated weights for policy 1, policy_version 35162 (0.0008) -[2023-10-10 22:09:24,661][98559] Updated weights for policy 0, policy_version 35300 (0.0007) -[2023-10-10 22:09:25,028][98559] Updated weights for policy 0, policy_version 35310 (0.0009) -[2023-10-10 22:09:25,391][98559] Updated weights for policy 0, policy_version 35320 (0.0008) -[2023-10-10 22:09:25,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 72155136. Throughput: 0: 1728.9, 1: 1678.4. Samples: 18048920. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-10 22:09:25,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.280')] -[2023-10-10 22:09:26,162][98560] Updated weights for policy 1, policy_version 35172 (0.0008) -[2023-10-10 22:09:26,521][98560] Updated weights for policy 1, policy_version 35182 (0.0009) -[2023-10-10 22:09:26,887][98560] Updated weights for policy 1, policy_version 35192 (0.0007) -[2023-10-10 22:09:29,165][98559] Updated weights for policy 0, policy_version 35330 (0.0008) -[2023-10-10 22:09:29,525][98559] Updated weights for policy 0, policy_version 35340 (0.0008) -[2023-10-10 22:09:29,889][98559] Updated weights for policy 0, policy_version 35350 (0.0008) -[2023-10-10 22:09:30,265][98559] Updated weights for policy 0, policy_version 35360 (0.0009) -[2023-10-10 22:09:30,556][97672] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 72253440. Throughput: 0: 1723.5, 1: 1695.0. Samples: 18069960. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-10 22:09:30,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.260')] -[2023-10-10 22:09:30,799][98560] Updated weights for policy 1, policy_version 35202 (0.0010) -[2023-10-10 22:09:31,159][98560] Updated weights for policy 1, policy_version 35212 (0.0011) -[2023-10-10 22:09:31,524][98560] Updated weights for policy 1, policy_version 35222 (0.0010) -[2023-10-10 22:09:31,893][98560] Updated weights for policy 1, policy_version 35232 (0.0011) -[2023-10-10 22:09:34,274][98559] Updated weights for policy 0, policy_version 35370 (0.0008) -[2023-10-10 22:09:34,645][98559] Updated weights for policy 0, policy_version 35380 (0.0009) -[2023-10-10 22:09:35,017][98559] Updated weights for policy 0, policy_version 35390 (0.0008) -[2023-10-10 22:09:35,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 72318976. Throughput: 0: 1696.4, 1: 1697.8. Samples: 18090144. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-10 22:09:35,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.320')] -[2023-10-10 22:09:35,892][98560] Updated weights for policy 1, policy_version 35242 (0.0008) -[2023-10-10 22:09:36,255][98560] Updated weights for policy 1, policy_version 35252 (0.0010) -[2023-10-10 22:09:36,629][98560] Updated weights for policy 1, policy_version 35262 (0.0008) -[2023-10-10 22:09:38,938][98559] Updated weights for policy 0, policy_version 35400 (0.0009) -[2023-10-10 22:09:39,304][98559] Updated weights for policy 0, policy_version 35410 (0.0007) -[2023-10-10 22:09:39,681][98559] Updated weights for policy 0, policy_version 35420 (0.0009) -[2023-10-10 22:09:40,524][98560] Updated weights for policy 1, policy_version 35272 (0.0011) -[2023-10-10 22:09:40,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 72384512. Throughput: 0: 1724.8, 1: 1695.0. Samples: 18100802. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-10 22:09:40,556][97672] Avg episode reward: [(0, '-1.200'), (1, '22.240')] -[2023-10-10 22:09:40,891][98560] Updated weights for policy 1, policy_version 35282 (0.0007) -[2023-10-10 22:09:41,258][98560] Updated weights for policy 1, policy_version 35292 (0.0011) -[2023-10-10 22:09:43,576][98559] Updated weights for policy 0, policy_version 35430 (0.0008) -[2023-10-10 22:09:43,953][98559] Updated weights for policy 0, policy_version 35440 (0.0009) -[2023-10-10 22:09:44,318][98559] Updated weights for policy 0, policy_version 35450 (0.0009) -[2023-10-10 22:09:45,087][98560] Updated weights for policy 1, policy_version 35302 (0.0008) -[2023-10-10 22:09:45,457][98560] Updated weights for policy 1, policy_version 35312 (0.0009) -[2023-10-10 22:09:45,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 72450048. Throughput: 0: 1699.8, 1: 1707.0. Samples: 18120972. Policy #0 lag: (min: 4.0, avg: 9.2, max: 36.0) -[2023-10-10 22:09:45,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.260')] -[2023-10-10 22:09:45,831][98560] Updated weights for policy 1, policy_version 35322 (0.0008) -[2023-10-10 22:09:48,367][98559] Updated weights for policy 0, policy_version 35460 (0.0008) -[2023-10-10 22:09:48,743][98559] Updated weights for policy 0, policy_version 35470 (0.0008) -[2023-10-10 22:09:49,110][98559] Updated weights for policy 0, policy_version 35480 (0.0007) -[2023-10-10 22:09:49,771][98560] Updated weights for policy 1, policy_version 35332 (0.0007) -[2023-10-10 22:09:50,146][98560] Updated weights for policy 1, policy_version 35342 (0.0009) -[2023-10-10 22:09:50,512][98560] Updated weights for policy 1, policy_version 35352 (0.0011) -[2023-10-10 22:09:50,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 72515584. Throughput: 0: 1691.9, 1: 1712.4. Samples: 18141788. Policy #0 lag: (min: 4.0, avg: 9.2, max: 36.0) -[2023-10-10 22:09:50,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.260')] -[2023-10-10 22:09:53,223][98559] Updated weights for policy 0, policy_version 35490 (0.0009) -[2023-10-10 22:09:53,596][98559] Updated weights for policy 0, policy_version 35500 (0.0007) -[2023-10-10 22:09:53,958][98559] Updated weights for policy 0, policy_version 35510 (0.0010) -[2023-10-10 22:09:54,324][98559] Updated weights for policy 0, policy_version 35520 (0.0009) -[2023-10-10 22:09:54,568][98560] Updated weights for policy 1, policy_version 35362 (0.0008) -[2023-10-10 22:09:54,929][98560] Updated weights for policy 1, policy_version 35372 (0.0008) -[2023-10-10 22:09:55,299][98560] Updated weights for policy 1, policy_version 35382 (0.0007) -[2023-10-10 22:09:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 72581120. Throughput: 0: 1716.4, 1: 1715.4. Samples: 18152224. Policy #0 lag: (min: 4.0, avg: 9.2, max: 36.0) -[2023-10-10 22:09:55,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.260')] -[2023-10-10 22:09:55,668][98560] Updated weights for policy 1, policy_version 35392 (0.0007) -[2023-10-10 22:09:58,223][98559] Updated weights for policy 0, policy_version 35530 (0.0009) -[2023-10-10 22:09:58,591][98559] Updated weights for policy 0, policy_version 35540 (0.0008) -[2023-10-10 22:09:58,961][98559] Updated weights for policy 0, policy_version 35550 (0.0009) -[2023-10-10 22:09:59,669][98560] Updated weights for policy 1, policy_version 35402 (0.0008) -[2023-10-10 22:10:00,036][98560] Updated weights for policy 1, policy_version 35412 (0.0007) -[2023-10-10 22:10:00,407][98560] Updated weights for policy 1, policy_version 35422 (0.0007) -[2023-10-10 22:10:00,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 72679424. Throughput: 0: 1699.3, 1: 1718.3. Samples: 18172468. Policy #0 lag: (min: 4.0, avg: 9.2, max: 36.0) -[2023-10-10 22:10:00,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.280')] -[2023-10-10 22:10:02,970][98559] Updated weights for policy 0, policy_version 35560 (0.0008) -[2023-10-10 22:10:03,343][98559] Updated weights for policy 0, policy_version 35570 (0.0007) -[2023-10-10 22:10:03,705][98559] Updated weights for policy 0, policy_version 35580 (0.0007) -[2023-10-10 22:10:04,362][98560] Updated weights for policy 1, policy_version 35432 (0.0007) -[2023-10-10 22:10:04,731][98560] Updated weights for policy 1, policy_version 35442 (0.0009) -[2023-10-10 22:10:05,106][98560] Updated weights for policy 1, policy_version 35452 (0.0007) -[2023-10-10 22:10:05,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 72744960. Throughput: 0: 1716.8, 1: 1708.8. Samples: 18193072. Policy #0 lag: (min: 4.0, avg: 9.2, max: 36.0) -[2023-10-10 22:10:05,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.300')] -[2023-10-10 22:10:07,667][98559] Updated weights for policy 0, policy_version 35590 (0.0008) -[2023-10-10 22:10:08,040][98559] Updated weights for policy 0, policy_version 35600 (0.0009) -[2023-10-10 22:10:08,413][98559] Updated weights for policy 0, policy_version 35610 (0.0010) -[2023-10-10 22:10:09,175][98560] Updated weights for policy 1, policy_version 35462 (0.0009) -[2023-10-10 22:10:09,535][98560] Updated weights for policy 1, policy_version 35472 (0.0007) -[2023-10-10 22:10:09,904][98560] Updated weights for policy 1, policy_version 35482 (0.0007) -[2023-10-10 22:10:10,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 72810496. Throughput: 0: 1705.5, 1: 1723.1. Samples: 18203204. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:10:10,557][97672] Avg episode reward: [(0, '-1.220'), (1, '22.320')] -[2023-10-10 22:10:12,367][98559] Updated weights for policy 0, policy_version 35620 (0.0010) -[2023-10-10 22:10:12,738][98559] Updated weights for policy 0, policy_version 35630 (0.0008) -[2023-10-10 22:10:13,102][98559] Updated weights for policy 0, policy_version 35640 (0.0008) -[2023-10-10 22:10:13,918][98560] Updated weights for policy 1, policy_version 35492 (0.0009) -[2023-10-10 22:10:14,284][98560] Updated weights for policy 1, policy_version 35502 (0.0007) -[2023-10-10 22:10:14,649][98560] Updated weights for policy 1, policy_version 35512 (0.0010) -[2023-10-10 22:10:15,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 72876032. Throughput: 0: 1698.0, 1: 1726.9. Samples: 18224082. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:10:15,557][97672] Avg episode reward: [(0, '-1.220'), (1, '22.360')] -[2023-10-10 22:10:17,077][98559] Updated weights for policy 0, policy_version 35650 (0.0008) -[2023-10-10 22:10:17,450][98559] Updated weights for policy 0, policy_version 35660 (0.0007) -[2023-10-10 22:10:17,823][98559] Updated weights for policy 0, policy_version 35670 (0.0009) -[2023-10-10 22:10:18,186][98559] Updated weights for policy 0, policy_version 35680 (0.0011) -[2023-10-10 22:10:18,568][98560] Updated weights for policy 1, policy_version 35522 (0.0010) -[2023-10-10 22:10:18,937][98560] Updated weights for policy 1, policy_version 35532 (0.0008) -[2023-10-10 22:10:19,306][98560] Updated weights for policy 1, policy_version 35542 (0.0009) -[2023-10-10 22:10:19,678][98560] Updated weights for policy 1, policy_version 35552 (0.0010) -[2023-10-10 22:10:20,556][97672] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 72941568. Throughput: 0: 1727.2, 1: 1698.0. Samples: 18244274. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:10:20,556][97672] Avg episode reward: [(0, '-1.220'), (1, '22.380')] -[2023-10-10 22:10:22,097][98559] Updated weights for policy 0, policy_version 35690 (0.0007) -[2023-10-10 22:10:22,477][98559] Updated weights for policy 0, policy_version 35700 (0.0009) -[2023-10-10 22:10:22,838][98559] Updated weights for policy 0, policy_version 35710 (0.0009) -[2023-10-10 22:10:23,744][98560] Updated weights for policy 1, policy_version 35562 (0.0010) -[2023-10-10 22:10:24,112][98560] Updated weights for policy 1, policy_version 35572 (0.0010) -[2023-10-10 22:10:24,481][98560] Updated weights for policy 1, policy_version 35582 (0.0008) -[2023-10-10 22:10:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 73007104. Throughput: 0: 1697.8, 1: 1725.5. Samples: 18254852. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:10:25,557][97672] Avg episode reward: [(0, '-1.220'), (1, '22.320')] -[2023-10-10 22:10:26,791][98559] Updated weights for policy 0, policy_version 35720 (0.0008) -[2023-10-10 22:10:27,164][98559] Updated weights for policy 0, policy_version 35730 (0.0009) -[2023-10-10 22:10:27,534][98559] Updated weights for policy 0, policy_version 35740 (0.0007) -[2023-10-10 22:10:28,308][98560] Updated weights for policy 1, policy_version 35592 (0.0007) -[2023-10-10 22:10:28,679][98560] Updated weights for policy 1, policy_version 35602 (0.0007) -[2023-10-10 22:10:29,044][98560] Updated weights for policy 1, policy_version 35612 (0.0009) -[2023-10-10 22:10:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 73072640. Throughput: 0: 1724.5, 1: 1706.2. Samples: 18275354. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:10:30,556][97672] Avg episode reward: [(0, '-1.220'), (1, '22.400')] -[2023-10-10 22:10:31,367][98559] Updated weights for policy 0, policy_version 35750 (0.0008) -[2023-10-10 22:10:31,730][98559] Updated weights for policy 0, policy_version 35760 (0.0008) -[2023-10-10 22:10:32,095][98559] Updated weights for policy 0, policy_version 35770 (0.0011) -[2023-10-10 22:10:32,981][98560] Updated weights for policy 1, policy_version 35622 (0.0009) -[2023-10-10 22:10:33,350][98560] Updated weights for policy 1, policy_version 35632 (0.0008) -[2023-10-10 22:10:33,714][98560] Updated weights for policy 1, policy_version 35642 (0.0009) -[2023-10-10 22:10:35,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 73138176. Throughput: 0: 1740.8, 1: 1689.2. Samples: 18296136. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:10:35,556][97672] Avg episode reward: [(0, '-1.220'), (1, '22.380')] -[2023-10-10 22:10:35,568][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000035648_36503552.pth... -[2023-10-10 22:10:35,568][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000035776_36634624.pth... -[2023-10-10 22:10:35,605][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000034176_34996224.pth -[2023-10-10 22:10:35,605][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000034048_34865152.pth -[2023-10-10 22:10:35,906][98559] Updated weights for policy 0, policy_version 35780 (0.0010) -[2023-10-10 22:10:36,279][98559] Updated weights for policy 0, policy_version 35790 (0.0007) -[2023-10-10 22:10:36,643][98559] Updated weights for policy 0, policy_version 35800 (0.0007) -[2023-10-10 22:10:37,947][98560] Updated weights for policy 1, policy_version 35652 (0.0008) -[2023-10-10 22:10:38,306][98560] Updated weights for policy 1, policy_version 35662 (0.0008) -[2023-10-10 22:10:38,672][98560] Updated weights for policy 1, policy_version 35672 (0.0009) -[2023-10-10 22:10:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 73203712. Throughput: 0: 1714.9, 1: 1714.1. Samples: 18306530. Policy #0 lag: (min: 31.0, avg: 31.5, max: 47.0) -[2023-10-10 22:10:40,556][97672] Avg episode reward: [(0, '-1.260'), (1, '22.320')] -[2023-10-10 22:10:40,626][98559] Updated weights for policy 0, policy_version 35810 (0.0009) -[2023-10-10 22:10:40,998][98559] Updated weights for policy 0, policy_version 35820 (0.0011) -[2023-10-10 22:10:41,355][98559] Updated weights for policy 0, policy_version 35830 (0.0010) -[2023-10-10 22:10:41,727][98559] Updated weights for policy 0, policy_version 35840 (0.0010) -[2023-10-10 22:10:42,680][98560] Updated weights for policy 1, policy_version 35682 (0.0009) -[2023-10-10 22:10:43,046][98560] Updated weights for policy 1, policy_version 35692 (0.0010) -[2023-10-10 22:10:43,413][98560] Updated weights for policy 1, policy_version 35702 (0.0009) -[2023-10-10 22:10:43,777][98560] Updated weights for policy 1, policy_version 35712 (0.0007) -[2023-10-10 22:10:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 73269248. Throughput: 0: 1738.0, 1: 1690.4. Samples: 18326746. Policy #0 lag: (min: 31.0, avg: 31.5, max: 47.0) -[2023-10-10 22:10:45,556][97672] Avg episode reward: [(0, '-1.260'), (1, '22.260')] -[2023-10-10 22:10:45,700][98559] Updated weights for policy 0, policy_version 35850 (0.0007) -[2023-10-10 22:10:46,073][98559] Updated weights for policy 0, policy_version 35860 (0.0007) -[2023-10-10 22:10:46,447][98559] Updated weights for policy 0, policy_version 35870 (0.0009) -[2023-10-10 22:10:47,762][98560] Updated weights for policy 1, policy_version 35722 (0.0008) -[2023-10-10 22:10:48,134][98560] Updated weights for policy 1, policy_version 35732 (0.0009) -[2023-10-10 22:10:48,500][98560] Updated weights for policy 1, policy_version 35742 (0.0007) -[2023-10-10 22:10:50,408][98559] Updated weights for policy 0, policy_version 35880 (0.0010) -[2023-10-10 22:10:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 73334784. Throughput: 0: 1728.4, 1: 1696.9. Samples: 18347212. Policy #0 lag: (min: 31.0, avg: 31.5, max: 47.0) -[2023-10-10 22:10:50,556][97672] Avg episode reward: [(0, '-1.260'), (1, '22.220')] -[2023-10-10 22:10:50,778][98559] Updated weights for policy 0, policy_version 35890 (0.0010) -[2023-10-10 22:10:51,137][98559] Updated weights for policy 0, policy_version 35900 (0.0009) -[2023-10-10 22:10:52,469][98560] Updated weights for policy 1, policy_version 35752 (0.0010) -[2023-10-10 22:10:52,836][98560] Updated weights for policy 1, policy_version 35762 (0.0011) -[2023-10-10 22:10:53,196][98560] Updated weights for policy 1, policy_version 35772 (0.0010) -[2023-10-10 22:10:55,103][98559] Updated weights for policy 0, policy_version 35910 (0.0009) -[2023-10-10 22:10:55,469][98559] Updated weights for policy 0, policy_version 35920 (0.0011) -[2023-10-10 22:10:55,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 73400320. Throughput: 0: 1728.1, 1: 1699.4. Samples: 18357442. Policy #0 lag: (min: 31.0, avg: 31.5, max: 47.0) -[2023-10-10 22:10:55,556][97672] Avg episode reward: [(0, '-1.260'), (1, '22.180')] -[2023-10-10 22:10:55,837][98559] Updated weights for policy 0, policy_version 35930 (0.0010) -[2023-10-10 22:10:57,266][98560] Updated weights for policy 1, policy_version 35782 (0.0009) -[2023-10-10 22:10:57,631][98560] Updated weights for policy 1, policy_version 35792 (0.0007) -[2023-10-10 22:10:57,990][98560] Updated weights for policy 1, policy_version 35802 (0.0008) -[2023-10-10 22:10:59,926][98559] Updated weights for policy 0, policy_version 35940 (0.0010) -[2023-10-10 22:11:00,289][98559] Updated weights for policy 0, policy_version 35950 (0.0011) -[2023-10-10 22:11:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 73465856. Throughput: 0: 1730.9, 1: 1680.7. Samples: 18377602. Policy #0 lag: (min: 31.0, avg: 31.5, max: 47.0) -[2023-10-10 22:11:00,556][97672] Avg episode reward: [(0, '-1.260'), (1, '22.140')] -[2023-10-10 22:11:00,654][98559] Updated weights for policy 0, policy_version 35960 (0.0011) -[2023-10-10 22:11:02,023][98560] Updated weights for policy 1, policy_version 35812 (0.0009) -[2023-10-10 22:11:02,399][98560] Updated weights for policy 1, policy_version 35822 (0.0009) -[2023-10-10 22:11:02,762][98560] Updated weights for policy 1, policy_version 35832 (0.0008) -[2023-10-10 22:11:04,752][98559] Updated weights for policy 0, policy_version 35970 (0.0010) -[2023-10-10 22:11:05,122][98559] Updated weights for policy 0, policy_version 35980 (0.0008) -[2023-10-10 22:11:05,489][98559] Updated weights for policy 0, policy_version 35990 (0.0008) -[2023-10-10 22:11:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 73531392. Throughput: 0: 1705.0, 1: 1701.5. Samples: 18397568. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:11:05,556][97672] Avg episode reward: [(0, '-1.260'), (1, '22.160')] -[2023-10-10 22:11:05,858][98559] Updated weights for policy 0, policy_version 36000 (0.0007) -[2023-10-10 22:11:06,801][98560] Updated weights for policy 1, policy_version 35842 (0.0008) -[2023-10-10 22:11:07,163][98560] Updated weights for policy 1, policy_version 35852 (0.0009) -[2023-10-10 22:11:07,531][98560] Updated weights for policy 1, policy_version 35862 (0.0009) -[2023-10-10 22:11:07,900][98560] Updated weights for policy 1, policy_version 35872 (0.0009) -[2023-10-10 22:11:09,788][98559] Updated weights for policy 0, policy_version 36010 (0.0009) -[2023-10-10 22:11:10,160][98559] Updated weights for policy 0, policy_version 36020 (0.0008) -[2023-10-10 22:11:10,530][98559] Updated weights for policy 0, policy_version 36030 (0.0007) -[2023-10-10 22:11:10,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 73596928. Throughput: 0: 1721.0, 1: 1681.3. Samples: 18407952. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:11:10,556][97672] Avg episode reward: [(0, '-1.260'), (1, '22.180')] -[2023-10-10 22:11:11,901][98560] Updated weights for policy 1, policy_version 35882 (0.0008) -[2023-10-10 22:11:12,278][98560] Updated weights for policy 1, policy_version 35892 (0.0008) -[2023-10-10 22:11:12,660][98560] Updated weights for policy 1, policy_version 35902 (0.0008) -[2023-10-10 22:11:14,605][98559] Updated weights for policy 0, policy_version 36040 (0.0010) -[2023-10-10 22:11:14,967][98559] Updated weights for policy 0, policy_version 36050 (0.0010) -[2023-10-10 22:11:15,335][98559] Updated weights for policy 0, policy_version 36060 (0.0010) -[2023-10-10 22:11:15,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 73695232. Throughput: 0: 1716.8, 1: 1689.0. Samples: 18428616. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:11:15,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.120')] -[2023-10-10 22:11:16,658][98560] Updated weights for policy 1, policy_version 35912 (0.0008) -[2023-10-10 22:11:17,031][98560] Updated weights for policy 1, policy_version 35922 (0.0008) -[2023-10-10 22:11:17,393][98560] Updated weights for policy 1, policy_version 35932 (0.0007) -[2023-10-10 22:11:19,297][98559] Updated weights for policy 0, policy_version 36070 (0.0009) -[2023-10-10 22:11:19,658][98559] Updated weights for policy 0, policy_version 36080 (0.0008) -[2023-10-10 22:11:20,029][98559] Updated weights for policy 0, policy_version 36090 (0.0009) -[2023-10-10 22:11:20,556][97672] Fps is (10 sec: 16383.4, 60 sec: 13653.2, 300 sec: 13662.6). Total num frames: 73760768. Throughput: 0: 1689.1, 1: 1704.5. Samples: 18448848. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:11:20,558][97672] Avg episode reward: [(0, '-1.260'), (1, '22.180')] -[2023-10-10 22:11:21,095][98560] Updated weights for policy 1, policy_version 35942 (0.0009) -[2023-10-10 22:11:21,470][98560] Updated weights for policy 1, policy_version 35952 (0.0007) -[2023-10-10 22:11:21,834][98560] Updated weights for policy 1, policy_version 35962 (0.0007) -[2023-10-10 22:11:24,001][98559] Updated weights for policy 0, policy_version 36100 (0.0007) -[2023-10-10 22:11:24,375][98559] Updated weights for policy 0, policy_version 36110 (0.0009) -[2023-10-10 22:11:24,745][98559] Updated weights for policy 0, policy_version 36120 (0.0008) -[2023-10-10 22:11:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 73826304. Throughput: 0: 1717.4, 1: 1680.2. Samples: 18459420. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:11:25,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.280')] -[2023-10-10 22:11:25,991][98560] Updated weights for policy 1, policy_version 35972 (0.0010) -[2023-10-10 22:11:26,360][98560] Updated weights for policy 1, policy_version 35982 (0.0009) -[2023-10-10 22:11:26,732][98560] Updated weights for policy 1, policy_version 35992 (0.0008) -[2023-10-10 22:11:28,601][98559] Updated weights for policy 0, policy_version 36130 (0.0008) -[2023-10-10 22:11:28,984][98559] Updated weights for policy 0, policy_version 36140 (0.0007) -[2023-10-10 22:11:29,347][98559] Updated weights for policy 0, policy_version 36150 (0.0010) -[2023-10-10 22:11:29,725][98559] Updated weights for policy 0, policy_version 36160 (0.0010) -[2023-10-10 22:11:30,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 73891840. Throughput: 0: 1699.1, 1: 1696.8. Samples: 18479564. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:11:30,557][97672] Avg episode reward: [(0, '-1.320'), (1, '22.280')] -[2023-10-10 22:11:30,862][98560] Updated weights for policy 1, policy_version 36002 (0.0010) -[2023-10-10 22:11:31,225][98560] Updated weights for policy 1, policy_version 36012 (0.0011) -[2023-10-10 22:11:31,604][98560] Updated weights for policy 1, policy_version 36022 (0.0009) -[2023-10-10 22:11:31,970][98560] Updated weights for policy 1, policy_version 36032 (0.0009) -[2023-10-10 22:11:33,583][98559] Updated weights for policy 0, policy_version 36170 (0.0007) -[2023-10-10 22:11:33,955][98559] Updated weights for policy 0, policy_version 36180 (0.0007) -[2023-10-10 22:11:34,318][98559] Updated weights for policy 0, policy_version 36190 (0.0009) -[2023-10-10 22:11:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 73957376. Throughput: 0: 1703.3, 1: 1700.3. Samples: 18500378. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:11:35,557][97672] Avg episode reward: [(0, '-1.320'), (1, '22.300')] -[2023-10-10 22:11:36,152][98560] Updated weights for policy 1, policy_version 36042 (0.0009) -[2023-10-10 22:11:36,515][98560] Updated weights for policy 1, policy_version 36052 (0.0010) -[2023-10-10 22:11:36,877][98560] Updated weights for policy 1, policy_version 36062 (0.0010) -[2023-10-10 22:11:38,582][98559] Updated weights for policy 0, policy_version 36200 (0.0008) -[2023-10-10 22:11:38,958][98559] Updated weights for policy 0, policy_version 36210 (0.0007) -[2023-10-10 22:11:39,324][98559] Updated weights for policy 0, policy_version 36220 (0.0009) -[2023-10-10 22:11:40,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 74022912. Throughput: 0: 1722.6, 1: 1681.8. Samples: 18510640. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:11:40,556][97672] Avg episode reward: [(0, '-1.320'), (1, '22.300')] -[2023-10-10 22:11:40,996][98560] Updated weights for policy 1, policy_version 36072 (0.0009) -[2023-10-10 22:11:41,365][98560] Updated weights for policy 1, policy_version 36082 (0.0007) -[2023-10-10 22:11:41,726][98560] Updated weights for policy 1, policy_version 36092 (0.0007) -[2023-10-10 22:11:43,349][98559] Updated weights for policy 0, policy_version 36230 (0.0010) -[2023-10-10 22:11:43,711][98559] Updated weights for policy 0, policy_version 36240 (0.0009) -[2023-10-10 22:11:44,089][98559] Updated weights for policy 0, policy_version 36250 (0.0007) -[2023-10-10 22:11:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 74088448. Throughput: 0: 1695.7, 1: 1700.3. Samples: 18530424. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:11:45,557][97672] Avg episode reward: [(0, '-1.320'), (1, '22.260')] -[2023-10-10 22:11:45,558][98560] Updated weights for policy 1, policy_version 36102 (0.0008) -[2023-10-10 22:11:45,920][98560] Updated weights for policy 1, policy_version 36112 (0.0007) -[2023-10-10 22:11:46,284][98560] Updated weights for policy 1, policy_version 36122 (0.0007) -[2023-10-10 22:11:48,107][98559] Updated weights for policy 0, policy_version 36260 (0.0010) -[2023-10-10 22:11:48,484][98559] Updated weights for policy 0, policy_version 36270 (0.0009) -[2023-10-10 22:11:48,852][98559] Updated weights for policy 0, policy_version 36280 (0.0007) -[2023-10-10 22:11:50,338][98560] Updated weights for policy 1, policy_version 36132 (0.0008) -[2023-10-10 22:11:50,556][97672] Fps is (10 sec: 13106.6, 60 sec: 13653.2, 300 sec: 13662.6). Total num frames: 74153984. Throughput: 0: 1712.0, 1: 1705.5. Samples: 18551356. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:11:50,558][97672] Avg episode reward: [(0, '-1.320'), (1, '22.220')] -[2023-10-10 22:11:50,709][98560] Updated weights for policy 1, policy_version 36142 (0.0008) -[2023-10-10 22:11:51,074][98560] Updated weights for policy 1, policy_version 36152 (0.0007) -[2023-10-10 22:11:52,882][98559] Updated weights for policy 0, policy_version 36290 (0.0008) -[2023-10-10 22:11:53,246][98559] Updated weights for policy 0, policy_version 36300 (0.0009) -[2023-10-10 22:11:53,621][98559] Updated weights for policy 0, policy_version 36310 (0.0008) -[2023-10-10 22:11:53,995][98559] Updated weights for policy 0, policy_version 36320 (0.0009) -[2023-10-10 22:11:55,038][98560] Updated weights for policy 1, policy_version 36162 (0.0008) -[2023-10-10 22:11:55,407][98560] Updated weights for policy 1, policy_version 36172 (0.0008) -[2023-10-10 22:11:55,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 74219520. Throughput: 0: 1709.4, 1: 1695.9. Samples: 18561190. Policy #0 lag: (min: 16.0, avg: 39.2, max: 48.0) -[2023-10-10 22:11:55,556][97672] Avg episode reward: [(0, '-1.340'), (1, '22.180')] -[2023-10-10 22:11:55,769][98560] Updated weights for policy 1, policy_version 36182 (0.0007) -[2023-10-10 22:11:56,138][98560] Updated weights for policy 1, policy_version 36192 (0.0008) -[2023-10-10 22:11:57,944][98559] Updated weights for policy 0, policy_version 36330 (0.0009) -[2023-10-10 22:11:58,318][98559] Updated weights for policy 0, policy_version 36340 (0.0009) -[2023-10-10 22:11:58,683][98559] Updated weights for policy 0, policy_version 36350 (0.0009) -[2023-10-10 22:12:00,179][98560] Updated weights for policy 1, policy_version 36202 (0.0011) -[2023-10-10 22:12:00,538][98560] Updated weights for policy 1, policy_version 36212 (0.0009) -[2023-10-10 22:12:00,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 74285056. Throughput: 0: 1694.4, 1: 1706.6. Samples: 18581664. Policy #0 lag: (min: 16.0, avg: 39.2, max: 48.0) -[2023-10-10 22:12:00,557][97672] Avg episode reward: [(0, '-1.340'), (1, '22.180')] -[2023-10-10 22:12:00,909][98560] Updated weights for policy 1, policy_version 36222 (0.0010) -[2023-10-10 22:12:02,571][98559] Updated weights for policy 0, policy_version 36360 (0.0008) -[2023-10-10 22:12:02,926][98559] Updated weights for policy 0, policy_version 36370 (0.0008) -[2023-10-10 22:12:03,304][98559] Updated weights for policy 0, policy_version 36380 (0.0008) -[2023-10-10 22:12:04,808][98560] Updated weights for policy 1, policy_version 36232 (0.0009) -[2023-10-10 22:12:05,171][98560] Updated weights for policy 1, policy_version 36242 (0.0010) -[2023-10-10 22:12:05,545][98560] Updated weights for policy 1, policy_version 36252 (0.0008) -[2023-10-10 22:12:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 74350592. Throughput: 0: 1720.2, 1: 1699.6. Samples: 18602740. Policy #0 lag: (min: 16.0, avg: 39.2, max: 48.0) -[2023-10-10 22:12:05,556][97672] Avg episode reward: [(0, '-1.340'), (1, '22.200')] -[2023-10-10 22:12:07,275][98559] Updated weights for policy 0, policy_version 36390 (0.0010) -[2023-10-10 22:12:07,640][98559] Updated weights for policy 0, policy_version 36400 (0.0007) -[2023-10-10 22:12:08,015][98559] Updated weights for policy 0, policy_version 36410 (0.0007) -[2023-10-10 22:12:09,454][98560] Updated weights for policy 1, policy_version 36262 (0.0009) -[2023-10-10 22:12:09,826][98560] Updated weights for policy 1, policy_version 36272 (0.0008) -[2023-10-10 22:12:10,185][98560] Updated weights for policy 1, policy_version 36282 (0.0010) -[2023-10-10 22:12:10,556][97672] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 74448896. Throughput: 0: 1689.2, 1: 1707.5. Samples: 18612272. Policy #0 lag: (min: 16.0, avg: 39.2, max: 48.0) -[2023-10-10 22:12:10,557][97672] Avg episode reward: [(0, '-1.340'), (1, '22.220')] -[2023-10-10 22:12:11,988][98559] Updated weights for policy 0, policy_version 36420 (0.0008) -[2023-10-10 22:12:12,361][98559] Updated weights for policy 0, policy_version 36430 (0.0007) -[2023-10-10 22:12:12,720][98559] Updated weights for policy 0, policy_version 36440 (0.0008) -[2023-10-10 22:12:14,154][98560] Updated weights for policy 1, policy_version 36292 (0.0008) -[2023-10-10 22:12:14,527][98560] Updated weights for policy 1, policy_version 36302 (0.0008) -[2023-10-10 22:12:14,889][98560] Updated weights for policy 1, policy_version 36312 (0.0010) -[2023-10-10 22:12:15,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 74514432. Throughput: 0: 1703.2, 1: 1719.6. Samples: 18633590. Policy #0 lag: (min: 16.0, avg: 39.2, max: 48.0) -[2023-10-10 22:12:15,557][97672] Avg episode reward: [(0, '-1.340'), (1, '22.260')] -[2023-10-10 22:12:16,824][98559] Updated weights for policy 0, policy_version 36450 (0.0008) -[2023-10-10 22:12:17,188][98559] Updated weights for policy 0, policy_version 36460 (0.0010) -[2023-10-10 22:12:17,564][98559] Updated weights for policy 0, policy_version 36470 (0.0010) -[2023-10-10 22:12:17,923][98559] Updated weights for policy 0, policy_version 36480 (0.0007) -[2023-10-10 22:12:18,806][98560] Updated weights for policy 1, policy_version 36322 (0.0009) -[2023-10-10 22:12:19,179][98560] Updated weights for policy 1, policy_version 36332 (0.0010) -[2023-10-10 22:12:19,547][98560] Updated weights for policy 1, policy_version 36342 (0.0011) -[2023-10-10 22:12:19,915][98560] Updated weights for policy 1, policy_version 36352 (0.0010) -[2023-10-10 22:12:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 74579968. Throughput: 0: 1703.4, 1: 1704.0. Samples: 18653712. Policy #0 lag: (min: 8.0, avg: 31.7, max: 40.0) -[2023-10-10 22:12:20,557][97672] Avg episode reward: [(0, '-1.340'), (1, '22.260')] -[2023-10-10 22:12:22,005][98559] Updated weights for policy 0, policy_version 36490 (0.0008) -[2023-10-10 22:12:22,368][98559] Updated weights for policy 0, policy_version 36500 (0.0007) -[2023-10-10 22:12:22,738][98559] Updated weights for policy 0, policy_version 36510 (0.0007) -[2023-10-10 22:12:23,972][98560] Updated weights for policy 1, policy_version 36362 (0.0008) -[2023-10-10 22:12:24,347][98560] Updated weights for policy 1, policy_version 36372 (0.0010) -[2023-10-10 22:12:24,706][98560] Updated weights for policy 1, policy_version 36382 (0.0008) -[2023-10-10 22:12:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 74645504. Throughput: 0: 1677.7, 1: 1731.6. Samples: 18664062. Policy #0 lag: (min: 8.0, avg: 31.7, max: 40.0) -[2023-10-10 22:12:25,557][97672] Avg episode reward: [(0, '-1.320'), (1, '22.320')] -[2023-10-10 22:12:26,749][98559] Updated weights for policy 0, policy_version 36520 (0.0009) -[2023-10-10 22:12:27,111][98559] Updated weights for policy 0, policy_version 36530 (0.0008) -[2023-10-10 22:12:27,472][98559] Updated weights for policy 0, policy_version 36540 (0.0007) -[2023-10-10 22:12:29,025][98560] Updated weights for policy 1, policy_version 36392 (0.0009) -[2023-10-10 22:12:29,401][98560] Updated weights for policy 1, policy_version 36402 (0.0009) -[2023-10-10 22:12:29,773][98560] Updated weights for policy 1, policy_version 36412 (0.0009) -[2023-10-10 22:12:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 74711040. Throughput: 0: 1706.2, 1: 1724.0. Samples: 18684782. Policy #0 lag: (min: 8.0, avg: 31.7, max: 40.0) -[2023-10-10 22:12:30,557][97672] Avg episode reward: [(0, '-1.300'), (1, '22.420')] -[2023-10-10 22:12:31,618][98559] Updated weights for policy 0, policy_version 36550 (0.0009) -[2023-10-10 22:12:31,985][98559] Updated weights for policy 0, policy_version 36560 (0.0008) -[2023-10-10 22:12:32,338][98559] Updated weights for policy 0, policy_version 36570 (0.0008) -[2023-10-10 22:12:33,730][98560] Updated weights for policy 1, policy_version 36422 (0.0008) -[2023-10-10 22:12:34,102][98560] Updated weights for policy 1, policy_version 36432 (0.0008) -[2023-10-10 22:12:34,474][98560] Updated weights for policy 1, policy_version 36442 (0.0008) -[2023-10-10 22:12:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 74776576. Throughput: 0: 1706.7, 1: 1690.8. Samples: 18704240. Policy #0 lag: (min: 8.0, avg: 31.7, max: 40.0) -[2023-10-10 22:12:35,557][97672] Avg episode reward: [(0, '-1.300'), (1, '22.480')] -[2023-10-10 22:12:35,569][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000036576_37453824.pth... -[2023-10-10 22:12:35,569][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000036448_37322752.pth... -[2023-10-10 22:12:35,599][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000034976_35815424.pth -[2023-10-10 22:12:35,615][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000034848_35684352.pth -[2023-10-10 22:12:36,238][98559] Updated weights for policy 0, policy_version 36580 (0.0007) -[2023-10-10 22:12:36,607][98559] Updated weights for policy 0, policy_version 36590 (0.0007) -[2023-10-10 22:12:36,971][98559] Updated weights for policy 0, policy_version 36600 (0.0007) -[2023-10-10 22:12:38,427][98560] Updated weights for policy 1, policy_version 36452 (0.0010) -[2023-10-10 22:12:38,808][98560] Updated weights for policy 1, policy_version 36462 (0.0008) -[2023-10-10 22:12:39,182][98560] Updated weights for policy 1, policy_version 36472 (0.0009) -[2023-10-10 22:12:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 74842112. Throughput: 0: 1691.1, 1: 1721.1. Samples: 18714744. Policy #0 lag: (min: 8.0, avg: 31.7, max: 40.0) -[2023-10-10 22:12:40,557][97672] Avg episode reward: [(0, '-1.300'), (1, '22.420')] -[2023-10-10 22:12:40,910][98559] Updated weights for policy 0, policy_version 36610 (0.0008) -[2023-10-10 22:12:41,276][98559] Updated weights for policy 0, policy_version 36620 (0.0007) -[2023-10-10 22:12:41,651][98559] Updated weights for policy 0, policy_version 36630 (0.0007) -[2023-10-10 22:12:42,009][98559] Updated weights for policy 0, policy_version 36640 (0.0007) -[2023-10-10 22:12:43,304][98560] Updated weights for policy 1, policy_version 36482 (0.0008) -[2023-10-10 22:12:43,675][98560] Updated weights for policy 1, policy_version 36492 (0.0007) -[2023-10-10 22:12:44,043][98560] Updated weights for policy 1, policy_version 36502 (0.0008) -[2023-10-10 22:12:44,410][98560] Updated weights for policy 1, policy_version 36512 (0.0007) -[2023-10-10 22:12:45,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 74907648. Throughput: 0: 1710.4, 1: 1702.8. Samples: 18735262. Policy #0 lag: (min: 2.0, avg: 3.1, max: 24.0) -[2023-10-10 22:12:45,557][97672] Avg episode reward: [(0, '-1.320'), (1, '22.460')] -[2023-10-10 22:12:46,013][98559] Updated weights for policy 0, policy_version 36650 (0.0009) -[2023-10-10 22:12:46,384][98559] Updated weights for policy 0, policy_version 36660 (0.0007) -[2023-10-10 22:12:46,742][98559] Updated weights for policy 0, policy_version 36670 (0.0009) -[2023-10-10 22:12:48,336][98560] Updated weights for policy 1, policy_version 36522 (0.0010) -[2023-10-10 22:12:48,704][98560] Updated weights for policy 1, policy_version 36532 (0.0010) -[2023-10-10 22:12:49,076][98560] Updated weights for policy 1, policy_version 36542 (0.0007) -[2023-10-10 22:12:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 74973184. Throughput: 0: 1709.1, 1: 1687.0. Samples: 18755564. Policy #0 lag: (min: 2.0, avg: 3.1, max: 24.0) -[2023-10-10 22:12:50,557][97672] Avg episode reward: [(0, '-1.320'), (1, '22.500')] -[2023-10-10 22:12:50,820][98559] Updated weights for policy 0, policy_version 36680 (0.0011) -[2023-10-10 22:12:51,196][98559] Updated weights for policy 0, policy_version 36690 (0.0010) -[2023-10-10 22:12:51,553][98559] Updated weights for policy 0, policy_version 36700 (0.0008) -[2023-10-10 22:12:53,134][98560] Updated weights for policy 1, policy_version 36552 (0.0009) -[2023-10-10 22:12:53,497][98560] Updated weights for policy 1, policy_version 36562 (0.0009) -[2023-10-10 22:12:53,868][98560] Updated weights for policy 1, policy_version 36572 (0.0008) -[2023-10-10 22:12:55,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 75038720. Throughput: 0: 1709.5, 1: 1708.1. Samples: 18766064. Policy #0 lag: (min: 2.0, avg: 3.1, max: 24.0) -[2023-10-10 22:12:55,557][97672] Avg episode reward: [(0, '-1.320'), (1, '22.420')] -[2023-10-10 22:12:55,562][98559] Updated weights for policy 0, policy_version 36710 (0.0008) -[2023-10-10 22:12:55,932][98559] Updated weights for policy 0, policy_version 36720 (0.0008) -[2023-10-10 22:12:56,307][98559] Updated weights for policy 0, policy_version 36730 (0.0008) -[2023-10-10 22:12:57,702][98560] Updated weights for policy 1, policy_version 36582 (0.0008) -[2023-10-10 22:12:58,062][98560] Updated weights for policy 1, policy_version 36592 (0.0008) -[2023-10-10 22:12:58,426][98560] Updated weights for policy 1, policy_version 36602 (0.0009) -[2023-10-10 22:13:00,167][98559] Updated weights for policy 0, policy_version 36740 (0.0009) -[2023-10-10 22:13:00,533][98559] Updated weights for policy 0, policy_version 36750 (0.0008) -[2023-10-10 22:13:00,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 75104256. Throughput: 0: 1711.3, 1: 1676.6. Samples: 18786044. Policy #0 lag: (min: 2.0, avg: 3.1, max: 24.0) -[2023-10-10 22:13:00,556][97672] Avg episode reward: [(0, '-1.320'), (1, '22.400')] -[2023-10-10 22:13:00,903][98559] Updated weights for policy 0, policy_version 36760 (0.0009) -[2023-10-10 22:13:02,371][98560] Updated weights for policy 1, policy_version 36612 (0.0008) -[2023-10-10 22:13:02,731][98560] Updated weights for policy 1, policy_version 36622 (0.0009) -[2023-10-10 22:13:03,094][98560] Updated weights for policy 1, policy_version 36632 (0.0009) -[2023-10-10 22:13:04,907][98559] Updated weights for policy 0, policy_version 36770 (0.0009) -[2023-10-10 22:13:05,277][98559] Updated weights for policy 0, policy_version 36780 (0.0010) -[2023-10-10 22:13:05,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 75169792. Throughput: 0: 1701.7, 1: 1694.7. Samples: 18806550. Policy #0 lag: (min: 2.0, avg: 3.1, max: 24.0) -[2023-10-10 22:13:05,557][97672] Avg episode reward: [(0, '-1.320'), (1, '22.280')] -[2023-10-10 22:13:05,657][98559] Updated weights for policy 0, policy_version 36790 (0.0008) -[2023-10-10 22:13:06,021][98559] Updated weights for policy 0, policy_version 36800 (0.0009) -[2023-10-10 22:13:07,239][98560] Updated weights for policy 1, policy_version 36642 (0.0007) -[2023-10-10 22:13:07,609][98560] Updated weights for policy 1, policy_version 36652 (0.0007) -[2023-10-10 22:13:07,980][98560] Updated weights for policy 1, policy_version 36662 (0.0009) -[2023-10-10 22:13:08,354][98560] Updated weights for policy 1, policy_version 36672 (0.0011) -[2023-10-10 22:13:09,989][98559] Updated weights for policy 0, policy_version 36810 (0.0010) -[2023-10-10 22:13:10,353][98559] Updated weights for policy 0, policy_version 36820 (0.0007) -[2023-10-10 22:13:10,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 75235328. Throughput: 0: 1714.7, 1: 1688.7. Samples: 18817214. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 22:13:10,557][97672] Avg episode reward: [(0, '-1.300'), (1, '22.220')] -[2023-10-10 22:13:10,729][98559] Updated weights for policy 0, policy_version 36830 (0.0007) -[2023-10-10 22:13:12,255][98560] Updated weights for policy 1, policy_version 36682 (0.0007) -[2023-10-10 22:13:12,624][98560] Updated weights for policy 1, policy_version 36692 (0.0009) -[2023-10-10 22:13:13,000][98560] Updated weights for policy 1, policy_version 36702 (0.0009) -[2023-10-10 22:13:14,796][98559] Updated weights for policy 0, policy_version 36840 (0.0011) -[2023-10-10 22:13:15,167][98559] Updated weights for policy 0, policy_version 36850 (0.0011) -[2023-10-10 22:13:15,526][98559] Updated weights for policy 0, policy_version 36860 (0.0010) -[2023-10-10 22:13:15,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 75300864. Throughput: 0: 1717.5, 1: 1676.9. Samples: 18837528. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 22:13:15,556][97672] Avg episode reward: [(0, '-1.300'), (1, '22.200')] -[2023-10-10 22:13:17,076][98560] Updated weights for policy 1, policy_version 36712 (0.0008) -[2023-10-10 22:13:17,436][98560] Updated weights for policy 1, policy_version 36722 (0.0010) -[2023-10-10 22:13:17,811][98560] Updated weights for policy 1, policy_version 36732 (0.0011) -[2023-10-10 22:13:19,467][98559] Updated weights for policy 0, policy_version 36870 (0.0010) -[2023-10-10 22:13:19,832][98559] Updated weights for policy 0, policy_version 36880 (0.0008) -[2023-10-10 22:13:20,201][98559] Updated weights for policy 0, policy_version 36890 (0.0007) -[2023-10-10 22:13:20,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 75399168. Throughput: 0: 1696.8, 1: 1707.5. Samples: 18857436. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 22:13:20,557][97672] Avg episode reward: [(0, '-1.280'), (1, '22.160')] -[2023-10-10 22:13:21,743][98560] Updated weights for policy 1, policy_version 36742 (0.0009) -[2023-10-10 22:13:22,115][98560] Updated weights for policy 1, policy_version 36752 (0.0007) -[2023-10-10 22:13:22,479][98560] Updated weights for policy 1, policy_version 36762 (0.0007) -[2023-10-10 22:13:24,157][98559] Updated weights for policy 0, policy_version 36900 (0.0009) -[2023-10-10 22:13:24,529][98559] Updated weights for policy 0, policy_version 36910 (0.0009) -[2023-10-10 22:13:24,884][98559] Updated weights for policy 0, policy_version 36920 (0.0007) -[2023-10-10 22:13:25,556][97672] Fps is (10 sec: 16383.5, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 75464704. Throughput: 0: 1726.0, 1: 1681.2. Samples: 18868066. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 22:13:25,557][97672] Avg episode reward: [(0, '-1.280'), (1, '22.200')] -[2023-10-10 22:13:26,559][98560] Updated weights for policy 1, policy_version 36772 (0.0009) -[2023-10-10 22:13:26,923][98560] Updated weights for policy 1, policy_version 36782 (0.0008) -[2023-10-10 22:13:27,303][98560] Updated weights for policy 1, policy_version 36792 (0.0009) -[2023-10-10 22:13:28,767][98559] Updated weights for policy 0, policy_version 36930 (0.0008) -[2023-10-10 22:13:29,128][98559] Updated weights for policy 0, policy_version 36940 (0.0007) -[2023-10-10 22:13:29,483][98559] Updated weights for policy 0, policy_version 36950 (0.0009) -[2023-10-10 22:13:29,853][98559] Updated weights for policy 0, policy_version 36960 (0.0007) -[2023-10-10 22:13:30,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 75530240. Throughput: 0: 1712.1, 1: 1690.5. Samples: 18888376. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 22:13:30,557][97672] Avg episode reward: [(0, '-1.280'), (1, '22.260')] -[2023-10-10 22:13:31,274][98560] Updated weights for policy 1, policy_version 36802 (0.0009) -[2023-10-10 22:13:31,645][98560] Updated weights for policy 1, policy_version 36812 (0.0008) -[2023-10-10 22:13:32,011][98560] Updated weights for policy 1, policy_version 36822 (0.0007) -[2023-10-10 22:13:32,382][98560] Updated weights for policy 1, policy_version 36832 (0.0007) -[2023-10-10 22:13:33,729][98559] Updated weights for policy 0, policy_version 36970 (0.0008) -[2023-10-10 22:13:34,100][98559] Updated weights for policy 0, policy_version 36980 (0.0008) -[2023-10-10 22:13:34,458][98559] Updated weights for policy 0, policy_version 36990 (0.0008) -[2023-10-10 22:13:35,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 75595776. Throughput: 0: 1702.6, 1: 1708.8. Samples: 18909076. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 22:13:35,556][97672] Avg episode reward: [(0, '-1.280'), (1, '22.280')] -[2023-10-10 22:13:36,445][98560] Updated weights for policy 1, policy_version 36842 (0.0009) -[2023-10-10 22:13:36,819][98560] Updated weights for policy 1, policy_version 36852 (0.0009) -[2023-10-10 22:13:37,184][98560] Updated weights for policy 1, policy_version 36862 (0.0008) -[2023-10-10 22:13:38,481][98559] Updated weights for policy 0, policy_version 37000 (0.0009) -[2023-10-10 22:13:38,851][98559] Updated weights for policy 0, policy_version 37010 (0.0010) -[2023-10-10 22:13:39,209][98559] Updated weights for policy 0, policy_version 37020 (0.0009) -[2023-10-10 22:13:40,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 75661312. Throughput: 0: 1728.6, 1: 1678.7. Samples: 18919394. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 22:13:40,557][97672] Avg episode reward: [(0, '-1.280'), (1, '22.280')] -[2023-10-10 22:13:41,309][98560] Updated weights for policy 1, policy_version 36872 (0.0008) -[2023-10-10 22:13:41,677][98560] Updated weights for policy 1, policy_version 36882 (0.0009) -[2023-10-10 22:13:42,046][98560] Updated weights for policy 1, policy_version 36892 (0.0009) -[2023-10-10 22:13:43,267][98559] Updated weights for policy 0, policy_version 37030 (0.0009) -[2023-10-10 22:13:43,629][98559] Updated weights for policy 0, policy_version 37040 (0.0008) -[2023-10-10 22:13:44,000][98559] Updated weights for policy 0, policy_version 37050 (0.0009) -[2023-10-10 22:13:45,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 75726848. Throughput: 0: 1697.9, 1: 1703.1. Samples: 18939092. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 22:13:45,557][97672] Avg episode reward: [(0, '-1.280'), (1, '22.360')] -[2023-10-10 22:13:45,894][98560] Updated weights for policy 1, policy_version 36902 (0.0010) -[2023-10-10 22:13:46,270][98560] Updated weights for policy 1, policy_version 36912 (0.0010) -[2023-10-10 22:13:46,637][98560] Updated weights for policy 1, policy_version 36922 (0.0008) -[2023-10-10 22:13:47,913][98559] Updated weights for policy 0, policy_version 37060 (0.0009) -[2023-10-10 22:13:48,276][98559] Updated weights for policy 0, policy_version 37070 (0.0011) -[2023-10-10 22:13:48,649][98559] Updated weights for policy 0, policy_version 37080 (0.0008) -[2023-10-10 22:13:50,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 75792384. Throughput: 0: 1708.8, 1: 1706.6. Samples: 18960240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 22:13:50,557][97672] Avg episode reward: [(0, '-1.280'), (1, '22.320')] -[2023-10-10 22:13:50,767][98560] Updated weights for policy 1, policy_version 36932 (0.0008) -[2023-10-10 22:13:51,137][98560] Updated weights for policy 1, policy_version 36942 (0.0011) -[2023-10-10 22:13:51,508][98560] Updated weights for policy 1, policy_version 36952 (0.0009) -[2023-10-10 22:13:52,637][98559] Updated weights for policy 0, policy_version 37090 (0.0010) -[2023-10-10 22:13:53,002][98559] Updated weights for policy 0, policy_version 37100 (0.0008) -[2023-10-10 22:13:53,367][98559] Updated weights for policy 0, policy_version 37110 (0.0008) -[2023-10-10 22:13:53,734][98559] Updated weights for policy 0, policy_version 37120 (0.0009) -[2023-10-10 22:13:55,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 75857920. Throughput: 0: 1706.5, 1: 1687.9. Samples: 18969964. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 22:13:55,556][97672] Avg episode reward: [(0, '-1.280'), (1, '22.340')] -[2023-10-10 22:13:55,605][98560] Updated weights for policy 1, policy_version 36962 (0.0009) -[2023-10-10 22:13:55,960][98560] Updated weights for policy 1, policy_version 36972 (0.0007) -[2023-10-10 22:13:56,318][98560] Updated weights for policy 1, policy_version 36982 (0.0008) -[2023-10-10 22:13:56,679][98560] Updated weights for policy 1, policy_version 36992 (0.0009) -[2023-10-10 22:13:57,743][98559] Updated weights for policy 0, policy_version 37130 (0.0008) -[2023-10-10 22:13:58,107][98559] Updated weights for policy 0, policy_version 37140 (0.0009) -[2023-10-10 22:13:58,468][98559] Updated weights for policy 0, policy_version 37150 (0.0009) -[2023-10-10 22:14:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 75923456. Throughput: 0: 1697.3, 1: 1700.8. Samples: 18990442. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) -[2023-10-10 22:14:00,557][97672] Avg episode reward: [(0, '-1.280'), (1, '22.320')] -[2023-10-10 22:14:00,856][98560] Updated weights for policy 1, policy_version 37002 (0.0009) -[2023-10-10 22:14:01,227][98560] Updated weights for policy 1, policy_version 37012 (0.0008) -[2023-10-10 22:14:01,589][98560] Updated weights for policy 1, policy_version 37022 (0.0008) -[2023-10-10 22:14:02,581][98559] Updated weights for policy 0, policy_version 37160 (0.0010) -[2023-10-10 22:14:02,953][98559] Updated weights for policy 0, policy_version 37170 (0.0010) -[2023-10-10 22:14:03,323][98559] Updated weights for policy 0, policy_version 37180 (0.0010) -[2023-10-10 22:14:05,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 75988992. Throughput: 0: 1720.0, 1: 1700.4. Samples: 19011352. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) -[2023-10-10 22:14:05,557][97672] Avg episode reward: [(0, '-1.280'), (1, '22.320')] -[2023-10-10 22:14:05,619][98560] Updated weights for policy 1, policy_version 37032 (0.0007) -[2023-10-10 22:14:06,000][98560] Updated weights for policy 1, policy_version 37042 (0.0009) -[2023-10-10 22:14:06,370][98560] Updated weights for policy 1, policy_version 37052 (0.0009) -[2023-10-10 22:14:07,267][98559] Updated weights for policy 0, policy_version 37190 (0.0009) -[2023-10-10 22:14:07,633][98559] Updated weights for policy 0, policy_version 37200 (0.0010) -[2023-10-10 22:14:08,008][98559] Updated weights for policy 0, policy_version 37210 (0.0009) -[2023-10-10 22:14:10,456][98560] Updated weights for policy 1, policy_version 37062 (0.0008) -[2023-10-10 22:14:10,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 76054528. Throughput: 0: 1693.8, 1: 1689.7. Samples: 19020320. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) -[2023-10-10 22:14:10,556][97672] Avg episode reward: [(0, '-1.280'), (1, '22.300')] -[2023-10-10 22:14:10,825][98560] Updated weights for policy 1, policy_version 37072 (0.0010) -[2023-10-10 22:14:11,189][98560] Updated weights for policy 1, policy_version 37082 (0.0010) -[2023-10-10 22:14:11,943][98559] Updated weights for policy 0, policy_version 37220 (0.0007) -[2023-10-10 22:14:12,307][98559] Updated weights for policy 0, policy_version 37230 (0.0008) -[2023-10-10 22:14:12,684][98559] Updated weights for policy 0, policy_version 37240 (0.0010) -[2023-10-10 22:14:15,247][98560] Updated weights for policy 1, policy_version 37092 (0.0009) -[2023-10-10 22:14:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 76120064. Throughput: 0: 1708.7, 1: 1693.2. Samples: 19041462. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) -[2023-10-10 22:14:15,556][97672] Avg episode reward: [(0, '-1.280'), (1, '22.240')] -[2023-10-10 22:14:15,606][98560] Updated weights for policy 1, policy_version 37102 (0.0007) -[2023-10-10 22:14:15,969][98560] Updated weights for policy 1, policy_version 37112 (0.0007) -[2023-10-10 22:14:16,503][98559] Updated weights for policy 0, policy_version 37250 (0.0008) -[2023-10-10 22:14:16,868][98559] Updated weights for policy 0, policy_version 37260 (0.0007) -[2023-10-10 22:14:17,240][98559] Updated weights for policy 0, policy_version 37270 (0.0010) -[2023-10-10 22:14:17,611][98559] Updated weights for policy 0, policy_version 37280 (0.0009) -[2023-10-10 22:14:19,799][98560] Updated weights for policy 1, policy_version 37122 (0.0008) -[2023-10-10 22:14:20,164][98560] Updated weights for policy 1, policy_version 37132 (0.0007) -[2023-10-10 22:14:20,534][98560] Updated weights for policy 1, policy_version 37142 (0.0007) -[2023-10-10 22:14:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13662.6). Total num frames: 76185600. Throughput: 0: 1721.6, 1: 1699.2. Samples: 19063010. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) -[2023-10-10 22:14:20,556][97672] Avg episode reward: [(0, '-1.260'), (1, '22.220')] -[2023-10-10 22:14:20,898][98560] Updated weights for policy 1, policy_version 37152 (0.0009) -[2023-10-10 22:14:21,508][98559] Updated weights for policy 0, policy_version 37290 (0.0010) -[2023-10-10 22:14:21,881][98559] Updated weights for policy 0, policy_version 37300 (0.0007) -[2023-10-10 22:14:22,245][98559] Updated weights for policy 0, policy_version 37310 (0.0007) -[2023-10-10 22:14:24,945][98560] Updated weights for policy 1, policy_version 37162 (0.0011) -[2023-10-10 22:14:25,308][98560] Updated weights for policy 1, policy_version 37172 (0.0009) -[2023-10-10 22:14:25,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 76251136. Throughput: 0: 1696.8, 1: 1700.2. Samples: 19072262. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) -[2023-10-10 22:14:25,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.160')] -[2023-10-10 22:14:25,672][98560] Updated weights for policy 1, policy_version 37182 (0.0008) -[2023-10-10 22:14:26,201][98559] Updated weights for policy 0, policy_version 37320 (0.0008) -[2023-10-10 22:14:26,563][98559] Updated weights for policy 0, policy_version 37330 (0.0008) -[2023-10-10 22:14:26,930][98559] Updated weights for policy 0, policy_version 37340 (0.0009) -[2023-10-10 22:14:29,477][98560] Updated weights for policy 1, policy_version 37192 (0.0010) -[2023-10-10 22:14:29,849][98560] Updated weights for policy 1, policy_version 37202 (0.0011) -[2023-10-10 22:14:30,209][98560] Updated weights for policy 1, policy_version 37212 (0.0011) -[2023-10-10 22:14:30,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 76349440. Throughput: 0: 1725.6, 1: 1706.4. Samples: 19093532. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 22:14:30,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.080')] -[2023-10-10 22:14:30,943][98559] Updated weights for policy 0, policy_version 37350 (0.0009) -[2023-10-10 22:14:31,302][98559] Updated weights for policy 0, policy_version 37360 (0.0008) -[2023-10-10 22:14:31,669][98559] Updated weights for policy 0, policy_version 37370 (0.0009) -[2023-10-10 22:14:34,249][98560] Updated weights for policy 1, policy_version 37222 (0.0008) -[2023-10-10 22:14:34,615][98560] Updated weights for policy 1, policy_version 37232 (0.0009) -[2023-10-10 22:14:34,983][98560] Updated weights for policy 1, policy_version 37242 (0.0007) -[2023-10-10 22:14:35,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 76414976. Throughput: 0: 1728.3, 1: 1691.0. Samples: 19114110. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 22:14:35,556][97672] Avg episode reward: [(0, '-1.260'), (1, '22.040')] -[2023-10-10 22:14:35,563][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000037248_38141952.pth... -[2023-10-10 22:14:35,597][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000035648_36503552.pth -[2023-10-10 22:14:35,789][98559] Updated weights for policy 0, policy_version 37380 (0.0008) -[2023-10-10 22:14:36,156][98559] Updated weights for policy 0, policy_version 37390 (0.0010) -[2023-10-10 22:14:36,531][98559] Updated weights for policy 0, policy_version 37400 (0.0008) -[2023-10-10 22:14:36,814][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000037408_38305792.pth... -[2023-10-10 22:14:36,843][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000035776_36634624.pth -[2023-10-10 22:14:38,904][98560] Updated weights for policy 1, policy_version 37252 (0.0007) -[2023-10-10 22:14:39,280][98560] Updated weights for policy 1, policy_version 37262 (0.0008) -[2023-10-10 22:14:39,643][98560] Updated weights for policy 1, policy_version 37272 (0.0009) -[2023-10-10 22:14:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 76480512. Throughput: 0: 1714.0, 1: 1711.9. Samples: 19124128. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 22:14:40,556][97672] Avg episode reward: [(0, '-1.260'), (1, '22.080')] -[2023-10-10 22:14:40,578][98559] Updated weights for policy 0, policy_version 37410 (0.0007) -[2023-10-10 22:14:40,953][98559] Updated weights for policy 0, policy_version 37420 (0.0011) -[2023-10-10 22:14:41,309][98559] Updated weights for policy 0, policy_version 37430 (0.0010) -[2023-10-10 22:14:41,674][98559] Updated weights for policy 0, policy_version 37440 (0.0008) -[2023-10-10 22:14:43,455][98560] Updated weights for policy 1, policy_version 37282 (0.0009) -[2023-10-10 22:14:43,812][98560] Updated weights for policy 1, policy_version 37292 (0.0009) -[2023-10-10 22:14:44,179][98560] Updated weights for policy 1, policy_version 37302 (0.0008) -[2023-10-10 22:14:44,546][98560] Updated weights for policy 1, policy_version 37312 (0.0009) -[2023-10-10 22:14:45,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 76546048. Throughput: 0: 1724.1, 1: 1716.1. Samples: 19145254. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 22:14:45,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.120')] -[2023-10-10 22:14:45,639][98559] Updated weights for policy 0, policy_version 37450 (0.0007) -[2023-10-10 22:14:45,998][98559] Updated weights for policy 0, policy_version 37460 (0.0008) -[2023-10-10 22:14:46,369][98559] Updated weights for policy 0, policy_version 37470 (0.0008) -[2023-10-10 22:14:48,617][98560] Updated weights for policy 1, policy_version 37322 (0.0008) -[2023-10-10 22:14:48,988][98560] Updated weights for policy 1, policy_version 37332 (0.0008) -[2023-10-10 22:14:49,358][98560] Updated weights for policy 1, policy_version 37342 (0.0009) -[2023-10-10 22:14:50,430][98559] Updated weights for policy 0, policy_version 37480 (0.0009) -[2023-10-10 22:14:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 76611584. Throughput: 0: 1721.0, 1: 1695.9. Samples: 19165110. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 22:14:50,557][97672] Avg episode reward: [(0, '-1.220'), (1, '22.140')] -[2023-10-10 22:14:50,794][98559] Updated weights for policy 0, policy_version 37490 (0.0008) -[2023-10-10 22:14:51,176][98559] Updated weights for policy 0, policy_version 37500 (0.0007) -[2023-10-10 22:14:53,413][98560] Updated weights for policy 1, policy_version 37352 (0.0008) -[2023-10-10 22:14:53,785][98560] Updated weights for policy 1, policy_version 37362 (0.0010) -[2023-10-10 22:14:54,153][98560] Updated weights for policy 1, policy_version 37372 (0.0007) -[2023-10-10 22:14:54,931][98559] Updated weights for policy 0, policy_version 37510 (0.0008) -[2023-10-10 22:14:55,293][98559] Updated weights for policy 0, policy_version 37520 (0.0007) -[2023-10-10 22:14:55,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 76677120. Throughput: 0: 1724.0, 1: 1736.8. Samples: 19176056. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 22:14:55,556][97672] Avg episode reward: [(0, '-1.220'), (1, '22.080')] -[2023-10-10 22:14:55,656][98559] Updated weights for policy 0, policy_version 37530 (0.0008) -[2023-10-10 22:14:58,197][98560] Updated weights for policy 1, policy_version 37382 (0.0008) -[2023-10-10 22:14:58,564][98560] Updated weights for policy 1, policy_version 37392 (0.0008) -[2023-10-10 22:14:58,939][98560] Updated weights for policy 1, policy_version 37402 (0.0007) -[2023-10-10 22:14:59,659][98559] Updated weights for policy 0, policy_version 37540 (0.0009) -[2023-10-10 22:15:00,017][98559] Updated weights for policy 0, policy_version 37550 (0.0008) -[2023-10-10 22:15:00,383][98559] Updated weights for policy 0, policy_version 37560 (0.0007) -[2023-10-10 22:15:00,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 76742656. Throughput: 0: 1719.4, 1: 1718.6. Samples: 19196174. Policy #0 lag: (min: 36.0, avg: 53.9, max: 56.0) -[2023-10-10 22:15:00,557][97672] Avg episode reward: [(0, '-1.220'), (1, '22.020')] -[2023-10-10 22:15:02,855][98560] Updated weights for policy 1, policy_version 37412 (0.0009) -[2023-10-10 22:15:03,227][98560] Updated weights for policy 1, policy_version 37422 (0.0011) -[2023-10-10 22:15:03,596][98560] Updated weights for policy 1, policy_version 37432 (0.0008) -[2023-10-10 22:15:04,399][98559] Updated weights for policy 0, policy_version 37570 (0.0008) -[2023-10-10 22:15:04,756][98559] Updated weights for policy 0, policy_version 37580 (0.0009) -[2023-10-10 22:15:05,125][98559] Updated weights for policy 0, policy_version 37590 (0.0010) -[2023-10-10 22:15:05,490][98559] Updated weights for policy 0, policy_version 37600 (0.0012) -[2023-10-10 22:15:05,556][97672] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 76840960. Throughput: 0: 1694.8, 1: 1700.3. Samples: 19215788. Policy #0 lag: (min: 36.0, avg: 53.9, max: 56.0) -[2023-10-10 22:15:05,556][97672] Avg episode reward: [(0, '-1.120'), (1, '22.100')] -[2023-10-10 22:15:07,580][98560] Updated weights for policy 1, policy_version 37442 (0.0009) -[2023-10-10 22:15:07,945][98560] Updated weights for policy 1, policy_version 37452 (0.0008) -[2023-10-10 22:15:08,321][98560] Updated weights for policy 1, policy_version 37462 (0.0007) -[2023-10-10 22:15:08,696][98560] Updated weights for policy 1, policy_version 37472 (0.0007) -[2023-10-10 22:15:09,570][98559] Updated weights for policy 0, policy_version 37610 (0.0010) -[2023-10-10 22:15:09,938][98559] Updated weights for policy 0, policy_version 37620 (0.0010) -[2023-10-10 22:15:10,310][98559] Updated weights for policy 0, policy_version 37630 (0.0009) -[2023-10-10 22:15:10,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 76906496. Throughput: 0: 1720.5, 1: 1724.8. Samples: 19227300. Policy #0 lag: (min: 36.0, avg: 53.9, max: 56.0) -[2023-10-10 22:15:10,557][97672] Avg episode reward: [(0, '-1.120'), (1, '22.140')] -[2023-10-10 22:15:12,708][98560] Updated weights for policy 1, policy_version 37482 (0.0008) -[2023-10-10 22:15:13,086][98560] Updated weights for policy 1, policy_version 37492 (0.0008) -[2023-10-10 22:15:13,450][98560] Updated weights for policy 1, policy_version 37502 (0.0009) -[2023-10-10 22:15:14,129][98559] Updated weights for policy 0, policy_version 37640 (0.0009) -[2023-10-10 22:15:14,491][98559] Updated weights for policy 0, policy_version 37650 (0.0008) -[2023-10-10 22:15:14,862][98559] Updated weights for policy 0, policy_version 37660 (0.0008) -[2023-10-10 22:15:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 76972032. Throughput: 0: 1707.3, 1: 1693.7. Samples: 19246578. Policy #0 lag: (min: 36.0, avg: 53.9, max: 56.0) -[2023-10-10 22:15:15,557][97672] Avg episode reward: [(0, '-1.120'), (1, '22.220')] -[2023-10-10 22:15:17,508][98560] Updated weights for policy 1, policy_version 37512 (0.0008) -[2023-10-10 22:15:17,883][98560] Updated weights for policy 1, policy_version 37522 (0.0009) -[2023-10-10 22:15:18,259][98560] Updated weights for policy 1, policy_version 37532 (0.0009) -[2023-10-10 22:15:19,012][98559] Updated weights for policy 0, policy_version 37670 (0.0009) -[2023-10-10 22:15:19,379][98559] Updated weights for policy 0, policy_version 37680 (0.0009) -[2023-10-10 22:15:19,743][98559] Updated weights for policy 0, policy_version 37690 (0.0011) -[2023-10-10 22:15:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 77037568. Throughput: 0: 1688.9, 1: 1704.4. Samples: 19266810. Policy #0 lag: (min: 36.0, avg: 53.9, max: 56.0) -[2023-10-10 22:15:20,557][97672] Avg episode reward: [(0, '-1.120'), (1, '22.200')] -[2023-10-10 22:15:22,424][98560] Updated weights for policy 1, policy_version 37542 (0.0009) -[2023-10-10 22:15:22,794][98560] Updated weights for policy 1, policy_version 37552 (0.0008) -[2023-10-10 22:15:23,163][98560] Updated weights for policy 1, policy_version 37562 (0.0007) -[2023-10-10 22:15:23,792][98559] Updated weights for policy 0, policy_version 37700 (0.0008) -[2023-10-10 22:15:24,162][98559] Updated weights for policy 0, policy_version 37710 (0.0008) -[2023-10-10 22:15:24,528][98559] Updated weights for policy 0, policy_version 37720 (0.0009) -[2023-10-10 22:15:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 77103104. Throughput: 0: 1720.9, 1: 1698.4. Samples: 19277994. Policy #0 lag: (min: 7.0, avg: 8.1, max: 30.0) -[2023-10-10 22:15:25,557][97672] Avg episode reward: [(0, '-1.120'), (1, '22.140')] -[2023-10-10 22:15:27,042][98560] Updated weights for policy 1, policy_version 37572 (0.0008) -[2023-10-10 22:15:27,413][98560] Updated weights for policy 1, policy_version 37582 (0.0007) -[2023-10-10 22:15:27,779][98560] Updated weights for policy 1, policy_version 37592 (0.0007) -[2023-10-10 22:15:28,297][98559] Updated weights for policy 0, policy_version 37730 (0.0008) -[2023-10-10 22:15:28,670][98559] Updated weights for policy 0, policy_version 37740 (0.0009) -[2023-10-10 22:15:29,044][98559] Updated weights for policy 0, policy_version 37750 (0.0010) -[2023-10-10 22:15:29,406][98559] Updated weights for policy 0, policy_version 37760 (0.0009) -[2023-10-10 22:15:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 77168640. Throughput: 0: 1696.5, 1: 1682.5. Samples: 19297304. Policy #0 lag: (min: 7.0, avg: 8.1, max: 30.0) -[2023-10-10 22:15:30,557][97672] Avg episode reward: [(0, '-1.120'), (1, '22.040')] -[2023-10-10 22:15:31,832][98560] Updated weights for policy 1, policy_version 37602 (0.0007) -[2023-10-10 22:15:32,196][98560] Updated weights for policy 1, policy_version 37612 (0.0009) -[2023-10-10 22:15:32,573][98560] Updated weights for policy 1, policy_version 37622 (0.0008) -[2023-10-10 22:15:32,938][98560] Updated weights for policy 1, policy_version 37632 (0.0009) -[2023-10-10 22:15:33,245][98559] Updated weights for policy 0, policy_version 37770 (0.0011) -[2023-10-10 22:15:33,609][98559] Updated weights for policy 0, policy_version 37780 (0.0011) -[2023-10-10 22:15:33,972][98559] Updated weights for policy 0, policy_version 37790 (0.0010) -[2023-10-10 22:15:35,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 77234176. Throughput: 0: 1702.6, 1: 1706.0. Samples: 19318498. Policy #0 lag: (min: 7.0, avg: 8.1, max: 30.0) -[2023-10-10 22:15:35,556][97672] Avg episode reward: [(0, '-1.120'), (1, '22.060')] -[2023-10-10 22:15:36,743][98560] Updated weights for policy 1, policy_version 37642 (0.0007) -[2023-10-10 22:15:37,117][98560] Updated weights for policy 1, policy_version 37652 (0.0007) -[2023-10-10 22:15:37,477][98560] Updated weights for policy 1, policy_version 37662 (0.0007) -[2023-10-10 22:15:38,176][98559] Updated weights for policy 0, policy_version 37800 (0.0010) -[2023-10-10 22:15:38,553][98559] Updated weights for policy 0, policy_version 37810 (0.0007) -[2023-10-10 22:15:38,906][98559] Updated weights for policy 0, policy_version 37820 (0.0011) -[2023-10-10 22:15:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 77299712. Throughput: 0: 1712.9, 1: 1674.1. Samples: 19328470. Policy #0 lag: (min: 7.0, avg: 8.1, max: 30.0) -[2023-10-10 22:15:40,557][97672] Avg episode reward: [(0, '-1.120'), (1, '22.060')] -[2023-10-10 22:15:41,596][98560] Updated weights for policy 1, policy_version 37672 (0.0007) -[2023-10-10 22:15:41,961][98560] Updated weights for policy 1, policy_version 37682 (0.0007) -[2023-10-10 22:15:42,332][98560] Updated weights for policy 1, policy_version 37692 (0.0010) -[2023-10-10 22:15:42,897][98559] Updated weights for policy 0, policy_version 37830 (0.0009) -[2023-10-10 22:15:43,266][98559] Updated weights for policy 0, policy_version 37840 (0.0009) -[2023-10-10 22:15:43,637][98559] Updated weights for policy 0, policy_version 37850 (0.0007) -[2023-10-10 22:15:45,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 77365248. Throughput: 0: 1695.8, 1: 1693.7. Samples: 19348704. Policy #0 lag: (min: 7.0, avg: 8.1, max: 30.0) -[2023-10-10 22:15:45,557][97672] Avg episode reward: [(0, '-1.140'), (1, '22.120')] -[2023-10-10 22:15:46,550][98560] Updated weights for policy 1, policy_version 37702 (0.0008) -[2023-10-10 22:15:46,927][98560] Updated weights for policy 1, policy_version 37712 (0.0007) -[2023-10-10 22:15:47,287][98560] Updated weights for policy 1, policy_version 37722 (0.0008) -[2023-10-10 22:15:47,690][98559] Updated weights for policy 0, policy_version 37860 (0.0008) -[2023-10-10 22:15:48,061][98559] Updated weights for policy 0, policy_version 37870 (0.0008) -[2023-10-10 22:15:48,425][98559] Updated weights for policy 0, policy_version 37880 (0.0010) -[2023-10-10 22:15:50,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 77430784. Throughput: 0: 1716.7, 1: 1703.4. Samples: 19369690. Policy #0 lag: (min: 7.0, avg: 8.1, max: 30.0) -[2023-10-10 22:15:50,557][97672] Avg episode reward: [(0, '-1.140'), (1, '22.100')] -[2023-10-10 22:15:51,340][98560] Updated weights for policy 1, policy_version 37732 (0.0009) -[2023-10-10 22:15:51,708][98560] Updated weights for policy 1, policy_version 37742 (0.0008) -[2023-10-10 22:15:52,074][98560] Updated weights for policy 1, policy_version 37752 (0.0007) -[2023-10-10 22:15:52,418][98559] Updated weights for policy 0, policy_version 37890 (0.0008) -[2023-10-10 22:15:52,783][98559] Updated weights for policy 0, policy_version 37900 (0.0010) -[2023-10-10 22:15:53,149][98559] Updated weights for policy 0, policy_version 37910 (0.0010) -[2023-10-10 22:15:53,521][98559] Updated weights for policy 0, policy_version 37920 (0.0008) -[2023-10-10 22:15:55,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 77496320. Throughput: 0: 1696.4, 1: 1674.6. Samples: 19378996. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-10 22:15:55,557][97672] Avg episode reward: [(0, '-1.140'), (1, '22.120')] -[2023-10-10 22:15:56,117][98560] Updated weights for policy 1, policy_version 37762 (0.0008) -[2023-10-10 22:15:56,483][98560] Updated weights for policy 1, policy_version 37772 (0.0009) -[2023-10-10 22:15:56,848][98560] Updated weights for policy 1, policy_version 37782 (0.0011) -[2023-10-10 22:15:57,213][98560] Updated weights for policy 1, policy_version 37792 (0.0010) -[2023-10-10 22:15:57,413][98559] Updated weights for policy 0, policy_version 37930 (0.0010) -[2023-10-10 22:15:57,778][98559] Updated weights for policy 0, policy_version 37940 (0.0008) -[2023-10-10 22:15:58,145][98559] Updated weights for policy 0, policy_version 37950 (0.0007) -[2023-10-10 22:16:00,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 77561856. Throughput: 0: 1704.3, 1: 1702.0. Samples: 19399864. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-10 22:16:00,556][97672] Avg episode reward: [(0, '-1.140'), (1, '22.120')] -[2023-10-10 22:16:01,340][98560] Updated weights for policy 1, policy_version 37802 (0.0009) -[2023-10-10 22:16:01,699][98560] Updated weights for policy 1, policy_version 37812 (0.0008) -[2023-10-10 22:16:02,070][98560] Updated weights for policy 1, policy_version 37822 (0.0007) -[2023-10-10 22:16:02,167][98559] Updated weights for policy 0, policy_version 37960 (0.0008) -[2023-10-10 22:16:02,533][98559] Updated weights for policy 0, policy_version 37970 (0.0007) -[2023-10-10 22:16:02,911][98559] Updated weights for policy 0, policy_version 37980 (0.0009) -[2023-10-10 22:16:05,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 77627392. Throughput: 0: 1724.4, 1: 1698.7. Samples: 19420848. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-10 22:16:05,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.160')] -[2023-10-10 22:16:06,110][98560] Updated weights for policy 1, policy_version 37832 (0.0009) -[2023-10-10 22:16:06,480][98560] Updated weights for policy 1, policy_version 37842 (0.0010) -[2023-10-10 22:16:06,812][98559] Updated weights for policy 0, policy_version 37990 (0.0007) -[2023-10-10 22:16:06,852][98560] Updated weights for policy 1, policy_version 37852 (0.0008) -[2023-10-10 22:16:07,175][98559] Updated weights for policy 0, policy_version 38000 (0.0008) -[2023-10-10 22:16:07,541][98559] Updated weights for policy 0, policy_version 38010 (0.0007) -[2023-10-10 22:16:10,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 77692928. Throughput: 0: 1694.8, 1: 1685.3. Samples: 19430098. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-10 22:16:10,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.220')] -[2023-10-10 22:16:10,727][98560] Updated weights for policy 1, policy_version 37862 (0.0011) -[2023-10-10 22:16:11,094][98560] Updated weights for policy 1, policy_version 37872 (0.0010) -[2023-10-10 22:16:11,463][98560] Updated weights for policy 1, policy_version 37882 (0.0010) -[2023-10-10 22:16:11,587][98559] Updated weights for policy 0, policy_version 38020 (0.0009) -[2023-10-10 22:16:11,951][98559] Updated weights for policy 0, policy_version 38030 (0.0009) -[2023-10-10 22:16:12,315][98559] Updated weights for policy 0, policy_version 38040 (0.0008) -[2023-10-10 22:16:15,534][98560] Updated weights for policy 1, policy_version 37892 (0.0008) -[2023-10-10 22:16:15,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 77758464. Throughput: 0: 1719.5, 1: 1701.3. Samples: 19451240. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-10 22:16:15,556][97672] Avg episode reward: [(0, '-1.200'), (1, '22.280')] -[2023-10-10 22:16:15,903][98560] Updated weights for policy 1, policy_version 37902 (0.0010) -[2023-10-10 22:16:16,107][98559] Updated weights for policy 0, policy_version 38050 (0.0008) -[2023-10-10 22:16:16,266][98560] Updated weights for policy 1, policy_version 37912 (0.0009) -[2023-10-10 22:16:16,469][98559] Updated weights for policy 0, policy_version 38060 (0.0008) -[2023-10-10 22:16:16,838][98559] Updated weights for policy 0, policy_version 38070 (0.0008) -[2023-10-10 22:16:17,203][98559] Updated weights for policy 0, policy_version 38080 (0.0008) -[2023-10-10 22:16:20,297][98560] Updated weights for policy 1, policy_version 37922 (0.0008) -[2023-10-10 22:16:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 77824000. Throughput: 0: 1718.4, 1: 1694.5. Samples: 19472080. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-10 22:16:20,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.340')] -[2023-10-10 22:16:20,667][98560] Updated weights for policy 1, policy_version 37932 (0.0007) -[2023-10-10 22:16:21,033][98560] Updated weights for policy 1, policy_version 37942 (0.0007) -[2023-10-10 22:16:21,310][98559] Updated weights for policy 0, policy_version 38090 (0.0009) -[2023-10-10 22:16:21,399][98560] Updated weights for policy 1, policy_version 37952 (0.0009) -[2023-10-10 22:16:21,683][98559] Updated weights for policy 0, policy_version 38100 (0.0008) -[2023-10-10 22:16:22,046][98559] Updated weights for policy 0, policy_version 38110 (0.0009) -[2023-10-10 22:16:25,457][98560] Updated weights for policy 1, policy_version 37962 (0.0008) -[2023-10-10 22:16:25,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 77889536. Throughput: 0: 1702.6, 1: 1694.6. Samples: 19481344. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-10 22:16:25,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.320')] -[2023-10-10 22:16:25,817][98560] Updated weights for policy 1, policy_version 37972 (0.0008) -[2023-10-10 22:16:26,090][98559] Updated weights for policy 0, policy_version 38120 (0.0008) -[2023-10-10 22:16:26,188][98560] Updated weights for policy 1, policy_version 37982 (0.0008) -[2023-10-10 22:16:26,454][98559] Updated weights for policy 0, policy_version 38130 (0.0009) -[2023-10-10 22:16:26,837][98559] Updated weights for policy 0, policy_version 38140 (0.0008) -[2023-10-10 22:16:30,278][98560] Updated weights for policy 1, policy_version 37992 (0.0009) -[2023-10-10 22:16:30,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 77955072. Throughput: 0: 1720.2, 1: 1691.3. Samples: 19502222. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-10 22:16:30,558][97672] Avg episode reward: [(0, '-1.200'), (1, '22.300')] -[2023-10-10 22:16:30,637][98560] Updated weights for policy 1, policy_version 38002 (0.0010) -[2023-10-10 22:16:30,883][98559] Updated weights for policy 0, policy_version 38150 (0.0008) -[2023-10-10 22:16:31,009][98560] Updated weights for policy 1, policy_version 38012 (0.0007) -[2023-10-10 22:16:31,244][98559] Updated weights for policy 0, policy_version 38160 (0.0010) -[2023-10-10 22:16:31,610][98559] Updated weights for policy 0, policy_version 38170 (0.0009) -[2023-10-10 22:16:35,039][98560] Updated weights for policy 1, policy_version 38022 (0.0008) -[2023-10-10 22:16:35,430][98560] Updated weights for policy 1, policy_version 38032 (0.0008) -[2023-10-10 22:16:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 78020608. Throughput: 0: 1721.1, 1: 1693.8. Samples: 19523360. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-10 22:16:35,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.300')] -[2023-10-10 22:16:35,642][98559] Updated weights for policy 0, policy_version 38180 (0.0009) -[2023-10-10 22:16:35,796][98560] Updated weights for policy 1, policy_version 38042 (0.0007) -[2023-10-10 22:16:36,007][98559] Updated weights for policy 0, policy_version 38190 (0.0008) -[2023-10-10 22:16:36,013][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000038048_38961152.pth... -[2023-10-10 22:16:36,045][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000036448_37322752.pth -[2023-10-10 22:16:36,366][98559] Updated weights for policy 0, policy_version 38200 (0.0011) -[2023-10-10 22:16:36,658][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000038208_39124992.pth... -[2023-10-10 22:16:36,696][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000036576_37453824.pth -[2023-10-10 22:16:39,716][98560] Updated weights for policy 1, policy_version 38052 (0.0010) -[2023-10-10 22:16:40,087][98560] Updated weights for policy 1, policy_version 38062 (0.0007) -[2023-10-10 22:16:40,329][98559] Updated weights for policy 0, policy_version 38210 (0.0009) -[2023-10-10 22:16:40,458][98560] Updated weights for policy 1, policy_version 38072 (0.0007) -[2023-10-10 22:16:40,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 78086144. Throughput: 0: 1717.4, 1: 1691.6. Samples: 19532398. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-10 22:16:40,556][97672] Avg episode reward: [(0, '-1.200'), (1, '22.240')] -[2023-10-10 22:16:40,691][98559] Updated weights for policy 0, policy_version 38220 (0.0007) -[2023-10-10 22:16:41,057][98559] Updated weights for policy 0, policy_version 38230 (0.0008) -[2023-10-10 22:16:41,425][98559] Updated weights for policy 0, policy_version 38240 (0.0007) -[2023-10-10 22:16:44,542][98560] Updated weights for policy 1, policy_version 38082 (0.0010) -[2023-10-10 22:16:44,917][98560] Updated weights for policy 1, policy_version 38092 (0.0010) -[2023-10-10 22:16:45,284][98560] Updated weights for policy 1, policy_version 38102 (0.0007) -[2023-10-10 22:16:45,471][98559] Updated weights for policy 0, policy_version 38250 (0.0008) -[2023-10-10 22:16:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 78151680. Throughput: 0: 1725.4, 1: 1693.1. Samples: 19553696. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-10 22:16:45,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.220')] -[2023-10-10 22:16:45,650][98560] Updated weights for policy 1, policy_version 38112 (0.0008) -[2023-10-10 22:16:45,841][98559] Updated weights for policy 0, policy_version 38260 (0.0007) -[2023-10-10 22:16:46,207][98559] Updated weights for policy 0, policy_version 38270 (0.0007) -[2023-10-10 22:16:49,667][98560] Updated weights for policy 1, policy_version 38122 (0.0009) -[2023-10-10 22:16:50,037][98560] Updated weights for policy 1, policy_version 38132 (0.0007) -[2023-10-10 22:16:50,096][98559] Updated weights for policy 0, policy_version 38280 (0.0007) -[2023-10-10 22:16:50,405][98560] Updated weights for policy 1, policy_version 38142 (0.0008) -[2023-10-10 22:16:50,463][98559] Updated weights for policy 0, policy_version 38290 (0.0007) -[2023-10-10 22:16:50,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 78249984. Throughput: 0: 1713.0, 1: 1685.7. Samples: 19573790. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-10 22:16:50,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.240')] -[2023-10-10 22:16:50,824][98559] Updated weights for policy 0, policy_version 38300 (0.0007) -[2023-10-10 22:16:54,363][98560] Updated weights for policy 1, policy_version 38152 (0.0008) -[2023-10-10 22:16:54,739][98560] Updated weights for policy 1, policy_version 38162 (0.0010) -[2023-10-10 22:16:54,820][98559] Updated weights for policy 0, policy_version 38310 (0.0010) -[2023-10-10 22:16:55,100][98560] Updated weights for policy 1, policy_version 38172 (0.0008) -[2023-10-10 22:16:55,187][98559] Updated weights for policy 0, policy_version 38320 (0.0008) -[2023-10-10 22:16:55,543][98559] Updated weights for policy 0, policy_version 38330 (0.0007) -[2023-10-10 22:16:55,556][97672] Fps is (10 sec: 16384.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 78315520. Throughput: 0: 1725.2, 1: 1695.7. Samples: 19584038. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:16:55,556][97672] Avg episode reward: [(0, '-1.200'), (1, '22.200')] -[2023-10-10 22:16:59,057][98560] Updated weights for policy 1, policy_version 38182 (0.0008) -[2023-10-10 22:16:59,422][98560] Updated weights for policy 1, policy_version 38192 (0.0010) -[2023-10-10 22:16:59,737][98559] Updated weights for policy 0, policy_version 38340 (0.0010) -[2023-10-10 22:16:59,786][98560] Updated weights for policy 1, policy_version 38202 (0.0008) -[2023-10-10 22:17:00,099][98559] Updated weights for policy 0, policy_version 38350 (0.0009) -[2023-10-10 22:17:00,463][98559] Updated weights for policy 0, policy_version 38360 (0.0008) -[2023-10-10 22:17:00,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 78381056. Throughput: 0: 1715.1, 1: 1699.0. Samples: 19604874. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:17:00,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.200')] -[2023-10-10 22:17:03,865][98560] Updated weights for policy 1, policy_version 38212 (0.0009) -[2023-10-10 22:17:04,235][98560] Updated weights for policy 1, policy_version 38222 (0.0009) -[2023-10-10 22:17:04,248][98559] Updated weights for policy 0, policy_version 38370 (0.0009) -[2023-10-10 22:17:04,603][98560] Updated weights for policy 1, policy_version 38232 (0.0007) -[2023-10-10 22:17:04,608][98559] Updated weights for policy 0, policy_version 38380 (0.0009) -[2023-10-10 22:17:04,978][98559] Updated weights for policy 0, policy_version 38390 (0.0009) -[2023-10-10 22:17:05,346][98559] Updated weights for policy 0, policy_version 38400 (0.0010) -[2023-10-10 22:17:05,556][97672] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 78479360. Throughput: 0: 1693.1, 1: 1681.3. Samples: 19623928. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:17:05,556][97672] Avg episode reward: [(0, '-1.200'), (1, '22.260')] -[2023-10-10 22:17:08,532][98560] Updated weights for policy 1, policy_version 38242 (0.0007) -[2023-10-10 22:17:08,901][98560] Updated weights for policy 1, policy_version 38252 (0.0008) -[2023-10-10 22:17:09,241][98559] Updated weights for policy 0, policy_version 38410 (0.0008) -[2023-10-10 22:17:09,278][98560] Updated weights for policy 1, policy_version 38262 (0.0009) -[2023-10-10 22:17:09,615][98559] Updated weights for policy 0, policy_version 38420 (0.0008) -[2023-10-10 22:17:09,641][98560] Updated weights for policy 1, policy_version 38272 (0.0009) -[2023-10-10 22:17:09,975][98559] Updated weights for policy 0, policy_version 38430 (0.0010) -[2023-10-10 22:17:10,556][97672] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 78544896. Throughput: 0: 1720.4, 1: 1706.7. Samples: 19635562. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:17:10,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.260')] -[2023-10-10 22:17:13,524][98560] Updated weights for policy 1, policy_version 38282 (0.0010) -[2023-10-10 22:17:13,894][98560] Updated weights for policy 1, policy_version 38292 (0.0009) -[2023-10-10 22:17:13,966][98559] Updated weights for policy 0, policy_version 38440 (0.0009) -[2023-10-10 22:17:14,262][98560] Updated weights for policy 1, policy_version 38302 (0.0007) -[2023-10-10 22:17:14,332][98559] Updated weights for policy 0, policy_version 38450 (0.0008) -[2023-10-10 22:17:14,695][98559] Updated weights for policy 0, policy_version 38460 (0.0008) -[2023-10-10 22:17:15,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 78610432. Throughput: 0: 1704.4, 1: 1701.0. Samples: 19655462. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:17:15,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.240')] -[2023-10-10 22:17:18,313][98560] Updated weights for policy 1, policy_version 38312 (0.0009) -[2023-10-10 22:17:18,677][98560] Updated weights for policy 1, policy_version 38322 (0.0007) -[2023-10-10 22:17:18,740][98559] Updated weights for policy 0, policy_version 38470 (0.0009) -[2023-10-10 22:17:19,042][98560] Updated weights for policy 1, policy_version 38332 (0.0009) -[2023-10-10 22:17:19,108][98559] Updated weights for policy 0, policy_version 38480 (0.0007) -[2023-10-10 22:17:19,468][98559] Updated weights for policy 0, policy_version 38490 (0.0009) -[2023-10-10 22:17:20,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 78675968. Throughput: 0: 1687.7, 1: 1685.7. Samples: 19675164. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-10 22:17:20,556][97672] Avg episode reward: [(0, '-1.100'), (1, '22.240')] -[2023-10-10 22:17:23,104][98560] Updated weights for policy 1, policy_version 38342 (0.0010) -[2023-10-10 22:17:23,450][98559] Updated weights for policy 0, policy_version 38500 (0.0009) -[2023-10-10 22:17:23,471][98560] Updated weights for policy 1, policy_version 38352 (0.0008) -[2023-10-10 22:17:23,817][98559] Updated weights for policy 0, policy_version 38510 (0.0007) -[2023-10-10 22:17:23,846][98560] Updated weights for policy 1, policy_version 38362 (0.0008) -[2023-10-10 22:17:24,181][98559] Updated weights for policy 0, policy_version 38520 (0.0009) -[2023-10-10 22:17:25,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 78741504. Throughput: 0: 1716.2, 1: 1720.5. Samples: 19687052. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-10 22:17:25,556][97672] Avg episode reward: [(0, '-1.140'), (1, '22.260')] -[2023-10-10 22:17:27,594][98560] Updated weights for policy 1, policy_version 38372 (0.0009) -[2023-10-10 22:17:27,954][98560] Updated weights for policy 1, policy_version 38382 (0.0009) -[2023-10-10 22:17:28,195][98559] Updated weights for policy 0, policy_version 38530 (0.0008) -[2023-10-10 22:17:28,324][98560] Updated weights for policy 1, policy_version 38392 (0.0008) -[2023-10-10 22:17:28,565][98559] Updated weights for policy 0, policy_version 38540 (0.0008) -[2023-10-10 22:17:28,931][98559] Updated weights for policy 0, policy_version 38550 (0.0008) -[2023-10-10 22:17:29,296][98559] Updated weights for policy 0, policy_version 38560 (0.0008) -[2023-10-10 22:17:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 78807040. Throughput: 0: 1685.9, 1: 1691.4. Samples: 19705674. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-10 22:17:30,557][97672] Avg episode reward: [(0, '-1.140'), (1, '22.340')] -[2023-10-10 22:17:32,578][98560] Updated weights for policy 1, policy_version 38402 (0.0007) -[2023-10-10 22:17:32,946][98560] Updated weights for policy 1, policy_version 38412 (0.0009) -[2023-10-10 22:17:33,228][98559] Updated weights for policy 0, policy_version 38570 (0.0010) -[2023-10-10 22:17:33,312][98560] Updated weights for policy 1, policy_version 38422 (0.0007) -[2023-10-10 22:17:33,592][98559] Updated weights for policy 0, policy_version 38580 (0.0008) -[2023-10-10 22:17:33,680][98560] Updated weights for policy 1, policy_version 38432 (0.0011) -[2023-10-10 22:17:33,963][98559] Updated weights for policy 0, policy_version 38590 (0.0009) -[2023-10-10 22:17:35,556][97672] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 78872576. Throughput: 0: 1694.9, 1: 1696.2. Samples: 19726388. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-10 22:17:35,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.280')] -[2023-10-10 22:17:37,639][98560] Updated weights for policy 1, policy_version 38442 (0.0007) -[2023-10-10 22:17:37,957][98559] Updated weights for policy 0, policy_version 38600 (0.0009) -[2023-10-10 22:17:38,006][98560] Updated weights for policy 1, policy_version 38452 (0.0009) -[2023-10-10 22:17:38,321][98559] Updated weights for policy 0, policy_version 38610 (0.0007) -[2023-10-10 22:17:38,381][98560] Updated weights for policy 1, policy_version 38462 (0.0009) -[2023-10-10 22:17:38,697][98559] Updated weights for policy 0, policy_version 38620 (0.0009) -[2023-10-10 22:17:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 78938112. Throughput: 0: 1698.8, 1: 1705.0. Samples: 19737210. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-10 22:17:40,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.220')] -[2023-10-10 22:17:42,435][98560] Updated weights for policy 1, policy_version 38472 (0.0008) -[2023-10-10 22:17:42,797][98560] Updated weights for policy 1, policy_version 38482 (0.0008) -[2023-10-10 22:17:42,821][98559] Updated weights for policy 0, policy_version 38630 (0.0009) -[2023-10-10 22:17:43,171][98560] Updated weights for policy 1, policy_version 38492 (0.0008) -[2023-10-10 22:17:43,184][98559] Updated weights for policy 0, policy_version 38640 (0.0008) -[2023-10-10 22:17:43,558][98559] Updated weights for policy 0, policy_version 38650 (0.0009) -[2023-10-10 22:17:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 79003648. Throughput: 0: 1691.8, 1: 1681.4. Samples: 19756668. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-10 22:17:45,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.200')] -[2023-10-10 22:17:47,234][98560] Updated weights for policy 1, policy_version 38502 (0.0008) -[2023-10-10 22:17:47,596][98560] Updated weights for policy 1, policy_version 38512 (0.0007) -[2023-10-10 22:17:47,618][98559] Updated weights for policy 0, policy_version 38660 (0.0009) -[2023-10-10 22:17:47,955][98560] Updated weights for policy 1, policy_version 38522 (0.0008) -[2023-10-10 22:17:47,990][98559] Updated weights for policy 0, policy_version 38670 (0.0009) -[2023-10-10 22:17:48,359][98559] Updated weights for policy 0, policy_version 38680 (0.0009) -[2023-10-10 22:17:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 79069184. Throughput: 0: 1716.1, 1: 1704.2. Samples: 19777844. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:17:50,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.160')] -[2023-10-10 22:17:51,980][98560] Updated weights for policy 1, policy_version 38532 (0.0007) -[2023-10-10 22:17:52,321][98559] Updated weights for policy 0, policy_version 38690 (0.0010) -[2023-10-10 22:17:52,346][98560] Updated weights for policy 1, policy_version 38542 (0.0008) -[2023-10-10 22:17:52,700][98559] Updated weights for policy 0, policy_version 38700 (0.0008) -[2023-10-10 22:17:52,712][98560] Updated weights for policy 1, policy_version 38552 (0.0009) -[2023-10-10 22:17:53,069][98559] Updated weights for policy 0, policy_version 38710 (0.0008) -[2023-10-10 22:17:53,430][98559] Updated weights for policy 0, policy_version 38720 (0.0009) -[2023-10-10 22:17:55,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 79134720. Throughput: 0: 1693.4, 1: 1687.4. Samples: 19787698. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:17:55,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.160')] -[2023-10-10 22:17:56,570][98560] Updated weights for policy 1, policy_version 38562 (0.0009) -[2023-10-10 22:17:56,941][98560] Updated weights for policy 1, policy_version 38572 (0.0008) -[2023-10-10 22:17:57,316][98560] Updated weights for policy 1, policy_version 38582 (0.0008) -[2023-10-10 22:17:57,495][98559] Updated weights for policy 0, policy_version 38730 (0.0010) -[2023-10-10 22:17:57,676][98560] Updated weights for policy 1, policy_version 38592 (0.0010) -[2023-10-10 22:17:57,857][98559] Updated weights for policy 0, policy_version 38740 (0.0007) -[2023-10-10 22:17:58,229][98559] Updated weights for policy 0, policy_version 38750 (0.0007) -[2023-10-10 22:18:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 79200256. Throughput: 0: 1704.2, 1: 1691.1. Samples: 19808252. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:18:00,556][97672] Avg episode reward: [(0, '-1.100'), (1, '22.200')] -[2023-10-10 22:18:01,817][98560] Updated weights for policy 1, policy_version 38602 (0.0008) -[2023-10-10 22:18:02,182][98560] Updated weights for policy 1, policy_version 38612 (0.0010) -[2023-10-10 22:18:02,305][98559] Updated weights for policy 0, policy_version 38760 (0.0008) -[2023-10-10 22:18:02,550][98560] Updated weights for policy 1, policy_version 38622 (0.0007) -[2023-10-10 22:18:02,669][98559] Updated weights for policy 0, policy_version 38770 (0.0008) -[2023-10-10 22:18:03,044][98559] Updated weights for policy 0, policy_version 38780 (0.0007) -[2023-10-10 22:18:05,556][97672] Fps is (10 sec: 13106.7, 60 sec: 13107.1, 300 sec: 13662.6). Total num frames: 79265792. Throughput: 0: 1717.9, 1: 1704.7. Samples: 19829184. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:18:05,558][97672] Avg episode reward: [(0, '-1.100'), (1, '22.240')] -[2023-10-10 22:18:06,532][98560] Updated weights for policy 1, policy_version 38632 (0.0008) -[2023-10-10 22:18:06,868][98559] Updated weights for policy 0, policy_version 38790 (0.0009) -[2023-10-10 22:18:06,893][98560] Updated weights for policy 1, policy_version 38642 (0.0008) -[2023-10-10 22:18:07,247][98559] Updated weights for policy 0, policy_version 38800 (0.0008) -[2023-10-10 22:18:07,265][98560] Updated weights for policy 1, policy_version 38652 (0.0010) -[2023-10-10 22:18:07,622][98559] Updated weights for policy 0, policy_version 38810 (0.0011) -[2023-10-10 22:18:10,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 79331328. Throughput: 0: 1690.9, 1: 1674.2. Samples: 19838484. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:18:10,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.180')] -[2023-10-10 22:18:11,346][98560] Updated weights for policy 1, policy_version 38662 (0.0010) -[2023-10-10 22:18:11,514][98559] Updated weights for policy 0, policy_version 38820 (0.0010) -[2023-10-10 22:18:11,710][98560] Updated weights for policy 1, policy_version 38672 (0.0009) -[2023-10-10 22:18:11,884][98559] Updated weights for policy 0, policy_version 38830 (0.0008) -[2023-10-10 22:18:12,068][98560] Updated weights for policy 1, policy_version 38682 (0.0010) -[2023-10-10 22:18:12,247][98559] Updated weights for policy 0, policy_version 38840 (0.0008) -[2023-10-10 22:18:15,556][97672] Fps is (10 sec: 13107.7, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 79396864. Throughput: 0: 1724.5, 1: 1695.6. Samples: 19859578. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:18:15,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.240')] -[2023-10-10 22:18:16,108][98559] Updated weights for policy 0, policy_version 38850 (0.0008) -[2023-10-10 22:18:16,196][98560] Updated weights for policy 1, policy_version 38692 (0.0008) -[2023-10-10 22:18:16,486][98559] Updated weights for policy 0, policy_version 38860 (0.0009) -[2023-10-10 22:18:16,551][98560] Updated weights for policy 1, policy_version 38702 (0.0010) -[2023-10-10 22:18:16,843][98559] Updated weights for policy 0, policy_version 38870 (0.0008) -[2023-10-10 22:18:16,926][98560] Updated weights for policy 1, policy_version 38712 (0.0008) -[2023-10-10 22:18:17,206][98559] Updated weights for policy 0, policy_version 38880 (0.0009) -[2023-10-10 22:18:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 79462400. Throughput: 0: 1723.8, 1: 1699.9. Samples: 19880454. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:18:20,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.140')] -[2023-10-10 22:18:20,927][98560] Updated weights for policy 1, policy_version 38722 (0.0009) -[2023-10-10 22:18:21,290][98560] Updated weights for policy 1, policy_version 38732 (0.0008) -[2023-10-10 22:18:21,296][98559] Updated weights for policy 0, policy_version 38890 (0.0007) -[2023-10-10 22:18:21,654][98560] Updated weights for policy 1, policy_version 38742 (0.0008) -[2023-10-10 22:18:21,662][98559] Updated weights for policy 0, policy_version 38900 (0.0008) -[2023-10-10 22:18:22,023][98560] Updated weights for policy 1, policy_version 38752 (0.0009) -[2023-10-10 22:18:22,025][98559] Updated weights for policy 0, policy_version 38910 (0.0007) -[2023-10-10 22:18:25,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 79527936. Throughput: 0: 1707.0, 1: 1678.8. Samples: 19889570. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:18:25,556][97672] Avg episode reward: [(0, '-1.100'), (1, '22.220')] -[2023-10-10 22:18:26,025][98559] Updated weights for policy 0, policy_version 38920 (0.0008) -[2023-10-10 22:18:26,141][98560] Updated weights for policy 1, policy_version 38762 (0.0008) -[2023-10-10 22:18:26,387][98559] Updated weights for policy 0, policy_version 38930 (0.0008) -[2023-10-10 22:18:26,497][98560] Updated weights for policy 1, policy_version 38772 (0.0008) -[2023-10-10 22:18:26,753][98559] Updated weights for policy 0, policy_version 38940 (0.0008) -[2023-10-10 22:18:26,870][98560] Updated weights for policy 1, policy_version 38782 (0.0007) -[2023-10-10 22:18:30,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 79593472. Throughput: 0: 1723.2, 1: 1697.6. Samples: 19910602. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:18:30,556][97672] Avg episode reward: [(0, '-1.080'), (1, '22.280')] -[2023-10-10 22:18:30,605][98559] Updated weights for policy 0, policy_version 38950 (0.0008) -[2023-10-10 22:18:30,930][98560] Updated weights for policy 1, policy_version 38792 (0.0010) -[2023-10-10 22:18:30,966][98559] Updated weights for policy 0, policy_version 38960 (0.0008) -[2023-10-10 22:18:31,294][98560] Updated weights for policy 1, policy_version 38802 (0.0009) -[2023-10-10 22:18:31,340][98559] Updated weights for policy 0, policy_version 38970 (0.0008) -[2023-10-10 22:18:31,672][98560] Updated weights for policy 1, policy_version 38812 (0.0007) -[2023-10-10 22:18:35,196][98559] Updated weights for policy 0, policy_version 38980 (0.0008) -[2023-10-10 22:18:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 79659008. Throughput: 0: 1717.3, 1: 1697.3. Samples: 19931504. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:18:35,557][97672] Avg episode reward: [(0, '-1.080'), (1, '22.260')] -[2023-10-10 22:18:35,569][98559] Updated weights for policy 0, policy_version 38990 (0.0010) -[2023-10-10 22:18:35,687][98560] Updated weights for policy 1, policy_version 38822 (0.0008) -[2023-10-10 22:18:35,934][98559] Updated weights for policy 0, policy_version 39000 (0.0007) -[2023-10-10 22:18:36,058][98560] Updated weights for policy 1, policy_version 38832 (0.0008) -[2023-10-10 22:18:36,216][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000039008_39944192.pth... -[2023-10-10 22:18:36,258][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000037408_38305792.pth -[2023-10-10 22:18:36,414][98560] Updated weights for policy 1, policy_version 38842 (0.0009) -[2023-10-10 22:18:36,635][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000038848_39780352.pth... -[2023-10-10 22:18:36,664][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000037248_38141952.pth -[2023-10-10 22:18:39,995][98559] Updated weights for policy 0, policy_version 39010 (0.0008) -[2023-10-10 22:18:40,356][98559] Updated weights for policy 0, policy_version 39020 (0.0009) -[2023-10-10 22:18:40,441][98560] Updated weights for policy 1, policy_version 38852 (0.0010) -[2023-10-10 22:18:40,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 79724544. Throughput: 0: 1718.3, 1: 1685.9. Samples: 19940884. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:18:40,557][97672] Avg episode reward: [(0, '-1.080'), (1, '22.220')] -[2023-10-10 22:18:40,708][98559] Updated weights for policy 0, policy_version 39030 (0.0007) -[2023-10-10 22:18:40,799][98560] Updated weights for policy 1, policy_version 38862 (0.0008) -[2023-10-10 22:18:41,077][98559] Updated weights for policy 0, policy_version 39040 (0.0008) -[2023-10-10 22:18:41,179][98560] Updated weights for policy 1, policy_version 38872 (0.0009) -[2023-10-10 22:18:45,083][98559] Updated weights for policy 0, policy_version 39050 (0.0008) -[2023-10-10 22:18:45,212][98560] Updated weights for policy 1, policy_version 38882 (0.0009) -[2023-10-10 22:18:45,440][98559] Updated weights for policy 0, policy_version 39060 (0.0008) -[2023-10-10 22:18:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 79790080. Throughput: 0: 1724.1, 1: 1694.3. Samples: 19962080. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:18:45,557][97672] Avg episode reward: [(0, '-1.080'), (1, '22.200')] -[2023-10-10 22:18:45,579][98560] Updated weights for policy 1, policy_version 38892 (0.0008) -[2023-10-10 22:18:45,813][98559] Updated weights for policy 0, policy_version 39070 (0.0010) -[2023-10-10 22:18:45,950][98560] Updated weights for policy 1, policy_version 38902 (0.0009) -[2023-10-10 22:18:46,325][98560] Updated weights for policy 1, policy_version 38912 (0.0008) -[2023-10-10 22:18:49,895][98559] Updated weights for policy 0, policy_version 39080 (0.0008) -[2023-10-10 22:18:50,255][98559] Updated weights for policy 0, policy_version 39090 (0.0007) -[2023-10-10 22:18:50,383][98560] Updated weights for policy 1, policy_version 38922 (0.0008) -[2023-10-10 22:18:50,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 79855616. Throughput: 0: 1701.9, 1: 1690.8. Samples: 19981854. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 22:18:50,557][97672] Avg episode reward: [(0, '-1.080'), (1, '22.220')] -[2023-10-10 22:18:50,624][98559] Updated weights for policy 0, policy_version 39100 (0.0009) -[2023-10-10 22:18:50,738][98560] Updated weights for policy 1, policy_version 38932 (0.0007) -[2023-10-10 22:18:51,099][98560] Updated weights for policy 1, policy_version 38942 (0.0010) -[2023-10-10 22:18:54,654][98559] Updated weights for policy 0, policy_version 39110 (0.0009) -[2023-10-10 22:18:55,019][98559] Updated weights for policy 0, policy_version 39120 (0.0009) -[2023-10-10 22:18:55,165][98560] Updated weights for policy 1, policy_version 38952 (0.0009) -[2023-10-10 22:18:55,379][98559] Updated weights for policy 0, policy_version 39130 (0.0007) -[2023-10-10 22:18:55,531][98560] Updated weights for policy 1, policy_version 38962 (0.0010) -[2023-10-10 22:18:55,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 79921152. Throughput: 0: 1715.6, 1: 1692.5. Samples: 19991850. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 22:18:55,557][97672] Avg episode reward: [(0, '-1.080'), (1, '22.260')] -[2023-10-10 22:18:55,906][98560] Updated weights for policy 1, policy_version 38972 (0.0011) -[2023-10-10 22:18:59,434][98559] Updated weights for policy 0, policy_version 39140 (0.0008) -[2023-10-10 22:18:59,804][98559] Updated weights for policy 0, policy_version 39150 (0.0008) -[2023-10-10 22:19:00,009][98560] Updated weights for policy 1, policy_version 38982 (0.0009) -[2023-10-10 22:19:00,166][98559] Updated weights for policy 0, policy_version 39160 (0.0008) -[2023-10-10 22:19:00,403][98560] Updated weights for policy 1, policy_version 38992 (0.0007) -[2023-10-10 22:19:00,556][97672] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 80019456. Throughput: 0: 1711.4, 1: 1694.7. Samples: 20012854. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 22:19:00,556][97672] Avg episode reward: [(0, '-1.120'), (1, '22.200')] -[2023-10-10 22:19:00,773][98560] Updated weights for policy 1, policy_version 39002 (0.0008) -[2023-10-10 22:19:03,979][98559] Updated weights for policy 0, policy_version 39170 (0.0008) -[2023-10-10 22:19:04,340][98559] Updated weights for policy 0, policy_version 39180 (0.0009) -[2023-10-10 22:19:04,706][98559] Updated weights for policy 0, policy_version 39190 (0.0007) -[2023-10-10 22:19:04,793][98560] Updated weights for policy 1, policy_version 39012 (0.0008) -[2023-10-10 22:19:05,077][98559] Updated weights for policy 0, policy_version 39200 (0.0007) -[2023-10-10 22:19:05,162][98560] Updated weights for policy 1, policy_version 39022 (0.0009) -[2023-10-10 22:19:05,530][98560] Updated weights for policy 1, policy_version 39032 (0.0007) -[2023-10-10 22:19:05,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 80084992. Throughput: 0: 1690.1, 1: 1690.8. Samples: 20032592. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 22:19:05,557][97672] Avg episode reward: [(0, '-1.120'), (1, '22.160')] -[2023-10-10 22:19:09,079][98559] Updated weights for policy 0, policy_version 39210 (0.0008) -[2023-10-10 22:19:09,438][98559] Updated weights for policy 0, policy_version 39220 (0.0008) -[2023-10-10 22:19:09,459][98560] Updated weights for policy 1, policy_version 39042 (0.0009) -[2023-10-10 22:19:09,801][98559] Updated weights for policy 0, policy_version 39230 (0.0009) -[2023-10-10 22:19:09,826][98560] Updated weights for policy 1, policy_version 39052 (0.0009) -[2023-10-10 22:19:10,201][98560] Updated weights for policy 1, policy_version 39062 (0.0009) -[2023-10-10 22:19:10,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 80150528. Throughput: 0: 1721.7, 1: 1693.9. Samples: 20043270. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 22:19:10,557][97672] Avg episode reward: [(0, '-1.120'), (1, '22.240')] -[2023-10-10 22:19:10,565][98560] Updated weights for policy 1, policy_version 39072 (0.0010) -[2023-10-10 22:19:14,007][98559] Updated weights for policy 0, policy_version 39240 (0.0010) -[2023-10-10 22:19:14,379][98559] Updated weights for policy 0, policy_version 39250 (0.0009) -[2023-10-10 22:19:14,747][98560] Updated weights for policy 1, policy_version 39082 (0.0010) -[2023-10-10 22:19:14,750][98559] Updated weights for policy 0, policy_version 39260 (0.0008) -[2023-10-10 22:19:15,123][98560] Updated weights for policy 1, policy_version 39092 (0.0010) -[2023-10-10 22:19:15,482][98560] Updated weights for policy 1, policy_version 39102 (0.0009) -[2023-10-10 22:19:15,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 80248832. Throughput: 0: 1700.1, 1: 1697.5. Samples: 20063494. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:19:15,557][97672] Avg episode reward: [(0, '-1.140'), (1, '22.200')] -[2023-10-10 22:19:18,815][98559] Updated weights for policy 0, policy_version 39270 (0.0009) -[2023-10-10 22:19:19,190][98559] Updated weights for policy 0, policy_version 39280 (0.0009) -[2023-10-10 22:19:19,560][98559] Updated weights for policy 0, policy_version 39290 (0.0008) -[2023-10-10 22:19:19,630][98560] Updated weights for policy 1, policy_version 39112 (0.0008) -[2023-10-10 22:19:19,988][98560] Updated weights for policy 1, policy_version 39122 (0.0010) -[2023-10-10 22:19:20,355][98560] Updated weights for policy 1, policy_version 39132 (0.0011) -[2023-10-10 22:19:20,556][97672] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 80314368. Throughput: 0: 1689.7, 1: 1687.8. Samples: 20083494. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:19:20,557][97672] Avg episode reward: [(0, '-1.140'), (1, '22.140')] -[2023-10-10 22:19:23,334][98559] Updated weights for policy 0, policy_version 39300 (0.0009) -[2023-10-10 22:19:23,707][98559] Updated weights for policy 0, policy_version 39310 (0.0009) -[2023-10-10 22:19:24,080][98559] Updated weights for policy 0, policy_version 39320 (0.0007) -[2023-10-10 22:19:24,424][98560] Updated weights for policy 1, policy_version 39142 (0.0009) -[2023-10-10 22:19:24,791][98560] Updated weights for policy 1, policy_version 39152 (0.0010) -[2023-10-10 22:19:25,162][98560] Updated weights for policy 1, policy_version 39162 (0.0007) -[2023-10-10 22:19:25,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 80379904. Throughput: 0: 1712.6, 1: 1696.7. Samples: 20094302. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:19:25,557][97672] Avg episode reward: [(0, '-1.140'), (1, '22.240')] -[2023-10-10 22:19:28,107][98559] Updated weights for policy 0, policy_version 39330 (0.0008) -[2023-10-10 22:19:28,474][98559] Updated weights for policy 0, policy_version 39340 (0.0008) -[2023-10-10 22:19:28,855][98559] Updated weights for policy 0, policy_version 39350 (0.0009) -[2023-10-10 22:19:29,063][98560] Updated weights for policy 1, policy_version 39172 (0.0008) -[2023-10-10 22:19:29,214][98559] Updated weights for policy 0, policy_version 39360 (0.0009) -[2023-10-10 22:19:29,436][98560] Updated weights for policy 1, policy_version 39182 (0.0009) -[2023-10-10 22:19:29,799][98560] Updated weights for policy 1, policy_version 39192 (0.0010) -[2023-10-10 22:19:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 80445440. Throughput: 0: 1690.0, 1: 1693.8. Samples: 20114350. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:19:30,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.280')] -[2023-10-10 22:19:33,159][98559] Updated weights for policy 0, policy_version 39370 (0.0009) -[2023-10-10 22:19:33,532][98559] Updated weights for policy 0, policy_version 39380 (0.0008) -[2023-10-10 22:19:33,853][98560] Updated weights for policy 1, policy_version 39202 (0.0008) -[2023-10-10 22:19:33,905][98559] Updated weights for policy 0, policy_version 39390 (0.0007) -[2023-10-10 22:19:34,225][98560] Updated weights for policy 1, policy_version 39212 (0.0009) -[2023-10-10 22:19:34,589][98560] Updated weights for policy 1, policy_version 39222 (0.0008) -[2023-10-10 22:19:34,956][98560] Updated weights for policy 1, policy_version 39232 (0.0008) -[2023-10-10 22:19:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 80510976. Throughput: 0: 1711.8, 1: 1679.7. Samples: 20134472. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:19:35,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.300')] -[2023-10-10 22:19:37,937][98559] Updated weights for policy 0, policy_version 39400 (0.0008) -[2023-10-10 22:19:38,308][98559] Updated weights for policy 0, policy_version 39410 (0.0008) -[2023-10-10 22:19:38,679][98559] Updated weights for policy 0, policy_version 39420 (0.0008) -[2023-10-10 22:19:38,982][98560] Updated weights for policy 1, policy_version 39242 (0.0008) -[2023-10-10 22:19:39,346][98560] Updated weights for policy 1, policy_version 39252 (0.0009) -[2023-10-10 22:19:39,721][98560] Updated weights for policy 1, policy_version 39262 (0.0008) -[2023-10-10 22:19:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 80576512. Throughput: 0: 1709.7, 1: 1698.7. Samples: 20145230. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:19:40,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.280')] -[2023-10-10 22:19:42,564][98559] Updated weights for policy 0, policy_version 39430 (0.0009) -[2023-10-10 22:19:42,933][98559] Updated weights for policy 0, policy_version 39440 (0.0008) -[2023-10-10 22:19:43,303][98559] Updated weights for policy 0, policy_version 39450 (0.0007) -[2023-10-10 22:19:43,613][98560] Updated weights for policy 1, policy_version 39272 (0.0008) -[2023-10-10 22:19:43,983][98560] Updated weights for policy 1, policy_version 39282 (0.0008) -[2023-10-10 22:19:44,350][98560] Updated weights for policy 1, policy_version 39292 (0.0008) -[2023-10-10 22:19:45,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 80642048. Throughput: 0: 1699.8, 1: 1694.7. Samples: 20165604. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-10 22:19:45,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.340')] -[2023-10-10 22:19:47,144][98559] Updated weights for policy 0, policy_version 39460 (0.0009) -[2023-10-10 22:19:47,512][98559] Updated weights for policy 0, policy_version 39470 (0.0011) -[2023-10-10 22:19:47,873][98559] Updated weights for policy 0, policy_version 39480 (0.0010) -[2023-10-10 22:19:48,444][98560] Updated weights for policy 1, policy_version 39302 (0.0008) -[2023-10-10 22:19:48,803][98560] Updated weights for policy 1, policy_version 39312 (0.0007) -[2023-10-10 22:19:49,172][98560] Updated weights for policy 1, policy_version 39322 (0.0008) -[2023-10-10 22:19:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 80707584. Throughput: 0: 1727.7, 1: 1680.2. Samples: 20185950. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-10 22:19:50,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.360')] -[2023-10-10 22:19:51,804][98559] Updated weights for policy 0, policy_version 39490 (0.0008) -[2023-10-10 22:19:52,171][98559] Updated weights for policy 0, policy_version 39500 (0.0009) -[2023-10-10 22:19:52,546][98559] Updated weights for policy 0, policy_version 39510 (0.0009) -[2023-10-10 22:19:52,904][98559] Updated weights for policy 0, policy_version 39520 (0.0008) -[2023-10-10 22:19:53,151][98560] Updated weights for policy 1, policy_version 39332 (0.0008) -[2023-10-10 22:19:53,526][98560] Updated weights for policy 1, policy_version 39342 (0.0007) -[2023-10-10 22:19:53,896][98560] Updated weights for policy 1, policy_version 39352 (0.0008) -[2023-10-10 22:19:55,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 80773120. Throughput: 0: 1698.8, 1: 1708.8. Samples: 20196608. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-10 22:19:55,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.360')] -[2023-10-10 22:19:56,977][98559] Updated weights for policy 0, policy_version 39530 (0.0007) -[2023-10-10 22:19:57,343][98559] Updated weights for policy 0, policy_version 39540 (0.0009) -[2023-10-10 22:19:57,712][98559] Updated weights for policy 0, policy_version 39550 (0.0007) -[2023-10-10 22:19:57,977][98560] Updated weights for policy 1, policy_version 39362 (0.0008) -[2023-10-10 22:19:58,352][98560] Updated weights for policy 1, policy_version 39372 (0.0010) -[2023-10-10 22:19:58,717][98560] Updated weights for policy 1, policy_version 39382 (0.0009) -[2023-10-10 22:19:59,096][98560] Updated weights for policy 1, policy_version 39392 (0.0007) -[2023-10-10 22:20:00,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 80838656. Throughput: 0: 1721.1, 1: 1687.7. Samples: 20216888. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-10 22:20:00,556][97672] Avg episode reward: [(0, '-1.180'), (1, '22.340')] -[2023-10-10 22:20:01,615][98559] Updated weights for policy 0, policy_version 39560 (0.0009) -[2023-10-10 22:20:01,976][98559] Updated weights for policy 0, policy_version 39570 (0.0007) -[2023-10-10 22:20:02,350][98559] Updated weights for policy 0, policy_version 39580 (0.0009) -[2023-10-10 22:20:03,033][98560] Updated weights for policy 1, policy_version 39402 (0.0008) -[2023-10-10 22:20:03,395][98560] Updated weights for policy 1, policy_version 39412 (0.0008) -[2023-10-10 22:20:03,764][98560] Updated weights for policy 1, policy_version 39422 (0.0010) -[2023-10-10 22:20:05,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 80904192. Throughput: 0: 1734.4, 1: 1687.0. Samples: 20237460. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-10 22:20:05,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.320')] -[2023-10-10 22:20:06,382][98559] Updated weights for policy 0, policy_version 39590 (0.0011) -[2023-10-10 22:20:06,741][98559] Updated weights for policy 0, policy_version 39600 (0.0010) -[2023-10-10 22:20:07,103][98559] Updated weights for policy 0, policy_version 39610 (0.0009) -[2023-10-10 22:20:07,722][98560] Updated weights for policy 1, policy_version 39432 (0.0008) -[2023-10-10 22:20:08,080][98560] Updated weights for policy 1, policy_version 39442 (0.0008) -[2023-10-10 22:20:08,456][98560] Updated weights for policy 1, policy_version 39452 (0.0007) -[2023-10-10 22:20:10,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 80969728. Throughput: 0: 1708.5, 1: 1708.3. Samples: 20248060. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-10 22:20:10,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.280')] -[2023-10-10 22:20:11,071][98559] Updated weights for policy 0, policy_version 39620 (0.0009) -[2023-10-10 22:20:11,445][98559] Updated weights for policy 0, policy_version 39630 (0.0009) -[2023-10-10 22:20:11,817][98559] Updated weights for policy 0, policy_version 39640 (0.0008) -[2023-10-10 22:20:12,371][98560] Updated weights for policy 1, policy_version 39462 (0.0010) -[2023-10-10 22:20:12,736][98560] Updated weights for policy 1, policy_version 39472 (0.0008) -[2023-10-10 22:20:13,101][98560] Updated weights for policy 1, policy_version 39482 (0.0008) -[2023-10-10 22:20:15,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 81035264. Throughput: 0: 1733.1, 1: 1690.3. Samples: 20268402. Policy #0 lag: (min: 13.0, avg: 16.6, max: 45.0) -[2023-10-10 22:20:15,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.260')] -[2023-10-10 22:20:15,700][98559] Updated weights for policy 0, policy_version 39650 (0.0008) -[2023-10-10 22:20:16,066][98559] Updated weights for policy 0, policy_version 39660 (0.0009) -[2023-10-10 22:20:16,431][98559] Updated weights for policy 0, policy_version 39670 (0.0007) -[2023-10-10 22:20:16,794][98559] Updated weights for policy 0, policy_version 39680 (0.0007) -[2023-10-10 22:20:17,164][98560] Updated weights for policy 1, policy_version 39492 (0.0008) -[2023-10-10 22:20:17,529][98560] Updated weights for policy 1, policy_version 39502 (0.0009) -[2023-10-10 22:20:17,898][98560] Updated weights for policy 1, policy_version 39512 (0.0010) -[2023-10-10 22:20:20,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 81100800. Throughput: 0: 1740.0, 1: 1707.2. Samples: 20289596. Policy #0 lag: (min: 13.0, avg: 16.6, max: 45.0) -[2023-10-10 22:20:20,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.220')] -[2023-10-10 22:20:20,709][98559] Updated weights for policy 0, policy_version 39690 (0.0009) -[2023-10-10 22:20:21,084][98559] Updated weights for policy 0, policy_version 39700 (0.0010) -[2023-10-10 22:20:21,444][98559] Updated weights for policy 0, policy_version 39710 (0.0008) -[2023-10-10 22:20:21,880][98560] Updated weights for policy 1, policy_version 39522 (0.0007) -[2023-10-10 22:20:22,247][98560] Updated weights for policy 1, policy_version 39532 (0.0009) -[2023-10-10 22:20:22,610][98560] Updated weights for policy 1, policy_version 39542 (0.0009) -[2023-10-10 22:20:22,979][98560] Updated weights for policy 1, policy_version 39552 (0.0010) -[2023-10-10 22:20:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 81166336. Throughput: 0: 1725.0, 1: 1696.0. Samples: 20299178. Policy #0 lag: (min: 13.0, avg: 16.6, max: 45.0) -[2023-10-10 22:20:25,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.200')] -[2023-10-10 22:20:25,624][98559] Updated weights for policy 0, policy_version 39720 (0.0008) -[2023-10-10 22:20:25,990][98559] Updated weights for policy 0, policy_version 39730 (0.0009) -[2023-10-10 22:20:26,371][98559] Updated weights for policy 0, policy_version 39740 (0.0009) -[2023-10-10 22:20:27,013][98560] Updated weights for policy 1, policy_version 39562 (0.0008) -[2023-10-10 22:20:27,386][98560] Updated weights for policy 1, policy_version 39572 (0.0009) -[2023-10-10 22:20:27,751][98560] Updated weights for policy 1, policy_version 39582 (0.0008) -[2023-10-10 22:20:30,421][98559] Updated weights for policy 0, policy_version 39750 (0.0008) -[2023-10-10 22:20:30,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 81231872. Throughput: 0: 1728.6, 1: 1692.5. Samples: 20319550. Policy #0 lag: (min: 13.0, avg: 16.6, max: 45.0) -[2023-10-10 22:20:30,556][97672] Avg episode reward: [(0, '-1.180'), (1, '22.140')] -[2023-10-10 22:20:30,796][98559] Updated weights for policy 0, policy_version 39760 (0.0007) -[2023-10-10 22:20:31,159][98559] Updated weights for policy 0, policy_version 39770 (0.0008) -[2023-10-10 22:20:31,850][98560] Updated weights for policy 1, policy_version 39592 (0.0008) -[2023-10-10 22:20:32,216][98560] Updated weights for policy 1, policy_version 39602 (0.0009) -[2023-10-10 22:20:32,580][98560] Updated weights for policy 1, policy_version 39612 (0.0011) -[2023-10-10 22:20:35,085][98559] Updated weights for policy 0, policy_version 39780 (0.0010) -[2023-10-10 22:20:35,460][98559] Updated weights for policy 0, policy_version 39790 (0.0008) -[2023-10-10 22:20:35,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 81297408. Throughput: 0: 1713.8, 1: 1712.2. Samples: 20340120. Policy #0 lag: (min: 13.0, avg: 16.6, max: 45.0) -[2023-10-10 22:20:35,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.160')] -[2023-10-10 22:20:35,565][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000039616_40566784.pth... -[2023-10-10 22:20:35,600][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000038048_38961152.pth -[2023-10-10 22:20:35,604][98439] Saving a milestone ./train_atari/atari_doubledunk_APPO/checkpoint_p1/milestones/checkpoint_000039616_40566784.pth -[2023-10-10 22:20:35,822][98559] Updated weights for policy 0, policy_version 39800 (0.0007) -[2023-10-10 22:20:36,111][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000039808_40763392.pth... -[2023-10-10 22:20:36,140][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000038208_39124992.pth -[2023-10-10 22:20:36,144][98385] Saving a milestone ./train_atari/atari_doubledunk_APPO/checkpoint_p0/milestones/checkpoint_000039808_40763392.pth -[2023-10-10 22:20:36,614][98560] Updated weights for policy 1, policy_version 39622 (0.0009) -[2023-10-10 22:20:36,985][98560] Updated weights for policy 1, policy_version 39632 (0.0008) -[2023-10-10 22:20:37,357][98560] Updated weights for policy 1, policy_version 39642 (0.0007) -[2023-10-10 22:20:39,762][98559] Updated weights for policy 0, policy_version 39810 (0.0009) -[2023-10-10 22:20:40,126][98559] Updated weights for policy 0, policy_version 39820 (0.0008) -[2023-10-10 22:20:40,496][98559] Updated weights for policy 0, policy_version 39830 (0.0007) -[2023-10-10 22:20:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 81362944. Throughput: 0: 1722.7, 1: 1682.6. Samples: 20349846. Policy #0 lag: (min: 13.0, avg: 16.6, max: 45.0) -[2023-10-10 22:20:40,556][97672] Avg episode reward: [(0, '-1.180'), (1, '22.120')] -[2023-10-10 22:20:40,872][98559] Updated weights for policy 0, policy_version 39840 (0.0008) -[2023-10-10 22:20:41,332][98560] Updated weights for policy 1, policy_version 39652 (0.0008) -[2023-10-10 22:20:41,704][98560] Updated weights for policy 1, policy_version 39662 (0.0007) -[2023-10-10 22:20:42,084][98560] Updated weights for policy 1, policy_version 39672 (0.0007) -[2023-10-10 22:20:44,782][98559] Updated weights for policy 0, policy_version 39850 (0.0011) -[2023-10-10 22:20:45,144][98559] Updated weights for policy 0, policy_version 39860 (0.0010) -[2023-10-10 22:20:45,507][98559] Updated weights for policy 0, policy_version 39870 (0.0009) -[2023-10-10 22:20:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 81428480. Throughput: 0: 1722.0, 1: 1700.4. Samples: 20370896. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:20:45,556][97672] Avg episode reward: [(0, '-1.140'), (1, '22.120')] -[2023-10-10 22:20:45,903][98560] Updated weights for policy 1, policy_version 39682 (0.0007) -[2023-10-10 22:20:46,276][98560] Updated weights for policy 1, policy_version 39692 (0.0008) -[2023-10-10 22:20:46,645][98560] Updated weights for policy 1, policy_version 39702 (0.0010) -[2023-10-10 22:20:47,010][98560] Updated weights for policy 1, policy_version 39712 (0.0011) -[2023-10-10 22:20:49,578][98559] Updated weights for policy 0, policy_version 39880 (0.0008) -[2023-10-10 22:20:49,944][98559] Updated weights for policy 0, policy_version 39890 (0.0009) -[2023-10-10 22:20:50,307][98559] Updated weights for policy 0, policy_version 39900 (0.0011) -[2023-10-10 22:20:50,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 81526784. Throughput: 0: 1696.9, 1: 1712.0. Samples: 20390862. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:20:50,557][97672] Avg episode reward: [(0, '-1.140'), (1, '22.180')] -[2023-10-10 22:20:50,979][98560] Updated weights for policy 1, policy_version 39722 (0.0009) -[2023-10-10 22:20:51,343][98560] Updated weights for policy 1, policy_version 39732 (0.0007) -[2023-10-10 22:20:51,714][98560] Updated weights for policy 1, policy_version 39742 (0.0007) -[2023-10-10 22:20:54,232][98559] Updated weights for policy 0, policy_version 39910 (0.0009) -[2023-10-10 22:20:54,590][98559] Updated weights for policy 0, policy_version 39920 (0.0009) -[2023-10-10 22:20:54,965][98559] Updated weights for policy 0, policy_version 39930 (0.0008) -[2023-10-10 22:20:55,556][97672] Fps is (10 sec: 16383.6, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 81592320. Throughput: 0: 1723.7, 1: 1685.8. Samples: 20401488. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:20:55,557][97672] Avg episode reward: [(0, '-1.140'), (1, '22.180')] -[2023-10-10 22:20:55,687][98560] Updated weights for policy 1, policy_version 39752 (0.0007) -[2023-10-10 22:20:56,053][98560] Updated weights for policy 1, policy_version 39762 (0.0008) -[2023-10-10 22:20:56,431][98560] Updated weights for policy 1, policy_version 39772 (0.0010) -[2023-10-10 22:20:58,851][98559] Updated weights for policy 0, policy_version 39940 (0.0009) -[2023-10-10 22:20:59,224][98559] Updated weights for policy 0, policy_version 39950 (0.0010) -[2023-10-10 22:20:59,589][98559] Updated weights for policy 0, policy_version 39960 (0.0008) -[2023-10-10 22:21:00,531][98560] Updated weights for policy 1, policy_version 39782 (0.0011) -[2023-10-10 22:21:00,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 81657856. Throughput: 0: 1705.5, 1: 1705.6. Samples: 20421904. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:21:00,557][97672] Avg episode reward: [(0, '-1.140'), (1, '22.240')] -[2023-10-10 22:21:00,898][98560] Updated weights for policy 1, policy_version 39792 (0.0008) -[2023-10-10 22:21:01,270][98560] Updated weights for policy 1, policy_version 39802 (0.0008) -[2023-10-10 22:21:03,496][98559] Updated weights for policy 0, policy_version 39970 (0.0008) -[2023-10-10 22:21:03,864][98559] Updated weights for policy 0, policy_version 39980 (0.0008) -[2023-10-10 22:21:04,235][98559] Updated weights for policy 0, policy_version 39990 (0.0007) -[2023-10-10 22:21:04,594][98559] Updated weights for policy 0, policy_version 40000 (0.0010) -[2023-10-10 22:21:05,258][98560] Updated weights for policy 1, policy_version 39812 (0.0008) -[2023-10-10 22:21:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 81723392. Throughput: 0: 1686.6, 1: 1707.9. Samples: 20442346. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:21:05,557][97672] Avg episode reward: [(0, '-1.140'), (1, '22.240')] -[2023-10-10 22:21:05,636][98560] Updated weights for policy 1, policy_version 39822 (0.0007) -[2023-10-10 22:21:05,999][98560] Updated weights for policy 1, policy_version 39832 (0.0008) -[2023-10-10 22:21:08,690][98559] Updated weights for policy 0, policy_version 40010 (0.0009) -[2023-10-10 22:21:09,058][98559] Updated weights for policy 0, policy_version 40020 (0.0008) -[2023-10-10 22:21:09,431][98559] Updated weights for policy 0, policy_version 40030 (0.0007) -[2023-10-10 22:21:10,067][98560] Updated weights for policy 1, policy_version 39842 (0.0008) -[2023-10-10 22:21:10,429][98560] Updated weights for policy 1, policy_version 39852 (0.0009) -[2023-10-10 22:21:10,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 81788928. Throughput: 0: 1714.4, 1: 1698.0. Samples: 20452736. Policy #0 lag: (min: 20.0, avg: 20.1, max: 27.0) -[2023-10-10 22:21:10,556][97672] Avg episode reward: [(0, '-1.140'), (1, '22.220')] -[2023-10-10 22:21:10,793][98560] Updated weights for policy 1, policy_version 39862 (0.0011) -[2023-10-10 22:21:11,167][98560] Updated weights for policy 1, policy_version 39872 (0.0011) -[2023-10-10 22:21:13,438][98559] Updated weights for policy 0, policy_version 40040 (0.0008) -[2023-10-10 22:21:13,810][98559] Updated weights for policy 0, policy_version 40050 (0.0010) -[2023-10-10 22:21:14,182][98559] Updated weights for policy 0, policy_version 40060 (0.0008) -[2023-10-10 22:21:15,155][98560] Updated weights for policy 1, policy_version 39882 (0.0009) -[2023-10-10 22:21:15,524][98560] Updated weights for policy 1, policy_version 39892 (0.0010) -[2023-10-10 22:21:15,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 81854464. Throughput: 0: 1689.5, 1: 1710.1. Samples: 20472530. Policy #0 lag: (min: 20.0, avg: 20.1, max: 27.0) -[2023-10-10 22:21:15,556][97672] Avg episode reward: [(0, '-1.140'), (1, '22.160')] -[2023-10-10 22:21:15,887][98560] Updated weights for policy 1, policy_version 39902 (0.0008) -[2023-10-10 22:21:18,220][98559] Updated weights for policy 0, policy_version 40070 (0.0010) -[2023-10-10 22:21:18,591][98559] Updated weights for policy 0, policy_version 40080 (0.0008) -[2023-10-10 22:21:18,959][98559] Updated weights for policy 0, policy_version 40090 (0.0008) -[2023-10-10 22:21:19,936][98560] Updated weights for policy 1, policy_version 39912 (0.0009) -[2023-10-10 22:21:20,294][98560] Updated weights for policy 1, policy_version 39922 (0.0009) -[2023-10-10 22:21:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 81920000. Throughput: 0: 1700.3, 1: 1712.2. Samples: 20493682. Policy #0 lag: (min: 20.0, avg: 20.1, max: 27.0) -[2023-10-10 22:21:20,556][97672] Avg episode reward: [(0, '-1.180'), (1, '22.200')] -[2023-10-10 22:21:20,662][98560] Updated weights for policy 1, policy_version 39932 (0.0009) -[2023-10-10 22:21:22,913][98559] Updated weights for policy 0, policy_version 40100 (0.0008) -[2023-10-10 22:21:23,287][98559] Updated weights for policy 0, policy_version 40110 (0.0008) -[2023-10-10 22:21:23,656][98559] Updated weights for policy 0, policy_version 40120 (0.0008) -[2023-10-10 22:21:24,561][98560] Updated weights for policy 1, policy_version 39942 (0.0010) -[2023-10-10 22:21:24,946][98560] Updated weights for policy 1, policy_version 39952 (0.0008) -[2023-10-10 22:21:25,312][98560] Updated weights for policy 1, policy_version 39962 (0.0007) -[2023-10-10 22:21:25,556][97672] Fps is (10 sec: 16383.3, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 82018304. Throughput: 0: 1703.3, 1: 1718.5. Samples: 20503828. Policy #0 lag: (min: 20.0, avg: 20.1, max: 27.0) -[2023-10-10 22:21:25,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.220')] -[2023-10-10 22:21:27,651][98559] Updated weights for policy 0, policy_version 40130 (0.0008) -[2023-10-10 22:21:28,020][98559] Updated weights for policy 0, policy_version 40140 (0.0009) -[2023-10-10 22:21:28,388][98559] Updated weights for policy 0, policy_version 40150 (0.0009) -[2023-10-10 22:21:28,753][98559] Updated weights for policy 0, policy_version 40160 (0.0008) -[2023-10-10 22:21:29,160][98560] Updated weights for policy 1, policy_version 39972 (0.0007) -[2023-10-10 22:21:29,521][98560] Updated weights for policy 1, policy_version 39982 (0.0007) -[2023-10-10 22:21:29,890][98560] Updated weights for policy 1, policy_version 39992 (0.0009) -[2023-10-10 22:21:30,556][97672] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 82083840. Throughput: 0: 1688.1, 1: 1722.6. Samples: 20524378. Policy #0 lag: (min: 20.0, avg: 20.1, max: 27.0) -[2023-10-10 22:21:30,557][97672] Avg episode reward: [(0, '-1.160'), (1, '22.240')] -[2023-10-10 22:21:32,781][98559] Updated weights for policy 0, policy_version 40170 (0.0008) -[2023-10-10 22:21:33,144][98559] Updated weights for policy 0, policy_version 40180 (0.0007) -[2023-10-10 22:21:33,512][98559] Updated weights for policy 0, policy_version 40190 (0.0008) -[2023-10-10 22:21:33,790][98560] Updated weights for policy 1, policy_version 40002 (0.0009) -[2023-10-10 22:21:34,158][98560] Updated weights for policy 1, policy_version 40012 (0.0009) -[2023-10-10 22:21:34,534][98560] Updated weights for policy 1, policy_version 40022 (0.0008) -[2023-10-10 22:21:34,899][98560] Updated weights for policy 1, policy_version 40032 (0.0009) -[2023-10-10 22:21:35,556][97672] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 82149376. Throughput: 0: 1713.0, 1: 1699.7. Samples: 20544434. Policy #0 lag: (min: 20.0, avg: 20.1, max: 27.0) -[2023-10-10 22:21:35,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.260')] -[2023-10-10 22:21:37,627][98559] Updated weights for policy 0, policy_version 40200 (0.0008) -[2023-10-10 22:21:37,994][98559] Updated weights for policy 0, policy_version 40210 (0.0010) -[2023-10-10 22:21:38,365][98559] Updated weights for policy 0, policy_version 40220 (0.0010) -[2023-10-10 22:21:38,920][98560] Updated weights for policy 1, policy_version 40042 (0.0008) -[2023-10-10 22:21:39,290][98560] Updated weights for policy 1, policy_version 40052 (0.0009) -[2023-10-10 22:21:39,662][98560] Updated weights for policy 1, policy_version 40062 (0.0009) -[2023-10-10 22:21:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 82214912. Throughput: 0: 1688.3, 1: 1720.3. Samples: 20554874. Policy #0 lag: (min: 9.0, avg: 22.6, max: 41.0) -[2023-10-10 22:21:40,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.340')] -[2023-10-10 22:21:42,411][98559] Updated weights for policy 0, policy_version 40230 (0.0009) -[2023-10-10 22:21:42,775][98559] Updated weights for policy 0, policy_version 40240 (0.0008) -[2023-10-10 22:21:43,140][98559] Updated weights for policy 0, policy_version 40250 (0.0009) -[2023-10-10 22:21:43,679][98560] Updated weights for policy 1, policy_version 40072 (0.0008) -[2023-10-10 22:21:44,055][98560] Updated weights for policy 1, policy_version 40082 (0.0007) -[2023-10-10 22:21:44,416][98560] Updated weights for policy 1, policy_version 40092 (0.0008) -[2023-10-10 22:21:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 82280448. Throughput: 0: 1694.9, 1: 1716.8. Samples: 20575434. Policy #0 lag: (min: 9.0, avg: 22.6, max: 41.0) -[2023-10-10 22:21:45,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.340')] -[2023-10-10 22:21:47,163][98559] Updated weights for policy 0, policy_version 40260 (0.0009) -[2023-10-10 22:21:47,525][98559] Updated weights for policy 0, policy_version 40270 (0.0010) -[2023-10-10 22:21:47,893][98559] Updated weights for policy 0, policy_version 40280 (0.0009) -[2023-10-10 22:21:48,505][98560] Updated weights for policy 1, policy_version 40102 (0.0010) -[2023-10-10 22:21:48,883][98560] Updated weights for policy 1, policy_version 40112 (0.0009) -[2023-10-10 22:21:49,246][98560] Updated weights for policy 1, policy_version 40122 (0.0009) -[2023-10-10 22:21:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 82345984. Throughput: 0: 1712.2, 1: 1693.1. Samples: 20595584. Policy #0 lag: (min: 9.0, avg: 22.6, max: 41.0) -[2023-10-10 22:21:50,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.320')] -[2023-10-10 22:21:51,873][98559] Updated weights for policy 0, policy_version 40290 (0.0009) -[2023-10-10 22:21:52,232][98559] Updated weights for policy 0, policy_version 40300 (0.0008) -[2023-10-10 22:21:52,606][98559] Updated weights for policy 0, policy_version 40310 (0.0007) -[2023-10-10 22:21:52,967][98559] Updated weights for policy 0, policy_version 40320 (0.0008) -[2023-10-10 22:21:53,250][98560] Updated weights for policy 1, policy_version 40132 (0.0009) -[2023-10-10 22:21:53,616][98560] Updated weights for policy 1, policy_version 40142 (0.0009) -[2023-10-10 22:21:53,992][98560] Updated weights for policy 1, policy_version 40152 (0.0008) -[2023-10-10 22:21:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 82411520. Throughput: 0: 1685.7, 1: 1723.5. Samples: 20606152. Policy #0 lag: (min: 9.0, avg: 22.6, max: 41.0) -[2023-10-10 22:21:55,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.240')] -[2023-10-10 22:21:56,905][98559] Updated weights for policy 0, policy_version 40330 (0.0011) -[2023-10-10 22:21:57,272][98559] Updated weights for policy 0, policy_version 40340 (0.0010) -[2023-10-10 22:21:57,640][98559] Updated weights for policy 0, policy_version 40350 (0.0010) -[2023-10-10 22:21:57,949][98560] Updated weights for policy 1, policy_version 40162 (0.0009) -[2023-10-10 22:21:58,315][98560] Updated weights for policy 1, policy_version 40172 (0.0008) -[2023-10-10 22:21:58,681][98560] Updated weights for policy 1, policy_version 40182 (0.0007) -[2023-10-10 22:21:59,052][98560] Updated weights for policy 1, policy_version 40192 (0.0008) -[2023-10-10 22:22:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 82477056. Throughput: 0: 1717.3, 1: 1704.6. Samples: 20626516. Policy #0 lag: (min: 9.0, avg: 22.6, max: 41.0) -[2023-10-10 22:22:00,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.220')] -[2023-10-10 22:22:01,627][98559] Updated weights for policy 0, policy_version 40360 (0.0011) -[2023-10-10 22:22:01,999][98559] Updated weights for policy 0, policy_version 40370 (0.0008) -[2023-10-10 22:22:02,376][98559] Updated weights for policy 0, policy_version 40380 (0.0008) -[2023-10-10 22:22:02,910][98560] Updated weights for policy 1, policy_version 40202 (0.0010) -[2023-10-10 22:22:03,280][98560] Updated weights for policy 1, policy_version 40212 (0.0008) -[2023-10-10 22:22:03,639][98560] Updated weights for policy 1, policy_version 40222 (0.0009) -[2023-10-10 22:22:05,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 82542592. Throughput: 0: 1714.6, 1: 1696.4. Samples: 20647180. Policy #0 lag: (min: 9.0, avg: 22.6, max: 41.0) -[2023-10-10 22:22:05,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.340')] -[2023-10-10 22:22:06,231][98559] Updated weights for policy 0, policy_version 40390 (0.0009) -[2023-10-10 22:22:06,595][98559] Updated weights for policy 0, policy_version 40400 (0.0008) -[2023-10-10 22:22:06,967][98559] Updated weights for policy 0, policy_version 40410 (0.0008) -[2023-10-10 22:22:07,640][98560] Updated weights for policy 1, policy_version 40232 (0.0008) -[2023-10-10 22:22:08,005][98560] Updated weights for policy 1, policy_version 40242 (0.0009) -[2023-10-10 22:22:08,374][98560] Updated weights for policy 1, policy_version 40252 (0.0009) -[2023-10-10 22:22:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 82608128. Throughput: 0: 1700.8, 1: 1711.6. Samples: 20657386. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:22:10,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.280')] -[2023-10-10 22:22:11,002][98559] Updated weights for policy 0, policy_version 40420 (0.0009) -[2023-10-10 22:22:11,375][98559] Updated weights for policy 0, policy_version 40430 (0.0007) -[2023-10-10 22:22:11,744][98559] Updated weights for policy 0, policy_version 40440 (0.0009) -[2023-10-10 22:22:12,410][98560] Updated weights for policy 1, policy_version 40262 (0.0008) -[2023-10-10 22:22:12,772][98560] Updated weights for policy 1, policy_version 40272 (0.0009) -[2023-10-10 22:22:13,132][98560] Updated weights for policy 1, policy_version 40282 (0.0009) -[2023-10-10 22:22:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 82673664. Throughput: 0: 1715.3, 1: 1689.3. Samples: 20677584. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:22:15,556][97672] Avg episode reward: [(0, '-1.260'), (1, '22.260')] -[2023-10-10 22:22:15,780][98559] Updated weights for policy 0, policy_version 40450 (0.0007) -[2023-10-10 22:22:16,146][98559] Updated weights for policy 0, policy_version 40460 (0.0007) -[2023-10-10 22:22:16,520][98559] Updated weights for policy 0, policy_version 40470 (0.0009) -[2023-10-10 22:22:16,882][98559] Updated weights for policy 0, policy_version 40480 (0.0009) -[2023-10-10 22:22:17,374][98560] Updated weights for policy 1, policy_version 40292 (0.0010) -[2023-10-10 22:22:17,766][98560] Updated weights for policy 1, policy_version 40302 (0.0010) -[2023-10-10 22:22:18,142][98560] Updated weights for policy 1, policy_version 40312 (0.0009) -[2023-10-10 22:22:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 82739200. Throughput: 0: 1718.8, 1: 1712.1. Samples: 20698824. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:22:20,556][97672] Avg episode reward: [(0, '-1.260'), (1, '22.260')] -[2023-10-10 22:22:20,735][98559] Updated weights for policy 0, policy_version 40490 (0.0008) -[2023-10-10 22:22:21,112][98559] Updated weights for policy 0, policy_version 40500 (0.0009) -[2023-10-10 22:22:21,487][98559] Updated weights for policy 0, policy_version 40510 (0.0007) -[2023-10-10 22:22:22,045][98560] Updated weights for policy 1, policy_version 40322 (0.0009) -[2023-10-10 22:22:22,418][98560] Updated weights for policy 1, policy_version 40332 (0.0009) -[2023-10-10 22:22:22,781][98560] Updated weights for policy 1, policy_version 40342 (0.0007) -[2023-10-10 22:22:23,141][98560] Updated weights for policy 1, policy_version 40352 (0.0008) -[2023-10-10 22:22:25,477][98559] Updated weights for policy 0, policy_version 40520 (0.0008) -[2023-10-10 22:22:25,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 82804736. Throughput: 0: 1715.7, 1: 1700.1. Samples: 20708584. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:22:25,556][97672] Avg episode reward: [(0, '-1.260'), (1, '22.260')] -[2023-10-10 22:22:25,847][98559] Updated weights for policy 0, policy_version 40530 (0.0007) -[2023-10-10 22:22:26,216][98559] Updated weights for policy 0, policy_version 40540 (0.0008) -[2023-10-10 22:22:27,384][98560] Updated weights for policy 1, policy_version 40362 (0.0008) -[2023-10-10 22:22:27,745][98560] Updated weights for policy 1, policy_version 40372 (0.0008) -[2023-10-10 22:22:28,120][98560] Updated weights for policy 1, policy_version 40382 (0.0008) -[2023-10-10 22:22:30,103][98559] Updated weights for policy 0, policy_version 40550 (0.0010) -[2023-10-10 22:22:30,468][98559] Updated weights for policy 0, policy_version 40560 (0.0008) -[2023-10-10 22:22:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 82870272. Throughput: 0: 1727.6, 1: 1688.2. Samples: 20729142. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:22:30,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.240')] -[2023-10-10 22:22:30,833][98559] Updated weights for policy 0, policy_version 40570 (0.0011) -[2023-10-10 22:22:32,031][98560] Updated weights for policy 1, policy_version 40392 (0.0009) -[2023-10-10 22:22:32,393][98560] Updated weights for policy 1, policy_version 40402 (0.0009) -[2023-10-10 22:22:32,757][98560] Updated weights for policy 1, policy_version 40412 (0.0009) -[2023-10-10 22:22:34,613][98559] Updated weights for policy 0, policy_version 40580 (0.0009) -[2023-10-10 22:22:34,988][98559] Updated weights for policy 0, policy_version 40590 (0.0008) -[2023-10-10 22:22:35,358][98559] Updated weights for policy 0, policy_version 40600 (0.0008) -[2023-10-10 22:22:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 82935808. Throughput: 0: 1707.2, 1: 1709.8. Samples: 20749348. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:22:35,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.340')] -[2023-10-10 22:22:35,564][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000040416_41385984.pth... -[2023-10-10 22:22:35,597][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000038848_39780352.pth -[2023-10-10 22:22:35,653][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000040608_41582592.pth... -[2023-10-10 22:22:35,696][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000039008_39944192.pth -[2023-10-10 22:22:36,725][98560] Updated weights for policy 1, policy_version 40422 (0.0008) -[2023-10-10 22:22:37,106][98560] Updated weights for policy 1, policy_version 40432 (0.0009) -[2023-10-10 22:22:37,475][98560] Updated weights for policy 1, policy_version 40442 (0.0008) -[2023-10-10 22:22:39,298][98559] Updated weights for policy 0, policy_version 40610 (0.0008) -[2023-10-10 22:22:39,665][98559] Updated weights for policy 0, policy_version 40620 (0.0009) -[2023-10-10 22:22:40,029][98559] Updated weights for policy 0, policy_version 40630 (0.0008) -[2023-10-10 22:22:40,395][98559] Updated weights for policy 0, policy_version 40640 (0.0008) -[2023-10-10 22:22:40,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 83034112. Throughput: 0: 1729.3, 1: 1685.7. Samples: 20759828. Policy #0 lag: (min: 14.0, avg: 17.4, max: 46.0) -[2023-10-10 22:22:40,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.380')] -[2023-10-10 22:22:41,193][98560] Updated weights for policy 1, policy_version 40452 (0.0008) -[2023-10-10 22:22:41,563][98560] Updated weights for policy 1, policy_version 40462 (0.0007) -[2023-10-10 22:22:41,931][98560] Updated weights for policy 1, policy_version 40472 (0.0008) -[2023-10-10 22:22:44,323][98559] Updated weights for policy 0, policy_version 40650 (0.0009) -[2023-10-10 22:22:44,700][98559] Updated weights for policy 0, policy_version 40660 (0.0011) -[2023-10-10 22:22:45,056][98559] Updated weights for policy 0, policy_version 40670 (0.0008) -[2023-10-10 22:22:45,556][97672] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 83099648. Throughput: 0: 1721.4, 1: 1706.0. Samples: 20780752. Policy #0 lag: (min: 14.0, avg: 17.4, max: 46.0) -[2023-10-10 22:22:45,556][97672] Avg episode reward: [(0, '-1.260'), (1, '22.400')] -[2023-10-10 22:22:45,858][98560] Updated weights for policy 1, policy_version 40482 (0.0007) -[2023-10-10 22:22:46,224][98560] Updated weights for policy 1, policy_version 40492 (0.0008) -[2023-10-10 22:22:46,591][98560] Updated weights for policy 1, policy_version 40502 (0.0008) -[2023-10-10 22:22:46,965][98560] Updated weights for policy 1, policy_version 40512 (0.0008) -[2023-10-10 22:22:49,112][98559] Updated weights for policy 0, policy_version 40680 (0.0008) -[2023-10-10 22:22:49,484][98559] Updated weights for policy 0, policy_version 40690 (0.0008) -[2023-10-10 22:22:49,846][98559] Updated weights for policy 0, policy_version 40700 (0.0009) -[2023-10-10 22:22:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 83165184. Throughput: 0: 1700.9, 1: 1714.1. Samples: 20800856. Policy #0 lag: (min: 14.0, avg: 17.4, max: 46.0) -[2023-10-10 22:22:50,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.360')] -[2023-10-10 22:22:50,975][98560] Updated weights for policy 1, policy_version 40522 (0.0008) -[2023-10-10 22:22:51,344][98560] Updated weights for policy 1, policy_version 40532 (0.0010) -[2023-10-10 22:22:51,710][98560] Updated weights for policy 1, policy_version 40542 (0.0008) -[2023-10-10 22:22:53,853][98559] Updated weights for policy 0, policy_version 40710 (0.0009) -[2023-10-10 22:22:54,217][98559] Updated weights for policy 0, policy_version 40720 (0.0008) -[2023-10-10 22:22:54,589][98559] Updated weights for policy 0, policy_version 40730 (0.0007) -[2023-10-10 22:22:55,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 83230720. Throughput: 0: 1731.4, 1: 1692.1. Samples: 20811442. Policy #0 lag: (min: 14.0, avg: 17.4, max: 46.0) -[2023-10-10 22:22:55,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.420')] -[2023-10-10 22:22:55,763][98560] Updated weights for policy 1, policy_version 40552 (0.0007) -[2023-10-10 22:22:56,132][98560] Updated weights for policy 1, policy_version 40562 (0.0007) -[2023-10-10 22:22:56,493][98560] Updated weights for policy 1, policy_version 40572 (0.0007) -[2023-10-10 22:22:58,611][98559] Updated weights for policy 0, policy_version 40740 (0.0008) -[2023-10-10 22:22:58,978][98559] Updated weights for policy 0, policy_version 40750 (0.0010) -[2023-10-10 22:22:59,343][98559] Updated weights for policy 0, policy_version 40760 (0.0009) -[2023-10-10 22:23:00,510][98560] Updated weights for policy 1, policy_version 40582 (0.0008) -[2023-10-10 22:23:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 83296256. Throughput: 0: 1712.3, 1: 1713.2. Samples: 20831732. Policy #0 lag: (min: 14.0, avg: 17.4, max: 46.0) -[2023-10-10 22:23:00,556][97672] Avg episode reward: [(0, '-1.260'), (1, '22.360')] -[2023-10-10 22:23:00,874][98560] Updated weights for policy 1, policy_version 40592 (0.0007) -[2023-10-10 22:23:01,246][98560] Updated weights for policy 1, policy_version 40602 (0.0007) -[2023-10-10 22:23:03,374][98559] Updated weights for policy 0, policy_version 40770 (0.0011) -[2023-10-10 22:23:03,734][98559] Updated weights for policy 0, policy_version 40780 (0.0011) -[2023-10-10 22:23:04,102][98559] Updated weights for policy 0, policy_version 40790 (0.0009) -[2023-10-10 22:23:04,474][98559] Updated weights for policy 0, policy_version 40800 (0.0008) -[2023-10-10 22:23:05,245][98560] Updated weights for policy 1, policy_version 40612 (0.0007) -[2023-10-10 22:23:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 83361792. Throughput: 0: 1696.0, 1: 1716.9. Samples: 20852404. Policy #0 lag: (min: 31.0, avg: 31.2, max: 40.0) -[2023-10-10 22:23:05,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.460')] -[2023-10-10 22:23:05,647][98560] Updated weights for policy 1, policy_version 40622 (0.0008) -[2023-10-10 22:23:06,018][98560] Updated weights for policy 1, policy_version 40632 (0.0008) -[2023-10-10 22:23:08,589][98559] Updated weights for policy 0, policy_version 40810 (0.0010) -[2023-10-10 22:23:08,955][98559] Updated weights for policy 0, policy_version 40820 (0.0009) -[2023-10-10 22:23:09,325][98559] Updated weights for policy 0, policy_version 40830 (0.0007) -[2023-10-10 22:23:10,097][98560] Updated weights for policy 1, policy_version 40642 (0.0008) -[2023-10-10 22:23:10,462][98560] Updated weights for policy 1, policy_version 40652 (0.0009) -[2023-10-10 22:23:10,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 83427328. Throughput: 0: 1719.0, 1: 1702.7. Samples: 20862560. Policy #0 lag: (min: 31.0, avg: 31.2, max: 40.0) -[2023-10-10 22:23:10,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.460')] -[2023-10-10 22:23:10,831][98560] Updated weights for policy 1, policy_version 40662 (0.0008) -[2023-10-10 22:23:11,202][98560] Updated weights for policy 1, policy_version 40672 (0.0008) -[2023-10-10 22:23:13,355][98559] Updated weights for policy 0, policy_version 40840 (0.0007) -[2023-10-10 22:23:13,719][98559] Updated weights for policy 0, policy_version 40850 (0.0008) -[2023-10-10 22:23:14,083][98559] Updated weights for policy 0, policy_version 40860 (0.0008) -[2023-10-10 22:23:15,220][98560] Updated weights for policy 1, policy_version 40682 (0.0007) -[2023-10-10 22:23:15,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 83492864. Throughput: 0: 1690.0, 1: 1722.5. Samples: 20882706. Policy #0 lag: (min: 31.0, avg: 31.2, max: 40.0) -[2023-10-10 22:23:15,556][97672] Avg episode reward: [(0, '-1.120'), (1, '22.440')] -[2023-10-10 22:23:15,586][98560] Updated weights for policy 1, policy_version 40692 (0.0008) -[2023-10-10 22:23:15,947][98560] Updated weights for policy 1, policy_version 40702 (0.0008) -[2023-10-10 22:23:17,901][98559] Updated weights for policy 0, policy_version 40870 (0.0007) -[2023-10-10 22:23:18,273][98559] Updated weights for policy 0, policy_version 40880 (0.0008) -[2023-10-10 22:23:18,631][98559] Updated weights for policy 0, policy_version 40890 (0.0009) -[2023-10-10 22:23:19,778][98560] Updated weights for policy 1, policy_version 40712 (0.0007) -[2023-10-10 22:23:20,152][98560] Updated weights for policy 1, policy_version 40722 (0.0009) -[2023-10-10 22:23:20,524][98560] Updated weights for policy 1, policy_version 40732 (0.0010) -[2023-10-10 22:23:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 83558400. Throughput: 0: 1718.1, 1: 1717.7. Samples: 20903960. Policy #0 lag: (min: 31.0, avg: 31.2, max: 40.0) -[2023-10-10 22:23:20,556][97672] Avg episode reward: [(0, '-1.160'), (1, '22.400')] -[2023-10-10 22:23:22,601][98559] Updated weights for policy 0, policy_version 40900 (0.0008) -[2023-10-10 22:23:22,964][98559] Updated weights for policy 0, policy_version 40910 (0.0008) -[2023-10-10 22:23:23,326][98559] Updated weights for policy 0, policy_version 40920 (0.0008) -[2023-10-10 22:23:24,509][98560] Updated weights for policy 1, policy_version 40742 (0.0008) -[2023-10-10 22:23:24,865][98560] Updated weights for policy 1, policy_version 40752 (0.0009) -[2023-10-10 22:23:25,239][98560] Updated weights for policy 1, policy_version 40762 (0.0007) -[2023-10-10 22:23:25,556][97672] Fps is (10 sec: 16383.4, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 83656704. Throughput: 0: 1703.5, 1: 1717.9. Samples: 20913794. Policy #0 lag: (min: 31.0, avg: 31.2, max: 40.0) -[2023-10-10 22:23:25,558][97672] Avg episode reward: [(0, '-1.160'), (1, '22.280')] -[2023-10-10 22:23:27,396][98559] Updated weights for policy 0, policy_version 40930 (0.0009) -[2023-10-10 22:23:27,769][98559] Updated weights for policy 0, policy_version 40940 (0.0010) -[2023-10-10 22:23:28,147][98559] Updated weights for policy 0, policy_version 40950 (0.0010) -[2023-10-10 22:23:28,515][98559] Updated weights for policy 0, policy_version 40960 (0.0010) -[2023-10-10 22:23:29,332][98560] Updated weights for policy 1, policy_version 40772 (0.0008) -[2023-10-10 22:23:29,694][98560] Updated weights for policy 1, policy_version 40782 (0.0007) -[2023-10-10 22:23:30,065][98560] Updated weights for policy 1, policy_version 40792 (0.0008) -[2023-10-10 22:23:30,556][97672] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 83722240. Throughput: 0: 1701.1, 1: 1716.6. Samples: 20934546. Policy #0 lag: (min: 31.0, avg: 31.2, max: 40.0) -[2023-10-10 22:23:30,556][97672] Avg episode reward: [(0, '-1.160'), (1, '22.260')] -[2023-10-10 22:23:32,599][98559] Updated weights for policy 0, policy_version 40970 (0.0009) -[2023-10-10 22:23:32,957][98559] Updated weights for policy 0, policy_version 40980 (0.0010) -[2023-10-10 22:23:33,324][98559] Updated weights for policy 0, policy_version 40990 (0.0010) -[2023-10-10 22:23:34,032][98560] Updated weights for policy 1, policy_version 40802 (0.0008) -[2023-10-10 22:23:34,403][98560] Updated weights for policy 1, policy_version 40812 (0.0008) -[2023-10-10 22:23:34,773][98560] Updated weights for policy 1, policy_version 40822 (0.0009) -[2023-10-10 22:23:35,136][98560] Updated weights for policy 1, policy_version 40832 (0.0009) -[2023-10-10 22:23:35,556][97672] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 83787776. Throughput: 0: 1726.2, 1: 1694.5. Samples: 20954790. Policy #0 lag: (min: 3.0, avg: 3.4, max: 16.0) -[2023-10-10 22:23:35,556][97672] Avg episode reward: [(0, '-1.160'), (1, '22.260')] -[2023-10-10 22:23:37,353][98559] Updated weights for policy 0, policy_version 41000 (0.0007) -[2023-10-10 22:23:37,715][98559] Updated weights for policy 0, policy_version 41010 (0.0008) -[2023-10-10 22:23:38,085][98559] Updated weights for policy 0, policy_version 41020 (0.0010) -[2023-10-10 22:23:39,108][98560] Updated weights for policy 1, policy_version 40842 (0.0009) -[2023-10-10 22:23:39,480][98560] Updated weights for policy 1, policy_version 40852 (0.0010) -[2023-10-10 22:23:39,863][98560] Updated weights for policy 1, policy_version 40862 (0.0010) -[2023-10-10 22:23:40,556][97672] Fps is (10 sec: 13106.7, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 83853312. Throughput: 0: 1694.6, 1: 1714.0. Samples: 20964828. Policy #0 lag: (min: 3.0, avg: 3.4, max: 16.0) -[2023-10-10 22:23:40,558][97672] Avg episode reward: [(0, '-0.960'), (1, '22.280')] -[2023-10-10 22:23:40,560][98385] Saving new best policy, reward=-0.960! -[2023-10-10 22:23:42,023][98559] Updated weights for policy 0, policy_version 41030 (0.0009) -[2023-10-10 22:23:42,380][98559] Updated weights for policy 0, policy_version 41040 (0.0009) -[2023-10-10 22:23:42,741][98559] Updated weights for policy 0, policy_version 41050 (0.0009) -[2023-10-10 22:23:43,958][98560] Updated weights for policy 1, policy_version 40872 (0.0007) -[2023-10-10 22:23:44,320][98560] Updated weights for policy 1, policy_version 40882 (0.0008) -[2023-10-10 22:23:44,688][98560] Updated weights for policy 1, policy_version 40892 (0.0009) -[2023-10-10 22:23:45,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 83918848. Throughput: 0: 1717.2, 1: 1708.4. Samples: 20985882. Policy #0 lag: (min: 3.0, avg: 3.4, max: 16.0) -[2023-10-10 22:23:45,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.220')] -[2023-10-10 22:23:46,744][98559] Updated weights for policy 0, policy_version 41060 (0.0009) -[2023-10-10 22:23:47,116][98559] Updated weights for policy 0, policy_version 41070 (0.0010) -[2023-10-10 22:23:47,478][98559] Updated weights for policy 0, policy_version 41080 (0.0010) -[2023-10-10 22:23:48,617][98560] Updated weights for policy 1, policy_version 40902 (0.0009) -[2023-10-10 22:23:48,985][98560] Updated weights for policy 1, policy_version 40912 (0.0010) -[2023-10-10 22:23:49,356][98560] Updated weights for policy 1, policy_version 40922 (0.0010) -[2023-10-10 22:23:50,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 83984384. Throughput: 0: 1732.1, 1: 1680.4. Samples: 21005966. Policy #0 lag: (min: 3.0, avg: 3.4, max: 16.0) -[2023-10-10 22:23:50,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.300')] -[2023-10-10 22:23:51,362][98559] Updated weights for policy 0, policy_version 41090 (0.0007) -[2023-10-10 22:23:51,734][98559] Updated weights for policy 0, policy_version 41100 (0.0008) -[2023-10-10 22:23:52,100][98559] Updated weights for policy 0, policy_version 41110 (0.0008) -[2023-10-10 22:23:52,470][98559] Updated weights for policy 0, policy_version 41120 (0.0009) -[2023-10-10 22:23:53,589][98560] Updated weights for policy 1, policy_version 40932 (0.0009) -[2023-10-10 22:23:53,995][98560] Updated weights for policy 1, policy_version 40942 (0.0009) -[2023-10-10 22:23:54,370][98560] Updated weights for policy 1, policy_version 40952 (0.0009) -[2023-10-10 22:23:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 84049920. Throughput: 0: 1708.0, 1: 1714.1. Samples: 21016554. Policy #0 lag: (min: 3.0, avg: 3.4, max: 16.0) -[2023-10-10 22:23:55,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.140')] -[2023-10-10 22:23:56,290][98559] Updated weights for policy 0, policy_version 41130 (0.0007) -[2023-10-10 22:23:56,659][98559] Updated weights for policy 0, policy_version 41140 (0.0007) -[2023-10-10 22:23:57,028][98559] Updated weights for policy 0, policy_version 41150 (0.0007) -[2023-10-10 22:23:58,308][98560] Updated weights for policy 1, policy_version 40962 (0.0010) -[2023-10-10 22:23:58,676][98560] Updated weights for policy 1, policy_version 40972 (0.0007) -[2023-10-10 22:23:59,049][98560] Updated weights for policy 1, policy_version 40982 (0.0008) -[2023-10-10 22:23:59,424][98560] Updated weights for policy 1, policy_version 40992 (0.0009) -[2023-10-10 22:24:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 84115456. Throughput: 0: 1739.3, 1: 1692.2. Samples: 21037124. Policy #0 lag: (min: 3.0, avg: 3.4, max: 16.0) -[2023-10-10 22:24:00,556][97672] Avg episode reward: [(0, '-0.960'), (1, '22.100')] -[2023-10-10 22:24:00,888][98559] Updated weights for policy 0, policy_version 41160 (0.0008) -[2023-10-10 22:24:01,257][98559] Updated weights for policy 0, policy_version 41170 (0.0010) -[2023-10-10 22:24:01,620][98559] Updated weights for policy 0, policy_version 41180 (0.0010) -[2023-10-10 22:24:03,429][98560] Updated weights for policy 1, policy_version 41002 (0.0009) -[2023-10-10 22:24:03,793][98560] Updated weights for policy 1, policy_version 41012 (0.0007) -[2023-10-10 22:24:04,168][98560] Updated weights for policy 1, policy_version 41022 (0.0007) -[2023-10-10 22:24:05,510][98559] Updated weights for policy 0, policy_version 41190 (0.0008) -[2023-10-10 22:24:05,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 84180992. Throughput: 0: 1728.7, 1: 1677.6. Samples: 21057244. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-10 22:24:05,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.120')] -[2023-10-10 22:24:05,870][98559] Updated weights for policy 0, policy_version 41200 (0.0008) -[2023-10-10 22:24:06,236][98559] Updated weights for policy 0, policy_version 41210 (0.0007) -[2023-10-10 22:24:06,458][98385] Saving new best policy, reward=-0.940! -[2023-10-10 22:24:08,192][98560] Updated weights for policy 1, policy_version 41032 (0.0009) -[2023-10-10 22:24:08,561][98560] Updated weights for policy 1, policy_version 41042 (0.0009) -[2023-10-10 22:24:08,934][98560] Updated weights for policy 1, policy_version 41052 (0.0007) -[2023-10-10 22:24:10,261][98559] Updated weights for policy 0, policy_version 41220 (0.0009) -[2023-10-10 22:24:10,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 84246528. Throughput: 0: 1722.2, 1: 1704.8. Samples: 21068008. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-10 22:24:10,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.160')] -[2023-10-10 22:24:10,630][98559] Updated weights for policy 0, policy_version 41230 (0.0010) -[2023-10-10 22:24:10,994][98559] Updated weights for policy 0, policy_version 41240 (0.0010) -[2023-10-10 22:24:12,900][98560] Updated weights for policy 1, policy_version 41062 (0.0007) -[2023-10-10 22:24:13,266][98560] Updated weights for policy 1, policy_version 41072 (0.0007) -[2023-10-10 22:24:13,630][98560] Updated weights for policy 1, policy_version 41082 (0.0011) -[2023-10-10 22:24:14,897][98559] Updated weights for policy 0, policy_version 41250 (0.0008) -[2023-10-10 22:24:15,268][98559] Updated weights for policy 0, policy_version 41260 (0.0008) -[2023-10-10 22:24:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 84312064. Throughput: 0: 1727.7, 1: 1680.6. Samples: 21087920. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-10 22:24:15,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.140')] -[2023-10-10 22:24:15,644][98559] Updated weights for policy 0, policy_version 41270 (0.0009) -[2023-10-10 22:24:16,009][98559] Updated weights for policy 0, policy_version 41280 (0.0009) -[2023-10-10 22:24:17,609][98560] Updated weights for policy 1, policy_version 41092 (0.0008) -[2023-10-10 22:24:17,975][98560] Updated weights for policy 1, policy_version 41102 (0.0011) -[2023-10-10 22:24:18,349][98560] Updated weights for policy 1, policy_version 41112 (0.0008) -[2023-10-10 22:24:20,085][98559] Updated weights for policy 0, policy_version 41290 (0.0009) -[2023-10-10 22:24:20,459][98559] Updated weights for policy 0, policy_version 41300 (0.0010) -[2023-10-10 22:24:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 84377600. Throughput: 0: 1709.6, 1: 1696.0. Samples: 21108040. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-10 22:24:20,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.100')] -[2023-10-10 22:24:20,823][98559] Updated weights for policy 0, policy_version 41310 (0.0010) -[2023-10-10 22:24:22,541][98560] Updated weights for policy 1, policy_version 41122 (0.0008) -[2023-10-10 22:24:22,904][98560] Updated weights for policy 1, policy_version 41132 (0.0010) -[2023-10-10 22:24:23,266][98560] Updated weights for policy 1, policy_version 41142 (0.0010) -[2023-10-10 22:24:23,634][98560] Updated weights for policy 1, policy_version 41152 (0.0008) -[2023-10-10 22:24:24,726][98559] Updated weights for policy 0, policy_version 41320 (0.0007) -[2023-10-10 22:24:25,099][98559] Updated weights for policy 0, policy_version 41330 (0.0008) -[2023-10-10 22:24:25,466][98559] Updated weights for policy 0, policy_version 41340 (0.0008) -[2023-10-10 22:24:25,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 84443136. Throughput: 0: 1732.1, 1: 1697.2. Samples: 21119146. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-10 22:24:25,558][97672] Avg episode reward: [(0, '-0.940'), (1, '22.060')] -[2023-10-10 22:24:27,557][98560] Updated weights for policy 1, policy_version 41162 (0.0010) -[2023-10-10 22:24:27,923][98560] Updated weights for policy 1, policy_version 41172 (0.0010) -[2023-10-10 22:24:28,288][98560] Updated weights for policy 1, policy_version 41182 (0.0009) -[2023-10-10 22:24:29,355][98559] Updated weights for policy 0, policy_version 41350 (0.0009) -[2023-10-10 22:24:29,724][98559] Updated weights for policy 0, policy_version 41360 (0.0008) -[2023-10-10 22:24:30,100][98559] Updated weights for policy 0, policy_version 41370 (0.0010) -[2023-10-10 22:24:30,556][97672] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 84541440. Throughput: 0: 1726.3, 1: 1678.0. Samples: 21139072. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 22:24:30,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.040')] -[2023-10-10 22:24:32,255][98560] Updated weights for policy 1, policy_version 41192 (0.0007) -[2023-10-10 22:24:32,633][98560] Updated weights for policy 1, policy_version 41202 (0.0010) -[2023-10-10 22:24:32,987][98560] Updated weights for policy 1, policy_version 41212 (0.0009) -[2023-10-10 22:24:34,043][98559] Updated weights for policy 0, policy_version 41380 (0.0010) -[2023-10-10 22:24:34,408][98559] Updated weights for policy 0, policy_version 41390 (0.0008) -[2023-10-10 22:24:34,773][98559] Updated weights for policy 0, policy_version 41400 (0.0007) -[2023-10-10 22:24:35,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 84606976. Throughput: 0: 1702.3, 1: 1704.4. Samples: 21159270. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 22:24:35,557][97672] Avg episode reward: [(0, '-0.900'), (1, '22.000')] -[2023-10-10 22:24:35,569][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000041408_42401792.pth... -[2023-10-10 22:24:35,569][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000041216_42205184.pth... -[2023-10-10 22:24:35,619][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000039808_40763392.pth -[2023-10-10 22:24:35,619][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000039616_40566784.pth -[2023-10-10 22:24:35,625][98385] Saving new best policy, reward=-0.900! -[2023-10-10 22:24:37,035][98560] Updated weights for policy 1, policy_version 41222 (0.0010) -[2023-10-10 22:24:37,401][98560] Updated weights for policy 1, policy_version 41232 (0.0010) -[2023-10-10 22:24:37,767][98560] Updated weights for policy 1, policy_version 41242 (0.0009) -[2023-10-10 22:24:38,720][98559] Updated weights for policy 0, policy_version 41410 (0.0007) -[2023-10-10 22:24:39,088][98559] Updated weights for policy 0, policy_version 41420 (0.0009) -[2023-10-10 22:24:39,457][98559] Updated weights for policy 0, policy_version 41430 (0.0009) -[2023-10-10 22:24:39,824][98559] Updated weights for policy 0, policy_version 41440 (0.0008) -[2023-10-10 22:24:40,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 84672512. Throughput: 0: 1736.6, 1: 1682.3. Samples: 21170404. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 22:24:40,556][97672] Avg episode reward: [(0, '-0.900'), (1, '21.940')] -[2023-10-10 22:24:41,805][98560] Updated weights for policy 1, policy_version 41252 (0.0009) -[2023-10-10 22:24:42,171][98560] Updated weights for policy 1, policy_version 41262 (0.0008) -[2023-10-10 22:24:42,546][98560] Updated weights for policy 1, policy_version 41272 (0.0008) -[2023-10-10 22:24:43,894][98559] Updated weights for policy 0, policy_version 41450 (0.0007) -[2023-10-10 22:24:44,259][98559] Updated weights for policy 0, policy_version 41460 (0.0009) -[2023-10-10 22:24:44,628][98559] Updated weights for policy 0, policy_version 41470 (0.0009) -[2023-10-10 22:24:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 84738048. Throughput: 0: 1710.5, 1: 1693.2. Samples: 21190290. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 22:24:45,557][97672] Avg episode reward: [(0, '-0.900'), (1, '22.040')] -[2023-10-10 22:24:46,416][98560] Updated weights for policy 1, policy_version 41282 (0.0009) -[2023-10-10 22:24:46,781][98560] Updated weights for policy 1, policy_version 41292 (0.0009) -[2023-10-10 22:24:47,144][98560] Updated weights for policy 1, policy_version 41302 (0.0010) -[2023-10-10 22:24:47,514][98560] Updated weights for policy 1, policy_version 41312 (0.0009) -[2023-10-10 22:24:48,564][98559] Updated weights for policy 0, policy_version 41480 (0.0011) -[2023-10-10 22:24:48,924][98559] Updated weights for policy 0, policy_version 41490 (0.0009) -[2023-10-10 22:24:49,299][98559] Updated weights for policy 0, policy_version 41500 (0.0008) -[2023-10-10 22:24:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 84803584. Throughput: 0: 1703.6, 1: 1714.3. Samples: 21211052. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 22:24:50,557][97672] Avg episode reward: [(0, '-0.900'), (1, '22.100')] -[2023-10-10 22:24:51,566][98560] Updated weights for policy 1, policy_version 41322 (0.0008) -[2023-10-10 22:24:51,941][98560] Updated weights for policy 1, policy_version 41332 (0.0007) -[2023-10-10 22:24:52,299][98560] Updated weights for policy 1, policy_version 41342 (0.0007) -[2023-10-10 22:24:53,337][98559] Updated weights for policy 0, policy_version 41510 (0.0007) -[2023-10-10 22:24:53,697][98559] Updated weights for policy 0, policy_version 41520 (0.0007) -[2023-10-10 22:24:54,062][98559] Updated weights for policy 0, policy_version 41530 (0.0007) -[2023-10-10 22:24:55,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 84869120. Throughput: 0: 1727.9, 1: 1682.4. Samples: 21221470. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 22:24:55,556][97672] Avg episode reward: [(0, '-0.880'), (1, '22.080')] -[2023-10-10 22:24:55,557][98385] Saving new best policy, reward=-0.880! -[2023-10-10 22:24:56,169][98560] Updated weights for policy 1, policy_version 41352 (0.0008) -[2023-10-10 22:24:56,527][98560] Updated weights for policy 1, policy_version 41362 (0.0009) -[2023-10-10 22:24:56,895][98560] Updated weights for policy 1, policy_version 41372 (0.0008) -[2023-10-10 22:24:57,996][98559] Updated weights for policy 0, policy_version 41540 (0.0008) -[2023-10-10 22:24:58,363][98559] Updated weights for policy 0, policy_version 41550 (0.0008) -[2023-10-10 22:24:58,734][98559] Updated weights for policy 0, policy_version 41560 (0.0009) -[2023-10-10 22:25:00,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 84934656. Throughput: 0: 1706.4, 1: 1709.9. Samples: 21241652. Policy #0 lag: (min: 8.0, avg: 36.0, max: 40.0) -[2023-10-10 22:25:00,557][97672] Avg episode reward: [(0, '-0.880'), (1, '22.100')] -[2023-10-10 22:25:00,989][98560] Updated weights for policy 1, policy_version 41382 (0.0008) -[2023-10-10 22:25:01,358][98560] Updated weights for policy 1, policy_version 41392 (0.0008) -[2023-10-10 22:25:01,720][98560] Updated weights for policy 1, policy_version 41402 (0.0010) -[2023-10-10 22:25:02,680][98559] Updated weights for policy 0, policy_version 41570 (0.0008) -[2023-10-10 22:25:03,054][98559] Updated weights for policy 0, policy_version 41580 (0.0008) -[2023-10-10 22:25:03,414][98559] Updated weights for policy 0, policy_version 41590 (0.0008) -[2023-10-10 22:25:03,780][98559] Updated weights for policy 0, policy_version 41600 (0.0008) -[2023-10-10 22:25:05,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 85000192. Throughput: 0: 1723.7, 1: 1716.5. Samples: 21262850. Policy #0 lag: (min: 8.0, avg: 36.0, max: 40.0) -[2023-10-10 22:25:05,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.080')] -[2023-10-10 22:25:05,678][98560] Updated weights for policy 1, policy_version 41412 (0.0008) -[2023-10-10 22:25:06,047][98560] Updated weights for policy 1, policy_version 41422 (0.0009) -[2023-10-10 22:25:06,413][98560] Updated weights for policy 1, policy_version 41432 (0.0008) -[2023-10-10 22:25:07,860][98559] Updated weights for policy 0, policy_version 41610 (0.0007) -[2023-10-10 22:25:08,232][98559] Updated weights for policy 0, policy_version 41620 (0.0007) -[2023-10-10 22:25:08,605][98559] Updated weights for policy 0, policy_version 41630 (0.0008) -[2023-10-10 22:25:10,304][98560] Updated weights for policy 1, policy_version 41442 (0.0007) -[2023-10-10 22:25:10,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 85065728. Throughput: 0: 1712.7, 1: 1696.1. Samples: 21272540. Policy #0 lag: (min: 8.0, avg: 36.0, max: 40.0) -[2023-10-10 22:25:10,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.120')] -[2023-10-10 22:25:10,674][98560] Updated weights for policy 1, policy_version 41452 (0.0008) -[2023-10-10 22:25:11,034][98560] Updated weights for policy 1, policy_version 41462 (0.0009) -[2023-10-10 22:25:11,407][98560] Updated weights for policy 1, policy_version 41472 (0.0007) -[2023-10-10 22:25:12,517][98559] Updated weights for policy 0, policy_version 41640 (0.0007) -[2023-10-10 22:25:12,879][98559] Updated weights for policy 0, policy_version 41650 (0.0008) -[2023-10-10 22:25:13,253][98559] Updated weights for policy 0, policy_version 41660 (0.0008) -[2023-10-10 22:25:15,544][98560] Updated weights for policy 1, policy_version 41482 (0.0007) -[2023-10-10 22:25:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 85131264. Throughput: 0: 1708.5, 1: 1719.8. Samples: 21293346. Policy #0 lag: (min: 8.0, avg: 36.0, max: 40.0) -[2023-10-10 22:25:15,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.220')] -[2023-10-10 22:25:15,909][98560] Updated weights for policy 1, policy_version 41492 (0.0010) -[2023-10-10 22:25:16,282][98560] Updated weights for policy 1, policy_version 41502 (0.0007) -[2023-10-10 22:25:17,317][98559] Updated weights for policy 0, policy_version 41670 (0.0009) -[2023-10-10 22:25:17,714][98559] Updated weights for policy 0, policy_version 41680 (0.0009) -[2023-10-10 22:25:18,082][98559] Updated weights for policy 0, policy_version 41690 (0.0008) -[2023-10-10 22:25:20,308][98560] Updated weights for policy 1, policy_version 41512 (0.0007) -[2023-10-10 22:25:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 85196800. Throughput: 0: 1728.2, 1: 1714.7. Samples: 21314200. Policy #0 lag: (min: 8.0, avg: 36.0, max: 40.0) -[2023-10-10 22:25:20,556][97672] Avg episode reward: [(0, '-0.980'), (1, '22.220')] -[2023-10-10 22:25:20,674][98560] Updated weights for policy 1, policy_version 41522 (0.0008) -[2023-10-10 22:25:21,040][98560] Updated weights for policy 1, policy_version 41532 (0.0008) -[2023-10-10 22:25:22,036][98559] Updated weights for policy 0, policy_version 41700 (0.0009) -[2023-10-10 22:25:22,411][98559] Updated weights for policy 0, policy_version 41710 (0.0010) -[2023-10-10 22:25:22,765][98559] Updated weights for policy 0, policy_version 41720 (0.0008) -[2023-10-10 22:25:24,965][98560] Updated weights for policy 1, policy_version 41542 (0.0008) -[2023-10-10 22:25:25,339][98560] Updated weights for policy 1, policy_version 41552 (0.0007) -[2023-10-10 22:25:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 85262336. Throughput: 0: 1693.7, 1: 1709.5. Samples: 21323548. Policy #0 lag: (min: 8.0, avg: 36.0, max: 40.0) -[2023-10-10 22:25:25,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.300')] -[2023-10-10 22:25:25,701][98560] Updated weights for policy 1, policy_version 41562 (0.0007) -[2023-10-10 22:25:26,626][98559] Updated weights for policy 0, policy_version 41730 (0.0007) -[2023-10-10 22:25:26,981][98559] Updated weights for policy 0, policy_version 41740 (0.0007) -[2023-10-10 22:25:27,349][98559] Updated weights for policy 0, policy_version 41750 (0.0009) -[2023-10-10 22:25:27,722][98559] Updated weights for policy 0, policy_version 41760 (0.0008) -[2023-10-10 22:25:29,803][98560] Updated weights for policy 1, policy_version 41572 (0.0007) -[2023-10-10 22:25:30,181][98560] Updated weights for policy 1, policy_version 41582 (0.0009) -[2023-10-10 22:25:30,540][98560] Updated weights for policy 1, policy_version 41592 (0.0008) -[2023-10-10 22:25:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 85327872. Throughput: 0: 1716.8, 1: 1712.7. Samples: 21344616. Policy #0 lag: (min: 25.0, avg: 30.1, max: 57.0) -[2023-10-10 22:25:30,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.280')] -[2023-10-10 22:25:31,623][98559] Updated weights for policy 0, policy_version 41770 (0.0007) -[2023-10-10 22:25:31,992][98559] Updated weights for policy 0, policy_version 41780 (0.0007) -[2023-10-10 22:25:32,361][98559] Updated weights for policy 0, policy_version 41790 (0.0007) -[2023-10-10 22:25:34,672][98560] Updated weights for policy 1, policy_version 41602 (0.0011) -[2023-10-10 22:25:35,088][98560] Updated weights for policy 1, policy_version 41612 (0.0010) -[2023-10-10 22:25:35,454][98560] Updated weights for policy 1, policy_version 41622 (0.0009) -[2023-10-10 22:25:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 85393408. Throughput: 0: 1723.6, 1: 1708.8. Samples: 21365510. Policy #0 lag: (min: 25.0, avg: 30.1, max: 57.0) -[2023-10-10 22:25:35,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.180')] -[2023-10-10 22:25:35,825][98560] Updated weights for policy 1, policy_version 41632 (0.0008) -[2023-10-10 22:25:36,284][98559] Updated weights for policy 0, policy_version 41800 (0.0009) -[2023-10-10 22:25:36,656][98559] Updated weights for policy 0, policy_version 41810 (0.0008) -[2023-10-10 22:25:37,018][98559] Updated weights for policy 0, policy_version 41820 (0.0008) -[2023-10-10 22:25:39,816][98560] Updated weights for policy 1, policy_version 41642 (0.0009) -[2023-10-10 22:25:40,190][98560] Updated weights for policy 1, policy_version 41652 (0.0009) -[2023-10-10 22:25:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 85458944. Throughput: 0: 1697.3, 1: 1706.9. Samples: 21374662. Policy #0 lag: (min: 25.0, avg: 30.1, max: 57.0) -[2023-10-10 22:25:40,556][97672] Avg episode reward: [(0, '-0.980'), (1, '22.080')] -[2023-10-10 22:25:40,557][98560] Updated weights for policy 1, policy_version 41662 (0.0009) -[2023-10-10 22:25:41,081][98559] Updated weights for policy 0, policy_version 41830 (0.0009) -[2023-10-10 22:25:41,451][98559] Updated weights for policy 0, policy_version 41840 (0.0007) -[2023-10-10 22:25:41,820][98559] Updated weights for policy 0, policy_version 41850 (0.0007) -[2023-10-10 22:25:44,576][98560] Updated weights for policy 1, policy_version 41672 (0.0009) -[2023-10-10 22:25:44,947][98560] Updated weights for policy 1, policy_version 41682 (0.0009) -[2023-10-10 22:25:45,327][98560] Updated weights for policy 1, policy_version 41692 (0.0008) -[2023-10-10 22:25:45,556][97672] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 85557248. Throughput: 0: 1718.4, 1: 1699.8. Samples: 21395470. Policy #0 lag: (min: 25.0, avg: 30.1, max: 57.0) -[2023-10-10 22:25:45,556][97672] Avg episode reward: [(0, '-0.960'), (1, '22.100')] -[2023-10-10 22:25:45,996][98559] Updated weights for policy 0, policy_version 41860 (0.0008) -[2023-10-10 22:25:46,363][98559] Updated weights for policy 0, policy_version 41870 (0.0007) -[2023-10-10 22:25:46,730][98559] Updated weights for policy 0, policy_version 41880 (0.0007) -[2023-10-10 22:25:49,251][98560] Updated weights for policy 1, policy_version 41702 (0.0008) -[2023-10-10 22:25:49,627][98560] Updated weights for policy 1, policy_version 41712 (0.0009) -[2023-10-10 22:25:49,993][98560] Updated weights for policy 1, policy_version 41722 (0.0009) -[2023-10-10 22:25:50,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 85622784. Throughput: 0: 1720.5, 1: 1683.2. Samples: 21416014. Policy #0 lag: (min: 25.0, avg: 30.1, max: 57.0) -[2023-10-10 22:25:50,556][97672] Avg episode reward: [(0, '-0.940'), (1, '22.120')] -[2023-10-10 22:25:50,654][98559] Updated weights for policy 0, policy_version 41890 (0.0009) -[2023-10-10 22:25:51,012][98559] Updated weights for policy 0, policy_version 41900 (0.0009) -[2023-10-10 22:25:51,381][98559] Updated weights for policy 0, policy_version 41910 (0.0007) -[2023-10-10 22:25:51,749][98559] Updated weights for policy 0, policy_version 41920 (0.0007) -[2023-10-10 22:25:53,883][98560] Updated weights for policy 1, policy_version 41732 (0.0009) -[2023-10-10 22:25:54,251][98560] Updated weights for policy 1, policy_version 41742 (0.0007) -[2023-10-10 22:25:54,623][98560] Updated weights for policy 1, policy_version 41752 (0.0009) -[2023-10-10 22:25:55,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 85688320. Throughput: 0: 1711.7, 1: 1703.1. Samples: 21426208. Policy #0 lag: (min: 25.0, avg: 30.1, max: 57.0) -[2023-10-10 22:25:55,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.140')] -[2023-10-10 22:25:55,572][98559] Updated weights for policy 0, policy_version 41930 (0.0009) -[2023-10-10 22:25:55,953][98559] Updated weights for policy 0, policy_version 41940 (0.0009) -[2023-10-10 22:25:56,321][98559] Updated weights for policy 0, policy_version 41950 (0.0009) -[2023-10-10 22:25:58,693][98560] Updated weights for policy 1, policy_version 41762 (0.0007) -[2023-10-10 22:25:59,068][98560] Updated weights for policy 1, policy_version 41772 (0.0008) -[2023-10-10 22:25:59,437][98560] Updated weights for policy 1, policy_version 41782 (0.0008) -[2023-10-10 22:25:59,809][98560] Updated weights for policy 1, policy_version 41792 (0.0009) -[2023-10-10 22:26:00,162][98559] Updated weights for policy 0, policy_version 41960 (0.0009) -[2023-10-10 22:26:00,526][98559] Updated weights for policy 0, policy_version 41970 (0.0008) -[2023-10-10 22:26:00,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 85753856. Throughput: 0: 1722.1, 1: 1697.4. Samples: 21447222. Policy #0 lag: (min: 9.0, avg: 21.3, max: 41.0) -[2023-10-10 22:26:00,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.180')] -[2023-10-10 22:26:00,898][98559] Updated weights for policy 0, policy_version 41980 (0.0007) -[2023-10-10 22:26:03,951][98560] Updated weights for policy 1, policy_version 41802 (0.0011) -[2023-10-10 22:26:04,310][98560] Updated weights for policy 1, policy_version 41812 (0.0011) -[2023-10-10 22:26:04,674][98560] Updated weights for policy 1, policy_version 41822 (0.0010) -[2023-10-10 22:26:05,051][98559] Updated weights for policy 0, policy_version 41990 (0.0010) -[2023-10-10 22:26:05,441][98559] Updated weights for policy 0, policy_version 42000 (0.0008) -[2023-10-10 22:26:05,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 85819392. Throughput: 0: 1715.5, 1: 1671.8. Samples: 21466628. Policy #0 lag: (min: 9.0, avg: 21.3, max: 41.0) -[2023-10-10 22:26:05,556][97672] Avg episode reward: [(0, '-0.940'), (1, '22.240')] -[2023-10-10 22:26:05,812][98559] Updated weights for policy 0, policy_version 42010 (0.0008) -[2023-10-10 22:26:08,892][98560] Updated weights for policy 1, policy_version 41832 (0.0009) -[2023-10-10 22:26:09,246][98560] Updated weights for policy 1, policy_version 41842 (0.0008) -[2023-10-10 22:26:09,610][98560] Updated weights for policy 1, policy_version 41852 (0.0009) -[2023-10-10 22:26:09,676][98559] Updated weights for policy 0, policy_version 42020 (0.0008) -[2023-10-10 22:26:10,030][98559] Updated weights for policy 0, policy_version 42030 (0.0009) -[2023-10-10 22:26:10,407][98559] Updated weights for policy 0, policy_version 42040 (0.0009) -[2023-10-10 22:26:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 85884928. Throughput: 0: 1731.5, 1: 1692.3. Samples: 21477618. Policy #0 lag: (min: 9.0, avg: 21.3, max: 41.0) -[2023-10-10 22:26:10,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.260')] -[2023-10-10 22:26:13,678][98560] Updated weights for policy 1, policy_version 41862 (0.0009) -[2023-10-10 22:26:14,041][98560] Updated weights for policy 1, policy_version 41872 (0.0010) -[2023-10-10 22:26:14,407][98560] Updated weights for policy 1, policy_version 41882 (0.0009) -[2023-10-10 22:26:14,414][98559] Updated weights for policy 0, policy_version 42050 (0.0007) -[2023-10-10 22:26:14,780][98559] Updated weights for policy 0, policy_version 42060 (0.0009) -[2023-10-10 22:26:15,152][98559] Updated weights for policy 0, policy_version 42070 (0.0009) -[2023-10-10 22:26:15,523][98559] Updated weights for policy 0, policy_version 42080 (0.0009) -[2023-10-10 22:26:15,556][97672] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 85983232. Throughput: 0: 1726.5, 1: 1682.6. Samples: 21498026. Policy #0 lag: (min: 9.0, avg: 21.3, max: 41.0) -[2023-10-10 22:26:15,556][97672] Avg episode reward: [(0, '-0.940'), (1, '22.180')] -[2023-10-10 22:26:18,486][98560] Updated weights for policy 1, policy_version 41892 (0.0008) -[2023-10-10 22:26:18,847][98560] Updated weights for policy 1, policy_version 41902 (0.0008) -[2023-10-10 22:26:19,206][98560] Updated weights for policy 1, policy_version 41912 (0.0007) -[2023-10-10 22:26:19,463][98559] Updated weights for policy 0, policy_version 42090 (0.0009) -[2023-10-10 22:26:19,820][98559] Updated weights for policy 0, policy_version 42100 (0.0009) -[2023-10-10 22:26:20,197][98559] Updated weights for policy 0, policy_version 42110 (0.0010) -[2023-10-10 22:26:20,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 86048768. Throughput: 0: 1701.0, 1: 1659.2. Samples: 21516718. Policy #0 lag: (min: 9.0, avg: 21.3, max: 41.0) -[2023-10-10 22:26:20,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.300')] -[2023-10-10 22:26:23,249][98560] Updated weights for policy 1, policy_version 41922 (0.0010) -[2023-10-10 22:26:23,648][98560] Updated weights for policy 1, policy_version 41932 (0.0011) -[2023-10-10 22:26:24,017][98560] Updated weights for policy 1, policy_version 41942 (0.0007) -[2023-10-10 22:26:24,170][98559] Updated weights for policy 0, policy_version 42120 (0.0008) -[2023-10-10 22:26:24,384][98560] Updated weights for policy 1, policy_version 41952 (0.0008) -[2023-10-10 22:26:24,529][98559] Updated weights for policy 0, policy_version 42130 (0.0010) -[2023-10-10 22:26:24,892][98559] Updated weights for policy 0, policy_version 42140 (0.0010) -[2023-10-10 22:26:25,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 86114304. Throughput: 0: 1729.6, 1: 1691.5. Samples: 21528614. Policy #0 lag: (min: 16.0, avg: 41.8, max: 48.0) -[2023-10-10 22:26:25,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.380')] -[2023-10-10 22:26:28,463][98560] Updated weights for policy 1, policy_version 41962 (0.0007) -[2023-10-10 22:26:28,835][98560] Updated weights for policy 1, policy_version 41972 (0.0008) -[2023-10-10 22:26:28,981][98559] Updated weights for policy 0, policy_version 42150 (0.0009) -[2023-10-10 22:26:29,199][98560] Updated weights for policy 1, policy_version 41982 (0.0007) -[2023-10-10 22:26:29,339][98559] Updated weights for policy 0, policy_version 42160 (0.0009) -[2023-10-10 22:26:29,702][98559] Updated weights for policy 0, policy_version 42170 (0.0008) -[2023-10-10 22:26:30,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 86179840. Throughput: 0: 1712.7, 1: 1675.0. Samples: 21547916. Policy #0 lag: (min: 16.0, avg: 41.8, max: 48.0) -[2023-10-10 22:26:30,556][97672] Avg episode reward: [(0, '-0.940'), (1, '22.440')] -[2023-10-10 22:26:33,416][98560] Updated weights for policy 1, policy_version 41992 (0.0007) -[2023-10-10 22:26:33,777][98560] Updated weights for policy 1, policy_version 42002 (0.0007) -[2023-10-10 22:26:33,837][98559] Updated weights for policy 0, policy_version 42180 (0.0007) -[2023-10-10 22:26:34,148][98560] Updated weights for policy 1, policy_version 42012 (0.0008) -[2023-10-10 22:26:34,198][98559] Updated weights for policy 0, policy_version 42190 (0.0009) -[2023-10-10 22:26:34,570][98559] Updated weights for policy 0, policy_version 42200 (0.0008) -[2023-10-10 22:26:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 86245376. Throughput: 0: 1693.6, 1: 1668.9. Samples: 21567328. Policy #0 lag: (min: 16.0, avg: 41.8, max: 48.0) -[2023-10-10 22:26:35,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.500')] -[2023-10-10 22:26:35,568][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000042208_43220992.pth... -[2023-10-10 22:26:35,568][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000042016_43024384.pth... -[2023-10-10 22:26:35,598][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000040416_41385984.pth -[2023-10-10 22:26:35,608][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000040608_41582592.pth -[2023-10-10 22:26:38,198][98560] Updated weights for policy 1, policy_version 42022 (0.0009) -[2023-10-10 22:26:38,498][98559] Updated weights for policy 0, policy_version 42210 (0.0007) -[2023-10-10 22:26:38,563][98560] Updated weights for policy 1, policy_version 42032 (0.0007) -[2023-10-10 22:26:38,869][98559] Updated weights for policy 0, policy_version 42220 (0.0007) -[2023-10-10 22:26:38,926][98560] Updated weights for policy 1, policy_version 42042 (0.0007) -[2023-10-10 22:26:39,226][98559] Updated weights for policy 0, policy_version 42230 (0.0007) -[2023-10-10 22:26:39,599][98559] Updated weights for policy 0, policy_version 42240 (0.0007) -[2023-10-10 22:26:40,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 86310912. Throughput: 0: 1725.8, 1: 1677.3. Samples: 21579350. Policy #0 lag: (min: 16.0, avg: 41.8, max: 48.0) -[2023-10-10 22:26:40,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.460')] -[2023-10-10 22:26:43,045][98560] Updated weights for policy 1, policy_version 42052 (0.0007) -[2023-10-10 22:26:43,415][98560] Updated weights for policy 1, policy_version 42062 (0.0007) -[2023-10-10 22:26:43,467][98559] Updated weights for policy 0, policy_version 42250 (0.0008) -[2023-10-10 22:26:43,786][98560] Updated weights for policy 1, policy_version 42072 (0.0007) -[2023-10-10 22:26:43,839][98559] Updated weights for policy 0, policy_version 42260 (0.0010) -[2023-10-10 22:26:44,202][98559] Updated weights for policy 0, policy_version 42270 (0.0007) -[2023-10-10 22:26:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 86376448. Throughput: 0: 1694.7, 1: 1660.3. Samples: 21598194. Policy #0 lag: (min: 16.0, avg: 41.8, max: 48.0) -[2023-10-10 22:26:45,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.480')] -[2023-10-10 22:26:47,813][98560] Updated weights for policy 1, policy_version 42082 (0.0009) -[2023-10-10 22:26:48,169][98560] Updated weights for policy 1, policy_version 42092 (0.0009) -[2023-10-10 22:26:48,390][98559] Updated weights for policy 0, policy_version 42280 (0.0010) -[2023-10-10 22:26:48,539][98560] Updated weights for policy 1, policy_version 42102 (0.0007) -[2023-10-10 22:26:48,750][98559] Updated weights for policy 0, policy_version 42290 (0.0008) -[2023-10-10 22:26:48,899][98560] Updated weights for policy 1, policy_version 42112 (0.0008) -[2023-10-10 22:26:49,115][98559] Updated weights for policy 0, policy_version 42300 (0.0008) -[2023-10-10 22:26:50,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 86441984. Throughput: 0: 1702.0, 1: 1679.4. Samples: 21618790. Policy #0 lag: (min: 16.0, avg: 41.8, max: 48.0) -[2023-10-10 22:26:50,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.480')] -[2023-10-10 22:26:52,875][98560] Updated weights for policy 1, policy_version 42122 (0.0009) -[2023-10-10 22:26:53,006][98559] Updated weights for policy 0, policy_version 42310 (0.0007) -[2023-10-10 22:26:53,238][98560] Updated weights for policy 1, policy_version 42132 (0.0010) -[2023-10-10 22:26:53,386][98559] Updated weights for policy 0, policy_version 42320 (0.0009) -[2023-10-10 22:26:53,608][98560] Updated weights for policy 1, policy_version 42142 (0.0010) -[2023-10-10 22:26:53,747][98559] Updated weights for policy 0, policy_version 42330 (0.0010) -[2023-10-10 22:26:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 86507520. Throughput: 0: 1701.6, 1: 1679.8. Samples: 21629780. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-10 22:26:55,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.440')] -[2023-10-10 22:26:57,595][98559] Updated weights for policy 0, policy_version 42340 (0.0008) -[2023-10-10 22:26:57,642][98560] Updated weights for policy 1, policy_version 42152 (0.0007) -[2023-10-10 22:26:57,956][98559] Updated weights for policy 0, policy_version 42350 (0.0007) -[2023-10-10 22:26:58,007][98560] Updated weights for policy 1, policy_version 42162 (0.0008) -[2023-10-10 22:26:58,320][98559] Updated weights for policy 0, policy_version 42360 (0.0008) -[2023-10-10 22:26:58,377][98560] Updated weights for policy 1, policy_version 42172 (0.0010) -[2023-10-10 22:27:00,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 86573056. Throughput: 0: 1688.6, 1: 1669.2. Samples: 21649128. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-10 22:27:00,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.420')] -[2023-10-10 22:27:02,342][98559] Updated weights for policy 0, policy_version 42370 (0.0009) -[2023-10-10 22:27:02,449][98560] Updated weights for policy 1, policy_version 42182 (0.0009) -[2023-10-10 22:27:02,704][98559] Updated weights for policy 0, policy_version 42380 (0.0011) -[2023-10-10 22:27:02,822][98560] Updated weights for policy 1, policy_version 42192 (0.0010) -[2023-10-10 22:27:03,076][98559] Updated weights for policy 0, policy_version 42390 (0.0010) -[2023-10-10 22:27:03,184][98560] Updated weights for policy 1, policy_version 42202 (0.0008) -[2023-10-10 22:27:03,437][98559] Updated weights for policy 0, policy_version 42400 (0.0008) -[2023-10-10 22:27:05,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 86638592. Throughput: 0: 1709.5, 1: 1694.8. Samples: 21669910. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-10 22:27:05,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.520')] -[2023-10-10 22:27:07,267][98560] Updated weights for policy 1, policy_version 42212 (0.0009) -[2023-10-10 22:27:07,576][98559] Updated weights for policy 0, policy_version 42410 (0.0007) -[2023-10-10 22:27:07,628][98560] Updated weights for policy 1, policy_version 42222 (0.0009) -[2023-10-10 22:27:07,940][98559] Updated weights for policy 0, policy_version 42420 (0.0009) -[2023-10-10 22:27:07,999][98560] Updated weights for policy 1, policy_version 42232 (0.0008) -[2023-10-10 22:27:08,299][98559] Updated weights for policy 0, policy_version 42430 (0.0008) -[2023-10-10 22:27:10,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 86704128. Throughput: 0: 1684.3, 1: 1676.7. Samples: 21679860. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-10 22:27:10,558][97672] Avg episode reward: [(0, '-0.940'), (1, '22.500')] -[2023-10-10 22:27:11,936][98560] Updated weights for policy 1, policy_version 42242 (0.0009) -[2023-10-10 22:27:12,285][98559] Updated weights for policy 0, policy_version 42440 (0.0008) -[2023-10-10 22:27:12,304][98560] Updated weights for policy 1, policy_version 42252 (0.0007) -[2023-10-10 22:27:12,657][98559] Updated weights for policy 0, policy_version 42450 (0.0009) -[2023-10-10 22:27:12,672][98560] Updated weights for policy 1, policy_version 42262 (0.0007) -[2023-10-10 22:27:13,014][98559] Updated weights for policy 0, policy_version 42460 (0.0009) -[2023-10-10 22:27:13,038][98560] Updated weights for policy 1, policy_version 42272 (0.0007) -[2023-10-10 22:27:15,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.1, 300 sec: 13662.6). Total num frames: 86769664. Throughput: 0: 1700.2, 1: 1683.0. Samples: 21700162. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-10 22:27:15,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.440')] -[2023-10-10 22:27:16,887][98559] Updated weights for policy 0, policy_version 42470 (0.0007) -[2023-10-10 22:27:17,244][98560] Updated weights for policy 1, policy_version 42282 (0.0007) -[2023-10-10 22:27:17,249][98559] Updated weights for policy 0, policy_version 42480 (0.0007) -[2023-10-10 22:27:17,619][98559] Updated weights for policy 0, policy_version 42490 (0.0008) -[2023-10-10 22:27:17,621][98560] Updated weights for policy 1, policy_version 42292 (0.0009) -[2023-10-10 22:27:17,988][98560] Updated weights for policy 1, policy_version 42302 (0.0008) -[2023-10-10 22:27:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.1, 300 sec: 13662.6). Total num frames: 86835200. Throughput: 0: 1721.5, 1: 1698.4. Samples: 21721226. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-10 22:27:20,558][97672] Avg episode reward: [(0, '-0.920'), (1, '22.360')] -[2023-10-10 22:27:21,550][98559] Updated weights for policy 0, policy_version 42500 (0.0009) -[2023-10-10 22:27:21,916][98559] Updated weights for policy 0, policy_version 42510 (0.0008) -[2023-10-10 22:27:21,931][98560] Updated weights for policy 1, policy_version 42312 (0.0010) -[2023-10-10 22:27:22,282][98559] Updated weights for policy 0, policy_version 42520 (0.0007) -[2023-10-10 22:27:22,303][98560] Updated weights for policy 1, policy_version 42322 (0.0010) -[2023-10-10 22:27:22,666][98560] Updated weights for policy 1, policy_version 42332 (0.0009) -[2023-10-10 22:27:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 86900736. Throughput: 0: 1686.4, 1: 1676.2. Samples: 21730670. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 22:27:25,557][97672] Avg episode reward: [(0, '-0.920'), (1, '22.320')] -[2023-10-10 22:27:26,335][98559] Updated weights for policy 0, policy_version 42530 (0.0009) -[2023-10-10 22:27:26,705][98559] Updated weights for policy 0, policy_version 42540 (0.0007) -[2023-10-10 22:27:26,832][98560] Updated weights for policy 1, policy_version 42342 (0.0009) -[2023-10-10 22:27:27,071][98559] Updated weights for policy 0, policy_version 42550 (0.0008) -[2023-10-10 22:27:27,201][98560] Updated weights for policy 1, policy_version 42352 (0.0007) -[2023-10-10 22:27:27,436][98559] Updated weights for policy 0, policy_version 42560 (0.0008) -[2023-10-10 22:27:27,568][98560] Updated weights for policy 1, policy_version 42362 (0.0008) -[2023-10-10 22:27:30,556][97672] Fps is (10 sec: 13107.8, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 86966272. Throughput: 0: 1715.9, 1: 1689.7. Samples: 21751442. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 22:27:30,556][97672] Avg episode reward: [(0, '-0.900'), (1, '22.320')] -[2023-10-10 22:27:31,527][98560] Updated weights for policy 1, policy_version 42372 (0.0009) -[2023-10-10 22:27:31,559][98559] Updated weights for policy 0, policy_version 42570 (0.0009) -[2023-10-10 22:27:31,887][98560] Updated weights for policy 1, policy_version 42382 (0.0008) -[2023-10-10 22:27:31,927][98559] Updated weights for policy 0, policy_version 42580 (0.0009) -[2023-10-10 22:27:32,248][98560] Updated weights for policy 1, policy_version 42392 (0.0008) -[2023-10-10 22:27:32,298][98559] Updated weights for policy 0, policy_version 42590 (0.0009) -[2023-10-10 22:27:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 87031808. Throughput: 0: 1720.3, 1: 1692.0. Samples: 21772342. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 22:27:35,557][97672] Avg episode reward: [(0, '-0.900'), (1, '22.220')] -[2023-10-10 22:27:36,093][98559] Updated weights for policy 0, policy_version 42600 (0.0007) -[2023-10-10 22:27:36,368][98560] Updated weights for policy 1, policy_version 42402 (0.0009) -[2023-10-10 22:27:36,466][98559] Updated weights for policy 0, policy_version 42610 (0.0007) -[2023-10-10 22:27:36,730][98560] Updated weights for policy 1, policy_version 42412 (0.0009) -[2023-10-10 22:27:36,834][98559] Updated weights for policy 0, policy_version 42620 (0.0009) -[2023-10-10 22:27:37,093][98560] Updated weights for policy 1, policy_version 42422 (0.0008) -[2023-10-10 22:27:37,461][98560] Updated weights for policy 1, policy_version 42432 (0.0009) -[2023-10-10 22:27:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 87097344. Throughput: 0: 1705.5, 1: 1669.5. Samples: 21781654. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 22:27:40,556][97672] Avg episode reward: [(0, '-0.900'), (1, '22.160')] -[2023-10-10 22:27:40,922][98559] Updated weights for policy 0, policy_version 42630 (0.0009) -[2023-10-10 22:27:41,299][98559] Updated weights for policy 0, policy_version 42640 (0.0009) -[2023-10-10 22:27:41,345][98560] Updated weights for policy 1, policy_version 42442 (0.0010) -[2023-10-10 22:27:41,662][98559] Updated weights for policy 0, policy_version 42650 (0.0009) -[2023-10-10 22:27:41,722][98560] Updated weights for policy 1, policy_version 42452 (0.0007) -[2023-10-10 22:27:42,090][98560] Updated weights for policy 1, policy_version 42462 (0.0008) -[2023-10-10 22:27:45,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 87162880. Throughput: 0: 1716.0, 1: 1696.2. Samples: 21802680. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 22:27:45,556][97672] Avg episode reward: [(0, '-0.920'), (1, '22.140')] -[2023-10-10 22:27:45,707][98559] Updated weights for policy 0, policy_version 42660 (0.0010) -[2023-10-10 22:27:46,071][98559] Updated weights for policy 0, policy_version 42670 (0.0010) -[2023-10-10 22:27:46,146][98560] Updated weights for policy 1, policy_version 42472 (0.0008) -[2023-10-10 22:27:46,440][98559] Updated weights for policy 0, policy_version 42680 (0.0008) -[2023-10-10 22:27:46,505][98560] Updated weights for policy 1, policy_version 42482 (0.0009) -[2023-10-10 22:27:46,874][98560] Updated weights for policy 1, policy_version 42492 (0.0009) -[2023-10-10 22:27:50,334][98559] Updated weights for policy 0, policy_version 42690 (0.0010) -[2023-10-10 22:27:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 87228416. Throughput: 0: 1717.8, 1: 1699.5. Samples: 21823686. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 22:27:50,556][97672] Avg episode reward: [(0, '-0.900'), (1, '22.120')] -[2023-10-10 22:27:50,707][98559] Updated weights for policy 0, policy_version 42700 (0.0009) -[2023-10-10 22:27:50,852][98560] Updated weights for policy 1, policy_version 42502 (0.0009) -[2023-10-10 22:27:51,074][98559] Updated weights for policy 0, policy_version 42710 (0.0009) -[2023-10-10 22:27:51,226][98560] Updated weights for policy 1, policy_version 42512 (0.0009) -[2023-10-10 22:27:51,448][98559] Updated weights for policy 0, policy_version 42720 (0.0007) -[2023-10-10 22:27:51,596][98560] Updated weights for policy 1, policy_version 42522 (0.0008) -[2023-10-10 22:27:55,383][98559] Updated weights for policy 0, policy_version 42730 (0.0008) -[2023-10-10 22:27:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 87293952. Throughput: 0: 1719.6, 1: 1687.7. Samples: 21833190. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:27:55,556][97672] Avg episode reward: [(0, '-0.900'), (1, '22.040')] -[2023-10-10 22:27:55,691][98560] Updated weights for policy 1, policy_version 42532 (0.0008) -[2023-10-10 22:27:55,748][98559] Updated weights for policy 0, policy_version 42740 (0.0007) -[2023-10-10 22:27:56,050][98560] Updated weights for policy 1, policy_version 42542 (0.0007) -[2023-10-10 22:27:56,112][98559] Updated weights for policy 0, policy_version 42750 (0.0007) -[2023-10-10 22:27:56,418][98560] Updated weights for policy 1, policy_version 42552 (0.0009) -[2023-10-10 22:28:00,056][98559] Updated weights for policy 0, policy_version 42760 (0.0008) -[2023-10-10 22:28:00,421][98559] Updated weights for policy 0, policy_version 42770 (0.0009) -[2023-10-10 22:28:00,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 87359488. Throughput: 0: 1729.0, 1: 1694.1. Samples: 21854204. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:28:00,557][97672] Avg episode reward: [(0, '-0.900'), (1, '22.000')] -[2023-10-10 22:28:00,598][98560] Updated weights for policy 1, policy_version 42562 (0.0009) -[2023-10-10 22:28:00,791][98559] Updated weights for policy 0, policy_version 42780 (0.0008) -[2023-10-10 22:28:00,973][98560] Updated weights for policy 1, policy_version 42572 (0.0008) -[2023-10-10 22:28:01,335][98560] Updated weights for policy 1, policy_version 42582 (0.0010) -[2023-10-10 22:28:01,700][98560] Updated weights for policy 1, policy_version 42592 (0.0010) -[2023-10-10 22:28:04,677][98559] Updated weights for policy 0, policy_version 42790 (0.0009) -[2023-10-10 22:28:05,042][98559] Updated weights for policy 0, policy_version 42800 (0.0009) -[2023-10-10 22:28:05,408][98559] Updated weights for policy 0, policy_version 42810 (0.0007) -[2023-10-10 22:28:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 87425024. Throughput: 0: 1703.3, 1: 1697.3. Samples: 21874252. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:28:05,556][97672] Avg episode reward: [(0, '-0.900'), (1, '22.000')] -[2023-10-10 22:28:05,827][98560] Updated weights for policy 1, policy_version 42602 (0.0008) -[2023-10-10 22:28:06,193][98560] Updated weights for policy 1, policy_version 42612 (0.0010) -[2023-10-10 22:28:06,559][98560] Updated weights for policy 1, policy_version 42622 (0.0007) -[2023-10-10 22:28:09,347][98559] Updated weights for policy 0, policy_version 42820 (0.0008) -[2023-10-10 22:28:09,715][98559] Updated weights for policy 0, policy_version 42830 (0.0010) -[2023-10-10 22:28:10,086][98559] Updated weights for policy 0, policy_version 42840 (0.0010) -[2023-10-10 22:28:10,537][98560] Updated weights for policy 1, policy_version 42632 (0.0007) -[2023-10-10 22:28:10,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 87523328. Throughput: 0: 1726.8, 1: 1688.1. Samples: 21884340. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:28:10,557][97672] Avg episode reward: [(0, '-0.900'), (1, '21.920')] -[2023-10-10 22:28:10,905][98560] Updated weights for policy 1, policy_version 42642 (0.0009) -[2023-10-10 22:28:11,270][98560] Updated weights for policy 1, policy_version 42652 (0.0008) -[2023-10-10 22:28:14,127][98559] Updated weights for policy 0, policy_version 42850 (0.0009) -[2023-10-10 22:28:14,502][98559] Updated weights for policy 0, policy_version 42860 (0.0009) -[2023-10-10 22:28:14,859][98559] Updated weights for policy 0, policy_version 42870 (0.0010) -[2023-10-10 22:28:15,228][98559] Updated weights for policy 0, policy_version 42880 (0.0010) -[2023-10-10 22:28:15,322][98560] Updated weights for policy 1, policy_version 42662 (0.0009) -[2023-10-10 22:28:15,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 87588864. Throughput: 0: 1716.7, 1: 1696.4. Samples: 21905030. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:28:15,556][97672] Avg episode reward: [(0, '-0.900'), (1, '21.940')] -[2023-10-10 22:28:15,684][98560] Updated weights for policy 1, policy_version 42672 (0.0009) -[2023-10-10 22:28:16,049][98560] Updated weights for policy 1, policy_version 42682 (0.0008) -[2023-10-10 22:28:19,067][98559] Updated weights for policy 0, policy_version 42890 (0.0007) -[2023-10-10 22:28:19,433][98559] Updated weights for policy 0, policy_version 42900 (0.0007) -[2023-10-10 22:28:19,803][98559] Updated weights for policy 0, policy_version 42910 (0.0008) -[2023-10-10 22:28:20,098][98560] Updated weights for policy 1, policy_version 42692 (0.0007) -[2023-10-10 22:28:20,454][98560] Updated weights for policy 1, policy_version 42702 (0.0007) -[2023-10-10 22:28:20,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 87654400. Throughput: 0: 1697.1, 1: 1702.4. Samples: 21925320. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:28:20,557][97672] Avg episode reward: [(0, '-0.860'), (1, '21.980')] -[2023-10-10 22:28:20,567][98385] Saving new best policy, reward=-0.860! -[2023-10-10 22:28:20,826][98560] Updated weights for policy 1, policy_version 42712 (0.0008) -[2023-10-10 22:28:23,849][98559] Updated weights for policy 0, policy_version 42920 (0.0010) -[2023-10-10 22:28:24,219][98559] Updated weights for policy 0, policy_version 42930 (0.0011) -[2023-10-10 22:28:24,596][98559] Updated weights for policy 0, policy_version 42940 (0.0011) -[2023-10-10 22:28:24,788][98560] Updated weights for policy 1, policy_version 42722 (0.0007) -[2023-10-10 22:28:25,153][98560] Updated weights for policy 1, policy_version 42732 (0.0009) -[2023-10-10 22:28:25,524][98560] Updated weights for policy 1, policy_version 42742 (0.0007) -[2023-10-10 22:28:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 87719936. Throughput: 0: 1726.3, 1: 1700.4. Samples: 21935858. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:28:25,556][97672] Avg episode reward: [(0, '-0.860'), (1, '22.000')] -[2023-10-10 22:28:25,887][98560] Updated weights for policy 1, policy_version 42752 (0.0007) -[2023-10-10 22:28:28,626][98559] Updated weights for policy 0, policy_version 42950 (0.0007) -[2023-10-10 22:28:29,002][98559] Updated weights for policy 0, policy_version 42960 (0.0008) -[2023-10-10 22:28:29,362][98559] Updated weights for policy 0, policy_version 42970 (0.0011) -[2023-10-10 22:28:29,839][98560] Updated weights for policy 1, policy_version 42762 (0.0008) -[2023-10-10 22:28:30,207][98560] Updated weights for policy 1, policy_version 42772 (0.0009) -[2023-10-10 22:28:30,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 87785472. Throughput: 0: 1704.5, 1: 1695.5. Samples: 21955682. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:28:30,557][97672] Avg episode reward: [(0, '-0.860'), (1, '22.040')] -[2023-10-10 22:28:30,571][98560] Updated weights for policy 1, policy_version 42782 (0.0008) -[2023-10-10 22:28:33,442][98559] Updated weights for policy 0, policy_version 42980 (0.0009) -[2023-10-10 22:28:33,806][98559] Updated weights for policy 0, policy_version 42990 (0.0009) -[2023-10-10 22:28:34,174][98559] Updated weights for policy 0, policy_version 43000 (0.0009) -[2023-10-10 22:28:34,533][98560] Updated weights for policy 1, policy_version 42792 (0.0009) -[2023-10-10 22:28:34,901][98560] Updated weights for policy 1, policy_version 42802 (0.0009) -[2023-10-10 22:28:35,270][98560] Updated weights for policy 1, policy_version 42812 (0.0007) -[2023-10-10 22:28:35,556][97672] Fps is (10 sec: 16383.4, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 87883776. Throughput: 0: 1700.9, 1: 1684.6. Samples: 21976034. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:28:35,557][97672] Avg episode reward: [(0, '-0.860'), (1, '22.040')] -[2023-10-10 22:28:35,571][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000042816_43843584.pth... -[2023-10-10 22:28:35,571][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000043008_44040192.pth... -[2023-10-10 22:28:35,614][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000041216_42205184.pth -[2023-10-10 22:28:35,617][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000041408_42401792.pth -[2023-10-10 22:28:38,205][98559] Updated weights for policy 0, policy_version 43010 (0.0009) -[2023-10-10 22:28:38,569][98559] Updated weights for policy 0, policy_version 43020 (0.0008) -[2023-10-10 22:28:38,942][98559] Updated weights for policy 0, policy_version 43030 (0.0007) -[2023-10-10 22:28:39,309][98559] Updated weights for policy 0, policy_version 43040 (0.0010) -[2023-10-10 22:28:39,383][98560] Updated weights for policy 1, policy_version 42822 (0.0008) -[2023-10-10 22:28:39,748][98560] Updated weights for policy 1, policy_version 42832 (0.0010) -[2023-10-10 22:28:40,122][98560] Updated weights for policy 1, policy_version 42842 (0.0009) -[2023-10-10 22:28:40,556][97672] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 87949312. Throughput: 0: 1717.0, 1: 1692.2. Samples: 21986604. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:28:40,557][97672] Avg episode reward: [(0, '-0.860'), (1, '22.040')] -[2023-10-10 22:28:43,324][98559] Updated weights for policy 0, policy_version 43050 (0.0009) -[2023-10-10 22:28:43,694][98559] Updated weights for policy 0, policy_version 43060 (0.0010) -[2023-10-10 22:28:44,063][98559] Updated weights for policy 0, policy_version 43070 (0.0009) -[2023-10-10 22:28:44,184][98560] Updated weights for policy 1, policy_version 42852 (0.0010) -[2023-10-10 22:28:44,552][98560] Updated weights for policy 1, policy_version 42862 (0.0011) -[2023-10-10 22:28:44,914][98560] Updated weights for policy 1, policy_version 42872 (0.0010) -[2023-10-10 22:28:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 88014848. Throughput: 0: 1689.8, 1: 1696.9. Samples: 22006604. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:28:45,557][97672] Avg episode reward: [(0, '-0.860'), (1, '22.140')] -[2023-10-10 22:28:48,121][98559] Updated weights for policy 0, policy_version 43080 (0.0010) -[2023-10-10 22:28:48,485][98559] Updated weights for policy 0, policy_version 43090 (0.0007) -[2023-10-10 22:28:48,858][98559] Updated weights for policy 0, policy_version 43100 (0.0010) -[2023-10-10 22:28:48,963][98560] Updated weights for policy 1, policy_version 42882 (0.0008) -[2023-10-10 22:28:49,324][98560] Updated weights for policy 1, policy_version 42892 (0.0009) -[2023-10-10 22:28:49,691][98560] Updated weights for policy 1, policy_version 42902 (0.0009) -[2023-10-10 22:28:50,058][98560] Updated weights for policy 1, policy_version 42912 (0.0009) -[2023-10-10 22:28:50,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 88080384. Throughput: 0: 1709.6, 1: 1680.7. Samples: 22026814. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-10 22:28:50,556][97672] Avg episode reward: [(0, '-0.860'), (1, '22.200')] -[2023-10-10 22:28:52,952][98559] Updated weights for policy 0, policy_version 43110 (0.0010) -[2023-10-10 22:28:53,330][98559] Updated weights for policy 0, policy_version 43120 (0.0008) -[2023-10-10 22:28:53,691][98559] Updated weights for policy 0, policy_version 43130 (0.0008) -[2023-10-10 22:28:54,050][98560] Updated weights for policy 1, policy_version 42922 (0.0009) -[2023-10-10 22:28:54,415][98560] Updated weights for policy 1, policy_version 42932 (0.0009) -[2023-10-10 22:28:54,780][98560] Updated weights for policy 1, policy_version 42942 (0.0008) -[2023-10-10 22:28:55,556][97672] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 88145920. Throughput: 0: 1701.3, 1: 1705.0. Samples: 22037624. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-10 22:28:55,557][97672] Avg episode reward: [(0, '-0.860'), (1, '22.240')] -[2023-10-10 22:28:57,732][98559] Updated weights for policy 0, policy_version 43140 (0.0007) -[2023-10-10 22:28:58,094][98559] Updated weights for policy 0, policy_version 43150 (0.0007) -[2023-10-10 22:28:58,473][98559] Updated weights for policy 0, policy_version 43160 (0.0008) -[2023-10-10 22:28:58,688][98560] Updated weights for policy 1, policy_version 42952 (0.0008) -[2023-10-10 22:28:59,048][98560] Updated weights for policy 1, policy_version 42962 (0.0008) -[2023-10-10 22:28:59,415][98560] Updated weights for policy 1, policy_version 42972 (0.0010) -[2023-10-10 22:29:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 88211456. Throughput: 0: 1696.4, 1: 1699.0. Samples: 22057820. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-10 22:29:00,556][97672] Avg episode reward: [(0, '-0.860'), (1, '22.260')] -[2023-10-10 22:29:02,446][98559] Updated weights for policy 0, policy_version 43170 (0.0008) -[2023-10-10 22:29:02,811][98559] Updated weights for policy 0, policy_version 43180 (0.0008) -[2023-10-10 22:29:03,173][98559] Updated weights for policy 0, policy_version 43190 (0.0008) -[2023-10-10 22:29:03,509][98560] Updated weights for policy 1, policy_version 42982 (0.0011) -[2023-10-10 22:29:03,538][98559] Updated weights for policy 0, policy_version 43200 (0.0007) -[2023-10-10 22:29:03,888][98560] Updated weights for policy 1, policy_version 42992 (0.0009) -[2023-10-10 22:29:04,253][98560] Updated weights for policy 1, policy_version 43002 (0.0010) -[2023-10-10 22:29:05,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 88276992. Throughput: 0: 1711.5, 1: 1676.5. Samples: 22077780. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-10 22:29:05,557][97672] Avg episode reward: [(0, '-0.860'), (1, '22.320')] -[2023-10-10 22:29:07,590][98559] Updated weights for policy 0, policy_version 43210 (0.0008) -[2023-10-10 22:29:07,969][98559] Updated weights for policy 0, policy_version 43220 (0.0008) -[2023-10-10 22:29:08,242][98560] Updated weights for policy 1, policy_version 43012 (0.0008) -[2023-10-10 22:29:08,330][98559] Updated weights for policy 0, policy_version 43230 (0.0008) -[2023-10-10 22:29:08,615][98560] Updated weights for policy 1, policy_version 43022 (0.0009) -[2023-10-10 22:29:08,993][98560] Updated weights for policy 1, policy_version 43032 (0.0009) -[2023-10-10 22:29:10,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 88342528. Throughput: 0: 1684.0, 1: 1707.0. Samples: 22088454. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-10 22:29:10,557][97672] Avg episode reward: [(0, '-0.860'), (1, '22.260')] -[2023-10-10 22:29:12,317][98559] Updated weights for policy 0, policy_version 43240 (0.0008) -[2023-10-10 22:29:12,686][98559] Updated weights for policy 0, policy_version 43250 (0.0007) -[2023-10-10 22:29:13,056][98560] Updated weights for policy 1, policy_version 43042 (0.0009) -[2023-10-10 22:29:13,058][98559] Updated weights for policy 0, policy_version 43260 (0.0008) -[2023-10-10 22:29:13,415][98560] Updated weights for policy 1, policy_version 43052 (0.0007) -[2023-10-10 22:29:13,783][98560] Updated weights for policy 1, policy_version 43062 (0.0007) -[2023-10-10 22:29:14,148][98560] Updated weights for policy 1, policy_version 43072 (0.0009) -[2023-10-10 22:29:15,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 88408064. Throughput: 0: 1712.9, 1: 1685.6. Samples: 22108614. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-10 22:29:15,556][97672] Avg episode reward: [(0, '-0.860'), (1, '22.300')] -[2023-10-10 22:29:17,007][98559] Updated weights for policy 0, policy_version 43270 (0.0009) -[2023-10-10 22:29:17,381][98559] Updated weights for policy 0, policy_version 43280 (0.0009) -[2023-10-10 22:29:17,747][98559] Updated weights for policy 0, policy_version 43290 (0.0007) -[2023-10-10 22:29:18,149][98560] Updated weights for policy 1, policy_version 43082 (0.0009) -[2023-10-10 22:29:18,516][98560] Updated weights for policy 1, policy_version 43092 (0.0010) -[2023-10-10 22:29:18,893][98560] Updated weights for policy 1, policy_version 43102 (0.0008) -[2023-10-10 22:29:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 88473600. Throughput: 0: 1714.5, 1: 1688.0. Samples: 22129150. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:29:20,557][97672] Avg episode reward: [(0, '-0.860'), (1, '22.380')] -[2023-10-10 22:29:21,808][98559] Updated weights for policy 0, policy_version 43300 (0.0008) -[2023-10-10 22:29:22,186][98559] Updated weights for policy 0, policy_version 43310 (0.0007) -[2023-10-10 22:29:22,548][98559] Updated weights for policy 0, policy_version 43320 (0.0007) -[2023-10-10 22:29:22,826][98560] Updated weights for policy 1, policy_version 43112 (0.0008) -[2023-10-10 22:29:23,194][98560] Updated weights for policy 1, policy_version 43122 (0.0007) -[2023-10-10 22:29:23,559][98560] Updated weights for policy 1, policy_version 43132 (0.0010) -[2023-10-10 22:29:25,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 88539136. Throughput: 0: 1692.6, 1: 1704.3. Samples: 22139466. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:29:25,557][97672] Avg episode reward: [(0, '-0.860'), (1, '22.380')] -[2023-10-10 22:29:26,468][98559] Updated weights for policy 0, policy_version 43330 (0.0010) -[2023-10-10 22:29:26,821][98559] Updated weights for policy 0, policy_version 43340 (0.0008) -[2023-10-10 22:29:27,190][98559] Updated weights for policy 0, policy_version 43350 (0.0008) -[2023-10-10 22:29:27,555][98559] Updated weights for policy 0, policy_version 43360 (0.0007) -[2023-10-10 22:29:27,563][98560] Updated weights for policy 1, policy_version 43142 (0.0009) -[2023-10-10 22:29:27,924][98560] Updated weights for policy 1, policy_version 43152 (0.0008) -[2023-10-10 22:29:28,288][98560] Updated weights for policy 1, policy_version 43162 (0.0008) -[2023-10-10 22:29:30,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 88604672. Throughput: 0: 1711.9, 1: 1683.0. Samples: 22159374. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:29:30,558][97672] Avg episode reward: [(0, '-0.860'), (1, '22.220')] -[2023-10-10 22:29:31,591][98559] Updated weights for policy 0, policy_version 43370 (0.0009) -[2023-10-10 22:29:31,954][98559] Updated weights for policy 0, policy_version 43380 (0.0008) -[2023-10-10 22:29:32,172][98560] Updated weights for policy 1, policy_version 43172 (0.0008) -[2023-10-10 22:29:32,325][98559] Updated weights for policy 0, policy_version 43390 (0.0008) -[2023-10-10 22:29:32,535][98560] Updated weights for policy 1, policy_version 43182 (0.0011) -[2023-10-10 22:29:32,909][98560] Updated weights for policy 1, policy_version 43192 (0.0009) -[2023-10-10 22:29:35,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 88670208. Throughput: 0: 1710.4, 1: 1708.9. Samples: 22180680. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:29:35,556][97672] Avg episode reward: [(0, '-0.860'), (1, '22.240')] -[2023-10-10 22:29:36,332][98559] Updated weights for policy 0, policy_version 43400 (0.0010) -[2023-10-10 22:29:36,706][98559] Updated weights for policy 0, policy_version 43410 (0.0008) -[2023-10-10 22:29:36,821][98560] Updated weights for policy 1, policy_version 43202 (0.0008) -[2023-10-10 22:29:37,076][98559] Updated weights for policy 0, policy_version 43420 (0.0007) -[2023-10-10 22:29:37,195][98560] Updated weights for policy 1, policy_version 43212 (0.0009) -[2023-10-10 22:29:37,564][98560] Updated weights for policy 1, policy_version 43222 (0.0009) -[2023-10-10 22:29:37,937][98560] Updated weights for policy 1, policy_version 43232 (0.0009) -[2023-10-10 22:29:40,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 88735744. Throughput: 0: 1697.5, 1: 1694.2. Samples: 22190250. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:29:40,557][97672] Avg episode reward: [(0, '-0.860'), (1, '22.100')] -[2023-10-10 22:29:40,879][98559] Updated weights for policy 0, policy_version 43430 (0.0009) -[2023-10-10 22:29:41,244][98559] Updated weights for policy 0, policy_version 43440 (0.0007) -[2023-10-10 22:29:41,619][98559] Updated weights for policy 0, policy_version 43450 (0.0008) -[2023-10-10 22:29:42,058][98560] Updated weights for policy 1, policy_version 43242 (0.0009) -[2023-10-10 22:29:42,429][98560] Updated weights for policy 1, policy_version 43252 (0.0010) -[2023-10-10 22:29:42,793][98560] Updated weights for policy 1, policy_version 43262 (0.0009) -[2023-10-10 22:29:45,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 88801280. Throughput: 0: 1712.7, 1: 1694.4. Samples: 22211138. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:29:45,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.080')] -[2023-10-10 22:29:45,604][98559] Updated weights for policy 0, policy_version 43460 (0.0009) -[2023-10-10 22:29:45,985][98559] Updated weights for policy 0, policy_version 43470 (0.0011) -[2023-10-10 22:29:46,347][98559] Updated weights for policy 0, policy_version 43480 (0.0008) -[2023-10-10 22:29:46,634][98385] Saving new best policy, reward=-0.800! -[2023-10-10 22:29:46,867][98560] Updated weights for policy 1, policy_version 43272 (0.0010) -[2023-10-10 22:29:47,246][98560] Updated weights for policy 1, policy_version 43282 (0.0010) -[2023-10-10 22:29:47,603][98560] Updated weights for policy 1, policy_version 43292 (0.0010) -[2023-10-10 22:29:50,439][98559] Updated weights for policy 0, policy_version 43490 (0.0008) -[2023-10-10 22:29:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 88866816. Throughput: 0: 1710.8, 1: 1712.4. Samples: 22231826. Policy #0 lag: (min: 4.0, avg: 9.8, max: 36.0) -[2023-10-10 22:29:50,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.100')] -[2023-10-10 22:29:50,800][98559] Updated weights for policy 0, policy_version 43500 (0.0008) -[2023-10-10 22:29:51,171][98559] Updated weights for policy 0, policy_version 43510 (0.0007) -[2023-10-10 22:29:51,456][98560] Updated weights for policy 1, policy_version 43302 (0.0008) -[2023-10-10 22:29:51,533][98559] Updated weights for policy 0, policy_version 43520 (0.0008) -[2023-10-10 22:29:51,832][98560] Updated weights for policy 1, policy_version 43312 (0.0010) -[2023-10-10 22:29:52,198][98560] Updated weights for policy 1, policy_version 43322 (0.0010) -[2023-10-10 22:29:55,512][98559] Updated weights for policy 0, policy_version 43530 (0.0007) -[2023-10-10 22:29:55,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 88932352. Throughput: 0: 1710.0, 1: 1681.8. Samples: 22241084. Policy #0 lag: (min: 4.0, avg: 9.8, max: 36.0) -[2023-10-10 22:29:55,556][97672] Avg episode reward: [(0, '-0.900'), (1, '22.180')] -[2023-10-10 22:29:55,876][98559] Updated weights for policy 0, policy_version 43540 (0.0007) -[2023-10-10 22:29:56,168][98560] Updated weights for policy 1, policy_version 43332 (0.0009) -[2023-10-10 22:29:56,251][98559] Updated weights for policy 0, policy_version 43550 (0.0010) -[2023-10-10 22:29:56,549][98560] Updated weights for policy 1, policy_version 43342 (0.0008) -[2023-10-10 22:29:56,923][98560] Updated weights for policy 1, policy_version 43352 (0.0009) -[2023-10-10 22:30:00,447][98559] Updated weights for policy 0, policy_version 43560 (0.0007) -[2023-10-10 22:30:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 88997888. Throughput: 0: 1705.9, 1: 1699.6. Samples: 22261864. Policy #0 lag: (min: 4.0, avg: 9.8, max: 36.0) -[2023-10-10 22:30:00,557][97672] Avg episode reward: [(0, '-0.900'), (1, '22.200')] -[2023-10-10 22:30:00,809][98559] Updated weights for policy 0, policy_version 43570 (0.0010) -[2023-10-10 22:30:01,039][98560] Updated weights for policy 1, policy_version 43362 (0.0009) -[2023-10-10 22:30:01,175][98559] Updated weights for policy 0, policy_version 43580 (0.0007) -[2023-10-10 22:30:01,406][98560] Updated weights for policy 1, policy_version 43372 (0.0007) -[2023-10-10 22:30:01,770][98560] Updated weights for policy 1, policy_version 43382 (0.0008) -[2023-10-10 22:30:02,135][98560] Updated weights for policy 1, policy_version 43392 (0.0009) -[2023-10-10 22:30:05,179][98559] Updated weights for policy 0, policy_version 43590 (0.0009) -[2023-10-10 22:30:05,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 89063424. Throughput: 0: 1698.4, 1: 1708.0. Samples: 22282440. Policy #0 lag: (min: 4.0, avg: 9.8, max: 36.0) -[2023-10-10 22:30:05,557][97672] Avg episode reward: [(0, '-0.920'), (1, '22.200')] -[2023-10-10 22:30:05,562][98559] Updated weights for policy 0, policy_version 43600 (0.0009) -[2023-10-10 22:30:05,938][98559] Updated weights for policy 0, policy_version 43610 (0.0007) -[2023-10-10 22:30:06,080][98560] Updated weights for policy 1, policy_version 43402 (0.0007) -[2023-10-10 22:30:06,440][98560] Updated weights for policy 1, policy_version 43412 (0.0007) -[2023-10-10 22:30:06,811][98560] Updated weights for policy 1, policy_version 43422 (0.0007) -[2023-10-10 22:30:09,955][98559] Updated weights for policy 0, policy_version 43620 (0.0008) -[2023-10-10 22:30:10,318][98559] Updated weights for policy 0, policy_version 43630 (0.0007) -[2023-10-10 22:30:10,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 89128960. Throughput: 0: 1707.8, 1: 1683.4. Samples: 22292070. Policy #0 lag: (min: 4.0, avg: 9.8, max: 36.0) -[2023-10-10 22:30:10,556][97672] Avg episode reward: [(0, '-0.920'), (1, '22.200')] -[2023-10-10 22:30:10,679][98559] Updated weights for policy 0, policy_version 43640 (0.0009) -[2023-10-10 22:30:11,057][98560] Updated weights for policy 1, policy_version 43432 (0.0009) -[2023-10-10 22:30:11,428][98560] Updated weights for policy 1, policy_version 43442 (0.0011) -[2023-10-10 22:30:11,798][98560] Updated weights for policy 1, policy_version 43452 (0.0010) -[2023-10-10 22:30:14,591][98559] Updated weights for policy 0, policy_version 43650 (0.0009) -[2023-10-10 22:30:14,954][98559] Updated weights for policy 0, policy_version 43660 (0.0010) -[2023-10-10 22:30:15,323][98559] Updated weights for policy 0, policy_version 43670 (0.0008) -[2023-10-10 22:30:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 89194496. Throughput: 0: 1709.3, 1: 1703.4. Samples: 22312944. Policy #0 lag: (min: 4.0, avg: 9.8, max: 36.0) -[2023-10-10 22:30:15,557][97672] Avg episode reward: [(0, '-0.920'), (1, '22.360')] -[2023-10-10 22:30:15,693][98559] Updated weights for policy 0, policy_version 43680 (0.0009) -[2023-10-10 22:30:15,771][98560] Updated weights for policy 1, policy_version 43462 (0.0010) -[2023-10-10 22:30:16,143][98560] Updated weights for policy 1, policy_version 43472 (0.0011) -[2023-10-10 22:30:16,504][98560] Updated weights for policy 1, policy_version 43482 (0.0010) -[2023-10-10 22:30:19,884][98559] Updated weights for policy 0, policy_version 43690 (0.0009) -[2023-10-10 22:30:20,256][98559] Updated weights for policy 0, policy_version 43700 (0.0009) -[2023-10-10 22:30:20,383][98560] Updated weights for policy 1, policy_version 43492 (0.0008) -[2023-10-10 22:30:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 89260032. Throughput: 0: 1685.3, 1: 1696.5. Samples: 22332862. Policy #0 lag: (min: 25.0, avg: 34.7, max: 57.0) -[2023-10-10 22:30:20,556][97672] Avg episode reward: [(0, '-0.920'), (1, '22.380')] -[2023-10-10 22:30:20,631][98559] Updated weights for policy 0, policy_version 43710 (0.0009) -[2023-10-10 22:30:20,751][98560] Updated weights for policy 1, policy_version 43502 (0.0009) -[2023-10-10 22:30:21,120][98560] Updated weights for policy 1, policy_version 43512 (0.0009) -[2023-10-10 22:30:24,703][98559] Updated weights for policy 0, policy_version 43720 (0.0009) -[2023-10-10 22:30:25,072][98559] Updated weights for policy 0, policy_version 43730 (0.0009) -[2023-10-10 22:30:25,275][98560] Updated weights for policy 1, policy_version 43522 (0.0008) -[2023-10-10 22:30:25,441][98559] Updated weights for policy 0, policy_version 43740 (0.0008) -[2023-10-10 22:30:25,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 89325568. Throughput: 0: 1701.3, 1: 1690.6. Samples: 22342886. Policy #0 lag: (min: 25.0, avg: 34.7, max: 57.0) -[2023-10-10 22:30:25,557][97672] Avg episode reward: [(0, '-0.920'), (1, '22.440')] -[2023-10-10 22:30:25,650][98560] Updated weights for policy 1, policy_version 43532 (0.0008) -[2023-10-10 22:30:26,013][98560] Updated weights for policy 1, policy_version 43542 (0.0009) -[2023-10-10 22:30:26,387][98560] Updated weights for policy 1, policy_version 43552 (0.0008) -[2023-10-10 22:30:29,317][98559] Updated weights for policy 0, policy_version 43750 (0.0009) -[2023-10-10 22:30:29,687][98559] Updated weights for policy 0, policy_version 43760 (0.0009) -[2023-10-10 22:30:30,055][98559] Updated weights for policy 0, policy_version 43770 (0.0007) -[2023-10-10 22:30:30,508][98560] Updated weights for policy 1, policy_version 43562 (0.0010) -[2023-10-10 22:30:30,556][97672] Fps is (10 sec: 16383.8, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 89423872. Throughput: 0: 1690.7, 1: 1695.5. Samples: 22363518. Policy #0 lag: (min: 25.0, avg: 34.7, max: 57.0) -[2023-10-10 22:30:30,557][97672] Avg episode reward: [(0, '-0.920'), (1, '22.480')] -[2023-10-10 22:30:30,876][98560] Updated weights for policy 1, policy_version 43572 (0.0008) -[2023-10-10 22:30:31,249][98560] Updated weights for policy 1, policy_version 43582 (0.0008) -[2023-10-10 22:30:33,993][98559] Updated weights for policy 0, policy_version 43780 (0.0008) -[2023-10-10 22:30:34,356][98559] Updated weights for policy 0, policy_version 43790 (0.0010) -[2023-10-10 22:30:34,723][98559] Updated weights for policy 0, policy_version 43800 (0.0011) -[2023-10-10 22:30:35,458][98560] Updated weights for policy 1, policy_version 43592 (0.0011) -[2023-10-10 22:30:35,556][97672] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 89489408. Throughput: 0: 1670.6, 1: 1697.5. Samples: 22383390. Policy #0 lag: (min: 25.0, avg: 34.7, max: 57.0) -[2023-10-10 22:30:35,557][97672] Avg episode reward: [(0, '-0.920'), (1, '22.480')] -[2023-10-10 22:30:35,567][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000043808_44859392.pth... -[2023-10-10 22:30:35,600][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000042208_43220992.pth -[2023-10-10 22:30:35,821][98560] Updated weights for policy 1, policy_version 43602 (0.0009) -[2023-10-10 22:30:36,193][98560] Updated weights for policy 1, policy_version 43612 (0.0008) -[2023-10-10 22:30:36,339][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000043616_44662784.pth... -[2023-10-10 22:30:36,369][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000042016_43024384.pth -[2023-10-10 22:30:38,661][98559] Updated weights for policy 0, policy_version 43810 (0.0008) -[2023-10-10 22:30:39,022][98559] Updated weights for policy 0, policy_version 43820 (0.0007) -[2023-10-10 22:30:39,384][98559] Updated weights for policy 0, policy_version 43830 (0.0009) -[2023-10-10 22:30:39,742][98559] Updated weights for policy 0, policy_version 43840 (0.0009) -[2023-10-10 22:30:40,282][98560] Updated weights for policy 1, policy_version 43622 (0.0009) -[2023-10-10 22:30:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 89554944. Throughput: 0: 1699.3, 1: 1695.8. Samples: 22393866. Policy #0 lag: (min: 25.0, avg: 34.7, max: 57.0) -[2023-10-10 22:30:40,557][97672] Avg episode reward: [(0, '-0.920'), (1, '22.500')] -[2023-10-10 22:30:40,644][98560] Updated weights for policy 1, policy_version 43632 (0.0008) -[2023-10-10 22:30:41,012][98560] Updated weights for policy 1, policy_version 43642 (0.0009) -[2023-10-10 22:30:43,872][98559] Updated weights for policy 0, policy_version 43850 (0.0011) -[2023-10-10 22:30:44,234][98559] Updated weights for policy 0, policy_version 43860 (0.0011) -[2023-10-10 22:30:44,596][98559] Updated weights for policy 0, policy_version 43870 (0.0009) -[2023-10-10 22:30:44,874][98560] Updated weights for policy 1, policy_version 43652 (0.0007) -[2023-10-10 22:30:45,234][98560] Updated weights for policy 1, policy_version 43662 (0.0008) -[2023-10-10 22:30:45,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 89620480. Throughput: 0: 1682.6, 1: 1698.4. Samples: 22414008. Policy #0 lag: (min: 7.0, avg: 7.2, max: 17.0) -[2023-10-10 22:30:45,557][97672] Avg episode reward: [(0, '-0.920'), (1, '22.460')] -[2023-10-10 22:30:45,605][98560] Updated weights for policy 1, policy_version 43672 (0.0009) -[2023-10-10 22:30:48,682][98559] Updated weights for policy 0, policy_version 43880 (0.0010) -[2023-10-10 22:30:49,053][98559] Updated weights for policy 0, policy_version 43890 (0.0011) -[2023-10-10 22:30:49,419][98559] Updated weights for policy 0, policy_version 43900 (0.0012) -[2023-10-10 22:30:49,603][98560] Updated weights for policy 1, policy_version 43682 (0.0007) -[2023-10-10 22:30:49,973][98560] Updated weights for policy 1, policy_version 43692 (0.0009) -[2023-10-10 22:30:50,339][98560] Updated weights for policy 1, policy_version 43702 (0.0008) -[2023-10-10 22:30:50,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 89686016. Throughput: 0: 1684.7, 1: 1698.3. Samples: 22434672. Policy #0 lag: (min: 7.0, avg: 7.2, max: 17.0) -[2023-10-10 22:30:50,557][97672] Avg episode reward: [(0, '-0.920'), (1, '22.420')] -[2023-10-10 22:30:50,706][98560] Updated weights for policy 1, policy_version 43712 (0.0008) -[2023-10-10 22:30:53,525][98559] Updated weights for policy 0, policy_version 43910 (0.0009) -[2023-10-10 22:30:53,909][98559] Updated weights for policy 0, policy_version 43920 (0.0010) -[2023-10-10 22:30:54,292][98559] Updated weights for policy 0, policy_version 43930 (0.0008) -[2023-10-10 22:30:54,624][98560] Updated weights for policy 1, policy_version 43722 (0.0009) -[2023-10-10 22:30:54,987][98560] Updated weights for policy 1, policy_version 43732 (0.0007) -[2023-10-10 22:30:55,353][98560] Updated weights for policy 1, policy_version 43742 (0.0008) -[2023-10-10 22:30:55,556][97672] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 89784320. Throughput: 0: 1703.6, 1: 1704.0. Samples: 22445410. Policy #0 lag: (min: 7.0, avg: 7.2, max: 17.0) -[2023-10-10 22:30:55,557][97672] Avg episode reward: [(0, '-0.920'), (1, '22.260')] -[2023-10-10 22:30:58,180][98559] Updated weights for policy 0, policy_version 43940 (0.0008) -[2023-10-10 22:30:58,539][98559] Updated weights for policy 0, policy_version 43950 (0.0007) -[2023-10-10 22:30:58,909][98559] Updated weights for policy 0, policy_version 43960 (0.0008) -[2023-10-10 22:30:59,399][98560] Updated weights for policy 1, policy_version 43752 (0.0007) -[2023-10-10 22:30:59,764][98560] Updated weights for policy 1, policy_version 43762 (0.0008) -[2023-10-10 22:31:00,125][98560] Updated weights for policy 1, policy_version 43772 (0.0009) -[2023-10-10 22:31:00,556][97672] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 89849856. Throughput: 0: 1677.0, 1: 1710.1. Samples: 22465366. Policy #0 lag: (min: 7.0, avg: 7.2, max: 17.0) -[2023-10-10 22:31:00,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.240')] -[2023-10-10 22:31:02,931][98559] Updated weights for policy 0, policy_version 43970 (0.0008) -[2023-10-10 22:31:03,298][98559] Updated weights for policy 0, policy_version 43980 (0.0008) -[2023-10-10 22:31:03,669][98559] Updated weights for policy 0, policy_version 43990 (0.0008) -[2023-10-10 22:31:04,038][98559] Updated weights for policy 0, policy_version 44000 (0.0009) -[2023-10-10 22:31:04,153][98560] Updated weights for policy 1, policy_version 43782 (0.0008) -[2023-10-10 22:31:04,513][98560] Updated weights for policy 1, policy_version 43792 (0.0009) -[2023-10-10 22:31:04,879][98560] Updated weights for policy 1, policy_version 43802 (0.0010) -[2023-10-10 22:31:05,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 89915392. Throughput: 0: 1706.6, 1: 1691.6. Samples: 22485784. Policy #0 lag: (min: 7.0, avg: 7.2, max: 17.0) -[2023-10-10 22:31:05,556][97672] Avg episode reward: [(0, '-1.000'), (1, '22.220')] -[2023-10-10 22:31:08,024][98559] Updated weights for policy 0, policy_version 44010 (0.0011) -[2023-10-10 22:31:08,392][98559] Updated weights for policy 0, policy_version 44020 (0.0009) -[2023-10-10 22:31:08,755][98559] Updated weights for policy 0, policy_version 44030 (0.0009) -[2023-10-10 22:31:08,850][98560] Updated weights for policy 1, policy_version 43812 (0.0009) -[2023-10-10 22:31:09,219][98560] Updated weights for policy 1, policy_version 43822 (0.0008) -[2023-10-10 22:31:09,587][98560] Updated weights for policy 1, policy_version 43832 (0.0008) -[2023-10-10 22:31:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 89980928. Throughput: 0: 1698.4, 1: 1710.0. Samples: 22496260. Policy #0 lag: (min: 7.0, avg: 7.2, max: 17.0) -[2023-10-10 22:31:10,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.140')] -[2023-10-10 22:31:12,797][98559] Updated weights for policy 0, policy_version 44040 (0.0010) -[2023-10-10 22:31:13,173][98559] Updated weights for policy 0, policy_version 44050 (0.0009) -[2023-10-10 22:31:13,547][98559] Updated weights for policy 0, policy_version 44060 (0.0007) -[2023-10-10 22:31:13,625][98560] Updated weights for policy 1, policy_version 43842 (0.0008) -[2023-10-10 22:31:13,992][98560] Updated weights for policy 1, policy_version 43852 (0.0007) -[2023-10-10 22:31:14,352][98560] Updated weights for policy 1, policy_version 43862 (0.0007) -[2023-10-10 22:31:14,720][98560] Updated weights for policy 1, policy_version 43872 (0.0008) -[2023-10-10 22:31:15,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 90046464. Throughput: 0: 1695.0, 1: 1705.6. Samples: 22516546. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-10 22:31:15,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.180')] -[2023-10-10 22:31:17,485][98559] Updated weights for policy 0, policy_version 44070 (0.0010) -[2023-10-10 22:31:17,851][98559] Updated weights for policy 0, policy_version 44080 (0.0008) -[2023-10-10 22:31:18,224][98559] Updated weights for policy 0, policy_version 44090 (0.0009) -[2023-10-10 22:31:18,747][98560] Updated weights for policy 1, policy_version 43882 (0.0009) -[2023-10-10 22:31:19,109][98560] Updated weights for policy 1, policy_version 43892 (0.0009) -[2023-10-10 22:31:19,484][98560] Updated weights for policy 1, policy_version 43902 (0.0009) -[2023-10-10 22:31:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 90112000. Throughput: 0: 1718.9, 1: 1683.8. Samples: 22536514. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-10 22:31:20,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.140')] -[2023-10-10 22:31:22,293][98559] Updated weights for policy 0, policy_version 44100 (0.0008) -[2023-10-10 22:31:22,666][98559] Updated weights for policy 0, policy_version 44110 (0.0007) -[2023-10-10 22:31:23,027][98559] Updated weights for policy 0, policy_version 44120 (0.0007) -[2023-10-10 22:31:23,608][98560] Updated weights for policy 1, policy_version 43912 (0.0008) -[2023-10-10 22:31:23,988][98560] Updated weights for policy 1, policy_version 43922 (0.0007) -[2023-10-10 22:31:24,357][98560] Updated weights for policy 1, policy_version 43932 (0.0010) -[2023-10-10 22:31:25,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 90177536. Throughput: 0: 1687.3, 1: 1719.2. Samples: 22547156. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-10 22:31:25,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.160')] -[2023-10-10 22:31:26,892][98559] Updated weights for policy 0, policy_version 44130 (0.0008) -[2023-10-10 22:31:27,254][98559] Updated weights for policy 0, policy_version 44140 (0.0011) -[2023-10-10 22:31:27,613][98559] Updated weights for policy 0, policy_version 44150 (0.0009) -[2023-10-10 22:31:27,986][98559] Updated weights for policy 0, policy_version 44160 (0.0009) -[2023-10-10 22:31:28,379][98560] Updated weights for policy 1, policy_version 43942 (0.0010) -[2023-10-10 22:31:28,749][98560] Updated weights for policy 1, policy_version 43952 (0.0010) -[2023-10-10 22:31:29,119][98560] Updated weights for policy 1, policy_version 43962 (0.0009) -[2023-10-10 22:31:30,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 90243072. Throughput: 0: 1708.4, 1: 1706.4. Samples: 22567672. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-10 22:31:30,556][97672] Avg episode reward: [(0, '-1.060'), (1, '22.160')] -[2023-10-10 22:31:32,120][98559] Updated weights for policy 0, policy_version 44170 (0.0008) -[2023-10-10 22:31:32,491][98559] Updated weights for policy 0, policy_version 44180 (0.0008) -[2023-10-10 22:31:32,864][98559] Updated weights for policy 0, policy_version 44190 (0.0007) -[2023-10-10 22:31:33,160][98560] Updated weights for policy 1, policy_version 43972 (0.0007) -[2023-10-10 22:31:33,529][98560] Updated weights for policy 1, policy_version 43982 (0.0007) -[2023-10-10 22:31:33,882][98560] Updated weights for policy 1, policy_version 43992 (0.0007) -[2023-10-10 22:31:35,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 90308608. Throughput: 0: 1715.3, 1: 1687.0. Samples: 22587774. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-10 22:31:35,556][97672] Avg episode reward: [(0, '-1.000'), (1, '22.220')] -[2023-10-10 22:31:36,914][98559] Updated weights for policy 0, policy_version 44200 (0.0008) -[2023-10-10 22:31:37,279][98559] Updated weights for policy 0, policy_version 44210 (0.0009) -[2023-10-10 22:31:37,647][98559] Updated weights for policy 0, policy_version 44220 (0.0009) -[2023-10-10 22:31:37,798][98560] Updated weights for policy 1, policy_version 44002 (0.0007) -[2023-10-10 22:31:38,170][98560] Updated weights for policy 1, policy_version 44012 (0.0008) -[2023-10-10 22:31:38,523][98560] Updated weights for policy 1, policy_version 44022 (0.0008) -[2023-10-10 22:31:38,903][98560] Updated weights for policy 1, policy_version 44032 (0.0007) -[2023-10-10 22:31:40,556][97672] Fps is (10 sec: 13106.7, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 90374144. Throughput: 0: 1686.3, 1: 1715.4. Samples: 22598490. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-10 22:31:40,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.180')] -[2023-10-10 22:31:41,565][98559] Updated weights for policy 0, policy_version 44230 (0.0009) -[2023-10-10 22:31:41,937][98559] Updated weights for policy 0, policy_version 44240 (0.0008) -[2023-10-10 22:31:42,310][98559] Updated weights for policy 0, policy_version 44250 (0.0008) -[2023-10-10 22:31:43,002][98560] Updated weights for policy 1, policy_version 44042 (0.0010) -[2023-10-10 22:31:43,370][98560] Updated weights for policy 1, policy_version 44052 (0.0009) -[2023-10-10 22:31:43,742][98560] Updated weights for policy 1, policy_version 44062 (0.0007) -[2023-10-10 22:31:45,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 90439680. Throughput: 0: 1719.8, 1: 1682.5. Samples: 22618470. Policy #0 lag: (min: 8.0, avg: 36.2, max: 40.0) -[2023-10-10 22:31:45,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.180')] -[2023-10-10 22:31:46,068][98559] Updated weights for policy 0, policy_version 44260 (0.0010) -[2023-10-10 22:31:46,433][98559] Updated weights for policy 0, policy_version 44270 (0.0009) -[2023-10-10 22:31:46,803][98559] Updated weights for policy 0, policy_version 44280 (0.0008) -[2023-10-10 22:31:47,706][98560] Updated weights for policy 1, policy_version 44072 (0.0008) -[2023-10-10 22:31:48,074][98560] Updated weights for policy 1, policy_version 44082 (0.0009) -[2023-10-10 22:31:48,450][98560] Updated weights for policy 1, policy_version 44092 (0.0008) -[2023-10-10 22:31:50,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 90505216. Throughput: 0: 1712.0, 1: 1695.9. Samples: 22639140. Policy #0 lag: (min: 8.0, avg: 36.2, max: 40.0) -[2023-10-10 22:31:50,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.220')] -[2023-10-10 22:31:50,913][98559] Updated weights for policy 0, policy_version 44290 (0.0009) -[2023-10-10 22:31:51,272][98559] Updated weights for policy 0, policy_version 44300 (0.0009) -[2023-10-10 22:31:51,647][98559] Updated weights for policy 0, policy_version 44310 (0.0009) -[2023-10-10 22:31:52,017][98559] Updated weights for policy 0, policy_version 44320 (0.0007) -[2023-10-10 22:31:52,460][98560] Updated weights for policy 1, policy_version 44102 (0.0008) -[2023-10-10 22:31:52,821][98560] Updated weights for policy 1, policy_version 44112 (0.0009) -[2023-10-10 22:31:53,183][98560] Updated weights for policy 1, policy_version 44122 (0.0010) -[2023-10-10 22:31:55,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 90570752. Throughput: 0: 1703.5, 1: 1696.1. Samples: 22649242. Policy #0 lag: (min: 8.0, avg: 36.2, max: 40.0) -[2023-10-10 22:31:55,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.240')] -[2023-10-10 22:31:55,984][98559] Updated weights for policy 0, policy_version 44330 (0.0009) -[2023-10-10 22:31:56,350][98559] Updated weights for policy 0, policy_version 44340 (0.0007) -[2023-10-10 22:31:56,718][98559] Updated weights for policy 0, policy_version 44350 (0.0009) -[2023-10-10 22:31:57,044][98560] Updated weights for policy 1, policy_version 44132 (0.0009) -[2023-10-10 22:31:57,417][98560] Updated weights for policy 1, policy_version 44142 (0.0008) -[2023-10-10 22:31:57,785][98560] Updated weights for policy 1, policy_version 44152 (0.0008) -[2023-10-10 22:32:00,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 90636288. Throughput: 0: 1713.3, 1: 1684.5. Samples: 22669450. Policy #0 lag: (min: 8.0, avg: 36.2, max: 40.0) -[2023-10-10 22:32:00,556][97672] Avg episode reward: [(0, '-1.000'), (1, '22.300')] -[2023-10-10 22:32:00,785][98559] Updated weights for policy 0, policy_version 44360 (0.0011) -[2023-10-10 22:32:01,160][98559] Updated weights for policy 0, policy_version 44370 (0.0009) -[2023-10-10 22:32:01,532][98559] Updated weights for policy 0, policy_version 44380 (0.0008) -[2023-10-10 22:32:01,635][98560] Updated weights for policy 1, policy_version 44162 (0.0009) -[2023-10-10 22:32:02,009][98560] Updated weights for policy 1, policy_version 44172 (0.0007) -[2023-10-10 22:32:02,376][98560] Updated weights for policy 1, policy_version 44182 (0.0008) -[2023-10-10 22:32:02,746][98560] Updated weights for policy 1, policy_version 44192 (0.0008) -[2023-10-10 22:32:05,512][98559] Updated weights for policy 0, policy_version 44390 (0.0007) -[2023-10-10 22:32:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 90701824. Throughput: 0: 1706.7, 1: 1711.2. Samples: 22690322. Policy #0 lag: (min: 8.0, avg: 36.2, max: 40.0) -[2023-10-10 22:32:05,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.300')] -[2023-10-10 22:32:05,882][98559] Updated weights for policy 0, policy_version 44400 (0.0008) -[2023-10-10 22:32:06,256][98559] Updated weights for policy 0, policy_version 44410 (0.0008) -[2023-10-10 22:32:06,725][98560] Updated weights for policy 1, policy_version 44202 (0.0010) -[2023-10-10 22:32:07,092][98560] Updated weights for policy 1, policy_version 44212 (0.0008) -[2023-10-10 22:32:07,465][98560] Updated weights for policy 1, policy_version 44222 (0.0007) -[2023-10-10 22:32:10,203][98559] Updated weights for policy 0, policy_version 44420 (0.0009) -[2023-10-10 22:32:10,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 90767360. Throughput: 0: 1711.5, 1: 1677.2. Samples: 22699650. Policy #0 lag: (min: 8.0, avg: 36.2, max: 40.0) -[2023-10-10 22:32:10,558][97672] Avg episode reward: [(0, '-0.960'), (1, '22.400')] -[2023-10-10 22:32:10,568][98559] Updated weights for policy 0, policy_version 44430 (0.0008) -[2023-10-10 22:32:10,930][98559] Updated weights for policy 0, policy_version 44440 (0.0008) -[2023-10-10 22:32:11,436][98560] Updated weights for policy 1, policy_version 44232 (0.0007) -[2023-10-10 22:32:11,803][98560] Updated weights for policy 1, policy_version 44242 (0.0008) -[2023-10-10 22:32:12,164][98560] Updated weights for policy 1, policy_version 44252 (0.0007) -[2023-10-10 22:32:14,977][98559] Updated weights for policy 0, policy_version 44450 (0.0009) -[2023-10-10 22:32:15,343][98559] Updated weights for policy 0, policy_version 44460 (0.0010) -[2023-10-10 22:32:15,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 90832896. Throughput: 0: 1705.1, 1: 1692.1. Samples: 22720546. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:32:15,556][97672] Avg episode reward: [(0, '-0.960'), (1, '22.260')] -[2023-10-10 22:32:15,706][98559] Updated weights for policy 0, policy_version 44470 (0.0007) -[2023-10-10 22:32:16,077][98559] Updated weights for policy 0, policy_version 44480 (0.0008) -[2023-10-10 22:32:16,410][98560] Updated weights for policy 1, policy_version 44262 (0.0009) -[2023-10-10 22:32:16,803][98560] Updated weights for policy 1, policy_version 44272 (0.0008) -[2023-10-10 22:32:17,175][98560] Updated weights for policy 1, policy_version 44282 (0.0009) -[2023-10-10 22:32:20,097][98559] Updated weights for policy 0, policy_version 44490 (0.0008) -[2023-10-10 22:32:20,469][98559] Updated weights for policy 0, policy_version 44500 (0.0007) -[2023-10-10 22:32:20,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 90898432. Throughput: 0: 1693.2, 1: 1703.8. Samples: 22740642. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:32:20,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.120')] -[2023-10-10 22:32:20,838][98559] Updated weights for policy 0, policy_version 44510 (0.0011) -[2023-10-10 22:32:21,238][98560] Updated weights for policy 1, policy_version 44292 (0.0008) -[2023-10-10 22:32:21,608][98560] Updated weights for policy 1, policy_version 44302 (0.0007) -[2023-10-10 22:32:21,973][98560] Updated weights for policy 1, policy_version 44312 (0.0007) -[2023-10-10 22:32:24,777][98559] Updated weights for policy 0, policy_version 44520 (0.0008) -[2023-10-10 22:32:25,150][98559] Updated weights for policy 0, policy_version 44530 (0.0009) -[2023-10-10 22:32:25,508][98559] Updated weights for policy 0, policy_version 44540 (0.0010) -[2023-10-10 22:32:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 90963968. Throughput: 0: 1712.5, 1: 1670.6. Samples: 22750726. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:32:25,556][97672] Avg episode reward: [(0, '-0.960'), (1, '22.080')] -[2023-10-10 22:32:25,819][98560] Updated weights for policy 1, policy_version 44322 (0.0007) -[2023-10-10 22:32:26,186][98560] Updated weights for policy 1, policy_version 44332 (0.0009) -[2023-10-10 22:32:26,562][98560] Updated weights for policy 1, policy_version 44342 (0.0009) -[2023-10-10 22:32:26,928][98560] Updated weights for policy 1, policy_version 44352 (0.0008) -[2023-10-10 22:32:29,496][98559] Updated weights for policy 0, policy_version 44550 (0.0010) -[2023-10-10 22:32:29,857][98559] Updated weights for policy 0, policy_version 44560 (0.0009) -[2023-10-10 22:32:30,240][98559] Updated weights for policy 0, policy_version 44570 (0.0008) -[2023-10-10 22:32:30,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 91062272. Throughput: 0: 1705.8, 1: 1704.7. Samples: 22771940. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:32:30,556][97672] Avg episode reward: [(0, '-0.980'), (1, '22.180')] -[2023-10-10 22:32:30,977][98560] Updated weights for policy 1, policy_version 44362 (0.0009) -[2023-10-10 22:32:31,340][98560] Updated weights for policy 1, policy_version 44372 (0.0009) -[2023-10-10 22:32:31,715][98560] Updated weights for policy 1, policy_version 44382 (0.0011) -[2023-10-10 22:32:34,166][98559] Updated weights for policy 0, policy_version 44580 (0.0008) -[2023-10-10 22:32:34,539][98559] Updated weights for policy 0, policy_version 44590 (0.0012) -[2023-10-10 22:32:34,910][98559] Updated weights for policy 0, policy_version 44600 (0.0008) -[2023-10-10 22:32:35,556][97672] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 91127808. Throughput: 0: 1685.6, 1: 1711.0. Samples: 22791990. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:32:35,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.320')] -[2023-10-10 22:32:35,565][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000044608_45678592.pth... -[2023-10-10 22:32:35,604][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000043008_44040192.pth -[2023-10-10 22:32:35,627][98560] Updated weights for policy 1, policy_version 44392 (0.0009) -[2023-10-10 22:32:35,996][98560] Updated weights for policy 1, policy_version 44402 (0.0009) -[2023-10-10 22:32:36,362][98560] Updated weights for policy 1, policy_version 44412 (0.0009) -[2023-10-10 22:32:36,507][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000044416_45481984.pth... -[2023-10-10 22:32:36,549][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000042816_43843584.pth -[2023-10-10 22:32:38,941][98559] Updated weights for policy 0, policy_version 44610 (0.0008) -[2023-10-10 22:32:39,309][98559] Updated weights for policy 0, policy_version 44620 (0.0009) -[2023-10-10 22:32:39,680][98559] Updated weights for policy 0, policy_version 44630 (0.0009) -[2023-10-10 22:32:40,043][98559] Updated weights for policy 0, policy_version 44640 (0.0007) -[2023-10-10 22:32:40,253][98560] Updated weights for policy 1, policy_version 44422 (0.0009) -[2023-10-10 22:32:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 91193344. Throughput: 0: 1716.6, 1: 1692.1. Samples: 22802632. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:32:40,556][97672] Avg episode reward: [(0, '-0.980'), (1, '22.340')] -[2023-10-10 22:32:40,616][98560] Updated weights for policy 1, policy_version 44432 (0.0009) -[2023-10-10 22:32:40,981][98560] Updated weights for policy 1, policy_version 44442 (0.0008) -[2023-10-10 22:32:44,033][98559] Updated weights for policy 0, policy_version 44650 (0.0009) -[2023-10-10 22:32:44,410][98559] Updated weights for policy 0, policy_version 44660 (0.0009) -[2023-10-10 22:32:44,781][98559] Updated weights for policy 0, policy_version 44670 (0.0009) -[2023-10-10 22:32:45,080][98560] Updated weights for policy 1, policy_version 44452 (0.0007) -[2023-10-10 22:32:45,455][98560] Updated weights for policy 1, policy_version 44462 (0.0008) -[2023-10-10 22:32:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 91258880. Throughput: 0: 1702.2, 1: 1710.8. Samples: 22823032. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:32:45,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.280')] -[2023-10-10 22:32:45,826][98560] Updated weights for policy 1, policy_version 44472 (0.0007) -[2023-10-10 22:32:48,593][98559] Updated weights for policy 0, policy_version 44680 (0.0008) -[2023-10-10 22:32:48,970][98559] Updated weights for policy 0, policy_version 44690 (0.0008) -[2023-10-10 22:32:49,336][98559] Updated weights for policy 0, policy_version 44700 (0.0009) -[2023-10-10 22:32:49,856][98560] Updated weights for policy 1, policy_version 44482 (0.0010) -[2023-10-10 22:32:50,224][98560] Updated weights for policy 1, policy_version 44492 (0.0008) -[2023-10-10 22:32:50,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 91324416. Throughput: 0: 1699.0, 1: 1707.4. Samples: 22843610. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:32:50,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.240')] -[2023-10-10 22:32:50,593][98560] Updated weights for policy 1, policy_version 44502 (0.0010) -[2023-10-10 22:32:50,951][98560] Updated weights for policy 1, policy_version 44512 (0.0008) -[2023-10-10 22:32:53,313][98559] Updated weights for policy 0, policy_version 44710 (0.0009) -[2023-10-10 22:32:53,691][98559] Updated weights for policy 0, policy_version 44720 (0.0009) -[2023-10-10 22:32:54,061][98559] Updated weights for policy 0, policy_version 44730 (0.0008) -[2023-10-10 22:32:55,155][98560] Updated weights for policy 1, policy_version 44522 (0.0008) -[2023-10-10 22:32:55,522][98560] Updated weights for policy 1, policy_version 44532 (0.0009) -[2023-10-10 22:32:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 91389952. Throughput: 0: 1716.2, 1: 1708.3. Samples: 22853752. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:32:55,556][97672] Avg episode reward: [(0, '-0.980'), (1, '22.280')] -[2023-10-10 22:32:55,894][98560] Updated weights for policy 1, policy_version 44542 (0.0009) -[2023-10-10 22:32:58,080][98559] Updated weights for policy 0, policy_version 44740 (0.0010) -[2023-10-10 22:32:58,445][98559] Updated weights for policy 0, policy_version 44750 (0.0009) -[2023-10-10 22:32:58,810][98559] Updated weights for policy 0, policy_version 44760 (0.0010) -[2023-10-10 22:32:59,804][98560] Updated weights for policy 1, policy_version 44552 (0.0009) -[2023-10-10 22:33:00,179][98560] Updated weights for policy 1, policy_version 44562 (0.0009) -[2023-10-10 22:33:00,549][98560] Updated weights for policy 1, policy_version 44572 (0.0008) -[2023-10-10 22:33:00,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 91455488. Throughput: 0: 1695.0, 1: 1711.6. Samples: 22873842. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:33:00,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.300')] -[2023-10-10 22:33:02,809][98559] Updated weights for policy 0, policy_version 44770 (0.0011) -[2023-10-10 22:33:03,180][98559] Updated weights for policy 0, policy_version 44780 (0.0010) -[2023-10-10 22:33:03,554][98559] Updated weights for policy 0, policy_version 44790 (0.0008) -[2023-10-10 22:33:03,918][98559] Updated weights for policy 0, policy_version 44800 (0.0010) -[2023-10-10 22:33:04,661][98560] Updated weights for policy 1, policy_version 44582 (0.0009) -[2023-10-10 22:33:05,033][98560] Updated weights for policy 1, policy_version 44592 (0.0011) -[2023-10-10 22:33:05,397][98560] Updated weights for policy 1, policy_version 44602 (0.0011) -[2023-10-10 22:33:05,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 91521024. Throughput: 0: 1715.3, 1: 1710.8. Samples: 22894816. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:33:05,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.340')] -[2023-10-10 22:33:07,833][98559] Updated weights for policy 0, policy_version 44810 (0.0010) -[2023-10-10 22:33:08,207][98559] Updated weights for policy 0, policy_version 44820 (0.0009) -[2023-10-10 22:33:08,565][98559] Updated weights for policy 0, policy_version 44830 (0.0007) -[2023-10-10 22:33:09,521][98560] Updated weights for policy 1, policy_version 44612 (0.0008) -[2023-10-10 22:33:09,887][98560] Updated weights for policy 1, policy_version 44622 (0.0009) -[2023-10-10 22:33:10,253][98560] Updated weights for policy 1, policy_version 44632 (0.0009) -[2023-10-10 22:33:10,559][97672] Fps is (10 sec: 16379.0, 60 sec: 14198.8, 300 sec: 13662.4). Total num frames: 91619328. Throughput: 0: 1710.0, 1: 1713.1. Samples: 22904776. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:33:10,560][97672] Avg episode reward: [(0, '-1.000'), (1, '22.400')] -[2023-10-10 22:33:12,562][98559] Updated weights for policy 0, policy_version 44840 (0.0009) -[2023-10-10 22:33:12,933][98559] Updated weights for policy 0, policy_version 44850 (0.0010) -[2023-10-10 22:33:13,293][98559] Updated weights for policy 0, policy_version 44860 (0.0011) -[2023-10-10 22:33:14,123][98560] Updated weights for policy 1, policy_version 44642 (0.0008) -[2023-10-10 22:33:14,494][98560] Updated weights for policy 1, policy_version 44652 (0.0009) -[2023-10-10 22:33:14,863][98560] Updated weights for policy 1, policy_version 44662 (0.0009) -[2023-10-10 22:33:15,226][98560] Updated weights for policy 1, policy_version 44672 (0.0009) -[2023-10-10 22:33:15,556][97672] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 91684864. Throughput: 0: 1705.5, 1: 1712.0. Samples: 22925730. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:33:15,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.380')] -[2023-10-10 22:33:17,262][98559] Updated weights for policy 0, policy_version 44870 (0.0009) -[2023-10-10 22:33:17,637][98559] Updated weights for policy 0, policy_version 44880 (0.0007) -[2023-10-10 22:33:18,000][98559] Updated weights for policy 0, policy_version 44890 (0.0009) -[2023-10-10 22:33:19,202][98560] Updated weights for policy 1, policy_version 44682 (0.0010) -[2023-10-10 22:33:19,575][98560] Updated weights for policy 1, policy_version 44692 (0.0008) -[2023-10-10 22:33:19,944][98560] Updated weights for policy 1, policy_version 44702 (0.0009) -[2023-10-10 22:33:20,556][97672] Fps is (10 sec: 13111.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 91750400. Throughput: 0: 1733.6, 1: 1690.3. Samples: 22946066. Policy #0 lag: (min: 7.0, avg: 7.7, max: 25.0) -[2023-10-10 22:33:20,556][97672] Avg episode reward: [(0, '-1.000'), (1, '22.380')] -[2023-10-10 22:33:22,148][98559] Updated weights for policy 0, policy_version 44900 (0.0010) -[2023-10-10 22:33:22,542][98559] Updated weights for policy 0, policy_version 44910 (0.0010) -[2023-10-10 22:33:22,901][98559] Updated weights for policy 0, policy_version 44920 (0.0008) -[2023-10-10 22:33:23,950][98560] Updated weights for policy 1, policy_version 44712 (0.0007) -[2023-10-10 22:33:24,312][98560] Updated weights for policy 1, policy_version 44722 (0.0008) -[2023-10-10 22:33:24,685][98560] Updated weights for policy 1, policy_version 44732 (0.0008) -[2023-10-10 22:33:25,556][97672] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 91815936. Throughput: 0: 1696.0, 1: 1712.6. Samples: 22956022. Policy #0 lag: (min: 7.0, avg: 7.7, max: 25.0) -[2023-10-10 22:33:25,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.220')] -[2023-10-10 22:33:26,721][98559] Updated weights for policy 0, policy_version 44930 (0.0007) -[2023-10-10 22:33:27,087][98559] Updated weights for policy 0, policy_version 44940 (0.0009) -[2023-10-10 22:33:27,468][98559] Updated weights for policy 0, policy_version 44950 (0.0010) -[2023-10-10 22:33:27,822][98559] Updated weights for policy 0, policy_version 44960 (0.0010) -[2023-10-10 22:33:28,633][98560] Updated weights for policy 1, policy_version 44742 (0.0009) -[2023-10-10 22:33:28,997][98560] Updated weights for policy 1, policy_version 44752 (0.0008) -[2023-10-10 22:33:29,359][98560] Updated weights for policy 1, policy_version 44762 (0.0008) -[2023-10-10 22:33:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 91881472. Throughput: 0: 1720.6, 1: 1703.0. Samples: 22977094. Policy #0 lag: (min: 7.0, avg: 7.7, max: 25.0) -[2023-10-10 22:33:30,556][97672] Avg episode reward: [(0, '-0.960'), (1, '22.220')] -[2023-10-10 22:33:31,783][98559] Updated weights for policy 0, policy_version 44970 (0.0010) -[2023-10-10 22:33:32,156][98559] Updated weights for policy 0, policy_version 44980 (0.0008) -[2023-10-10 22:33:32,516][98559] Updated weights for policy 0, policy_version 44990 (0.0009) -[2023-10-10 22:33:33,368][98560] Updated weights for policy 1, policy_version 44772 (0.0007) -[2023-10-10 22:33:33,737][98560] Updated weights for policy 1, policy_version 44782 (0.0009) -[2023-10-10 22:33:34,107][98560] Updated weights for policy 1, policy_version 44792 (0.0010) -[2023-10-10 22:33:35,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 91947008. Throughput: 0: 1729.9, 1: 1685.6. Samples: 22997308. Policy #0 lag: (min: 7.0, avg: 7.7, max: 25.0) -[2023-10-10 22:33:35,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.220')] -[2023-10-10 22:33:36,499][98559] Updated weights for policy 0, policy_version 45000 (0.0008) -[2023-10-10 22:33:36,878][98559] Updated weights for policy 0, policy_version 45010 (0.0007) -[2023-10-10 22:33:37,241][98559] Updated weights for policy 0, policy_version 45020 (0.0009) -[2023-10-10 22:33:38,106][98560] Updated weights for policy 1, policy_version 44802 (0.0007) -[2023-10-10 22:33:38,474][98560] Updated weights for policy 1, policy_version 44812 (0.0007) -[2023-10-10 22:33:38,850][98560] Updated weights for policy 1, policy_version 44822 (0.0007) -[2023-10-10 22:33:39,223][98560] Updated weights for policy 1, policy_version 44832 (0.0007) -[2023-10-10 22:33:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 92012544. Throughput: 0: 1708.2, 1: 1715.5. Samples: 23007820. Policy #0 lag: (min: 7.0, avg: 7.7, max: 25.0) -[2023-10-10 22:33:40,556][97672] Avg episode reward: [(0, '-0.960'), (1, '22.220')] -[2023-10-10 22:33:41,269][98559] Updated weights for policy 0, policy_version 45030 (0.0008) -[2023-10-10 22:33:41,634][98559] Updated weights for policy 0, policy_version 45040 (0.0007) -[2023-10-10 22:33:42,007][98559] Updated weights for policy 0, policy_version 45050 (0.0009) -[2023-10-10 22:33:43,162][98560] Updated weights for policy 1, policy_version 44842 (0.0008) -[2023-10-10 22:33:43,537][98560] Updated weights for policy 1, policy_version 44852 (0.0007) -[2023-10-10 22:33:43,901][98560] Updated weights for policy 1, policy_version 44862 (0.0008) -[2023-10-10 22:33:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 92078080. Throughput: 0: 1731.9, 1: 1695.2. Samples: 23028058. Policy #0 lag: (min: 7.0, avg: 7.7, max: 25.0) -[2023-10-10 22:33:45,556][97672] Avg episode reward: [(0, '-0.960'), (1, '22.220')] -[2023-10-10 22:33:45,929][98559] Updated weights for policy 0, policy_version 45060 (0.0008) -[2023-10-10 22:33:46,309][98559] Updated weights for policy 0, policy_version 45070 (0.0007) -[2023-10-10 22:33:46,679][98559] Updated weights for policy 0, policy_version 45080 (0.0009) -[2023-10-10 22:33:47,963][98560] Updated weights for policy 1, policy_version 44872 (0.0007) -[2023-10-10 22:33:48,343][98560] Updated weights for policy 1, policy_version 44882 (0.0007) -[2023-10-10 22:33:48,712][98560] Updated weights for policy 1, policy_version 44892 (0.0008) -[2023-10-10 22:33:50,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 92143616. Throughput: 0: 1728.5, 1: 1695.0. Samples: 23048872. Policy #0 lag: (min: 31.0, avg: 32.5, max: 57.0) -[2023-10-10 22:33:50,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.240')] -[2023-10-10 22:33:50,603][98559] Updated weights for policy 0, policy_version 45090 (0.0008) -[2023-10-10 22:33:50,967][98559] Updated weights for policy 0, policy_version 45100 (0.0009) -[2023-10-10 22:33:51,338][98559] Updated weights for policy 0, policy_version 45110 (0.0008) -[2023-10-10 22:33:51,704][98559] Updated weights for policy 0, policy_version 45120 (0.0007) -[2023-10-10 22:33:52,818][98560] Updated weights for policy 1, policy_version 44902 (0.0007) -[2023-10-10 22:33:53,215][98560] Updated weights for policy 1, policy_version 44912 (0.0007) -[2023-10-10 22:33:53,576][98560] Updated weights for policy 1, policy_version 44922 (0.0007) -[2023-10-10 22:33:55,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 92209152. Throughput: 0: 1715.4, 1: 1711.6. Samples: 23058980. Policy #0 lag: (min: 31.0, avg: 32.5, max: 57.0) -[2023-10-10 22:33:55,556][97672] Avg episode reward: [(0, '-0.960'), (1, '22.320')] -[2023-10-10 22:33:55,815][98559] Updated weights for policy 0, policy_version 45130 (0.0007) -[2023-10-10 22:33:56,177][98559] Updated weights for policy 0, policy_version 45140 (0.0009) -[2023-10-10 22:33:56,545][98559] Updated weights for policy 0, policy_version 45150 (0.0007) -[2023-10-10 22:33:57,369][98560] Updated weights for policy 1, policy_version 44932 (0.0009) -[2023-10-10 22:33:57,742][98560] Updated weights for policy 1, policy_version 44942 (0.0008) -[2023-10-10 22:33:58,108][98560] Updated weights for policy 1, policy_version 44952 (0.0008) -[2023-10-10 22:34:00,243][98559] Updated weights for policy 0, policy_version 45160 (0.0009) -[2023-10-10 22:34:00,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 92274688. Throughput: 0: 1722.6, 1: 1685.7. Samples: 23079104. Policy #0 lag: (min: 31.0, avg: 32.5, max: 57.0) -[2023-10-10 22:34:00,556][97672] Avg episode reward: [(0, '-0.960'), (1, '22.300')] -[2023-10-10 22:34:00,609][98559] Updated weights for policy 0, policy_version 45170 (0.0009) -[2023-10-10 22:34:00,987][98559] Updated weights for policy 0, policy_version 45180 (0.0008) -[2023-10-10 22:34:02,023][98560] Updated weights for policy 1, policy_version 44962 (0.0008) -[2023-10-10 22:34:02,387][98560] Updated weights for policy 1, policy_version 44972 (0.0009) -[2023-10-10 22:34:02,752][98560] Updated weights for policy 1, policy_version 44982 (0.0009) -[2023-10-10 22:34:03,119][98560] Updated weights for policy 1, policy_version 44992 (0.0009) -[2023-10-10 22:34:05,206][98559] Updated weights for policy 0, policy_version 45190 (0.0008) -[2023-10-10 22:34:05,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 92340224. Throughput: 0: 1703.1, 1: 1708.8. Samples: 23099604. Policy #0 lag: (min: 31.0, avg: 32.5, max: 57.0) -[2023-10-10 22:34:05,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.300')] -[2023-10-10 22:34:05,567][98559] Updated weights for policy 0, policy_version 45200 (0.0008) -[2023-10-10 22:34:05,940][98559] Updated weights for policy 0, policy_version 45210 (0.0007) -[2023-10-10 22:34:07,158][98560] Updated weights for policy 1, policy_version 45002 (0.0010) -[2023-10-10 22:34:07,523][98560] Updated weights for policy 1, policy_version 45012 (0.0011) -[2023-10-10 22:34:07,893][98560] Updated weights for policy 1, policy_version 45022 (0.0009) -[2023-10-10 22:34:09,965][98559] Updated weights for policy 0, policy_version 45220 (0.0008) -[2023-10-10 22:34:10,353][98559] Updated weights for policy 0, policy_version 45230 (0.0009) -[2023-10-10 22:34:10,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.9, 300 sec: 13551.5). Total num frames: 92405760. Throughput: 0: 1720.0, 1: 1697.0. Samples: 23109788. Policy #0 lag: (min: 31.0, avg: 32.5, max: 57.0) -[2023-10-10 22:34:10,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.220')] -[2023-10-10 22:34:10,728][98559] Updated weights for policy 0, policy_version 45240 (0.0008) -[2023-10-10 22:34:11,892][98560] Updated weights for policy 1, policy_version 45032 (0.0008) -[2023-10-10 22:34:12,268][98560] Updated weights for policy 1, policy_version 45042 (0.0007) -[2023-10-10 22:34:12,638][98560] Updated weights for policy 1, policy_version 45052 (0.0008) -[2023-10-10 22:34:14,674][98559] Updated weights for policy 0, policy_version 45250 (0.0009) -[2023-10-10 22:34:15,040][98559] Updated weights for policy 0, policy_version 45260 (0.0008) -[2023-10-10 22:34:15,409][98559] Updated weights for policy 0, policy_version 45270 (0.0008) -[2023-10-10 22:34:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 92471296. Throughput: 0: 1711.1, 1: 1698.8. Samples: 23130536. Policy #0 lag: (min: 31.0, avg: 32.5, max: 57.0) -[2023-10-10 22:34:15,556][97672] Avg episode reward: [(0, '-0.960'), (1, '22.280')] -[2023-10-10 22:34:15,775][98559] Updated weights for policy 0, policy_version 45280 (0.0007) -[2023-10-10 22:34:16,501][98560] Updated weights for policy 1, policy_version 45062 (0.0009) -[2023-10-10 22:34:16,861][98560] Updated weights for policy 1, policy_version 45072 (0.0011) -[2023-10-10 22:34:17,231][98560] Updated weights for policy 1, policy_version 45082 (0.0011) -[2023-10-10 22:34:19,743][98559] Updated weights for policy 0, policy_version 45290 (0.0008) -[2023-10-10 22:34:20,105][98559] Updated weights for policy 0, policy_version 45300 (0.0008) -[2023-10-10 22:34:20,477][98559] Updated weights for policy 0, policy_version 45310 (0.0007) -[2023-10-10 22:34:20,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 92569600. Throughput: 0: 1687.7, 1: 1719.6. Samples: 23150636. Policy #0 lag: (min: 26.0, avg: 26.4, max: 39.0) -[2023-10-10 22:34:20,556][97672] Avg episode reward: [(0, '-0.900'), (1, '22.300')] -[2023-10-10 22:34:21,344][98560] Updated weights for policy 1, policy_version 45092 (0.0009) -[2023-10-10 22:34:21,709][98560] Updated weights for policy 1, policy_version 45102 (0.0009) -[2023-10-10 22:34:22,076][98560] Updated weights for policy 1, policy_version 45112 (0.0008) -[2023-10-10 22:34:24,385][98559] Updated weights for policy 0, policy_version 45320 (0.0008) -[2023-10-10 22:34:24,761][98559] Updated weights for policy 0, policy_version 45330 (0.0010) -[2023-10-10 22:34:25,120][98559] Updated weights for policy 0, policy_version 45340 (0.0010) -[2023-10-10 22:34:25,556][97672] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 92635136. Throughput: 0: 1713.7, 1: 1689.9. Samples: 23160982. Policy #0 lag: (min: 26.0, avg: 26.4, max: 39.0) -[2023-10-10 22:34:25,557][97672] Avg episode reward: [(0, '-0.900'), (1, '22.260')] -[2023-10-10 22:34:26,042][98560] Updated weights for policy 1, policy_version 45122 (0.0009) -[2023-10-10 22:34:26,406][98560] Updated weights for policy 1, policy_version 45132 (0.0007) -[2023-10-10 22:34:26,774][98560] Updated weights for policy 1, policy_version 45142 (0.0007) -[2023-10-10 22:34:27,141][98560] Updated weights for policy 1, policy_version 45152 (0.0008) -[2023-10-10 22:34:29,169][98559] Updated weights for policy 0, policy_version 45350 (0.0008) -[2023-10-10 22:34:29,547][98559] Updated weights for policy 0, policy_version 45360 (0.0009) -[2023-10-10 22:34:29,914][98559] Updated weights for policy 0, policy_version 45370 (0.0009) -[2023-10-10 22:34:30,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 92700672. Throughput: 0: 1706.5, 1: 1708.6. Samples: 23181738. Policy #0 lag: (min: 26.0, avg: 26.4, max: 39.0) -[2023-10-10 22:34:30,557][97672] Avg episode reward: [(0, '-0.900'), (1, '22.160')] -[2023-10-10 22:34:31,118][98560] Updated weights for policy 1, policy_version 45162 (0.0008) -[2023-10-10 22:34:31,492][98560] Updated weights for policy 1, policy_version 45172 (0.0008) -[2023-10-10 22:34:31,867][98560] Updated weights for policy 1, policy_version 45182 (0.0008) -[2023-10-10 22:34:33,826][98559] Updated weights for policy 0, policy_version 45380 (0.0009) -[2023-10-10 22:34:34,198][98559] Updated weights for policy 0, policy_version 45390 (0.0009) -[2023-10-10 22:34:34,573][98559] Updated weights for policy 0, policy_version 45400 (0.0008) -[2023-10-10 22:34:35,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 92766208. Throughput: 0: 1690.2, 1: 1715.7. Samples: 23202138. Policy #0 lag: (min: 26.0, avg: 26.4, max: 39.0) -[2023-10-10 22:34:35,557][97672] Avg episode reward: [(0, '-0.900'), (1, '22.200')] -[2023-10-10 22:34:35,566][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000045408_46497792.pth... -[2023-10-10 22:34:35,566][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000045184_46268416.pth... -[2023-10-10 22:34:35,617][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000043808_44859392.pth -[2023-10-10 22:34:35,617][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000043616_44662784.pth -[2023-10-10 22:34:36,014][98560] Updated weights for policy 1, policy_version 45192 (0.0007) -[2023-10-10 22:34:36,391][98560] Updated weights for policy 1, policy_version 45202 (0.0007) -[2023-10-10 22:34:36,755][98560] Updated weights for policy 1, policy_version 45212 (0.0007) -[2023-10-10 22:34:38,524][98559] Updated weights for policy 0, policy_version 45410 (0.0008) -[2023-10-10 22:34:38,895][98559] Updated weights for policy 0, policy_version 45420 (0.0009) -[2023-10-10 22:34:39,252][98559] Updated weights for policy 0, policy_version 45430 (0.0007) -[2023-10-10 22:34:39,614][98559] Updated weights for policy 0, policy_version 45440 (0.0008) -[2023-10-10 22:34:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 92831744. Throughput: 0: 1721.5, 1: 1694.2. Samples: 23212686. Policy #0 lag: (min: 26.0, avg: 26.4, max: 39.0) -[2023-10-10 22:34:40,557][97672] Avg episode reward: [(0, '-0.920'), (1, '22.120')] -[2023-10-10 22:34:40,813][98560] Updated weights for policy 1, policy_version 45222 (0.0009) -[2023-10-10 22:34:41,189][98560] Updated weights for policy 1, policy_version 45232 (0.0010) -[2023-10-10 22:34:41,560][98560] Updated weights for policy 1, policy_version 45242 (0.0008) -[2023-10-10 22:34:43,569][98559] Updated weights for policy 0, policy_version 45450 (0.0010) -[2023-10-10 22:34:43,942][98559] Updated weights for policy 0, policy_version 45460 (0.0010) -[2023-10-10 22:34:44,302][98559] Updated weights for policy 0, policy_version 45470 (0.0009) -[2023-10-10 22:34:45,541][98560] Updated weights for policy 1, policy_version 45252 (0.0010) -[2023-10-10 22:34:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 92897280. Throughput: 0: 1694.8, 1: 1713.9. Samples: 23232496. Policy #0 lag: (min: 26.0, avg: 26.4, max: 39.0) -[2023-10-10 22:34:45,556][97672] Avg episode reward: [(0, '-0.920'), (1, '22.100')] -[2023-10-10 22:34:45,910][98560] Updated weights for policy 1, policy_version 45262 (0.0007) -[2023-10-10 22:34:46,284][98560] Updated weights for policy 1, policy_version 45272 (0.0007) -[2023-10-10 22:34:48,210][98559] Updated weights for policy 0, policy_version 45480 (0.0008) -[2023-10-10 22:34:48,576][98559] Updated weights for policy 0, policy_version 45490 (0.0010) -[2023-10-10 22:34:48,951][98559] Updated weights for policy 0, policy_version 45500 (0.0007) -[2023-10-10 22:34:50,258][98560] Updated weights for policy 1, policy_version 45282 (0.0008) -[2023-10-10 22:34:50,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 92962816. Throughput: 0: 1710.8, 1: 1712.5. Samples: 23253652. Policy #0 lag: (min: 26.0, avg: 26.4, max: 39.0) -[2023-10-10 22:34:50,556][97672] Avg episode reward: [(0, '-0.920'), (1, '22.040')] -[2023-10-10 22:34:50,625][98560] Updated weights for policy 1, policy_version 45292 (0.0007) -[2023-10-10 22:34:50,991][98560] Updated weights for policy 1, policy_version 45302 (0.0011) -[2023-10-10 22:34:51,359][98560] Updated weights for policy 1, policy_version 45312 (0.0009) -[2023-10-10 22:34:52,849][98559] Updated weights for policy 0, policy_version 45510 (0.0009) -[2023-10-10 22:34:53,214][98559] Updated weights for policy 0, policy_version 45520 (0.0010) -[2023-10-10 22:34:53,582][98559] Updated weights for policy 0, policy_version 45530 (0.0008) -[2023-10-10 22:34:55,420][98560] Updated weights for policy 1, policy_version 45322 (0.0011) -[2023-10-10 22:34:55,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 93028352. Throughput: 0: 1713.8, 1: 1699.4. Samples: 23263380. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:34:55,557][97672] Avg episode reward: [(0, '-0.920'), (1, '22.100')] -[2023-10-10 22:34:55,785][98560] Updated weights for policy 1, policy_version 45332 (0.0011) -[2023-10-10 22:34:56,165][98560] Updated weights for policy 1, policy_version 45342 (0.0010) -[2023-10-10 22:34:57,602][98559] Updated weights for policy 0, policy_version 45540 (0.0008) -[2023-10-10 22:34:57,978][98559] Updated weights for policy 0, policy_version 45550 (0.0007) -[2023-10-10 22:34:58,347][98559] Updated weights for policy 0, policy_version 45560 (0.0009) -[2023-10-10 22:35:00,255][98560] Updated weights for policy 1, policy_version 45352 (0.0009) -[2023-10-10 22:35:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 93093888. Throughput: 0: 1704.2, 1: 1707.0. Samples: 23284040. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:35:00,556][97672] Avg episode reward: [(0, '-0.920'), (1, '22.140')] -[2023-10-10 22:35:00,627][98560] Updated weights for policy 1, policy_version 45362 (0.0010) -[2023-10-10 22:35:00,996][98560] Updated weights for policy 1, policy_version 45372 (0.0009) -[2023-10-10 22:35:02,324][98559] Updated weights for policy 0, policy_version 45570 (0.0009) -[2023-10-10 22:35:02,701][98559] Updated weights for policy 0, policy_version 45580 (0.0011) -[2023-10-10 22:35:03,072][98559] Updated weights for policy 0, policy_version 45590 (0.0007) -[2023-10-10 22:35:03,429][98559] Updated weights for policy 0, policy_version 45600 (0.0007) -[2023-10-10 22:35:05,126][98560] Updated weights for policy 1, policy_version 45382 (0.0009) -[2023-10-10 22:35:05,490][98560] Updated weights for policy 1, policy_version 45392 (0.0008) -[2023-10-10 22:35:05,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 93159424. Throughput: 0: 1730.7, 1: 1699.2. Samples: 23304982. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:35:05,557][97672] Avg episode reward: [(0, '-0.920'), (1, '22.080')] -[2023-10-10 22:35:05,862][98560] Updated weights for policy 1, policy_version 45402 (0.0009) -[2023-10-10 22:35:07,354][98559] Updated weights for policy 0, policy_version 45610 (0.0008) -[2023-10-10 22:35:07,722][98559] Updated weights for policy 0, policy_version 45620 (0.0008) -[2023-10-10 22:35:08,097][98559] Updated weights for policy 0, policy_version 45630 (0.0009) -[2023-10-10 22:35:09,730][98560] Updated weights for policy 1, policy_version 45412 (0.0010) -[2023-10-10 22:35:10,103][98560] Updated weights for policy 1, policy_version 45422 (0.0008) -[2023-10-10 22:35:10,463][98560] Updated weights for policy 1, policy_version 45432 (0.0009) -[2023-10-10 22:35:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 93224960. Throughput: 0: 1709.7, 1: 1700.0. Samples: 23314416. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:35:10,557][97672] Avg episode reward: [(0, '-0.920'), (1, '22.040')] -[2023-10-10 22:35:12,029][98559] Updated weights for policy 0, policy_version 45640 (0.0011) -[2023-10-10 22:35:12,396][98559] Updated weights for policy 0, policy_version 45650 (0.0009) -[2023-10-10 22:35:12,766][98559] Updated weights for policy 0, policy_version 45660 (0.0007) -[2023-10-10 22:35:14,343][98560] Updated weights for policy 1, policy_version 45442 (0.0008) -[2023-10-10 22:35:14,717][98560] Updated weights for policy 1, policy_version 45452 (0.0008) -[2023-10-10 22:35:15,084][98560] Updated weights for policy 1, policy_version 45462 (0.0009) -[2023-10-10 22:35:15,446][98560] Updated weights for policy 1, policy_version 45472 (0.0008) -[2023-10-10 22:35:15,556][97672] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 93323264. Throughput: 0: 1721.8, 1: 1700.9. Samples: 23335758. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:35:15,557][97672] Avg episode reward: [(0, '-0.920'), (1, '22.020')] -[2023-10-10 22:35:16,557][98559] Updated weights for policy 0, policy_version 45670 (0.0007) -[2023-10-10 22:35:16,921][98559] Updated weights for policy 0, policy_version 45680 (0.0007) -[2023-10-10 22:35:17,296][98559] Updated weights for policy 0, policy_version 45690 (0.0007) -[2023-10-10 22:35:19,277][98560] Updated weights for policy 1, policy_version 45482 (0.0009) -[2023-10-10 22:35:19,643][98560] Updated weights for policy 1, policy_version 45492 (0.0007) -[2023-10-10 22:35:20,013][98560] Updated weights for policy 1, policy_version 45502 (0.0008) -[2023-10-10 22:35:20,556][97672] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 93388800. Throughput: 0: 1744.0, 1: 1685.5. Samples: 23356464. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:35:20,557][97672] Avg episode reward: [(0, '-0.920'), (1, '22.100')] -[2023-10-10 22:35:21,291][98559] Updated weights for policy 0, policy_version 45700 (0.0008) -[2023-10-10 22:35:21,647][98559] Updated weights for policy 0, policy_version 45710 (0.0008) -[2023-10-10 22:35:22,014][98559] Updated weights for policy 0, policy_version 45720 (0.0008) -[2023-10-10 22:35:23,938][98560] Updated weights for policy 1, policy_version 45512 (0.0008) -[2023-10-10 22:35:24,317][98560] Updated weights for policy 1, policy_version 45522 (0.0010) -[2023-10-10 22:35:24,678][98560] Updated weights for policy 1, policy_version 45532 (0.0008) -[2023-10-10 22:35:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 93454336. Throughput: 0: 1713.5, 1: 1708.0. Samples: 23366654. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:35:25,557][97672] Avg episode reward: [(0, '-0.920'), (1, '22.040')] -[2023-10-10 22:35:25,878][98559] Updated weights for policy 0, policy_version 45730 (0.0007) -[2023-10-10 22:35:26,236][98559] Updated weights for policy 0, policy_version 45740 (0.0011) -[2023-10-10 22:35:26,608][98559] Updated weights for policy 0, policy_version 45750 (0.0011) -[2023-10-10 22:35:26,980][98559] Updated weights for policy 0, policy_version 45760 (0.0011) -[2023-10-10 22:35:28,935][98560] Updated weights for policy 1, policy_version 45542 (0.0008) -[2023-10-10 22:35:29,324][98560] Updated weights for policy 1, policy_version 45552 (0.0008) -[2023-10-10 22:35:29,692][98560] Updated weights for policy 1, policy_version 45562 (0.0007) -[2023-10-10 22:35:30,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 93519872. Throughput: 0: 1736.0, 1: 1713.8. Samples: 23387734. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 22:35:30,556][97672] Avg episode reward: [(0, '-0.920'), (1, '21.980')] -[2023-10-10 22:35:31,106][98559] Updated weights for policy 0, policy_version 45770 (0.0008) -[2023-10-10 22:35:31,478][98559] Updated weights for policy 0, policy_version 45780 (0.0007) -[2023-10-10 22:35:31,836][98559] Updated weights for policy 0, policy_version 45790 (0.0008) -[2023-10-10 22:35:33,598][98560] Updated weights for policy 1, policy_version 45572 (0.0009) -[2023-10-10 22:35:33,965][98560] Updated weights for policy 1, policy_version 45582 (0.0010) -[2023-10-10 22:35:34,331][98560] Updated weights for policy 1, policy_version 45592 (0.0009) -[2023-10-10 22:35:35,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 93585408. Throughput: 0: 1741.1, 1: 1682.3. Samples: 23407704. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 22:35:35,556][97672] Avg episode reward: [(0, '-0.920'), (1, '22.000')] -[2023-10-10 22:35:35,677][98559] Updated weights for policy 0, policy_version 45800 (0.0007) -[2023-10-10 22:35:36,040][98559] Updated weights for policy 0, policy_version 45810 (0.0007) -[2023-10-10 22:35:36,405][98559] Updated weights for policy 0, policy_version 45820 (0.0007) -[2023-10-10 22:35:38,426][98560] Updated weights for policy 1, policy_version 45602 (0.0009) -[2023-10-10 22:35:38,796][98560] Updated weights for policy 1, policy_version 45612 (0.0008) -[2023-10-10 22:35:39,165][98560] Updated weights for policy 1, policy_version 45622 (0.0009) -[2023-10-10 22:35:39,527][98560] Updated weights for policy 1, policy_version 45632 (0.0008) -[2023-10-10 22:35:40,451][98559] Updated weights for policy 0, policy_version 45830 (0.0010) -[2023-10-10 22:35:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 93650944. Throughput: 0: 1728.0, 1: 1710.7. Samples: 23418124. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 22:35:40,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.100')] -[2023-10-10 22:35:40,820][98559] Updated weights for policy 0, policy_version 45840 (0.0009) -[2023-10-10 22:35:41,190][98559] Updated weights for policy 0, policy_version 45850 (0.0008) -[2023-10-10 22:35:43,507][98560] Updated weights for policy 1, policy_version 45642 (0.0007) -[2023-10-10 22:35:43,885][98560] Updated weights for policy 1, policy_version 45652 (0.0011) -[2023-10-10 22:35:44,264][98560] Updated weights for policy 1, policy_version 45662 (0.0008) -[2023-10-10 22:35:45,401][98559] Updated weights for policy 0, policy_version 45860 (0.0010) -[2023-10-10 22:35:45,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 93716480. Throughput: 0: 1738.0, 1: 1696.4. Samples: 23438588. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 22:35:45,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.040')] -[2023-10-10 22:35:45,789][98559] Updated weights for policy 0, policy_version 45870 (0.0009) -[2023-10-10 22:35:46,159][98559] Updated weights for policy 0, policy_version 45880 (0.0010) -[2023-10-10 22:35:48,235][98560] Updated weights for policy 1, policy_version 45672 (0.0008) -[2023-10-10 22:35:48,597][98560] Updated weights for policy 1, policy_version 45682 (0.0008) -[2023-10-10 22:35:48,972][98560] Updated weights for policy 1, policy_version 45692 (0.0007) -[2023-10-10 22:35:49,956][98559] Updated weights for policy 0, policy_version 45890 (0.0008) -[2023-10-10 22:35:50,320][98559] Updated weights for policy 0, policy_version 45900 (0.0008) -[2023-10-10 22:35:50,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 93782016. Throughput: 0: 1720.0, 1: 1687.9. Samples: 23458334. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 22:35:50,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.000')] -[2023-10-10 22:35:50,689][98559] Updated weights for policy 0, policy_version 45910 (0.0007) -[2023-10-10 22:35:51,045][98559] Updated weights for policy 0, policy_version 45920 (0.0009) -[2023-10-10 22:35:52,893][98560] Updated weights for policy 1, policy_version 45702 (0.0009) -[2023-10-10 22:35:53,261][98560] Updated weights for policy 1, policy_version 45712 (0.0010) -[2023-10-10 22:35:53,626][98560] Updated weights for policy 1, policy_version 45722 (0.0009) -[2023-10-10 22:35:55,084][98559] Updated weights for policy 0, policy_version 45930 (0.0010) -[2023-10-10 22:35:55,454][98559] Updated weights for policy 0, policy_version 45940 (0.0010) -[2023-10-10 22:35:55,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 93847552. Throughput: 0: 1727.7, 1: 1717.2. Samples: 23469438. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 22:35:55,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.020')] -[2023-10-10 22:35:55,809][98559] Updated weights for policy 0, policy_version 45950 (0.0010) -[2023-10-10 22:35:57,591][98560] Updated weights for policy 1, policy_version 45732 (0.0007) -[2023-10-10 22:35:57,966][98560] Updated weights for policy 1, policy_version 45742 (0.0009) -[2023-10-10 22:35:58,320][98560] Updated weights for policy 1, policy_version 45752 (0.0007) -[2023-10-10 22:35:59,634][98559] Updated weights for policy 0, policy_version 45960 (0.0011) -[2023-10-10 22:36:00,001][98559] Updated weights for policy 0, policy_version 45970 (0.0010) -[2023-10-10 22:36:00,367][98559] Updated weights for policy 0, policy_version 45980 (0.0008) -[2023-10-10 22:36:00,556][97672] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 93945856. Throughput: 0: 1726.7, 1: 1689.2. Samples: 23489474. Policy #0 lag: (min: 1.0, avg: 14.0, max: 33.0) -[2023-10-10 22:36:00,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.000')] -[2023-10-10 22:36:02,405][98560] Updated weights for policy 1, policy_version 45762 (0.0007) -[2023-10-10 22:36:02,770][98560] Updated weights for policy 1, policy_version 45772 (0.0009) -[2023-10-10 22:36:03,144][98560] Updated weights for policy 1, policy_version 45782 (0.0010) -[2023-10-10 22:36:03,508][98560] Updated weights for policy 1, policy_version 45792 (0.0009) -[2023-10-10 22:36:04,292][98559] Updated weights for policy 0, policy_version 45990 (0.0009) -[2023-10-10 22:36:04,660][98559] Updated weights for policy 0, policy_version 46000 (0.0007) -[2023-10-10 22:36:05,030][98559] Updated weights for policy 0, policy_version 46010 (0.0007) -[2023-10-10 22:36:05,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 94011392. Throughput: 0: 1692.0, 1: 1704.0. Samples: 23509282. Policy #0 lag: (min: 1.0, avg: 14.0, max: 33.0) -[2023-10-10 22:36:05,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.000')] -[2023-10-10 22:36:07,373][98560] Updated weights for policy 1, policy_version 45802 (0.0011) -[2023-10-10 22:36:07,739][98560] Updated weights for policy 1, policy_version 45812 (0.0010) -[2023-10-10 22:36:08,104][98560] Updated weights for policy 1, policy_version 45822 (0.0007) -[2023-10-10 22:36:09,148][98559] Updated weights for policy 0, policy_version 46020 (0.0008) -[2023-10-10 22:36:09,519][98559] Updated weights for policy 0, policy_version 46030 (0.0007) -[2023-10-10 22:36:09,893][98559] Updated weights for policy 0, policy_version 46040 (0.0008) -[2023-10-10 22:36:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 94076928. Throughput: 0: 1722.7, 1: 1697.4. Samples: 23520558. Policy #0 lag: (min: 1.0, avg: 14.0, max: 33.0) -[2023-10-10 22:36:10,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.040')] -[2023-10-10 22:36:12,298][98560] Updated weights for policy 1, policy_version 45832 (0.0007) -[2023-10-10 22:36:12,657][98560] Updated weights for policy 1, policy_version 45842 (0.0007) -[2023-10-10 22:36:13,030][98560] Updated weights for policy 1, policy_version 45852 (0.0007) -[2023-10-10 22:36:13,820][98559] Updated weights for policy 0, policy_version 46050 (0.0011) -[2023-10-10 22:36:14,187][98559] Updated weights for policy 0, policy_version 46060 (0.0009) -[2023-10-10 22:36:14,561][98559] Updated weights for policy 0, policy_version 46070 (0.0009) -[2023-10-10 22:36:14,925][98559] Updated weights for policy 0, policy_version 46080 (0.0008) -[2023-10-10 22:36:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 94142464. Throughput: 0: 1708.8, 1: 1682.9. Samples: 23540362. Policy #0 lag: (min: 1.0, avg: 14.0, max: 33.0) -[2023-10-10 22:36:15,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.020')] -[2023-10-10 22:36:17,248][98560] Updated weights for policy 1, policy_version 45862 (0.0008) -[2023-10-10 22:36:17,620][98560] Updated weights for policy 1, policy_version 45872 (0.0007) -[2023-10-10 22:36:17,984][98560] Updated weights for policy 1, policy_version 45882 (0.0007) -[2023-10-10 22:36:18,825][98559] Updated weights for policy 0, policy_version 46090 (0.0008) -[2023-10-10 22:36:19,199][98559] Updated weights for policy 0, policy_version 46100 (0.0010) -[2023-10-10 22:36:19,565][98559] Updated weights for policy 0, policy_version 46110 (0.0008) -[2023-10-10 22:36:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 94208000. Throughput: 0: 1691.2, 1: 1710.7. Samples: 23560792. Policy #0 lag: (min: 1.0, avg: 14.0, max: 33.0) -[2023-10-10 22:36:20,557][97672] Avg episode reward: [(0, '-1.020'), (1, '22.080')] -[2023-10-10 22:36:21,817][98560] Updated weights for policy 1, policy_version 45892 (0.0009) -[2023-10-10 22:36:22,185][98560] Updated weights for policy 1, policy_version 45902 (0.0008) -[2023-10-10 22:36:22,540][98560] Updated weights for policy 1, policy_version 45912 (0.0007) -[2023-10-10 22:36:23,651][98559] Updated weights for policy 0, policy_version 46120 (0.0008) -[2023-10-10 22:36:24,021][98559] Updated weights for policy 0, policy_version 46130 (0.0008) -[2023-10-10 22:36:24,379][98559] Updated weights for policy 0, policy_version 46140 (0.0008) -[2023-10-10 22:36:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 94273536. Throughput: 0: 1722.6, 1: 1691.6. Samples: 23571764. Policy #0 lag: (min: 1.0, avg: 14.0, max: 33.0) -[2023-10-10 22:36:25,557][97672] Avg episode reward: [(0, '-1.020'), (1, '22.120')] -[2023-10-10 22:36:26,545][98560] Updated weights for policy 1, policy_version 45922 (0.0007) -[2023-10-10 22:36:26,901][98560] Updated weights for policy 1, policy_version 45932 (0.0008) -[2023-10-10 22:36:27,264][98560] Updated weights for policy 1, policy_version 45942 (0.0009) -[2023-10-10 22:36:27,631][98560] Updated weights for policy 1, policy_version 45952 (0.0009) -[2023-10-10 22:36:28,301][98559] Updated weights for policy 0, policy_version 46150 (0.0008) -[2023-10-10 22:36:28,669][98559] Updated weights for policy 0, policy_version 46160 (0.0007) -[2023-10-10 22:36:29,040][98559] Updated weights for policy 0, policy_version 46170 (0.0009) -[2023-10-10 22:36:30,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 94339072. Throughput: 0: 1694.0, 1: 1702.4. Samples: 23591424. Policy #0 lag: (min: 1.0, avg: 14.0, max: 33.0) -[2023-10-10 22:36:30,557][97672] Avg episode reward: [(0, '-1.020'), (1, '22.040')] -[2023-10-10 22:36:31,505][98560] Updated weights for policy 1, policy_version 45962 (0.0011) -[2023-10-10 22:36:31,872][98560] Updated weights for policy 1, policy_version 45972 (0.0009) -[2023-10-10 22:36:32,233][98560] Updated weights for policy 1, policy_version 45982 (0.0008) -[2023-10-10 22:36:33,121][98559] Updated weights for policy 0, policy_version 46180 (0.0010) -[2023-10-10 22:36:33,514][98559] Updated weights for policy 0, policy_version 46190 (0.0008) -[2023-10-10 22:36:33,878][98559] Updated weights for policy 0, policy_version 46200 (0.0008) -[2023-10-10 22:36:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 94404608. Throughput: 0: 1708.3, 1: 1717.6. Samples: 23612496. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-10-10 22:36:35,557][97672] Avg episode reward: [(0, '-1.020'), (1, '22.060')] -[2023-10-10 22:36:35,568][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000045984_47087616.pth... -[2023-10-10 22:36:35,569][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000046208_47316992.pth... -[2023-10-10 22:36:35,608][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000044416_45481984.pth -[2023-10-10 22:36:35,611][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000044608_45678592.pth -[2023-10-10 22:36:36,390][98560] Updated weights for policy 1, policy_version 45992 (0.0010) -[2023-10-10 22:36:36,760][98560] Updated weights for policy 1, policy_version 46002 (0.0009) -[2023-10-10 22:36:37,134][98560] Updated weights for policy 1, policy_version 46012 (0.0008) -[2023-10-10 22:36:37,821][98559] Updated weights for policy 0, policy_version 46210 (0.0009) -[2023-10-10 22:36:38,193][98559] Updated weights for policy 0, policy_version 46220 (0.0007) -[2023-10-10 22:36:38,557][98559] Updated weights for policy 0, policy_version 46230 (0.0008) -[2023-10-10 22:36:38,925][98559] Updated weights for policy 0, policy_version 46240 (0.0007) -[2023-10-10 22:36:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 94470144. Throughput: 0: 1710.9, 1: 1686.1. Samples: 23622306. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-10-10 22:36:40,556][97672] Avg episode reward: [(0, '-1.020'), (1, '22.100')] -[2023-10-10 22:36:41,050][98560] Updated weights for policy 1, policy_version 46022 (0.0009) -[2023-10-10 22:36:41,418][98560] Updated weights for policy 1, policy_version 46032 (0.0008) -[2023-10-10 22:36:41,790][98560] Updated weights for policy 1, policy_version 46042 (0.0009) -[2023-10-10 22:36:42,791][98559] Updated weights for policy 0, policy_version 46250 (0.0010) -[2023-10-10 22:36:43,150][98559] Updated weights for policy 0, policy_version 46260 (0.0010) -[2023-10-10 22:36:43,517][98559] Updated weights for policy 0, policy_version 46270 (0.0008) -[2023-10-10 22:36:45,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 94535680. Throughput: 0: 1693.6, 1: 1711.2. Samples: 23642686. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-10-10 22:36:45,556][97672] Avg episode reward: [(0, '-0.980'), (1, '22.120')] -[2023-10-10 22:36:45,654][98560] Updated weights for policy 1, policy_version 46052 (0.0009) -[2023-10-10 22:36:46,011][98560] Updated weights for policy 1, policy_version 46062 (0.0010) -[2023-10-10 22:36:46,384][98560] Updated weights for policy 1, policy_version 46072 (0.0010) -[2023-10-10 22:36:47,479][98559] Updated weights for policy 0, policy_version 46280 (0.0008) -[2023-10-10 22:36:47,851][98559] Updated weights for policy 0, policy_version 46290 (0.0008) -[2023-10-10 22:36:48,212][98559] Updated weights for policy 0, policy_version 46300 (0.0007) -[2023-10-10 22:36:50,538][98560] Updated weights for policy 1, policy_version 46082 (0.0009) -[2023-10-10 22:36:50,556][97672] Fps is (10 sec: 13106.6, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 94601216. Throughput: 0: 1721.3, 1: 1713.9. Samples: 23663864. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-10-10 22:36:50,558][97672] Avg episode reward: [(0, '-0.980'), (1, '22.180')] -[2023-10-10 22:36:50,902][98560] Updated weights for policy 1, policy_version 46092 (0.0008) -[2023-10-10 22:36:51,261][98560] Updated weights for policy 1, policy_version 46102 (0.0011) -[2023-10-10 22:36:51,634][98560] Updated weights for policy 1, policy_version 46112 (0.0009) -[2023-10-10 22:36:52,216][98559] Updated weights for policy 0, policy_version 46310 (0.0008) -[2023-10-10 22:36:52,581][98559] Updated weights for policy 0, policy_version 46320 (0.0007) -[2023-10-10 22:36:52,949][98559] Updated weights for policy 0, policy_version 46330 (0.0009) -[2023-10-10 22:36:55,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 94666752. Throughput: 0: 1689.5, 1: 1702.5. Samples: 23673200. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-10-10 22:36:55,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.180')] -[2023-10-10 22:36:55,620][98560] Updated weights for policy 1, policy_version 46122 (0.0010) -[2023-10-10 22:36:55,984][98560] Updated weights for policy 1, policy_version 46132 (0.0008) -[2023-10-10 22:36:56,355][98560] Updated weights for policy 1, policy_version 46142 (0.0008) -[2023-10-10 22:36:56,856][98559] Updated weights for policy 0, policy_version 46340 (0.0008) -[2023-10-10 22:36:57,218][98559] Updated weights for policy 0, policy_version 46350 (0.0007) -[2023-10-10 22:36:57,590][98559] Updated weights for policy 0, policy_version 46360 (0.0007) -[2023-10-10 22:37:00,317][98560] Updated weights for policy 1, policy_version 46152 (0.0007) -[2023-10-10 22:37:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 94732288. Throughput: 0: 1712.2, 1: 1715.0. Samples: 23694584. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-10-10 22:37:00,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.220')] -[2023-10-10 22:37:00,685][98560] Updated weights for policy 1, policy_version 46162 (0.0009) -[2023-10-10 22:37:01,061][98560] Updated weights for policy 1, policy_version 46172 (0.0010) -[2023-10-10 22:37:01,531][98559] Updated weights for policy 0, policy_version 46370 (0.0008) -[2023-10-10 22:37:01,906][98559] Updated weights for policy 0, policy_version 46380 (0.0011) -[2023-10-10 22:37:02,266][98559] Updated weights for policy 0, policy_version 46390 (0.0009) -[2023-10-10 22:37:02,631][98559] Updated weights for policy 0, policy_version 46400 (0.0008) -[2023-10-10 22:37:05,162][98560] Updated weights for policy 1, policy_version 46182 (0.0008) -[2023-10-10 22:37:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 94797824. Throughput: 0: 1723.0, 1: 1720.3. Samples: 23715740. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-10-10 22:37:05,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.260')] -[2023-10-10 22:37:05,563][98560] Updated weights for policy 1, policy_version 46192 (0.0007) -[2023-10-10 22:37:05,937][98560] Updated weights for policy 1, policy_version 46202 (0.0009) -[2023-10-10 22:37:06,686][98559] Updated weights for policy 0, policy_version 46410 (0.0011) -[2023-10-10 22:37:07,047][98559] Updated weights for policy 0, policy_version 46420 (0.0012) -[2023-10-10 22:37:07,425][98559] Updated weights for policy 0, policy_version 46430 (0.0008) -[2023-10-10 22:37:09,851][98560] Updated weights for policy 1, policy_version 46212 (0.0009) -[2023-10-10 22:37:10,219][98560] Updated weights for policy 1, policy_version 46222 (0.0010) -[2023-10-10 22:37:10,556][97672] Fps is (10 sec: 13107.7, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 94863360. Throughput: 0: 1694.0, 1: 1711.5. Samples: 23725010. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 22:37:10,556][97672] Avg episode reward: [(0, '-0.980'), (1, '22.240')] -[2023-10-10 22:37:10,590][98560] Updated weights for policy 1, policy_version 46232 (0.0008) -[2023-10-10 22:37:11,391][98559] Updated weights for policy 0, policy_version 46440 (0.0010) -[2023-10-10 22:37:11,767][98559] Updated weights for policy 0, policy_version 46450 (0.0011) -[2023-10-10 22:37:12,127][98559] Updated weights for policy 0, policy_version 46460 (0.0009) -[2023-10-10 22:37:14,521][98560] Updated weights for policy 1, policy_version 46242 (0.0009) -[2023-10-10 22:37:14,897][98560] Updated weights for policy 1, policy_version 46252 (0.0007) -[2023-10-10 22:37:15,262][98560] Updated weights for policy 1, policy_version 46262 (0.0008) -[2023-10-10 22:37:15,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 94928896. Throughput: 0: 1722.8, 1: 1717.5. Samples: 23746234. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 22:37:15,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.160')] -[2023-10-10 22:37:15,631][98560] Updated weights for policy 1, policy_version 46272 (0.0009) -[2023-10-10 22:37:16,045][98559] Updated weights for policy 0, policy_version 46470 (0.0008) -[2023-10-10 22:37:16,417][98559] Updated weights for policy 0, policy_version 46480 (0.0008) -[2023-10-10 22:37:16,783][98559] Updated weights for policy 0, policy_version 46490 (0.0009) -[2023-10-10 22:37:19,495][98560] Updated weights for policy 1, policy_version 46282 (0.0007) -[2023-10-10 22:37:19,864][98560] Updated weights for policy 1, policy_version 46292 (0.0008) -[2023-10-10 22:37:20,230][98560] Updated weights for policy 1, policy_version 46302 (0.0009) -[2023-10-10 22:37:20,556][97672] Fps is (10 sec: 16383.6, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 95027200. Throughput: 0: 1725.1, 1: 1706.8. Samples: 23766928. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 22:37:20,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.200')] -[2023-10-10 22:37:20,883][98559] Updated weights for policy 0, policy_version 46500 (0.0009) -[2023-10-10 22:37:21,269][98559] Updated weights for policy 0, policy_version 46510 (0.0008) -[2023-10-10 22:37:21,640][98559] Updated weights for policy 0, policy_version 46520 (0.0008) -[2023-10-10 22:37:24,210][98560] Updated weights for policy 1, policy_version 46312 (0.0008) -[2023-10-10 22:37:24,576][98560] Updated weights for policy 1, policy_version 46322 (0.0008) -[2023-10-10 22:37:24,940][98560] Updated weights for policy 1, policy_version 46332 (0.0008) -[2023-10-10 22:37:25,508][98559] Updated weights for policy 0, policy_version 46530 (0.0008) -[2023-10-10 22:37:25,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 95092736. Throughput: 0: 1707.2, 1: 1723.3. Samples: 23776682. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 22:37:25,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.200')] -[2023-10-10 22:37:25,868][98559] Updated weights for policy 0, policy_version 46540 (0.0008) -[2023-10-10 22:37:26,234][98559] Updated weights for policy 0, policy_version 46550 (0.0010) -[2023-10-10 22:37:26,600][98559] Updated weights for policy 0, policy_version 46560 (0.0010) -[2023-10-10 22:37:28,921][98560] Updated weights for policy 1, policy_version 46342 (0.0007) -[2023-10-10 22:37:29,290][98560] Updated weights for policy 1, policy_version 46352 (0.0009) -[2023-10-10 22:37:29,658][98560] Updated weights for policy 1, policy_version 46362 (0.0008) -[2023-10-10 22:37:30,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 95158272. Throughput: 0: 1723.5, 1: 1723.6. Samples: 23797802. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 22:37:30,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.260')] -[2023-10-10 22:37:30,750][98559] Updated weights for policy 0, policy_version 46570 (0.0008) -[2023-10-10 22:37:31,126][98559] Updated weights for policy 0, policy_version 46580 (0.0008) -[2023-10-10 22:37:31,484][98559] Updated weights for policy 0, policy_version 46590 (0.0007) -[2023-10-10 22:37:33,531][98560] Updated weights for policy 1, policy_version 46372 (0.0009) -[2023-10-10 22:37:33,911][98560] Updated weights for policy 1, policy_version 46382 (0.0008) -[2023-10-10 22:37:34,288][98560] Updated weights for policy 1, policy_version 46392 (0.0009) -[2023-10-10 22:37:35,444][98559] Updated weights for policy 0, policy_version 46600 (0.0007) -[2023-10-10 22:37:35,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 95223808. Throughput: 0: 1722.2, 1: 1697.7. Samples: 23817758. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 22:37:35,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.280')] -[2023-10-10 22:37:35,816][98559] Updated weights for policy 0, policy_version 46610 (0.0007) -[2023-10-10 22:37:36,191][98559] Updated weights for policy 0, policy_version 46620 (0.0009) -[2023-10-10 22:37:38,407][98560] Updated weights for policy 1, policy_version 46402 (0.0010) -[2023-10-10 22:37:38,769][98560] Updated weights for policy 1, policy_version 46412 (0.0010) -[2023-10-10 22:37:39,146][98560] Updated weights for policy 1, policy_version 46422 (0.0009) -[2023-10-10 22:37:39,515][98560] Updated weights for policy 1, policy_version 46432 (0.0009) -[2023-10-10 22:37:40,197][98559] Updated weights for policy 0, policy_version 46630 (0.0008) -[2023-10-10 22:37:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 95289344. Throughput: 0: 1728.1, 1: 1725.0. Samples: 23828590. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 22:37:40,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.280')] -[2023-10-10 22:37:40,575][98559] Updated weights for policy 0, policy_version 46640 (0.0008) -[2023-10-10 22:37:40,935][98559] Updated weights for policy 0, policy_version 46650 (0.0009) -[2023-10-10 22:37:43,529][98560] Updated weights for policy 1, policy_version 46442 (0.0008) -[2023-10-10 22:37:43,896][98560] Updated weights for policy 1, policy_version 46452 (0.0007) -[2023-10-10 22:37:44,268][98560] Updated weights for policy 1, policy_version 46462 (0.0008) -[2023-10-10 22:37:44,741][98559] Updated weights for policy 0, policy_version 46660 (0.0007) -[2023-10-10 22:37:45,110][98559] Updated weights for policy 0, policy_version 46670 (0.0007) -[2023-10-10 22:37:45,471][98559] Updated weights for policy 0, policy_version 46680 (0.0008) -[2023-10-10 22:37:45,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 95354880. Throughput: 0: 1726.1, 1: 1709.8. Samples: 23849200. Policy #0 lag: (min: 19.0, avg: 38.4, max: 40.0) -[2023-10-10 22:37:45,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.260')] -[2023-10-10 22:37:48,255][98560] Updated weights for policy 1, policy_version 46472 (0.0010) -[2023-10-10 22:37:48,620][98560] Updated weights for policy 1, policy_version 46482 (0.0010) -[2023-10-10 22:37:48,985][98560] Updated weights for policy 1, policy_version 46492 (0.0010) -[2023-10-10 22:37:49,581][98559] Updated weights for policy 0, policy_version 46690 (0.0008) -[2023-10-10 22:37:49,948][98559] Updated weights for policy 0, policy_version 46700 (0.0009) -[2023-10-10 22:37:50,316][98559] Updated weights for policy 0, policy_version 46710 (0.0009) -[2023-10-10 22:37:50,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 95420416. Throughput: 0: 1706.4, 1: 1689.2. Samples: 23868540. Policy #0 lag: (min: 19.0, avg: 38.4, max: 40.0) -[2023-10-10 22:37:50,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.260')] -[2023-10-10 22:37:50,676][98559] Updated weights for policy 0, policy_version 46720 (0.0008) -[2023-10-10 22:37:53,115][98560] Updated weights for policy 1, policy_version 46502 (0.0008) -[2023-10-10 22:37:53,501][98560] Updated weights for policy 1, policy_version 46512 (0.0010) -[2023-10-10 22:37:53,874][98560] Updated weights for policy 1, policy_version 46522 (0.0009) -[2023-10-10 22:37:54,531][98559] Updated weights for policy 0, policy_version 46730 (0.0010) -[2023-10-10 22:37:54,906][98559] Updated weights for policy 0, policy_version 46740 (0.0008) -[2023-10-10 22:37:55,268][98559] Updated weights for policy 0, policy_version 46750 (0.0009) -[2023-10-10 22:37:55,556][97672] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 95518720. Throughput: 0: 1726.0, 1: 1721.6. Samples: 23880156. Policy #0 lag: (min: 19.0, avg: 38.4, max: 40.0) -[2023-10-10 22:37:55,556][97672] Avg episode reward: [(0, '-0.940'), (1, '22.220')] -[2023-10-10 22:37:57,791][98560] Updated weights for policy 1, policy_version 46532 (0.0009) -[2023-10-10 22:37:58,167][98560] Updated weights for policy 1, policy_version 46542 (0.0010) -[2023-10-10 22:37:58,521][98560] Updated weights for policy 1, policy_version 46552 (0.0010) -[2023-10-10 22:37:59,111][98559] Updated weights for policy 0, policy_version 46760 (0.0007) -[2023-10-10 22:37:59,475][98559] Updated weights for policy 0, policy_version 46770 (0.0008) -[2023-10-10 22:37:59,839][98559] Updated weights for policy 0, policy_version 46780 (0.0009) -[2023-10-10 22:38:00,556][97672] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 95584256. Throughput: 0: 1721.1, 1: 1688.4. Samples: 23899660. Policy #0 lag: (min: 19.0, avg: 38.4, max: 40.0) -[2023-10-10 22:38:00,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.260')] -[2023-10-10 22:38:02,470][98560] Updated weights for policy 1, policy_version 46562 (0.0009) -[2023-10-10 22:38:02,838][98560] Updated weights for policy 1, policy_version 46572 (0.0009) -[2023-10-10 22:38:03,204][98560] Updated weights for policy 1, policy_version 46582 (0.0007) -[2023-10-10 22:38:03,572][98560] Updated weights for policy 1, policy_version 46592 (0.0007) -[2023-10-10 22:38:03,831][98559] Updated weights for policy 0, policy_version 46790 (0.0008) -[2023-10-10 22:38:04,194][98559] Updated weights for policy 0, policy_version 46800 (0.0008) -[2023-10-10 22:38:04,566][98559] Updated weights for policy 0, policy_version 46810 (0.0009) -[2023-10-10 22:38:05,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13662.7). Total num frames: 95649792. Throughput: 0: 1700.9, 1: 1697.2. Samples: 23919842. Policy #0 lag: (min: 19.0, avg: 38.4, max: 40.0) -[2023-10-10 22:38:05,556][97672] Avg episode reward: [(0, '-0.960'), (1, '22.340')] -[2023-10-10 22:38:07,664][98560] Updated weights for policy 1, policy_version 46602 (0.0009) -[2023-10-10 22:38:08,034][98560] Updated weights for policy 1, policy_version 46612 (0.0008) -[2023-10-10 22:38:08,403][98560] Updated weights for policy 1, policy_version 46622 (0.0009) -[2023-10-10 22:38:08,606][98559] Updated weights for policy 0, policy_version 46820 (0.0007) -[2023-10-10 22:38:09,000][98559] Updated weights for policy 0, policy_version 46830 (0.0008) -[2023-10-10 22:38:09,378][98559] Updated weights for policy 0, policy_version 46840 (0.0008) -[2023-10-10 22:38:10,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 95715328. Throughput: 0: 1737.3, 1: 1700.4. Samples: 23931382. Policy #0 lag: (min: 19.0, avg: 38.4, max: 40.0) -[2023-10-10 22:38:10,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.340')] -[2023-10-10 22:38:12,485][98560] Updated weights for policy 1, policy_version 46632 (0.0009) -[2023-10-10 22:38:12,847][98560] Updated weights for policy 1, policy_version 46642 (0.0009) -[2023-10-10 22:38:13,210][98560] Updated weights for policy 1, policy_version 46652 (0.0009) -[2023-10-10 22:38:13,312][98559] Updated weights for policy 0, policy_version 46850 (0.0009) -[2023-10-10 22:38:13,690][98559] Updated weights for policy 0, policy_version 46860 (0.0009) -[2023-10-10 22:38:14,064][98559] Updated weights for policy 0, policy_version 46870 (0.0009) -[2023-10-10 22:38:14,431][98559] Updated weights for policy 0, policy_version 46880 (0.0008) -[2023-10-10 22:38:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 95780864. Throughput: 0: 1710.9, 1: 1675.4. Samples: 23950186. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-10 22:38:15,556][97672] Avg episode reward: [(0, '-0.940'), (1, '22.300')] -[2023-10-10 22:38:17,237][98560] Updated weights for policy 1, policy_version 46662 (0.0009) -[2023-10-10 22:38:17,598][98560] Updated weights for policy 1, policy_version 46672 (0.0008) -[2023-10-10 22:38:17,971][98560] Updated weights for policy 1, policy_version 46682 (0.0009) -[2023-10-10 22:38:18,350][98559] Updated weights for policy 0, policy_version 46890 (0.0007) -[2023-10-10 22:38:18,713][98559] Updated weights for policy 0, policy_version 46900 (0.0010) -[2023-10-10 22:38:19,082][98559] Updated weights for policy 0, policy_version 46910 (0.0008) -[2023-10-10 22:38:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 95846400. Throughput: 0: 1707.6, 1: 1703.4. Samples: 23971252. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-10 22:38:20,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.360')] -[2023-10-10 22:38:21,926][98560] Updated weights for policy 1, policy_version 46692 (0.0008) -[2023-10-10 22:38:22,302][98560] Updated weights for policy 1, policy_version 46702 (0.0007) -[2023-10-10 22:38:22,674][98560] Updated weights for policy 1, policy_version 46712 (0.0007) -[2023-10-10 22:38:22,984][98559] Updated weights for policy 0, policy_version 46920 (0.0010) -[2023-10-10 22:38:23,351][98559] Updated weights for policy 0, policy_version 46930 (0.0008) -[2023-10-10 22:38:23,721][98559] Updated weights for policy 0, policy_version 46940 (0.0007) -[2023-10-10 22:38:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 95911936. Throughput: 0: 1716.9, 1: 1677.0. Samples: 23981316. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-10 22:38:25,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.340')] -[2023-10-10 22:38:26,651][98560] Updated weights for policy 1, policy_version 46722 (0.0008) -[2023-10-10 22:38:27,011][98560] Updated weights for policy 1, policy_version 46732 (0.0007) -[2023-10-10 22:38:27,382][98560] Updated weights for policy 1, policy_version 46742 (0.0007) -[2023-10-10 22:38:27,682][98559] Updated weights for policy 0, policy_version 46950 (0.0008) -[2023-10-10 22:38:27,740][98560] Updated weights for policy 1, policy_version 46752 (0.0007) -[2023-10-10 22:38:28,050][98559] Updated weights for policy 0, policy_version 46960 (0.0010) -[2023-10-10 22:38:28,420][98559] Updated weights for policy 0, policy_version 46970 (0.0009) -[2023-10-10 22:38:30,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 95977472. Throughput: 0: 1701.0, 1: 1685.2. Samples: 24001576. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-10 22:38:30,556][97672] Avg episode reward: [(0, '-0.960'), (1, '22.260')] -[2023-10-10 22:38:31,874][98560] Updated weights for policy 1, policy_version 46762 (0.0007) -[2023-10-10 22:38:32,241][98560] Updated weights for policy 1, policy_version 46772 (0.0007) -[2023-10-10 22:38:32,466][98559] Updated weights for policy 0, policy_version 46980 (0.0007) -[2023-10-10 22:38:32,616][98560] Updated weights for policy 1, policy_version 46782 (0.0008) -[2023-10-10 22:38:32,829][98559] Updated weights for policy 0, policy_version 46990 (0.0008) -[2023-10-10 22:38:33,197][98559] Updated weights for policy 0, policy_version 47000 (0.0007) -[2023-10-10 22:38:35,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 96043008. Throughput: 0: 1718.0, 1: 1699.4. Samples: 24022322. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-10 22:38:35,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.280')] -[2023-10-10 22:38:35,568][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000047008_48136192.pth... -[2023-10-10 22:38:35,568][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000046784_47906816.pth... -[2023-10-10 22:38:35,622][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000045408_46497792.pth -[2023-10-10 22:38:35,623][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000045184_46268416.pth -[2023-10-10 22:38:36,600][98560] Updated weights for policy 1, policy_version 46792 (0.0008) -[2023-10-10 22:38:36,971][98560] Updated weights for policy 1, policy_version 46802 (0.0009) -[2023-10-10 22:38:37,171][98559] Updated weights for policy 0, policy_version 47010 (0.0008) -[2023-10-10 22:38:37,334][98560] Updated weights for policy 1, policy_version 46812 (0.0007) -[2023-10-10 22:38:37,532][98559] Updated weights for policy 0, policy_version 47020 (0.0009) -[2023-10-10 22:38:37,900][98559] Updated weights for policy 0, policy_version 47030 (0.0010) -[2023-10-10 22:38:38,265][98559] Updated weights for policy 0, policy_version 47040 (0.0007) -[2023-10-10 22:38:40,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 96108544. Throughput: 0: 1695.9, 1: 1668.4. Samples: 24031552. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-10 22:38:40,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.240')] -[2023-10-10 22:38:41,367][98560] Updated weights for policy 1, policy_version 46822 (0.0010) -[2023-10-10 22:38:41,727][98560] Updated weights for policy 1, policy_version 46832 (0.0008) -[2023-10-10 22:38:42,102][98560] Updated weights for policy 1, policy_version 46842 (0.0008) -[2023-10-10 22:38:42,330][98559] Updated weights for policy 0, policy_version 47050 (0.0009) -[2023-10-10 22:38:42,694][98559] Updated weights for policy 0, policy_version 47060 (0.0008) -[2023-10-10 22:38:43,058][98559] Updated weights for policy 0, policy_version 47070 (0.0010) -[2023-10-10 22:38:45,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 96174080. Throughput: 0: 1698.9, 1: 1699.1. Samples: 24052572. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-10 22:38:45,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.200')] -[2023-10-10 22:38:46,226][98560] Updated weights for policy 1, policy_version 46852 (0.0010) -[2023-10-10 22:38:46,620][98560] Updated weights for policy 1, policy_version 46862 (0.0009) -[2023-10-10 22:38:46,993][98560] Updated weights for policy 1, policy_version 46872 (0.0009) -[2023-10-10 22:38:47,091][98559] Updated weights for policy 0, policy_version 47080 (0.0008) -[2023-10-10 22:38:47,464][98559] Updated weights for policy 0, policy_version 47090 (0.0007) -[2023-10-10 22:38:47,835][98559] Updated weights for policy 0, policy_version 47100 (0.0007) -[2023-10-10 22:38:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 96239616. Throughput: 0: 1715.8, 1: 1698.0. Samples: 24073464. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-10 22:38:50,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.180')] -[2023-10-10 22:38:50,942][98560] Updated weights for policy 1, policy_version 46882 (0.0008) -[2023-10-10 22:38:51,314][98560] Updated weights for policy 1, policy_version 46892 (0.0008) -[2023-10-10 22:38:51,681][98560] Updated weights for policy 1, policy_version 46902 (0.0007) -[2023-10-10 22:38:51,891][98559] Updated weights for policy 0, policy_version 47110 (0.0008) -[2023-10-10 22:38:52,058][98560] Updated weights for policy 1, policy_version 46912 (0.0009) -[2023-10-10 22:38:52,253][98559] Updated weights for policy 0, policy_version 47120 (0.0007) -[2023-10-10 22:38:52,625][98559] Updated weights for policy 0, policy_version 47130 (0.0007) -[2023-10-10 22:38:55,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 96305152. Throughput: 0: 1683.3, 1: 1678.6. Samples: 24082668. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-10 22:38:55,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.220')] -[2023-10-10 22:38:56,127][98560] Updated weights for policy 1, policy_version 46922 (0.0009) -[2023-10-10 22:38:56,491][98560] Updated weights for policy 1, policy_version 46932 (0.0010) -[2023-10-10 22:38:56,763][98559] Updated weights for policy 0, policy_version 47140 (0.0010) -[2023-10-10 22:38:56,857][98560] Updated weights for policy 1, policy_version 46942 (0.0008) -[2023-10-10 22:38:57,146][98559] Updated weights for policy 0, policy_version 47150 (0.0009) -[2023-10-10 22:38:57,518][98559] Updated weights for policy 0, policy_version 47160 (0.0008) -[2023-10-10 22:39:00,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 96370688. Throughput: 0: 1706.0, 1: 1697.3. Samples: 24103334. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-10 22:39:00,556][97672] Avg episode reward: [(0, '-0.980'), (1, '22.140')] -[2023-10-10 22:39:00,960][98560] Updated weights for policy 1, policy_version 46952 (0.0009) -[2023-10-10 22:39:01,328][98560] Updated weights for policy 1, policy_version 46962 (0.0009) -[2023-10-10 22:39:01,454][98559] Updated weights for policy 0, policy_version 47170 (0.0008) -[2023-10-10 22:39:01,687][98560] Updated weights for policy 1, policy_version 46972 (0.0009) -[2023-10-10 22:39:01,819][98559] Updated weights for policy 0, policy_version 47180 (0.0007) -[2023-10-10 22:39:02,190][98559] Updated weights for policy 0, policy_version 47190 (0.0008) -[2023-10-10 22:39:02,554][98559] Updated weights for policy 0, policy_version 47200 (0.0010) -[2023-10-10 22:39:05,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 96436224. Throughput: 0: 1705.8, 1: 1694.1. Samples: 24124248. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-10 22:39:05,556][97672] Avg episode reward: [(0, '-0.980'), (1, '22.060')] -[2023-10-10 22:39:05,692][98560] Updated weights for policy 1, policy_version 46982 (0.0009) -[2023-10-10 22:39:06,072][98560] Updated weights for policy 1, policy_version 46992 (0.0008) -[2023-10-10 22:39:06,441][98560] Updated weights for policy 1, policy_version 47002 (0.0009) -[2023-10-10 22:39:06,578][98559] Updated weights for policy 0, policy_version 47210 (0.0009) -[2023-10-10 22:39:06,945][98559] Updated weights for policy 0, policy_version 47220 (0.0010) -[2023-10-10 22:39:07,324][98559] Updated weights for policy 0, policy_version 47230 (0.0010) -[2023-10-10 22:39:10,462][98560] Updated weights for policy 1, policy_version 47012 (0.0008) -[2023-10-10 22:39:10,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 96501760. Throughput: 0: 1693.2, 1: 1689.6. Samples: 24133540. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-10 22:39:10,556][97672] Avg episode reward: [(0, '-0.980'), (1, '22.100')] -[2023-10-10 22:39:10,822][98560] Updated weights for policy 1, policy_version 47022 (0.0007) -[2023-10-10 22:39:11,193][98560] Updated weights for policy 1, policy_version 47032 (0.0007) -[2023-10-10 22:39:11,339][98559] Updated weights for policy 0, policy_version 47240 (0.0007) -[2023-10-10 22:39:11,701][98559] Updated weights for policy 0, policy_version 47250 (0.0007) -[2023-10-10 22:39:12,069][98559] Updated weights for policy 0, policy_version 47260 (0.0009) -[2023-10-10 22:39:15,219][98560] Updated weights for policy 1, policy_version 47042 (0.0008) -[2023-10-10 22:39:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 96567296. Throughput: 0: 1702.5, 1: 1694.9. Samples: 24154462. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-10 22:39:15,556][97672] Avg episode reward: [(0, '-0.980'), (1, '22.000')] -[2023-10-10 22:39:15,590][98560] Updated weights for policy 1, policy_version 47052 (0.0010) -[2023-10-10 22:39:15,947][98560] Updated weights for policy 1, policy_version 47062 (0.0009) -[2023-10-10 22:39:16,159][98559] Updated weights for policy 0, policy_version 47270 (0.0010) -[2023-10-10 22:39:16,314][98560] Updated weights for policy 1, policy_version 47072 (0.0009) -[2023-10-10 22:39:16,521][98559] Updated weights for policy 0, policy_version 47280 (0.0007) -[2023-10-10 22:39:16,886][98559] Updated weights for policy 0, policy_version 47290 (0.0007) -[2023-10-10 22:39:20,443][98560] Updated weights for policy 1, policy_version 47082 (0.0009) -[2023-10-10 22:39:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 96632832. Throughput: 0: 1704.7, 1: 1699.3. Samples: 24175502. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-10 22:39:20,556][97672] Avg episode reward: [(0, '-0.980'), (1, '21.940')] -[2023-10-10 22:39:20,820][98560] Updated weights for policy 1, policy_version 47092 (0.0008) -[2023-10-10 22:39:21,005][98559] Updated weights for policy 0, policy_version 47300 (0.0008) -[2023-10-10 22:39:21,192][98560] Updated weights for policy 1, policy_version 47102 (0.0009) -[2023-10-10 22:39:21,369][98559] Updated weights for policy 0, policy_version 47310 (0.0009) -[2023-10-10 22:39:21,732][98559] Updated weights for policy 0, policy_version 47320 (0.0008) -[2023-10-10 22:39:25,217][98560] Updated weights for policy 1, policy_version 47112 (0.0009) -[2023-10-10 22:39:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 96698368. Throughput: 0: 1702.5, 1: 1701.2. Samples: 24184722. Policy #0 lag: (min: 2.0, avg: 4.1, max: 34.0) -[2023-10-10 22:39:25,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.020')] -[2023-10-10 22:39:25,587][98560] Updated weights for policy 1, policy_version 47122 (0.0010) -[2023-10-10 22:39:25,698][98559] Updated weights for policy 0, policy_version 47330 (0.0007) -[2023-10-10 22:39:25,951][98560] Updated weights for policy 1, policy_version 47132 (0.0008) -[2023-10-10 22:39:26,054][98559] Updated weights for policy 0, policy_version 47340 (0.0009) -[2023-10-10 22:39:26,425][98559] Updated weights for policy 0, policy_version 47350 (0.0010) -[2023-10-10 22:39:26,797][98559] Updated weights for policy 0, policy_version 47360 (0.0010) -[2023-10-10 22:39:29,976][98560] Updated weights for policy 1, policy_version 47142 (0.0009) -[2023-10-10 22:39:30,339][98560] Updated weights for policy 1, policy_version 47152 (0.0008) -[2023-10-10 22:39:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 96763904. Throughput: 0: 1703.7, 1: 1702.6. Samples: 24205856. Policy #0 lag: (min: 2.0, avg: 4.1, max: 34.0) -[2023-10-10 22:39:30,556][97672] Avg episode reward: [(0, '-0.980'), (1, '22.040')] -[2023-10-10 22:39:30,702][98560] Updated weights for policy 1, policy_version 47162 (0.0008) -[2023-10-10 22:39:30,799][98559] Updated weights for policy 0, policy_version 47370 (0.0008) -[2023-10-10 22:39:31,161][98559] Updated weights for policy 0, policy_version 47380 (0.0010) -[2023-10-10 22:39:31,537][98559] Updated weights for policy 0, policy_version 47390 (0.0009) -[2023-10-10 22:39:34,778][98560] Updated weights for policy 1, policy_version 47172 (0.0008) -[2023-10-10 22:39:35,147][98560] Updated weights for policy 1, policy_version 47182 (0.0007) -[2023-10-10 22:39:35,403][98559] Updated weights for policy 0, policy_version 47400 (0.0009) -[2023-10-10 22:39:35,513][98560] Updated weights for policy 1, policy_version 47192 (0.0007) -[2023-10-10 22:39:35,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 96829440. Throughput: 0: 1701.4, 1: 1697.3. Samples: 24226404. Policy #0 lag: (min: 2.0, avg: 4.1, max: 34.0) -[2023-10-10 22:39:35,556][97672] Avg episode reward: [(0, '-0.980'), (1, '22.100')] -[2023-10-10 22:39:35,766][98559] Updated weights for policy 0, policy_version 47410 (0.0007) -[2023-10-10 22:39:36,138][98559] Updated weights for policy 0, policy_version 47420 (0.0008) -[2023-10-10 22:39:39,420][98560] Updated weights for policy 1, policy_version 47202 (0.0007) -[2023-10-10 22:39:39,792][98560] Updated weights for policy 1, policy_version 47212 (0.0007) -[2023-10-10 22:39:40,084][98559] Updated weights for policy 0, policy_version 47430 (0.0009) -[2023-10-10 22:39:40,151][98560] Updated weights for policy 1, policy_version 47222 (0.0009) -[2023-10-10 22:39:40,444][98559] Updated weights for policy 0, policy_version 47440 (0.0009) -[2023-10-10 22:39:40,520][98560] Updated weights for policy 1, policy_version 47232 (0.0007) -[2023-10-10 22:39:40,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 96927744. Throughput: 0: 1710.6, 1: 1697.7. Samples: 24236040. Policy #0 lag: (min: 2.0, avg: 4.1, max: 34.0) -[2023-10-10 22:39:40,556][97672] Avg episode reward: [(0, '-0.980'), (1, '22.120')] -[2023-10-10 22:39:40,802][98559] Updated weights for policy 0, policy_version 47450 (0.0009) -[2023-10-10 22:39:44,650][98560] Updated weights for policy 1, policy_version 47242 (0.0008) -[2023-10-10 22:39:44,775][98559] Updated weights for policy 0, policy_version 47460 (0.0009) -[2023-10-10 22:39:45,008][98560] Updated weights for policy 1, policy_version 47252 (0.0009) -[2023-10-10 22:39:45,164][98559] Updated weights for policy 0, policy_version 47470 (0.0011) -[2023-10-10 22:39:45,377][98560] Updated weights for policy 1, policy_version 47262 (0.0008) -[2023-10-10 22:39:45,536][98559] Updated weights for policy 0, policy_version 47480 (0.0010) -[2023-10-10 22:39:45,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 96993280. Throughput: 0: 1715.2, 1: 1702.5. Samples: 24257130. Policy #0 lag: (min: 2.0, avg: 4.1, max: 34.0) -[2023-10-10 22:39:45,556][97672] Avg episode reward: [(0, '-0.980'), (1, '21.940')] -[2023-10-10 22:39:49,449][98560] Updated weights for policy 1, policy_version 47272 (0.0008) -[2023-10-10 22:39:49,466][98559] Updated weights for policy 0, policy_version 47490 (0.0010) -[2023-10-10 22:39:49,824][98560] Updated weights for policy 1, policy_version 47282 (0.0009) -[2023-10-10 22:39:49,832][98559] Updated weights for policy 0, policy_version 47500 (0.0009) -[2023-10-10 22:39:50,188][98560] Updated weights for policy 1, policy_version 47292 (0.0008) -[2023-10-10 22:39:50,190][98559] Updated weights for policy 0, policy_version 47510 (0.0008) -[2023-10-10 22:39:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 97058816. Throughput: 0: 1691.5, 1: 1685.8. Samples: 24276226. Policy #0 lag: (min: 2.0, avg: 4.1, max: 34.0) -[2023-10-10 22:39:50,557][97672] Avg episode reward: [(0, '-1.040'), (1, '21.960')] -[2023-10-10 22:39:50,561][98559] Updated weights for policy 0, policy_version 47520 (0.0009) -[2023-10-10 22:39:54,260][98560] Updated weights for policy 1, policy_version 47302 (0.0008) -[2023-10-10 22:39:54,584][98559] Updated weights for policy 0, policy_version 47530 (0.0009) -[2023-10-10 22:39:54,621][98560] Updated weights for policy 1, policy_version 47312 (0.0008) -[2023-10-10 22:39:54,958][98559] Updated weights for policy 0, policy_version 47540 (0.0008) -[2023-10-10 22:39:54,986][98560] Updated weights for policy 1, policy_version 47322 (0.0008) -[2023-10-10 22:39:55,335][98559] Updated weights for policy 0, policy_version 47550 (0.0010) -[2023-10-10 22:39:55,556][97672] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 97157120. Throughput: 0: 1714.3, 1: 1697.7. Samples: 24287082. Policy #0 lag: (min: 17.0, avg: 26.5, max: 49.0) -[2023-10-10 22:39:55,557][97672] Avg episode reward: [(0, '-1.040'), (1, '22.000')] -[2023-10-10 22:39:59,082][98560] Updated weights for policy 1, policy_version 47332 (0.0008) -[2023-10-10 22:39:59,206][98559] Updated weights for policy 0, policy_version 47560 (0.0008) -[2023-10-10 22:39:59,442][98560] Updated weights for policy 1, policy_version 47342 (0.0009) -[2023-10-10 22:39:59,573][98559] Updated weights for policy 0, policy_version 47570 (0.0007) -[2023-10-10 22:39:59,810][98560] Updated weights for policy 1, policy_version 47352 (0.0007) -[2023-10-10 22:39:59,941][98559] Updated weights for policy 0, policy_version 47580 (0.0008) -[2023-10-10 22:40:00,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 97222656. Throughput: 0: 1706.0, 1: 1695.3. Samples: 24307520. Policy #0 lag: (min: 17.0, avg: 26.5, max: 49.0) -[2023-10-10 22:40:00,556][97672] Avg episode reward: [(0, '-1.080'), (1, '21.960')] -[2023-10-10 22:40:03,860][98560] Updated weights for policy 1, policy_version 47362 (0.0008) -[2023-10-10 22:40:03,893][98559] Updated weights for policy 0, policy_version 47590 (0.0007) -[2023-10-10 22:40:04,225][98560] Updated weights for policy 1, policy_version 47372 (0.0008) -[2023-10-10 22:40:04,259][98559] Updated weights for policy 0, policy_version 47600 (0.0009) -[2023-10-10 22:40:04,596][98560] Updated weights for policy 1, policy_version 47382 (0.0008) -[2023-10-10 22:40:04,620][98559] Updated weights for policy 0, policy_version 47610 (0.0008) -[2023-10-10 22:40:04,958][98560] Updated weights for policy 1, policy_version 47392 (0.0007) -[2023-10-10 22:40:05,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 97288192. Throughput: 0: 1692.2, 1: 1670.9. Samples: 24326842. Policy #0 lag: (min: 17.0, avg: 26.5, max: 49.0) -[2023-10-10 22:40:05,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.000')] -[2023-10-10 22:40:08,613][98559] Updated weights for policy 0, policy_version 47620 (0.0008) -[2023-10-10 22:40:08,978][98559] Updated weights for policy 0, policy_version 47630 (0.0008) -[2023-10-10 22:40:09,006][98560] Updated weights for policy 1, policy_version 47402 (0.0008) -[2023-10-10 22:40:09,338][98559] Updated weights for policy 0, policy_version 47640 (0.0008) -[2023-10-10 22:40:09,364][98560] Updated weights for policy 1, policy_version 47412 (0.0009) -[2023-10-10 22:40:09,731][98560] Updated weights for policy 1, policy_version 47422 (0.0009) -[2023-10-10 22:40:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 97353728. Throughput: 0: 1726.7, 1: 1690.9. Samples: 24338512. Policy #0 lag: (min: 17.0, avg: 26.5, max: 49.0) -[2023-10-10 22:40:10,556][97672] Avg episode reward: [(0, '-1.100'), (1, '22.120')] -[2023-10-10 22:40:13,197][98559] Updated weights for policy 0, policy_version 47650 (0.0008) -[2023-10-10 22:40:13,564][98559] Updated weights for policy 0, policy_version 47660 (0.0007) -[2023-10-10 22:40:13,810][98560] Updated weights for policy 1, policy_version 47432 (0.0008) -[2023-10-10 22:40:13,942][98559] Updated weights for policy 0, policy_version 47670 (0.0009) -[2023-10-10 22:40:14,173][98560] Updated weights for policy 1, policy_version 47442 (0.0007) -[2023-10-10 22:40:14,305][98559] Updated weights for policy 0, policy_version 47680 (0.0009) -[2023-10-10 22:40:14,543][98560] Updated weights for policy 1, policy_version 47452 (0.0011) -[2023-10-10 22:40:15,556][97672] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 97419264. Throughput: 0: 1700.1, 1: 1682.3. Samples: 24358064. Policy #0 lag: (min: 17.0, avg: 26.5, max: 49.0) -[2023-10-10 22:40:15,556][97672] Avg episode reward: [(0, '-1.100'), (1, '22.120')] -[2023-10-10 22:40:18,371][98559] Updated weights for policy 0, policy_version 47690 (0.0008) -[2023-10-10 22:40:18,739][98559] Updated weights for policy 0, policy_version 47700 (0.0009) -[2023-10-10 22:40:18,740][98560] Updated weights for policy 1, policy_version 47462 (0.0010) -[2023-10-10 22:40:19,107][98559] Updated weights for policy 0, policy_version 47710 (0.0009) -[2023-10-10 22:40:19,109][98560] Updated weights for policy 1, policy_version 47472 (0.0009) -[2023-10-10 22:40:19,470][98560] Updated weights for policy 1, policy_version 47482 (0.0008) -[2023-10-10 22:40:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 97484800. Throughput: 0: 1704.8, 1: 1660.2. Samples: 24377826. Policy #0 lag: (min: 17.0, avg: 26.5, max: 49.0) -[2023-10-10 22:40:20,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.120')] -[2023-10-10 22:40:23,078][98559] Updated weights for policy 0, policy_version 47720 (0.0011) -[2023-10-10 22:40:23,440][98559] Updated weights for policy 0, policy_version 47730 (0.0008) -[2023-10-10 22:40:23,614][98560] Updated weights for policy 1, policy_version 47492 (0.0009) -[2023-10-10 22:40:23,810][98559] Updated weights for policy 0, policy_version 47740 (0.0007) -[2023-10-10 22:40:24,019][98560] Updated weights for policy 1, policy_version 47502 (0.0008) -[2023-10-10 22:40:24,387][98560] Updated weights for policy 1, policy_version 47512 (0.0009) -[2023-10-10 22:40:25,556][97672] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 97550336. Throughput: 0: 1710.2, 1: 1688.5. Samples: 24388984. Policy #0 lag: (min: 17.0, avg: 26.5, max: 49.0) -[2023-10-10 22:40:25,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.180')] -[2023-10-10 22:40:27,803][98559] Updated weights for policy 0, policy_version 47750 (0.0008) -[2023-10-10 22:40:28,166][98559] Updated weights for policy 0, policy_version 47760 (0.0009) -[2023-10-10 22:40:28,411][98560] Updated weights for policy 1, policy_version 47522 (0.0010) -[2023-10-10 22:40:28,527][98559] Updated weights for policy 0, policy_version 47770 (0.0009) -[2023-10-10 22:40:28,775][98560] Updated weights for policy 1, policy_version 47532 (0.0008) -[2023-10-10 22:40:29,144][98560] Updated weights for policy 1, policy_version 47542 (0.0007) -[2023-10-10 22:40:29,514][98560] Updated weights for policy 1, policy_version 47552 (0.0009) -[2023-10-10 22:40:30,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 97615872. Throughput: 0: 1693.5, 1: 1676.6. Samples: 24408784. Policy #0 lag: (min: 4.0, avg: 5.5, max: 30.0) -[2023-10-10 22:40:30,556][97672] Avg episode reward: [(0, '-1.100'), (1, '22.100')] -[2023-10-10 22:40:32,670][98559] Updated weights for policy 0, policy_version 47780 (0.0009) -[2023-10-10 22:40:33,055][98559] Updated weights for policy 0, policy_version 47790 (0.0008) -[2023-10-10 22:40:33,417][98559] Updated weights for policy 0, policy_version 47800 (0.0009) -[2023-10-10 22:40:33,457][98560] Updated weights for policy 1, policy_version 47562 (0.0008) -[2023-10-10 22:40:33,824][98560] Updated weights for policy 1, policy_version 47572 (0.0008) -[2023-10-10 22:40:34,180][98560] Updated weights for policy 1, policy_version 47582 (0.0008) -[2023-10-10 22:40:35,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 97681408. Throughput: 0: 1720.0, 1: 1673.8. Samples: 24428946. Policy #0 lag: (min: 4.0, avg: 5.5, max: 30.0) -[2023-10-10 22:40:35,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.200')] -[2023-10-10 22:40:35,567][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000047808_48955392.pth... -[2023-10-10 22:40:35,567][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000047584_48726016.pth... -[2023-10-10 22:40:35,603][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000045984_47087616.pth -[2023-10-10 22:40:35,606][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000046208_47316992.pth -[2023-10-10 22:40:35,607][98439] Saving a milestone ./train_atari/atari_doubledunk_APPO/checkpoint_p1/milestones/checkpoint_000047584_48726016.pth -[2023-10-10 22:40:35,612][98385] Saving a milestone ./train_atari/atari_doubledunk_APPO/checkpoint_p0/milestones/checkpoint_000047808_48955392.pth -[2023-10-10 22:40:37,211][98559] Updated weights for policy 0, policy_version 47810 (0.0008) -[2023-10-10 22:40:37,577][98559] Updated weights for policy 0, policy_version 47820 (0.0007) -[2023-10-10 22:40:37,954][98559] Updated weights for policy 0, policy_version 47830 (0.0008) -[2023-10-10 22:40:38,138][98560] Updated weights for policy 1, policy_version 47592 (0.0007) -[2023-10-10 22:40:38,313][98559] Updated weights for policy 0, policy_version 47840 (0.0009) -[2023-10-10 22:40:38,511][98560] Updated weights for policy 1, policy_version 47602 (0.0007) -[2023-10-10 22:40:38,881][98560] Updated weights for policy 1, policy_version 47612 (0.0008) -[2023-10-10 22:40:40,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 97746944. Throughput: 0: 1697.8, 1: 1689.6. Samples: 24439512. Policy #0 lag: (min: 4.0, avg: 5.5, max: 30.0) -[2023-10-10 22:40:40,556][97672] Avg episode reward: [(0, '-1.100'), (1, '22.300')] -[2023-10-10 22:40:42,265][98559] Updated weights for policy 0, policy_version 47850 (0.0010) -[2023-10-10 22:40:42,636][98559] Updated weights for policy 0, policy_version 47860 (0.0008) -[2023-10-10 22:40:43,001][98559] Updated weights for policy 0, policy_version 47870 (0.0009) -[2023-10-10 22:40:43,157][98560] Updated weights for policy 1, policy_version 47622 (0.0009) -[2023-10-10 22:40:43,523][98560] Updated weights for policy 1, policy_version 47632 (0.0008) -[2023-10-10 22:40:43,884][98560] Updated weights for policy 1, policy_version 47642 (0.0011) -[2023-10-10 22:40:45,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 97812480. Throughput: 0: 1708.4, 1: 1668.3. Samples: 24459470. Policy #0 lag: (min: 4.0, avg: 5.5, max: 30.0) -[2023-10-10 22:40:45,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.300')] -[2023-10-10 22:40:46,998][98559] Updated weights for policy 0, policy_version 47880 (0.0007) -[2023-10-10 22:40:47,362][98559] Updated weights for policy 0, policy_version 47890 (0.0008) -[2023-10-10 22:40:47,738][98559] Updated weights for policy 0, policy_version 47900 (0.0008) -[2023-10-10 22:40:47,949][98560] Updated weights for policy 1, policy_version 47652 (0.0008) -[2023-10-10 22:40:48,329][98560] Updated weights for policy 1, policy_version 47662 (0.0011) -[2023-10-10 22:40:48,702][98560] Updated weights for policy 1, policy_version 47672 (0.0008) -[2023-10-10 22:40:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 97878016. Throughput: 0: 1722.9, 1: 1677.4. Samples: 24479854. Policy #0 lag: (min: 4.0, avg: 5.5, max: 30.0) -[2023-10-10 22:40:50,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.320')] -[2023-10-10 22:40:51,621][98559] Updated weights for policy 0, policy_version 47910 (0.0008) -[2023-10-10 22:40:51,994][98559] Updated weights for policy 0, policy_version 47920 (0.0007) -[2023-10-10 22:40:52,360][98559] Updated weights for policy 0, policy_version 47930 (0.0008) -[2023-10-10 22:40:52,731][98560] Updated weights for policy 1, policy_version 47682 (0.0009) -[2023-10-10 22:40:53,101][98560] Updated weights for policy 1, policy_version 47692 (0.0010) -[2023-10-10 22:40:53,459][98560] Updated weights for policy 1, policy_version 47702 (0.0008) -[2023-10-10 22:40:53,834][98560] Updated weights for policy 1, policy_version 47712 (0.0008) -[2023-10-10 22:40:55,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 97943552. Throughput: 0: 1690.6, 1: 1688.6. Samples: 24490578. Policy #0 lag: (min: 4.0, avg: 5.5, max: 30.0) -[2023-10-10 22:40:55,557][97672] Avg episode reward: [(0, '-1.120'), (1, '22.360')] -[2023-10-10 22:40:56,332][98559] Updated weights for policy 0, policy_version 47940 (0.0009) -[2023-10-10 22:40:56,710][98559] Updated weights for policy 0, policy_version 47950 (0.0009) -[2023-10-10 22:40:57,082][98559] Updated weights for policy 0, policy_version 47960 (0.0008) -[2023-10-10 22:40:57,879][98560] Updated weights for policy 1, policy_version 47722 (0.0010) -[2023-10-10 22:40:58,242][98560] Updated weights for policy 1, policy_version 47732 (0.0008) -[2023-10-10 22:40:58,612][98560] Updated weights for policy 1, policy_version 47742 (0.0009) -[2023-10-10 22:41:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 98009088. Throughput: 0: 1723.4, 1: 1665.5. Samples: 24510562. Policy #0 lag: (min: 4.0, avg: 5.5, max: 30.0) -[2023-10-10 22:41:00,557][97672] Avg episode reward: [(0, '-1.120'), (1, '22.340')] -[2023-10-10 22:41:00,978][98559] Updated weights for policy 0, policy_version 47970 (0.0009) -[2023-10-10 22:41:01,347][98559] Updated weights for policy 0, policy_version 47980 (0.0007) -[2023-10-10 22:41:01,707][98559] Updated weights for policy 0, policy_version 47990 (0.0008) -[2023-10-10 22:41:02,075][98559] Updated weights for policy 0, policy_version 48000 (0.0009) -[2023-10-10 22:41:02,751][98560] Updated weights for policy 1, policy_version 47752 (0.0009) -[2023-10-10 22:41:03,120][98560] Updated weights for policy 1, policy_version 47762 (0.0009) -[2023-10-10 22:41:03,480][98560] Updated weights for policy 1, policy_version 47772 (0.0008) -[2023-10-10 22:41:05,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 98074624. Throughput: 0: 1722.8, 1: 1691.8. Samples: 24531482. Policy #0 lag: (min: 17.0, avg: 17.0, max: 17.0) -[2023-10-10 22:41:05,558][97672] Avg episode reward: [(0, '-1.120'), (1, '22.300')] -[2023-10-10 22:41:06,064][98559] Updated weights for policy 0, policy_version 48010 (0.0008) -[2023-10-10 22:41:06,431][98559] Updated weights for policy 0, policy_version 48020 (0.0009) -[2023-10-10 22:41:06,786][98559] Updated weights for policy 0, policy_version 48030 (0.0009) -[2023-10-10 22:41:07,415][98560] Updated weights for policy 1, policy_version 47782 (0.0009) -[2023-10-10 22:41:07,790][98560] Updated weights for policy 1, policy_version 47792 (0.0009) -[2023-10-10 22:41:08,157][98560] Updated weights for policy 1, policy_version 47802 (0.0008) -[2023-10-10 22:41:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 98140160. Throughput: 0: 1706.5, 1: 1680.7. Samples: 24541410. Policy #0 lag: (min: 17.0, avg: 17.0, max: 17.0) -[2023-10-10 22:41:10,557][97672] Avg episode reward: [(0, '-1.120'), (1, '22.320')] -[2023-10-10 22:41:10,819][98559] Updated weights for policy 0, policy_version 48040 (0.0009) -[2023-10-10 22:41:11,172][98559] Updated weights for policy 0, policy_version 48050 (0.0011) -[2023-10-10 22:41:11,546][98559] Updated weights for policy 0, policy_version 48060 (0.0008) -[2023-10-10 22:41:12,056][98560] Updated weights for policy 1, policy_version 47812 (0.0007) -[2023-10-10 22:41:12,427][98560] Updated weights for policy 1, policy_version 47822 (0.0009) -[2023-10-10 22:41:12,809][98560] Updated weights for policy 1, policy_version 47832 (0.0009) -[2023-10-10 22:41:15,403][98559] Updated weights for policy 0, policy_version 48070 (0.0008) -[2023-10-10 22:41:15,556][97672] Fps is (10 sec: 13107.8, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 98205696. Throughput: 0: 1725.5, 1: 1679.8. Samples: 24562022. Policy #0 lag: (min: 17.0, avg: 17.0, max: 17.0) -[2023-10-10 22:41:15,556][97672] Avg episode reward: [(0, '-1.120'), (1, '22.360')] -[2023-10-10 22:41:15,775][98559] Updated weights for policy 0, policy_version 48080 (0.0007) -[2023-10-10 22:41:16,150][98559] Updated weights for policy 0, policy_version 48090 (0.0009) -[2023-10-10 22:41:16,842][98560] Updated weights for policy 1, policy_version 47842 (0.0010) -[2023-10-10 22:41:17,245][98560] Updated weights for policy 1, policy_version 47852 (0.0009) -[2023-10-10 22:41:17,617][98560] Updated weights for policy 1, policy_version 47862 (0.0010) -[2023-10-10 22:41:17,981][98560] Updated weights for policy 1, policy_version 47872 (0.0008) -[2023-10-10 22:41:20,400][98559] Updated weights for policy 0, policy_version 48100 (0.0009) -[2023-10-10 22:41:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 98271232. Throughput: 0: 1720.4, 1: 1697.6. Samples: 24582756. Policy #0 lag: (min: 17.0, avg: 17.0, max: 17.0) -[2023-10-10 22:41:20,557][97672] Avg episode reward: [(0, '-1.120'), (1, '22.420')] -[2023-10-10 22:41:20,792][98559] Updated weights for policy 0, policy_version 48110 (0.0009) -[2023-10-10 22:41:21,162][98559] Updated weights for policy 0, policy_version 48120 (0.0008) -[2023-10-10 22:41:21,933][98560] Updated weights for policy 1, policy_version 47882 (0.0007) -[2023-10-10 22:41:22,300][98560] Updated weights for policy 1, policy_version 47892 (0.0007) -[2023-10-10 22:41:22,661][98560] Updated weights for policy 1, policy_version 47902 (0.0007) -[2023-10-10 22:41:25,026][98559] Updated weights for policy 0, policy_version 48130 (0.0009) -[2023-10-10 22:41:25,390][98559] Updated weights for policy 0, policy_version 48140 (0.0009) -[2023-10-10 22:41:25,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 98336768. Throughput: 0: 1724.0, 1: 1674.6. Samples: 24592450. Policy #0 lag: (min: 17.0, avg: 17.0, max: 17.0) -[2023-10-10 22:41:25,556][97672] Avg episode reward: [(0, '-1.120'), (1, '22.400')] -[2023-10-10 22:41:25,752][98559] Updated weights for policy 0, policy_version 48150 (0.0009) -[2023-10-10 22:41:26,117][98559] Updated weights for policy 0, policy_version 48160 (0.0010) -[2023-10-10 22:41:26,531][98560] Updated weights for policy 1, policy_version 47912 (0.0008) -[2023-10-10 22:41:26,892][98560] Updated weights for policy 1, policy_version 47922 (0.0008) -[2023-10-10 22:41:27,267][98560] Updated weights for policy 1, policy_version 47932 (0.0011) -[2023-10-10 22:41:30,177][98559] Updated weights for policy 0, policy_version 48170 (0.0009) -[2023-10-10 22:41:30,542][98559] Updated weights for policy 0, policy_version 48180 (0.0007) -[2023-10-10 22:41:30,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 98402304. Throughput: 0: 1725.4, 1: 1696.9. Samples: 24613474. Policy #0 lag: (min: 17.0, avg: 17.0, max: 17.0) -[2023-10-10 22:41:30,556][97672] Avg episode reward: [(0, '-1.160'), (1, '22.420')] -[2023-10-10 22:41:30,909][98559] Updated weights for policy 0, policy_version 48190 (0.0007) -[2023-10-10 22:41:31,226][98560] Updated weights for policy 1, policy_version 47942 (0.0009) -[2023-10-10 22:41:31,602][98560] Updated weights for policy 1, policy_version 47952 (0.0007) -[2023-10-10 22:41:31,978][98560] Updated weights for policy 1, policy_version 47962 (0.0007) -[2023-10-10 22:41:34,916][98559] Updated weights for policy 0, policy_version 48200 (0.0007) -[2023-10-10 22:41:35,279][98559] Updated weights for policy 0, policy_version 48210 (0.0009) -[2023-10-10 22:41:35,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 98467840. Throughput: 0: 1706.1, 1: 1711.7. Samples: 24633658. Policy #0 lag: (min: 17.0, avg: 17.0, max: 17.0) -[2023-10-10 22:41:35,556][97672] Avg episode reward: [(0, '-1.160'), (1, '22.400')] -[2023-10-10 22:41:35,651][98559] Updated weights for policy 0, policy_version 48220 (0.0008) -[2023-10-10 22:41:36,071][98560] Updated weights for policy 1, policy_version 47972 (0.0008) -[2023-10-10 22:41:36,442][98560] Updated weights for policy 1, policy_version 47982 (0.0008) -[2023-10-10 22:41:36,805][98560] Updated weights for policy 1, policy_version 47992 (0.0008) -[2023-10-10 22:41:39,769][98559] Updated weights for policy 0, policy_version 48230 (0.0009) -[2023-10-10 22:41:40,130][98559] Updated weights for policy 0, policy_version 48240 (0.0009) -[2023-10-10 22:41:40,502][98559] Updated weights for policy 0, policy_version 48250 (0.0010) -[2023-10-10 22:41:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 98533376. Throughput: 0: 1723.1, 1: 1680.6. Samples: 24643744. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-10 22:41:40,556][97672] Avg episode reward: [(0, '-1.160'), (1, '22.420')] -[2023-10-10 22:41:40,581][98560] Updated weights for policy 1, policy_version 48002 (0.0009) -[2023-10-10 22:41:40,949][98560] Updated weights for policy 1, policy_version 48012 (0.0007) -[2023-10-10 22:41:41,317][98560] Updated weights for policy 1, policy_version 48022 (0.0008) -[2023-10-10 22:41:41,680][98560] Updated weights for policy 1, policy_version 48032 (0.0007) -[2023-10-10 22:41:44,457][98559] Updated weights for policy 0, policy_version 48260 (0.0009) -[2023-10-10 22:41:44,830][98559] Updated weights for policy 0, policy_version 48270 (0.0008) -[2023-10-10 22:41:45,188][98559] Updated weights for policy 0, policy_version 48280 (0.0007) -[2023-10-10 22:41:45,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 98631680. Throughput: 0: 1719.2, 1: 1710.3. Samples: 24664890. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-10 22:41:45,556][97672] Avg episode reward: [(0, '-1.120'), (1, '22.320')] -[2023-10-10 22:41:45,760][98560] Updated weights for policy 1, policy_version 48042 (0.0009) -[2023-10-10 22:41:46,128][98560] Updated weights for policy 1, policy_version 48052 (0.0007) -[2023-10-10 22:41:46,497][98560] Updated weights for policy 1, policy_version 48062 (0.0009) -[2023-10-10 22:41:49,176][98559] Updated weights for policy 0, policy_version 48290 (0.0008) -[2023-10-10 22:41:49,545][98559] Updated weights for policy 0, policy_version 48300 (0.0008) -[2023-10-10 22:41:49,904][98559] Updated weights for policy 0, policy_version 48310 (0.0009) -[2023-10-10 22:41:50,269][98559] Updated weights for policy 0, policy_version 48320 (0.0009) -[2023-10-10 22:41:50,556][97672] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 98697216. Throughput: 0: 1692.5, 1: 1712.1. Samples: 24684686. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-10 22:41:50,557][97672] Avg episode reward: [(0, '-1.120'), (1, '22.340')] -[2023-10-10 22:41:50,623][98560] Updated weights for policy 1, policy_version 48072 (0.0009) -[2023-10-10 22:41:51,002][98560] Updated weights for policy 1, policy_version 48082 (0.0009) -[2023-10-10 22:41:51,373][98560] Updated weights for policy 1, policy_version 48092 (0.0007) -[2023-10-10 22:41:54,075][98559] Updated weights for policy 0, policy_version 48330 (0.0010) -[2023-10-10 22:41:54,440][98559] Updated weights for policy 0, policy_version 48340 (0.0011) -[2023-10-10 22:41:54,806][98559] Updated weights for policy 0, policy_version 48350 (0.0009) -[2023-10-10 22:41:55,076][98560] Updated weights for policy 1, policy_version 48102 (0.0009) -[2023-10-10 22:41:55,450][98560] Updated weights for policy 1, policy_version 48112 (0.0009) -[2023-10-10 22:41:55,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 98762752. Throughput: 0: 1725.6, 1: 1695.0. Samples: 24695340. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-10 22:41:55,557][97672] Avg episode reward: [(0, '-1.120'), (1, '22.360')] -[2023-10-10 22:41:55,816][98560] Updated weights for policy 1, policy_version 48122 (0.0007) -[2023-10-10 22:41:58,843][98559] Updated weights for policy 0, policy_version 48360 (0.0010) -[2023-10-10 22:41:59,200][98559] Updated weights for policy 0, policy_version 48370 (0.0008) -[2023-10-10 22:41:59,564][98559] Updated weights for policy 0, policy_version 48380 (0.0007) -[2023-10-10 22:41:59,752][98560] Updated weights for policy 1, policy_version 48132 (0.0009) -[2023-10-10 22:42:00,114][98560] Updated weights for policy 1, policy_version 48142 (0.0008) -[2023-10-10 22:42:00,481][98560] Updated weights for policy 1, policy_version 48152 (0.0007) -[2023-10-10 22:42:00,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 98828288. Throughput: 0: 1703.0, 1: 1712.9. Samples: 24715736. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-10 22:42:00,556][97672] Avg episode reward: [(0, '-1.120'), (1, '22.380')] -[2023-10-10 22:42:03,594][98559] Updated weights for policy 0, policy_version 48390 (0.0010) -[2023-10-10 22:42:03,963][98559] Updated weights for policy 0, policy_version 48400 (0.0008) -[2023-10-10 22:42:04,326][98559] Updated weights for policy 0, policy_version 48410 (0.0008) -[2023-10-10 22:42:04,587][98560] Updated weights for policy 1, policy_version 48162 (0.0009) -[2023-10-10 22:42:04,960][98560] Updated weights for policy 1, policy_version 48172 (0.0008) -[2023-10-10 22:42:05,321][98560] Updated weights for policy 1, policy_version 48182 (0.0009) -[2023-10-10 22:42:05,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 98893824. Throughput: 0: 1699.3, 1: 1707.2. Samples: 24736046. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-10 22:42:05,557][97672] Avg episode reward: [(0, '-1.120'), (1, '22.340')] -[2023-10-10 22:42:05,685][98560] Updated weights for policy 1, policy_version 48192 (0.0008) -[2023-10-10 22:42:08,340][98559] Updated weights for policy 0, policy_version 48420 (0.0008) -[2023-10-10 22:42:08,716][98559] Updated weights for policy 0, policy_version 48430 (0.0007) -[2023-10-10 22:42:09,083][98559] Updated weights for policy 0, policy_version 48440 (0.0008) -[2023-10-10 22:42:09,687][98560] Updated weights for policy 1, policy_version 48202 (0.0008) -[2023-10-10 22:42:10,050][98560] Updated weights for policy 1, policy_version 48212 (0.0008) -[2023-10-10 22:42:10,412][98560] Updated weights for policy 1, policy_version 48222 (0.0008) -[2023-10-10 22:42:10,556][97672] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 98992128. Throughput: 0: 1719.4, 1: 1705.0. Samples: 24746550. Policy #0 lag: (min: 30.0, avg: 38.0, max: 62.0) -[2023-10-10 22:42:10,556][97672] Avg episode reward: [(0, '-1.120'), (1, '22.460')] -[2023-10-10 22:42:13,048][98559] Updated weights for policy 0, policy_version 48450 (0.0008) -[2023-10-10 22:42:13,409][98559] Updated weights for policy 0, policy_version 48460 (0.0007) -[2023-10-10 22:42:13,772][98559] Updated weights for policy 0, policy_version 48470 (0.0008) -[2023-10-10 22:42:14,146][98559] Updated weights for policy 0, policy_version 48480 (0.0008) -[2023-10-10 22:42:14,674][98560] Updated weights for policy 1, policy_version 48232 (0.0010) -[2023-10-10 22:42:15,036][98560] Updated weights for policy 1, policy_version 48242 (0.0011) -[2023-10-10 22:42:15,402][98560] Updated weights for policy 1, policy_version 48252 (0.0010) -[2023-10-10 22:42:15,556][97672] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 99057664. Throughput: 0: 1693.0, 1: 1710.3. Samples: 24766620. Policy #0 lag: (min: 30.0, avg: 38.0, max: 62.0) -[2023-10-10 22:42:15,557][97672] Avg episode reward: [(0, '-1.120'), (1, '22.480')] -[2023-10-10 22:42:18,287][98559] Updated weights for policy 0, policy_version 48490 (0.0008) -[2023-10-10 22:42:18,654][98559] Updated weights for policy 0, policy_version 48500 (0.0008) -[2023-10-10 22:42:19,020][98559] Updated weights for policy 0, policy_version 48510 (0.0007) -[2023-10-10 22:42:19,362][98560] Updated weights for policy 1, policy_version 48262 (0.0007) -[2023-10-10 22:42:19,726][98560] Updated weights for policy 1, policy_version 48272 (0.0008) -[2023-10-10 22:42:20,093][98560] Updated weights for policy 1, policy_version 48282 (0.0008) -[2023-10-10 22:42:20,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 99123200. Throughput: 0: 1715.4, 1: 1698.8. Samples: 24787296. Policy #0 lag: (min: 30.0, avg: 38.0, max: 62.0) -[2023-10-10 22:42:20,557][97672] Avg episode reward: [(0, '-1.140'), (1, '22.440')] -[2023-10-10 22:42:23,054][98559] Updated weights for policy 0, policy_version 48520 (0.0009) -[2023-10-10 22:42:23,420][98559] Updated weights for policy 0, policy_version 48530 (0.0010) -[2023-10-10 22:42:23,783][98559] Updated weights for policy 0, policy_version 48540 (0.0009) -[2023-10-10 22:42:23,802][98560] Updated weights for policy 1, policy_version 48292 (0.0008) -[2023-10-10 22:42:24,169][98560] Updated weights for policy 1, policy_version 48302 (0.0008) -[2023-10-10 22:42:24,532][98560] Updated weights for policy 1, policy_version 48312 (0.0010) -[2023-10-10 22:42:25,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 99188736. Throughput: 0: 1711.7, 1: 1715.0. Samples: 24797946. Policy #0 lag: (min: 30.0, avg: 38.0, max: 62.0) -[2023-10-10 22:42:25,556][97672] Avg episode reward: [(0, '-1.060'), (1, '22.420')] -[2023-10-10 22:42:27,724][98559] Updated weights for policy 0, policy_version 48550 (0.0008) -[2023-10-10 22:42:28,091][98559] Updated weights for policy 0, policy_version 48560 (0.0009) -[2023-10-10 22:42:28,462][98559] Updated weights for policy 0, policy_version 48570 (0.0008) -[2023-10-10 22:42:28,659][98560] Updated weights for policy 1, policy_version 48322 (0.0008) -[2023-10-10 22:42:29,023][98560] Updated weights for policy 1, policy_version 48332 (0.0007) -[2023-10-10 22:42:29,381][98560] Updated weights for policy 1, policy_version 48342 (0.0008) -[2023-10-10 22:42:29,743][98560] Updated weights for policy 1, policy_version 48352 (0.0008) -[2023-10-10 22:42:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 99254272. Throughput: 0: 1691.5, 1: 1714.4. Samples: 24818156. Policy #0 lag: (min: 30.0, avg: 38.0, max: 62.0) -[2023-10-10 22:42:30,557][97672] Avg episode reward: [(0, '-1.060'), (1, '22.440')] -[2023-10-10 22:42:32,373][98559] Updated weights for policy 0, policy_version 48580 (0.0007) -[2023-10-10 22:42:32,735][98559] Updated weights for policy 0, policy_version 48590 (0.0009) -[2023-10-10 22:42:33,093][98559] Updated weights for policy 0, policy_version 48600 (0.0008) -[2023-10-10 22:42:33,808][98560] Updated weights for policy 1, policy_version 48362 (0.0008) -[2023-10-10 22:42:34,181][98560] Updated weights for policy 1, policy_version 48372 (0.0007) -[2023-10-10 22:42:34,538][98560] Updated weights for policy 1, policy_version 48382 (0.0008) -[2023-10-10 22:42:35,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 99319808. Throughput: 0: 1723.4, 1: 1687.0. Samples: 24838156. Policy #0 lag: (min: 30.0, avg: 38.0, max: 62.0) -[2023-10-10 22:42:35,557][97672] Avg episode reward: [(0, '-1.060'), (1, '22.580')] -[2023-10-10 22:42:35,567][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000048608_49774592.pth... -[2023-10-10 22:42:35,567][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000048384_49545216.pth... -[2023-10-10 22:42:35,605][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000047008_48136192.pth -[2023-10-10 22:42:35,612][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000046784_47906816.pth -[2023-10-10 22:42:35,618][98439] Saving new best policy, reward=22.580! -[2023-10-10 22:42:36,926][98559] Updated weights for policy 0, policy_version 48610 (0.0008) -[2023-10-10 22:42:37,294][98559] Updated weights for policy 0, policy_version 48620 (0.0008) -[2023-10-10 22:42:37,665][98559] Updated weights for policy 0, policy_version 48630 (0.0008) -[2023-10-10 22:42:38,029][98559] Updated weights for policy 0, policy_version 48640 (0.0009) -[2023-10-10 22:42:38,666][98560] Updated weights for policy 1, policy_version 48392 (0.0009) -[2023-10-10 22:42:39,036][98560] Updated weights for policy 1, policy_version 48402 (0.0009) -[2023-10-10 22:42:39,399][98560] Updated weights for policy 1, policy_version 48412 (0.0008) -[2023-10-10 22:42:40,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 99385344. Throughput: 0: 1691.5, 1: 1714.8. Samples: 24848624. Policy #0 lag: (min: 30.0, avg: 38.0, max: 62.0) -[2023-10-10 22:42:40,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.620')] -[2023-10-10 22:42:40,558][98439] Saving new best policy, reward=22.620! -[2023-10-10 22:42:42,086][98559] Updated weights for policy 0, policy_version 48650 (0.0011) -[2023-10-10 22:42:42,443][98559] Updated weights for policy 0, policy_version 48660 (0.0008) -[2023-10-10 22:42:42,812][98559] Updated weights for policy 0, policy_version 48670 (0.0008) -[2023-10-10 22:42:43,475][98560] Updated weights for policy 1, policy_version 48422 (0.0011) -[2023-10-10 22:42:43,838][98560] Updated weights for policy 1, policy_version 48432 (0.0009) -[2023-10-10 22:42:44,211][98560] Updated weights for policy 1, policy_version 48442 (0.0011) -[2023-10-10 22:42:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 99450880. Throughput: 0: 1709.8, 1: 1700.5. Samples: 24869202. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:42:45,556][97672] Avg episode reward: [(0, '-1.180'), (1, '22.580')] -[2023-10-10 22:42:46,651][98559] Updated weights for policy 0, policy_version 48680 (0.0010) -[2023-10-10 22:42:47,026][98559] Updated weights for policy 0, policy_version 48690 (0.0009) -[2023-10-10 22:42:47,385][98559] Updated weights for policy 0, policy_version 48700 (0.0009) -[2023-10-10 22:42:48,174][98560] Updated weights for policy 1, policy_version 48452 (0.0010) -[2023-10-10 22:42:48,535][98560] Updated weights for policy 1, policy_version 48462 (0.0008) -[2023-10-10 22:42:48,906][98560] Updated weights for policy 1, policy_version 48472 (0.0007) -[2023-10-10 22:42:50,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 99516416. Throughput: 0: 1723.6, 1: 1686.8. Samples: 24889514. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:42:50,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.600')] -[2023-10-10 22:42:51,473][98559] Updated weights for policy 0, policy_version 48710 (0.0010) -[2023-10-10 22:42:51,841][98559] Updated weights for policy 0, policy_version 48720 (0.0007) -[2023-10-10 22:42:52,204][98559] Updated weights for policy 0, policy_version 48730 (0.0007) -[2023-10-10 22:42:52,946][98560] Updated weights for policy 1, policy_version 48482 (0.0010) -[2023-10-10 22:42:53,349][98560] Updated weights for policy 1, policy_version 48492 (0.0007) -[2023-10-10 22:42:53,721][98560] Updated weights for policy 1, policy_version 48502 (0.0007) -[2023-10-10 22:42:54,092][98560] Updated weights for policy 1, policy_version 48512 (0.0009) -[2023-10-10 22:42:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 99581952. Throughput: 0: 1693.9, 1: 1715.2. Samples: 24899956. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:42:55,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.560')] -[2023-10-10 22:42:56,223][98559] Updated weights for policy 0, policy_version 48740 (0.0009) -[2023-10-10 22:42:56,593][98559] Updated weights for policy 0, policy_version 48750 (0.0008) -[2023-10-10 22:42:56,970][98559] Updated weights for policy 0, policy_version 48760 (0.0008) -[2023-10-10 22:42:58,173][98560] Updated weights for policy 1, policy_version 48522 (0.0009) -[2023-10-10 22:42:58,538][98560] Updated weights for policy 1, policy_version 48532 (0.0011) -[2023-10-10 22:42:58,911][98560] Updated weights for policy 1, policy_version 48542 (0.0007) -[2023-10-10 22:43:00,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 99647488. Throughput: 0: 1715.8, 1: 1686.4. Samples: 24919716. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:43:00,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.420')] -[2023-10-10 22:43:01,174][98559] Updated weights for policy 0, policy_version 48770 (0.0010) -[2023-10-10 22:43:01,543][98559] Updated weights for policy 0, policy_version 48780 (0.0009) -[2023-10-10 22:43:01,913][98559] Updated weights for policy 0, policy_version 48790 (0.0009) -[2023-10-10 22:43:02,280][98559] Updated weights for policy 0, policy_version 48800 (0.0009) -[2023-10-10 22:43:02,984][98560] Updated weights for policy 1, policy_version 48552 (0.0008) -[2023-10-10 22:43:03,356][98560] Updated weights for policy 1, policy_version 48562 (0.0009) -[2023-10-10 22:43:03,723][98560] Updated weights for policy 1, policy_version 48572 (0.0008) -[2023-10-10 22:43:05,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 99713024. Throughput: 0: 1713.4, 1: 1688.0. Samples: 24940362. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:43:05,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.500')] -[2023-10-10 22:43:06,332][98559] Updated weights for policy 0, policy_version 48810 (0.0010) -[2023-10-10 22:43:06,701][98559] Updated weights for policy 0, policy_version 48820 (0.0011) -[2023-10-10 22:43:07,060][98559] Updated weights for policy 0, policy_version 48830 (0.0009) -[2023-10-10 22:43:07,677][98560] Updated weights for policy 1, policy_version 48582 (0.0010) -[2023-10-10 22:43:08,042][98560] Updated weights for policy 1, policy_version 48592 (0.0008) -[2023-10-10 22:43:08,413][98560] Updated weights for policy 1, policy_version 48602 (0.0011) -[2023-10-10 22:43:10,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 99778560. Throughput: 0: 1703.4, 1: 1695.2. Samples: 24950884. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:43:10,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.460')] -[2023-10-10 22:43:10,947][98559] Updated weights for policy 0, policy_version 48840 (0.0007) -[2023-10-10 22:43:11,309][98559] Updated weights for policy 0, policy_version 48850 (0.0012) -[2023-10-10 22:43:11,682][98559] Updated weights for policy 0, policy_version 48860 (0.0010) -[2023-10-10 22:43:12,317][98560] Updated weights for policy 1, policy_version 48612 (0.0010) -[2023-10-10 22:43:12,675][98560] Updated weights for policy 1, policy_version 48622 (0.0008) -[2023-10-10 22:43:13,047][98560] Updated weights for policy 1, policy_version 48632 (0.0008) -[2023-10-10 22:43:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 99844096. Throughput: 0: 1722.3, 1: 1674.4. Samples: 24971006. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:43:15,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.440')] -[2023-10-10 22:43:15,594][98559] Updated weights for policy 0, policy_version 48870 (0.0009) -[2023-10-10 22:43:15,966][98559] Updated weights for policy 0, policy_version 48880 (0.0008) -[2023-10-10 22:43:16,329][98559] Updated weights for policy 0, policy_version 48890 (0.0009) -[2023-10-10 22:43:16,972][98560] Updated weights for policy 1, policy_version 48642 (0.0008) -[2023-10-10 22:43:17,332][98560] Updated weights for policy 1, policy_version 48652 (0.0008) -[2023-10-10 22:43:17,704][98560] Updated weights for policy 1, policy_version 48662 (0.0008) -[2023-10-10 22:43:18,072][98560] Updated weights for policy 1, policy_version 48672 (0.0007) -[2023-10-10 22:43:20,206][98559] Updated weights for policy 0, policy_version 48900 (0.0009) -[2023-10-10 22:43:20,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 99909632. Throughput: 0: 1711.6, 1: 1704.0. Samples: 24991860. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-10 22:43:20,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.400')] -[2023-10-10 22:43:20,577][98559] Updated weights for policy 0, policy_version 48910 (0.0012) -[2023-10-10 22:43:20,940][98559] Updated weights for policy 0, policy_version 48920 (0.0008) -[2023-10-10 22:43:22,065][98560] Updated weights for policy 1, policy_version 48682 (0.0007) -[2023-10-10 22:43:22,436][98560] Updated weights for policy 1, policy_version 48692 (0.0009) -[2023-10-10 22:43:22,814][98560] Updated weights for policy 1, policy_version 48702 (0.0008) -[2023-10-10 22:43:25,002][98559] Updated weights for policy 0, policy_version 48930 (0.0007) -[2023-10-10 22:43:25,366][98559] Updated weights for policy 0, policy_version 48940 (0.0011) -[2023-10-10 22:43:25,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 99975168. Throughput: 0: 1718.3, 1: 1685.7. Samples: 25001804. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-10 22:43:25,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.300')] -[2023-10-10 22:43:25,725][98559] Updated weights for policy 0, policy_version 48950 (0.0009) -[2023-10-10 22:43:26,093][98559] Updated weights for policy 0, policy_version 48960 (0.0009) -[2023-10-10 22:43:26,753][98560] Updated weights for policy 1, policy_version 48712 (0.0009) -[2023-10-10 22:43:27,115][98560] Updated weights for policy 1, policy_version 48722 (0.0008) -[2023-10-10 22:43:27,488][98560] Updated weights for policy 1, policy_version 48732 (0.0008) -[2023-10-10 22:43:30,100][98559] Updated weights for policy 0, policy_version 48970 (0.0009) -[2023-10-10 22:43:30,465][98559] Updated weights for policy 0, policy_version 48980 (0.0010) -[2023-10-10 22:43:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 100040704. Throughput: 0: 1717.4, 1: 1692.3. Samples: 25022638. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-10 22:43:30,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.320')] -[2023-10-10 22:43:30,826][98559] Updated weights for policy 0, policy_version 48990 (0.0008) -[2023-10-10 22:43:31,706][98560] Updated weights for policy 1, policy_version 48742 (0.0009) -[2023-10-10 22:43:32,086][98560] Updated weights for policy 1, policy_version 48752 (0.0009) -[2023-10-10 22:43:32,452][98560] Updated weights for policy 1, policy_version 48762 (0.0011) -[2023-10-10 22:43:34,935][98559] Updated weights for policy 0, policy_version 49000 (0.0009) -[2023-10-10 22:43:35,309][98559] Updated weights for policy 0, policy_version 49010 (0.0009) -[2023-10-10 22:43:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 100106240. Throughput: 0: 1701.6, 1: 1708.7. Samples: 25042978. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-10 22:43:35,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.280')] -[2023-10-10 22:43:35,681][98559] Updated weights for policy 0, policy_version 49020 (0.0008) -[2023-10-10 22:43:36,411][98560] Updated weights for policy 1, policy_version 48772 (0.0011) -[2023-10-10 22:43:36,769][98560] Updated weights for policy 1, policy_version 48782 (0.0010) -[2023-10-10 22:43:37,134][98560] Updated weights for policy 1, policy_version 48792 (0.0010) -[2023-10-10 22:43:39,448][98559] Updated weights for policy 0, policy_version 49030 (0.0008) -[2023-10-10 22:43:39,804][98559] Updated weights for policy 0, policy_version 49040 (0.0008) -[2023-10-10 22:43:40,172][98559] Updated weights for policy 0, policy_version 49050 (0.0008) -[2023-10-10 22:43:40,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 100204544. Throughput: 0: 1726.2, 1: 1678.2. Samples: 25053154. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-10 22:43:40,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.260')] -[2023-10-10 22:43:41,309][98560] Updated weights for policy 1, policy_version 48802 (0.0008) -[2023-10-10 22:43:41,678][98560] Updated weights for policy 1, policy_version 48812 (0.0009) -[2023-10-10 22:43:42,045][98560] Updated weights for policy 1, policy_version 48822 (0.0007) -[2023-10-10 22:43:42,411][98560] Updated weights for policy 1, policy_version 48832 (0.0007) -[2023-10-10 22:43:44,095][98559] Updated weights for policy 0, policy_version 49060 (0.0008) -[2023-10-10 22:43:44,473][98559] Updated weights for policy 0, policy_version 49070 (0.0008) -[2023-10-10 22:43:44,844][98559] Updated weights for policy 0, policy_version 49080 (0.0007) -[2023-10-10 22:43:45,556][97672] Fps is (10 sec: 16384.5, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 100270080. Throughput: 0: 1722.9, 1: 1700.4. Samples: 25073764. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-10 22:43:45,556][97672] Avg episode reward: [(0, '-1.180'), (1, '22.200')] -[2023-10-10 22:43:46,452][98560] Updated weights for policy 1, policy_version 48842 (0.0007) -[2023-10-10 22:43:46,818][98560] Updated weights for policy 1, policy_version 48852 (0.0008) -[2023-10-10 22:43:47,177][98560] Updated weights for policy 1, policy_version 48862 (0.0009) -[2023-10-10 22:43:48,682][98559] Updated weights for policy 0, policy_version 49090 (0.0007) -[2023-10-10 22:43:49,050][98559] Updated weights for policy 0, policy_version 49100 (0.0008) -[2023-10-10 22:43:49,421][98559] Updated weights for policy 0, policy_version 49110 (0.0008) -[2023-10-10 22:43:49,792][98559] Updated weights for policy 0, policy_version 49120 (0.0008) -[2023-10-10 22:43:50,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 100335616. Throughput: 0: 1708.1, 1: 1710.3. Samples: 25094188. Policy #0 lag: (min: 11.0, avg: 31.1, max: 32.0) -[2023-10-10 22:43:50,556][97672] Avg episode reward: [(0, '-1.180'), (1, '22.180')] -[2023-10-10 22:43:51,141][98560] Updated weights for policy 1, policy_version 48872 (0.0011) -[2023-10-10 22:43:51,500][98560] Updated weights for policy 1, policy_version 48882 (0.0008) -[2023-10-10 22:43:51,880][98560] Updated weights for policy 1, policy_version 48892 (0.0008) -[2023-10-10 22:43:53,577][98559] Updated weights for policy 0, policy_version 49130 (0.0007) -[2023-10-10 22:43:53,946][98559] Updated weights for policy 0, policy_version 49140 (0.0007) -[2023-10-10 22:43:54,304][98559] Updated weights for policy 0, policy_version 49150 (0.0008) -[2023-10-10 22:43:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 100401152. Throughput: 0: 1734.4, 1: 1683.7. Samples: 25104696. Policy #0 lag: (min: 11.0, avg: 31.1, max: 32.0) -[2023-10-10 22:43:55,556][97672] Avg episode reward: [(0, '-1.180'), (1, '22.160')] -[2023-10-10 22:43:55,942][98560] Updated weights for policy 1, policy_version 48902 (0.0008) -[2023-10-10 22:43:56,315][98560] Updated weights for policy 1, policy_version 48912 (0.0007) -[2023-10-10 22:43:56,688][98560] Updated weights for policy 1, policy_version 48922 (0.0009) -[2023-10-10 22:43:58,204][98559] Updated weights for policy 0, policy_version 49160 (0.0009) -[2023-10-10 22:43:58,565][98559] Updated weights for policy 0, policy_version 49170 (0.0011) -[2023-10-10 22:43:58,928][98559] Updated weights for policy 0, policy_version 49180 (0.0010) -[2023-10-10 22:44:00,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 100466688. Throughput: 0: 1712.8, 1: 1701.2. Samples: 25124638. Policy #0 lag: (min: 11.0, avg: 31.1, max: 32.0) -[2023-10-10 22:44:00,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.160')] -[2023-10-10 22:44:00,831][98560] Updated weights for policy 1, policy_version 48932 (0.0009) -[2023-10-10 22:44:01,199][98560] Updated weights for policy 1, policy_version 48942 (0.0009) -[2023-10-10 22:44:01,565][98560] Updated weights for policy 1, policy_version 48952 (0.0009) -[2023-10-10 22:44:02,970][98559] Updated weights for policy 0, policy_version 49190 (0.0009) -[2023-10-10 22:44:03,329][98559] Updated weights for policy 0, policy_version 49200 (0.0010) -[2023-10-10 22:44:03,699][98559] Updated weights for policy 0, policy_version 49210 (0.0009) -[2023-10-10 22:44:05,476][98560] Updated weights for policy 1, policy_version 48962 (0.0009) -[2023-10-10 22:44:05,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 100532224. Throughput: 0: 1720.3, 1: 1700.7. Samples: 25145802. Policy #0 lag: (min: 11.0, avg: 31.1, max: 32.0) -[2023-10-10 22:44:05,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.240')] -[2023-10-10 22:44:05,843][98560] Updated weights for policy 1, policy_version 48972 (0.0007) -[2023-10-10 22:44:06,212][98560] Updated weights for policy 1, policy_version 48982 (0.0009) -[2023-10-10 22:44:06,581][98560] Updated weights for policy 1, policy_version 48992 (0.0007) -[2023-10-10 22:44:07,621][98559] Updated weights for policy 0, policy_version 49220 (0.0009) -[2023-10-10 22:44:07,995][98559] Updated weights for policy 0, policy_version 49230 (0.0010) -[2023-10-10 22:44:08,363][98559] Updated weights for policy 0, policy_version 49240 (0.0010) -[2023-10-10 22:44:10,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 100597760. Throughput: 0: 1724.1, 1: 1690.7. Samples: 25155470. Policy #0 lag: (min: 11.0, avg: 31.1, max: 32.0) -[2023-10-10 22:44:10,557][97672] Avg episode reward: [(0, '-1.220'), (1, '22.240')] -[2023-10-10 22:44:10,639][98560] Updated weights for policy 1, policy_version 49002 (0.0010) -[2023-10-10 22:44:10,998][98560] Updated weights for policy 1, policy_version 49012 (0.0008) -[2023-10-10 22:44:11,356][98560] Updated weights for policy 1, policy_version 49022 (0.0009) -[2023-10-10 22:44:12,263][98559] Updated weights for policy 0, policy_version 49250 (0.0010) -[2023-10-10 22:44:12,636][98559] Updated weights for policy 0, policy_version 49260 (0.0008) -[2023-10-10 22:44:13,006][98559] Updated weights for policy 0, policy_version 49270 (0.0010) -[2023-10-10 22:44:13,374][98559] Updated weights for policy 0, policy_version 49280 (0.0010) -[2023-10-10 22:44:15,239][98560] Updated weights for policy 1, policy_version 49032 (0.0008) -[2023-10-10 22:44:15,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 100663296. Throughput: 0: 1717.7, 1: 1699.2. Samples: 25176402. Policy #0 lag: (min: 11.0, avg: 31.1, max: 32.0) -[2023-10-10 22:44:15,557][97672] Avg episode reward: [(0, '-1.220'), (1, '22.220')] -[2023-10-10 22:44:15,606][98560] Updated weights for policy 1, policy_version 49042 (0.0007) -[2023-10-10 22:44:15,978][98560] Updated weights for policy 1, policy_version 49052 (0.0007) -[2023-10-10 22:44:17,242][98559] Updated weights for policy 0, policy_version 49290 (0.0008) -[2023-10-10 22:44:17,604][98559] Updated weights for policy 0, policy_version 49300 (0.0009) -[2023-10-10 22:44:17,978][98559] Updated weights for policy 0, policy_version 49310 (0.0008) -[2023-10-10 22:44:19,969][98560] Updated weights for policy 1, policy_version 49062 (0.0008) -[2023-10-10 22:44:20,337][98560] Updated weights for policy 1, policy_version 49072 (0.0009) -[2023-10-10 22:44:20,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 100728832. Throughput: 0: 1734.7, 1: 1704.9. Samples: 25197756. Policy #0 lag: (min: 11.0, avg: 31.1, max: 32.0) -[2023-10-10 22:44:20,556][97672] Avg episode reward: [(0, '-1.220'), (1, '22.260')] -[2023-10-10 22:44:20,708][98560] Updated weights for policy 1, policy_version 49082 (0.0008) -[2023-10-10 22:44:21,972][98559] Updated weights for policy 0, policy_version 49320 (0.0008) -[2023-10-10 22:44:22,342][98559] Updated weights for policy 0, policy_version 49330 (0.0009) -[2023-10-10 22:44:22,713][98559] Updated weights for policy 0, policy_version 49340 (0.0010) -[2023-10-10 22:44:24,609][98560] Updated weights for policy 1, policy_version 49092 (0.0009) -[2023-10-10 22:44:24,981][98560] Updated weights for policy 1, policy_version 49102 (0.0009) -[2023-10-10 22:44:25,350][98560] Updated weights for policy 1, policy_version 49112 (0.0007) -[2023-10-10 22:44:25,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 100794368. Throughput: 0: 1716.7, 1: 1707.4. Samples: 25207238. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-10 22:44:25,556][97672] Avg episode reward: [(0, '-1.220'), (1, '22.340')] -[2023-10-10 22:44:26,678][98559] Updated weights for policy 0, policy_version 49350 (0.0009) -[2023-10-10 22:44:27,043][98559] Updated weights for policy 0, policy_version 49360 (0.0008) -[2023-10-10 22:44:27,411][98559] Updated weights for policy 0, policy_version 49370 (0.0008) -[2023-10-10 22:44:29,248][98560] Updated weights for policy 1, policy_version 49122 (0.0008) -[2023-10-10 22:44:29,617][98560] Updated weights for policy 1, policy_version 49132 (0.0008) -[2023-10-10 22:44:29,978][98560] Updated weights for policy 1, policy_version 49142 (0.0011) -[2023-10-10 22:44:30,345][98560] Updated weights for policy 1, policy_version 49152 (0.0009) -[2023-10-10 22:44:30,556][97672] Fps is (10 sec: 16383.4, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 100892672. Throughput: 0: 1723.5, 1: 1714.3. Samples: 25228464. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-10 22:44:30,558][97672] Avg episode reward: [(0, '-1.220'), (1, '22.380')] -[2023-10-10 22:44:31,625][98559] Updated weights for policy 0, policy_version 49380 (0.0009) -[2023-10-10 22:44:32,011][98559] Updated weights for policy 0, policy_version 49390 (0.0009) -[2023-10-10 22:44:32,375][98559] Updated weights for policy 0, policy_version 49400 (0.0011) -[2023-10-10 22:44:34,574][98560] Updated weights for policy 1, policy_version 49162 (0.0010) -[2023-10-10 22:44:34,944][98560] Updated weights for policy 1, policy_version 49172 (0.0008) -[2023-10-10 22:44:35,303][98560] Updated weights for policy 1, policy_version 49182 (0.0010) -[2023-10-10 22:44:35,556][97672] Fps is (10 sec: 16383.5, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 100958208. Throughput: 0: 1738.3, 1: 1698.9. Samples: 25248862. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-10 22:44:35,557][97672] Avg episode reward: [(0, '-1.220'), (1, '22.440')] -[2023-10-10 22:44:35,567][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000049184_50364416.pth... -[2023-10-10 22:44:35,568][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000049408_50593792.pth... -[2023-10-10 22:44:35,606][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000047808_48955392.pth -[2023-10-10 22:44:35,608][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000047584_48726016.pth -[2023-10-10 22:44:36,119][98559] Updated weights for policy 0, policy_version 49410 (0.0010) -[2023-10-10 22:44:36,484][98559] Updated weights for policy 0, policy_version 49420 (0.0010) -[2023-10-10 22:44:36,852][98559] Updated weights for policy 0, policy_version 49430 (0.0007) -[2023-10-10 22:44:37,218][98559] Updated weights for policy 0, policy_version 49440 (0.0010) -[2023-10-10 22:44:39,467][98560] Updated weights for policy 1, policy_version 49192 (0.0009) -[2023-10-10 22:44:39,838][98560] Updated weights for policy 1, policy_version 49202 (0.0010) -[2023-10-10 22:44:40,201][98560] Updated weights for policy 1, policy_version 49212 (0.0008) -[2023-10-10 22:44:40,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 101023744. Throughput: 0: 1707.2, 1: 1712.8. Samples: 25258592. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-10 22:44:40,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.420')] -[2023-10-10 22:44:41,267][98559] Updated weights for policy 0, policy_version 49450 (0.0009) -[2023-10-10 22:44:41,640][98559] Updated weights for policy 0, policy_version 49460 (0.0009) -[2023-10-10 22:44:42,006][98559] Updated weights for policy 0, policy_version 49470 (0.0009) -[2023-10-10 22:44:44,209][98560] Updated weights for policy 1, policy_version 49222 (0.0007) -[2023-10-10 22:44:44,574][98560] Updated weights for policy 1, policy_version 49232 (0.0011) -[2023-10-10 22:44:44,947][98560] Updated weights for policy 1, policy_version 49242 (0.0011) -[2023-10-10 22:44:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 101089280. Throughput: 0: 1731.6, 1: 1715.5. Samples: 25279756. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-10 22:44:45,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.460')] -[2023-10-10 22:44:45,854][98559] Updated weights for policy 0, policy_version 49480 (0.0007) -[2023-10-10 22:44:46,216][98559] Updated weights for policy 0, policy_version 49490 (0.0009) -[2023-10-10 22:44:46,581][98559] Updated weights for policy 0, policy_version 49500 (0.0008) -[2023-10-10 22:44:49,020][98560] Updated weights for policy 1, policy_version 49252 (0.0009) -[2023-10-10 22:44:49,400][98560] Updated weights for policy 1, policy_version 49262 (0.0008) -[2023-10-10 22:44:49,759][98560] Updated weights for policy 1, policy_version 49272 (0.0008) -[2023-10-10 22:44:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 101154816. Throughput: 0: 1729.6, 1: 1691.8. Samples: 25299768. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-10 22:44:50,557][97672] Avg episode reward: [(0, '-1.160'), (1, '22.460')] -[2023-10-10 22:44:50,618][98559] Updated weights for policy 0, policy_version 49510 (0.0009) -[2023-10-10 22:44:50,988][98559] Updated weights for policy 0, policy_version 49520 (0.0010) -[2023-10-10 22:44:51,354][98559] Updated weights for policy 0, policy_version 49530 (0.0011) -[2023-10-10 22:44:53,475][98560] Updated weights for policy 1, policy_version 49282 (0.0010) -[2023-10-10 22:44:53,837][98560] Updated weights for policy 1, policy_version 49292 (0.0009) -[2023-10-10 22:44:54,202][98560] Updated weights for policy 1, policy_version 49302 (0.0010) -[2023-10-10 22:44:54,572][98560] Updated weights for policy 1, policy_version 49312 (0.0008) -[2023-10-10 22:44:55,315][98559] Updated weights for policy 0, policy_version 49540 (0.0008) -[2023-10-10 22:44:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 101220352. Throughput: 0: 1718.0, 1: 1717.2. Samples: 25310056. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-10 22:44:55,557][97672] Avg episode reward: [(0, '-1.160'), (1, '22.500')] -[2023-10-10 22:44:55,695][98559] Updated weights for policy 0, policy_version 49550 (0.0009) -[2023-10-10 22:44:56,063][98559] Updated weights for policy 0, policy_version 49560 (0.0008) -[2023-10-10 22:44:58,421][98560] Updated weights for policy 1, policy_version 49322 (0.0008) -[2023-10-10 22:44:58,776][98560] Updated weights for policy 1, policy_version 49332 (0.0009) -[2023-10-10 22:44:59,149][98560] Updated weights for policy 1, policy_version 49342 (0.0008) -[2023-10-10 22:45:00,134][98559] Updated weights for policy 0, policy_version 49570 (0.0009) -[2023-10-10 22:45:00,504][98559] Updated weights for policy 0, policy_version 49580 (0.0010) -[2023-10-10 22:45:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 101285888. Throughput: 0: 1727.1, 1: 1703.7. Samples: 25330788. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:45:00,556][97672] Avg episode reward: [(0, '-1.160'), (1, '22.560')] -[2023-10-10 22:45:00,877][98559] Updated weights for policy 0, policy_version 49590 (0.0010) -[2023-10-10 22:45:01,245][98559] Updated weights for policy 0, policy_version 49600 (0.0008) -[2023-10-10 22:45:03,339][98560] Updated weights for policy 1, policy_version 49352 (0.0009) -[2023-10-10 22:45:03,712][98560] Updated weights for policy 1, policy_version 49362 (0.0007) -[2023-10-10 22:45:04,079][98560] Updated weights for policy 1, policy_version 49372 (0.0007) -[2023-10-10 22:45:05,174][98559] Updated weights for policy 0, policy_version 49610 (0.0009) -[2023-10-10 22:45:05,546][98559] Updated weights for policy 0, policy_version 49620 (0.0007) -[2023-10-10 22:45:05,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 101351424. Throughput: 0: 1707.4, 1: 1685.0. Samples: 25350412. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:45:05,556][97672] Avg episode reward: [(0, '-1.160'), (1, '22.580')] -[2023-10-10 22:45:05,904][98559] Updated weights for policy 0, policy_version 49630 (0.0007) -[2023-10-10 22:45:08,202][98560] Updated weights for policy 1, policy_version 49382 (0.0010) -[2023-10-10 22:45:08,570][98560] Updated weights for policy 1, policy_version 49392 (0.0009) -[2023-10-10 22:45:08,939][98560] Updated weights for policy 1, policy_version 49402 (0.0009) -[2023-10-10 22:45:10,007][98559] Updated weights for policy 0, policy_version 49640 (0.0010) -[2023-10-10 22:45:10,373][98559] Updated weights for policy 0, policy_version 49650 (0.0010) -[2023-10-10 22:45:10,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 101416960. Throughput: 0: 1717.2, 1: 1707.3. Samples: 25361340. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:45:10,557][97672] Avg episode reward: [(0, '-1.160'), (1, '22.580')] -[2023-10-10 22:45:10,739][98559] Updated weights for policy 0, policy_version 49660 (0.0009) -[2023-10-10 22:45:12,970][98560] Updated weights for policy 1, policy_version 49412 (0.0009) -[2023-10-10 22:45:13,323][98560] Updated weights for policy 1, policy_version 49422 (0.0007) -[2023-10-10 22:45:13,699][98560] Updated weights for policy 1, policy_version 49432 (0.0008) -[2023-10-10 22:45:14,651][98559] Updated weights for policy 0, policy_version 49670 (0.0008) -[2023-10-10 22:45:15,026][98559] Updated weights for policy 0, policy_version 49680 (0.0007) -[2023-10-10 22:45:15,401][98559] Updated weights for policy 0, policy_version 49690 (0.0008) -[2023-10-10 22:45:15,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 101482496. Throughput: 0: 1717.9, 1: 1679.3. Samples: 25381338. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:45:15,557][97672] Avg episode reward: [(0, '-1.160'), (1, '22.540')] -[2023-10-10 22:45:17,718][98560] Updated weights for policy 1, policy_version 49442 (0.0007) -[2023-10-10 22:45:18,090][98560] Updated weights for policy 1, policy_version 49452 (0.0008) -[2023-10-10 22:45:18,454][98560] Updated weights for policy 1, policy_version 49462 (0.0007) -[2023-10-10 22:45:18,818][98560] Updated weights for policy 1, policy_version 49472 (0.0007) -[2023-10-10 22:45:19,510][98559] Updated weights for policy 0, policy_version 49700 (0.0008) -[2023-10-10 22:45:19,887][98559] Updated weights for policy 0, policy_version 49710 (0.0009) -[2023-10-10 22:45:20,258][98559] Updated weights for policy 0, policy_version 49720 (0.0008) -[2023-10-10 22:45:20,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 101580800. Throughput: 0: 1692.8, 1: 1689.9. Samples: 25401084. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:45:20,556][97672] Avg episode reward: [(0, '-1.160'), (1, '22.540')] -[2023-10-10 22:45:22,969][98560] Updated weights for policy 1, policy_version 49482 (0.0010) -[2023-10-10 22:45:23,341][98560] Updated weights for policy 1, policy_version 49492 (0.0010) -[2023-10-10 22:45:23,704][98560] Updated weights for policy 1, policy_version 49502 (0.0009) -[2023-10-10 22:45:24,113][98559] Updated weights for policy 0, policy_version 49730 (0.0009) -[2023-10-10 22:45:24,482][98559] Updated weights for policy 0, policy_version 49740 (0.0010) -[2023-10-10 22:45:24,840][98559] Updated weights for policy 0, policy_version 49750 (0.0009) -[2023-10-10 22:45:25,213][98559] Updated weights for policy 0, policy_version 49760 (0.0009) -[2023-10-10 22:45:25,556][97672] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 101646336. Throughput: 0: 1716.1, 1: 1703.1. Samples: 25412458. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:45:25,557][97672] Avg episode reward: [(0, '-1.160'), (1, '22.560')] -[2023-10-10 22:45:27,754][98560] Updated weights for policy 1, policy_version 49512 (0.0008) -[2023-10-10 22:45:28,113][98560] Updated weights for policy 1, policy_version 49522 (0.0007) -[2023-10-10 22:45:28,482][98560] Updated weights for policy 1, policy_version 49532 (0.0007) -[2023-10-10 22:45:29,183][98559] Updated weights for policy 0, policy_version 49770 (0.0010) -[2023-10-10 22:45:29,548][98559] Updated weights for policy 0, policy_version 49780 (0.0011) -[2023-10-10 22:45:29,916][98559] Updated weights for policy 0, policy_version 49790 (0.0009) -[2023-10-10 22:45:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 101711872. Throughput: 0: 1703.2, 1: 1677.7. Samples: 25431898. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-10 22:45:30,557][97672] Avg episode reward: [(0, '-1.160'), (1, '22.600')] -[2023-10-10 22:45:32,318][98560] Updated weights for policy 1, policy_version 49542 (0.0008) -[2023-10-10 22:45:32,688][98560] Updated weights for policy 1, policy_version 49552 (0.0009) -[2023-10-10 22:45:33,051][98560] Updated weights for policy 1, policy_version 49562 (0.0009) -[2023-10-10 22:45:33,940][98559] Updated weights for policy 0, policy_version 49800 (0.0009) -[2023-10-10 22:45:34,312][98559] Updated weights for policy 0, policy_version 49810 (0.0008) -[2023-10-10 22:45:34,679][98559] Updated weights for policy 0, policy_version 49820 (0.0009) -[2023-10-10 22:45:35,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 101777408. Throughput: 0: 1682.9, 1: 1705.4. Samples: 25452242. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-10 22:45:35,557][97672] Avg episode reward: [(0, '-1.160'), (1, '22.640')] -[2023-10-10 22:45:35,566][98439] Saving new best policy, reward=22.640! -[2023-10-10 22:45:37,065][98560] Updated weights for policy 1, policy_version 49572 (0.0007) -[2023-10-10 22:45:37,424][98560] Updated weights for policy 1, policy_version 49582 (0.0008) -[2023-10-10 22:45:37,792][98560] Updated weights for policy 1, policy_version 49592 (0.0008) -[2023-10-10 22:45:38,641][98559] Updated weights for policy 0, policy_version 49830 (0.0010) -[2023-10-10 22:45:39,012][98559] Updated weights for policy 0, policy_version 49840 (0.0008) -[2023-10-10 22:45:39,376][98559] Updated weights for policy 0, policy_version 49850 (0.0007) -[2023-10-10 22:45:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 101842944. Throughput: 0: 1711.7, 1: 1688.4. Samples: 25463060. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-10 22:45:40,556][97672] Avg episode reward: [(0, '-1.200'), (1, '22.500')] -[2023-10-10 22:45:41,707][98560] Updated weights for policy 1, policy_version 49602 (0.0009) -[2023-10-10 22:45:42,074][98560] Updated weights for policy 1, policy_version 49612 (0.0008) -[2023-10-10 22:45:42,437][98560] Updated weights for policy 1, policy_version 49622 (0.0007) -[2023-10-10 22:45:42,802][98560] Updated weights for policy 1, policy_version 49632 (0.0007) -[2023-10-10 22:45:43,384][98559] Updated weights for policy 0, policy_version 49860 (0.0007) -[2023-10-10 22:45:43,749][98559] Updated weights for policy 0, policy_version 49870 (0.0008) -[2023-10-10 22:45:44,114][98559] Updated weights for policy 0, policy_version 49880 (0.0008) -[2023-10-10 22:45:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 101908480. Throughput: 0: 1683.7, 1: 1694.4. Samples: 25482804. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-10 22:45:45,556][97672] Avg episode reward: [(0, '-1.200'), (1, '22.460')] -[2023-10-10 22:45:46,749][98560] Updated weights for policy 1, policy_version 49642 (0.0007) -[2023-10-10 22:45:47,113][98560] Updated weights for policy 1, policy_version 49652 (0.0009) -[2023-10-10 22:45:47,483][98560] Updated weights for policy 1, policy_version 49662 (0.0010) -[2023-10-10 22:45:48,084][98559] Updated weights for policy 0, policy_version 49890 (0.0007) -[2023-10-10 22:45:48,450][98559] Updated weights for policy 0, policy_version 49900 (0.0007) -[2023-10-10 22:45:48,820][98559] Updated weights for policy 0, policy_version 49910 (0.0007) -[2023-10-10 22:45:49,184][98559] Updated weights for policy 0, policy_version 49920 (0.0010) -[2023-10-10 22:45:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 101974016. Throughput: 0: 1698.4, 1: 1712.4. Samples: 25503902. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-10 22:45:50,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.440')] -[2023-10-10 22:45:51,562][98560] Updated weights for policy 1, policy_version 49672 (0.0008) -[2023-10-10 22:45:51,930][98560] Updated weights for policy 1, policy_version 49682 (0.0009) -[2023-10-10 22:45:52,299][98560] Updated weights for policy 1, policy_version 49692 (0.0009) -[2023-10-10 22:45:53,190][98559] Updated weights for policy 0, policy_version 49930 (0.0009) -[2023-10-10 22:45:53,568][98559] Updated weights for policy 0, policy_version 49940 (0.0007) -[2023-10-10 22:45:53,939][98559] Updated weights for policy 0, policy_version 49950 (0.0008) -[2023-10-10 22:45:55,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 102039552. Throughput: 0: 1703.3, 1: 1683.1. Samples: 25513730. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-10 22:45:55,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.420')] -[2023-10-10 22:45:56,292][98560] Updated weights for policy 1, policy_version 49702 (0.0008) -[2023-10-10 22:45:56,656][98560] Updated weights for policy 1, policy_version 49712 (0.0009) -[2023-10-10 22:45:57,022][98560] Updated weights for policy 1, policy_version 49722 (0.0007) -[2023-10-10 22:45:57,900][98559] Updated weights for policy 0, policy_version 49960 (0.0008) -[2023-10-10 22:45:58,261][98559] Updated weights for policy 0, policy_version 49970 (0.0007) -[2023-10-10 22:45:58,626][98559] Updated weights for policy 0, policy_version 49980 (0.0009) -[2023-10-10 22:46:00,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 102105088. Throughput: 0: 1687.1, 1: 1713.9. Samples: 25534384. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-10 22:46:00,556][97672] Avg episode reward: [(0, '-1.120'), (1, '22.460')] -[2023-10-10 22:46:01,109][98560] Updated weights for policy 1, policy_version 49732 (0.0008) -[2023-10-10 22:46:01,476][98560] Updated weights for policy 1, policy_version 49742 (0.0009) -[2023-10-10 22:46:01,846][98560] Updated weights for policy 1, policy_version 49752 (0.0009) -[2023-10-10 22:46:02,600][98559] Updated weights for policy 0, policy_version 49990 (0.0007) -[2023-10-10 22:46:02,969][98559] Updated weights for policy 0, policy_version 50000 (0.0010) -[2023-10-10 22:46:03,339][98559] Updated weights for policy 0, policy_version 50010 (0.0011) -[2023-10-10 22:46:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 102170624. Throughput: 0: 1716.3, 1: 1716.3. Samples: 25555554. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:46:05,557][97672] Avg episode reward: [(0, '-1.120'), (1, '22.500')] -[2023-10-10 22:46:05,798][98560] Updated weights for policy 1, policy_version 49762 (0.0009) -[2023-10-10 22:46:06,164][98560] Updated weights for policy 1, policy_version 49772 (0.0009) -[2023-10-10 22:46:06,532][98560] Updated weights for policy 1, policy_version 49782 (0.0007) -[2023-10-10 22:46:06,900][98560] Updated weights for policy 1, policy_version 49792 (0.0007) -[2023-10-10 22:46:07,275][98559] Updated weights for policy 0, policy_version 50020 (0.0010) -[2023-10-10 22:46:07,660][98559] Updated weights for policy 0, policy_version 50030 (0.0010) -[2023-10-10 22:46:08,016][98559] Updated weights for policy 0, policy_version 50040 (0.0009) -[2023-10-10 22:46:10,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 102236160. Throughput: 0: 1693.7, 1: 1690.7. Samples: 25564754. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:46:10,556][97672] Avg episode reward: [(0, '-1.120'), (1, '22.520')] -[2023-10-10 22:46:10,945][98560] Updated weights for policy 1, policy_version 49802 (0.0008) -[2023-10-10 22:46:11,315][98560] Updated weights for policy 1, policy_version 49812 (0.0007) -[2023-10-10 22:46:11,686][98560] Updated weights for policy 1, policy_version 49822 (0.0009) -[2023-10-10 22:46:12,146][98559] Updated weights for policy 0, policy_version 50050 (0.0010) -[2023-10-10 22:46:12,518][98559] Updated weights for policy 0, policy_version 50060 (0.0009) -[2023-10-10 22:46:12,897][98559] Updated weights for policy 0, policy_version 50070 (0.0007) -[2023-10-10 22:46:13,270][98559] Updated weights for policy 0, policy_version 50080 (0.0009) -[2023-10-10 22:46:15,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 102301696. Throughput: 0: 1703.8, 1: 1719.1. Samples: 25585926. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:46:15,556][97672] Avg episode reward: [(0, '-1.120'), (1, '22.480')] -[2023-10-10 22:46:15,637][98560] Updated weights for policy 1, policy_version 49832 (0.0007) -[2023-10-10 22:46:16,008][98560] Updated weights for policy 1, policy_version 49842 (0.0009) -[2023-10-10 22:46:16,366][98560] Updated weights for policy 1, policy_version 49852 (0.0007) -[2023-10-10 22:46:17,292][98559] Updated weights for policy 0, policy_version 50090 (0.0009) -[2023-10-10 22:46:17,659][98559] Updated weights for policy 0, policy_version 50100 (0.0008) -[2023-10-10 22:46:18,019][98559] Updated weights for policy 0, policy_version 50110 (0.0010) -[2023-10-10 22:46:20,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 102367232. Throughput: 0: 1727.5, 1: 1711.2. Samples: 25606982. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:46:20,557][97672] Avg episode reward: [(0, '-1.120'), (1, '22.520')] -[2023-10-10 22:46:20,573][98560] Updated weights for policy 1, policy_version 49862 (0.0008) -[2023-10-10 22:46:20,941][98560] Updated weights for policy 1, policy_version 49872 (0.0008) -[2023-10-10 22:46:21,300][98560] Updated weights for policy 1, policy_version 49882 (0.0008) -[2023-10-10 22:46:21,813][98559] Updated weights for policy 0, policy_version 50120 (0.0010) -[2023-10-10 22:46:22,177][98559] Updated weights for policy 0, policy_version 50130 (0.0008) -[2023-10-10 22:46:22,539][98559] Updated weights for policy 0, policy_version 50140 (0.0008) -[2023-10-10 22:46:25,276][98560] Updated weights for policy 1, policy_version 49892 (0.0007) -[2023-10-10 22:46:25,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 102432768. Throughput: 0: 1702.9, 1: 1702.5. Samples: 25616304. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:46:25,557][97672] Avg episode reward: [(0, '-1.120'), (1, '22.540')] -[2023-10-10 22:46:25,641][98560] Updated weights for policy 1, policy_version 49902 (0.0008) -[2023-10-10 22:46:26,015][98560] Updated weights for policy 1, policy_version 49912 (0.0009) -[2023-10-10 22:46:26,467][98559] Updated weights for policy 0, policy_version 50150 (0.0010) -[2023-10-10 22:46:26,832][98559] Updated weights for policy 0, policy_version 50160 (0.0007) -[2023-10-10 22:46:27,205][98559] Updated weights for policy 0, policy_version 50170 (0.0007) -[2023-10-10 22:46:29,961][98560] Updated weights for policy 1, policy_version 49922 (0.0009) -[2023-10-10 22:46:30,333][98560] Updated weights for policy 1, policy_version 49932 (0.0008) -[2023-10-10 22:46:30,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 102498304. Throughput: 0: 1731.7, 1: 1708.1. Samples: 25637596. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:46:30,556][97672] Avg episode reward: [(0, '-1.080'), (1, '22.580')] -[2023-10-10 22:46:30,706][98560] Updated weights for policy 1, policy_version 49942 (0.0011) -[2023-10-10 22:46:31,070][98560] Updated weights for policy 1, policy_version 49952 (0.0007) -[2023-10-10 22:46:31,123][98559] Updated weights for policy 0, policy_version 50180 (0.0007) -[2023-10-10 22:46:31,493][98559] Updated weights for policy 0, policy_version 50190 (0.0008) -[2023-10-10 22:46:31,868][98559] Updated weights for policy 0, policy_version 50200 (0.0008) -[2023-10-10 22:46:35,056][98560] Updated weights for policy 1, policy_version 49962 (0.0008) -[2023-10-10 22:46:35,431][98560] Updated weights for policy 1, policy_version 49972 (0.0008) -[2023-10-10 22:46:35,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 102563840. Throughput: 0: 1730.2, 1: 1707.6. Samples: 25658604. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:46:35,556][97672] Avg episode reward: [(0, '-1.080'), (1, '22.560')] -[2023-10-10 22:46:35,564][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000050208_51412992.pth... -[2023-10-10 22:46:35,605][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000048608_49774592.pth -[2023-10-10 22:46:35,810][98560] Updated weights for policy 1, policy_version 49982 (0.0008) -[2023-10-10 22:46:35,880][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000049984_51183616.pth... -[2023-10-10 22:46:35,882][98559] Updated weights for policy 0, policy_version 50210 (0.0008) -[2023-10-10 22:46:35,908][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000048384_49545216.pth -[2023-10-10 22:46:36,250][98559] Updated weights for policy 0, policy_version 50220 (0.0007) -[2023-10-10 22:46:36,618][98559] Updated weights for policy 0, policy_version 50230 (0.0009) -[2023-10-10 22:46:36,987][98559] Updated weights for policy 0, policy_version 50240 (0.0010) -[2023-10-10 22:46:39,818][98560] Updated weights for policy 1, policy_version 49992 (0.0008) -[2023-10-10 22:46:40,182][98560] Updated weights for policy 1, policy_version 50002 (0.0007) -[2023-10-10 22:46:40,541][98560] Updated weights for policy 1, policy_version 50012 (0.0007) -[2023-10-10 22:46:40,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 102629376. Throughput: 0: 1710.2, 1: 1710.2. Samples: 25667650. Policy #0 lag: (min: 18.0, avg: 18.5, max: 31.0) -[2023-10-10 22:46:40,557][97672] Avg episode reward: [(0, '-1.080'), (1, '22.540')] -[2023-10-10 22:46:41,090][98559] Updated weights for policy 0, policy_version 50250 (0.0007) -[2023-10-10 22:46:41,456][98559] Updated weights for policy 0, policy_version 50260 (0.0007) -[2023-10-10 22:46:41,825][98559] Updated weights for policy 0, policy_version 50270 (0.0008) -[2023-10-10 22:46:44,464][98560] Updated weights for policy 1, policy_version 50022 (0.0009) -[2023-10-10 22:46:44,836][98560] Updated weights for policy 1, policy_version 50032 (0.0008) -[2023-10-10 22:46:45,204][98560] Updated weights for policy 1, policy_version 50042 (0.0007) -[2023-10-10 22:46:45,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 102727680. Throughput: 0: 1723.7, 1: 1707.5. Samples: 25688788. Policy #0 lag: (min: 18.0, avg: 18.5, max: 31.0) -[2023-10-10 22:46:45,556][97672] Avg episode reward: [(0, '-1.080'), (1, '22.540')] -[2023-10-10 22:46:45,800][98559] Updated weights for policy 0, policy_version 50280 (0.0008) -[2023-10-10 22:46:46,159][98559] Updated weights for policy 0, policy_version 50290 (0.0009) -[2023-10-10 22:46:46,518][98559] Updated weights for policy 0, policy_version 50300 (0.0009) -[2023-10-10 22:46:49,100][98560] Updated weights for policy 1, policy_version 50052 (0.0009) -[2023-10-10 22:46:49,466][98560] Updated weights for policy 1, policy_version 50062 (0.0009) -[2023-10-10 22:46:49,841][98560] Updated weights for policy 1, policy_version 50072 (0.0009) -[2023-10-10 22:46:50,528][98559] Updated weights for policy 0, policy_version 50310 (0.0008) -[2023-10-10 22:46:50,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 102793216. Throughput: 0: 1720.6, 1: 1693.2. Samples: 25709174. Policy #0 lag: (min: 18.0, avg: 18.5, max: 31.0) -[2023-10-10 22:46:50,556][97672] Avg episode reward: [(0, '-1.080'), (1, '22.520')] -[2023-10-10 22:46:50,894][98559] Updated weights for policy 0, policy_version 50320 (0.0010) -[2023-10-10 22:46:51,254][98559] Updated weights for policy 0, policy_version 50330 (0.0009) -[2023-10-10 22:46:53,986][98560] Updated weights for policy 1, policy_version 50082 (0.0008) -[2023-10-10 22:46:54,354][98560] Updated weights for policy 1, policy_version 50092 (0.0007) -[2023-10-10 22:46:54,706][98560] Updated weights for policy 1, policy_version 50102 (0.0009) -[2023-10-10 22:46:55,079][98560] Updated weights for policy 1, policy_version 50112 (0.0009) -[2023-10-10 22:46:55,503][98559] Updated weights for policy 0, policy_version 50340 (0.0007) -[2023-10-10 22:46:55,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 102858752. Throughput: 0: 1721.2, 1: 1708.6. Samples: 25719096. Policy #0 lag: (min: 18.0, avg: 18.5, max: 31.0) -[2023-10-10 22:46:55,557][97672] Avg episode reward: [(0, '-1.060'), (1, '22.540')] -[2023-10-10 22:46:55,900][98559] Updated weights for policy 0, policy_version 50350 (0.0007) -[2023-10-10 22:46:56,260][98559] Updated weights for policy 0, policy_version 50360 (0.0009) -[2023-10-10 22:46:59,042][98560] Updated weights for policy 1, policy_version 50122 (0.0007) -[2023-10-10 22:46:59,420][98560] Updated weights for policy 1, policy_version 50132 (0.0009) -[2023-10-10 22:46:59,789][98560] Updated weights for policy 1, policy_version 50142 (0.0007) -[2023-10-10 22:47:00,285][98559] Updated weights for policy 0, policy_version 50370 (0.0009) -[2023-10-10 22:47:00,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 102924288. Throughput: 0: 1713.1, 1: 1706.6. Samples: 25739810. Policy #0 lag: (min: 18.0, avg: 18.5, max: 31.0) -[2023-10-10 22:47:00,557][97672] Avg episode reward: [(0, '-1.060'), (1, '22.600')] -[2023-10-10 22:47:00,645][98559] Updated weights for policy 0, policy_version 50380 (0.0008) -[2023-10-10 22:47:01,011][98559] Updated weights for policy 0, policy_version 50390 (0.0009) -[2023-10-10 22:47:01,376][98559] Updated weights for policy 0, policy_version 50400 (0.0008) -[2023-10-10 22:47:03,864][98560] Updated weights for policy 1, policy_version 50152 (0.0010) -[2023-10-10 22:47:04,239][98560] Updated weights for policy 1, policy_version 50162 (0.0008) -[2023-10-10 22:47:04,604][98560] Updated weights for policy 1, policy_version 50172 (0.0008) -[2023-10-10 22:47:05,330][98559] Updated weights for policy 0, policy_version 50410 (0.0008) -[2023-10-10 22:47:05,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 102989824. Throughput: 0: 1701.0, 1: 1685.4. Samples: 25759370. Policy #0 lag: (min: 18.0, avg: 18.5, max: 31.0) -[2023-10-10 22:47:05,557][97672] Avg episode reward: [(0, '-1.060'), (1, '22.660')] -[2023-10-10 22:47:05,567][98439] Saving new best policy, reward=22.660! -[2023-10-10 22:47:05,706][98559] Updated weights for policy 0, policy_version 50420 (0.0007) -[2023-10-10 22:47:06,081][98559] Updated weights for policy 0, policy_version 50430 (0.0009) -[2023-10-10 22:47:08,435][98560] Updated weights for policy 1, policy_version 50182 (0.0008) -[2023-10-10 22:47:08,801][98560] Updated weights for policy 1, policy_version 50192 (0.0008) -[2023-10-10 22:47:09,168][98560] Updated weights for policy 1, policy_version 50202 (0.0011) -[2023-10-10 22:47:10,057][98559] Updated weights for policy 0, policy_version 50440 (0.0008) -[2023-10-10 22:47:10,433][98559] Updated weights for policy 0, policy_version 50450 (0.0009) -[2023-10-10 22:47:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 103055360. Throughput: 0: 1705.7, 1: 1715.4. Samples: 25770254. Policy #0 lag: (min: 18.0, avg: 18.5, max: 31.0) -[2023-10-10 22:47:10,557][97672] Avg episode reward: [(0, '-1.060'), (1, '22.640')] -[2023-10-10 22:47:10,793][98559] Updated weights for policy 0, policy_version 50460 (0.0008) -[2023-10-10 22:47:13,302][98560] Updated weights for policy 1, policy_version 50212 (0.0010) -[2023-10-10 22:47:13,667][98560] Updated weights for policy 1, policy_version 50222 (0.0008) -[2023-10-10 22:47:14,036][98560] Updated weights for policy 1, policy_version 50232 (0.0011) -[2023-10-10 22:47:14,696][98559] Updated weights for policy 0, policy_version 50470 (0.0008) -[2023-10-10 22:47:15,064][98559] Updated weights for policy 0, policy_version 50480 (0.0009) -[2023-10-10 22:47:15,432][98559] Updated weights for policy 0, policy_version 50490 (0.0008) -[2023-10-10 22:47:15,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 103120896. Throughput: 0: 1711.1, 1: 1698.0. Samples: 25791006. Policy #0 lag: (min: 3.0, avg: 14.9, max: 35.0) -[2023-10-10 22:47:15,556][97672] Avg episode reward: [(0, '-1.060'), (1, '22.660')] -[2023-10-10 22:47:18,070][98560] Updated weights for policy 1, policy_version 50242 (0.0008) -[2023-10-10 22:47:18,438][98560] Updated weights for policy 1, policy_version 50252 (0.0008) -[2023-10-10 22:47:18,798][98560] Updated weights for policy 1, policy_version 50262 (0.0010) -[2023-10-10 22:47:19,166][98560] Updated weights for policy 1, policy_version 50272 (0.0010) -[2023-10-10 22:47:19,212][98559] Updated weights for policy 0, policy_version 50500 (0.0010) -[2023-10-10 22:47:19,587][98559] Updated weights for policy 0, policy_version 50510 (0.0007) -[2023-10-10 22:47:19,955][98559] Updated weights for policy 0, policy_version 50520 (0.0010) -[2023-10-10 22:47:20,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 103219200. Throughput: 0: 1688.6, 1: 1683.2. Samples: 25810334. Policy #0 lag: (min: 3.0, avg: 14.9, max: 35.0) -[2023-10-10 22:47:20,557][97672] Avg episode reward: [(0, '-1.060'), (1, '22.720')] -[2023-10-10 22:47:20,564][98439] Saving new best policy, reward=22.720! -[2023-10-10 22:47:23,174][98560] Updated weights for policy 1, policy_version 50282 (0.0009) -[2023-10-10 22:47:23,542][98560] Updated weights for policy 1, policy_version 50292 (0.0007) -[2023-10-10 22:47:23,893][98559] Updated weights for policy 0, policy_version 50530 (0.0009) -[2023-10-10 22:47:23,910][98560] Updated weights for policy 1, policy_version 50302 (0.0009) -[2023-10-10 22:47:24,259][98559] Updated weights for policy 0, policy_version 50540 (0.0010) -[2023-10-10 22:47:24,615][98559] Updated weights for policy 0, policy_version 50550 (0.0008) -[2023-10-10 22:47:24,988][98559] Updated weights for policy 0, policy_version 50560 (0.0009) -[2023-10-10 22:47:25,556][97672] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 103284736. Throughput: 0: 1720.3, 1: 1713.5. Samples: 25822170. Policy #0 lag: (min: 3.0, avg: 14.9, max: 35.0) -[2023-10-10 22:47:25,557][97672] Avg episode reward: [(0, '-1.020'), (1, '22.740')] -[2023-10-10 22:47:25,559][98439] Saving new best policy, reward=22.740! -[2023-10-10 22:47:27,962][98560] Updated weights for policy 1, policy_version 50312 (0.0011) -[2023-10-10 22:47:28,336][98560] Updated weights for policy 1, policy_version 50322 (0.0009) -[2023-10-10 22:47:28,705][98560] Updated weights for policy 1, policy_version 50332 (0.0008) -[2023-10-10 22:47:28,984][98559] Updated weights for policy 0, policy_version 50570 (0.0008) -[2023-10-10 22:47:29,351][98559] Updated weights for policy 0, policy_version 50580 (0.0007) -[2023-10-10 22:47:29,706][98559] Updated weights for policy 0, policy_version 50590 (0.0009) -[2023-10-10 22:47:30,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 103350272. Throughput: 0: 1706.3, 1: 1685.5. Samples: 25841420. Policy #0 lag: (min: 3.0, avg: 14.9, max: 35.0) -[2023-10-10 22:47:30,557][97672] Avg episode reward: [(0, '-1.020'), (1, '22.800')] -[2023-10-10 22:47:30,559][98439] Saving new best policy, reward=22.800! -[2023-10-10 22:47:32,563][98560] Updated weights for policy 1, policy_version 50342 (0.0007) -[2023-10-10 22:47:32,933][98560] Updated weights for policy 1, policy_version 50352 (0.0008) -[2023-10-10 22:47:33,297][98560] Updated weights for policy 1, policy_version 50362 (0.0008) -[2023-10-10 22:47:33,561][98559] Updated weights for policy 0, policy_version 50600 (0.0008) -[2023-10-10 22:47:33,916][98559] Updated weights for policy 0, policy_version 50610 (0.0010) -[2023-10-10 22:47:34,281][98559] Updated weights for policy 0, policy_version 50620 (0.0009) -[2023-10-10 22:47:35,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 103415808. Throughput: 0: 1696.9, 1: 1700.0. Samples: 25862032. Policy #0 lag: (min: 3.0, avg: 14.9, max: 35.0) -[2023-10-10 22:47:35,556][97672] Avg episode reward: [(0, '-1.020'), (1, '22.800')] -[2023-10-10 22:47:37,373][98560] Updated weights for policy 1, policy_version 50372 (0.0008) -[2023-10-10 22:47:37,737][98560] Updated weights for policy 1, policy_version 50382 (0.0010) -[2023-10-10 22:47:38,108][98560] Updated weights for policy 1, policy_version 50392 (0.0011) -[2023-10-10 22:47:38,291][98559] Updated weights for policy 0, policy_version 50630 (0.0009) -[2023-10-10 22:47:38,655][98559] Updated weights for policy 0, policy_version 50640 (0.0009) -[2023-10-10 22:47:39,035][98559] Updated weights for policy 0, policy_version 50650 (0.0008) -[2023-10-10 22:47:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 103481344. Throughput: 0: 1717.2, 1: 1700.7. Samples: 25872902. Policy #0 lag: (min: 3.0, avg: 14.9, max: 35.0) -[2023-10-10 22:47:40,557][97672] Avg episode reward: [(0, '-1.060'), (1, '22.720')] -[2023-10-10 22:47:42,047][98560] Updated weights for policy 1, policy_version 50402 (0.0010) -[2023-10-10 22:47:42,416][98560] Updated weights for policy 1, policy_version 50412 (0.0008) -[2023-10-10 22:47:42,785][98560] Updated weights for policy 1, policy_version 50422 (0.0007) -[2023-10-10 22:47:42,961][98559] Updated weights for policy 0, policy_version 50660 (0.0008) -[2023-10-10 22:47:43,150][98560] Updated weights for policy 1, policy_version 50432 (0.0008) -[2023-10-10 22:47:43,324][98559] Updated weights for policy 0, policy_version 50670 (0.0007) -[2023-10-10 22:47:43,691][98559] Updated weights for policy 0, policy_version 50680 (0.0008) -[2023-10-10 22:47:45,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 103546880. Throughput: 0: 1704.6, 1: 1684.8. Samples: 25892332. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-10 22:47:45,557][97672] Avg episode reward: [(0, '-1.060'), (1, '22.660')] -[2023-10-10 22:47:47,354][98560] Updated weights for policy 1, policy_version 50442 (0.0009) -[2023-10-10 22:47:47,627][98559] Updated weights for policy 0, policy_version 50690 (0.0008) -[2023-10-10 22:47:47,733][98560] Updated weights for policy 1, policy_version 50452 (0.0009) -[2023-10-10 22:47:47,997][98559] Updated weights for policy 0, policy_version 50700 (0.0008) -[2023-10-10 22:47:48,095][98560] Updated weights for policy 1, policy_version 50462 (0.0007) -[2023-10-10 22:47:48,371][98559] Updated weights for policy 0, policy_version 50710 (0.0008) -[2023-10-10 22:47:48,734][98559] Updated weights for policy 0, policy_version 50720 (0.0008) -[2023-10-10 22:47:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 103612416. Throughput: 0: 1718.8, 1: 1700.4. Samples: 25913236. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-10 22:47:50,557][97672] Avg episode reward: [(0, '-1.060'), (1, '22.580')] -[2023-10-10 22:47:52,187][98560] Updated weights for policy 1, policy_version 50472 (0.0010) -[2023-10-10 22:47:52,553][98560] Updated weights for policy 1, policy_version 50482 (0.0009) -[2023-10-10 22:47:52,793][98559] Updated weights for policy 0, policy_version 50730 (0.0009) -[2023-10-10 22:47:52,911][98560] Updated weights for policy 1, policy_version 50492 (0.0009) -[2023-10-10 22:47:53,152][98559] Updated weights for policy 0, policy_version 50740 (0.0007) -[2023-10-10 22:47:53,521][98559] Updated weights for policy 0, policy_version 50750 (0.0008) -[2023-10-10 22:47:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 103677952. Throughput: 0: 1716.8, 1: 1679.2. Samples: 25923076. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-10 22:47:55,557][97672] Avg episode reward: [(0, '-1.060'), (1, '22.580')] -[2023-10-10 22:47:56,967][98560] Updated weights for policy 1, policy_version 50502 (0.0010) -[2023-10-10 22:47:57,341][98560] Updated weights for policy 1, policy_version 50512 (0.0009) -[2023-10-10 22:47:57,564][98559] Updated weights for policy 0, policy_version 50760 (0.0008) -[2023-10-10 22:47:57,708][98560] Updated weights for policy 1, policy_version 50522 (0.0008) -[2023-10-10 22:47:57,927][98559] Updated weights for policy 0, policy_version 50770 (0.0009) -[2023-10-10 22:47:58,288][98559] Updated weights for policy 0, policy_version 50780 (0.0011) -[2023-10-10 22:48:00,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 103743488. Throughput: 0: 1700.0, 1: 1683.7. Samples: 25943276. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-10 22:48:00,557][97672] Avg episode reward: [(0, '-1.060'), (1, '22.580')] -[2023-10-10 22:48:01,672][98560] Updated weights for policy 1, policy_version 50532 (0.0009) -[2023-10-10 22:48:02,047][98560] Updated weights for policy 1, policy_version 50542 (0.0007) -[2023-10-10 22:48:02,350][98559] Updated weights for policy 0, policy_version 50790 (0.0008) -[2023-10-10 22:48:02,407][98560] Updated weights for policy 1, policy_version 50552 (0.0007) -[2023-10-10 22:48:02,709][98559] Updated weights for policy 0, policy_version 50800 (0.0008) -[2023-10-10 22:48:03,073][98559] Updated weights for policy 0, policy_version 50810 (0.0008) -[2023-10-10 22:48:05,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 103809024. Throughput: 0: 1722.7, 1: 1698.2. Samples: 25964276. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-10 22:48:05,557][97672] Avg episode reward: [(0, '-1.020'), (1, '22.540')] -[2023-10-10 22:48:06,441][98560] Updated weights for policy 1, policy_version 50562 (0.0007) -[2023-10-10 22:48:06,812][98560] Updated weights for policy 1, policy_version 50572 (0.0009) -[2023-10-10 22:48:07,109][98559] Updated weights for policy 0, policy_version 50820 (0.0009) -[2023-10-10 22:48:07,179][98560] Updated weights for policy 1, policy_version 50582 (0.0009) -[2023-10-10 22:48:07,469][98559] Updated weights for policy 0, policy_version 50830 (0.0007) -[2023-10-10 22:48:07,551][98560] Updated weights for policy 1, policy_version 50592 (0.0011) -[2023-10-10 22:48:07,836][98559] Updated weights for policy 0, policy_version 50840 (0.0011) -[2023-10-10 22:48:10,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 103874560. Throughput: 0: 1693.1, 1: 1670.4. Samples: 25973528. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-10 22:48:10,557][97672] Avg episode reward: [(0, '-1.020'), (1, '22.580')] -[2023-10-10 22:48:11,582][98560] Updated weights for policy 1, policy_version 50602 (0.0010) -[2023-10-10 22:48:11,955][98559] Updated weights for policy 0, policy_version 50850 (0.0010) -[2023-10-10 22:48:11,964][98560] Updated weights for policy 1, policy_version 50612 (0.0010) -[2023-10-10 22:48:12,320][98559] Updated weights for policy 0, policy_version 50860 (0.0007) -[2023-10-10 22:48:12,330][98560] Updated weights for policy 1, policy_version 50622 (0.0008) -[2023-10-10 22:48:12,694][98559] Updated weights for policy 0, policy_version 50870 (0.0008) -[2023-10-10 22:48:13,058][98559] Updated weights for policy 0, policy_version 50880 (0.0008) -[2023-10-10 22:48:15,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 103940096. Throughput: 0: 1706.8, 1: 1696.2. Samples: 25994554. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-10 22:48:15,556][97672] Avg episode reward: [(0, '-1.020'), (1, '22.560')] -[2023-10-10 22:48:16,410][98560] Updated weights for policy 1, policy_version 50632 (0.0008) -[2023-10-10 22:48:16,778][98559] Updated weights for policy 0, policy_version 50890 (0.0007) -[2023-10-10 22:48:16,782][98560] Updated weights for policy 1, policy_version 50642 (0.0009) -[2023-10-10 22:48:17,134][98559] Updated weights for policy 0, policy_version 50900 (0.0010) -[2023-10-10 22:48:17,142][98560] Updated weights for policy 1, policy_version 50652 (0.0009) -[2023-10-10 22:48:17,505][98559] Updated weights for policy 0, policy_version 50910 (0.0010) -[2023-10-10 22:48:20,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 104005632. Throughput: 0: 1720.7, 1: 1695.8. Samples: 26015776. Policy #0 lag: (min: 17.0, avg: 22.8, max: 49.0) -[2023-10-10 22:48:20,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.520')] -[2023-10-10 22:48:21,039][98560] Updated weights for policy 1, policy_version 50662 (0.0008) -[2023-10-10 22:48:21,407][98560] Updated weights for policy 1, policy_version 50672 (0.0008) -[2023-10-10 22:48:21,589][98559] Updated weights for policy 0, policy_version 50920 (0.0008) -[2023-10-10 22:48:21,771][98560] Updated weights for policy 1, policy_version 50682 (0.0008) -[2023-10-10 22:48:21,953][98559] Updated weights for policy 0, policy_version 50930 (0.0008) -[2023-10-10 22:48:22,321][98559] Updated weights for policy 0, policy_version 50940 (0.0008) -[2023-10-10 22:48:25,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 104071168. Throughput: 0: 1696.9, 1: 1678.8. Samples: 26024810. Policy #0 lag: (min: 17.0, avg: 22.8, max: 49.0) -[2023-10-10 22:48:25,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.520')] -[2023-10-10 22:48:25,690][98560] Updated weights for policy 1, policy_version 50692 (0.0008) -[2023-10-10 22:48:26,069][98560] Updated weights for policy 1, policy_version 50702 (0.0009) -[2023-10-10 22:48:26,351][98559] Updated weights for policy 0, policy_version 50950 (0.0010) -[2023-10-10 22:48:26,432][98560] Updated weights for policy 1, policy_version 50712 (0.0009) -[2023-10-10 22:48:26,718][98559] Updated weights for policy 0, policy_version 50960 (0.0009) -[2023-10-10 22:48:27,085][98559] Updated weights for policy 0, policy_version 50970 (0.0012) -[2023-10-10 22:48:30,529][98560] Updated weights for policy 1, policy_version 50722 (0.0009) -[2023-10-10 22:48:30,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 104136704. Throughput: 0: 1717.7, 1: 1699.7. Samples: 26046114. Policy #0 lag: (min: 17.0, avg: 22.8, max: 49.0) -[2023-10-10 22:48:30,556][97672] Avg episode reward: [(0, '-0.940'), (1, '22.580')] -[2023-10-10 22:48:30,889][98560] Updated weights for policy 1, policy_version 50732 (0.0009) -[2023-10-10 22:48:30,983][98559] Updated weights for policy 0, policy_version 50980 (0.0009) -[2023-10-10 22:48:31,264][98560] Updated weights for policy 1, policy_version 50742 (0.0009) -[2023-10-10 22:48:31,348][98559] Updated weights for policy 0, policy_version 50990 (0.0008) -[2023-10-10 22:48:31,627][98560] Updated weights for policy 1, policy_version 50752 (0.0009) -[2023-10-10 22:48:31,724][98559] Updated weights for policy 0, policy_version 51000 (0.0010) -[2023-10-10 22:48:35,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 104202240. Throughput: 0: 1715.3, 1: 1707.4. Samples: 26067256. Policy #0 lag: (min: 17.0, avg: 22.8, max: 49.0) -[2023-10-10 22:48:35,556][97672] Avg episode reward: [(0, '-0.940'), (1, '22.580')] -[2023-10-10 22:48:35,685][98560] Updated weights for policy 1, policy_version 50762 (0.0009) -[2023-10-10 22:48:35,709][98559] Updated weights for policy 0, policy_version 51010 (0.0008) -[2023-10-10 22:48:36,042][98560] Updated weights for policy 1, policy_version 50772 (0.0009) -[2023-10-10 22:48:36,084][98559] Updated weights for policy 0, policy_version 51020 (0.0008) -[2023-10-10 22:48:36,407][98560] Updated weights for policy 1, policy_version 50782 (0.0009) -[2023-10-10 22:48:36,445][98559] Updated weights for policy 0, policy_version 51030 (0.0009) -[2023-10-10 22:48:36,479][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000050784_52002816.pth... -[2023-10-10 22:48:36,508][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000049184_50364416.pth -[2023-10-10 22:48:36,804][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000051040_52264960.pth... -[2023-10-10 22:48:36,809][98559] Updated weights for policy 0, policy_version 51040 (0.0010) -[2023-10-10 22:48:36,844][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000049408_50593792.pth -[2023-10-10 22:48:40,501][98560] Updated weights for policy 1, policy_version 50792 (0.0008) -[2023-10-10 22:48:40,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 104267776. Throughput: 0: 1707.1, 1: 1698.0. Samples: 26076302. Policy #0 lag: (min: 17.0, avg: 22.8, max: 49.0) -[2023-10-10 22:48:40,556][97672] Avg episode reward: [(0, '-0.940'), (1, '22.640')] -[2023-10-10 22:48:40,796][98559] Updated weights for policy 0, policy_version 51050 (0.0007) -[2023-10-10 22:48:40,866][98560] Updated weights for policy 1, policy_version 50802 (0.0009) -[2023-10-10 22:48:41,165][98559] Updated weights for policy 0, policy_version 51060 (0.0008) -[2023-10-10 22:48:41,246][98560] Updated weights for policy 1, policy_version 50812 (0.0009) -[2023-10-10 22:48:41,532][98559] Updated weights for policy 0, policy_version 51070 (0.0010) -[2023-10-10 22:48:45,344][98560] Updated weights for policy 1, policy_version 50822 (0.0009) -[2023-10-10 22:48:45,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 104333312. Throughput: 0: 1715.4, 1: 1703.6. Samples: 26097132. Policy #0 lag: (min: 17.0, avg: 22.8, max: 49.0) -[2023-10-10 22:48:45,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.660')] -[2023-10-10 22:48:45,668][98559] Updated weights for policy 0, policy_version 51080 (0.0008) -[2023-10-10 22:48:45,714][98560] Updated weights for policy 1, policy_version 50832 (0.0008) -[2023-10-10 22:48:46,032][98559] Updated weights for policy 0, policy_version 51090 (0.0007) -[2023-10-10 22:48:46,085][98560] Updated weights for policy 1, policy_version 50842 (0.0007) -[2023-10-10 22:48:46,394][98559] Updated weights for policy 0, policy_version 51100 (0.0008) -[2023-10-10 22:48:50,224][98560] Updated weights for policy 1, policy_version 50852 (0.0008) -[2023-10-10 22:48:50,351][98559] Updated weights for policy 0, policy_version 51110 (0.0009) -[2023-10-10 22:48:50,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 104398848. Throughput: 0: 1707.9, 1: 1699.5. Samples: 26117608. Policy #0 lag: (min: 17.0, avg: 22.8, max: 49.0) -[2023-10-10 22:48:50,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.680')] -[2023-10-10 22:48:50,586][98560] Updated weights for policy 1, policy_version 50862 (0.0008) -[2023-10-10 22:48:50,711][98559] Updated weights for policy 0, policy_version 51120 (0.0009) -[2023-10-10 22:48:50,958][98560] Updated weights for policy 1, policy_version 50872 (0.0007) -[2023-10-10 22:48:51,073][98559] Updated weights for policy 0, policy_version 51130 (0.0007) -[2023-10-10 22:48:55,030][98560] Updated weights for policy 1, policy_version 50882 (0.0007) -[2023-10-10 22:48:55,141][98559] Updated weights for policy 0, policy_version 51140 (0.0008) -[2023-10-10 22:48:55,395][98560] Updated weights for policy 1, policy_version 50892 (0.0007) -[2023-10-10 22:48:55,507][98559] Updated weights for policy 0, policy_version 51150 (0.0008) -[2023-10-10 22:48:55,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 104464384. Throughput: 0: 1712.1, 1: 1696.0. Samples: 26126892. Policy #0 lag: (min: 25.0, avg: 30.0, max: 57.0) -[2023-10-10 22:48:55,556][97672] Avg episode reward: [(0, '-0.960'), (1, '22.660')] -[2023-10-10 22:48:55,761][98560] Updated weights for policy 1, policy_version 50902 (0.0009) -[2023-10-10 22:48:55,869][98559] Updated weights for policy 0, policy_version 51160 (0.0008) -[2023-10-10 22:48:56,129][98560] Updated weights for policy 1, policy_version 50912 (0.0008) -[2023-10-10 22:48:59,900][98559] Updated weights for policy 0, policy_version 51170 (0.0007) -[2023-10-10 22:49:00,174][98560] Updated weights for policy 1, policy_version 50922 (0.0008) -[2023-10-10 22:49:00,267][98559] Updated weights for policy 0, policy_version 51180 (0.0008) -[2023-10-10 22:49:00,538][98560] Updated weights for policy 1, policy_version 50932 (0.0008) -[2023-10-10 22:49:00,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 104529920. Throughput: 0: 1714.4, 1: 1694.9. Samples: 26147976. Policy #0 lag: (min: 25.0, avg: 30.0, max: 57.0) -[2023-10-10 22:49:00,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.580')] -[2023-10-10 22:49:00,640][98559] Updated weights for policy 0, policy_version 51190 (0.0008) -[2023-10-10 22:49:00,909][98560] Updated weights for policy 1, policy_version 50942 (0.0010) -[2023-10-10 22:49:00,996][98559] Updated weights for policy 0, policy_version 51200 (0.0007) -[2023-10-10 22:49:04,874][98560] Updated weights for policy 1, policy_version 50952 (0.0008) -[2023-10-10 22:49:05,121][98559] Updated weights for policy 0, policy_version 51210 (0.0011) -[2023-10-10 22:49:05,242][98560] Updated weights for policy 1, policy_version 50962 (0.0008) -[2023-10-10 22:49:05,498][98559] Updated weights for policy 0, policy_version 51220 (0.0009) -[2023-10-10 22:49:05,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 104595456. Throughput: 0: 1691.6, 1: 1694.4. Samples: 26168144. Policy #0 lag: (min: 25.0, avg: 30.0, max: 57.0) -[2023-10-10 22:49:05,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.560')] -[2023-10-10 22:49:05,605][98560] Updated weights for policy 1, policy_version 50972 (0.0008) -[2023-10-10 22:49:05,867][98559] Updated weights for policy 0, policy_version 51230 (0.0010) -[2023-10-10 22:49:09,644][98560] Updated weights for policy 1, policy_version 50982 (0.0010) -[2023-10-10 22:49:09,937][98559] Updated weights for policy 0, policy_version 51240 (0.0008) -[2023-10-10 22:49:10,015][98560] Updated weights for policy 1, policy_version 50992 (0.0007) -[2023-10-10 22:49:10,292][98559] Updated weights for policy 0, policy_version 51250 (0.0009) -[2023-10-10 22:49:10,386][98560] Updated weights for policy 1, policy_version 51002 (0.0009) -[2023-10-10 22:49:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 104660992. Throughput: 0: 1707.7, 1: 1692.5. Samples: 26177820. Policy #0 lag: (min: 25.0, avg: 30.0, max: 57.0) -[2023-10-10 22:49:10,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.600')] -[2023-10-10 22:49:10,660][98559] Updated weights for policy 0, policy_version 51260 (0.0008) -[2023-10-10 22:49:14,563][98560] Updated weights for policy 1, policy_version 51012 (0.0008) -[2023-10-10 22:49:14,606][98559] Updated weights for policy 0, policy_version 51270 (0.0009) -[2023-10-10 22:49:14,923][98560] Updated weights for policy 1, policy_version 51022 (0.0009) -[2023-10-10 22:49:14,969][98559] Updated weights for policy 0, policy_version 51280 (0.0008) -[2023-10-10 22:49:15,296][98560] Updated weights for policy 1, policy_version 51032 (0.0007) -[2023-10-10 22:49:15,341][98559] Updated weights for policy 0, policy_version 51290 (0.0008) -[2023-10-10 22:49:15,556][97672] Fps is (10 sec: 16384.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 104759296. Throughput: 0: 1707.1, 1: 1679.7. Samples: 26198518. Policy #0 lag: (min: 25.0, avg: 30.0, max: 57.0) -[2023-10-10 22:49:15,556][97672] Avg episode reward: [(0, '-0.960'), (1, '22.620')] -[2023-10-10 22:49:19,271][98559] Updated weights for policy 0, policy_version 51300 (0.0007) -[2023-10-10 22:49:19,373][98560] Updated weights for policy 1, policy_version 51042 (0.0007) -[2023-10-10 22:49:19,636][98559] Updated weights for policy 0, policy_version 51310 (0.0008) -[2023-10-10 22:49:19,736][98560] Updated weights for policy 1, policy_version 51052 (0.0008) -[2023-10-10 22:49:20,005][98559] Updated weights for policy 0, policy_version 51320 (0.0009) -[2023-10-10 22:49:20,102][98560] Updated weights for policy 1, policy_version 51062 (0.0009) -[2023-10-10 22:49:20,472][98560] Updated weights for policy 1, policy_version 51072 (0.0007) -[2023-10-10 22:49:20,556][97672] Fps is (10 sec: 19659.9, 60 sec: 14199.4, 300 sec: 13773.6). Total num frames: 104857600. Throughput: 0: 1677.6, 1: 1668.3. Samples: 26217822. Policy #0 lag: (min: 25.0, avg: 30.0, max: 57.0) -[2023-10-10 22:49:20,558][97672] Avg episode reward: [(0, '-0.960'), (1, '22.520')] -[2023-10-10 22:49:24,011][98559] Updated weights for policy 0, policy_version 51330 (0.0008) -[2023-10-10 22:49:24,406][98559] Updated weights for policy 0, policy_version 51340 (0.0009) -[2023-10-10 22:49:24,552][98560] Updated weights for policy 1, policy_version 51082 (0.0009) -[2023-10-10 22:49:24,763][98559] Updated weights for policy 0, policy_version 51350 (0.0008) -[2023-10-10 22:49:24,914][98560] Updated weights for policy 1, policy_version 51092 (0.0009) -[2023-10-10 22:49:25,134][98559] Updated weights for policy 0, policy_version 51360 (0.0009) -[2023-10-10 22:49:25,276][98560] Updated weights for policy 1, policy_version 51102 (0.0007) -[2023-10-10 22:49:25,556][97672] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 104923136. Throughput: 0: 1711.7, 1: 1679.5. Samples: 26228908. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) -[2023-10-10 22:49:25,556][97672] Avg episode reward: [(0, '-0.960'), (1, '22.540')] -[2023-10-10 22:49:29,098][98559] Updated weights for policy 0, policy_version 51370 (0.0007) -[2023-10-10 22:49:29,392][98560] Updated weights for policy 1, policy_version 51112 (0.0009) -[2023-10-10 22:49:29,462][98559] Updated weights for policy 0, policy_version 51380 (0.0008) -[2023-10-10 22:49:29,768][98560] Updated weights for policy 1, policy_version 51122 (0.0007) -[2023-10-10 22:49:29,825][98559] Updated weights for policy 0, policy_version 51390 (0.0008) -[2023-10-10 22:49:30,137][98560] Updated weights for policy 1, policy_version 51132 (0.0009) -[2023-10-10 22:49:30,556][97672] Fps is (10 sec: 13107.9, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 104988672. Throughput: 0: 1698.2, 1: 1678.4. Samples: 26249078. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) -[2023-10-10 22:49:30,556][97672] Avg episode reward: [(0, '-0.960'), (1, '22.500')] -[2023-10-10 22:49:33,798][98559] Updated weights for policy 0, policy_version 51400 (0.0007) -[2023-10-10 22:49:34,168][98559] Updated weights for policy 0, policy_version 51410 (0.0008) -[2023-10-10 22:49:34,171][98560] Updated weights for policy 1, policy_version 51142 (0.0010) -[2023-10-10 22:49:34,538][98559] Updated weights for policy 0, policy_version 51420 (0.0009) -[2023-10-10 22:49:34,539][98560] Updated weights for policy 1, policy_version 51152 (0.0009) -[2023-10-10 22:49:34,912][98560] Updated weights for policy 1, policy_version 51162 (0.0008) -[2023-10-10 22:49:35,556][97672] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 105054208. Throughput: 0: 1694.8, 1: 1663.7. Samples: 26268742. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) -[2023-10-10 22:49:35,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.380')] -[2023-10-10 22:49:38,437][98559] Updated weights for policy 0, policy_version 51430 (0.0008) -[2023-10-10 22:49:38,813][98559] Updated weights for policy 0, policy_version 51440 (0.0007) -[2023-10-10 22:49:39,076][98560] Updated weights for policy 1, policy_version 51172 (0.0008) -[2023-10-10 22:49:39,185][98559] Updated weights for policy 0, policy_version 51450 (0.0008) -[2023-10-10 22:49:39,442][98560] Updated weights for policy 1, policy_version 51182 (0.0007) -[2023-10-10 22:49:39,797][98560] Updated weights for policy 1, policy_version 51192 (0.0009) -[2023-10-10 22:49:40,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 105119744. Throughput: 0: 1721.0, 1: 1680.7. Samples: 26279970. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) -[2023-10-10 22:49:40,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.340')] -[2023-10-10 22:49:43,032][98559] Updated weights for policy 0, policy_version 51460 (0.0007) -[2023-10-10 22:49:43,402][98559] Updated weights for policy 0, policy_version 51470 (0.0007) -[2023-10-10 22:49:43,772][98559] Updated weights for policy 0, policy_version 51480 (0.0007) -[2023-10-10 22:49:43,783][98560] Updated weights for policy 1, policy_version 51202 (0.0007) -[2023-10-10 22:49:44,151][98560] Updated weights for policy 1, policy_version 51212 (0.0009) -[2023-10-10 22:49:44,525][98560] Updated weights for policy 1, policy_version 51222 (0.0009) -[2023-10-10 22:49:44,888][98560] Updated weights for policy 1, policy_version 51232 (0.0007) -[2023-10-10 22:49:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 105185280. Throughput: 0: 1698.8, 1: 1682.9. Samples: 26300150. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) -[2023-10-10 22:49:45,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.360')] -[2023-10-10 22:49:47,795][98559] Updated weights for policy 0, policy_version 51490 (0.0007) -[2023-10-10 22:49:48,157][98559] Updated weights for policy 0, policy_version 51500 (0.0008) -[2023-10-10 22:49:48,525][98559] Updated weights for policy 0, policy_version 51510 (0.0009) -[2023-10-10 22:49:48,875][98560] Updated weights for policy 1, policy_version 51242 (0.0007) -[2023-10-10 22:49:48,892][98559] Updated weights for policy 0, policy_version 51520 (0.0007) -[2023-10-10 22:49:49,235][98560] Updated weights for policy 1, policy_version 51252 (0.0007) -[2023-10-10 22:49:49,607][98560] Updated weights for policy 1, policy_version 51262 (0.0007) -[2023-10-10 22:49:50,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 105250816. Throughput: 0: 1716.4, 1: 1656.3. Samples: 26319912. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) -[2023-10-10 22:49:50,556][97672] Avg episode reward: [(0, '-0.960'), (1, '22.400')] -[2023-10-10 22:49:52,799][98559] Updated weights for policy 0, policy_version 51530 (0.0008) -[2023-10-10 22:49:53,156][98559] Updated weights for policy 0, policy_version 51540 (0.0007) -[2023-10-10 22:49:53,521][98559] Updated weights for policy 0, policy_version 51550 (0.0010) -[2023-10-10 22:49:53,618][98560] Updated weights for policy 1, policy_version 51272 (0.0007) -[2023-10-10 22:49:53,983][98560] Updated weights for policy 1, policy_version 51282 (0.0007) -[2023-10-10 22:49:54,359][98560] Updated weights for policy 1, policy_version 51292 (0.0008) -[2023-10-10 22:49:55,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 105316352. Throughput: 0: 1711.1, 1: 1683.9. Samples: 26330596. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) -[2023-10-10 22:49:55,556][97672] Avg episode reward: [(0, '-0.940'), (1, '22.400')] -[2023-10-10 22:49:57,566][98559] Updated weights for policy 0, policy_version 51560 (0.0010) -[2023-10-10 22:49:57,923][98559] Updated weights for policy 0, policy_version 51570 (0.0011) -[2023-10-10 22:49:58,291][98559] Updated weights for policy 0, policy_version 51580 (0.0010) -[2023-10-10 22:49:58,475][98560] Updated weights for policy 1, policy_version 51302 (0.0008) -[2023-10-10 22:49:58,846][98560] Updated weights for policy 1, policy_version 51312 (0.0008) -[2023-10-10 22:49:59,222][98560] Updated weights for policy 1, policy_version 51322 (0.0010) -[2023-10-10 22:50:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 105381888. Throughput: 0: 1704.8, 1: 1682.0. Samples: 26350922. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-10 22:50:00,556][97672] Avg episode reward: [(0, '-0.940'), (1, '22.360')] -[2023-10-10 22:50:02,249][98559] Updated weights for policy 0, policy_version 51590 (0.0009) -[2023-10-10 22:50:02,607][98559] Updated weights for policy 0, policy_version 51600 (0.0008) -[2023-10-10 22:50:02,984][98559] Updated weights for policy 0, policy_version 51610 (0.0010) -[2023-10-10 22:50:03,247][98560] Updated weights for policy 1, policy_version 51332 (0.0007) -[2023-10-10 22:50:03,622][98560] Updated weights for policy 1, policy_version 51342 (0.0007) -[2023-10-10 22:50:03,988][98560] Updated weights for policy 1, policy_version 51352 (0.0009) -[2023-10-10 22:50:05,556][97672] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 105447424. Throughput: 0: 1730.8, 1: 1674.7. Samples: 26371068. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-10 22:50:05,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.460')] -[2023-10-10 22:50:06,988][98559] Updated weights for policy 0, policy_version 51620 (0.0009) -[2023-10-10 22:50:07,347][98559] Updated weights for policy 0, policy_version 51630 (0.0007) -[2023-10-10 22:50:07,720][98559] Updated weights for policy 0, policy_version 51640 (0.0008) -[2023-10-10 22:50:07,876][98560] Updated weights for policy 1, policy_version 51362 (0.0009) -[2023-10-10 22:50:08,253][98560] Updated weights for policy 1, policy_version 51372 (0.0010) -[2023-10-10 22:50:08,607][98560] Updated weights for policy 1, policy_version 51382 (0.0010) -[2023-10-10 22:50:08,981][98560] Updated weights for policy 1, policy_version 51392 (0.0010) -[2023-10-10 22:50:10,556][97672] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 105512960. Throughput: 0: 1696.4, 1: 1697.1. Samples: 26381620. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-10 22:50:10,558][97672] Avg episode reward: [(0, '-0.940'), (1, '22.460')] -[2023-10-10 22:50:11,789][98559] Updated weights for policy 0, policy_version 51650 (0.0008) -[2023-10-10 22:50:12,159][98559] Updated weights for policy 0, policy_version 51660 (0.0010) -[2023-10-10 22:50:12,524][98559] Updated weights for policy 0, policy_version 51670 (0.0009) -[2023-10-10 22:50:12,894][98559] Updated weights for policy 0, policy_version 51680 (0.0010) -[2023-10-10 22:50:13,055][98560] Updated weights for policy 1, policy_version 51402 (0.0008) -[2023-10-10 22:50:13,419][98560] Updated weights for policy 1, policy_version 51412 (0.0010) -[2023-10-10 22:50:13,782][98560] Updated weights for policy 1, policy_version 51422 (0.0011) -[2023-10-10 22:50:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 105578496. Throughput: 0: 1710.3, 1: 1677.4. Samples: 26401524. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-10 22:50:15,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.460')] -[2023-10-10 22:50:16,789][98559] Updated weights for policy 0, policy_version 51690 (0.0009) -[2023-10-10 22:50:17,146][98559] Updated weights for policy 0, policy_version 51700 (0.0009) -[2023-10-10 22:50:17,518][98559] Updated weights for policy 0, policy_version 51710 (0.0009) -[2023-10-10 22:50:17,845][98560] Updated weights for policy 1, policy_version 51432 (0.0009) -[2023-10-10 22:50:18,212][98560] Updated weights for policy 1, policy_version 51442 (0.0009) -[2023-10-10 22:50:18,572][98560] Updated weights for policy 1, policy_version 51452 (0.0009) -[2023-10-10 22:50:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 105644032. Throughput: 0: 1723.2, 1: 1687.7. Samples: 26422232. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-10 22:50:20,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.420')] -[2023-10-10 22:50:21,516][98559] Updated weights for policy 0, policy_version 51720 (0.0011) -[2023-10-10 22:50:21,885][98559] Updated weights for policy 0, policy_version 51730 (0.0009) -[2023-10-10 22:50:22,253][98559] Updated weights for policy 0, policy_version 51740 (0.0008) -[2023-10-10 22:50:22,537][98560] Updated weights for policy 1, policy_version 51462 (0.0008) -[2023-10-10 22:50:22,904][98560] Updated weights for policy 1, policy_version 51472 (0.0009) -[2023-10-10 22:50:23,264][98560] Updated weights for policy 1, policy_version 51482 (0.0009) -[2023-10-10 22:50:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 105709568. Throughput: 0: 1695.4, 1: 1693.7. Samples: 26432480. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-10 22:50:25,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.360')] -[2023-10-10 22:50:26,101][98559] Updated weights for policy 0, policy_version 51750 (0.0008) -[2023-10-10 22:50:26,473][98559] Updated weights for policy 0, policy_version 51760 (0.0010) -[2023-10-10 22:50:26,839][98559] Updated weights for policy 0, policy_version 51770 (0.0010) -[2023-10-10 22:50:27,235][98560] Updated weights for policy 1, policy_version 51492 (0.0009) -[2023-10-10 22:50:27,614][98560] Updated weights for policy 1, policy_version 51502 (0.0009) -[2023-10-10 22:50:27,983][98560] Updated weights for policy 1, policy_version 51512 (0.0008) -[2023-10-10 22:50:30,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 105775104. Throughput: 0: 1721.0, 1: 1674.7. Samples: 26452956. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-10 22:50:30,556][97672] Avg episode reward: [(0, '-0.940'), (1, '22.380')] -[2023-10-10 22:50:30,756][98559] Updated weights for policy 0, policy_version 51780 (0.0008) -[2023-10-10 22:50:31,121][98559] Updated weights for policy 0, policy_version 51790 (0.0009) -[2023-10-10 22:50:31,488][98559] Updated weights for policy 0, policy_version 51800 (0.0011) -[2023-10-10 22:50:31,938][98560] Updated weights for policy 1, policy_version 51522 (0.0008) -[2023-10-10 22:50:32,307][98560] Updated weights for policy 1, policy_version 51532 (0.0010) -[2023-10-10 22:50:32,668][98560] Updated weights for policy 1, policy_version 51542 (0.0008) -[2023-10-10 22:50:33,038][98560] Updated weights for policy 1, policy_version 51552 (0.0008) -[2023-10-10 22:50:35,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 105840640. Throughput: 0: 1719.9, 1: 1706.2. Samples: 26474084. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 22:50:35,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.380')] -[2023-10-10 22:50:35,564][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000051552_52789248.pth... -[2023-10-10 22:50:35,599][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000049984_51183616.pth -[2023-10-10 22:50:35,694][98559] Updated weights for policy 0, policy_version 51810 (0.0009) -[2023-10-10 22:50:36,066][98559] Updated weights for policy 0, policy_version 51820 (0.0008) -[2023-10-10 22:50:36,428][98559] Updated weights for policy 0, policy_version 51830 (0.0008) -[2023-10-10 22:50:36,795][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000051840_53084160.pth... -[2023-10-10 22:50:36,796][98559] Updated weights for policy 0, policy_version 51840 (0.0008) -[2023-10-10 22:50:36,823][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000050208_51412992.pth -[2023-10-10 22:50:37,051][98560] Updated weights for policy 1, policy_version 51562 (0.0010) -[2023-10-10 22:50:37,417][98560] Updated weights for policy 1, policy_version 51572 (0.0009) -[2023-10-10 22:50:37,771][98560] Updated weights for policy 1, policy_version 51582 (0.0007) -[2023-10-10 22:50:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 105906176. Throughput: 0: 1711.3, 1: 1687.3. Samples: 26483532. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 22:50:40,556][97672] Avg episode reward: [(0, '-0.920'), (1, '22.320')] -[2023-10-10 22:50:40,895][98559] Updated weights for policy 0, policy_version 51850 (0.0009) -[2023-10-10 22:50:41,257][98559] Updated weights for policy 0, policy_version 51860 (0.0007) -[2023-10-10 22:50:41,638][98559] Updated weights for policy 0, policy_version 51870 (0.0009) -[2023-10-10 22:50:41,821][98560] Updated weights for policy 1, policy_version 51592 (0.0009) -[2023-10-10 22:50:42,187][98560] Updated weights for policy 1, policy_version 51602 (0.0008) -[2023-10-10 22:50:42,559][98560] Updated weights for policy 1, policy_version 51612 (0.0010) -[2023-10-10 22:50:45,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 105971712. Throughput: 0: 1712.6, 1: 1692.1. Samples: 26504134. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 22:50:45,556][97672] Avg episode reward: [(0, '-0.960'), (1, '22.260')] -[2023-10-10 22:50:45,695][98559] Updated weights for policy 0, policy_version 51880 (0.0007) -[2023-10-10 22:50:46,067][98559] Updated weights for policy 0, policy_version 51890 (0.0009) -[2023-10-10 22:50:46,430][98559] Updated weights for policy 0, policy_version 51900 (0.0010) -[2023-10-10 22:50:46,615][98560] Updated weights for policy 1, policy_version 51622 (0.0008) -[2023-10-10 22:50:46,983][98560] Updated weights for policy 1, policy_version 51632 (0.0009) -[2023-10-10 22:50:47,345][98560] Updated weights for policy 1, policy_version 51642 (0.0009) -[2023-10-10 22:50:50,340][98559] Updated weights for policy 0, policy_version 51910 (0.0009) -[2023-10-10 22:50:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 106037248. Throughput: 0: 1708.7, 1: 1708.2. Samples: 26524828. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 22:50:50,556][97672] Avg episode reward: [(0, '-0.960'), (1, '22.160')] -[2023-10-10 22:50:50,707][98559] Updated weights for policy 0, policy_version 51920 (0.0009) -[2023-10-10 22:50:51,071][98559] Updated weights for policy 0, policy_version 51930 (0.0008) -[2023-10-10 22:50:51,407][98560] Updated weights for policy 1, policy_version 51652 (0.0009) -[2023-10-10 22:50:51,770][98560] Updated weights for policy 1, policy_version 51662 (0.0007) -[2023-10-10 22:50:52,134][98560] Updated weights for policy 1, policy_version 51672 (0.0007) -[2023-10-10 22:50:55,131][98559] Updated weights for policy 0, policy_version 51940 (0.0008) -[2023-10-10 22:50:55,502][98559] Updated weights for policy 0, policy_version 51950 (0.0008) -[2023-10-10 22:50:55,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 106102784. Throughput: 0: 1719.9, 1: 1677.6. Samples: 26534506. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 22:50:55,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.200')] -[2023-10-10 22:50:55,859][98559] Updated weights for policy 0, policy_version 51960 (0.0009) -[2023-10-10 22:50:56,087][98560] Updated weights for policy 1, policy_version 51682 (0.0007) -[2023-10-10 22:50:56,457][98560] Updated weights for policy 1, policy_version 51692 (0.0009) -[2023-10-10 22:50:56,834][98560] Updated weights for policy 1, policy_version 51702 (0.0010) -[2023-10-10 22:50:57,198][98560] Updated weights for policy 1, policy_version 51712 (0.0009) -[2023-10-10 22:50:59,850][98559] Updated weights for policy 0, policy_version 51970 (0.0007) -[2023-10-10 22:51:00,260][98559] Updated weights for policy 0, policy_version 51980 (0.0011) -[2023-10-10 22:51:00,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 106168320. Throughput: 0: 1719.2, 1: 1704.3. Samples: 26555580. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 22:51:00,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.140')] -[2023-10-10 22:51:00,626][98559] Updated weights for policy 0, policy_version 51990 (0.0011) -[2023-10-10 22:51:00,995][98559] Updated weights for policy 0, policy_version 52000 (0.0009) -[2023-10-10 22:51:01,295][98560] Updated weights for policy 1, policy_version 51722 (0.0008) -[2023-10-10 22:51:01,666][98560] Updated weights for policy 1, policy_version 51732 (0.0008) -[2023-10-10 22:51:02,028][98560] Updated weights for policy 1, policy_version 51742 (0.0007) -[2023-10-10 22:51:04,977][98559] Updated weights for policy 0, policy_version 52010 (0.0008) -[2023-10-10 22:51:05,343][98559] Updated weights for policy 0, policy_version 52020 (0.0009) -[2023-10-10 22:51:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 106233856. Throughput: 0: 1697.3, 1: 1718.1. Samples: 26575926. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 22:51:05,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.220')] -[2023-10-10 22:51:05,706][98559] Updated weights for policy 0, policy_version 52030 (0.0009) -[2023-10-10 22:51:05,916][98560] Updated weights for policy 1, policy_version 51752 (0.0007) -[2023-10-10 22:51:06,286][98560] Updated weights for policy 1, policy_version 51762 (0.0008) -[2023-10-10 22:51:06,647][98560] Updated weights for policy 1, policy_version 51772 (0.0007) -[2023-10-10 22:51:09,770][98559] Updated weights for policy 0, policy_version 52040 (0.0008) -[2023-10-10 22:51:10,143][98559] Updated weights for policy 0, policy_version 52050 (0.0007) -[2023-10-10 22:51:10,507][98559] Updated weights for policy 0, policy_version 52060 (0.0009) -[2023-10-10 22:51:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 106299392. Throughput: 0: 1710.5, 1: 1696.4. Samples: 26585794. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-10 22:51:10,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.180')] -[2023-10-10 22:51:10,610][98560] Updated weights for policy 1, policy_version 51782 (0.0008) -[2023-10-10 22:51:10,968][98560] Updated weights for policy 1, policy_version 51792 (0.0010) -[2023-10-10 22:51:11,335][98560] Updated weights for policy 1, policy_version 51802 (0.0011) -[2023-10-10 22:51:14,457][98559] Updated weights for policy 0, policy_version 52070 (0.0010) -[2023-10-10 22:51:14,829][98559] Updated weights for policy 0, policy_version 52080 (0.0008) -[2023-10-10 22:51:15,191][98559] Updated weights for policy 0, policy_version 52090 (0.0009) -[2023-10-10 22:51:15,375][98560] Updated weights for policy 1, policy_version 51812 (0.0009) -[2023-10-10 22:51:15,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 106397696. Throughput: 0: 1704.5, 1: 1717.1. Samples: 26606928. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-10 22:51:15,556][97672] Avg episode reward: [(0, '-0.980'), (1, '22.180')] -[2023-10-10 22:51:15,741][98560] Updated weights for policy 1, policy_version 51822 (0.0009) -[2023-10-10 22:51:16,105][98560] Updated weights for policy 1, policy_version 51832 (0.0009) -[2023-10-10 22:51:19,079][98559] Updated weights for policy 0, policy_version 52100 (0.0008) -[2023-10-10 22:51:19,456][98559] Updated weights for policy 0, policy_version 52110 (0.0011) -[2023-10-10 22:51:19,821][98559] Updated weights for policy 0, policy_version 52120 (0.0007) -[2023-10-10 22:51:20,098][98560] Updated weights for policy 1, policy_version 51842 (0.0008) -[2023-10-10 22:51:20,473][98560] Updated weights for policy 1, policy_version 51852 (0.0008) -[2023-10-10 22:51:20,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 106463232. Throughput: 0: 1682.2, 1: 1718.8. Samples: 26627130. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-10 22:51:20,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.200')] -[2023-10-10 22:51:20,842][98560] Updated weights for policy 1, policy_version 51862 (0.0007) -[2023-10-10 22:51:21,207][98560] Updated weights for policy 1, policy_version 51872 (0.0008) -[2023-10-10 22:51:23,866][98559] Updated weights for policy 0, policy_version 52130 (0.0007) -[2023-10-10 22:51:24,226][98559] Updated weights for policy 0, policy_version 52140 (0.0007) -[2023-10-10 22:51:24,600][98559] Updated weights for policy 0, policy_version 52150 (0.0008) -[2023-10-10 22:51:24,967][98559] Updated weights for policy 0, policy_version 52160 (0.0007) -[2023-10-10 22:51:25,274][98560] Updated weights for policy 1, policy_version 51882 (0.0007) -[2023-10-10 22:51:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 106528768. Throughput: 0: 1714.6, 1: 1715.1. Samples: 26637872. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-10 22:51:25,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.200')] -[2023-10-10 22:51:25,636][98560] Updated weights for policy 1, policy_version 51892 (0.0010) -[2023-10-10 22:51:25,994][98560] Updated weights for policy 1, policy_version 51902 (0.0009) -[2023-10-10 22:51:28,867][98559] Updated weights for policy 0, policy_version 52170 (0.0008) -[2023-10-10 22:51:29,234][98559] Updated weights for policy 0, policy_version 52180 (0.0010) -[2023-10-10 22:51:29,610][98559] Updated weights for policy 0, policy_version 52190 (0.0010) -[2023-10-10 22:51:29,984][98560] Updated weights for policy 1, policy_version 51912 (0.0010) -[2023-10-10 22:51:30,353][98560] Updated weights for policy 1, policy_version 51922 (0.0009) -[2023-10-10 22:51:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 106594304. Throughput: 0: 1701.5, 1: 1716.6. Samples: 26657946. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-10 22:51:30,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.240')] -[2023-10-10 22:51:30,727][98560] Updated weights for policy 1, policy_version 51932 (0.0010) -[2023-10-10 22:51:33,610][98559] Updated weights for policy 0, policy_version 52200 (0.0008) -[2023-10-10 22:51:33,981][98559] Updated weights for policy 0, policy_version 52210 (0.0009) -[2023-10-10 22:51:34,349][98559] Updated weights for policy 0, policy_version 52220 (0.0009) -[2023-10-10 22:51:34,650][98560] Updated weights for policy 1, policy_version 51942 (0.0009) -[2023-10-10 22:51:35,018][98560] Updated weights for policy 1, policy_version 51952 (0.0011) -[2023-10-10 22:51:35,392][98560] Updated weights for policy 1, policy_version 51962 (0.0009) -[2023-10-10 22:51:35,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 106659840. Throughput: 0: 1696.5, 1: 1714.9. Samples: 26678340. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-10 22:51:35,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.220')] -[2023-10-10 22:51:38,372][98559] Updated weights for policy 0, policy_version 52230 (0.0009) -[2023-10-10 22:51:38,735][98559] Updated weights for policy 0, policy_version 52240 (0.0007) -[2023-10-10 22:51:39,092][98559] Updated weights for policy 0, policy_version 52250 (0.0008) -[2023-10-10 22:51:39,462][98560] Updated weights for policy 1, policy_version 51972 (0.0009) -[2023-10-10 22:51:39,820][98560] Updated weights for policy 1, policy_version 51982 (0.0007) -[2023-10-10 22:51:40,192][98560] Updated weights for policy 1, policy_version 51992 (0.0010) -[2023-10-10 22:51:40,556][97672] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 106758144. Throughput: 0: 1712.1, 1: 1720.3. Samples: 26688964. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-10 22:51:40,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.060')] -[2023-10-10 22:51:43,041][98559] Updated weights for policy 0, policy_version 52260 (0.0010) -[2023-10-10 22:51:43,400][98559] Updated weights for policy 0, policy_version 52270 (0.0009) -[2023-10-10 22:51:43,767][98559] Updated weights for policy 0, policy_version 52280 (0.0007) -[2023-10-10 22:51:44,173][98560] Updated weights for policy 1, policy_version 52002 (0.0011) -[2023-10-10 22:51:44,541][98560] Updated weights for policy 1, policy_version 52012 (0.0007) -[2023-10-10 22:51:44,898][98560] Updated weights for policy 1, policy_version 52022 (0.0009) -[2023-10-10 22:51:45,263][98560] Updated weights for policy 1, policy_version 52032 (0.0008) -[2023-10-10 22:51:45,556][97672] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 106823680. Throughput: 0: 1687.6, 1: 1719.9. Samples: 26708916. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-10 22:51:45,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.000')] -[2023-10-10 22:51:47,715][98559] Updated weights for policy 0, policy_version 52290 (0.0008) -[2023-10-10 22:51:48,122][98559] Updated weights for policy 0, policy_version 52300 (0.0009) -[2023-10-10 22:51:48,496][98559] Updated weights for policy 0, policy_version 52310 (0.0008) -[2023-10-10 22:51:48,852][98559] Updated weights for policy 0, policy_version 52320 (0.0008) -[2023-10-10 22:51:49,353][98560] Updated weights for policy 1, policy_version 52042 (0.0009) -[2023-10-10 22:51:49,712][98560] Updated weights for policy 1, policy_version 52052 (0.0009) -[2023-10-10 22:51:50,082][98560] Updated weights for policy 1, policy_version 52062 (0.0010) -[2023-10-10 22:51:50,556][97672] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 106889216. Throughput: 0: 1708.0, 1: 1695.9. Samples: 26729102. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-10 22:51:50,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.060')] -[2023-10-10 22:51:52,822][98559] Updated weights for policy 0, policy_version 52330 (0.0007) -[2023-10-10 22:51:53,184][98559] Updated weights for policy 0, policy_version 52340 (0.0007) -[2023-10-10 22:51:53,556][98559] Updated weights for policy 0, policy_version 52350 (0.0008) -[2023-10-10 22:51:54,032][98560] Updated weights for policy 1, policy_version 52072 (0.0008) -[2023-10-10 22:51:54,396][98560] Updated weights for policy 1, policy_version 52082 (0.0009) -[2023-10-10 22:51:54,766][98560] Updated weights for policy 1, policy_version 52092 (0.0010) -[2023-10-10 22:51:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 106954752. Throughput: 0: 1701.6, 1: 1713.2. Samples: 26739462. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-10 22:51:55,557][97672] Avg episode reward: [(0, '-0.940'), (1, '21.980')] -[2023-10-10 22:51:57,618][98559] Updated weights for policy 0, policy_version 52360 (0.0008) -[2023-10-10 22:51:57,982][98559] Updated weights for policy 0, policy_version 52370 (0.0007) -[2023-10-10 22:51:58,351][98559] Updated weights for policy 0, policy_version 52380 (0.0009) -[2023-10-10 22:51:58,793][98560] Updated weights for policy 1, policy_version 52102 (0.0008) -[2023-10-10 22:51:59,158][98560] Updated weights for policy 1, policy_version 52112 (0.0007) -[2023-10-10 22:51:59,529][98560] Updated weights for policy 1, policy_version 52122 (0.0009) -[2023-10-10 22:52:00,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 107020288. Throughput: 0: 1702.1, 1: 1706.9. Samples: 26760336. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-10 22:52:00,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.140')] -[2023-10-10 22:52:02,219][98559] Updated weights for policy 0, policy_version 52390 (0.0008) -[2023-10-10 22:52:02,591][98559] Updated weights for policy 0, policy_version 52400 (0.0008) -[2023-10-10 22:52:02,952][98559] Updated weights for policy 0, policy_version 52410 (0.0008) -[2023-10-10 22:52:03,616][98560] Updated weights for policy 1, policy_version 52132 (0.0009) -[2023-10-10 22:52:03,979][98560] Updated weights for policy 1, policy_version 52142 (0.0007) -[2023-10-10 22:52:04,352][98560] Updated weights for policy 1, policy_version 52152 (0.0007) -[2023-10-10 22:52:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 107085824. Throughput: 0: 1728.4, 1: 1673.9. Samples: 26780230. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-10 22:52:05,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.040')] -[2023-10-10 22:52:06,842][98559] Updated weights for policy 0, policy_version 52420 (0.0010) -[2023-10-10 22:52:07,210][98559] Updated weights for policy 0, policy_version 52430 (0.0007) -[2023-10-10 22:52:07,576][98559] Updated weights for policy 0, policy_version 52440 (0.0009) -[2023-10-10 22:52:08,261][98560] Updated weights for policy 1, policy_version 52162 (0.0008) -[2023-10-10 22:52:08,637][98560] Updated weights for policy 1, policy_version 52172 (0.0009) -[2023-10-10 22:52:08,994][98560] Updated weights for policy 1, policy_version 52182 (0.0009) -[2023-10-10 22:52:09,368][98560] Updated weights for policy 1, policy_version 52192 (0.0011) -[2023-10-10 22:52:10,556][97672] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 107151360. Throughput: 0: 1699.3, 1: 1703.1. Samples: 26790982. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-10 22:52:10,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.120')] -[2023-10-10 22:52:11,636][98559] Updated weights for policy 0, policy_version 52450 (0.0008) -[2023-10-10 22:52:12,018][98559] Updated weights for policy 0, policy_version 52460 (0.0009) -[2023-10-10 22:52:12,381][98559] Updated weights for policy 0, policy_version 52470 (0.0009) -[2023-10-10 22:52:12,759][98559] Updated weights for policy 0, policy_version 52480 (0.0009) -[2023-10-10 22:52:13,393][98560] Updated weights for policy 1, policy_version 52202 (0.0007) -[2023-10-10 22:52:13,766][98560] Updated weights for policy 1, policy_version 52212 (0.0007) -[2023-10-10 22:52:14,141][98560] Updated weights for policy 1, policy_version 52222 (0.0007) -[2023-10-10 22:52:15,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 107216896. Throughput: 0: 1720.6, 1: 1688.7. Samples: 26811364. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-10 22:52:15,556][97672] Avg episode reward: [(0, '-0.960'), (1, '22.180')] -[2023-10-10 22:52:16,703][98559] Updated weights for policy 0, policy_version 52490 (0.0009) -[2023-10-10 22:52:17,074][98559] Updated weights for policy 0, policy_version 52500 (0.0010) -[2023-10-10 22:52:17,442][98559] Updated weights for policy 0, policy_version 52510 (0.0011) -[2023-10-10 22:52:18,133][98560] Updated weights for policy 1, policy_version 52232 (0.0009) -[2023-10-10 22:52:18,499][98560] Updated weights for policy 1, policy_version 52242 (0.0007) -[2023-10-10 22:52:18,865][98560] Updated weights for policy 1, policy_version 52252 (0.0008) -[2023-10-10 22:52:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 107282432. Throughput: 0: 1734.4, 1: 1677.5. Samples: 26831872. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:52:20,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.200')] -[2023-10-10 22:52:21,405][98559] Updated weights for policy 0, policy_version 52520 (0.0008) -[2023-10-10 22:52:21,777][98559] Updated weights for policy 0, policy_version 52530 (0.0008) -[2023-10-10 22:52:22,141][98559] Updated weights for policy 0, policy_version 52540 (0.0010) -[2023-10-10 22:52:22,858][98560] Updated weights for policy 1, policy_version 52262 (0.0009) -[2023-10-10 22:52:23,227][98560] Updated weights for policy 1, policy_version 52272 (0.0008) -[2023-10-10 22:52:23,590][98560] Updated weights for policy 1, policy_version 52282 (0.0008) -[2023-10-10 22:52:25,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 107347968. Throughput: 0: 1709.9, 1: 1699.6. Samples: 26842388. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:52:25,556][97672] Avg episode reward: [(0, '-0.960'), (1, '22.360')] -[2023-10-10 22:52:25,907][98559] Updated weights for policy 0, policy_version 52550 (0.0009) -[2023-10-10 22:52:26,276][98559] Updated weights for policy 0, policy_version 52560 (0.0009) -[2023-10-10 22:52:26,645][98559] Updated weights for policy 0, policy_version 52570 (0.0009) -[2023-10-10 22:52:27,670][98560] Updated weights for policy 1, policy_version 52292 (0.0007) -[2023-10-10 22:52:28,029][98560] Updated weights for policy 1, policy_version 52302 (0.0010) -[2023-10-10 22:52:28,397][98560] Updated weights for policy 1, policy_version 52312 (0.0010) -[2023-10-10 22:52:30,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 107413504. Throughput: 0: 1733.7, 1: 1674.9. Samples: 26862298. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:52:30,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.360')] -[2023-10-10 22:52:30,822][98559] Updated weights for policy 0, policy_version 52580 (0.0008) -[2023-10-10 22:52:31,186][98559] Updated weights for policy 0, policy_version 52590 (0.0009) -[2023-10-10 22:52:31,552][98559] Updated weights for policy 0, policy_version 52600 (0.0010) -[2023-10-10 22:52:32,320][98560] Updated weights for policy 1, policy_version 52322 (0.0010) -[2023-10-10 22:52:32,687][98560] Updated weights for policy 1, policy_version 52332 (0.0010) -[2023-10-10 22:52:33,049][98560] Updated weights for policy 1, policy_version 52342 (0.0010) -[2023-10-10 22:52:33,422][98560] Updated weights for policy 1, policy_version 52352 (0.0008) -[2023-10-10 22:52:35,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 107479040. Throughput: 0: 1736.5, 1: 1695.7. Samples: 26883550. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:52:35,556][97672] Avg episode reward: [(0, '-0.940'), (1, '22.320')] -[2023-10-10 22:52:35,564][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000052352_53608448.pth... -[2023-10-10 22:52:35,590][98559] Updated weights for policy 0, policy_version 52610 (0.0009) -[2023-10-10 22:52:35,593][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000050784_52002816.pth -[2023-10-10 22:52:36,006][98559] Updated weights for policy 0, policy_version 52620 (0.0008) -[2023-10-10 22:52:36,380][98559] Updated weights for policy 0, policy_version 52630 (0.0008) -[2023-10-10 22:52:36,740][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000052640_53903360.pth... -[2023-10-10 22:52:36,744][98559] Updated weights for policy 0, policy_version 52640 (0.0008) -[2023-10-10 22:52:36,777][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000051040_52264960.pth -[2023-10-10 22:52:37,651][98560] Updated weights for policy 1, policy_version 52362 (0.0008) -[2023-10-10 22:52:38,023][98560] Updated weights for policy 1, policy_version 52372 (0.0010) -[2023-10-10 22:52:38,389][98560] Updated weights for policy 1, policy_version 52382 (0.0009) -[2023-10-10 22:52:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 107544576. Throughput: 0: 1725.9, 1: 1693.7. Samples: 26893342. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:52:40,556][97672] Avg episode reward: [(0, '-0.940'), (1, '22.400')] -[2023-10-10 22:52:40,726][98559] Updated weights for policy 0, policy_version 52650 (0.0008) -[2023-10-10 22:52:41,101][98559] Updated weights for policy 0, policy_version 52660 (0.0011) -[2023-10-10 22:52:41,463][98559] Updated weights for policy 0, policy_version 52670 (0.0009) -[2023-10-10 22:52:42,473][98560] Updated weights for policy 1, policy_version 52392 (0.0008) -[2023-10-10 22:52:42,841][98560] Updated weights for policy 1, policy_version 52402 (0.0008) -[2023-10-10 22:52:43,201][98560] Updated weights for policy 1, policy_version 52412 (0.0008) -[2023-10-10 22:52:45,334][98559] Updated weights for policy 0, policy_version 52680 (0.0009) -[2023-10-10 22:52:45,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 107610112. Throughput: 0: 1727.5, 1: 1676.9. Samples: 26913530. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:52:45,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.360')] -[2023-10-10 22:52:45,694][98559] Updated weights for policy 0, policy_version 52690 (0.0008) -[2023-10-10 22:52:46,064][98559] Updated weights for policy 0, policy_version 52700 (0.0008) -[2023-10-10 22:52:47,215][98560] Updated weights for policy 1, policy_version 52422 (0.0010) -[2023-10-10 22:52:47,573][98560] Updated weights for policy 1, policy_version 52432 (0.0010) -[2023-10-10 22:52:47,948][98560] Updated weights for policy 1, policy_version 52442 (0.0010) -[2023-10-10 22:52:49,918][98559] Updated weights for policy 0, policy_version 52710 (0.0008) -[2023-10-10 22:52:50,281][98559] Updated weights for policy 0, policy_version 52720 (0.0007) -[2023-10-10 22:52:50,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 107675648. Throughput: 0: 1712.7, 1: 1705.4. Samples: 26934044. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:52:50,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.340')] -[2023-10-10 22:52:50,651][98559] Updated weights for policy 0, policy_version 52730 (0.0009) -[2023-10-10 22:52:52,109][98560] Updated weights for policy 1, policy_version 52452 (0.0008) -[2023-10-10 22:52:52,468][98560] Updated weights for policy 1, policy_version 52462 (0.0008) -[2023-10-10 22:52:52,834][98560] Updated weights for policy 1, policy_version 52472 (0.0008) -[2023-10-10 22:52:54,550][98559] Updated weights for policy 0, policy_version 52740 (0.0009) -[2023-10-10 22:52:54,923][98559] Updated weights for policy 0, policy_version 52750 (0.0008) -[2023-10-10 22:52:55,291][98559] Updated weights for policy 0, policy_version 52760 (0.0010) -[2023-10-10 22:52:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 107741184. Throughput: 0: 1727.2, 1: 1684.5. Samples: 26944512. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:52:55,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.340')] -[2023-10-10 22:52:56,846][98560] Updated weights for policy 1, policy_version 52482 (0.0008) -[2023-10-10 22:52:57,219][98560] Updated weights for policy 1, policy_version 52492 (0.0011) -[2023-10-10 22:52:57,586][98560] Updated weights for policy 1, policy_version 52502 (0.0009) -[2023-10-10 22:52:57,943][98560] Updated weights for policy 1, policy_version 52512 (0.0009) -[2023-10-10 22:52:59,299][98559] Updated weights for policy 0, policy_version 52770 (0.0008) -[2023-10-10 22:52:59,660][98559] Updated weights for policy 0, policy_version 52780 (0.0011) -[2023-10-10 22:53:00,019][98559] Updated weights for policy 0, policy_version 52790 (0.0009) -[2023-10-10 22:53:00,385][98559] Updated weights for policy 0, policy_version 52800 (0.0007) -[2023-10-10 22:53:00,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 107839488. Throughput: 0: 1720.3, 1: 1691.5. Samples: 26964896. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) -[2023-10-10 22:53:00,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.360')] -[2023-10-10 22:53:01,821][98560] Updated weights for policy 1, policy_version 52522 (0.0010) -[2023-10-10 22:53:02,192][98560] Updated weights for policy 1, policy_version 52532 (0.0009) -[2023-10-10 22:53:02,552][98560] Updated weights for policy 1, policy_version 52542 (0.0009) -[2023-10-10 22:53:04,289][98559] Updated weights for policy 0, policy_version 52810 (0.0008) -[2023-10-10 22:53:04,657][98559] Updated weights for policy 0, policy_version 52820 (0.0008) -[2023-10-10 22:53:05,020][98559] Updated weights for policy 0, policy_version 52830 (0.0008) -[2023-10-10 22:53:05,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 107905024. Throughput: 0: 1696.2, 1: 1706.8. Samples: 26985006. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) -[2023-10-10 22:53:05,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.360')] -[2023-10-10 22:53:06,742][98560] Updated weights for policy 1, policy_version 52552 (0.0009) -[2023-10-10 22:53:07,102][98560] Updated weights for policy 1, policy_version 52562 (0.0009) -[2023-10-10 22:53:07,479][98560] Updated weights for policy 1, policy_version 52572 (0.0010) -[2023-10-10 22:53:08,983][98559] Updated weights for policy 0, policy_version 52840 (0.0007) -[2023-10-10 22:53:09,352][98559] Updated weights for policy 0, policy_version 52850 (0.0010) -[2023-10-10 22:53:09,709][98559] Updated weights for policy 0, policy_version 52860 (0.0009) -[2023-10-10 22:53:10,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 107970560. Throughput: 0: 1728.9, 1: 1677.6. Samples: 26995684. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) -[2023-10-10 22:53:10,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.300')] -[2023-10-10 22:53:11,341][98560] Updated weights for policy 1, policy_version 52582 (0.0007) -[2023-10-10 22:53:11,709][98560] Updated weights for policy 1, policy_version 52592 (0.0007) -[2023-10-10 22:53:12,074][98560] Updated weights for policy 1, policy_version 52602 (0.0009) -[2023-10-10 22:53:13,654][98559] Updated weights for policy 0, policy_version 52870 (0.0010) -[2023-10-10 22:53:14,025][98559] Updated weights for policy 0, policy_version 52880 (0.0007) -[2023-10-10 22:53:14,396][98559] Updated weights for policy 0, policy_version 52890 (0.0008) -[2023-10-10 22:53:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 108036096. Throughput: 0: 1709.2, 1: 1701.0. Samples: 27015756. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) -[2023-10-10 22:53:15,556][97672] Avg episode reward: [(0, '-0.940'), (1, '22.280')] -[2023-10-10 22:53:16,076][98560] Updated weights for policy 1, policy_version 52612 (0.0009) -[2023-10-10 22:53:16,438][98560] Updated weights for policy 1, policy_version 52622 (0.0008) -[2023-10-10 22:53:16,805][98560] Updated weights for policy 1, policy_version 52632 (0.0008) -[2023-10-10 22:53:18,323][98559] Updated weights for policy 0, policy_version 52900 (0.0010) -[2023-10-10 22:53:18,693][98559] Updated weights for policy 0, policy_version 52910 (0.0009) -[2023-10-10 22:53:19,048][98559] Updated weights for policy 0, policy_version 52920 (0.0009) -[2023-10-10 22:53:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 108101632. Throughput: 0: 1699.2, 1: 1701.6. Samples: 27036586. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) -[2023-10-10 22:53:20,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.360')] -[2023-10-10 22:53:20,759][98560] Updated weights for policy 1, policy_version 52642 (0.0007) -[2023-10-10 22:53:21,130][98560] Updated weights for policy 1, policy_version 52652 (0.0007) -[2023-10-10 22:53:21,491][98560] Updated weights for policy 1, policy_version 52662 (0.0008) -[2023-10-10 22:53:21,863][98560] Updated weights for policy 1, policy_version 52672 (0.0009) -[2023-10-10 22:53:23,048][98559] Updated weights for policy 0, policy_version 52930 (0.0008) -[2023-10-10 22:53:23,444][98559] Updated weights for policy 0, policy_version 52940 (0.0009) -[2023-10-10 22:53:23,798][98559] Updated weights for policy 0, policy_version 52950 (0.0007) -[2023-10-10 22:53:24,166][98559] Updated weights for policy 0, policy_version 52960 (0.0007) -[2023-10-10 22:53:25,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 108167168. Throughput: 0: 1723.4, 1: 1687.2. Samples: 27046820. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) -[2023-10-10 22:53:25,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.320')] -[2023-10-10 22:53:25,960][98560] Updated weights for policy 1, policy_version 52682 (0.0009) -[2023-10-10 22:53:26,330][98560] Updated weights for policy 1, policy_version 52692 (0.0008) -[2023-10-10 22:53:26,687][98560] Updated weights for policy 1, policy_version 52702 (0.0008) -[2023-10-10 22:53:28,141][98559] Updated weights for policy 0, policy_version 52970 (0.0011) -[2023-10-10 22:53:28,509][98559] Updated weights for policy 0, policy_version 52980 (0.0008) -[2023-10-10 22:53:28,877][98559] Updated weights for policy 0, policy_version 52990 (0.0007) -[2023-10-10 22:53:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 108232704. Throughput: 0: 1702.8, 1: 1703.2. Samples: 27066798. Policy #0 lag: (min: 22.0, avg: 27.6, max: 54.0) -[2023-10-10 22:53:30,557][97672] Avg episode reward: [(0, '-0.920'), (1, '22.280')] -[2023-10-10 22:53:30,838][98560] Updated weights for policy 1, policy_version 52712 (0.0009) -[2023-10-10 22:53:31,198][98560] Updated weights for policy 1, policy_version 52722 (0.0010) -[2023-10-10 22:53:31,564][98560] Updated weights for policy 1, policy_version 52732 (0.0010) -[2023-10-10 22:53:32,901][98559] Updated weights for policy 0, policy_version 53000 (0.0010) -[2023-10-10 22:53:33,269][98559] Updated weights for policy 0, policy_version 53010 (0.0009) -[2023-10-10 22:53:33,639][98559] Updated weights for policy 0, policy_version 53020 (0.0011) -[2023-10-10 22:53:35,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 108298240. Throughput: 0: 1716.8, 1: 1699.3. Samples: 27087770. Policy #0 lag: (min: 22.0, avg: 27.6, max: 54.0) -[2023-10-10 22:53:35,557][97672] Avg episode reward: [(0, '-0.920'), (1, '22.340')] -[2023-10-10 22:53:35,566][98560] Updated weights for policy 1, policy_version 52742 (0.0008) -[2023-10-10 22:53:35,936][98560] Updated weights for policy 1, policy_version 52752 (0.0009) -[2023-10-10 22:53:36,310][98560] Updated weights for policy 1, policy_version 52762 (0.0008) -[2023-10-10 22:53:37,471][98559] Updated weights for policy 0, policy_version 53030 (0.0009) -[2023-10-10 22:53:37,833][98559] Updated weights for policy 0, policy_version 53040 (0.0011) -[2023-10-10 22:53:38,204][98559] Updated weights for policy 0, policy_version 53050 (0.0011) -[2023-10-10 22:53:40,247][98560] Updated weights for policy 1, policy_version 52772 (0.0008) -[2023-10-10 22:53:40,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 108363776. Throughput: 0: 1704.8, 1: 1691.8. Samples: 27097362. Policy #0 lag: (min: 22.0, avg: 27.6, max: 54.0) -[2023-10-10 22:53:40,557][97672] Avg episode reward: [(0, '-0.920'), (1, '22.420')] -[2023-10-10 22:53:40,621][98560] Updated weights for policy 1, policy_version 52782 (0.0008) -[2023-10-10 22:53:40,991][98560] Updated weights for policy 1, policy_version 52792 (0.0007) -[2023-10-10 22:53:42,346][98559] Updated weights for policy 0, policy_version 53060 (0.0008) -[2023-10-10 22:53:42,718][98559] Updated weights for policy 0, policy_version 53070 (0.0008) -[2023-10-10 22:53:43,077][98559] Updated weights for policy 0, policy_version 53080 (0.0010) -[2023-10-10 22:53:44,889][98560] Updated weights for policy 1, policy_version 52802 (0.0009) -[2023-10-10 22:53:45,253][98560] Updated weights for policy 1, policy_version 52812 (0.0009) -[2023-10-10 22:53:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 108429312. Throughput: 0: 1707.2, 1: 1702.3. Samples: 27118322. Policy #0 lag: (min: 22.0, avg: 27.6, max: 54.0) -[2023-10-10 22:53:45,557][97672] Avg episode reward: [(0, '-0.920'), (1, '22.440')] -[2023-10-10 22:53:45,622][98560] Updated weights for policy 1, policy_version 52822 (0.0007) -[2023-10-10 22:53:45,984][98560] Updated weights for policy 1, policy_version 52832 (0.0007) -[2023-10-10 22:53:47,035][98559] Updated weights for policy 0, policy_version 53090 (0.0007) -[2023-10-10 22:53:47,400][98559] Updated weights for policy 0, policy_version 53100 (0.0008) -[2023-10-10 22:53:47,765][98559] Updated weights for policy 0, policy_version 53110 (0.0008) -[2023-10-10 22:53:48,136][98559] Updated weights for policy 0, policy_version 53120 (0.0009) -[2023-10-10 22:53:49,982][98560] Updated weights for policy 1, policy_version 52842 (0.0010) -[2023-10-10 22:53:50,349][98560] Updated weights for policy 1, policy_version 52852 (0.0010) -[2023-10-10 22:53:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 108494848. Throughput: 0: 1728.1, 1: 1706.2. Samples: 27139550. Policy #0 lag: (min: 22.0, avg: 27.6, max: 54.0) -[2023-10-10 22:53:50,557][97672] Avg episode reward: [(0, '-0.920'), (1, '22.420')] -[2023-10-10 22:53:50,726][98560] Updated weights for policy 1, policy_version 52862 (0.0009) -[2023-10-10 22:53:51,999][98559] Updated weights for policy 0, policy_version 53130 (0.0007) -[2023-10-10 22:53:52,351][98559] Updated weights for policy 0, policy_version 53140 (0.0007) -[2023-10-10 22:53:52,711][98559] Updated weights for policy 0, policy_version 53150 (0.0007) -[2023-10-10 22:53:54,694][98560] Updated weights for policy 1, policy_version 52872 (0.0009) -[2023-10-10 22:53:55,067][98560] Updated weights for policy 1, policy_version 52882 (0.0008) -[2023-10-10 22:53:55,430][98560] Updated weights for policy 1, policy_version 52892 (0.0008) -[2023-10-10 22:53:55,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 108560384. Throughput: 0: 1698.9, 1: 1712.0. Samples: 27149174. Policy #0 lag: (min: 22.0, avg: 27.6, max: 54.0) -[2023-10-10 22:53:55,557][97672] Avg episode reward: [(0, '-0.920'), (1, '22.420')] -[2023-10-10 22:53:56,724][98559] Updated weights for policy 0, policy_version 53160 (0.0010) -[2023-10-10 22:53:57,097][98559] Updated weights for policy 0, policy_version 53170 (0.0008) -[2023-10-10 22:53:57,452][98559] Updated weights for policy 0, policy_version 53180 (0.0011) -[2023-10-10 22:53:59,477][98560] Updated weights for policy 1, policy_version 52902 (0.0008) -[2023-10-10 22:53:59,838][98560] Updated weights for policy 1, policy_version 52912 (0.0008) -[2023-10-10 22:54:00,208][98560] Updated weights for policy 1, policy_version 52922 (0.0010) -[2023-10-10 22:54:00,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 108658688. Throughput: 0: 1719.0, 1: 1713.7. Samples: 27170226. Policy #0 lag: (min: 22.0, avg: 27.6, max: 54.0) -[2023-10-10 22:54:00,557][97672] Avg episode reward: [(0, '-0.920'), (1, '22.480')] -[2023-10-10 22:54:01,584][98559] Updated weights for policy 0, policy_version 53190 (0.0008) -[2023-10-10 22:54:01,947][98559] Updated weights for policy 0, policy_version 53200 (0.0008) -[2023-10-10 22:54:02,310][98559] Updated weights for policy 0, policy_version 53210 (0.0010) -[2023-10-10 22:54:04,124][98560] Updated weights for policy 1, policy_version 52932 (0.0011) -[2023-10-10 22:54:04,485][98560] Updated weights for policy 1, policy_version 52942 (0.0011) -[2023-10-10 22:54:04,843][98560] Updated weights for policy 1, policy_version 52952 (0.0011) -[2023-10-10 22:54:05,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 108724224. Throughput: 0: 1728.6, 1: 1692.5. Samples: 27190538. Policy #0 lag: (min: 22.0, avg: 27.6, max: 54.0) -[2023-10-10 22:54:05,556][97672] Avg episode reward: [(0, '-0.920'), (1, '22.540')] -[2023-10-10 22:54:06,249][98559] Updated weights for policy 0, policy_version 53220 (0.0010) -[2023-10-10 22:54:06,620][98559] Updated weights for policy 0, policy_version 53230 (0.0009) -[2023-10-10 22:54:06,978][98559] Updated weights for policy 0, policy_version 53240 (0.0008) -[2023-10-10 22:54:08,899][98560] Updated weights for policy 1, policy_version 52962 (0.0009) -[2023-10-10 22:54:09,258][98560] Updated weights for policy 1, policy_version 52972 (0.0007) -[2023-10-10 22:54:09,632][98560] Updated weights for policy 1, policy_version 52982 (0.0007) -[2023-10-10 22:54:09,995][98560] Updated weights for policy 1, policy_version 52992 (0.0008) -[2023-10-10 22:54:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 108789760. Throughput: 0: 1706.1, 1: 1708.6. Samples: 27200484. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 22:54:10,557][97672] Avg episode reward: [(0, '-0.880'), (1, '22.500')] -[2023-10-10 22:54:10,889][98559] Updated weights for policy 0, policy_version 53250 (0.0008) -[2023-10-10 22:54:11,262][98559] Updated weights for policy 0, policy_version 53260 (0.0008) -[2023-10-10 22:54:11,643][98559] Updated weights for policy 0, policy_version 53270 (0.0009) -[2023-10-10 22:54:12,013][98559] Updated weights for policy 0, policy_version 53280 (0.0009) -[2023-10-10 22:54:14,091][98560] Updated weights for policy 1, policy_version 53002 (0.0008) -[2023-10-10 22:54:14,469][98560] Updated weights for policy 1, policy_version 53012 (0.0010) -[2023-10-10 22:54:14,833][98560] Updated weights for policy 1, policy_version 53022 (0.0011) -[2023-10-10 22:54:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 108855296. Throughput: 0: 1726.2, 1: 1713.1. Samples: 27221568. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 22:54:15,556][97672] Avg episode reward: [(0, '-0.880'), (1, '22.580')] -[2023-10-10 22:54:15,966][98559] Updated weights for policy 0, policy_version 53290 (0.0007) -[2023-10-10 22:54:16,334][98559] Updated weights for policy 0, policy_version 53300 (0.0009) -[2023-10-10 22:54:16,693][98559] Updated weights for policy 0, policy_version 53310 (0.0010) -[2023-10-10 22:54:18,865][98560] Updated weights for policy 1, policy_version 53032 (0.0010) -[2023-10-10 22:54:19,236][98560] Updated weights for policy 1, policy_version 53042 (0.0007) -[2023-10-10 22:54:19,596][98560] Updated weights for policy 1, policy_version 53052 (0.0007) -[2023-10-10 22:54:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 108920832. Throughput: 0: 1726.6, 1: 1690.1. Samples: 27241522. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 22:54:20,557][97672] Avg episode reward: [(0, '-0.880'), (1, '22.540')] -[2023-10-10 22:54:20,680][98559] Updated weights for policy 0, policy_version 53320 (0.0012) -[2023-10-10 22:54:21,039][98559] Updated weights for policy 0, policy_version 53330 (0.0008) -[2023-10-10 22:54:21,405][98559] Updated weights for policy 0, policy_version 53340 (0.0009) -[2023-10-10 22:54:23,541][98560] Updated weights for policy 1, policy_version 53062 (0.0010) -[2023-10-10 22:54:23,910][98560] Updated weights for policy 1, policy_version 53072 (0.0011) -[2023-10-10 22:54:24,274][98560] Updated weights for policy 1, policy_version 53082 (0.0008) -[2023-10-10 22:54:25,348][98559] Updated weights for policy 0, policy_version 53350 (0.0008) -[2023-10-10 22:54:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 108986368. Throughput: 0: 1721.8, 1: 1717.2. Samples: 27252116. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 22:54:25,556][97672] Avg episode reward: [(0, '-0.880'), (1, '22.500')] -[2023-10-10 22:54:25,721][98559] Updated weights for policy 0, policy_version 53360 (0.0008) -[2023-10-10 22:54:26,081][98559] Updated weights for policy 0, policy_version 53370 (0.0007) -[2023-10-10 22:54:28,252][98560] Updated weights for policy 1, policy_version 53092 (0.0008) -[2023-10-10 22:54:28,612][98560] Updated weights for policy 1, policy_version 53102 (0.0007) -[2023-10-10 22:54:28,980][98560] Updated weights for policy 1, policy_version 53112 (0.0007) -[2023-10-10 22:54:29,929][98559] Updated weights for policy 0, policy_version 53380 (0.0008) -[2023-10-10 22:54:30,284][98559] Updated weights for policy 0, policy_version 53390 (0.0007) -[2023-10-10 22:54:30,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 109051904. Throughput: 0: 1728.2, 1: 1702.0. Samples: 27272678. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 22:54:30,557][97672] Avg episode reward: [(0, '-0.880'), (1, '22.440')] -[2023-10-10 22:54:30,658][98559] Updated weights for policy 0, policy_version 53400 (0.0007) -[2023-10-10 22:54:32,919][98560] Updated weights for policy 1, policy_version 53122 (0.0008) -[2023-10-10 22:54:33,282][98560] Updated weights for policy 1, policy_version 53132 (0.0010) -[2023-10-10 22:54:33,645][98560] Updated weights for policy 1, policy_version 53142 (0.0011) -[2023-10-10 22:54:34,009][98560] Updated weights for policy 1, policy_version 53152 (0.0010) -[2023-10-10 22:54:34,712][98559] Updated weights for policy 0, policy_version 53410 (0.0009) -[2023-10-10 22:54:35,082][98559] Updated weights for policy 0, policy_version 53420 (0.0008) -[2023-10-10 22:54:35,458][98559] Updated weights for policy 0, policy_version 53430 (0.0009) -[2023-10-10 22:54:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 109117440. Throughput: 0: 1712.0, 1: 1682.2. Samples: 27292288. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 22:54:35,556][97672] Avg episode reward: [(0, '-0.880'), (1, '22.420')] -[2023-10-10 22:54:35,564][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000053152_54427648.pth... -[2023-10-10 22:54:35,599][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000051552_52789248.pth -[2023-10-10 22:54:35,825][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000053440_54722560.pth... -[2023-10-10 22:54:35,829][98559] Updated weights for policy 0, policy_version 53440 (0.0011) -[2023-10-10 22:54:35,861][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000051840_53084160.pth -[2023-10-10 22:54:38,147][98560] Updated weights for policy 1, policy_version 53162 (0.0009) -[2023-10-10 22:54:38,518][98560] Updated weights for policy 1, policy_version 53172 (0.0009) -[2023-10-10 22:54:38,888][98560] Updated weights for policy 1, policy_version 53182 (0.0009) -[2023-10-10 22:54:39,696][98559] Updated weights for policy 0, policy_version 53450 (0.0008) -[2023-10-10 22:54:40,071][98559] Updated weights for policy 0, policy_version 53460 (0.0007) -[2023-10-10 22:54:40,434][98559] Updated weights for policy 0, policy_version 53470 (0.0010) -[2023-10-10 22:54:40,556][97672] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 109215744. Throughput: 0: 1728.7, 1: 1706.1. Samples: 27303742. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 22:54:40,557][97672] Avg episode reward: [(0, '-0.880'), (1, '22.460')] -[2023-10-10 22:54:42,887][98560] Updated weights for policy 1, policy_version 53192 (0.0008) -[2023-10-10 22:54:43,242][98560] Updated weights for policy 1, policy_version 53202 (0.0008) -[2023-10-10 22:54:43,602][98560] Updated weights for policy 1, policy_version 53212 (0.0007) -[2023-10-10 22:54:44,471][98559] Updated weights for policy 0, policy_version 53480 (0.0010) -[2023-10-10 22:54:44,834][98559] Updated weights for policy 0, policy_version 53490 (0.0009) -[2023-10-10 22:54:45,200][98559] Updated weights for policy 0, policy_version 53500 (0.0007) -[2023-10-10 22:54:45,556][97672] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 109281280. Throughput: 0: 1726.9, 1: 1681.2. Samples: 27323590. Policy #0 lag: (min: 13.0, avg: 14.7, max: 42.0) -[2023-10-10 22:54:45,556][97672] Avg episode reward: [(0, '-0.880'), (1, '22.580')] -[2023-10-10 22:54:47,605][98560] Updated weights for policy 1, policy_version 53222 (0.0008) -[2023-10-10 22:54:47,969][98560] Updated weights for policy 1, policy_version 53232 (0.0009) -[2023-10-10 22:54:48,336][98560] Updated weights for policy 1, policy_version 53242 (0.0008) -[2023-10-10 22:54:49,168][98559] Updated weights for policy 0, policy_version 53510 (0.0009) -[2023-10-10 22:54:49,535][98559] Updated weights for policy 0, policy_version 53520 (0.0009) -[2023-10-10 22:54:49,907][98559] Updated weights for policy 0, policy_version 53530 (0.0009) -[2023-10-10 22:54:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 109346816. Throughput: 0: 1701.9, 1: 1705.0. Samples: 27343848. Policy #0 lag: (min: 13.0, avg: 14.7, max: 42.0) -[2023-10-10 22:54:50,557][97672] Avg episode reward: [(0, '-0.880'), (1, '22.580')] -[2023-10-10 22:54:52,401][98560] Updated weights for policy 1, policy_version 53252 (0.0008) -[2023-10-10 22:54:52,781][98560] Updated weights for policy 1, policy_version 53262 (0.0007) -[2023-10-10 22:54:53,154][98560] Updated weights for policy 1, policy_version 53272 (0.0007) -[2023-10-10 22:54:53,787][98559] Updated weights for policy 0, policy_version 53540 (0.0009) -[2023-10-10 22:54:54,149][98559] Updated weights for policy 0, policy_version 53550 (0.0008) -[2023-10-10 22:54:54,523][98559] Updated weights for policy 0, policy_version 53560 (0.0008) -[2023-10-10 22:54:55,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 109412352. Throughput: 0: 1733.5, 1: 1708.4. Samples: 27355370. Policy #0 lag: (min: 13.0, avg: 14.7, max: 42.0) -[2023-10-10 22:54:55,557][97672] Avg episode reward: [(0, '-0.860'), (1, '22.560')] -[2023-10-10 22:54:57,087][98560] Updated weights for policy 1, policy_version 53282 (0.0008) -[2023-10-10 22:54:57,458][98560] Updated weights for policy 1, policy_version 53292 (0.0009) -[2023-10-10 22:54:57,830][98560] Updated weights for policy 1, policy_version 53302 (0.0008) -[2023-10-10 22:54:58,189][98560] Updated weights for policy 1, policy_version 53312 (0.0008) -[2023-10-10 22:54:58,332][98559] Updated weights for policy 0, policy_version 53570 (0.0008) -[2023-10-10 22:54:58,717][98559] Updated weights for policy 0, policy_version 53580 (0.0008) -[2023-10-10 22:54:59,080][98559] Updated weights for policy 0, policy_version 53590 (0.0008) -[2023-10-10 22:54:59,447][98559] Updated weights for policy 0, policy_version 53600 (0.0009) -[2023-10-10 22:55:00,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 109477888. Throughput: 0: 1714.2, 1: 1690.7. Samples: 27374786. Policy #0 lag: (min: 13.0, avg: 14.7, max: 42.0) -[2023-10-10 22:55:00,556][97672] Avg episode reward: [(0, '-0.860'), (1, '22.560')] -[2023-10-10 22:55:02,204][98560] Updated weights for policy 1, policy_version 53322 (0.0010) -[2023-10-10 22:55:02,578][98560] Updated weights for policy 1, policy_version 53332 (0.0008) -[2023-10-10 22:55:02,942][98560] Updated weights for policy 1, policy_version 53342 (0.0009) -[2023-10-10 22:55:03,338][98559] Updated weights for policy 0, policy_version 53610 (0.0010) -[2023-10-10 22:55:03,700][98559] Updated weights for policy 0, policy_version 53620 (0.0009) -[2023-10-10 22:55:04,066][98559] Updated weights for policy 0, policy_version 53630 (0.0009) -[2023-10-10 22:55:05,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 109543424. Throughput: 0: 1708.0, 1: 1717.6. Samples: 27395672. Policy #0 lag: (min: 13.0, avg: 14.7, max: 42.0) -[2023-10-10 22:55:05,557][97672] Avg episode reward: [(0, '-0.860'), (1, '22.580')] -[2023-10-10 22:55:06,859][98560] Updated weights for policy 1, policy_version 53352 (0.0010) -[2023-10-10 22:55:07,224][98560] Updated weights for policy 1, policy_version 53362 (0.0011) -[2023-10-10 22:55:07,586][98560] Updated weights for policy 1, policy_version 53372 (0.0007) -[2023-10-10 22:55:08,039][98559] Updated weights for policy 0, policy_version 53640 (0.0009) -[2023-10-10 22:55:08,411][98559] Updated weights for policy 0, policy_version 53650 (0.0009) -[2023-10-10 22:55:08,775][98559] Updated weights for policy 0, policy_version 53660 (0.0009) -[2023-10-10 22:55:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 109608960. Throughput: 0: 1721.8, 1: 1692.6. Samples: 27405764. Policy #0 lag: (min: 13.0, avg: 14.7, max: 42.0) -[2023-10-10 22:55:10,556][97672] Avg episode reward: [(0, '-0.860'), (1, '22.640')] -[2023-10-10 22:55:11,807][98560] Updated weights for policy 1, policy_version 53382 (0.0009) -[2023-10-10 22:55:12,185][98560] Updated weights for policy 1, policy_version 53392 (0.0008) -[2023-10-10 22:55:12,548][98560] Updated weights for policy 1, policy_version 53402 (0.0008) -[2023-10-10 22:55:12,707][98559] Updated weights for policy 0, policy_version 53670 (0.0008) -[2023-10-10 22:55:13,065][98559] Updated weights for policy 0, policy_version 53680 (0.0008) -[2023-10-10 22:55:13,429][98559] Updated weights for policy 0, policy_version 53690 (0.0011) -[2023-10-10 22:55:15,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 109674496. Throughput: 0: 1702.5, 1: 1703.2. Samples: 27425936. Policy #0 lag: (min: 13.0, avg: 14.7, max: 42.0) -[2023-10-10 22:55:15,557][97672] Avg episode reward: [(0, '-0.860'), (1, '22.700')] -[2023-10-10 22:55:16,388][98560] Updated weights for policy 1, policy_version 53412 (0.0009) -[2023-10-10 22:55:16,772][98560] Updated weights for policy 1, policy_version 53422 (0.0008) -[2023-10-10 22:55:17,135][98560] Updated weights for policy 1, policy_version 53432 (0.0008) -[2023-10-10 22:55:17,486][98559] Updated weights for policy 0, policy_version 53700 (0.0010) -[2023-10-10 22:55:17,845][98559] Updated weights for policy 0, policy_version 53710 (0.0007) -[2023-10-10 22:55:18,213][98559] Updated weights for policy 0, policy_version 53720 (0.0008) -[2023-10-10 22:55:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 109740032. Throughput: 0: 1720.0, 1: 1725.7. Samples: 27447348. Policy #0 lag: (min: 13.0, avg: 14.7, max: 42.0) -[2023-10-10 22:55:20,556][97672] Avg episode reward: [(0, '-0.860'), (1, '22.660')] -[2023-10-10 22:55:21,071][98560] Updated weights for policy 1, policy_version 53442 (0.0008) -[2023-10-10 22:55:21,444][98560] Updated weights for policy 1, policy_version 53452 (0.0008) -[2023-10-10 22:55:21,822][98560] Updated weights for policy 1, policy_version 53462 (0.0010) -[2023-10-10 22:55:22,181][98559] Updated weights for policy 0, policy_version 53730 (0.0007) -[2023-10-10 22:55:22,185][98560] Updated weights for policy 1, policy_version 53472 (0.0008) -[2023-10-10 22:55:22,549][98559] Updated weights for policy 0, policy_version 53740 (0.0009) -[2023-10-10 22:55:22,912][98559] Updated weights for policy 0, policy_version 53750 (0.0010) -[2023-10-10 22:55:23,282][98559] Updated weights for policy 0, policy_version 53760 (0.0011) -[2023-10-10 22:55:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 109805568. Throughput: 0: 1702.2, 1: 1693.9. Samples: 27456564. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 22:55:25,557][97672] Avg episode reward: [(0, '-0.860'), (1, '22.620')] -[2023-10-10 22:55:26,117][98560] Updated weights for policy 1, policy_version 53482 (0.0007) -[2023-10-10 22:55:26,487][98560] Updated weights for policy 1, policy_version 53492 (0.0007) -[2023-10-10 22:55:26,852][98560] Updated weights for policy 1, policy_version 53502 (0.0009) -[2023-10-10 22:55:27,226][98559] Updated weights for policy 0, policy_version 53770 (0.0008) -[2023-10-10 22:55:27,585][98559] Updated weights for policy 0, policy_version 53780 (0.0010) -[2023-10-10 22:55:27,953][98559] Updated weights for policy 0, policy_version 53790 (0.0011) -[2023-10-10 22:55:30,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 109871104. Throughput: 0: 1707.6, 1: 1719.8. Samples: 27477824. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 22:55:30,557][97672] Avg episode reward: [(0, '-0.920'), (1, '22.500')] -[2023-10-10 22:55:30,934][98560] Updated weights for policy 1, policy_version 53512 (0.0007) -[2023-10-10 22:55:31,299][98560] Updated weights for policy 1, policy_version 53522 (0.0008) -[2023-10-10 22:55:31,656][98560] Updated weights for policy 1, policy_version 53532 (0.0008) -[2023-10-10 22:55:31,986][98559] Updated weights for policy 0, policy_version 53800 (0.0008) -[2023-10-10 22:55:32,347][98559] Updated weights for policy 0, policy_version 53810 (0.0008) -[2023-10-10 22:55:32,713][98559] Updated weights for policy 0, policy_version 53820 (0.0007) -[2023-10-10 22:55:35,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 109936640. Throughput: 0: 1730.8, 1: 1712.5. Samples: 27498796. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 22:55:35,557][97672] Avg episode reward: [(0, '-0.920'), (1, '22.600')] -[2023-10-10 22:55:35,576][98560] Updated weights for policy 1, policy_version 53542 (0.0007) -[2023-10-10 22:55:35,936][98560] Updated weights for policy 1, policy_version 53552 (0.0009) -[2023-10-10 22:55:36,307][98560] Updated weights for policy 1, policy_version 53562 (0.0008) -[2023-10-10 22:55:36,695][98559] Updated weights for policy 0, policy_version 53830 (0.0008) -[2023-10-10 22:55:37,053][98559] Updated weights for policy 0, policy_version 53840 (0.0007) -[2023-10-10 22:55:37,418][98559] Updated weights for policy 0, policy_version 53850 (0.0009) -[2023-10-10 22:55:40,474][98560] Updated weights for policy 1, policy_version 53572 (0.0007) -[2023-10-10 22:55:40,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 110002176. Throughput: 0: 1698.9, 1: 1692.4. Samples: 27507978. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 22:55:40,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.520')] -[2023-10-10 22:55:40,839][98560] Updated weights for policy 1, policy_version 53582 (0.0008) -[2023-10-10 22:55:41,198][98560] Updated weights for policy 1, policy_version 53592 (0.0007) -[2023-10-10 22:55:41,400][98559] Updated weights for policy 0, policy_version 53860 (0.0009) -[2023-10-10 22:55:41,755][98559] Updated weights for policy 0, policy_version 53870 (0.0008) -[2023-10-10 22:55:42,125][98559] Updated weights for policy 0, policy_version 53880 (0.0007) -[2023-10-10 22:55:45,315][98560] Updated weights for policy 1, policy_version 53602 (0.0007) -[2023-10-10 22:55:45,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 110067712. Throughput: 0: 1720.5, 1: 1703.6. Samples: 27528872. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 22:55:45,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.480')] -[2023-10-10 22:55:45,682][98560] Updated weights for policy 1, policy_version 53612 (0.0008) -[2023-10-10 22:55:46,044][98560] Updated weights for policy 1, policy_version 53622 (0.0011) -[2023-10-10 22:55:46,119][98559] Updated weights for policy 0, policy_version 53890 (0.0008) -[2023-10-10 22:55:46,413][98560] Updated weights for policy 1, policy_version 53632 (0.0007) -[2023-10-10 22:55:46,529][98559] Updated weights for policy 0, policy_version 53900 (0.0008) -[2023-10-10 22:55:46,886][98559] Updated weights for policy 0, policy_version 53910 (0.0009) -[2023-10-10 22:55:47,257][98559] Updated weights for policy 0, policy_version 53920 (0.0009) -[2023-10-10 22:55:50,543][98560] Updated weights for policy 1, policy_version 53642 (0.0008) -[2023-10-10 22:55:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 110133248. Throughput: 0: 1718.6, 1: 1701.4. Samples: 27549572. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 22:55:50,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.480')] -[2023-10-10 22:55:50,906][98560] Updated weights for policy 1, policy_version 53652 (0.0008) -[2023-10-10 22:55:51,270][98560] Updated weights for policy 1, policy_version 53662 (0.0010) -[2023-10-10 22:55:51,314][98559] Updated weights for policy 0, policy_version 53930 (0.0007) -[2023-10-10 22:55:51,681][98559] Updated weights for policy 0, policy_version 53940 (0.0008) -[2023-10-10 22:55:52,043][98559] Updated weights for policy 0, policy_version 53950 (0.0008) -[2023-10-10 22:55:55,156][98560] Updated weights for policy 1, policy_version 53672 (0.0007) -[2023-10-10 22:55:55,516][98560] Updated weights for policy 1, policy_version 53682 (0.0008) -[2023-10-10 22:55:55,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 110198784. Throughput: 0: 1705.4, 1: 1689.1. Samples: 27558518. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 22:55:55,556][97672] Avg episode reward: [(0, '-0.840'), (1, '22.400')] -[2023-10-10 22:55:55,879][98560] Updated weights for policy 1, policy_version 53692 (0.0008) -[2023-10-10 22:55:56,115][98559] Updated weights for policy 0, policy_version 53960 (0.0007) -[2023-10-10 22:55:56,476][98559] Updated weights for policy 0, policy_version 53970 (0.0008) -[2023-10-10 22:55:56,839][98559] Updated weights for policy 0, policy_version 53980 (0.0008) -[2023-10-10 22:55:59,820][98560] Updated weights for policy 1, policy_version 53702 (0.0008) -[2023-10-10 22:56:00,196][98560] Updated weights for policy 1, policy_version 53712 (0.0008) -[2023-10-10 22:56:00,552][98560] Updated weights for policy 1, policy_version 53722 (0.0008) -[2023-10-10 22:56:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 110264320. Throughput: 0: 1722.0, 1: 1696.9. Samples: 27579790. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 22:56:00,558][97672] Avg episode reward: [(0, '-0.840'), (1, '22.440')] -[2023-10-10 22:56:00,898][98559] Updated weights for policy 0, policy_version 53990 (0.0009) -[2023-10-10 22:56:01,264][98559] Updated weights for policy 0, policy_version 54000 (0.0008) -[2023-10-10 22:56:01,629][98559] Updated weights for policy 0, policy_version 54010 (0.0009) -[2023-10-10 22:56:04,489][98560] Updated weights for policy 1, policy_version 53732 (0.0009) -[2023-10-10 22:56:04,856][98560] Updated weights for policy 1, policy_version 53742 (0.0008) -[2023-10-10 22:56:05,226][98560] Updated weights for policy 1, policy_version 53752 (0.0007) -[2023-10-10 22:56:05,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 110362624. Throughput: 0: 1717.9, 1: 1685.1. Samples: 27600480. Policy #0 lag: (min: 31.0, avg: 32.9, max: 60.0) -[2023-10-10 22:56:05,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.460')] -[2023-10-10 22:56:05,742][98559] Updated weights for policy 0, policy_version 54020 (0.0010) -[2023-10-10 22:56:06,103][98559] Updated weights for policy 0, policy_version 54030 (0.0010) -[2023-10-10 22:56:06,469][98559] Updated weights for policy 0, policy_version 54040 (0.0009) -[2023-10-10 22:56:09,355][98560] Updated weights for policy 1, policy_version 53762 (0.0007) -[2023-10-10 22:56:09,716][98560] Updated weights for policy 1, policy_version 53772 (0.0007) -[2023-10-10 22:56:10,078][98560] Updated weights for policy 1, policy_version 53782 (0.0007) -[2023-10-10 22:56:10,442][98560] Updated weights for policy 1, policy_version 53792 (0.0007) -[2023-10-10 22:56:10,556][97672] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 110428160. Throughput: 0: 1713.4, 1: 1698.1. Samples: 27610078. Policy #0 lag: (min: 31.0, avg: 32.9, max: 60.0) -[2023-10-10 22:56:10,556][97672] Avg episode reward: [(0, '-0.840'), (1, '22.480')] -[2023-10-10 22:56:10,556][98559] Updated weights for policy 0, policy_version 54050 (0.0008) -[2023-10-10 22:56:10,920][98559] Updated weights for policy 0, policy_version 54060 (0.0009) -[2023-10-10 22:56:11,299][98559] Updated weights for policy 0, policy_version 54070 (0.0007) -[2023-10-10 22:56:11,659][98559] Updated weights for policy 0, policy_version 54080 (0.0008) -[2023-10-10 22:56:14,494][98560] Updated weights for policy 1, policy_version 53802 (0.0009) -[2023-10-10 22:56:14,867][98560] Updated weights for policy 1, policy_version 53812 (0.0007) -[2023-10-10 22:56:15,235][98560] Updated weights for policy 1, policy_version 53822 (0.0007) -[2023-10-10 22:56:15,552][98559] Updated weights for policy 0, policy_version 54090 (0.0008) -[2023-10-10 22:56:15,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 110493696. Throughput: 0: 1711.2, 1: 1696.7. Samples: 27631176. Policy #0 lag: (min: 31.0, avg: 32.9, max: 60.0) -[2023-10-10 22:56:15,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.480')] -[2023-10-10 22:56:15,909][98559] Updated weights for policy 0, policy_version 54100 (0.0007) -[2023-10-10 22:56:16,275][98559] Updated weights for policy 0, policy_version 54110 (0.0008) -[2023-10-10 22:56:19,328][98560] Updated weights for policy 1, policy_version 53832 (0.0009) -[2023-10-10 22:56:19,707][98560] Updated weights for policy 1, policy_version 53842 (0.0008) -[2023-10-10 22:56:20,075][98560] Updated weights for policy 1, policy_version 53852 (0.0009) -[2023-10-10 22:56:20,404][98559] Updated weights for policy 0, policy_version 54120 (0.0008) -[2023-10-10 22:56:20,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 110559232. Throughput: 0: 1701.6, 1: 1679.5. Samples: 27650946. Policy #0 lag: (min: 31.0, avg: 32.9, max: 60.0) -[2023-10-10 22:56:20,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.480')] -[2023-10-10 22:56:20,776][98559] Updated weights for policy 0, policy_version 54130 (0.0008) -[2023-10-10 22:56:21,146][98559] Updated weights for policy 0, policy_version 54140 (0.0009) -[2023-10-10 22:56:24,058][98560] Updated weights for policy 1, policy_version 53862 (0.0008) -[2023-10-10 22:56:24,422][98560] Updated weights for policy 1, policy_version 53872 (0.0008) -[2023-10-10 22:56:24,782][98560] Updated weights for policy 1, policy_version 53882 (0.0007) -[2023-10-10 22:56:24,976][98559] Updated weights for policy 0, policy_version 54150 (0.0007) -[2023-10-10 22:56:25,333][98559] Updated weights for policy 0, policy_version 54160 (0.0008) -[2023-10-10 22:56:25,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 110624768. Throughput: 0: 1707.8, 1: 1701.2. Samples: 27661384. Policy #0 lag: (min: 31.0, avg: 32.9, max: 60.0) -[2023-10-10 22:56:25,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.380')] -[2023-10-10 22:56:25,703][98559] Updated weights for policy 0, policy_version 54170 (0.0007) -[2023-10-10 22:56:28,887][98560] Updated weights for policy 1, policy_version 53892 (0.0008) -[2023-10-10 22:56:29,262][98560] Updated weights for policy 1, policy_version 53902 (0.0008) -[2023-10-10 22:56:29,622][98560] Updated weights for policy 1, policy_version 53912 (0.0008) -[2023-10-10 22:56:29,721][98559] Updated weights for policy 0, policy_version 54180 (0.0008) -[2023-10-10 22:56:30,096][98559] Updated weights for policy 0, policy_version 54190 (0.0009) -[2023-10-10 22:56:30,463][98559] Updated weights for policy 0, policy_version 54200 (0.0008) -[2023-10-10 22:56:30,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 110690304. Throughput: 0: 1706.6, 1: 1709.1. Samples: 27682578. Policy #0 lag: (min: 31.0, avg: 32.9, max: 60.0) -[2023-10-10 22:56:30,556][97672] Avg episode reward: [(0, '-0.840'), (1, '22.420')] -[2023-10-10 22:56:33,411][98560] Updated weights for policy 1, policy_version 53922 (0.0008) -[2023-10-10 22:56:33,781][98560] Updated weights for policy 1, policy_version 53932 (0.0008) -[2023-10-10 22:56:34,144][98560] Updated weights for policy 1, policy_version 53942 (0.0008) -[2023-10-10 22:56:34,458][98559] Updated weights for policy 0, policy_version 54210 (0.0009) -[2023-10-10 22:56:34,514][98560] Updated weights for policy 1, policy_version 53952 (0.0008) -[2023-10-10 22:56:34,870][98559] Updated weights for policy 0, policy_version 54220 (0.0008) -[2023-10-10 22:56:35,239][98559] Updated weights for policy 0, policy_version 54230 (0.0009) -[2023-10-10 22:56:35,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 110755840. Throughput: 0: 1689.8, 1: 1683.0. Samples: 27701346. Policy #0 lag: (min: 31.0, avg: 32.9, max: 60.0) -[2023-10-10 22:56:35,556][97672] Avg episode reward: [(0, '-1.020'), (1, '22.320')] -[2023-10-10 22:56:35,564][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000053952_55246848.pth... -[2023-10-10 22:56:35,594][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000052352_53608448.pth -[2023-10-10 22:56:35,601][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000054240_55541760.pth... -[2023-10-10 22:56:35,603][98559] Updated weights for policy 0, policy_version 54240 (0.0008) -[2023-10-10 22:56:35,630][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000052640_53903360.pth -[2023-10-10 22:56:38,621][98560] Updated weights for policy 1, policy_version 53962 (0.0007) -[2023-10-10 22:56:38,982][98560] Updated weights for policy 1, policy_version 53972 (0.0007) -[2023-10-10 22:56:39,354][98560] Updated weights for policy 1, policy_version 53982 (0.0008) -[2023-10-10 22:56:39,649][98559] Updated weights for policy 0, policy_version 54250 (0.0009) -[2023-10-10 22:56:40,008][98559] Updated weights for policy 0, policy_version 54260 (0.0008) -[2023-10-10 22:56:40,370][98559] Updated weights for policy 0, policy_version 54270 (0.0009) -[2023-10-10 22:56:40,556][97672] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 110854144. Throughput: 0: 1710.2, 1: 1723.2. Samples: 27713022. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:56:40,557][97672] Avg episode reward: [(0, '-1.020'), (1, '22.460')] -[2023-10-10 22:56:43,407][98560] Updated weights for policy 1, policy_version 53992 (0.0009) -[2023-10-10 22:56:43,783][98560] Updated weights for policy 1, policy_version 54002 (0.0008) -[2023-10-10 22:56:44,146][98560] Updated weights for policy 1, policy_version 54012 (0.0008) -[2023-10-10 22:56:44,460][98559] Updated weights for policy 0, policy_version 54280 (0.0008) -[2023-10-10 22:56:44,819][98559] Updated weights for policy 0, policy_version 54290 (0.0009) -[2023-10-10 22:56:45,198][98559] Updated weights for policy 0, policy_version 54300 (0.0008) -[2023-10-10 22:56:45,556][97672] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 110919680. Throughput: 0: 1707.8, 1: 1703.2. Samples: 27733282. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:56:45,557][97672] Avg episode reward: [(0, '-1.020'), (1, '22.420')] -[2023-10-10 22:56:48,043][98560] Updated weights for policy 1, policy_version 54022 (0.0008) -[2023-10-10 22:56:48,411][98560] Updated weights for policy 1, policy_version 54032 (0.0007) -[2023-10-10 22:56:48,768][98560] Updated weights for policy 1, policy_version 54042 (0.0009) -[2023-10-10 22:56:49,266][98559] Updated weights for policy 0, policy_version 54310 (0.0010) -[2023-10-10 22:56:49,633][98559] Updated weights for policy 0, policy_version 54320 (0.0009) -[2023-10-10 22:56:50,001][98559] Updated weights for policy 0, policy_version 54330 (0.0011) -[2023-10-10 22:56:50,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 110985216. Throughput: 0: 1678.8, 1: 1696.6. Samples: 27752374. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:56:50,556][97672] Avg episode reward: [(0, '-1.020'), (1, '22.380')] -[2023-10-10 22:56:52,655][98560] Updated weights for policy 1, policy_version 54052 (0.0008) -[2023-10-10 22:56:53,027][98560] Updated weights for policy 1, policy_version 54062 (0.0008) -[2023-10-10 22:56:53,389][98560] Updated weights for policy 1, policy_version 54072 (0.0008) -[2023-10-10 22:56:53,919][98559] Updated weights for policy 0, policy_version 54340 (0.0008) -[2023-10-10 22:56:54,280][98559] Updated weights for policy 0, policy_version 54350 (0.0008) -[2023-10-10 22:56:54,638][98559] Updated weights for policy 0, policy_version 54360 (0.0009) -[2023-10-10 22:56:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 111050752. Throughput: 0: 1711.9, 1: 1712.1. Samples: 27764158. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:56:55,556][97672] Avg episode reward: [(0, '-1.020'), (1, '22.320')] -[2023-10-10 22:56:57,350][98560] Updated weights for policy 1, policy_version 54082 (0.0008) -[2023-10-10 22:56:57,710][98560] Updated weights for policy 1, policy_version 54092 (0.0009) -[2023-10-10 22:56:58,086][98560] Updated weights for policy 1, policy_version 54102 (0.0008) -[2023-10-10 22:56:58,358][98559] Updated weights for policy 0, policy_version 54370 (0.0010) -[2023-10-10 22:56:58,457][98560] Updated weights for policy 1, policy_version 54112 (0.0009) -[2023-10-10 22:56:58,734][98559] Updated weights for policy 0, policy_version 54380 (0.0007) -[2023-10-10 22:56:59,105][98559] Updated weights for policy 0, policy_version 54390 (0.0009) -[2023-10-10 22:56:59,477][98559] Updated weights for policy 0, policy_version 54400 (0.0008) -[2023-10-10 22:57:00,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 111116288. Throughput: 0: 1691.5, 1: 1688.0. Samples: 27783252. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:57:00,557][97672] Avg episode reward: [(0, '-1.020'), (1, '22.360')] -[2023-10-10 22:57:02,477][98560] Updated weights for policy 1, policy_version 54122 (0.0009) -[2023-10-10 22:57:02,844][98560] Updated weights for policy 1, policy_version 54132 (0.0008) -[2023-10-10 22:57:03,221][98560] Updated weights for policy 1, policy_version 54142 (0.0009) -[2023-10-10 22:57:03,601][98559] Updated weights for policy 0, policy_version 54410 (0.0008) -[2023-10-10 22:57:03,964][98559] Updated weights for policy 0, policy_version 54420 (0.0007) -[2023-10-10 22:57:04,328][98559] Updated weights for policy 0, policy_version 54430 (0.0007) -[2023-10-10 22:57:05,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 111181824. Throughput: 0: 1693.6, 1: 1707.0. Samples: 27803972. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:57:05,557][97672] Avg episode reward: [(0, '-1.020'), (1, '22.380')] -[2023-10-10 22:57:07,320][98560] Updated weights for policy 1, policy_version 54152 (0.0007) -[2023-10-10 22:57:07,689][98560] Updated weights for policy 1, policy_version 54162 (0.0007) -[2023-10-10 22:57:08,056][98560] Updated weights for policy 1, policy_version 54172 (0.0009) -[2023-10-10 22:57:08,214][98559] Updated weights for policy 0, policy_version 54440 (0.0009) -[2023-10-10 22:57:08,591][98559] Updated weights for policy 0, policy_version 54450 (0.0009) -[2023-10-10 22:57:08,959][98559] Updated weights for policy 0, policy_version 54460 (0.0007) -[2023-10-10 22:57:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 111247360. Throughput: 0: 1709.1, 1: 1701.4. Samples: 27814858. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:57:10,556][97672] Avg episode reward: [(0, '-1.020'), (1, '22.420')] -[2023-10-10 22:57:12,137][98560] Updated weights for policy 1, policy_version 54182 (0.0008) -[2023-10-10 22:57:12,510][98560] Updated weights for policy 1, policy_version 54192 (0.0007) -[2023-10-10 22:57:12,887][98560] Updated weights for policy 1, policy_version 54202 (0.0008) -[2023-10-10 22:57:12,975][98559] Updated weights for policy 0, policy_version 54470 (0.0007) -[2023-10-10 22:57:13,345][98559] Updated weights for policy 0, policy_version 54480 (0.0009) -[2023-10-10 22:57:13,713][98559] Updated weights for policy 0, policy_version 54490 (0.0008) -[2023-10-10 22:57:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 111312896. Throughput: 0: 1689.0, 1: 1685.0. Samples: 27834406. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:57:15,556][97672] Avg episode reward: [(0, '-1.000'), (1, '22.440')] -[2023-10-10 22:57:16,967][98560] Updated weights for policy 1, policy_version 54212 (0.0009) -[2023-10-10 22:57:17,327][98560] Updated weights for policy 1, policy_version 54222 (0.0008) -[2023-10-10 22:57:17,696][98560] Updated weights for policy 1, policy_version 54232 (0.0010) -[2023-10-10 22:57:17,779][98559] Updated weights for policy 0, policy_version 54500 (0.0007) -[2023-10-10 22:57:18,146][98559] Updated weights for policy 0, policy_version 54510 (0.0008) -[2023-10-10 22:57:18,513][98559] Updated weights for policy 0, policy_version 54520 (0.0009) -[2023-10-10 22:57:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 111378432. Throughput: 0: 1712.1, 1: 1709.0. Samples: 27855296. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-10 22:57:20,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.420')] -[2023-10-10 22:57:21,737][98560] Updated weights for policy 1, policy_version 54242 (0.0009) -[2023-10-10 22:57:22,107][98560] Updated weights for policy 1, policy_version 54252 (0.0007) -[2023-10-10 22:57:22,467][98560] Updated weights for policy 1, policy_version 54262 (0.0008) -[2023-10-10 22:57:22,636][98559] Updated weights for policy 0, policy_version 54530 (0.0008) -[2023-10-10 22:57:22,827][98560] Updated weights for policy 1, policy_version 54272 (0.0008) -[2023-10-10 22:57:23,017][98559] Updated weights for policy 0, policy_version 54540 (0.0009) -[2023-10-10 22:57:23,375][98559] Updated weights for policy 0, policy_version 54550 (0.0010) -[2023-10-10 22:57:23,736][98559] Updated weights for policy 0, policy_version 54560 (0.0011) -[2023-10-10 22:57:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 111443968. Throughput: 0: 1697.6, 1: 1679.5. Samples: 27864992. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-10 22:57:25,556][97672] Avg episode reward: [(0, '-1.000'), (1, '22.420')] -[2023-10-10 22:57:26,987][98560] Updated weights for policy 1, policy_version 54282 (0.0008) -[2023-10-10 22:57:27,361][98560] Updated weights for policy 1, policy_version 54292 (0.0007) -[2023-10-10 22:57:27,732][98560] Updated weights for policy 1, policy_version 54302 (0.0007) -[2023-10-10 22:57:27,737][98559] Updated weights for policy 0, policy_version 54570 (0.0008) -[2023-10-10 22:57:28,111][98559] Updated weights for policy 0, policy_version 54580 (0.0008) -[2023-10-10 22:57:28,475][98559] Updated weights for policy 0, policy_version 54590 (0.0008) -[2023-10-10 22:57:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 111509504. Throughput: 0: 1687.6, 1: 1687.8. Samples: 27885178. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-10 22:57:30,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.360')] -[2023-10-10 22:57:31,682][98560] Updated weights for policy 1, policy_version 54312 (0.0007) -[2023-10-10 22:57:32,054][98560] Updated weights for policy 1, policy_version 54322 (0.0010) -[2023-10-10 22:57:32,419][98559] Updated weights for policy 0, policy_version 54600 (0.0007) -[2023-10-10 22:57:32,425][98560] Updated weights for policy 1, policy_version 54332 (0.0008) -[2023-10-10 22:57:32,781][98559] Updated weights for policy 0, policy_version 54610 (0.0007) -[2023-10-10 22:57:33,158][98559] Updated weights for policy 0, policy_version 54620 (0.0007) -[2023-10-10 22:57:35,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 111575040. Throughput: 0: 1724.3, 1: 1704.4. Samples: 27906666. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-10 22:57:35,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.380')] -[2023-10-10 22:57:36,403][98560] Updated weights for policy 1, policy_version 54342 (0.0009) -[2023-10-10 22:57:36,773][98560] Updated weights for policy 1, policy_version 54352 (0.0011) -[2023-10-10 22:57:37,010][98559] Updated weights for policy 0, policy_version 54630 (0.0008) -[2023-10-10 22:57:37,137][98560] Updated weights for policy 1, policy_version 54362 (0.0008) -[2023-10-10 22:57:37,377][98559] Updated weights for policy 0, policy_version 54640 (0.0007) -[2023-10-10 22:57:37,734][98559] Updated weights for policy 0, policy_version 54650 (0.0008) -[2023-10-10 22:57:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 111640576. Throughput: 0: 1695.1, 1: 1679.2. Samples: 27916000. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-10 22:57:40,557][97672] Avg episode reward: [(0, '-0.920'), (1, '22.440')] -[2023-10-10 22:57:41,032][98560] Updated weights for policy 1, policy_version 54372 (0.0008) -[2023-10-10 22:57:41,406][98560] Updated weights for policy 1, policy_version 54382 (0.0010) -[2023-10-10 22:57:41,764][98560] Updated weights for policy 1, policy_version 54392 (0.0008) -[2023-10-10 22:57:41,806][98559] Updated weights for policy 0, policy_version 54660 (0.0008) -[2023-10-10 22:57:42,167][98559] Updated weights for policy 0, policy_version 54670 (0.0007) -[2023-10-10 22:57:42,540][98559] Updated weights for policy 0, policy_version 54680 (0.0009) -[2023-10-10 22:57:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 111706112. Throughput: 0: 1714.3, 1: 1703.1. Samples: 27937036. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-10 22:57:45,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.480')] -[2023-10-10 22:57:45,859][98560] Updated weights for policy 1, policy_version 54402 (0.0007) -[2023-10-10 22:57:46,227][98560] Updated weights for policy 1, policy_version 54412 (0.0008) -[2023-10-10 22:57:46,457][98559] Updated weights for policy 0, policy_version 54690 (0.0009) -[2023-10-10 22:57:46,587][98560] Updated weights for policy 1, policy_version 54422 (0.0007) -[2023-10-10 22:57:46,818][98559] Updated weights for policy 0, policy_version 54700 (0.0008) -[2023-10-10 22:57:46,951][98560] Updated weights for policy 1, policy_version 54432 (0.0007) -[2023-10-10 22:57:47,189][98559] Updated weights for policy 0, policy_version 54710 (0.0008) -[2023-10-10 22:57:47,556][98559] Updated weights for policy 0, policy_version 54720 (0.0008) -[2023-10-10 22:57:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 111771648. Throughput: 0: 1719.0, 1: 1700.2. Samples: 27957836. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-10 22:57:50,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.440')] -[2023-10-10 22:57:50,924][98560] Updated weights for policy 1, policy_version 54442 (0.0011) -[2023-10-10 22:57:51,282][98560] Updated weights for policy 1, policy_version 54452 (0.0011) -[2023-10-10 22:57:51,527][98559] Updated weights for policy 0, policy_version 54730 (0.0008) -[2023-10-10 22:57:51,654][98560] Updated weights for policy 1, policy_version 54462 (0.0009) -[2023-10-10 22:57:51,901][98559] Updated weights for policy 0, policy_version 54740 (0.0008) -[2023-10-10 22:57:52,267][98559] Updated weights for policy 0, policy_version 54750 (0.0010) -[2023-10-10 22:57:55,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 111837184. Throughput: 0: 1697.0, 1: 1686.7. Samples: 27967124. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-10 22:57:55,556][97672] Avg episode reward: [(0, '-1.000'), (1, '22.460')] -[2023-10-10 22:57:55,751][98560] Updated weights for policy 1, policy_version 54472 (0.0008) -[2023-10-10 22:57:56,128][98560] Updated weights for policy 1, policy_version 54482 (0.0009) -[2023-10-10 22:57:56,329][98559] Updated weights for policy 0, policy_version 54760 (0.0007) -[2023-10-10 22:57:56,502][98560] Updated weights for policy 1, policy_version 54492 (0.0009) -[2023-10-10 22:57:56,694][98559] Updated weights for policy 0, policy_version 54770 (0.0007) -[2023-10-10 22:57:57,053][98559] Updated weights for policy 0, policy_version 54780 (0.0009) -[2023-10-10 22:58:00,518][98560] Updated weights for policy 1, policy_version 54502 (0.0009) -[2023-10-10 22:58:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 111902720. Throughput: 0: 1716.6, 1: 1700.7. Samples: 27988184. Policy #0 lag: (min: 25.0, avg: 29.0, max: 57.0) -[2023-10-10 22:58:00,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.480')] -[2023-10-10 22:58:00,886][98560] Updated weights for policy 1, policy_version 54512 (0.0007) -[2023-10-10 22:58:01,114][98559] Updated weights for policy 0, policy_version 54790 (0.0008) -[2023-10-10 22:58:01,254][98560] Updated weights for policy 1, policy_version 54522 (0.0008) -[2023-10-10 22:58:01,479][98559] Updated weights for policy 0, policy_version 54800 (0.0009) -[2023-10-10 22:58:01,854][98559] Updated weights for policy 0, policy_version 54810 (0.0008) -[2023-10-10 22:58:05,314][98560] Updated weights for policy 1, policy_version 54532 (0.0009) -[2023-10-10 22:58:05,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 111968256. Throughput: 0: 1714.4, 1: 1702.8. Samples: 28009070. Policy #0 lag: (min: 25.0, avg: 29.0, max: 57.0) -[2023-10-10 22:58:05,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.420')] -[2023-10-10 22:58:05,685][98560] Updated weights for policy 1, policy_version 54542 (0.0008) -[2023-10-10 22:58:05,819][98559] Updated weights for policy 0, policy_version 54820 (0.0010) -[2023-10-10 22:58:06,050][98560] Updated weights for policy 1, policy_version 54552 (0.0007) -[2023-10-10 22:58:06,192][98559] Updated weights for policy 0, policy_version 54830 (0.0008) -[2023-10-10 22:58:06,564][98559] Updated weights for policy 0, policy_version 54840 (0.0009) -[2023-10-10 22:58:10,149][98560] Updated weights for policy 1, policy_version 54562 (0.0007) -[2023-10-10 22:58:10,521][98560] Updated weights for policy 1, policy_version 54572 (0.0009) -[2023-10-10 22:58:10,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 112033792. Throughput: 0: 1703.3, 1: 1701.5. Samples: 28018210. Policy #0 lag: (min: 25.0, avg: 29.0, max: 57.0) -[2023-10-10 22:58:10,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.360')] -[2023-10-10 22:58:10,634][98559] Updated weights for policy 0, policy_version 54850 (0.0011) -[2023-10-10 22:58:10,878][98560] Updated weights for policy 1, policy_version 54582 (0.0007) -[2023-10-10 22:58:11,019][98559] Updated weights for policy 0, policy_version 54860 (0.0009) -[2023-10-10 22:58:11,241][98560] Updated weights for policy 1, policy_version 54592 (0.0009) -[2023-10-10 22:58:11,383][98559] Updated weights for policy 0, policy_version 54870 (0.0008) -[2023-10-10 22:58:11,760][98559] Updated weights for policy 0, policy_version 54880 (0.0008) -[2023-10-10 22:58:15,381][98560] Updated weights for policy 1, policy_version 54602 (0.0010) -[2023-10-10 22:58:15,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 112099328. Throughput: 0: 1709.0, 1: 1700.5. Samples: 28038606. Policy #0 lag: (min: 25.0, avg: 29.0, max: 57.0) -[2023-10-10 22:58:15,556][97672] Avg episode reward: [(0, '-1.000'), (1, '22.460')] -[2023-10-10 22:58:15,752][98560] Updated weights for policy 1, policy_version 54612 (0.0008) -[2023-10-10 22:58:15,820][98559] Updated weights for policy 0, policy_version 54890 (0.0008) -[2023-10-10 22:58:16,122][98560] Updated weights for policy 1, policy_version 54622 (0.0007) -[2023-10-10 22:58:16,186][98559] Updated weights for policy 0, policy_version 54900 (0.0009) -[2023-10-10 22:58:16,556][98559] Updated weights for policy 0, policy_version 54910 (0.0009) -[2023-10-10 22:58:19,981][98560] Updated weights for policy 1, policy_version 54632 (0.0008) -[2023-10-10 22:58:20,351][98560] Updated weights for policy 1, policy_version 54642 (0.0007) -[2023-10-10 22:58:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 112164864. Throughput: 0: 1697.2, 1: 1699.9. Samples: 28059532. Policy #0 lag: (min: 25.0, avg: 29.0, max: 57.0) -[2023-10-10 22:58:20,557][97672] Avg episode reward: [(0, '-1.140'), (1, '22.440')] -[2023-10-10 22:58:20,625][98559] Updated weights for policy 0, policy_version 54920 (0.0008) -[2023-10-10 22:58:20,720][98560] Updated weights for policy 1, policy_version 54652 (0.0007) -[2023-10-10 22:58:20,985][98559] Updated weights for policy 0, policy_version 54930 (0.0008) -[2023-10-10 22:58:21,353][98559] Updated weights for policy 0, policy_version 54940 (0.0009) -[2023-10-10 22:58:24,823][98560] Updated weights for policy 1, policy_version 54662 (0.0008) -[2023-10-10 22:58:25,181][98560] Updated weights for policy 1, policy_version 54672 (0.0009) -[2023-10-10 22:58:25,451][98559] Updated weights for policy 0, policy_version 54950 (0.0008) -[2023-10-10 22:58:25,552][98560] Updated weights for policy 1, policy_version 54682 (0.0008) -[2023-10-10 22:58:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 112230400. Throughput: 0: 1694.3, 1: 1702.5. Samples: 28068858. Policy #0 lag: (min: 25.0, avg: 29.0, max: 57.0) -[2023-10-10 22:58:25,556][97672] Avg episode reward: [(0, '-1.160'), (1, '22.420')] -[2023-10-10 22:58:25,816][98559] Updated weights for policy 0, policy_version 54960 (0.0010) -[2023-10-10 22:58:26,185][98559] Updated weights for policy 0, policy_version 54970 (0.0008) -[2023-10-10 22:58:29,477][98560] Updated weights for policy 1, policy_version 54692 (0.0009) -[2023-10-10 22:58:29,833][98560] Updated weights for policy 1, policy_version 54702 (0.0007) -[2023-10-10 22:58:30,034][98559] Updated weights for policy 0, policy_version 54980 (0.0008) -[2023-10-10 22:58:30,204][98560] Updated weights for policy 1, policy_version 54712 (0.0008) -[2023-10-10 22:58:30,407][98559] Updated weights for policy 0, policy_version 54990 (0.0008) -[2023-10-10 22:58:30,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 112328704. Throughput: 0: 1698.9, 1: 1703.4. Samples: 28090142. Policy #0 lag: (min: 25.0, avg: 29.0, max: 57.0) -[2023-10-10 22:58:30,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.400')] -[2023-10-10 22:58:30,765][98559] Updated weights for policy 0, policy_version 55000 (0.0011) -[2023-10-10 22:58:34,320][98560] Updated weights for policy 1, policy_version 54722 (0.0007) -[2023-10-10 22:58:34,695][98560] Updated weights for policy 1, policy_version 54732 (0.0009) -[2023-10-10 22:58:34,864][98559] Updated weights for policy 0, policy_version 55010 (0.0010) -[2023-10-10 22:58:35,059][98560] Updated weights for policy 1, policy_version 54742 (0.0008) -[2023-10-10 22:58:35,237][98559] Updated weights for policy 0, policy_version 55020 (0.0008) -[2023-10-10 22:58:35,423][98560] Updated weights for policy 1, policy_version 54752 (0.0008) -[2023-10-10 22:58:35,556][97672] Fps is (10 sec: 16383.8, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 112394240. Throughput: 0: 1685.2, 1: 1690.7. Samples: 28109752. Policy #0 lag: (min: 25.0, avg: 29.0, max: 57.0) -[2023-10-10 22:58:35,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.420')] -[2023-10-10 22:58:35,565][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000054752_56066048.pth... -[2023-10-10 22:58:35,595][98559] Updated weights for policy 0, policy_version 55030 (0.0008) -[2023-10-10 22:58:35,597][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000053152_54427648.pth -[2023-10-10 22:58:35,961][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000055040_56360960.pth... -[2023-10-10 22:58:35,961][98559] Updated weights for policy 0, policy_version 55040 (0.0009) -[2023-10-10 22:58:35,990][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000053440_54722560.pth -[2023-10-10 22:58:39,559][98560] Updated weights for policy 1, policy_version 54762 (0.0007) -[2023-10-10 22:58:39,918][98560] Updated weights for policy 1, policy_version 54772 (0.0010) -[2023-10-10 22:58:40,122][98559] Updated weights for policy 0, policy_version 55050 (0.0009) -[2023-10-10 22:58:40,282][98560] Updated weights for policy 1, policy_version 54782 (0.0009) -[2023-10-10 22:58:40,499][98559] Updated weights for policy 0, policy_version 55060 (0.0009) -[2023-10-10 22:58:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 112459776. Throughput: 0: 1696.5, 1: 1698.1. Samples: 28119882. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:58:40,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.420')] -[2023-10-10 22:58:40,851][98559] Updated weights for policy 0, policy_version 55070 (0.0010) -[2023-10-10 22:58:44,219][98560] Updated weights for policy 1, policy_version 54792 (0.0009) -[2023-10-10 22:58:44,586][98560] Updated weights for policy 1, policy_version 54802 (0.0009) -[2023-10-10 22:58:44,680][98559] Updated weights for policy 0, policy_version 55080 (0.0008) -[2023-10-10 22:58:44,951][98560] Updated weights for policy 1, policy_version 54812 (0.0009) -[2023-10-10 22:58:45,045][98559] Updated weights for policy 0, policy_version 55090 (0.0007) -[2023-10-10 22:58:45,422][98559] Updated weights for policy 0, policy_version 55100 (0.0010) -[2023-10-10 22:58:45,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 112525312. Throughput: 0: 1694.7, 1: 1698.4. Samples: 28140876. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:58:45,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.400')] -[2023-10-10 22:58:49,089][98560] Updated weights for policy 1, policy_version 54822 (0.0008) -[2023-10-10 22:58:49,448][98560] Updated weights for policy 1, policy_version 54832 (0.0010) -[2023-10-10 22:58:49,492][98559] Updated weights for policy 0, policy_version 55110 (0.0008) -[2023-10-10 22:58:49,813][98560] Updated weights for policy 1, policy_version 54842 (0.0008) -[2023-10-10 22:58:49,859][98559] Updated weights for policy 0, policy_version 55120 (0.0008) -[2023-10-10 22:58:50,217][98559] Updated weights for policy 0, policy_version 55130 (0.0007) -[2023-10-10 22:58:50,556][97672] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 112623616. Throughput: 0: 1668.2, 1: 1675.7. Samples: 28159548. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:58:50,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.460')] -[2023-10-10 22:58:53,758][98560] Updated weights for policy 1, policy_version 54852 (0.0009) -[2023-10-10 22:58:54,124][98560] Updated weights for policy 1, policy_version 54862 (0.0009) -[2023-10-10 22:58:54,136][98559] Updated weights for policy 0, policy_version 55140 (0.0008) -[2023-10-10 22:58:54,477][98560] Updated weights for policy 1, policy_version 54872 (0.0008) -[2023-10-10 22:58:54,509][98559] Updated weights for policy 0, policy_version 55150 (0.0009) -[2023-10-10 22:58:54,870][98559] Updated weights for policy 0, policy_version 55160 (0.0009) -[2023-10-10 22:58:55,556][97672] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 112689152. Throughput: 0: 1698.0, 1: 1694.7. Samples: 28170884. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:58:55,556][97672] Avg episode reward: [(0, '-1.180'), (1, '22.580')] -[2023-10-10 22:58:58,531][98560] Updated weights for policy 1, policy_version 54882 (0.0009) -[2023-10-10 22:58:58,857][98559] Updated weights for policy 0, policy_version 55170 (0.0008) -[2023-10-10 22:58:58,893][98560] Updated weights for policy 1, policy_version 54892 (0.0008) -[2023-10-10 22:58:59,255][98559] Updated weights for policy 0, policy_version 55180 (0.0007) -[2023-10-10 22:58:59,268][98560] Updated weights for policy 1, policy_version 54902 (0.0007) -[2023-10-10 22:58:59,621][98559] Updated weights for policy 0, policy_version 55190 (0.0009) -[2023-10-10 22:58:59,637][98560] Updated weights for policy 1, policy_version 54912 (0.0009) -[2023-10-10 22:58:59,980][98559] Updated weights for policy 0, policy_version 55200 (0.0007) -[2023-10-10 22:59:00,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 112754688. Throughput: 0: 1692.6, 1: 1699.4. Samples: 28191246. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:59:00,558][97672] Avg episode reward: [(0, '-1.180'), (1, '22.580')] -[2023-10-10 22:59:03,686][98560] Updated weights for policy 1, policy_version 54922 (0.0008) -[2023-10-10 22:59:03,787][98559] Updated weights for policy 0, policy_version 55210 (0.0007) -[2023-10-10 22:59:04,055][98560] Updated weights for policy 1, policy_version 54932 (0.0010) -[2023-10-10 22:59:04,144][98559] Updated weights for policy 0, policy_version 55220 (0.0008) -[2023-10-10 22:59:04,422][98560] Updated weights for policy 1, policy_version 54942 (0.0009) -[2023-10-10 22:59:04,516][98559] Updated weights for policy 0, policy_version 55230 (0.0011) -[2023-10-10 22:59:05,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 112820224. Throughput: 0: 1685.7, 1: 1673.3. Samples: 28210688. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:59:05,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.540')] -[2023-10-10 22:59:08,431][98560] Updated weights for policy 1, policy_version 54952 (0.0007) -[2023-10-10 22:59:08,545][98559] Updated weights for policy 0, policy_version 55240 (0.0007) -[2023-10-10 22:59:08,800][98560] Updated weights for policy 1, policy_version 54962 (0.0007) -[2023-10-10 22:59:08,914][98559] Updated weights for policy 0, policy_version 55250 (0.0007) -[2023-10-10 22:59:09,162][98560] Updated weights for policy 1, policy_version 54972 (0.0007) -[2023-10-10 22:59:09,281][98559] Updated weights for policy 0, policy_version 55260 (0.0008) -[2023-10-10 22:59:10,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 112885760. Throughput: 0: 1715.2, 1: 1698.3. Samples: 28222468. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 22:59:10,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.560')] -[2023-10-10 22:59:13,111][98560] Updated weights for policy 1, policy_version 54982 (0.0007) -[2023-10-10 22:59:13,260][98559] Updated weights for policy 0, policy_version 55270 (0.0010) -[2023-10-10 22:59:13,478][98560] Updated weights for policy 1, policy_version 54992 (0.0008) -[2023-10-10 22:59:13,612][98559] Updated weights for policy 0, policy_version 55280 (0.0008) -[2023-10-10 22:59:13,843][98560] Updated weights for policy 1, policy_version 55002 (0.0010) -[2023-10-10 22:59:13,984][98559] Updated weights for policy 0, policy_version 55290 (0.0007) -[2023-10-10 22:59:15,556][97672] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 112951296. Throughput: 0: 1686.7, 1: 1677.1. Samples: 28241510. Policy #0 lag: (min: 20.0, avg: 23.2, max: 52.0) -[2023-10-10 22:59:15,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.500')] -[2023-10-10 22:59:17,959][98560] Updated weights for policy 1, policy_version 55012 (0.0010) -[2023-10-10 22:59:18,270][98559] Updated weights for policy 0, policy_version 55300 (0.0007) -[2023-10-10 22:59:18,317][98560] Updated weights for policy 1, policy_version 55022 (0.0010) -[2023-10-10 22:59:18,633][98559] Updated weights for policy 0, policy_version 55310 (0.0008) -[2023-10-10 22:59:18,682][98560] Updated weights for policy 1, policy_version 55032 (0.0008) -[2023-10-10 22:59:18,993][98559] Updated weights for policy 0, policy_version 55320 (0.0008) -[2023-10-10 22:59:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 113016832. Throughput: 0: 1699.8, 1: 1682.3. Samples: 28261946. Policy #0 lag: (min: 20.0, avg: 23.2, max: 52.0) -[2023-10-10 22:59:20,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.520')] -[2023-10-10 22:59:22,735][98560] Updated weights for policy 1, policy_version 55042 (0.0007) -[2023-10-10 22:59:22,986][98559] Updated weights for policy 0, policy_version 55330 (0.0009) -[2023-10-10 22:59:23,089][98560] Updated weights for policy 1, policy_version 55052 (0.0009) -[2023-10-10 22:59:23,357][98559] Updated weights for policy 0, policy_version 55340 (0.0009) -[2023-10-10 22:59:23,473][98560] Updated weights for policy 1, policy_version 55062 (0.0007) -[2023-10-10 22:59:23,722][98559] Updated weights for policy 0, policy_version 55350 (0.0008) -[2023-10-10 22:59:23,839][98560] Updated weights for policy 1, policy_version 55072 (0.0009) -[2023-10-10 22:59:24,082][98559] Updated weights for policy 0, policy_version 55360 (0.0007) -[2023-10-10 22:59:25,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 113082368. Throughput: 0: 1708.4, 1: 1699.8. Samples: 28273248. Policy #0 lag: (min: 20.0, avg: 23.2, max: 52.0) -[2023-10-10 22:59:25,556][97672] Avg episode reward: [(0, '-1.200'), (1, '22.520')] -[2023-10-10 22:59:27,760][98560] Updated weights for policy 1, policy_version 55082 (0.0008) -[2023-10-10 22:59:27,980][98559] Updated weights for policy 0, policy_version 55370 (0.0007) -[2023-10-10 22:59:28,128][98560] Updated weights for policy 1, policy_version 55092 (0.0008) -[2023-10-10 22:59:28,350][98559] Updated weights for policy 0, policy_version 55380 (0.0009) -[2023-10-10 22:59:28,486][98560] Updated weights for policy 1, policy_version 55102 (0.0007) -[2023-10-10 22:59:28,717][98559] Updated weights for policy 0, policy_version 55390 (0.0010) -[2023-10-10 22:59:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 113147904. Throughput: 0: 1693.0, 1: 1672.2. Samples: 28292308. Policy #0 lag: (min: 20.0, avg: 23.2, max: 52.0) -[2023-10-10 22:59:30,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.560')] -[2023-10-10 22:59:32,538][98559] Updated weights for policy 0, policy_version 55400 (0.0010) -[2023-10-10 22:59:32,602][98560] Updated weights for policy 1, policy_version 55112 (0.0008) -[2023-10-10 22:59:32,903][98559] Updated weights for policy 0, policy_version 55410 (0.0009) -[2023-10-10 22:59:32,966][98560] Updated weights for policy 1, policy_version 55122 (0.0008) -[2023-10-10 22:59:33,270][98559] Updated weights for policy 0, policy_version 55420 (0.0009) -[2023-10-10 22:59:33,336][98560] Updated weights for policy 1, policy_version 55132 (0.0008) -[2023-10-10 22:59:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 113213440. Throughput: 0: 1724.9, 1: 1695.0. Samples: 28313442. Policy #0 lag: (min: 20.0, avg: 23.2, max: 52.0) -[2023-10-10 22:59:35,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.380')] -[2023-10-10 22:59:37,224][98559] Updated weights for policy 0, policy_version 55430 (0.0008) -[2023-10-10 22:59:37,370][98560] Updated weights for policy 1, policy_version 55142 (0.0008) -[2023-10-10 22:59:37,595][98559] Updated weights for policy 0, policy_version 55440 (0.0007) -[2023-10-10 22:59:37,743][98560] Updated weights for policy 1, policy_version 55152 (0.0008) -[2023-10-10 22:59:37,963][98559] Updated weights for policy 0, policy_version 55450 (0.0008) -[2023-10-10 22:59:38,098][98560] Updated weights for policy 1, policy_version 55162 (0.0009) -[2023-10-10 22:59:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 113278976. Throughput: 0: 1701.1, 1: 1687.1. Samples: 28323354. Policy #0 lag: (min: 20.0, avg: 23.2, max: 52.0) -[2023-10-10 22:59:40,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.320')] -[2023-10-10 22:59:42,039][98559] Updated weights for policy 0, policy_version 55460 (0.0010) -[2023-10-10 22:59:42,079][98560] Updated weights for policy 1, policy_version 55172 (0.0008) -[2023-10-10 22:59:42,407][98559] Updated weights for policy 0, policy_version 55470 (0.0008) -[2023-10-10 22:59:42,439][98560] Updated weights for policy 1, policy_version 55182 (0.0008) -[2023-10-10 22:59:42,766][98559] Updated weights for policy 0, policy_version 55480 (0.0008) -[2023-10-10 22:59:42,804][98560] Updated weights for policy 1, policy_version 55192 (0.0010) -[2023-10-10 22:59:45,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 113344512. Throughput: 0: 1709.5, 1: 1678.8. Samples: 28343720. Policy #0 lag: (min: 20.0, avg: 23.2, max: 52.0) -[2023-10-10 22:59:45,557][97672] Avg episode reward: [(0, '-1.300'), (1, '22.380')] -[2023-10-10 22:59:46,749][98560] Updated weights for policy 1, policy_version 55202 (0.0008) -[2023-10-10 22:59:46,892][98559] Updated weights for policy 0, policy_version 55490 (0.0008) -[2023-10-10 22:59:47,119][98560] Updated weights for policy 1, policy_version 55212 (0.0008) -[2023-10-10 22:59:47,298][98559] Updated weights for policy 0, policy_version 55500 (0.0007) -[2023-10-10 22:59:47,476][98560] Updated weights for policy 1, policy_version 55222 (0.0008) -[2023-10-10 22:59:47,660][98559] Updated weights for policy 0, policy_version 55510 (0.0009) -[2023-10-10 22:59:47,844][98560] Updated weights for policy 1, policy_version 55232 (0.0007) -[2023-10-10 22:59:48,026][98559] Updated weights for policy 0, policy_version 55520 (0.0008) -[2023-10-10 22:59:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 113410048. Throughput: 0: 1719.2, 1: 1705.2. Samples: 28364788. Policy #0 lag: (min: 20.0, avg: 23.2, max: 52.0) -[2023-10-10 22:59:50,557][97672] Avg episode reward: [(0, '-1.300'), (1, '22.460')] -[2023-10-10 22:59:51,926][98560] Updated weights for policy 1, policy_version 55242 (0.0008) -[2023-10-10 22:59:52,122][98559] Updated weights for policy 0, policy_version 55530 (0.0008) -[2023-10-10 22:59:52,299][98560] Updated weights for policy 1, policy_version 55252 (0.0007) -[2023-10-10 22:59:52,490][98559] Updated weights for policy 0, policy_version 55540 (0.0009) -[2023-10-10 22:59:52,656][98560] Updated weights for policy 1, policy_version 55262 (0.0008) -[2023-10-10 22:59:52,855][98559] Updated weights for policy 0, policy_version 55550 (0.0009) -[2023-10-10 22:59:55,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 113475584. Throughput: 0: 1688.8, 1: 1676.5. Samples: 28373908. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 22:59:55,557][97672] Avg episode reward: [(0, '-1.300'), (1, '22.520')] -[2023-10-10 22:59:56,680][98560] Updated weights for policy 1, policy_version 55272 (0.0008) -[2023-10-10 22:59:56,738][98559] Updated weights for policy 0, policy_version 55560 (0.0008) -[2023-10-10 22:59:57,048][98560] Updated weights for policy 1, policy_version 55282 (0.0010) -[2023-10-10 22:59:57,115][98559] Updated weights for policy 0, policy_version 55570 (0.0009) -[2023-10-10 22:59:57,411][98560] Updated weights for policy 1, policy_version 55292 (0.0009) -[2023-10-10 22:59:57,477][98559] Updated weights for policy 0, policy_version 55580 (0.0009) -[2023-10-10 23:00:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 113541120. Throughput: 0: 1714.0, 1: 1694.6. Samples: 28394898. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 23:00:00,557][97672] Avg episode reward: [(0, '-1.280'), (1, '22.580')] -[2023-10-10 23:00:01,407][98560] Updated weights for policy 1, policy_version 55302 (0.0009) -[2023-10-10 23:00:01,535][98559] Updated weights for policy 0, policy_version 55590 (0.0010) -[2023-10-10 23:00:01,766][98560] Updated weights for policy 1, policy_version 55312 (0.0007) -[2023-10-10 23:00:01,889][98559] Updated weights for policy 0, policy_version 55600 (0.0009) -[2023-10-10 23:00:02,131][98560] Updated weights for policy 1, policy_version 55322 (0.0009) -[2023-10-10 23:00:02,259][98559] Updated weights for policy 0, policy_version 55610 (0.0009) -[2023-10-10 23:00:05,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 113606656. Throughput: 0: 1713.6, 1: 1698.1. Samples: 28415472. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 23:00:05,557][97672] Avg episode reward: [(0, '-1.280'), (1, '22.480')] -[2023-10-10 23:00:06,240][98560] Updated weights for policy 1, policy_version 55332 (0.0008) -[2023-10-10 23:00:06,305][98559] Updated weights for policy 0, policy_version 55620 (0.0009) -[2023-10-10 23:00:06,598][98560] Updated weights for policy 1, policy_version 55342 (0.0010) -[2023-10-10 23:00:06,672][98559] Updated weights for policy 0, policy_version 55630 (0.0008) -[2023-10-10 23:00:06,967][98560] Updated weights for policy 1, policy_version 55352 (0.0009) -[2023-10-10 23:00:07,043][98559] Updated weights for policy 0, policy_version 55640 (0.0008) -[2023-10-10 23:00:10,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 113672192. Throughput: 0: 1695.0, 1: 1675.1. Samples: 28424902. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 23:00:10,557][97672] Avg episode reward: [(0, '-1.280'), (1, '22.480')] -[2023-10-10 23:00:11,063][98559] Updated weights for policy 0, policy_version 55650 (0.0008) -[2023-10-10 23:00:11,171][98560] Updated weights for policy 1, policy_version 55362 (0.0009) -[2023-10-10 23:00:11,428][98559] Updated weights for policy 0, policy_version 55660 (0.0008) -[2023-10-10 23:00:11,530][98560] Updated weights for policy 1, policy_version 55372 (0.0008) -[2023-10-10 23:00:11,802][98559] Updated weights for policy 0, policy_version 55670 (0.0007) -[2023-10-10 23:00:11,894][98560] Updated weights for policy 1, policy_version 55382 (0.0008) -[2023-10-10 23:00:12,166][98559] Updated weights for policy 0, policy_version 55680 (0.0009) -[2023-10-10 23:00:12,260][98560] Updated weights for policy 1, policy_version 55392 (0.0009) -[2023-10-10 23:00:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 113737728. Throughput: 0: 1715.6, 1: 1701.7. Samples: 28446088. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 23:00:15,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.440')] -[2023-10-10 23:00:16,059][98559] Updated weights for policy 0, policy_version 55690 (0.0009) -[2023-10-10 23:00:16,171][98560] Updated weights for policy 1, policy_version 55402 (0.0009) -[2023-10-10 23:00:16,419][98559] Updated weights for policy 0, policy_version 55700 (0.0009) -[2023-10-10 23:00:16,534][98560] Updated weights for policy 1, policy_version 55412 (0.0009) -[2023-10-10 23:00:16,789][98559] Updated weights for policy 0, policy_version 55710 (0.0009) -[2023-10-10 23:00:16,905][98560] Updated weights for policy 1, policy_version 55422 (0.0009) -[2023-10-10 23:00:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 113803264. Throughput: 0: 1716.0, 1: 1705.5. Samples: 28467410. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 23:00:20,556][97672] Avg episode reward: [(0, '-1.260'), (1, '22.520')] -[2023-10-10 23:00:20,595][98559] Updated weights for policy 0, policy_version 55720 (0.0010) -[2023-10-10 23:00:20,809][98560] Updated weights for policy 1, policy_version 55432 (0.0007) -[2023-10-10 23:00:20,955][98559] Updated weights for policy 0, policy_version 55730 (0.0007) -[2023-10-10 23:00:21,166][98560] Updated weights for policy 1, policy_version 55442 (0.0007) -[2023-10-10 23:00:21,309][98559] Updated weights for policy 0, policy_version 55740 (0.0009) -[2023-10-10 23:00:21,530][98560] Updated weights for policy 1, policy_version 55452 (0.0009) -[2023-10-10 23:00:25,224][98559] Updated weights for policy 0, policy_version 55750 (0.0008) -[2023-10-10 23:00:25,487][98560] Updated weights for policy 1, policy_version 55462 (0.0008) -[2023-10-10 23:00:25,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 113868800. Throughput: 0: 1717.3, 1: 1690.1. Samples: 28476684. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 23:00:25,556][97672] Avg episode reward: [(0, '-1.260'), (1, '22.640')] -[2023-10-10 23:00:25,587][98559] Updated weights for policy 0, policy_version 55760 (0.0008) -[2023-10-10 23:00:25,855][98560] Updated weights for policy 1, policy_version 55472 (0.0010) -[2023-10-10 23:00:25,956][98559] Updated weights for policy 0, policy_version 55770 (0.0008) -[2023-10-10 23:00:26,237][98560] Updated weights for policy 1, policy_version 55482 (0.0008) -[2023-10-10 23:00:29,941][98559] Updated weights for policy 0, policy_version 55780 (0.0008) -[2023-10-10 23:00:30,313][98559] Updated weights for policy 0, policy_version 55790 (0.0008) -[2023-10-10 23:00:30,313][98560] Updated weights for policy 1, policy_version 55492 (0.0010) -[2023-10-10 23:00:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 113934336. Throughput: 0: 1719.7, 1: 1704.0. Samples: 28497782. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 23:00:30,556][97672] Avg episode reward: [(0, '-1.260'), (1, '22.560')] -[2023-10-10 23:00:30,666][98559] Updated weights for policy 0, policy_version 55800 (0.0008) -[2023-10-10 23:00:30,680][98560] Updated weights for policy 1, policy_version 55502 (0.0008) -[2023-10-10 23:00:31,039][98560] Updated weights for policy 1, policy_version 55512 (0.0009) -[2023-10-10 23:00:34,603][98559] Updated weights for policy 0, policy_version 55810 (0.0008) -[2023-10-10 23:00:35,010][98559] Updated weights for policy 0, policy_version 55820 (0.0009) -[2023-10-10 23:00:35,052][98560] Updated weights for policy 1, policy_version 55522 (0.0007) -[2023-10-10 23:00:35,372][98559] Updated weights for policy 0, policy_version 55830 (0.0007) -[2023-10-10 23:00:35,411][98560] Updated weights for policy 1, policy_version 55532 (0.0009) -[2023-10-10 23:00:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 113999872. Throughput: 0: 1704.6, 1: 1702.4. Samples: 28518104. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:00:35,556][97672] Avg episode reward: [(0, '-1.280'), (1, '22.560')] -[2023-10-10 23:00:35,732][98559] Updated weights for policy 0, policy_version 55840 (0.0007) -[2023-10-10 23:00:35,732][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000055840_57180160.pth... -[2023-10-10 23:00:35,772][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000054240_55541760.pth -[2023-10-10 23:00:35,775][98560] Updated weights for policy 1, policy_version 55542 (0.0009) -[2023-10-10 23:00:35,777][98385] Saving a milestone ./train_atari/atari_doubledunk_APPO/checkpoint_p0/milestones/checkpoint_000055840_57180160.pth -[2023-10-10 23:00:36,131][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000055552_56885248.pth... -[2023-10-10 23:00:36,136][98560] Updated weights for policy 1, policy_version 55552 (0.0008) -[2023-10-10 23:00:36,171][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000053952_55246848.pth -[2023-10-10 23:00:36,177][98439] Saving a milestone ./train_atari/atari_doubledunk_APPO/checkpoint_p1/milestones/checkpoint_000055552_56885248.pth -[2023-10-10 23:00:39,707][98559] Updated weights for policy 0, policy_version 55850 (0.0008) -[2023-10-10 23:00:40,068][98559] Updated weights for policy 0, policy_version 55860 (0.0009) -[2023-10-10 23:00:40,121][98560] Updated weights for policy 1, policy_version 55562 (0.0008) -[2023-10-10 23:00:40,432][98559] Updated weights for policy 0, policy_version 55870 (0.0009) -[2023-10-10 23:00:40,493][98560] Updated weights for policy 1, policy_version 55572 (0.0007) -[2023-10-10 23:00:40,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 114098176. Throughput: 0: 1725.8, 1: 1701.5. Samples: 28528136. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:00:40,557][97672] Avg episode reward: [(0, '-1.280'), (1, '22.480')] -[2023-10-10 23:00:40,863][98560] Updated weights for policy 1, policy_version 55582 (0.0010) -[2023-10-10 23:00:44,404][98559] Updated weights for policy 0, policy_version 55880 (0.0009) -[2023-10-10 23:00:44,773][98559] Updated weights for policy 0, policy_version 55890 (0.0008) -[2023-10-10 23:00:44,910][98560] Updated weights for policy 1, policy_version 55592 (0.0010) -[2023-10-10 23:00:45,137][98559] Updated weights for policy 0, policy_version 55900 (0.0007) -[2023-10-10 23:00:45,277][98560] Updated weights for policy 1, policy_version 55602 (0.0008) -[2023-10-10 23:00:45,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 114163712. Throughput: 0: 1721.8, 1: 1698.5. Samples: 28548812. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:00:45,557][97672] Avg episode reward: [(0, '-1.320'), (1, '22.200')] -[2023-10-10 23:00:45,650][98560] Updated weights for policy 1, policy_version 55612 (0.0007) -[2023-10-10 23:00:49,280][98559] Updated weights for policy 0, policy_version 55910 (0.0008) -[2023-10-10 23:00:49,636][98560] Updated weights for policy 1, policy_version 55622 (0.0009) -[2023-10-10 23:00:49,652][98559] Updated weights for policy 0, policy_version 55920 (0.0008) -[2023-10-10 23:00:50,001][98560] Updated weights for policy 1, policy_version 55632 (0.0009) -[2023-10-10 23:00:50,015][98559] Updated weights for policy 0, policy_version 55930 (0.0008) -[2023-10-10 23:00:50,364][98560] Updated weights for policy 1, policy_version 55642 (0.0008) -[2023-10-10 23:00:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 114229248. Throughput: 0: 1699.0, 1: 1702.5. Samples: 28568538. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:00:50,557][97672] Avg episode reward: [(0, '-1.320'), (1, '22.280')] -[2023-10-10 23:00:54,013][98559] Updated weights for policy 0, policy_version 55940 (0.0008) -[2023-10-10 23:00:54,376][98560] Updated weights for policy 1, policy_version 55652 (0.0009) -[2023-10-10 23:00:54,379][98559] Updated weights for policy 0, policy_version 55950 (0.0009) -[2023-10-10 23:00:54,739][98559] Updated weights for policy 0, policy_version 55960 (0.0010) -[2023-10-10 23:00:54,742][98560] Updated weights for policy 1, policy_version 55662 (0.0009) -[2023-10-10 23:00:55,110][98560] Updated weights for policy 1, policy_version 55672 (0.0008) -[2023-10-10 23:00:55,556][97672] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 114327552. Throughput: 0: 1728.7, 1: 1704.7. Samples: 28579406. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:00:55,557][97672] Avg episode reward: [(0, '-1.300'), (1, '22.260')] -[2023-10-10 23:00:58,781][98559] Updated weights for policy 0, policy_version 55970 (0.0009) -[2023-10-10 23:00:59,023][98560] Updated weights for policy 1, policy_version 55682 (0.0008) -[2023-10-10 23:00:59,150][98559] Updated weights for policy 0, policy_version 55980 (0.0010) -[2023-10-10 23:00:59,387][98560] Updated weights for policy 1, policy_version 55692 (0.0008) -[2023-10-10 23:00:59,514][98559] Updated weights for policy 0, policy_version 55990 (0.0007) -[2023-10-10 23:00:59,752][98560] Updated weights for policy 1, policy_version 55702 (0.0007) -[2023-10-10 23:00:59,866][98559] Updated weights for policy 0, policy_version 56000 (0.0008) -[2023-10-10 23:01:00,118][98560] Updated weights for policy 1, policy_version 55712 (0.0010) -[2023-10-10 23:01:00,556][97672] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 114393088. Throughput: 0: 1708.5, 1: 1709.3. Samples: 28599890. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:01:00,557][97672] Avg episode reward: [(0, '-1.300'), (1, '22.340')] -[2023-10-10 23:01:03,874][98559] Updated weights for policy 0, policy_version 56010 (0.0007) -[2023-10-10 23:01:04,096][98560] Updated weights for policy 1, policy_version 55722 (0.0007) -[2023-10-10 23:01:04,240][98559] Updated weights for policy 0, policy_version 56020 (0.0008) -[2023-10-10 23:01:04,461][98560] Updated weights for policy 1, policy_version 55732 (0.0008) -[2023-10-10 23:01:04,602][98559] Updated weights for policy 0, policy_version 56030 (0.0010) -[2023-10-10 23:01:04,825][98560] Updated weights for policy 1, policy_version 55742 (0.0007) -[2023-10-10 23:01:05,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 114458624. Throughput: 0: 1689.9, 1: 1688.2. Samples: 28619428. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:01:05,557][97672] Avg episode reward: [(0, '-1.300'), (1, '22.340')] -[2023-10-10 23:01:08,531][98559] Updated weights for policy 0, policy_version 56040 (0.0010) -[2023-10-10 23:01:08,893][98559] Updated weights for policy 0, policy_version 56050 (0.0007) -[2023-10-10 23:01:08,988][98560] Updated weights for policy 1, policy_version 55752 (0.0007) -[2023-10-10 23:01:09,257][98559] Updated weights for policy 0, policy_version 56060 (0.0008) -[2023-10-10 23:01:09,357][98560] Updated weights for policy 1, policy_version 55762 (0.0008) -[2023-10-10 23:01:09,729][98560] Updated weights for policy 1, policy_version 55772 (0.0008) -[2023-10-10 23:01:10,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 114524160. Throughput: 0: 1715.0, 1: 1711.0. Samples: 28630854. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:01:10,556][97672] Avg episode reward: [(0, '-1.300'), (1, '22.360')] -[2023-10-10 23:01:13,402][98559] Updated weights for policy 0, policy_version 56070 (0.0009) -[2023-10-10 23:01:13,766][98559] Updated weights for policy 0, policy_version 56080 (0.0008) -[2023-10-10 23:01:13,900][98560] Updated weights for policy 1, policy_version 55782 (0.0007) -[2023-10-10 23:01:14,118][98559] Updated weights for policy 0, policy_version 56090 (0.0008) -[2023-10-10 23:01:14,263][98560] Updated weights for policy 1, policy_version 55792 (0.0007) -[2023-10-10 23:01:14,635][98560] Updated weights for policy 1, policy_version 55802 (0.0010) -[2023-10-10 23:01:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 114589696. Throughput: 0: 1685.8, 1: 1712.0. Samples: 28650686. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:01:15,557][97672] Avg episode reward: [(0, '-1.300'), (1, '22.280')] -[2023-10-10 23:01:18,192][98559] Updated weights for policy 0, policy_version 56100 (0.0009) -[2023-10-10 23:01:18,552][98560] Updated weights for policy 1, policy_version 55812 (0.0009) -[2023-10-10 23:01:18,553][98559] Updated weights for policy 0, policy_version 56110 (0.0007) -[2023-10-10 23:01:18,911][98560] Updated weights for policy 1, policy_version 55822 (0.0008) -[2023-10-10 23:01:18,918][98559] Updated weights for policy 0, policy_version 56120 (0.0008) -[2023-10-10 23:01:19,277][98560] Updated weights for policy 1, policy_version 55832 (0.0008) -[2023-10-10 23:01:20,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 114655232. Throughput: 0: 1701.3, 1: 1684.3. Samples: 28670454. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:01:20,557][97672] Avg episode reward: [(0, '-1.300'), (1, '22.280')] -[2023-10-10 23:01:22,779][98559] Updated weights for policy 0, policy_version 56130 (0.0008) -[2023-10-10 23:01:23,184][98559] Updated weights for policy 0, policy_version 56140 (0.0011) -[2023-10-10 23:01:23,279][98560] Updated weights for policy 1, policy_version 55842 (0.0007) -[2023-10-10 23:01:23,544][98559] Updated weights for policy 0, policy_version 56150 (0.0009) -[2023-10-10 23:01:23,649][98560] Updated weights for policy 1, policy_version 55852 (0.0007) -[2023-10-10 23:01:23,907][98559] Updated weights for policy 0, policy_version 56160 (0.0008) -[2023-10-10 23:01:24,023][98560] Updated weights for policy 1, policy_version 55862 (0.0008) -[2023-10-10 23:01:24,391][98560] Updated weights for policy 1, policy_version 55872 (0.0008) -[2023-10-10 23:01:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 114720768. Throughput: 0: 1696.3, 1: 1710.9. Samples: 28681460. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:01:25,557][97672] Avg episode reward: [(0, '-1.300'), (1, '22.300')] -[2023-10-10 23:01:27,893][98559] Updated weights for policy 0, policy_version 56170 (0.0008) -[2023-10-10 23:01:28,255][98559] Updated weights for policy 0, policy_version 56180 (0.0008) -[2023-10-10 23:01:28,580][98560] Updated weights for policy 1, policy_version 55882 (0.0008) -[2023-10-10 23:01:28,619][98559] Updated weights for policy 0, policy_version 56190 (0.0007) -[2023-10-10 23:01:28,960][98560] Updated weights for policy 1, policy_version 55892 (0.0009) -[2023-10-10 23:01:29,325][98560] Updated weights for policy 1, policy_version 55902 (0.0009) -[2023-10-10 23:01:30,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 114786304. Throughput: 0: 1687.5, 1: 1698.4. Samples: 28701180. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:01:30,557][97672] Avg episode reward: [(0, '-1.300'), (1, '22.420')] -[2023-10-10 23:01:32,595][98559] Updated weights for policy 0, policy_version 56200 (0.0007) -[2023-10-10 23:01:32,959][98559] Updated weights for policy 0, policy_version 56210 (0.0008) -[2023-10-10 23:01:33,314][98560] Updated weights for policy 1, policy_version 55912 (0.0008) -[2023-10-10 23:01:33,332][98559] Updated weights for policy 0, policy_version 56220 (0.0007) -[2023-10-10 23:01:33,681][98560] Updated weights for policy 1, policy_version 55922 (0.0010) -[2023-10-10 23:01:34,048][98560] Updated weights for policy 1, policy_version 55932 (0.0010) -[2023-10-10 23:01:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 114851840. Throughput: 0: 1715.0, 1: 1682.8. Samples: 28721440. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:01:35,557][97672] Avg episode reward: [(0, '-1.300'), (1, '22.540')] -[2023-10-10 23:01:37,283][98559] Updated weights for policy 0, policy_version 56230 (0.0009) -[2023-10-10 23:01:37,646][98559] Updated weights for policy 0, policy_version 56240 (0.0008) -[2023-10-10 23:01:37,953][98560] Updated weights for policy 1, policy_version 55942 (0.0009) -[2023-10-10 23:01:38,014][98559] Updated weights for policy 0, policy_version 56250 (0.0009) -[2023-10-10 23:01:38,313][98560] Updated weights for policy 1, policy_version 55952 (0.0007) -[2023-10-10 23:01:38,684][98560] Updated weights for policy 1, policy_version 55962 (0.0007) -[2023-10-10 23:01:40,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 114917376. Throughput: 0: 1684.5, 1: 1708.7. Samples: 28732098. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:01:40,557][97672] Avg episode reward: [(0, '-1.300'), (1, '22.500')] -[2023-10-10 23:01:41,965][98559] Updated weights for policy 0, policy_version 56260 (0.0007) -[2023-10-10 23:01:42,339][98559] Updated weights for policy 0, policy_version 56270 (0.0007) -[2023-10-10 23:01:42,707][98559] Updated weights for policy 0, policy_version 56280 (0.0007) -[2023-10-10 23:01:42,835][98560] Updated weights for policy 1, policy_version 55972 (0.0007) -[2023-10-10 23:01:43,210][98560] Updated weights for policy 1, policy_version 55982 (0.0008) -[2023-10-10 23:01:43,583][98560] Updated weights for policy 1, policy_version 55992 (0.0008) -[2023-10-10 23:01:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 114982912. Throughput: 0: 1702.1, 1: 1679.7. Samples: 28752072. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:01:45,557][97672] Avg episode reward: [(0, '-1.300'), (1, '22.520')] -[2023-10-10 23:01:46,744][98559] Updated weights for policy 0, policy_version 56290 (0.0009) -[2023-10-10 23:01:47,118][98559] Updated weights for policy 0, policy_version 56300 (0.0009) -[2023-10-10 23:01:47,475][98559] Updated weights for policy 0, policy_version 56310 (0.0011) -[2023-10-10 23:01:47,592][98560] Updated weights for policy 1, policy_version 56002 (0.0007) -[2023-10-10 23:01:47,843][98559] Updated weights for policy 0, policy_version 56320 (0.0008) -[2023-10-10 23:01:47,967][98560] Updated weights for policy 1, policy_version 56012 (0.0009) -[2023-10-10 23:01:48,332][98560] Updated weights for policy 1, policy_version 56022 (0.0009) -[2023-10-10 23:01:48,700][98560] Updated weights for policy 1, policy_version 56032 (0.0007) -[2023-10-10 23:01:50,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 115048448. Throughput: 0: 1717.5, 1: 1694.0. Samples: 28772944. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:01:50,557][97672] Avg episode reward: [(0, '-1.300'), (1, '22.400')] -[2023-10-10 23:01:51,771][98559] Updated weights for policy 0, policy_version 56330 (0.0007) -[2023-10-10 23:01:52,135][98559] Updated weights for policy 0, policy_version 56340 (0.0007) -[2023-10-10 23:01:52,490][98559] Updated weights for policy 0, policy_version 56350 (0.0008) -[2023-10-10 23:01:52,741][98560] Updated weights for policy 1, policy_version 56042 (0.0009) -[2023-10-10 23:01:53,119][98560] Updated weights for policy 1, policy_version 56052 (0.0009) -[2023-10-10 23:01:53,497][98560] Updated weights for policy 1, policy_version 56062 (0.0010) -[2023-10-10 23:01:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 115113984. Throughput: 0: 1687.8, 1: 1693.4. Samples: 28783010. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:01:55,557][97672] Avg episode reward: [(0, '-1.240'), (1, '22.460')] -[2023-10-10 23:01:56,526][98559] Updated weights for policy 0, policy_version 56360 (0.0008) -[2023-10-10 23:01:56,896][98559] Updated weights for policy 0, policy_version 56370 (0.0008) -[2023-10-10 23:01:57,265][98559] Updated weights for policy 0, policy_version 56380 (0.0009) -[2023-10-10 23:01:57,593][98560] Updated weights for policy 1, policy_version 56072 (0.0010) -[2023-10-10 23:01:57,962][98560] Updated weights for policy 1, policy_version 56082 (0.0009) -[2023-10-10 23:01:58,324][98560] Updated weights for policy 1, policy_version 56092 (0.0007) -[2023-10-10 23:02:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 115179520. Throughput: 0: 1719.9, 1: 1670.8. Samples: 28803264. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:02:00,556][97672] Avg episode reward: [(0, '-1.240'), (1, '22.440')] -[2023-10-10 23:02:01,198][98559] Updated weights for policy 0, policy_version 56390 (0.0009) -[2023-10-10 23:02:01,568][98559] Updated weights for policy 0, policy_version 56400 (0.0011) -[2023-10-10 23:02:01,939][98559] Updated weights for policy 0, policy_version 56410 (0.0010) -[2023-10-10 23:02:02,336][98560] Updated weights for policy 1, policy_version 56102 (0.0007) -[2023-10-10 23:02:02,703][98560] Updated weights for policy 1, policy_version 56112 (0.0007) -[2023-10-10 23:02:03,056][98560] Updated weights for policy 1, policy_version 56122 (0.0008) -[2023-10-10 23:02:05,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 115245056. Throughput: 0: 1724.3, 1: 1695.1. Samples: 28824324. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:02:05,557][97672] Avg episode reward: [(0, '-1.240'), (1, '22.400')] -[2023-10-10 23:02:05,944][98559] Updated weights for policy 0, policy_version 56420 (0.0009) -[2023-10-10 23:02:06,313][98559] Updated weights for policy 0, policy_version 56430 (0.0007) -[2023-10-10 23:02:06,684][98559] Updated weights for policy 0, policy_version 56440 (0.0007) -[2023-10-10 23:02:07,044][98560] Updated weights for policy 1, policy_version 56132 (0.0008) -[2023-10-10 23:02:07,410][98560] Updated weights for policy 1, policy_version 56142 (0.0009) -[2023-10-10 23:02:07,779][98560] Updated weights for policy 1, policy_version 56152 (0.0009) -[2023-10-10 23:02:10,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 115310592. Throughput: 0: 1711.8, 1: 1679.5. Samples: 28834066. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:02:10,556][97672] Avg episode reward: [(0, '-1.240'), (1, '22.380')] -[2023-10-10 23:02:10,699][98559] Updated weights for policy 0, policy_version 56450 (0.0008) -[2023-10-10 23:02:11,065][98559] Updated weights for policy 0, policy_version 56460 (0.0008) -[2023-10-10 23:02:11,436][98559] Updated weights for policy 0, policy_version 56470 (0.0010) -[2023-10-10 23:02:11,801][98559] Updated weights for policy 0, policy_version 56480 (0.0010) -[2023-10-10 23:02:11,885][98560] Updated weights for policy 1, policy_version 56162 (0.0007) -[2023-10-10 23:02:12,254][98560] Updated weights for policy 1, policy_version 56172 (0.0007) -[2023-10-10 23:02:12,615][98560] Updated weights for policy 1, policy_version 56182 (0.0007) -[2023-10-10 23:02:12,983][98560] Updated weights for policy 1, policy_version 56192 (0.0007) -[2023-10-10 23:02:15,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 115376128. Throughput: 0: 1729.5, 1: 1683.2. Samples: 28854748. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:02:15,557][97672] Avg episode reward: [(0, '-1.240'), (1, '22.420')] -[2023-10-10 23:02:15,715][98559] Updated weights for policy 0, policy_version 56490 (0.0009) -[2023-10-10 23:02:16,088][98559] Updated weights for policy 0, policy_version 56500 (0.0009) -[2023-10-10 23:02:16,468][98559] Updated weights for policy 0, policy_version 56510 (0.0008) -[2023-10-10 23:02:17,152][98560] Updated weights for policy 1, policy_version 56202 (0.0009) -[2023-10-10 23:02:17,517][98560] Updated weights for policy 1, policy_version 56212 (0.0008) -[2023-10-10 23:02:17,887][98560] Updated weights for policy 1, policy_version 56222 (0.0009) -[2023-10-10 23:02:20,437][98559] Updated weights for policy 0, policy_version 56520 (0.0007) -[2023-10-10 23:02:20,556][97672] Fps is (10 sec: 13106.7, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 115441664. Throughput: 0: 1726.5, 1: 1699.2. Samples: 28875600. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:02:20,557][97672] Avg episode reward: [(0, '-1.240'), (1, '22.420')] -[2023-10-10 23:02:20,799][98559] Updated weights for policy 0, policy_version 56530 (0.0008) -[2023-10-10 23:02:21,170][98559] Updated weights for policy 0, policy_version 56540 (0.0007) -[2023-10-10 23:02:21,890][98560] Updated weights for policy 1, policy_version 56232 (0.0007) -[2023-10-10 23:02:22,261][98560] Updated weights for policy 1, policy_version 56242 (0.0007) -[2023-10-10 23:02:22,629][98560] Updated weights for policy 1, policy_version 56252 (0.0008) -[2023-10-10 23:02:25,193][98559] Updated weights for policy 0, policy_version 56550 (0.0009) -[2023-10-10 23:02:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 115507200. Throughput: 0: 1733.6, 1: 1671.6. Samples: 28885334. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:02:25,557][98559] Updated weights for policy 0, policy_version 56560 (0.0010) -[2023-10-10 23:02:25,557][97672] Avg episode reward: [(0, '-1.240'), (1, '22.360')] -[2023-10-10 23:02:25,930][98559] Updated weights for policy 0, policy_version 56570 (0.0010) -[2023-10-10 23:02:26,630][98560] Updated weights for policy 1, policy_version 56262 (0.0007) -[2023-10-10 23:02:26,989][98560] Updated weights for policy 1, policy_version 56272 (0.0007) -[2023-10-10 23:02:27,360][98560] Updated weights for policy 1, policy_version 56282 (0.0008) -[2023-10-10 23:02:29,950][98559] Updated weights for policy 0, policy_version 56580 (0.0009) -[2023-10-10 23:02:30,327][98559] Updated weights for policy 0, policy_version 56590 (0.0007) -[2023-10-10 23:02:30,556][97672] Fps is (10 sec: 13107.7, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 115572736. Throughput: 0: 1729.5, 1: 1692.2. Samples: 28906050. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:02:30,556][97672] Avg episode reward: [(0, '-1.240'), (1, '22.340')] -[2023-10-10 23:02:30,686][98559] Updated weights for policy 0, policy_version 56600 (0.0008) -[2023-10-10 23:02:31,402][98560] Updated weights for policy 1, policy_version 56292 (0.0008) -[2023-10-10 23:02:31,762][98560] Updated weights for policy 1, policy_version 56302 (0.0007) -[2023-10-10 23:02:32,132][98560] Updated weights for policy 1, policy_version 56312 (0.0008) -[2023-10-10 23:02:34,580][98559] Updated weights for policy 0, policy_version 56610 (0.0010) -[2023-10-10 23:02:34,940][98559] Updated weights for policy 0, policy_version 56620 (0.0007) -[2023-10-10 23:02:35,309][98559] Updated weights for policy 0, policy_version 56630 (0.0007) -[2023-10-10 23:02:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 115638272. Throughput: 0: 1710.3, 1: 1698.8. Samples: 28926354. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:02:35,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.340')] -[2023-10-10 23:02:35,571][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000056320_57671680.pth... -[2023-10-10 23:02:35,604][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000054752_56066048.pth -[2023-10-10 23:02:35,671][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000056640_57999360.pth... -[2023-10-10 23:02:35,675][98559] Updated weights for policy 0, policy_version 56640 (0.0008) -[2023-10-10 23:02:35,700][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000055040_56360960.pth -[2023-10-10 23:02:36,100][98560] Updated weights for policy 1, policy_version 56322 (0.0008) -[2023-10-10 23:02:36,465][98560] Updated weights for policy 1, policy_version 56332 (0.0008) -[2023-10-10 23:02:36,836][98560] Updated weights for policy 1, policy_version 56342 (0.0007) -[2023-10-10 23:02:37,202][98560] Updated weights for policy 1, policy_version 56352 (0.0007) -[2023-10-10 23:02:39,642][98559] Updated weights for policy 0, policy_version 56650 (0.0008) -[2023-10-10 23:02:40,004][98559] Updated weights for policy 0, policy_version 56660 (0.0008) -[2023-10-10 23:02:40,380][98559] Updated weights for policy 0, policy_version 56670 (0.0007) -[2023-10-10 23:02:40,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 115736576. Throughput: 0: 1733.1, 1: 1681.3. Samples: 28936658. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:02:40,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.420')] -[2023-10-10 23:02:41,092][98560] Updated weights for policy 1, policy_version 56362 (0.0008) -[2023-10-10 23:02:41,455][98560] Updated weights for policy 1, policy_version 56372 (0.0008) -[2023-10-10 23:02:41,823][98560] Updated weights for policy 1, policy_version 56382 (0.0009) -[2023-10-10 23:02:44,288][98559] Updated weights for policy 0, policy_version 56680 (0.0008) -[2023-10-10 23:02:44,650][98559] Updated weights for policy 0, policy_version 56690 (0.0009) -[2023-10-10 23:02:45,019][98559] Updated weights for policy 0, policy_version 56700 (0.0009) -[2023-10-10 23:02:45,556][97672] Fps is (10 sec: 16384.5, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 115802112. Throughput: 0: 1727.2, 1: 1703.7. Samples: 28957654. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:02:45,556][97672] Avg episode reward: [(0, '-1.180'), (1, '22.520')] -[2023-10-10 23:02:45,806][98560] Updated weights for policy 1, policy_version 56392 (0.0010) -[2023-10-10 23:02:46,173][98560] Updated weights for policy 1, policy_version 56402 (0.0009) -[2023-10-10 23:02:46,545][98560] Updated weights for policy 1, policy_version 56412 (0.0009) -[2023-10-10 23:02:48,991][98559] Updated weights for policy 0, policy_version 56710 (0.0007) -[2023-10-10 23:02:49,360][98559] Updated weights for policy 0, policy_version 56720 (0.0008) -[2023-10-10 23:02:49,743][98559] Updated weights for policy 0, policy_version 56730 (0.0009) -[2023-10-10 23:02:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 115867648. Throughput: 0: 1705.6, 1: 1708.4. Samples: 28977958. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:02:50,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.560')] -[2023-10-10 23:02:50,676][98560] Updated weights for policy 1, policy_version 56422 (0.0008) -[2023-10-10 23:02:51,034][98560] Updated weights for policy 1, policy_version 56432 (0.0017) -[2023-10-10 23:02:51,403][98560] Updated weights for policy 1, policy_version 56442 (0.0008) -[2023-10-10 23:02:53,817][98559] Updated weights for policy 0, policy_version 56740 (0.0008) -[2023-10-10 23:02:54,185][98559] Updated weights for policy 0, policy_version 56750 (0.0009) -[2023-10-10 23:02:54,546][98559] Updated weights for policy 0, policy_version 56760 (0.0007) -[2023-10-10 23:02:55,374][98560] Updated weights for policy 1, policy_version 56452 (0.0008) -[2023-10-10 23:02:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 115933184. Throughput: 0: 1732.1, 1: 1695.9. Samples: 28988328. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:02:55,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.500')] -[2023-10-10 23:02:55,754][98560] Updated weights for policy 1, policy_version 56462 (0.0007) -[2023-10-10 23:02:56,117][98560] Updated weights for policy 1, policy_version 56472 (0.0008) -[2023-10-10 23:02:58,456][98559] Updated weights for policy 0, policy_version 56770 (0.0009) -[2023-10-10 23:02:58,825][98559] Updated weights for policy 0, policy_version 56780 (0.0009) -[2023-10-10 23:02:59,200][98559] Updated weights for policy 0, policy_version 56790 (0.0009) -[2023-10-10 23:02:59,561][98559] Updated weights for policy 0, policy_version 56800 (0.0008) -[2023-10-10 23:03:00,272][98560] Updated weights for policy 1, policy_version 56482 (0.0011) -[2023-10-10 23:03:00,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 115998720. Throughput: 0: 1702.9, 1: 1711.0. Samples: 29008374. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:03:00,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.520')] -[2023-10-10 23:03:00,647][98560] Updated weights for policy 1, policy_version 56492 (0.0009) -[2023-10-10 23:03:01,013][98560] Updated weights for policy 1, policy_version 56502 (0.0007) -[2023-10-10 23:03:01,373][98560] Updated weights for policy 1, policy_version 56512 (0.0007) -[2023-10-10 23:03:03,443][98559] Updated weights for policy 0, policy_version 56810 (0.0008) -[2023-10-10 23:03:03,802][98559] Updated weights for policy 0, policy_version 56820 (0.0007) -[2023-10-10 23:03:04,175][98559] Updated weights for policy 0, policy_version 56830 (0.0011) -[2023-10-10 23:03:05,458][98560] Updated weights for policy 1, policy_version 56522 (0.0008) -[2023-10-10 23:03:05,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 116064256. Throughput: 0: 1704.6, 1: 1710.5. Samples: 29029280. Policy #0 lag: (min: 26.0, avg: 34.9, max: 58.0) -[2023-10-10 23:03:05,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.420')] -[2023-10-10 23:03:05,841][98560] Updated weights for policy 1, policy_version 56532 (0.0008) -[2023-10-10 23:03:06,201][98560] Updated weights for policy 1, policy_version 56542 (0.0007) -[2023-10-10 23:03:08,226][98559] Updated weights for policy 0, policy_version 56840 (0.0009) -[2023-10-10 23:03:08,583][98559] Updated weights for policy 0, policy_version 56850 (0.0010) -[2023-10-10 23:03:08,959][98559] Updated weights for policy 0, policy_version 56860 (0.0010) -[2023-10-10 23:03:10,141][98560] Updated weights for policy 1, policy_version 56552 (0.0007) -[2023-10-10 23:03:10,505][98560] Updated weights for policy 1, policy_version 56562 (0.0009) -[2023-10-10 23:03:10,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 116129792. Throughput: 0: 1713.1, 1: 1701.6. Samples: 29038994. Policy #0 lag: (min: 26.0, avg: 34.9, max: 58.0) -[2023-10-10 23:03:10,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.440')] -[2023-10-10 23:03:10,871][98560] Updated weights for policy 1, policy_version 56572 (0.0009) -[2023-10-10 23:03:13,052][98559] Updated weights for policy 0, policy_version 56870 (0.0010) -[2023-10-10 23:03:13,416][98559] Updated weights for policy 0, policy_version 56880 (0.0008) -[2023-10-10 23:03:13,782][98559] Updated weights for policy 0, policy_version 56890 (0.0008) -[2023-10-10 23:03:14,684][98560] Updated weights for policy 1, policy_version 56582 (0.0010) -[2023-10-10 23:03:15,052][98560] Updated weights for policy 1, policy_version 56592 (0.0008) -[2023-10-10 23:03:15,421][98560] Updated weights for policy 1, policy_version 56602 (0.0007) -[2023-10-10 23:03:15,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 116195328. Throughput: 0: 1694.2, 1: 1708.7. Samples: 29059180. Policy #0 lag: (min: 26.0, avg: 34.9, max: 58.0) -[2023-10-10 23:03:15,556][97672] Avg episode reward: [(0, '-1.220'), (1, '22.460')] -[2023-10-10 23:03:17,762][98559] Updated weights for policy 0, policy_version 56900 (0.0011) -[2023-10-10 23:03:18,123][98559] Updated weights for policy 0, policy_version 56910 (0.0011) -[2023-10-10 23:03:18,497][98559] Updated weights for policy 0, policy_version 56920 (0.0010) -[2023-10-10 23:03:19,503][98560] Updated weights for policy 1, policy_version 56612 (0.0008) -[2023-10-10 23:03:19,870][98560] Updated weights for policy 1, policy_version 56622 (0.0009) -[2023-10-10 23:03:20,238][98560] Updated weights for policy 1, policy_version 56632 (0.0010) -[2023-10-10 23:03:20,556][97672] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 116293632. Throughput: 0: 1710.2, 1: 1698.6. Samples: 29079750. Policy #0 lag: (min: 26.0, avg: 34.9, max: 58.0) -[2023-10-10 23:03:20,557][97672] Avg episode reward: [(0, '-1.240'), (1, '22.500')] -[2023-10-10 23:03:22,667][98559] Updated weights for policy 0, policy_version 56930 (0.0008) -[2023-10-10 23:03:23,033][98559] Updated weights for policy 0, policy_version 56940 (0.0007) -[2023-10-10 23:03:23,410][98559] Updated weights for policy 0, policy_version 56950 (0.0009) -[2023-10-10 23:03:23,775][98559] Updated weights for policy 0, policy_version 56960 (0.0007) -[2023-10-10 23:03:24,249][98560] Updated weights for policy 1, policy_version 56642 (0.0008) -[2023-10-10 23:03:24,608][98560] Updated weights for policy 1, policy_version 56652 (0.0008) -[2023-10-10 23:03:24,979][98560] Updated weights for policy 1, policy_version 56662 (0.0008) -[2023-10-10 23:03:25,342][98560] Updated weights for policy 1, policy_version 56672 (0.0007) -[2023-10-10 23:03:25,556][97672] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 116359168. Throughput: 0: 1697.0, 1: 1704.7. Samples: 29089734. Policy #0 lag: (min: 26.0, avg: 34.9, max: 58.0) -[2023-10-10 23:03:25,557][97672] Avg episode reward: [(0, '-1.240'), (1, '22.460')] -[2023-10-10 23:03:27,561][98559] Updated weights for policy 0, policy_version 56970 (0.0009) -[2023-10-10 23:03:27,926][98559] Updated weights for policy 0, policy_version 56980 (0.0008) -[2023-10-10 23:03:28,299][98559] Updated weights for policy 0, policy_version 56990 (0.0008) -[2023-10-10 23:03:29,437][98560] Updated weights for policy 1, policy_version 56682 (0.0007) -[2023-10-10 23:03:29,798][98560] Updated weights for policy 1, policy_version 56692 (0.0009) -[2023-10-10 23:03:30,175][98560] Updated weights for policy 1, policy_version 56702 (0.0010) -[2023-10-10 23:03:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 116424704. Throughput: 0: 1693.2, 1: 1707.0. Samples: 29110664. Policy #0 lag: (min: 26.0, avg: 34.9, max: 58.0) -[2023-10-10 23:03:30,557][97672] Avg episode reward: [(0, '-1.240'), (1, '22.420')] -[2023-10-10 23:03:32,296][98559] Updated weights for policy 0, policy_version 57000 (0.0008) -[2023-10-10 23:03:32,670][98559] Updated weights for policy 0, policy_version 57010 (0.0008) -[2023-10-10 23:03:33,035][98559] Updated weights for policy 0, policy_version 57020 (0.0009) -[2023-10-10 23:03:33,985][98560] Updated weights for policy 1, policy_version 56712 (0.0009) -[2023-10-10 23:03:34,353][98560] Updated weights for policy 1, policy_version 56722 (0.0007) -[2023-10-10 23:03:34,724][98560] Updated weights for policy 1, policy_version 56732 (0.0008) -[2023-10-10 23:03:35,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 116490240. Throughput: 0: 1715.7, 1: 1681.1. Samples: 29130816. Policy #0 lag: (min: 26.0, avg: 34.9, max: 58.0) -[2023-10-10 23:03:35,557][97672] Avg episode reward: [(0, '-1.240'), (1, '22.380')] -[2023-10-10 23:03:36,946][98559] Updated weights for policy 0, policy_version 57030 (0.0009) -[2023-10-10 23:03:37,313][98559] Updated weights for policy 0, policy_version 57040 (0.0010) -[2023-10-10 23:03:37,685][98559] Updated weights for policy 0, policy_version 57050 (0.0011) -[2023-10-10 23:03:38,690][98560] Updated weights for policy 1, policy_version 56742 (0.0010) -[2023-10-10 23:03:39,048][98560] Updated weights for policy 1, policy_version 56752 (0.0007) -[2023-10-10 23:03:39,423][98560] Updated weights for policy 1, policy_version 56762 (0.0008) -[2023-10-10 23:03:40,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 116555776. Throughput: 0: 1684.9, 1: 1709.0. Samples: 29141056. Policy #0 lag: (min: 26.0, avg: 34.9, max: 58.0) -[2023-10-10 23:03:40,556][97672] Avg episode reward: [(0, '-1.240'), (1, '22.460')] -[2023-10-10 23:03:41,604][98559] Updated weights for policy 0, policy_version 57060 (0.0010) -[2023-10-10 23:03:41,977][98559] Updated weights for policy 0, policy_version 57070 (0.0008) -[2023-10-10 23:03:42,339][98559] Updated weights for policy 0, policy_version 57080 (0.0007) -[2023-10-10 23:03:43,667][98560] Updated weights for policy 1, policy_version 56772 (0.0009) -[2023-10-10 23:03:44,027][98560] Updated weights for policy 1, policy_version 56782 (0.0011) -[2023-10-10 23:03:44,391][98560] Updated weights for policy 1, policy_version 56792 (0.0010) -[2023-10-10 23:03:45,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 116621312. Throughput: 0: 1712.5, 1: 1700.0. Samples: 29161936. Policy #0 lag: (min: 31.0, avg: 32.0, max: 52.0) -[2023-10-10 23:03:45,557][97672] Avg episode reward: [(0, '-1.240'), (1, '22.360')] -[2023-10-10 23:03:46,456][98559] Updated weights for policy 0, policy_version 57090 (0.0007) -[2023-10-10 23:03:46,860][98559] Updated weights for policy 0, policy_version 57100 (0.0009) -[2023-10-10 23:03:47,226][98559] Updated weights for policy 0, policy_version 57110 (0.0009) -[2023-10-10 23:03:47,598][98559] Updated weights for policy 0, policy_version 57120 (0.0009) -[2023-10-10 23:03:48,325][98560] Updated weights for policy 1, policy_version 56802 (0.0010) -[2023-10-10 23:03:48,704][98560] Updated weights for policy 1, policy_version 56812 (0.0011) -[2023-10-10 23:03:49,061][98560] Updated weights for policy 1, policy_version 56822 (0.0008) -[2023-10-10 23:03:49,430][98560] Updated weights for policy 1, policy_version 56832 (0.0009) -[2023-10-10 23:03:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 116686848. Throughput: 0: 1706.3, 1: 1678.1. Samples: 29181574. Policy #0 lag: (min: 31.0, avg: 32.0, max: 52.0) -[2023-10-10 23:03:50,556][97672] Avg episode reward: [(0, '-1.240'), (1, '22.400')] -[2023-10-10 23:03:51,504][98559] Updated weights for policy 0, policy_version 57130 (0.0010) -[2023-10-10 23:03:51,870][98559] Updated weights for policy 0, policy_version 57140 (0.0010) -[2023-10-10 23:03:52,243][98559] Updated weights for policy 0, policy_version 57150 (0.0010) -[2023-10-10 23:03:53,517][98560] Updated weights for policy 1, policy_version 56842 (0.0008) -[2023-10-10 23:03:53,893][98560] Updated weights for policy 1, policy_version 56852 (0.0008) -[2023-10-10 23:03:54,264][98560] Updated weights for policy 1, policy_version 56862 (0.0009) -[2023-10-10 23:03:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 116752384. Throughput: 0: 1689.1, 1: 1715.4. Samples: 29192196. Policy #0 lag: (min: 31.0, avg: 32.0, max: 52.0) -[2023-10-10 23:03:55,557][97672] Avg episode reward: [(0, '-1.240'), (1, '22.460')] -[2023-10-10 23:03:56,278][98559] Updated weights for policy 0, policy_version 57160 (0.0009) -[2023-10-10 23:03:56,647][98559] Updated weights for policy 0, policy_version 57170 (0.0007) -[2023-10-10 23:03:57,019][98559] Updated weights for policy 0, policy_version 57180 (0.0008) -[2023-10-10 23:03:58,304][98560] Updated weights for policy 1, policy_version 56872 (0.0008) -[2023-10-10 23:03:58,662][98560] Updated weights for policy 1, policy_version 56882 (0.0010) -[2023-10-10 23:03:59,033][98560] Updated weights for policy 1, policy_version 56892 (0.0010) -[2023-10-10 23:04:00,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 116817920. Throughput: 0: 1711.1, 1: 1689.1. Samples: 29212192. Policy #0 lag: (min: 31.0, avg: 32.0, max: 52.0) -[2023-10-10 23:04:00,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.520')] -[2023-10-10 23:04:01,060][98559] Updated weights for policy 0, policy_version 57190 (0.0010) -[2023-10-10 23:04:01,422][98559] Updated weights for policy 0, policy_version 57200 (0.0009) -[2023-10-10 23:04:01,796][98559] Updated weights for policy 0, policy_version 57210 (0.0007) -[2023-10-10 23:04:02,866][98560] Updated weights for policy 1, policy_version 56902 (0.0010) -[2023-10-10 23:04:03,233][98560] Updated weights for policy 1, policy_version 56912 (0.0008) -[2023-10-10 23:04:03,595][98560] Updated weights for policy 1, policy_version 56922 (0.0008) -[2023-10-10 23:04:05,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 116883456. Throughput: 0: 1712.5, 1: 1687.5. Samples: 29232748. Policy #0 lag: (min: 31.0, avg: 32.0, max: 52.0) -[2023-10-10 23:04:05,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.440')] -[2023-10-10 23:04:05,931][98559] Updated weights for policy 0, policy_version 57220 (0.0007) -[2023-10-10 23:04:06,290][98559] Updated weights for policy 0, policy_version 57230 (0.0007) -[2023-10-10 23:04:06,664][98559] Updated weights for policy 0, policy_version 57240 (0.0007) -[2023-10-10 23:04:07,553][98560] Updated weights for policy 1, policy_version 56932 (0.0008) -[2023-10-10 23:04:07,918][98560] Updated weights for policy 1, policy_version 56942 (0.0007) -[2023-10-10 23:04:08,288][98560] Updated weights for policy 1, policy_version 56952 (0.0007) -[2023-10-10 23:04:10,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 116948992. Throughput: 0: 1705.8, 1: 1700.0. Samples: 29242992. Policy #0 lag: (min: 31.0, avg: 32.0, max: 52.0) -[2023-10-10 23:04:10,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.380')] -[2023-10-10 23:04:10,597][98559] Updated weights for policy 0, policy_version 57250 (0.0008) -[2023-10-10 23:04:10,962][98559] Updated weights for policy 0, policy_version 57260 (0.0009) -[2023-10-10 23:04:11,324][98559] Updated weights for policy 0, policy_version 57270 (0.0010) -[2023-10-10 23:04:11,697][98559] Updated weights for policy 0, policy_version 57280 (0.0008) -[2023-10-10 23:04:12,392][98560] Updated weights for policy 1, policy_version 56962 (0.0008) -[2023-10-10 23:04:12,747][98560] Updated weights for policy 1, policy_version 56972 (0.0008) -[2023-10-10 23:04:13,112][98560] Updated weights for policy 1, policy_version 56982 (0.0009) -[2023-10-10 23:04:13,483][98560] Updated weights for policy 1, policy_version 56992 (0.0008) -[2023-10-10 23:04:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 117014528. Throughput: 0: 1712.6, 1: 1670.6. Samples: 29262908. Policy #0 lag: (min: 31.0, avg: 32.0, max: 52.0) -[2023-10-10 23:04:15,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.460')] -[2023-10-10 23:04:15,782][98559] Updated weights for policy 0, policy_version 57290 (0.0008) -[2023-10-10 23:04:16,150][98559] Updated weights for policy 0, policy_version 57300 (0.0007) -[2023-10-10 23:04:16,512][98559] Updated weights for policy 0, policy_version 57310 (0.0008) -[2023-10-10 23:04:17,537][98560] Updated weights for policy 1, policy_version 57002 (0.0008) -[2023-10-10 23:04:17,909][98560] Updated weights for policy 1, policy_version 57012 (0.0007) -[2023-10-10 23:04:18,277][98560] Updated weights for policy 1, policy_version 57022 (0.0007) -[2023-10-10 23:04:20,473][98559] Updated weights for policy 0, policy_version 57320 (0.0010) -[2023-10-10 23:04:20,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 117080064. Throughput: 0: 1702.9, 1: 1696.1. Samples: 29283772. Policy #0 lag: (min: 31.0, avg: 32.0, max: 52.0) -[2023-10-10 23:04:20,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.440')] -[2023-10-10 23:04:20,845][98559] Updated weights for policy 0, policy_version 57330 (0.0010) -[2023-10-10 23:04:21,209][98559] Updated weights for policy 0, policy_version 57340 (0.0010) -[2023-10-10 23:04:22,239][98560] Updated weights for policy 1, policy_version 57032 (0.0010) -[2023-10-10 23:04:22,617][98560] Updated weights for policy 1, policy_version 57042 (0.0010) -[2023-10-10 23:04:22,973][98560] Updated weights for policy 1, policy_version 57052 (0.0009) -[2023-10-10 23:04:25,197][98559] Updated weights for policy 0, policy_version 57350 (0.0008) -[2023-10-10 23:04:25,556][98559] Updated weights for policy 0, policy_version 57360 (0.0007) -[2023-10-10 23:04:25,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 117145600. Throughput: 0: 1711.1, 1: 1682.9. Samples: 29293786. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 23:04:25,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.400')] -[2023-10-10 23:04:25,932][98559] Updated weights for policy 0, policy_version 57370 (0.0007) -[2023-10-10 23:04:26,933][98560] Updated weights for policy 1, policy_version 57062 (0.0010) -[2023-10-10 23:04:27,301][98560] Updated weights for policy 1, policy_version 57072 (0.0009) -[2023-10-10 23:04:27,676][98560] Updated weights for policy 1, policy_version 57082 (0.0011) -[2023-10-10 23:04:29,817][98559] Updated weights for policy 0, policy_version 57380 (0.0008) -[2023-10-10 23:04:30,191][98559] Updated weights for policy 0, policy_version 57390 (0.0009) -[2023-10-10 23:04:30,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 117211136. Throughput: 0: 1706.6, 1: 1678.8. Samples: 29314278. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 23:04:30,556][97672] Avg episode reward: [(0, '-1.200'), (1, '22.460')] -[2023-10-10 23:04:30,565][98559] Updated weights for policy 0, policy_version 57400 (0.0008) -[2023-10-10 23:04:31,770][98560] Updated weights for policy 1, policy_version 57092 (0.0009) -[2023-10-10 23:04:32,132][98560] Updated weights for policy 1, policy_version 57102 (0.0007) -[2023-10-10 23:04:32,497][98560] Updated weights for policy 1, policy_version 57112 (0.0009) -[2023-10-10 23:04:34,496][98559] Updated weights for policy 0, policy_version 57410 (0.0010) -[2023-10-10 23:04:34,910][98559] Updated weights for policy 0, policy_version 57420 (0.0010) -[2023-10-10 23:04:35,283][98559] Updated weights for policy 0, policy_version 57430 (0.0008) -[2023-10-10 23:04:35,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 117276672. Throughput: 0: 1695.5, 1: 1700.7. Samples: 29334408. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 23:04:35,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.400')] -[2023-10-10 23:04:35,566][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000057120_58490880.pth... -[2023-10-10 23:04:35,605][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000055552_56885248.pth -[2023-10-10 23:04:35,649][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000057440_58818560.pth... -[2023-10-10 23:04:35,652][98559] Updated weights for policy 0, policy_version 57440 (0.0009) -[2023-10-10 23:04:35,688][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000055840_57180160.pth -[2023-10-10 23:04:36,496][98560] Updated weights for policy 1, policy_version 57122 (0.0008) -[2023-10-10 23:04:36,853][98560] Updated weights for policy 1, policy_version 57132 (0.0010) -[2023-10-10 23:04:37,224][98560] Updated weights for policy 1, policy_version 57142 (0.0010) -[2023-10-10 23:04:37,597][98560] Updated weights for policy 1, policy_version 57152 (0.0010) -[2023-10-10 23:04:39,481][98559] Updated weights for policy 0, policy_version 57450 (0.0008) -[2023-10-10 23:04:39,842][98559] Updated weights for policy 0, policy_version 57460 (0.0009) -[2023-10-10 23:04:40,211][98559] Updated weights for policy 0, policy_version 57470 (0.0008) -[2023-10-10 23:04:40,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 117374976. Throughput: 0: 1719.8, 1: 1671.2. Samples: 29344792. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 23:04:40,556][97672] Avg episode reward: [(0, '-1.200'), (1, '22.400')] -[2023-10-10 23:04:41,791][98560] Updated weights for policy 1, policy_version 57162 (0.0009) -[2023-10-10 23:04:42,167][98560] Updated weights for policy 1, policy_version 57172 (0.0010) -[2023-10-10 23:04:42,526][98560] Updated weights for policy 1, policy_version 57182 (0.0011) -[2023-10-10 23:04:44,279][98559] Updated weights for policy 0, policy_version 57480 (0.0008) -[2023-10-10 23:04:44,652][98559] Updated weights for policy 0, policy_version 57490 (0.0008) -[2023-10-10 23:04:45,034][98559] Updated weights for policy 0, policy_version 57500 (0.0010) -[2023-10-10 23:04:45,556][97672] Fps is (10 sec: 16384.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 117440512. Throughput: 0: 1710.9, 1: 1692.1. Samples: 29365328. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 23:04:45,556][97672] Avg episode reward: [(0, '-1.200'), (1, '22.300')] -[2023-10-10 23:04:46,660][98560] Updated weights for policy 1, policy_version 57192 (0.0010) -[2023-10-10 23:04:47,039][98560] Updated weights for policy 1, policy_version 57202 (0.0007) -[2023-10-10 23:04:47,408][98560] Updated weights for policy 1, policy_version 57212 (0.0009) -[2023-10-10 23:04:49,108][98559] Updated weights for policy 0, policy_version 57510 (0.0010) -[2023-10-10 23:04:49,471][98559] Updated weights for policy 0, policy_version 57520 (0.0010) -[2023-10-10 23:04:49,832][98559] Updated weights for policy 0, policy_version 57530 (0.0010) -[2023-10-10 23:04:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 117506048. Throughput: 0: 1690.3, 1: 1698.1. Samples: 29385222. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 23:04:50,556][97672] Avg episode reward: [(0, '-1.200'), (1, '22.380')] -[2023-10-10 23:04:51,471][98560] Updated weights for policy 1, policy_version 57222 (0.0008) -[2023-10-10 23:04:51,833][98560] Updated weights for policy 1, policy_version 57232 (0.0008) -[2023-10-10 23:04:52,197][98560] Updated weights for policy 1, policy_version 57242 (0.0007) -[2023-10-10 23:04:53,889][98559] Updated weights for policy 0, policy_version 57540 (0.0009) -[2023-10-10 23:04:54,250][98559] Updated weights for policy 0, policy_version 57550 (0.0007) -[2023-10-10 23:04:54,615][98559] Updated weights for policy 0, policy_version 57560 (0.0008) -[2023-10-10 23:04:55,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 117571584. Throughput: 0: 1717.7, 1: 1677.5. Samples: 29395776. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 23:04:55,556][97672] Avg episode reward: [(0, '-1.200'), (1, '22.360')] -[2023-10-10 23:04:56,075][98560] Updated weights for policy 1, policy_version 57252 (0.0010) -[2023-10-10 23:04:56,456][98560] Updated weights for policy 1, policy_version 57262 (0.0010) -[2023-10-10 23:04:56,827][98560] Updated weights for policy 1, policy_version 57272 (0.0010) -[2023-10-10 23:04:58,526][98559] Updated weights for policy 0, policy_version 57570 (0.0009) -[2023-10-10 23:04:58,897][98559] Updated weights for policy 0, policy_version 57580 (0.0007) -[2023-10-10 23:04:59,266][98559] Updated weights for policy 0, policy_version 57590 (0.0009) -[2023-10-10 23:04:59,635][98559] Updated weights for policy 0, policy_version 57600 (0.0009) -[2023-10-10 23:05:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 117637120. Throughput: 0: 1700.5, 1: 1705.3. Samples: 29416168. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:05:00,556][97672] Avg episode reward: [(0, '-1.200'), (1, '22.360')] -[2023-10-10 23:05:00,980][98560] Updated weights for policy 1, policy_version 57282 (0.0010) -[2023-10-10 23:05:01,352][98560] Updated weights for policy 1, policy_version 57292 (0.0008) -[2023-10-10 23:05:01,714][98560] Updated weights for policy 1, policy_version 57302 (0.0008) -[2023-10-10 23:05:02,089][98560] Updated weights for policy 1, policy_version 57312 (0.0009) -[2023-10-10 23:05:03,660][98559] Updated weights for policy 0, policy_version 57610 (0.0008) -[2023-10-10 23:05:04,025][98559] Updated weights for policy 0, policy_version 57620 (0.0008) -[2023-10-10 23:05:04,400][98559] Updated weights for policy 0, policy_version 57630 (0.0009) -[2023-10-10 23:05:05,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 117702656. Throughput: 0: 1698.5, 1: 1703.6. Samples: 29436864. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:05:05,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.360')] -[2023-10-10 23:05:06,005][98560] Updated weights for policy 1, policy_version 57322 (0.0007) -[2023-10-10 23:05:06,381][98560] Updated weights for policy 1, policy_version 57332 (0.0008) -[2023-10-10 23:05:06,742][98560] Updated weights for policy 1, policy_version 57342 (0.0009) -[2023-10-10 23:05:08,170][98559] Updated weights for policy 0, policy_version 57640 (0.0007) -[2023-10-10 23:05:08,544][98559] Updated weights for policy 0, policy_version 57650 (0.0007) -[2023-10-10 23:05:08,917][98559] Updated weights for policy 0, policy_version 57660 (0.0010) -[2023-10-10 23:05:10,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 117768192. Throughput: 0: 1717.1, 1: 1689.0. Samples: 29447062. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:05:10,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.460')] -[2023-10-10 23:05:10,847][98560] Updated weights for policy 1, policy_version 57352 (0.0010) -[2023-10-10 23:05:11,219][98560] Updated weights for policy 1, policy_version 57362 (0.0011) -[2023-10-10 23:05:11,585][98560] Updated weights for policy 1, policy_version 57372 (0.0011) -[2023-10-10 23:05:13,006][98559] Updated weights for policy 0, policy_version 57670 (0.0007) -[2023-10-10 23:05:13,375][98559] Updated weights for policy 0, policy_version 57680 (0.0008) -[2023-10-10 23:05:13,743][98559] Updated weights for policy 0, policy_version 57690 (0.0009) -[2023-10-10 23:05:15,546][98560] Updated weights for policy 1, policy_version 57382 (0.0007) -[2023-10-10 23:05:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 117833728. Throughput: 0: 1698.5, 1: 1698.2. Samples: 29467130. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:05:15,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.440')] -[2023-10-10 23:05:15,910][98560] Updated weights for policy 1, policy_version 57392 (0.0007) -[2023-10-10 23:05:16,272][98560] Updated weights for policy 1, policy_version 57402 (0.0007) -[2023-10-10 23:05:17,696][98559] Updated weights for policy 0, policy_version 57700 (0.0007) -[2023-10-10 23:05:18,060][98559] Updated weights for policy 0, policy_version 57710 (0.0009) -[2023-10-10 23:05:18,418][98559] Updated weights for policy 0, policy_version 57720 (0.0009) -[2023-10-10 23:05:20,422][98560] Updated weights for policy 1, policy_version 57412 (0.0007) -[2023-10-10 23:05:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 117899264. Throughput: 0: 1715.6, 1: 1705.6. Samples: 29488366. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:05:20,556][97672] Avg episode reward: [(0, '-1.180'), (1, '22.440')] -[2023-10-10 23:05:20,784][98560] Updated weights for policy 1, policy_version 57422 (0.0009) -[2023-10-10 23:05:21,156][98560] Updated weights for policy 1, policy_version 57432 (0.0007) -[2023-10-10 23:05:22,354][98559] Updated weights for policy 0, policy_version 57730 (0.0010) -[2023-10-10 23:05:22,771][98559] Updated weights for policy 0, policy_version 57740 (0.0011) -[2023-10-10 23:05:23,137][98559] Updated weights for policy 0, policy_version 57750 (0.0010) -[2023-10-10 23:05:23,498][98559] Updated weights for policy 0, policy_version 57760 (0.0009) -[2023-10-10 23:05:25,170][98560] Updated weights for policy 1, policy_version 57442 (0.0007) -[2023-10-10 23:05:25,532][98560] Updated weights for policy 1, policy_version 57452 (0.0009) -[2023-10-10 23:05:25,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 117964800. Throughput: 0: 1699.2, 1: 1702.1. Samples: 29497850. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:05:25,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.460')] -[2023-10-10 23:05:25,895][98560] Updated weights for policy 1, policy_version 57462 (0.0008) -[2023-10-10 23:05:26,255][98560] Updated weights for policy 1, policy_version 57472 (0.0008) -[2023-10-10 23:05:27,303][98559] Updated weights for policy 0, policy_version 57770 (0.0009) -[2023-10-10 23:05:27,668][98559] Updated weights for policy 0, policy_version 57780 (0.0011) -[2023-10-10 23:05:28,034][98559] Updated weights for policy 0, policy_version 57790 (0.0010) -[2023-10-10 23:05:30,157][98560] Updated weights for policy 1, policy_version 57482 (0.0010) -[2023-10-10 23:05:30,523][98560] Updated weights for policy 1, policy_version 57492 (0.0008) -[2023-10-10 23:05:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 118030336. Throughput: 0: 1704.4, 1: 1709.2. Samples: 29518936. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:05:30,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.600')] -[2023-10-10 23:05:30,891][98560] Updated weights for policy 1, policy_version 57502 (0.0007) -[2023-10-10 23:05:32,008][98559] Updated weights for policy 0, policy_version 57800 (0.0010) -[2023-10-10 23:05:32,371][98559] Updated weights for policy 0, policy_version 57810 (0.0007) -[2023-10-10 23:05:32,738][98559] Updated weights for policy 0, policy_version 57820 (0.0010) -[2023-10-10 23:05:35,024][98560] Updated weights for policy 1, policy_version 57512 (0.0009) -[2023-10-10 23:05:35,404][98560] Updated weights for policy 1, policy_version 57522 (0.0010) -[2023-10-10 23:05:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 118095872. Throughput: 0: 1728.3, 1: 1714.1. Samples: 29540128. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:05:35,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.540')] -[2023-10-10 23:05:35,782][98560] Updated weights for policy 1, policy_version 57532 (0.0007) -[2023-10-10 23:05:36,719][98559] Updated weights for policy 0, policy_version 57830 (0.0009) -[2023-10-10 23:05:37,084][98559] Updated weights for policy 0, policy_version 57840 (0.0011) -[2023-10-10 23:05:37,453][98559] Updated weights for policy 0, policy_version 57850 (0.0009) -[2023-10-10 23:05:39,832][98560] Updated weights for policy 1, policy_version 57542 (0.0009) -[2023-10-10 23:05:40,201][98560] Updated weights for policy 1, policy_version 57552 (0.0008) -[2023-10-10 23:05:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 118161408. Throughput: 0: 1700.2, 1: 1713.2. Samples: 29549378. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) -[2023-10-10 23:05:40,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.560')] -[2023-10-10 23:05:40,559][98560] Updated weights for policy 1, policy_version 57562 (0.0011) -[2023-10-10 23:05:41,451][98559] Updated weights for policy 0, policy_version 57860 (0.0008) -[2023-10-10 23:05:41,816][98559] Updated weights for policy 0, policy_version 57870 (0.0008) -[2023-10-10 23:05:42,191][98559] Updated weights for policy 0, policy_version 57880 (0.0008) -[2023-10-10 23:05:44,382][98560] Updated weights for policy 1, policy_version 57572 (0.0009) -[2023-10-10 23:05:44,750][98560] Updated weights for policy 1, policy_version 57582 (0.0010) -[2023-10-10 23:05:45,115][98560] Updated weights for policy 1, policy_version 57592 (0.0008) -[2023-10-10 23:05:45,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 118259712. Throughput: 0: 1716.6, 1: 1710.2. Samples: 29570374. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) -[2023-10-10 23:05:45,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.580')] -[2023-10-10 23:05:46,186][98559] Updated weights for policy 0, policy_version 57890 (0.0009) -[2023-10-10 23:05:46,547][98559] Updated weights for policy 0, policy_version 57900 (0.0008) -[2023-10-10 23:05:46,918][98559] Updated weights for policy 0, policy_version 57910 (0.0008) -[2023-10-10 23:05:47,290][98559] Updated weights for policy 0, policy_version 57920 (0.0009) -[2023-10-10 23:05:49,277][98560] Updated weights for policy 1, policy_version 57602 (0.0009) -[2023-10-10 23:05:49,635][98560] Updated weights for policy 1, policy_version 57612 (0.0009) -[2023-10-10 23:05:50,003][98560] Updated weights for policy 1, policy_version 57622 (0.0011) -[2023-10-10 23:05:50,378][98560] Updated weights for policy 1, policy_version 57632 (0.0011) -[2023-10-10 23:05:50,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 118325248. Throughput: 0: 1728.3, 1: 1697.8. Samples: 29591036. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) -[2023-10-10 23:05:50,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.580')] -[2023-10-10 23:05:51,429][98559] Updated weights for policy 0, policy_version 57930 (0.0008) -[2023-10-10 23:05:51,796][98559] Updated weights for policy 0, policy_version 57940 (0.0007) -[2023-10-10 23:05:52,166][98559] Updated weights for policy 0, policy_version 57950 (0.0010) -[2023-10-10 23:05:54,509][98560] Updated weights for policy 1, policy_version 57642 (0.0009) -[2023-10-10 23:05:54,879][98560] Updated weights for policy 1, policy_version 57652 (0.0009) -[2023-10-10 23:05:55,238][98560] Updated weights for policy 1, policy_version 57662 (0.0009) -[2023-10-10 23:05:55,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 118390784. Throughput: 0: 1699.7, 1: 1709.5. Samples: 29600478. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) -[2023-10-10 23:05:55,556][97672] Avg episode reward: [(0, '-1.180'), (1, '22.560')] -[2023-10-10 23:05:56,193][98559] Updated weights for policy 0, policy_version 57960 (0.0009) -[2023-10-10 23:05:56,559][98559] Updated weights for policy 0, policy_version 57970 (0.0010) -[2023-10-10 23:05:56,917][98559] Updated weights for policy 0, policy_version 57980 (0.0009) -[2023-10-10 23:05:59,230][98560] Updated weights for policy 1, policy_version 57672 (0.0008) -[2023-10-10 23:05:59,595][98560] Updated weights for policy 1, policy_version 57682 (0.0011) -[2023-10-10 23:05:59,959][98560] Updated weights for policy 1, policy_version 57692 (0.0010) -[2023-10-10 23:06:00,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 118456320. Throughput: 0: 1724.4, 1: 1710.5. Samples: 29621702. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) -[2023-10-10 23:06:00,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.440')] -[2023-10-10 23:06:00,916][98559] Updated weights for policy 0, policy_version 57990 (0.0008) -[2023-10-10 23:06:01,282][98559] Updated weights for policy 0, policy_version 58000 (0.0008) -[2023-10-10 23:06:01,633][98559] Updated weights for policy 0, policy_version 58010 (0.0008) -[2023-10-10 23:06:04,023][98560] Updated weights for policy 1, policy_version 57702 (0.0009) -[2023-10-10 23:06:04,391][98560] Updated weights for policy 1, policy_version 57712 (0.0010) -[2023-10-10 23:06:04,762][98560] Updated weights for policy 1, policy_version 57722 (0.0009) -[2023-10-10 23:06:05,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 118521856. Throughput: 0: 1725.9, 1: 1682.3. Samples: 29641734. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) -[2023-10-10 23:06:05,557][97672] Avg episode reward: [(0, '-1.180'), (1, '22.380')] -[2023-10-10 23:06:05,625][98559] Updated weights for policy 0, policy_version 58020 (0.0008) -[2023-10-10 23:06:05,996][98559] Updated weights for policy 0, policy_version 58030 (0.0009) -[2023-10-10 23:06:06,355][98559] Updated weights for policy 0, policy_version 58040 (0.0010) -[2023-10-10 23:06:08,701][98560] Updated weights for policy 1, policy_version 57732 (0.0008) -[2023-10-10 23:06:09,070][98560] Updated weights for policy 1, policy_version 57742 (0.0009) -[2023-10-10 23:06:09,436][98560] Updated weights for policy 1, policy_version 57752 (0.0008) -[2023-10-10 23:06:10,389][98559] Updated weights for policy 0, policy_version 58050 (0.0010) -[2023-10-10 23:06:10,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 118587392. Throughput: 0: 1720.0, 1: 1707.7. Samples: 29652096. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) -[2023-10-10 23:06:10,556][97672] Avg episode reward: [(0, '-1.100'), (1, '22.320')] -[2023-10-10 23:06:10,783][98559] Updated weights for policy 0, policy_version 58060 (0.0010) -[2023-10-10 23:06:11,147][98559] Updated weights for policy 0, policy_version 58070 (0.0008) -[2023-10-10 23:06:11,514][98559] Updated weights for policy 0, policy_version 58080 (0.0007) -[2023-10-10 23:06:13,540][98560] Updated weights for policy 1, policy_version 57762 (0.0009) -[2023-10-10 23:06:13,902][98560] Updated weights for policy 1, policy_version 57772 (0.0011) -[2023-10-10 23:06:14,277][98560] Updated weights for policy 1, policy_version 57782 (0.0011) -[2023-10-10 23:06:14,635][98560] Updated weights for policy 1, policy_version 57792 (0.0008) -[2023-10-10 23:06:15,416][98559] Updated weights for policy 0, policy_version 58090 (0.0012) -[2023-10-10 23:06:15,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 118652928. Throughput: 0: 1724.6, 1: 1691.9. Samples: 29672678. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) -[2023-10-10 23:06:15,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.260')] -[2023-10-10 23:06:15,790][98559] Updated weights for policy 0, policy_version 58100 (0.0009) -[2023-10-10 23:06:16,148][98559] Updated weights for policy 0, policy_version 58110 (0.0011) -[2023-10-10 23:06:18,645][98560] Updated weights for policy 1, policy_version 57802 (0.0009) -[2023-10-10 23:06:19,018][98560] Updated weights for policy 1, policy_version 57812 (0.0010) -[2023-10-10 23:06:19,388][98560] Updated weights for policy 1, policy_version 57822 (0.0010) -[2023-10-10 23:06:20,135][98559] Updated weights for policy 0, policy_version 58120 (0.0009) -[2023-10-10 23:06:20,502][98559] Updated weights for policy 0, policy_version 58130 (0.0007) -[2023-10-10 23:06:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 118718464. Throughput: 0: 1707.6, 1: 1666.1. Samples: 29691946. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 23:06:20,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.120')] -[2023-10-10 23:06:20,868][98559] Updated weights for policy 0, policy_version 58140 (0.0008) -[2023-10-10 23:06:23,475][98560] Updated weights for policy 1, policy_version 57832 (0.0008) -[2023-10-10 23:06:23,851][98560] Updated weights for policy 1, policy_version 57842 (0.0007) -[2023-10-10 23:06:24,218][98560] Updated weights for policy 1, policy_version 57852 (0.0008) -[2023-10-10 23:06:24,727][98559] Updated weights for policy 0, policy_version 58150 (0.0009) -[2023-10-10 23:06:25,091][98559] Updated weights for policy 0, policy_version 58160 (0.0011) -[2023-10-10 23:06:25,459][98559] Updated weights for policy 0, policy_version 58170 (0.0008) -[2023-10-10 23:06:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 118784000. Throughput: 0: 1721.8, 1: 1695.2. Samples: 29703144. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 23:06:25,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.120')] -[2023-10-10 23:06:28,234][98560] Updated weights for policy 1, policy_version 57862 (0.0008) -[2023-10-10 23:06:28,601][98560] Updated weights for policy 1, policy_version 57872 (0.0009) -[2023-10-10 23:06:28,960][98560] Updated weights for policy 1, policy_version 57882 (0.0007) -[2023-10-10 23:06:29,262][98559] Updated weights for policy 0, policy_version 58180 (0.0008) -[2023-10-10 23:06:29,629][98559] Updated weights for policy 0, policy_version 58190 (0.0008) -[2023-10-10 23:06:29,992][98559] Updated weights for policy 0, policy_version 58200 (0.0008) -[2023-10-10 23:06:30,556][97672] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 118882304. Throughput: 0: 1725.2, 1: 1673.0. Samples: 29723292. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 23:06:30,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.140')] -[2023-10-10 23:06:32,942][98560] Updated weights for policy 1, policy_version 57892 (0.0008) -[2023-10-10 23:06:33,311][98560] Updated weights for policy 1, policy_version 57902 (0.0007) -[2023-10-10 23:06:33,675][98560] Updated weights for policy 1, policy_version 57912 (0.0008) -[2023-10-10 23:06:34,072][98559] Updated weights for policy 0, policy_version 58210 (0.0007) -[2023-10-10 23:06:34,440][98559] Updated weights for policy 0, policy_version 58220 (0.0009) -[2023-10-10 23:06:34,803][98559] Updated weights for policy 0, policy_version 58230 (0.0011) -[2023-10-10 23:06:35,168][98559] Updated weights for policy 0, policy_version 58240 (0.0012) -[2023-10-10 23:06:35,556][97672] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 118947840. Throughput: 0: 1696.9, 1: 1670.7. Samples: 29742578. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 23:06:35,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.120')] -[2023-10-10 23:06:35,568][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000057920_59310080.pth... -[2023-10-10 23:06:35,568][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000058240_59637760.pth... -[2023-10-10 23:06:35,608][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000056640_57999360.pth -[2023-10-10 23:06:35,610][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000056320_57671680.pth -[2023-10-10 23:06:37,817][98560] Updated weights for policy 1, policy_version 57922 (0.0008) -[2023-10-10 23:06:38,174][98560] Updated weights for policy 1, policy_version 57932 (0.0009) -[2023-10-10 23:06:38,536][98560] Updated weights for policy 1, policy_version 57942 (0.0009) -[2023-10-10 23:06:38,905][98560] Updated weights for policy 1, policy_version 57952 (0.0009) -[2023-10-10 23:06:38,906][98559] Updated weights for policy 0, policy_version 58250 (0.0009) -[2023-10-10 23:06:39,268][98559] Updated weights for policy 0, policy_version 58260 (0.0010) -[2023-10-10 23:06:39,630][98559] Updated weights for policy 0, policy_version 58270 (0.0010) -[2023-10-10 23:06:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 119013376. Throughput: 0: 1736.3, 1: 1689.2. Samples: 29754624. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 23:06:40,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.100')] -[2023-10-10 23:06:42,819][98560] Updated weights for policy 1, policy_version 57962 (0.0008) -[2023-10-10 23:06:43,186][98560] Updated weights for policy 1, policy_version 57972 (0.0008) -[2023-10-10 23:06:43,558][98560] Updated weights for policy 1, policy_version 57982 (0.0009) -[2023-10-10 23:06:43,793][98559] Updated weights for policy 0, policy_version 58280 (0.0008) -[2023-10-10 23:06:44,156][98559] Updated weights for policy 0, policy_version 58290 (0.0007) -[2023-10-10 23:06:44,519][98559] Updated weights for policy 0, policy_version 58300 (0.0010) -[2023-10-10 23:06:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 119078912. Throughput: 0: 1710.7, 1: 1660.8. Samples: 29773422. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 23:06:45,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.100')] -[2023-10-10 23:06:47,549][98560] Updated weights for policy 1, policy_version 57992 (0.0010) -[2023-10-10 23:06:47,914][98560] Updated weights for policy 1, policy_version 58002 (0.0010) -[2023-10-10 23:06:48,285][98560] Updated weights for policy 1, policy_version 58012 (0.0010) -[2023-10-10 23:06:48,506][98559] Updated weights for policy 0, policy_version 58310 (0.0008) -[2023-10-10 23:06:48,875][98559] Updated weights for policy 0, policy_version 58320 (0.0007) -[2023-10-10 23:06:49,231][98559] Updated weights for policy 0, policy_version 58330 (0.0008) -[2023-10-10 23:06:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 119144448. Throughput: 0: 1699.1, 1: 1685.6. Samples: 29794042. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 23:06:50,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.060')] -[2023-10-10 23:06:52,432][98560] Updated weights for policy 1, policy_version 58022 (0.0009) -[2023-10-10 23:06:52,811][98560] Updated weights for policy 1, policy_version 58032 (0.0010) -[2023-10-10 23:06:53,124][98559] Updated weights for policy 0, policy_version 58340 (0.0009) -[2023-10-10 23:06:53,176][98560] Updated weights for policy 1, policy_version 58042 (0.0008) -[2023-10-10 23:06:53,497][98559] Updated weights for policy 0, policy_version 58350 (0.0009) -[2023-10-10 23:06:53,855][98559] Updated weights for policy 0, policy_version 58360 (0.0011) -[2023-10-10 23:06:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 119209984. Throughput: 0: 1723.1, 1: 1679.5. Samples: 29805214. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 23:06:55,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.100')] -[2023-10-10 23:06:56,995][98560] Updated weights for policy 1, policy_version 58052 (0.0008) -[2023-10-10 23:06:57,357][98560] Updated weights for policy 1, policy_version 58062 (0.0009) -[2023-10-10 23:06:57,724][98560] Updated weights for policy 1, policy_version 58072 (0.0007) -[2023-10-10 23:06:57,831][98559] Updated weights for policy 0, policy_version 58370 (0.0009) -[2023-10-10 23:06:58,228][98559] Updated weights for policy 0, policy_version 58380 (0.0007) -[2023-10-10 23:06:58,598][98559] Updated weights for policy 0, policy_version 58390 (0.0007) -[2023-10-10 23:06:58,961][98559] Updated weights for policy 0, policy_version 58400 (0.0007) -[2023-10-10 23:07:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 119275520. Throughput: 0: 1702.2, 1: 1675.1. Samples: 29824658. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 23:07:00,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.200')] -[2023-10-10 23:07:01,757][98560] Updated weights for policy 1, policy_version 58082 (0.0007) -[2023-10-10 23:07:02,128][98560] Updated weights for policy 1, policy_version 58092 (0.0007) -[2023-10-10 23:07:02,491][98560] Updated weights for policy 1, policy_version 58102 (0.0008) -[2023-10-10 23:07:02,853][98560] Updated weights for policy 1, policy_version 58112 (0.0008) -[2023-10-10 23:07:02,916][98559] Updated weights for policy 0, policy_version 58410 (0.0009) -[2023-10-10 23:07:03,280][98559] Updated weights for policy 0, policy_version 58420 (0.0008) -[2023-10-10 23:07:03,653][98559] Updated weights for policy 0, policy_version 58430 (0.0008) -[2023-10-10 23:07:05,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 119341056. Throughput: 0: 1717.5, 1: 1697.4. Samples: 29845618. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 23:07:05,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.240')] -[2023-10-10 23:07:06,972][98560] Updated weights for policy 1, policy_version 58122 (0.0010) -[2023-10-10 23:07:07,344][98560] Updated weights for policy 1, policy_version 58132 (0.0010) -[2023-10-10 23:07:07,679][98559] Updated weights for policy 0, policy_version 58440 (0.0008) -[2023-10-10 23:07:07,703][98560] Updated weights for policy 1, policy_version 58142 (0.0007) -[2023-10-10 23:07:08,049][98559] Updated weights for policy 0, policy_version 58450 (0.0009) -[2023-10-10 23:07:08,416][98559] Updated weights for policy 0, policy_version 58460 (0.0009) -[2023-10-10 23:07:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 119406592. Throughput: 0: 1712.1, 1: 1672.4. Samples: 29855446. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 23:07:10,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.400')] -[2023-10-10 23:07:11,812][98560] Updated weights for policy 1, policy_version 58152 (0.0007) -[2023-10-10 23:07:12,180][98560] Updated weights for policy 1, policy_version 58162 (0.0008) -[2023-10-10 23:07:12,434][98559] Updated weights for policy 0, policy_version 58470 (0.0009) -[2023-10-10 23:07:12,541][98560] Updated weights for policy 1, policy_version 58172 (0.0009) -[2023-10-10 23:07:12,801][98559] Updated weights for policy 0, policy_version 58480 (0.0008) -[2023-10-10 23:07:13,172][98559] Updated weights for policy 0, policy_version 58490 (0.0009) -[2023-10-10 23:07:15,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 119472128. Throughput: 0: 1698.8, 1: 1689.6. Samples: 29875770. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 23:07:15,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.420')] -[2023-10-10 23:07:16,603][98560] Updated weights for policy 1, policy_version 58182 (0.0009) -[2023-10-10 23:07:16,976][98560] Updated weights for policy 1, policy_version 58192 (0.0009) -[2023-10-10 23:07:17,139][98559] Updated weights for policy 0, policy_version 58500 (0.0008) -[2023-10-10 23:07:17,347][98560] Updated weights for policy 1, policy_version 58202 (0.0008) -[2023-10-10 23:07:17,500][98559] Updated weights for policy 0, policy_version 58510 (0.0010) -[2023-10-10 23:07:17,870][98559] Updated weights for policy 0, policy_version 58520 (0.0010) -[2023-10-10 23:07:20,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 119537664. Throughput: 0: 1729.6, 1: 1705.3. Samples: 29897146. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 23:07:20,557][97672] Avg episode reward: [(0, '-1.100'), (1, '22.460')] -[2023-10-10 23:07:21,420][98560] Updated weights for policy 1, policy_version 58212 (0.0008) -[2023-10-10 23:07:21,786][98560] Updated weights for policy 1, policy_version 58222 (0.0008) -[2023-10-10 23:07:21,840][98559] Updated weights for policy 0, policy_version 58530 (0.0010) -[2023-10-10 23:07:22,149][98560] Updated weights for policy 1, policy_version 58232 (0.0008) -[2023-10-10 23:07:22,196][98559] Updated weights for policy 0, policy_version 58540 (0.0007) -[2023-10-10 23:07:22,559][98559] Updated weights for policy 0, policy_version 58550 (0.0008) -[2023-10-10 23:07:22,920][98559] Updated weights for policy 0, policy_version 58560 (0.0008) -[2023-10-10 23:07:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 119603200. Throughput: 0: 1697.5, 1: 1677.2. Samples: 29906488. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 23:07:25,557][97672] Avg episode reward: [(0, '-1.080'), (1, '22.440')] -[2023-10-10 23:07:26,345][98560] Updated weights for policy 1, policy_version 58242 (0.0007) -[2023-10-10 23:07:26,705][98560] Updated weights for policy 1, policy_version 58252 (0.0008) -[2023-10-10 23:07:26,854][98559] Updated weights for policy 0, policy_version 58570 (0.0009) -[2023-10-10 23:07:27,067][98560] Updated weights for policy 1, policy_version 58262 (0.0007) -[2023-10-10 23:07:27,228][98559] Updated weights for policy 0, policy_version 58580 (0.0010) -[2023-10-10 23:07:27,442][98560] Updated weights for policy 1, policy_version 58272 (0.0008) -[2023-10-10 23:07:27,589][98559] Updated weights for policy 0, policy_version 58590 (0.0008) -[2023-10-10 23:07:30,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 119668736. Throughput: 0: 1724.5, 1: 1699.5. Samples: 29927498. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 23:07:30,556][97672] Avg episode reward: [(0, '-1.040'), (1, '22.500')] -[2023-10-10 23:07:31,447][98560] Updated weights for policy 1, policy_version 58282 (0.0007) -[2023-10-10 23:07:31,486][98559] Updated weights for policy 0, policy_version 58600 (0.0008) -[2023-10-10 23:07:31,808][98560] Updated weights for policy 1, policy_version 58292 (0.0008) -[2023-10-10 23:07:31,858][98559] Updated weights for policy 0, policy_version 58610 (0.0007) -[2023-10-10 23:07:32,181][98560] Updated weights for policy 1, policy_version 58302 (0.0008) -[2023-10-10 23:07:32,224][98559] Updated weights for policy 0, policy_version 58620 (0.0007) -[2023-10-10 23:07:35,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 119734272. Throughput: 0: 1731.5, 1: 1697.8. Samples: 29948360. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:07:35,557][97672] Avg episode reward: [(0, '-1.040'), (1, '22.540')] -[2023-10-10 23:07:36,296][98560] Updated weights for policy 1, policy_version 58312 (0.0008) -[2023-10-10 23:07:36,439][98559] Updated weights for policy 0, policy_version 58630 (0.0009) -[2023-10-10 23:07:36,670][98560] Updated weights for policy 1, policy_version 58322 (0.0008) -[2023-10-10 23:07:36,809][98559] Updated weights for policy 0, policy_version 58640 (0.0008) -[2023-10-10 23:07:37,044][98560] Updated weights for policy 1, policy_version 58332 (0.0008) -[2023-10-10 23:07:37,173][98559] Updated weights for policy 0, policy_version 58650 (0.0009) -[2023-10-10 23:07:40,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 119799808. Throughput: 0: 1706.1, 1: 1680.4. Samples: 29957608. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:07:40,557][97672] Avg episode reward: [(0, '-1.040'), (1, '22.640')] -[2023-10-10 23:07:41,038][98560] Updated weights for policy 1, policy_version 58342 (0.0008) -[2023-10-10 23:07:41,193][98559] Updated weights for policy 0, policy_version 58660 (0.0008) -[2023-10-10 23:07:41,407][98560] Updated weights for policy 1, policy_version 58352 (0.0009) -[2023-10-10 23:07:41,567][98559] Updated weights for policy 0, policy_version 58670 (0.0007) -[2023-10-10 23:07:41,771][98560] Updated weights for policy 1, policy_version 58362 (0.0008) -[2023-10-10 23:07:41,925][98559] Updated weights for policy 0, policy_version 58680 (0.0008) -[2023-10-10 23:07:45,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 119865344. Throughput: 0: 1723.1, 1: 1696.0. Samples: 29978516. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:07:45,557][97672] Avg episode reward: [(0, '-1.040'), (1, '22.680')] -[2023-10-10 23:07:45,618][98560] Updated weights for policy 1, policy_version 58372 (0.0010) -[2023-10-10 23:07:45,956][98559] Updated weights for policy 0, policy_version 58690 (0.0007) -[2023-10-10 23:07:45,982][98560] Updated weights for policy 1, policy_version 58382 (0.0007) -[2023-10-10 23:07:46,346][98560] Updated weights for policy 1, policy_version 58392 (0.0007) -[2023-10-10 23:07:46,349][98559] Updated weights for policy 0, policy_version 58700 (0.0008) -[2023-10-10 23:07:46,720][98559] Updated weights for policy 0, policy_version 58710 (0.0009) -[2023-10-10 23:07:47,095][98559] Updated weights for policy 0, policy_version 58720 (0.0008) -[2023-10-10 23:07:50,480][98560] Updated weights for policy 1, policy_version 58402 (0.0010) -[2023-10-10 23:07:50,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 119930880. Throughput: 0: 1718.0, 1: 1698.7. Samples: 29999366. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:07:50,556][97672] Avg episode reward: [(0, '-1.040'), (1, '22.680')] -[2023-10-10 23:07:50,848][98560] Updated weights for policy 1, policy_version 58412 (0.0008) -[2023-10-10 23:07:51,111][98559] Updated weights for policy 0, policy_version 58730 (0.0008) -[2023-10-10 23:07:51,211][98560] Updated weights for policy 1, policy_version 58422 (0.0010) -[2023-10-10 23:07:51,471][98559] Updated weights for policy 0, policy_version 58740 (0.0009) -[2023-10-10 23:07:51,579][98560] Updated weights for policy 1, policy_version 58432 (0.0009) -[2023-10-10 23:07:51,842][98559] Updated weights for policy 0, policy_version 58750 (0.0010) -[2023-10-10 23:07:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 119996416. Throughput: 0: 1707.6, 1: 1694.3. Samples: 30008532. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:07:55,556][97672] Avg episode reward: [(0, '-1.040'), (1, '22.680')] -[2023-10-10 23:07:55,702][98560] Updated weights for policy 1, policy_version 58442 (0.0008) -[2023-10-10 23:07:55,756][98559] Updated weights for policy 0, policy_version 58760 (0.0008) -[2023-10-10 23:07:56,064][98560] Updated weights for policy 1, policy_version 58452 (0.0009) -[2023-10-10 23:07:56,129][98559] Updated weights for policy 0, policy_version 58770 (0.0007) -[2023-10-10 23:07:56,444][98560] Updated weights for policy 1, policy_version 58462 (0.0009) -[2023-10-10 23:07:56,496][98559] Updated weights for policy 0, policy_version 58780 (0.0007) -[2023-10-10 23:08:00,455][98559] Updated weights for policy 0, policy_version 58790 (0.0009) -[2023-10-10 23:08:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 120061952. Throughput: 0: 1725.3, 1: 1694.3. Samples: 30029650. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:08:00,556][97672] Avg episode reward: [(0, '-1.040'), (1, '22.560')] -[2023-10-10 23:08:00,614][98560] Updated weights for policy 1, policy_version 58472 (0.0008) -[2023-10-10 23:08:00,824][98559] Updated weights for policy 0, policy_version 58800 (0.0010) -[2023-10-10 23:08:00,984][98560] Updated weights for policy 1, policy_version 58482 (0.0010) -[2023-10-10 23:08:01,195][98559] Updated weights for policy 0, policy_version 58810 (0.0010) -[2023-10-10 23:08:01,353][98560] Updated weights for policy 1, policy_version 58492 (0.0008) -[2023-10-10 23:08:05,205][98559] Updated weights for policy 0, policy_version 58820 (0.0007) -[2023-10-10 23:08:05,446][98560] Updated weights for policy 1, policy_version 58502 (0.0007) -[2023-10-10 23:08:05,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 120127488. Throughput: 0: 1710.8, 1: 1692.7. Samples: 30050300. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:08:05,556][97672] Avg episode reward: [(0, '-1.040'), (1, '22.560')] -[2023-10-10 23:08:05,575][98559] Updated weights for policy 0, policy_version 58830 (0.0007) -[2023-10-10 23:08:05,837][98560] Updated weights for policy 1, policy_version 58512 (0.0007) -[2023-10-10 23:08:05,942][98559] Updated weights for policy 0, policy_version 58840 (0.0008) -[2023-10-10 23:08:06,200][98560] Updated weights for policy 1, policy_version 58522 (0.0007) -[2023-10-10 23:08:09,799][98559] Updated weights for policy 0, policy_version 58850 (0.0009) -[2023-10-10 23:08:10,154][98559] Updated weights for policy 0, policy_version 58860 (0.0008) -[2023-10-10 23:08:10,163][98560] Updated weights for policy 1, policy_version 58532 (0.0009) -[2023-10-10 23:08:10,517][98559] Updated weights for policy 0, policy_version 58870 (0.0008) -[2023-10-10 23:08:10,520][98560] Updated weights for policy 1, policy_version 58542 (0.0007) -[2023-10-10 23:08:10,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 120193024. Throughput: 0: 1717.1, 1: 1689.8. Samples: 30059798. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:08:10,557][97672] Avg episode reward: [(0, '-1.040'), (1, '22.500')] -[2023-10-10 23:08:10,876][98559] Updated weights for policy 0, policy_version 58880 (0.0007) -[2023-10-10 23:08:10,887][98560] Updated weights for policy 1, policy_version 58552 (0.0008) -[2023-10-10 23:08:14,913][98560] Updated weights for policy 1, policy_version 58562 (0.0008) -[2023-10-10 23:08:14,919][98559] Updated weights for policy 0, policy_version 58890 (0.0009) -[2023-10-10 23:08:15,270][98560] Updated weights for policy 1, policy_version 58572 (0.0008) -[2023-10-10 23:08:15,285][98559] Updated weights for policy 0, policy_version 58900 (0.0008) -[2023-10-10 23:08:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 120258560. Throughput: 0: 1710.8, 1: 1697.7. Samples: 30080878. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:08:15,556][97672] Avg episode reward: [(0, '-1.040'), (1, '22.500')] -[2023-10-10 23:08:15,635][98560] Updated weights for policy 1, policy_version 58582 (0.0007) -[2023-10-10 23:08:15,647][98559] Updated weights for policy 0, policy_version 58910 (0.0008) -[2023-10-10 23:08:16,006][98560] Updated weights for policy 1, policy_version 58592 (0.0007) -[2023-10-10 23:08:19,510][98559] Updated weights for policy 0, policy_version 58920 (0.0007) -[2023-10-10 23:08:19,882][98559] Updated weights for policy 0, policy_version 58930 (0.0008) -[2023-10-10 23:08:20,048][98560] Updated weights for policy 1, policy_version 58602 (0.0007) -[2023-10-10 23:08:20,244][98559] Updated weights for policy 0, policy_version 58940 (0.0008) -[2023-10-10 23:08:20,414][98560] Updated weights for policy 1, policy_version 58612 (0.0008) -[2023-10-10 23:08:20,556][97672] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 120356864. Throughput: 0: 1687.7, 1: 1693.8. Samples: 30100526. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:08:20,557][97672] Avg episode reward: [(0, '-1.040'), (1, '22.480')] -[2023-10-10 23:08:20,781][98560] Updated weights for policy 1, policy_version 58622 (0.0008) -[2023-10-10 23:08:24,308][98559] Updated weights for policy 0, policy_version 58950 (0.0009) -[2023-10-10 23:08:24,674][98559] Updated weights for policy 0, policy_version 58960 (0.0009) -[2023-10-10 23:08:25,004][98560] Updated weights for policy 1, policy_version 58632 (0.0008) -[2023-10-10 23:08:25,047][98559] Updated weights for policy 0, policy_version 58970 (0.0008) -[2023-10-10 23:08:25,361][98560] Updated weights for policy 1, policy_version 58642 (0.0008) -[2023-10-10 23:08:25,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 120422400. Throughput: 0: 1717.6, 1: 1689.5. Samples: 30110928. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:08:25,557][97672] Avg episode reward: [(0, '-1.040'), (1, '22.460')] -[2023-10-10 23:08:25,739][98560] Updated weights for policy 1, policy_version 58652 (0.0009) -[2023-10-10 23:08:29,156][98559] Updated weights for policy 0, policy_version 58980 (0.0009) -[2023-10-10 23:08:29,511][98559] Updated weights for policy 0, policy_version 58990 (0.0008) -[2023-10-10 23:08:29,807][98560] Updated weights for policy 1, policy_version 58662 (0.0011) -[2023-10-10 23:08:29,881][98559] Updated weights for policy 0, policy_version 59000 (0.0009) -[2023-10-10 23:08:30,172][98560] Updated weights for policy 1, policy_version 58672 (0.0009) -[2023-10-10 23:08:30,541][98560] Updated weights for policy 1, policy_version 58682 (0.0009) -[2023-10-10 23:08:30,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 120487936. Throughput: 0: 1709.2, 1: 1685.4. Samples: 30131272. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:08:30,556][97672] Avg episode reward: [(0, '-1.080'), (1, '22.460')] -[2023-10-10 23:08:33,924][98559] Updated weights for policy 0, policy_version 59010 (0.0007) -[2023-10-10 23:08:34,334][98559] Updated weights for policy 0, policy_version 59020 (0.0011) -[2023-10-10 23:08:34,480][98560] Updated weights for policy 1, policy_version 58692 (0.0009) -[2023-10-10 23:08:34,701][98559] Updated weights for policy 0, policy_version 59030 (0.0009) -[2023-10-10 23:08:34,846][98560] Updated weights for policy 1, policy_version 58702 (0.0009) -[2023-10-10 23:08:35,064][98559] Updated weights for policy 0, policy_version 59040 (0.0008) -[2023-10-10 23:08:35,227][98560] Updated weights for policy 1, policy_version 58712 (0.0008) -[2023-10-10 23:08:35,556][97672] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 120586240. Throughput: 0: 1690.2, 1: 1676.3. Samples: 30150858. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:08:35,557][97672] Avg episode reward: [(0, '-1.080'), (1, '22.500')] -[2023-10-10 23:08:35,566][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000058720_60129280.pth... -[2023-10-10 23:08:35,567][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000059040_60456960.pth... -[2023-10-10 23:08:35,596][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000057120_58490880.pth -[2023-10-10 23:08:35,599][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000057440_58818560.pth -[2023-10-10 23:08:39,001][98559] Updated weights for policy 0, policy_version 59050 (0.0011) -[2023-10-10 23:08:39,363][98559] Updated weights for policy 0, policy_version 59060 (0.0010) -[2023-10-10 23:08:39,383][98560] Updated weights for policy 1, policy_version 58722 (0.0009) -[2023-10-10 23:08:39,725][98559] Updated weights for policy 0, policy_version 59070 (0.0009) -[2023-10-10 23:08:39,755][98560] Updated weights for policy 1, policy_version 58732 (0.0007) -[2023-10-10 23:08:40,118][98560] Updated weights for policy 1, policy_version 58742 (0.0007) -[2023-10-10 23:08:40,483][98560] Updated weights for policy 1, policy_version 58752 (0.0008) -[2023-10-10 23:08:40,556][97672] Fps is (10 sec: 16383.4, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 120651776. Throughput: 0: 1723.3, 1: 1685.1. Samples: 30161910. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:08:40,558][97672] Avg episode reward: [(0, '-1.080'), (1, '22.400')] -[2023-10-10 23:08:43,874][98559] Updated weights for policy 0, policy_version 59080 (0.0008) -[2023-10-10 23:08:44,241][98559] Updated weights for policy 0, policy_version 59090 (0.0008) -[2023-10-10 23:08:44,335][98560] Updated weights for policy 1, policy_version 58762 (0.0007) -[2023-10-10 23:08:44,595][98559] Updated weights for policy 0, policy_version 59100 (0.0010) -[2023-10-10 23:08:44,708][98560] Updated weights for policy 1, policy_version 58772 (0.0007) -[2023-10-10 23:08:45,070][98560] Updated weights for policy 1, policy_version 58782 (0.0008) -[2023-10-10 23:08:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 120717312. Throughput: 0: 1692.9, 1: 1693.5. Samples: 30182038. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:08:45,557][97672] Avg episode reward: [(0, '-1.080'), (1, '22.440')] -[2023-10-10 23:08:48,507][98559] Updated weights for policy 0, policy_version 59110 (0.0009) -[2023-10-10 23:08:48,866][98559] Updated weights for policy 0, policy_version 59120 (0.0008) -[2023-10-10 23:08:49,066][98560] Updated weights for policy 1, policy_version 58792 (0.0007) -[2023-10-10 23:08:49,234][98559] Updated weights for policy 0, policy_version 59130 (0.0008) -[2023-10-10 23:08:49,423][98560] Updated weights for policy 1, policy_version 58802 (0.0007) -[2023-10-10 23:08:49,789][98560] Updated weights for policy 1, policy_version 58812 (0.0011) -[2023-10-10 23:08:50,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 120782848. Throughput: 0: 1691.8, 1: 1672.9. Samples: 30201714. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-10-10 23:08:50,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.460')] -[2023-10-10 23:08:53,219][98559] Updated weights for policy 0, policy_version 59140 (0.0009) -[2023-10-10 23:08:53,598][98559] Updated weights for policy 0, policy_version 59150 (0.0010) -[2023-10-10 23:08:53,822][98560] Updated weights for policy 1, policy_version 58822 (0.0009) -[2023-10-10 23:08:53,966][98559] Updated weights for policy 0, policy_version 59160 (0.0008) -[2023-10-10 23:08:54,200][98560] Updated weights for policy 1, policy_version 58832 (0.0009) -[2023-10-10 23:08:54,572][98560] Updated weights for policy 1, policy_version 58842 (0.0010) -[2023-10-10 23:08:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 120848384. Throughput: 0: 1705.0, 1: 1701.2. Samples: 30213078. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-10-10 23:08:55,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.500')] -[2023-10-10 23:08:57,942][98559] Updated weights for policy 0, policy_version 59170 (0.0010) -[2023-10-10 23:08:58,301][98559] Updated weights for policy 0, policy_version 59180 (0.0008) -[2023-10-10 23:08:58,630][98560] Updated weights for policy 1, policy_version 58852 (0.0007) -[2023-10-10 23:08:58,662][98559] Updated weights for policy 0, policy_version 59190 (0.0007) -[2023-10-10 23:08:58,997][98560] Updated weights for policy 1, policy_version 58862 (0.0007) -[2023-10-10 23:08:59,029][98559] Updated weights for policy 0, policy_version 59200 (0.0007) -[2023-10-10 23:08:59,363][98560] Updated weights for policy 1, policy_version 58872 (0.0008) -[2023-10-10 23:09:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 120913920. Throughput: 0: 1680.5, 1: 1691.6. Samples: 30232622. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-10-10 23:09:00,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.500')] -[2023-10-10 23:09:02,984][98559] Updated weights for policy 0, policy_version 59210 (0.0008) -[2023-10-10 23:09:03,350][98559] Updated weights for policy 0, policy_version 59220 (0.0008) -[2023-10-10 23:09:03,357][98560] Updated weights for policy 1, policy_version 58882 (0.0010) -[2023-10-10 23:09:03,715][98559] Updated weights for policy 0, policy_version 59230 (0.0007) -[2023-10-10 23:09:03,732][98560] Updated weights for policy 1, policy_version 58892 (0.0009) -[2023-10-10 23:09:04,100][98560] Updated weights for policy 1, policy_version 58902 (0.0008) -[2023-10-10 23:09:04,460][98560] Updated weights for policy 1, policy_version 58912 (0.0009) -[2023-10-10 23:09:05,556][97672] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 120979456. Throughput: 0: 1709.4, 1: 1669.4. Samples: 30252572. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-10-10 23:09:05,556][97672] Avg episode reward: [(0, '-0.980'), (1, '22.460')] -[2023-10-10 23:09:07,761][98559] Updated weights for policy 0, policy_version 59240 (0.0008) -[2023-10-10 23:09:08,123][98559] Updated weights for policy 0, policy_version 59250 (0.0008) -[2023-10-10 23:09:08,492][98559] Updated weights for policy 0, policy_version 59260 (0.0007) -[2023-10-10 23:09:08,537][98560] Updated weights for policy 1, policy_version 58922 (0.0008) -[2023-10-10 23:09:08,899][98560] Updated weights for policy 1, policy_version 58932 (0.0008) -[2023-10-10 23:09:09,270][98560] Updated weights for policy 1, policy_version 58942 (0.0008) -[2023-10-10 23:09:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 121044992. Throughput: 0: 1685.4, 1: 1701.6. Samples: 30263342. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-10-10 23:09:10,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.440')] -[2023-10-10 23:09:12,332][98559] Updated weights for policy 0, policy_version 59270 (0.0008) -[2023-10-10 23:09:12,696][98559] Updated weights for policy 0, policy_version 59280 (0.0008) -[2023-10-10 23:09:13,056][98559] Updated weights for policy 0, policy_version 59290 (0.0008) -[2023-10-10 23:09:13,231][98560] Updated weights for policy 1, policy_version 58952 (0.0007) -[2023-10-10 23:09:13,593][98560] Updated weights for policy 1, policy_version 58962 (0.0009) -[2023-10-10 23:09:13,967][98560] Updated weights for policy 1, policy_version 58972 (0.0008) -[2023-10-10 23:09:15,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 121110528. Throughput: 0: 1694.8, 1: 1689.9. Samples: 30283586. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-10-10 23:09:15,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.400')] -[2023-10-10 23:09:17,118][98559] Updated weights for policy 0, policy_version 59300 (0.0008) -[2023-10-10 23:09:17,484][98559] Updated weights for policy 0, policy_version 59310 (0.0008) -[2023-10-10 23:09:17,851][98559] Updated weights for policy 0, policy_version 59320 (0.0008) -[2023-10-10 23:09:17,933][98560] Updated weights for policy 1, policy_version 58982 (0.0007) -[2023-10-10 23:09:18,297][98560] Updated weights for policy 1, policy_version 58992 (0.0009) -[2023-10-10 23:09:18,668][98560] Updated weights for policy 1, policy_version 59002 (0.0011) -[2023-10-10 23:09:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 121176064. Throughput: 0: 1717.0, 1: 1689.3. Samples: 30304142. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-10-10 23:09:20,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.340')] -[2023-10-10 23:09:21,891][98559] Updated weights for policy 0, policy_version 59330 (0.0010) -[2023-10-10 23:09:22,255][98559] Updated weights for policy 0, policy_version 59340 (0.0009) -[2023-10-10 23:09:22,619][98559] Updated weights for policy 0, policy_version 59350 (0.0010) -[2023-10-10 23:09:22,755][98560] Updated weights for policy 1, policy_version 59012 (0.0010) -[2023-10-10 23:09:22,981][98559] Updated weights for policy 0, policy_version 59360 (0.0009) -[2023-10-10 23:09:23,125][98560] Updated weights for policy 1, policy_version 59022 (0.0008) -[2023-10-10 23:09:23,489][98560] Updated weights for policy 1, policy_version 59032 (0.0009) -[2023-10-10 23:09:25,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 121241600. Throughput: 0: 1681.0, 1: 1708.3. Samples: 30314428. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-10-10 23:09:25,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.280')] -[2023-10-10 23:09:27,137][98559] Updated weights for policy 0, policy_version 59370 (0.0007) -[2023-10-10 23:09:27,500][98559] Updated weights for policy 0, policy_version 59380 (0.0008) -[2023-10-10 23:09:27,591][98560] Updated weights for policy 1, policy_version 59042 (0.0008) -[2023-10-10 23:09:27,874][98559] Updated weights for policy 0, policy_version 59390 (0.0008) -[2023-10-10 23:09:27,961][98560] Updated weights for policy 1, policy_version 59052 (0.0008) -[2023-10-10 23:09:28,318][98560] Updated weights for policy 1, policy_version 59062 (0.0010) -[2023-10-10 23:09:28,685][98560] Updated weights for policy 1, policy_version 59072 (0.0010) -[2023-10-10 23:09:30,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.2, 300 sec: 13662.6). Total num frames: 121307136. Throughput: 0: 1701.2, 1: 1675.7. Samples: 30333998. Policy #0 lag: (min: 29.0, avg: 34.3, max: 61.0) -[2023-10-10 23:09:30,558][97672] Avg episode reward: [(0, '-0.980'), (1, '22.320')] -[2023-10-10 23:09:31,892][98559] Updated weights for policy 0, policy_version 59400 (0.0009) -[2023-10-10 23:09:32,253][98559] Updated weights for policy 0, policy_version 59410 (0.0010) -[2023-10-10 23:09:32,617][98559] Updated weights for policy 0, policy_version 59420 (0.0008) -[2023-10-10 23:09:32,746][98560] Updated weights for policy 1, policy_version 59082 (0.0007) -[2023-10-10 23:09:33,115][98560] Updated weights for policy 1, policy_version 59092 (0.0010) -[2023-10-10 23:09:33,478][98560] Updated weights for policy 1, policy_version 59102 (0.0007) -[2023-10-10 23:09:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 121372672. Throughput: 0: 1709.8, 1: 1691.1. Samples: 30354752. Policy #0 lag: (min: 29.0, avg: 34.3, max: 61.0) -[2023-10-10 23:09:35,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.300')] -[2023-10-10 23:09:36,545][98559] Updated weights for policy 0, policy_version 59430 (0.0009) -[2023-10-10 23:09:36,916][98559] Updated weights for policy 0, policy_version 59440 (0.0011) -[2023-10-10 23:09:37,277][98559] Updated weights for policy 0, policy_version 59450 (0.0008) -[2023-10-10 23:09:37,365][98560] Updated weights for policy 1, policy_version 59112 (0.0008) -[2023-10-10 23:09:37,736][98560] Updated weights for policy 1, policy_version 59122 (0.0008) -[2023-10-10 23:09:38,110][98560] Updated weights for policy 1, policy_version 59132 (0.0008) -[2023-10-10 23:09:40,556][97672] Fps is (10 sec: 13107.7, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 121438208. Throughput: 0: 1688.6, 1: 1681.6. Samples: 30364734. Policy #0 lag: (min: 29.0, avg: 34.3, max: 61.0) -[2023-10-10 23:09:40,556][97672] Avg episode reward: [(0, '-0.980'), (1, '22.320')] -[2023-10-10 23:09:41,339][98559] Updated weights for policy 0, policy_version 59460 (0.0008) -[2023-10-10 23:09:41,706][98559] Updated weights for policy 0, policy_version 59470 (0.0008) -[2023-10-10 23:09:42,069][98559] Updated weights for policy 0, policy_version 59480 (0.0009) -[2023-10-10 23:09:42,165][98560] Updated weights for policy 1, policy_version 59142 (0.0008) -[2023-10-10 23:09:42,542][98560] Updated weights for policy 1, policy_version 59152 (0.0008) -[2023-10-10 23:09:42,920][98560] Updated weights for policy 1, policy_version 59162 (0.0009) -[2023-10-10 23:09:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 121503744. Throughput: 0: 1712.2, 1: 1673.6. Samples: 30384980. Policy #0 lag: (min: 29.0, avg: 34.3, max: 61.0) -[2023-10-10 23:09:45,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.220')] -[2023-10-10 23:09:46,056][98559] Updated weights for policy 0, policy_version 59490 (0.0010) -[2023-10-10 23:09:46,413][98559] Updated weights for policy 0, policy_version 59500 (0.0008) -[2023-10-10 23:09:46,783][98559] Updated weights for policy 0, policy_version 59510 (0.0008) -[2023-10-10 23:09:47,065][98560] Updated weights for policy 1, policy_version 59172 (0.0010) -[2023-10-10 23:09:47,139][98559] Updated weights for policy 0, policy_version 59520 (0.0008) -[2023-10-10 23:09:47,437][98560] Updated weights for policy 1, policy_version 59182 (0.0008) -[2023-10-10 23:09:47,803][98560] Updated weights for policy 1, policy_version 59192 (0.0009) -[2023-10-10 23:09:50,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 121569280. Throughput: 0: 1705.5, 1: 1700.3. Samples: 30405836. Policy #0 lag: (min: 29.0, avg: 34.3, max: 61.0) -[2023-10-10 23:09:50,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.280')] -[2023-10-10 23:09:51,236][98559] Updated weights for policy 0, policy_version 59530 (0.0007) -[2023-10-10 23:09:51,597][98559] Updated weights for policy 0, policy_version 59540 (0.0008) -[2023-10-10 23:09:51,791][98560] Updated weights for policy 1, policy_version 59202 (0.0009) -[2023-10-10 23:09:51,957][98559] Updated weights for policy 0, policy_version 59550 (0.0007) -[2023-10-10 23:09:52,165][98560] Updated weights for policy 1, policy_version 59212 (0.0007) -[2023-10-10 23:09:52,538][98560] Updated weights for policy 1, policy_version 59222 (0.0007) -[2023-10-10 23:09:52,897][98560] Updated weights for policy 1, policy_version 59232 (0.0009) -[2023-10-10 23:09:55,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 121634816. Throughput: 0: 1699.8, 1: 1679.3. Samples: 30415400. Policy #0 lag: (min: 29.0, avg: 34.3, max: 61.0) -[2023-10-10 23:09:55,556][97672] Avg episode reward: [(0, '-0.980'), (1, '22.320')] -[2023-10-10 23:09:56,042][98559] Updated weights for policy 0, policy_version 59560 (0.0009) -[2023-10-10 23:09:56,406][98559] Updated weights for policy 0, policy_version 59570 (0.0009) -[2023-10-10 23:09:56,770][98559] Updated weights for policy 0, policy_version 59580 (0.0008) -[2023-10-10 23:09:56,898][98560] Updated weights for policy 1, policy_version 59242 (0.0007) -[2023-10-10 23:09:57,273][98560] Updated weights for policy 1, policy_version 59252 (0.0009) -[2023-10-10 23:09:57,649][98560] Updated weights for policy 1, policy_version 59262 (0.0008) -[2023-10-10 23:10:00,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 121700352. Throughput: 0: 1699.4, 1: 1693.8. Samples: 30436282. Policy #0 lag: (min: 29.0, avg: 34.3, max: 61.0) -[2023-10-10 23:10:00,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.400')] -[2023-10-10 23:10:00,758][98559] Updated weights for policy 0, policy_version 59590 (0.0009) -[2023-10-10 23:10:01,124][98559] Updated weights for policy 0, policy_version 59600 (0.0009) -[2023-10-10 23:10:01,491][98559] Updated weights for policy 0, policy_version 59610 (0.0008) -[2023-10-10 23:10:01,549][98560] Updated weights for policy 1, policy_version 59272 (0.0008) -[2023-10-10 23:10:01,918][98560] Updated weights for policy 1, policy_version 59282 (0.0008) -[2023-10-10 23:10:02,280][98560] Updated weights for policy 1, policy_version 59292 (0.0009) -[2023-10-10 23:10:05,441][98559] Updated weights for policy 0, policy_version 59620 (0.0008) -[2023-10-10 23:10:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 121765888. Throughput: 0: 1702.0, 1: 1705.2. Samples: 30457466. Policy #0 lag: (min: 29.0, avg: 34.3, max: 61.0) -[2023-10-10 23:10:05,556][97672] Avg episode reward: [(0, '-0.980'), (1, '22.440')] -[2023-10-10 23:10:05,807][98559] Updated weights for policy 0, policy_version 59630 (0.0009) -[2023-10-10 23:10:06,169][98559] Updated weights for policy 0, policy_version 59640 (0.0010) -[2023-10-10 23:10:06,383][98560] Updated weights for policy 1, policy_version 59302 (0.0010) -[2023-10-10 23:10:06,750][98560] Updated weights for policy 1, policy_version 59312 (0.0010) -[2023-10-10 23:10:07,113][98560] Updated weights for policy 1, policy_version 59322 (0.0009) -[2023-10-10 23:10:10,087][98559] Updated weights for policy 0, policy_version 59650 (0.0008) -[2023-10-10 23:10:10,483][98559] Updated weights for policy 0, policy_version 59660 (0.0011) -[2023-10-10 23:10:10,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 121831424. Throughput: 0: 1711.0, 1: 1674.8. Samples: 30466792. Policy #0 lag: (min: 14.0, avg: 14.5, max: 28.0) -[2023-10-10 23:10:10,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.520')] -[2023-10-10 23:10:10,858][98559] Updated weights for policy 0, policy_version 59670 (0.0010) -[2023-10-10 23:10:11,163][98560] Updated weights for policy 1, policy_version 59332 (0.0009) -[2023-10-10 23:10:11,216][98559] Updated weights for policy 0, policy_version 59680 (0.0009) -[2023-10-10 23:10:11,524][98560] Updated weights for policy 1, policy_version 59342 (0.0009) -[2023-10-10 23:10:11,886][98560] Updated weights for policy 1, policy_version 59352 (0.0008) -[2023-10-10 23:10:15,168][98559] Updated weights for policy 0, policy_version 59690 (0.0007) -[2023-10-10 23:10:15,527][98559] Updated weights for policy 0, policy_version 59700 (0.0007) -[2023-10-10 23:10:15,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 121896960. Throughput: 0: 1713.2, 1: 1703.1. Samples: 30487732. Policy #0 lag: (min: 14.0, avg: 14.5, max: 28.0) -[2023-10-10 23:10:15,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.560')] -[2023-10-10 23:10:15,791][98560] Updated weights for policy 1, policy_version 59362 (0.0010) -[2023-10-10 23:10:15,894][98559] Updated weights for policy 0, policy_version 59710 (0.0007) -[2023-10-10 23:10:16,168][98560] Updated weights for policy 1, policy_version 59372 (0.0008) -[2023-10-10 23:10:16,538][98560] Updated weights for policy 1, policy_version 59382 (0.0008) -[2023-10-10 23:10:16,912][98560] Updated weights for policy 1, policy_version 59392 (0.0010) -[2023-10-10 23:10:19,867][98559] Updated weights for policy 0, policy_version 59720 (0.0008) -[2023-10-10 23:10:20,235][98559] Updated weights for policy 0, policy_version 59730 (0.0007) -[2023-10-10 23:10:20,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 121962496. Throughput: 0: 1697.5, 1: 1710.5. Samples: 30508112. Policy #0 lag: (min: 14.0, avg: 14.5, max: 28.0) -[2023-10-10 23:10:20,557][97672] Avg episode reward: [(0, '-1.020'), (1, '22.620')] -[2023-10-10 23:10:20,603][98559] Updated weights for policy 0, policy_version 59740 (0.0007) -[2023-10-10 23:10:20,901][98560] Updated weights for policy 1, policy_version 59402 (0.0008) -[2023-10-10 23:10:21,276][98560] Updated weights for policy 1, policy_version 59412 (0.0008) -[2023-10-10 23:10:21,644][98560] Updated weights for policy 1, policy_version 59422 (0.0009) -[2023-10-10 23:10:24,605][98559] Updated weights for policy 0, policy_version 59750 (0.0009) -[2023-10-10 23:10:24,972][98559] Updated weights for policy 0, policy_version 59760 (0.0007) -[2023-10-10 23:10:25,337][98559] Updated weights for policy 0, policy_version 59770 (0.0008) -[2023-10-10 23:10:25,556][97672] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 122060800. Throughput: 0: 1718.8, 1: 1693.3. Samples: 30518282. Policy #0 lag: (min: 14.0, avg: 14.5, max: 28.0) -[2023-10-10 23:10:25,557][97672] Avg episode reward: [(0, '-1.020'), (1, '22.580')] -[2023-10-10 23:10:25,724][98560] Updated weights for policy 1, policy_version 59432 (0.0008) -[2023-10-10 23:10:26,091][98560] Updated weights for policy 1, policy_version 59442 (0.0009) -[2023-10-10 23:10:26,460][98560] Updated weights for policy 1, policy_version 59452 (0.0010) -[2023-10-10 23:10:29,236][98559] Updated weights for policy 0, policy_version 59780 (0.0009) -[2023-10-10 23:10:29,607][98559] Updated weights for policy 0, policy_version 59790 (0.0008) -[2023-10-10 23:10:29,977][98559] Updated weights for policy 0, policy_version 59800 (0.0009) -[2023-10-10 23:10:30,466][98560] Updated weights for policy 1, policy_version 59462 (0.0010) -[2023-10-10 23:10:30,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 122126336. Throughput: 0: 1715.1, 1: 1704.0. Samples: 30538838. Policy #0 lag: (min: 14.0, avg: 14.5, max: 28.0) -[2023-10-10 23:10:30,556][97672] Avg episode reward: [(0, '-0.980'), (1, '22.640')] -[2023-10-10 23:10:30,834][98560] Updated weights for policy 1, policy_version 59472 (0.0008) -[2023-10-10 23:10:31,199][98560] Updated weights for policy 1, policy_version 59482 (0.0008) -[2023-10-10 23:10:33,931][98559] Updated weights for policy 0, policy_version 59810 (0.0008) -[2023-10-10 23:10:34,291][98559] Updated weights for policy 0, policy_version 59820 (0.0009) -[2023-10-10 23:10:34,650][98559] Updated weights for policy 0, policy_version 59830 (0.0009) -[2023-10-10 23:10:35,020][98559] Updated weights for policy 0, policy_version 59840 (0.0009) -[2023-10-10 23:10:35,237][98560] Updated weights for policy 1, policy_version 59492 (0.0009) -[2023-10-10 23:10:35,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 122191872. Throughput: 0: 1698.5, 1: 1707.4. Samples: 30559104. Policy #0 lag: (min: 14.0, avg: 14.5, max: 28.0) -[2023-10-10 23:10:35,556][97672] Avg episode reward: [(0, '-0.980'), (1, '22.720')] -[2023-10-10 23:10:35,564][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000059840_61276160.pth... -[2023-10-10 23:10:35,599][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000058240_59637760.pth -[2023-10-10 23:10:35,638][98560] Updated weights for policy 1, policy_version 59502 (0.0009) -[2023-10-10 23:10:36,017][98560] Updated weights for policy 1, policy_version 59512 (0.0010) -[2023-10-10 23:10:36,309][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000059520_60948480.pth... -[2023-10-10 23:10:36,349][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000057920_59310080.pth -[2023-10-10 23:10:39,130][98559] Updated weights for policy 0, policy_version 59850 (0.0009) -[2023-10-10 23:10:39,483][98559] Updated weights for policy 0, policy_version 59860 (0.0012) -[2023-10-10 23:10:39,851][98559] Updated weights for policy 0, policy_version 59870 (0.0010) -[2023-10-10 23:10:40,061][98560] Updated weights for policy 1, policy_version 59522 (0.0007) -[2023-10-10 23:10:40,420][98560] Updated weights for policy 1, policy_version 59532 (0.0009) -[2023-10-10 23:10:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 122257408. Throughput: 0: 1729.1, 1: 1698.4. Samples: 30569634. Policy #0 lag: (min: 14.0, avg: 14.5, max: 28.0) -[2023-10-10 23:10:40,556][97672] Avg episode reward: [(0, '-0.980'), (1, '22.720')] -[2023-10-10 23:10:40,791][98560] Updated weights for policy 1, policy_version 59542 (0.0009) -[2023-10-10 23:10:41,156][98560] Updated weights for policy 1, policy_version 59552 (0.0009) -[2023-10-10 23:10:43,782][98559] Updated weights for policy 0, policy_version 59880 (0.0009) -[2023-10-10 23:10:44,148][98559] Updated weights for policy 0, policy_version 59890 (0.0007) -[2023-10-10 23:10:44,510][98559] Updated weights for policy 0, policy_version 59900 (0.0010) -[2023-10-10 23:10:45,299][98560] Updated weights for policy 1, policy_version 59562 (0.0011) -[2023-10-10 23:10:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 122322944. Throughput: 0: 1710.8, 1: 1700.6. Samples: 30589796. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-10 23:10:45,556][97672] Avg episode reward: [(0, '-0.980'), (1, '22.660')] -[2023-10-10 23:10:45,665][98560] Updated weights for policy 1, policy_version 59572 (0.0008) -[2023-10-10 23:10:46,023][98560] Updated weights for policy 1, policy_version 59582 (0.0010) -[2023-10-10 23:10:48,466][98559] Updated weights for policy 0, policy_version 59910 (0.0009) -[2023-10-10 23:10:48,838][98559] Updated weights for policy 0, policy_version 59920 (0.0009) -[2023-10-10 23:10:49,205][98559] Updated weights for policy 0, policy_version 59930 (0.0009) -[2023-10-10 23:10:49,829][98560] Updated weights for policy 1, policy_version 59592 (0.0010) -[2023-10-10 23:10:50,193][98560] Updated weights for policy 1, policy_version 59602 (0.0007) -[2023-10-10 23:10:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 122388480. Throughput: 0: 1707.3, 1: 1698.7. Samples: 30610734. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-10 23:10:50,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.640')] -[2023-10-10 23:10:50,568][98560] Updated weights for policy 1, policy_version 59612 (0.0007) -[2023-10-10 23:10:53,054][98559] Updated weights for policy 0, policy_version 59940 (0.0008) -[2023-10-10 23:10:53,429][98559] Updated weights for policy 0, policy_version 59950 (0.0008) -[2023-10-10 23:10:53,799][98559] Updated weights for policy 0, policy_version 59960 (0.0009) -[2023-10-10 23:10:54,653][98560] Updated weights for policy 1, policy_version 59622 (0.0007) -[2023-10-10 23:10:55,028][98560] Updated weights for policy 1, policy_version 59632 (0.0008) -[2023-10-10 23:10:55,393][98560] Updated weights for policy 1, policy_version 59642 (0.0007) -[2023-10-10 23:10:55,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 122454016. Throughput: 0: 1723.7, 1: 1702.8. Samples: 30620980. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-10 23:10:55,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.580')] -[2023-10-10 23:10:57,759][98559] Updated weights for policy 0, policy_version 59970 (0.0007) -[2023-10-10 23:10:58,146][98559] Updated weights for policy 0, policy_version 59980 (0.0009) -[2023-10-10 23:10:58,511][98559] Updated weights for policy 0, policy_version 59990 (0.0011) -[2023-10-10 23:10:58,873][98559] Updated weights for policy 0, policy_version 60000 (0.0010) -[2023-10-10 23:10:59,246][98560] Updated weights for policy 1, policy_version 59652 (0.0008) -[2023-10-10 23:10:59,606][98560] Updated weights for policy 1, policy_version 59662 (0.0008) -[2023-10-10 23:10:59,970][98560] Updated weights for policy 1, policy_version 59672 (0.0007) -[2023-10-10 23:11:00,556][97672] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 122552320. Throughput: 0: 1704.5, 1: 1706.4. Samples: 30641220. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-10 23:11:00,557][97672] Avg episode reward: [(0, '-1.020'), (1, '22.580')] -[2023-10-10 23:11:02,666][98559] Updated weights for policy 0, policy_version 60010 (0.0009) -[2023-10-10 23:11:03,028][98559] Updated weights for policy 0, policy_version 60020 (0.0007) -[2023-10-10 23:11:03,395][98559] Updated weights for policy 0, policy_version 60030 (0.0008) -[2023-10-10 23:11:04,001][98560] Updated weights for policy 1, policy_version 59682 (0.0008) -[2023-10-10 23:11:04,368][98560] Updated weights for policy 1, policy_version 59692 (0.0008) -[2023-10-10 23:11:04,733][98560] Updated weights for policy 1, policy_version 59702 (0.0007) -[2023-10-10 23:11:05,107][98560] Updated weights for policy 1, policy_version 59712 (0.0007) -[2023-10-10 23:11:05,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 122617856. Throughput: 0: 1725.3, 1: 1689.9. Samples: 30661796. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-10 23:11:05,556][97672] Avg episode reward: [(0, '-1.040'), (1, '22.600')] -[2023-10-10 23:11:07,482][98559] Updated weights for policy 0, policy_version 60040 (0.0008) -[2023-10-10 23:11:07,854][98559] Updated weights for policy 0, policy_version 60050 (0.0009) -[2023-10-10 23:11:08,219][98559] Updated weights for policy 0, policy_version 60060 (0.0007) -[2023-10-10 23:11:09,098][98560] Updated weights for policy 1, policy_version 59722 (0.0009) -[2023-10-10 23:11:09,475][98560] Updated weights for policy 1, policy_version 59732 (0.0008) -[2023-10-10 23:11:09,833][98560] Updated weights for policy 1, policy_version 59742 (0.0009) -[2023-10-10 23:11:10,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 122683392. Throughput: 0: 1705.5, 1: 1709.2. Samples: 30671942. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-10 23:11:10,556][97672] Avg episode reward: [(0, '-1.040'), (1, '22.580')] -[2023-10-10 23:11:12,069][98559] Updated weights for policy 0, policy_version 60070 (0.0008) -[2023-10-10 23:11:12,424][98559] Updated weights for policy 0, policy_version 60080 (0.0009) -[2023-10-10 23:11:12,796][98559] Updated weights for policy 0, policy_version 60090 (0.0011) -[2023-10-10 23:11:13,807][98560] Updated weights for policy 1, policy_version 59752 (0.0008) -[2023-10-10 23:11:14,172][98560] Updated weights for policy 1, policy_version 59762 (0.0009) -[2023-10-10 23:11:14,540][98560] Updated weights for policy 1, policy_version 59772 (0.0011) -[2023-10-10 23:11:15,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 122748928. Throughput: 0: 1709.5, 1: 1711.1. Samples: 30692764. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-10 23:11:15,557][97672] Avg episode reward: [(0, '-1.040'), (1, '22.540')] -[2023-10-10 23:11:16,828][98559] Updated weights for policy 0, policy_version 60100 (0.0010) -[2023-10-10 23:11:17,189][98559] Updated weights for policy 0, policy_version 60110 (0.0009) -[2023-10-10 23:11:17,558][98559] Updated weights for policy 0, policy_version 60120 (0.0008) -[2023-10-10 23:11:18,509][98560] Updated weights for policy 1, policy_version 59782 (0.0010) -[2023-10-10 23:11:18,882][98560] Updated weights for policy 1, policy_version 59792 (0.0008) -[2023-10-10 23:11:19,256][98560] Updated weights for policy 1, policy_version 59802 (0.0008) -[2023-10-10 23:11:20,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 122814464. Throughput: 0: 1727.3, 1: 1687.1. Samples: 30712752. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-10 23:11:20,557][97672] Avg episode reward: [(0, '-1.040'), (1, '22.560')] -[2023-10-10 23:11:21,546][98559] Updated weights for policy 0, policy_version 60130 (0.0011) -[2023-10-10 23:11:21,906][98559] Updated weights for policy 0, policy_version 60140 (0.0007) -[2023-10-10 23:11:22,274][98559] Updated weights for policy 0, policy_version 60150 (0.0008) -[2023-10-10 23:11:22,639][98559] Updated weights for policy 0, policy_version 60160 (0.0007) -[2023-10-10 23:11:23,401][98560] Updated weights for policy 1, policy_version 59812 (0.0008) -[2023-10-10 23:11:23,805][98560] Updated weights for policy 1, policy_version 59822 (0.0007) -[2023-10-10 23:11:24,174][98560] Updated weights for policy 1, policy_version 59832 (0.0008) -[2023-10-10 23:11:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 122880000. Throughput: 0: 1696.7, 1: 1718.6. Samples: 30723324. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-10 23:11:25,557][97672] Avg episode reward: [(0, '-1.040'), (1, '22.380')] -[2023-10-10 23:11:26,627][98559] Updated weights for policy 0, policy_version 60170 (0.0011) -[2023-10-10 23:11:26,990][98559] Updated weights for policy 0, policy_version 60180 (0.0009) -[2023-10-10 23:11:27,360][98559] Updated weights for policy 0, policy_version 60190 (0.0008) -[2023-10-10 23:11:28,090][98560] Updated weights for policy 1, policy_version 59842 (0.0011) -[2023-10-10 23:11:28,465][98560] Updated weights for policy 1, policy_version 59852 (0.0011) -[2023-10-10 23:11:28,829][98560] Updated weights for policy 1, policy_version 59862 (0.0010) -[2023-10-10 23:11:29,207][98560] Updated weights for policy 1, policy_version 59872 (0.0008) -[2023-10-10 23:11:30,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 122945536. Throughput: 0: 1721.4, 1: 1698.4. Samples: 30743684. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:11:30,557][97672] Avg episode reward: [(0, '-1.040'), (1, '22.420')] -[2023-10-10 23:11:31,388][98559] Updated weights for policy 0, policy_version 60200 (0.0008) -[2023-10-10 23:11:31,744][98559] Updated weights for policy 0, policy_version 60210 (0.0008) -[2023-10-10 23:11:32,113][98559] Updated weights for policy 0, policy_version 60220 (0.0008) -[2023-10-10 23:11:33,221][98560] Updated weights for policy 1, policy_version 59882 (0.0008) -[2023-10-10 23:11:33,582][98560] Updated weights for policy 1, policy_version 59892 (0.0008) -[2023-10-10 23:11:33,949][98560] Updated weights for policy 1, policy_version 59902 (0.0007) -[2023-10-10 23:11:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 123011072. Throughput: 0: 1724.3, 1: 1684.6. Samples: 30764132. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:11:35,557][97672] Avg episode reward: [(0, '-1.040'), (1, '22.420')] -[2023-10-10 23:11:36,120][98559] Updated weights for policy 0, policy_version 60230 (0.0011) -[2023-10-10 23:11:36,496][98559] Updated weights for policy 0, policy_version 60240 (0.0008) -[2023-10-10 23:11:36,858][98559] Updated weights for policy 0, policy_version 60250 (0.0007) -[2023-10-10 23:11:37,867][98560] Updated weights for policy 1, policy_version 59912 (0.0009) -[2023-10-10 23:11:38,236][98560] Updated weights for policy 1, policy_version 59922 (0.0010) -[2023-10-10 23:11:38,602][98560] Updated weights for policy 1, policy_version 59932 (0.0007) -[2023-10-10 23:11:40,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 123076608. Throughput: 0: 1703.4, 1: 1711.7. Samples: 30774662. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:11:40,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.400')] -[2023-10-10 23:11:40,743][98559] Updated weights for policy 0, policy_version 60260 (0.0009) -[2023-10-10 23:11:41,113][98559] Updated weights for policy 0, policy_version 60270 (0.0008) -[2023-10-10 23:11:41,478][98559] Updated weights for policy 0, policy_version 60280 (0.0009) -[2023-10-10 23:11:42,876][98560] Updated weights for policy 1, policy_version 59942 (0.0010) -[2023-10-10 23:11:43,243][98560] Updated weights for policy 1, policy_version 59952 (0.0008) -[2023-10-10 23:11:43,609][98560] Updated weights for policy 1, policy_version 59962 (0.0007) -[2023-10-10 23:11:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 123142144. Throughput: 0: 1723.7, 1: 1684.2. Samples: 30794578. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:11:45,557][97672] Avg episode reward: [(0, '-1.240'), (1, '22.420')] -[2023-10-10 23:11:45,649][98559] Updated weights for policy 0, policy_version 60290 (0.0008) -[2023-10-10 23:11:46,041][98559] Updated weights for policy 0, policy_version 60300 (0.0007) -[2023-10-10 23:11:46,399][98559] Updated weights for policy 0, policy_version 60310 (0.0007) -[2023-10-10 23:11:46,758][98559] Updated weights for policy 0, policy_version 60320 (0.0008) -[2023-10-10 23:11:47,580][98560] Updated weights for policy 1, policy_version 59972 (0.0008) -[2023-10-10 23:11:47,942][98560] Updated weights for policy 1, policy_version 59982 (0.0010) -[2023-10-10 23:11:48,303][98560] Updated weights for policy 1, policy_version 59992 (0.0008) -[2023-10-10 23:11:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 123207680. Throughput: 0: 1714.7, 1: 1694.3. Samples: 30815198. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:11:50,557][97672] Avg episode reward: [(0, '-1.240'), (1, '22.400')] -[2023-10-10 23:11:50,907][98559] Updated weights for policy 0, policy_version 60330 (0.0010) -[2023-10-10 23:11:51,283][98559] Updated weights for policy 0, policy_version 60340 (0.0011) -[2023-10-10 23:11:51,649][98559] Updated weights for policy 0, policy_version 60350 (0.0009) -[2023-10-10 23:11:52,214][98560] Updated weights for policy 1, policy_version 60002 (0.0009) -[2023-10-10 23:11:52,595][98560] Updated weights for policy 1, policy_version 60012 (0.0009) -[2023-10-10 23:11:52,958][98560] Updated weights for policy 1, policy_version 60022 (0.0008) -[2023-10-10 23:11:53,335][98560] Updated weights for policy 1, policy_version 60032 (0.0011) -[2023-10-10 23:11:55,464][98559] Updated weights for policy 0, policy_version 60360 (0.0009) -[2023-10-10 23:11:55,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 123273216. Throughput: 0: 1711.3, 1: 1696.2. Samples: 30825280. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:11:55,556][97672] Avg episode reward: [(0, '-1.240'), (1, '22.380')] -[2023-10-10 23:11:55,834][98559] Updated weights for policy 0, policy_version 60370 (0.0008) -[2023-10-10 23:11:56,195][98559] Updated weights for policy 0, policy_version 60380 (0.0010) -[2023-10-10 23:11:57,270][98560] Updated weights for policy 1, policy_version 60042 (0.0010) -[2023-10-10 23:11:57,633][98560] Updated weights for policy 1, policy_version 60052 (0.0008) -[2023-10-10 23:11:58,008][98560] Updated weights for policy 1, policy_version 60062 (0.0008) -[2023-10-10 23:12:00,413][98559] Updated weights for policy 0, policy_version 60390 (0.0010) -[2023-10-10 23:12:00,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 123338752. Throughput: 0: 1713.3, 1: 1686.3. Samples: 30845748. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:12:00,557][97672] Avg episode reward: [(0, '-1.240'), (1, '22.440')] -[2023-10-10 23:12:00,784][98559] Updated weights for policy 0, policy_version 60400 (0.0008) -[2023-10-10 23:12:01,149][98559] Updated weights for policy 0, policy_version 60410 (0.0010) -[2023-10-10 23:12:01,909][98560] Updated weights for policy 1, policy_version 60072 (0.0007) -[2023-10-10 23:12:02,273][98560] Updated weights for policy 1, policy_version 60082 (0.0008) -[2023-10-10 23:12:02,647][98560] Updated weights for policy 1, policy_version 60092 (0.0009) -[2023-10-10 23:12:05,028][98559] Updated weights for policy 0, policy_version 60420 (0.0009) -[2023-10-10 23:12:05,399][98559] Updated weights for policy 0, policy_version 60430 (0.0011) -[2023-10-10 23:12:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 123404288. Throughput: 0: 1706.2, 1: 1709.9. Samples: 30866476. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:12:05,556][97672] Avg episode reward: [(0, '-1.240'), (1, '22.360')] -[2023-10-10 23:12:05,761][98559] Updated weights for policy 0, policy_version 60440 (0.0007) -[2023-10-10 23:12:06,768][98560] Updated weights for policy 1, policy_version 60102 (0.0010) -[2023-10-10 23:12:07,135][98560] Updated weights for policy 1, policy_version 60112 (0.0009) -[2023-10-10 23:12:07,499][98560] Updated weights for policy 1, policy_version 60122 (0.0007) -[2023-10-10 23:12:09,722][98559] Updated weights for policy 0, policy_version 60450 (0.0008) -[2023-10-10 23:12:10,093][98559] Updated weights for policy 0, policy_version 60460 (0.0010) -[2023-10-10 23:12:10,467][98559] Updated weights for policy 0, policy_version 60470 (0.0009) -[2023-10-10 23:12:10,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 123469824. Throughput: 0: 1719.4, 1: 1683.7. Samples: 30876464. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:12:10,557][97672] Avg episode reward: [(0, '-1.240'), (1, '22.500')] -[2023-10-10 23:12:10,832][98559] Updated weights for policy 0, policy_version 60480 (0.0008) -[2023-10-10 23:12:11,385][98560] Updated weights for policy 1, policy_version 60132 (0.0009) -[2023-10-10 23:12:11,764][98560] Updated weights for policy 1, policy_version 60142 (0.0007) -[2023-10-10 23:12:12,124][98560] Updated weights for policy 1, policy_version 60152 (0.0008) -[2023-10-10 23:12:14,808][98559] Updated weights for policy 0, policy_version 60490 (0.0009) -[2023-10-10 23:12:15,163][98559] Updated weights for policy 0, policy_version 60500 (0.0009) -[2023-10-10 23:12:15,538][98559] Updated weights for policy 0, policy_version 60510 (0.0009) -[2023-10-10 23:12:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 123535360. Throughput: 0: 1716.4, 1: 1702.5. Samples: 30897534. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:12:15,556][97672] Avg episode reward: [(0, '-1.240'), (1, '22.500')] -[2023-10-10 23:12:16,074][98560] Updated weights for policy 1, policy_version 60162 (0.0009) -[2023-10-10 23:12:16,491][98560] Updated weights for policy 1, policy_version 60172 (0.0008) -[2023-10-10 23:12:16,852][98560] Updated weights for policy 1, policy_version 60182 (0.0009) -[2023-10-10 23:12:17,214][98560] Updated weights for policy 1, policy_version 60192 (0.0008) -[2023-10-10 23:12:19,505][98559] Updated weights for policy 0, policy_version 60520 (0.0008) -[2023-10-10 23:12:19,871][98559] Updated weights for policy 0, policy_version 60530 (0.0010) -[2023-10-10 23:12:20,242][98559] Updated weights for policy 0, policy_version 60540 (0.0008) -[2023-10-10 23:12:20,556][97672] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 123633664. Throughput: 0: 1690.8, 1: 1713.0. Samples: 30917304. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:12:20,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.460')] -[2023-10-10 23:12:21,111][98560] Updated weights for policy 1, policy_version 60202 (0.0009) -[2023-10-10 23:12:21,484][98560] Updated weights for policy 1, policy_version 60212 (0.0007) -[2023-10-10 23:12:21,861][98560] Updated weights for policy 1, policy_version 60222 (0.0009) -[2023-10-10 23:12:24,210][98559] Updated weights for policy 0, policy_version 60550 (0.0008) -[2023-10-10 23:12:24,572][98559] Updated weights for policy 0, policy_version 60560 (0.0009) -[2023-10-10 23:12:24,942][98559] Updated weights for policy 0, policy_version 60570 (0.0010) -[2023-10-10 23:12:25,556][97672] Fps is (10 sec: 16383.8, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 123699200. Throughput: 0: 1717.8, 1: 1689.1. Samples: 30927972. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:12:25,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.540')] -[2023-10-10 23:12:25,875][98560] Updated weights for policy 1, policy_version 60232 (0.0011) -[2023-10-10 23:12:26,237][98560] Updated weights for policy 1, policy_version 60242 (0.0009) -[2023-10-10 23:12:26,598][98560] Updated weights for policy 1, policy_version 60252 (0.0008) -[2023-10-10 23:12:28,843][98559] Updated weights for policy 0, policy_version 60580 (0.0009) -[2023-10-10 23:12:29,220][98559] Updated weights for policy 0, policy_version 60590 (0.0011) -[2023-10-10 23:12:29,572][98559] Updated weights for policy 0, policy_version 60600 (0.0009) -[2023-10-10 23:12:30,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 123764736. Throughput: 0: 1700.9, 1: 1714.8. Samples: 30948286. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:12:30,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.540')] -[2023-10-10 23:12:30,688][98560] Updated weights for policy 1, policy_version 60262 (0.0008) -[2023-10-10 23:12:31,058][98560] Updated weights for policy 1, policy_version 60272 (0.0009) -[2023-10-10 23:12:31,428][98560] Updated weights for policy 1, policy_version 60282 (0.0007) -[2023-10-10 23:12:33,480][98559] Updated weights for policy 0, policy_version 60610 (0.0008) -[2023-10-10 23:12:33,884][98559] Updated weights for policy 0, policy_version 60620 (0.0007) -[2023-10-10 23:12:34,261][98559] Updated weights for policy 0, policy_version 60630 (0.0008) -[2023-10-10 23:12:34,617][98559] Updated weights for policy 0, policy_version 60640 (0.0009) -[2023-10-10 23:12:35,393][98560] Updated weights for policy 1, policy_version 60292 (0.0008) -[2023-10-10 23:12:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 123830272. Throughput: 0: 1696.6, 1: 1720.7. Samples: 30968976. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:12:35,557][97672] Avg episode reward: [(0, '-1.280'), (1, '22.540')] -[2023-10-10 23:12:35,569][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000060640_62095360.pth... -[2023-10-10 23:12:35,608][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000059040_60456960.pth -[2023-10-10 23:12:35,755][98560] Updated weights for policy 1, policy_version 60302 (0.0007) -[2023-10-10 23:12:36,119][98560] Updated weights for policy 1, policy_version 60312 (0.0011) -[2023-10-10 23:12:36,413][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000060320_61767680.pth... -[2023-10-10 23:12:36,442][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000058720_60129280.pth -[2023-10-10 23:12:38,780][98559] Updated weights for policy 0, policy_version 60650 (0.0007) -[2023-10-10 23:12:39,139][98559] Updated weights for policy 0, policy_version 60660 (0.0007) -[2023-10-10 23:12:39,513][98559] Updated weights for policy 0, policy_version 60670 (0.0009) -[2023-10-10 23:12:40,295][98560] Updated weights for policy 1, policy_version 60322 (0.0011) -[2023-10-10 23:12:40,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 123895808. Throughput: 0: 1728.6, 1: 1696.2. Samples: 30979394. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:12:40,557][97672] Avg episode reward: [(0, '-1.280'), (1, '22.560')] -[2023-10-10 23:12:40,660][98560] Updated weights for policy 1, policy_version 60332 (0.0010) -[2023-10-10 23:12:41,023][98560] Updated weights for policy 1, policy_version 60342 (0.0011) -[2023-10-10 23:12:41,396][98560] Updated weights for policy 1, policy_version 60352 (0.0010) -[2023-10-10 23:12:43,260][98559] Updated weights for policy 0, policy_version 60680 (0.0008) -[2023-10-10 23:12:43,625][98559] Updated weights for policy 0, policy_version 60690 (0.0008) -[2023-10-10 23:12:43,982][98559] Updated weights for policy 0, policy_version 60700 (0.0008) -[2023-10-10 23:12:45,432][98560] Updated weights for policy 1, policy_version 60362 (0.0008) -[2023-10-10 23:12:45,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 123961344. Throughput: 0: 1699.2, 1: 1708.0. Samples: 30999074. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:12:45,556][97672] Avg episode reward: [(0, '-1.280'), (1, '22.580')] -[2023-10-10 23:12:45,810][98560] Updated weights for policy 1, policy_version 60372 (0.0009) -[2023-10-10 23:12:46,178][98560] Updated weights for policy 1, policy_version 60382 (0.0009) -[2023-10-10 23:12:47,929][98559] Updated weights for policy 0, policy_version 60710 (0.0008) -[2023-10-10 23:12:48,295][98559] Updated weights for policy 0, policy_version 60720 (0.0009) -[2023-10-10 23:12:48,652][98559] Updated weights for policy 0, policy_version 60730 (0.0009) -[2023-10-10 23:12:50,080][98560] Updated weights for policy 1, policy_version 60392 (0.0009) -[2023-10-10 23:12:50,457][98560] Updated weights for policy 1, policy_version 60402 (0.0008) -[2023-10-10 23:12:50,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 124026880. Throughput: 0: 1714.8, 1: 1706.2. Samples: 31020420. Policy #0 lag: (min: 21.0, avg: 21.2, max: 29.0) -[2023-10-10 23:12:50,556][97672] Avg episode reward: [(0, '-1.300'), (1, '22.700')] -[2023-10-10 23:12:50,820][98560] Updated weights for policy 1, policy_version 60412 (0.0008) -[2023-10-10 23:12:52,509][98559] Updated weights for policy 0, policy_version 60740 (0.0010) -[2023-10-10 23:12:52,871][98559] Updated weights for policy 0, policy_version 60750 (0.0010) -[2023-10-10 23:12:53,238][98559] Updated weights for policy 0, policy_version 60760 (0.0011) -[2023-10-10 23:12:54,868][98560] Updated weights for policy 1, policy_version 60422 (0.0007) -[2023-10-10 23:12:55,229][98560] Updated weights for policy 1, policy_version 60432 (0.0007) -[2023-10-10 23:12:55,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 124092416. Throughput: 0: 1710.7, 1: 1701.7. Samples: 31030022. Policy #0 lag: (min: 21.0, avg: 21.2, max: 29.0) -[2023-10-10 23:12:55,557][97672] Avg episode reward: [(0, '-1.300'), (1, '22.660')] -[2023-10-10 23:12:55,601][98560] Updated weights for policy 1, policy_version 60442 (0.0007) -[2023-10-10 23:12:57,282][98559] Updated weights for policy 0, policy_version 60770 (0.0009) -[2023-10-10 23:12:57,654][98559] Updated weights for policy 0, policy_version 60780 (0.0009) -[2023-10-10 23:12:58,020][98559] Updated weights for policy 0, policy_version 60790 (0.0010) -[2023-10-10 23:12:58,398][98559] Updated weights for policy 0, policy_version 60800 (0.0010) -[2023-10-10 23:12:59,534][98560] Updated weights for policy 1, policy_version 60452 (0.0009) -[2023-10-10 23:12:59,899][98560] Updated weights for policy 1, policy_version 60462 (0.0010) -[2023-10-10 23:13:00,264][98560] Updated weights for policy 1, policy_version 60472 (0.0008) -[2023-10-10 23:13:00,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 124157952. Throughput: 0: 1699.1, 1: 1705.4. Samples: 31050738. Policy #0 lag: (min: 21.0, avg: 21.2, max: 29.0) -[2023-10-10 23:13:00,557][97672] Avg episode reward: [(0, '-1.300'), (1, '22.640')] -[2023-10-10 23:13:02,423][98559] Updated weights for policy 0, policy_version 60810 (0.0008) -[2023-10-10 23:13:02,779][98559] Updated weights for policy 0, policy_version 60820 (0.0009) -[2023-10-10 23:13:03,148][98559] Updated weights for policy 0, policy_version 60830 (0.0007) -[2023-10-10 23:13:04,369][98560] Updated weights for policy 1, policy_version 60482 (0.0008) -[2023-10-10 23:13:04,758][98560] Updated weights for policy 1, policy_version 60492 (0.0010) -[2023-10-10 23:13:05,132][98560] Updated weights for policy 1, policy_version 60502 (0.0008) -[2023-10-10 23:13:05,496][98560] Updated weights for policy 1, policy_version 60512 (0.0007) -[2023-10-10 23:13:05,556][97672] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 124256256. Throughput: 0: 1730.8, 1: 1697.8. Samples: 31071592. Policy #0 lag: (min: 21.0, avg: 21.2, max: 29.0) -[2023-10-10 23:13:05,557][97672] Avg episode reward: [(0, '-1.300'), (1, '22.720')] -[2023-10-10 23:13:07,026][98559] Updated weights for policy 0, policy_version 60840 (0.0008) -[2023-10-10 23:13:07,393][98559] Updated weights for policy 0, policy_version 60850 (0.0009) -[2023-10-10 23:13:07,770][98559] Updated weights for policy 0, policy_version 60860 (0.0008) -[2023-10-10 23:13:09,492][98560] Updated weights for policy 1, policy_version 60522 (0.0007) -[2023-10-10 23:13:09,850][98560] Updated weights for policy 1, policy_version 60532 (0.0007) -[2023-10-10 23:13:10,221][98560] Updated weights for policy 1, policy_version 60542 (0.0009) -[2023-10-10 23:13:10,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 124321792. Throughput: 0: 1701.8, 1: 1703.1. Samples: 31081194. Policy #0 lag: (min: 21.0, avg: 21.2, max: 29.0) -[2023-10-10 23:13:10,557][97672] Avg episode reward: [(0, '-1.300'), (1, '22.760')] -[2023-10-10 23:13:11,832][98559] Updated weights for policy 0, policy_version 60870 (0.0008) -[2023-10-10 23:13:12,199][98559] Updated weights for policy 0, policy_version 60880 (0.0008) -[2023-10-10 23:13:12,560][98559] Updated weights for policy 0, policy_version 60890 (0.0008) -[2023-10-10 23:13:14,287][98560] Updated weights for policy 1, policy_version 60552 (0.0008) -[2023-10-10 23:13:14,645][98560] Updated weights for policy 1, policy_version 60562 (0.0008) -[2023-10-10 23:13:15,015][98560] Updated weights for policy 1, policy_version 60572 (0.0008) -[2023-10-10 23:13:15,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 124387328. Throughput: 0: 1716.6, 1: 1703.6. Samples: 31102198. Policy #0 lag: (min: 21.0, avg: 21.2, max: 29.0) -[2023-10-10 23:13:15,557][97672] Avg episode reward: [(0, '-1.300'), (1, '22.660')] -[2023-10-10 23:13:16,410][98559] Updated weights for policy 0, policy_version 60900 (0.0010) -[2023-10-10 23:13:16,792][98559] Updated weights for policy 0, policy_version 60910 (0.0009) -[2023-10-10 23:13:17,158][98559] Updated weights for policy 0, policy_version 60920 (0.0009) -[2023-10-10 23:13:18,927][98560] Updated weights for policy 1, policy_version 60582 (0.0009) -[2023-10-10 23:13:19,288][98560] Updated weights for policy 1, policy_version 60592 (0.0007) -[2023-10-10 23:13:19,658][98560] Updated weights for policy 1, policy_version 60602 (0.0008) -[2023-10-10 23:13:20,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 124452864. Throughput: 0: 1735.1, 1: 1681.6. Samples: 31122724. Policy #0 lag: (min: 21.0, avg: 21.2, max: 29.0) -[2023-10-10 23:13:20,557][97672] Avg episode reward: [(0, '-1.300'), (1, '22.620')] -[2023-10-10 23:13:21,081][98559] Updated weights for policy 0, policy_version 60930 (0.0008) -[2023-10-10 23:13:21,454][98559] Updated weights for policy 0, policy_version 60940 (0.0007) -[2023-10-10 23:13:21,819][98559] Updated weights for policy 0, policy_version 60950 (0.0007) -[2023-10-10 23:13:22,183][98559] Updated weights for policy 0, policy_version 60960 (0.0009) -[2023-10-10 23:13:23,455][98560] Updated weights for policy 1, policy_version 60612 (0.0009) -[2023-10-10 23:13:23,823][98560] Updated weights for policy 1, policy_version 60622 (0.0008) -[2023-10-10 23:13:24,189][98560] Updated weights for policy 1, policy_version 60632 (0.0007) -[2023-10-10 23:13:25,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 124518400. Throughput: 0: 1701.4, 1: 1718.0. Samples: 31133270. Policy #0 lag: (min: 21.0, avg: 21.2, max: 29.0) -[2023-10-10 23:13:25,557][97672] Avg episode reward: [(0, '-1.300'), (1, '22.580')] -[2023-10-10 23:13:26,197][98559] Updated weights for policy 0, policy_version 60970 (0.0008) -[2023-10-10 23:13:26,557][98559] Updated weights for policy 0, policy_version 60980 (0.0008) -[2023-10-10 23:13:26,920][98559] Updated weights for policy 0, policy_version 60990 (0.0009) -[2023-10-10 23:13:28,164][98560] Updated weights for policy 1, policy_version 60642 (0.0009) -[2023-10-10 23:13:28,529][98560] Updated weights for policy 1, policy_version 60652 (0.0008) -[2023-10-10 23:13:28,906][98560] Updated weights for policy 1, policy_version 60662 (0.0008) -[2023-10-10 23:13:29,271][98560] Updated weights for policy 1, policy_version 60672 (0.0009) -[2023-10-10 23:13:30,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 124583936. Throughput: 0: 1734.4, 1: 1708.0. Samples: 31153984. Policy #0 lag: (min: 21.0, avg: 21.2, max: 29.0) -[2023-10-10 23:13:30,556][97672] Avg episode reward: [(0, '-1.220'), (1, '22.580')] -[2023-10-10 23:13:30,861][98559] Updated weights for policy 0, policy_version 61000 (0.0008) -[2023-10-10 23:13:31,225][98559] Updated weights for policy 0, policy_version 61010 (0.0009) -[2023-10-10 23:13:31,590][98559] Updated weights for policy 0, policy_version 61020 (0.0011) -[2023-10-10 23:13:33,236][98560] Updated weights for policy 1, policy_version 60682 (0.0007) -[2023-10-10 23:13:33,599][98560] Updated weights for policy 1, policy_version 60692 (0.0009) -[2023-10-10 23:13:33,966][98560] Updated weights for policy 1, policy_version 60702 (0.0008) -[2023-10-10 23:13:35,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 124649472. Throughput: 0: 1732.6, 1: 1691.2. Samples: 31174490. Policy #0 lag: (min: 0.0, avg: 27.6, max: 32.0) -[2023-10-10 23:13:35,556][97672] Avg episode reward: [(0, '-1.220'), (1, '22.540')] -[2023-10-10 23:13:35,570][98559] Updated weights for policy 0, policy_version 61030 (0.0010) -[2023-10-10 23:13:35,939][98559] Updated weights for policy 0, policy_version 61040 (0.0008) -[2023-10-10 23:13:36,301][98559] Updated weights for policy 0, policy_version 61050 (0.0008) -[2023-10-10 23:13:38,015][98560] Updated weights for policy 1, policy_version 60712 (0.0010) -[2023-10-10 23:13:38,383][98560] Updated weights for policy 1, policy_version 60722 (0.0008) -[2023-10-10 23:13:38,745][98560] Updated weights for policy 1, policy_version 60732 (0.0007) -[2023-10-10 23:13:40,353][98559] Updated weights for policy 0, policy_version 61060 (0.0009) -[2023-10-10 23:13:40,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 124715008. Throughput: 0: 1725.5, 1: 1717.9. Samples: 31184974. Policy #0 lag: (min: 0.0, avg: 27.6, max: 32.0) -[2023-10-10 23:13:40,557][97672] Avg episode reward: [(0, '-1.220'), (1, '22.560')] -[2023-10-10 23:13:40,728][98559] Updated weights for policy 0, policy_version 61070 (0.0009) -[2023-10-10 23:13:41,082][98559] Updated weights for policy 0, policy_version 61080 (0.0011) -[2023-10-10 23:13:42,895][98560] Updated weights for policy 1, policy_version 60742 (0.0009) -[2023-10-10 23:13:43,258][98560] Updated weights for policy 1, policy_version 60752 (0.0011) -[2023-10-10 23:13:43,632][98560] Updated weights for policy 1, policy_version 60762 (0.0010) -[2023-10-10 23:13:45,165][98559] Updated weights for policy 0, policy_version 61090 (0.0010) -[2023-10-10 23:13:45,530][98559] Updated weights for policy 0, policy_version 61100 (0.0008) -[2023-10-10 23:13:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 124780544. Throughput: 0: 1734.4, 1: 1693.6. Samples: 31204994. Policy #0 lag: (min: 0.0, avg: 27.6, max: 32.0) -[2023-10-10 23:13:45,556][97672] Avg episode reward: [(0, '-1.220'), (1, '22.600')] -[2023-10-10 23:13:45,904][98559] Updated weights for policy 0, policy_version 61110 (0.0007) -[2023-10-10 23:13:46,275][98559] Updated weights for policy 0, policy_version 61120 (0.0009) -[2023-10-10 23:13:47,650][98560] Updated weights for policy 1, policy_version 60772 (0.0011) -[2023-10-10 23:13:48,015][98560] Updated weights for policy 1, policy_version 60782 (0.0010) -[2023-10-10 23:13:48,380][98560] Updated weights for policy 1, policy_version 60792 (0.0009) -[2023-10-10 23:13:50,369][98559] Updated weights for policy 0, policy_version 61130 (0.0009) -[2023-10-10 23:13:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 124846080. Throughput: 0: 1717.3, 1: 1696.1. Samples: 31225196. Policy #0 lag: (min: 0.0, avg: 27.6, max: 32.0) -[2023-10-10 23:13:50,557][97672] Avg episode reward: [(0, '-1.220'), (1, '22.540')] -[2023-10-10 23:13:50,740][98559] Updated weights for policy 0, policy_version 61140 (0.0009) -[2023-10-10 23:13:51,104][98559] Updated weights for policy 0, policy_version 61150 (0.0008) -[2023-10-10 23:13:52,523][98560] Updated weights for policy 1, policy_version 60802 (0.0009) -[2023-10-10 23:13:52,932][98560] Updated weights for policy 1, policy_version 60812 (0.0009) -[2023-10-10 23:13:53,308][98560] Updated weights for policy 1, policy_version 60822 (0.0009) -[2023-10-10 23:13:53,676][98560] Updated weights for policy 1, policy_version 60832 (0.0007) -[2023-10-10 23:13:55,127][98559] Updated weights for policy 0, policy_version 61160 (0.0009) -[2023-10-10 23:13:55,498][98559] Updated weights for policy 0, policy_version 61170 (0.0008) -[2023-10-10 23:13:55,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 124911616. Throughput: 0: 1727.6, 1: 1708.0. Samples: 31235796. Policy #0 lag: (min: 0.0, avg: 27.6, max: 32.0) -[2023-10-10 23:13:55,556][97672] Avg episode reward: [(0, '-1.220'), (1, '22.540')] -[2023-10-10 23:13:55,865][98559] Updated weights for policy 0, policy_version 61180 (0.0008) -[2023-10-10 23:13:57,642][98560] Updated weights for policy 1, policy_version 60842 (0.0008) -[2023-10-10 23:13:58,015][98560] Updated weights for policy 1, policy_version 60852 (0.0010) -[2023-10-10 23:13:58,381][98560] Updated weights for policy 1, policy_version 60862 (0.0010) -[2023-10-10 23:13:59,748][98559] Updated weights for policy 0, policy_version 61190 (0.0009) -[2023-10-10 23:14:00,112][98559] Updated weights for policy 0, policy_version 61200 (0.0008) -[2023-10-10 23:14:00,477][98559] Updated weights for policy 0, policy_version 61210 (0.0008) -[2023-10-10 23:14:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 124977152. Throughput: 0: 1729.8, 1: 1687.7. Samples: 31255986. Policy #0 lag: (min: 0.0, avg: 27.6, max: 32.0) -[2023-10-10 23:14:00,557][97672] Avg episode reward: [(0, '-1.240'), (1, '22.560')] -[2023-10-10 23:14:02,399][98560] Updated weights for policy 1, policy_version 60872 (0.0009) -[2023-10-10 23:14:02,759][98560] Updated weights for policy 1, policy_version 60882 (0.0008) -[2023-10-10 23:14:03,130][98560] Updated weights for policy 1, policy_version 60892 (0.0009) -[2023-10-10 23:14:04,315][98559] Updated weights for policy 0, policy_version 61220 (0.0009) -[2023-10-10 23:14:04,683][98559] Updated weights for policy 0, policy_version 61230 (0.0011) -[2023-10-10 23:14:05,051][98559] Updated weights for policy 0, policy_version 61240 (0.0010) -[2023-10-10 23:14:05,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 125075456. Throughput: 0: 1699.4, 1: 1705.5. Samples: 31275942. Policy #0 lag: (min: 0.0, avg: 27.6, max: 32.0) -[2023-10-10 23:14:05,556][97672] Avg episode reward: [(0, '-1.240'), (1, '22.600')] -[2023-10-10 23:14:07,119][98560] Updated weights for policy 1, policy_version 60902 (0.0008) -[2023-10-10 23:14:07,489][98560] Updated weights for policy 1, policy_version 60912 (0.0009) -[2023-10-10 23:14:07,855][98560] Updated weights for policy 1, policy_version 60922 (0.0008) -[2023-10-10 23:14:08,890][98559] Updated weights for policy 0, policy_version 61250 (0.0009) -[2023-10-10 23:14:09,301][98559] Updated weights for policy 0, policy_version 61260 (0.0008) -[2023-10-10 23:14:09,668][98559] Updated weights for policy 0, policy_version 61270 (0.0008) -[2023-10-10 23:14:10,037][98559] Updated weights for policy 0, policy_version 61280 (0.0008) -[2023-10-10 23:14:10,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 125140992. Throughput: 0: 1732.2, 1: 1681.7. Samples: 31286896. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:14:10,557][97672] Avg episode reward: [(0, '-1.240'), (1, '22.600')] -[2023-10-10 23:14:12,107][98560] Updated weights for policy 1, policy_version 60932 (0.0008) -[2023-10-10 23:14:12,476][98560] Updated weights for policy 1, policy_version 60942 (0.0007) -[2023-10-10 23:14:12,834][98560] Updated weights for policy 1, policy_version 60952 (0.0009) -[2023-10-10 23:14:13,947][98559] Updated weights for policy 0, policy_version 61290 (0.0010) -[2023-10-10 23:14:14,309][98559] Updated weights for policy 0, policy_version 61300 (0.0011) -[2023-10-10 23:14:14,683][98559] Updated weights for policy 0, policy_version 61310 (0.0008) -[2023-10-10 23:14:15,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 125206528. Throughput: 0: 1703.1, 1: 1682.0. Samples: 31306316. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:14:15,557][97672] Avg episode reward: [(0, '-1.240'), (1, '22.640')] -[2023-10-10 23:14:16,775][98560] Updated weights for policy 1, policy_version 60962 (0.0009) -[2023-10-10 23:14:17,149][98560] Updated weights for policy 1, policy_version 60972 (0.0010) -[2023-10-10 23:14:17,526][98560] Updated weights for policy 1, policy_version 60982 (0.0011) -[2023-10-10 23:14:17,894][98560] Updated weights for policy 1, policy_version 60992 (0.0010) -[2023-10-10 23:14:18,775][98559] Updated weights for policy 0, policy_version 61320 (0.0008) -[2023-10-10 23:14:19,147][98559] Updated weights for policy 0, policy_version 61330 (0.0009) -[2023-10-10 23:14:19,518][98559] Updated weights for policy 0, policy_version 61340 (0.0009) -[2023-10-10 23:14:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 125272064. Throughput: 0: 1684.7, 1: 1700.6. Samples: 31326828. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:14:20,557][97672] Avg episode reward: [(0, '-1.240'), (1, '22.700')] -[2023-10-10 23:14:21,859][98560] Updated weights for policy 1, policy_version 61002 (0.0008) -[2023-10-10 23:14:22,216][98560] Updated weights for policy 1, policy_version 61012 (0.0010) -[2023-10-10 23:14:22,584][98560] Updated weights for policy 1, policy_version 61022 (0.0008) -[2023-10-10 23:14:23,471][98559] Updated weights for policy 0, policy_version 61350 (0.0009) -[2023-10-10 23:14:23,851][98559] Updated weights for policy 0, policy_version 61360 (0.0009) -[2023-10-10 23:14:24,216][98559] Updated weights for policy 0, policy_version 61370 (0.0007) -[2023-10-10 23:14:25,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 125337600. Throughput: 0: 1712.3, 1: 1674.0. Samples: 31337356. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:14:25,557][97672] Avg episode reward: [(0, '-1.240'), (1, '22.640')] -[2023-10-10 23:14:26,505][98560] Updated weights for policy 1, policy_version 61032 (0.0010) -[2023-10-10 23:14:26,868][98560] Updated weights for policy 1, policy_version 61042 (0.0010) -[2023-10-10 23:14:27,232][98560] Updated weights for policy 1, policy_version 61052 (0.0009) -[2023-10-10 23:14:28,153][98559] Updated weights for policy 0, policy_version 61380 (0.0007) -[2023-10-10 23:14:28,522][98559] Updated weights for policy 0, policy_version 61390 (0.0007) -[2023-10-10 23:14:28,891][98559] Updated weights for policy 0, policy_version 61400 (0.0007) -[2023-10-10 23:14:30,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 125403136. Throughput: 0: 1689.1, 1: 1698.0. Samples: 31357412. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:14:30,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.600')] -[2023-10-10 23:14:31,203][98560] Updated weights for policy 1, policy_version 61062 (0.0009) -[2023-10-10 23:14:31,571][98560] Updated weights for policy 1, policy_version 61072 (0.0010) -[2023-10-10 23:14:31,941][98560] Updated weights for policy 1, policy_version 61082 (0.0011) -[2023-10-10 23:14:32,799][98559] Updated weights for policy 0, policy_version 61410 (0.0009) -[2023-10-10 23:14:33,172][98559] Updated weights for policy 0, policy_version 61420 (0.0009) -[2023-10-10 23:14:33,536][98559] Updated weights for policy 0, policy_version 61430 (0.0008) -[2023-10-10 23:14:33,908][98559] Updated weights for policy 0, policy_version 61440 (0.0007) -[2023-10-10 23:14:35,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 125468672. Throughput: 0: 1702.8, 1: 1700.4. Samples: 31378344. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:14:35,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.600')] -[2023-10-10 23:14:35,570][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000061088_62554112.pth... -[2023-10-10 23:14:35,570][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000061440_62914560.pth... -[2023-10-10 23:14:35,607][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000059520_60948480.pth -[2023-10-10 23:14:35,607][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000059840_61276160.pth -[2023-10-10 23:14:36,184][98560] Updated weights for policy 1, policy_version 61092 (0.0011) -[2023-10-10 23:14:36,556][98560] Updated weights for policy 1, policy_version 61102 (0.0010) -[2023-10-10 23:14:36,924][98560] Updated weights for policy 1, policy_version 61112 (0.0010) -[2023-10-10 23:14:37,869][98559] Updated weights for policy 0, policy_version 61450 (0.0007) -[2023-10-10 23:14:38,247][98559] Updated weights for policy 0, policy_version 61460 (0.0008) -[2023-10-10 23:14:38,619][98559] Updated weights for policy 0, policy_version 61470 (0.0008) -[2023-10-10 23:14:40,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 125534208. Throughput: 0: 1706.2, 1: 1677.5. Samples: 31388064. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:14:40,556][97672] Avg episode reward: [(0, '-1.260'), (1, '22.540')] -[2023-10-10 23:14:41,065][98560] Updated weights for policy 1, policy_version 61122 (0.0011) -[2023-10-10 23:14:41,441][98560] Updated weights for policy 1, policy_version 61132 (0.0007) -[2023-10-10 23:14:41,812][98560] Updated weights for policy 1, policy_version 61142 (0.0010) -[2023-10-10 23:14:42,176][98560] Updated weights for policy 1, policy_version 61152 (0.0010) -[2023-10-10 23:14:42,689][98559] Updated weights for policy 0, policy_version 61480 (0.0008) -[2023-10-10 23:14:43,051][98559] Updated weights for policy 0, policy_version 61490 (0.0007) -[2023-10-10 23:14:43,418][98559] Updated weights for policy 0, policy_version 61500 (0.0007) -[2023-10-10 23:14:45,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 125599744. Throughput: 0: 1697.3, 1: 1696.7. Samples: 31408718. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:14:45,557][97672] Avg episode reward: [(0, '-1.400'), (1, '22.580')] -[2023-10-10 23:14:46,503][98560] Updated weights for policy 1, policy_version 61162 (0.0011) -[2023-10-10 23:14:46,871][98560] Updated weights for policy 1, policy_version 61172 (0.0009) -[2023-10-10 23:14:47,239][98560] Updated weights for policy 1, policy_version 61182 (0.0010) -[2023-10-10 23:14:47,455][98559] Updated weights for policy 0, policy_version 61510 (0.0007) -[2023-10-10 23:14:47,826][98559] Updated weights for policy 0, policy_version 61520 (0.0008) -[2023-10-10 23:14:48,190][98559] Updated weights for policy 0, policy_version 61530 (0.0009) -[2023-10-10 23:14:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 125665280. Throughput: 0: 1718.7, 1: 1693.3. Samples: 31429484. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:14:50,557][97672] Avg episode reward: [(0, '-1.400'), (1, '22.560')] -[2023-10-10 23:14:51,267][98560] Updated weights for policy 1, policy_version 61192 (0.0010) -[2023-10-10 23:14:51,636][98560] Updated weights for policy 1, policy_version 61202 (0.0010) -[2023-10-10 23:14:51,996][98560] Updated weights for policy 1, policy_version 61212 (0.0009) -[2023-10-10 23:14:52,101][98559] Updated weights for policy 0, policy_version 61540 (0.0007) -[2023-10-10 23:14:52,472][98559] Updated weights for policy 0, policy_version 61550 (0.0010) -[2023-10-10 23:14:52,837][98559] Updated weights for policy 0, policy_version 61560 (0.0011) -[2023-10-10 23:14:55,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 125730816. Throughput: 0: 1688.4, 1: 1684.8. Samples: 31438692. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:14:55,557][97672] Avg episode reward: [(0, '-1.400'), (1, '22.560')] -[2023-10-10 23:14:55,891][98560] Updated weights for policy 1, policy_version 61222 (0.0010) -[2023-10-10 23:14:56,265][98560] Updated weights for policy 1, policy_version 61232 (0.0008) -[2023-10-10 23:14:56,630][98560] Updated weights for policy 1, policy_version 61242 (0.0007) -[2023-10-10 23:14:56,917][98559] Updated weights for policy 0, policy_version 61570 (0.0011) -[2023-10-10 23:14:57,319][98559] Updated weights for policy 0, policy_version 61580 (0.0009) -[2023-10-10 23:14:57,690][98559] Updated weights for policy 0, policy_version 61590 (0.0007) -[2023-10-10 23:14:58,055][98559] Updated weights for policy 0, policy_version 61600 (0.0008) -[2023-10-10 23:15:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 125796352. Throughput: 0: 1710.9, 1: 1696.8. Samples: 31459662. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:15:00,556][97672] Avg episode reward: [(0, '-1.400'), (1, '22.520')] -[2023-10-10 23:15:00,680][98560] Updated weights for policy 1, policy_version 61252 (0.0009) -[2023-10-10 23:15:01,051][98560] Updated weights for policy 1, policy_version 61262 (0.0008) -[2023-10-10 23:15:01,420][98560] Updated weights for policy 1, policy_version 61272 (0.0008) -[2023-10-10 23:15:02,017][98559] Updated weights for policy 0, policy_version 61610 (0.0010) -[2023-10-10 23:15:02,391][98559] Updated weights for policy 0, policy_version 61620 (0.0009) -[2023-10-10 23:15:02,755][98559] Updated weights for policy 0, policy_version 61630 (0.0008) -[2023-10-10 23:15:05,263][98560] Updated weights for policy 1, policy_version 61282 (0.0007) -[2023-10-10 23:15:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.1, 300 sec: 13662.6). Total num frames: 125861888. Throughput: 0: 1724.3, 1: 1695.2. Samples: 31480706. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:15:05,557][97672] Avg episode reward: [(0, '-1.400'), (1, '22.460')] -[2023-10-10 23:15:05,621][98560] Updated weights for policy 1, policy_version 61292 (0.0007) -[2023-10-10 23:15:05,989][98560] Updated weights for policy 1, policy_version 61302 (0.0008) -[2023-10-10 23:15:06,352][98560] Updated weights for policy 1, policy_version 61312 (0.0007) -[2023-10-10 23:15:06,752][98559] Updated weights for policy 0, policy_version 61640 (0.0010) -[2023-10-10 23:15:07,117][98559] Updated weights for policy 0, policy_version 61650 (0.0009) -[2023-10-10 23:15:07,495][98559] Updated weights for policy 0, policy_version 61660 (0.0009) -[2023-10-10 23:15:10,351][98560] Updated weights for policy 1, policy_version 61322 (0.0009) -[2023-10-10 23:15:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 125927424. Throughput: 0: 1696.6, 1: 1698.3. Samples: 31490126. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:15:10,556][97672] Avg episode reward: [(0, '-1.400'), (1, '22.460')] -[2023-10-10 23:15:10,730][98560] Updated weights for policy 1, policy_version 61332 (0.0009) -[2023-10-10 23:15:11,104][98560] Updated weights for policy 1, policy_version 61342 (0.0008) -[2023-10-10 23:15:11,488][98559] Updated weights for policy 0, policy_version 61670 (0.0009) -[2023-10-10 23:15:11,854][98559] Updated weights for policy 0, policy_version 61680 (0.0009) -[2023-10-10 23:15:12,216][98559] Updated weights for policy 0, policy_version 61690 (0.0007) -[2023-10-10 23:15:15,084][98560] Updated weights for policy 1, policy_version 61352 (0.0009) -[2023-10-10 23:15:15,465][98560] Updated weights for policy 1, policy_version 61362 (0.0008) -[2023-10-10 23:15:15,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 125992960. Throughput: 0: 1722.9, 1: 1690.7. Samples: 31511022. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:15:15,556][97672] Avg episode reward: [(0, '-1.480'), (1, '22.480')] -[2023-10-10 23:15:15,825][98560] Updated weights for policy 1, policy_version 61372 (0.0011) -[2023-10-10 23:15:16,270][98559] Updated weights for policy 0, policy_version 61700 (0.0009) -[2023-10-10 23:15:16,636][98559] Updated weights for policy 0, policy_version 61710 (0.0009) -[2023-10-10 23:15:16,995][98559] Updated weights for policy 0, policy_version 61720 (0.0008) -[2023-10-10 23:15:20,093][98560] Updated weights for policy 1, policy_version 61382 (0.0008) -[2023-10-10 23:15:20,453][98560] Updated weights for policy 1, policy_version 61392 (0.0009) -[2023-10-10 23:15:20,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 126058496. Throughput: 0: 1717.4, 1: 1694.0. Samples: 31531856. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:15:20,557][97672] Avg episode reward: [(0, '-1.480'), (1, '22.500')] -[2023-10-10 23:15:20,829][98560] Updated weights for policy 1, policy_version 61402 (0.0008) -[2023-10-10 23:15:21,009][98559] Updated weights for policy 0, policy_version 61730 (0.0009) -[2023-10-10 23:15:21,371][98559] Updated weights for policy 0, policy_version 61740 (0.0008) -[2023-10-10 23:15:21,725][98559] Updated weights for policy 0, policy_version 61750 (0.0008) -[2023-10-10 23:15:22,092][98559] Updated weights for policy 0, policy_version 61760 (0.0010) -[2023-10-10 23:15:24,997][98560] Updated weights for policy 1, policy_version 61412 (0.0007) -[2023-10-10 23:15:25,368][98560] Updated weights for policy 1, policy_version 61422 (0.0008) -[2023-10-10 23:15:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 126124032. Throughput: 0: 1706.8, 1: 1695.8. Samples: 31541184. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:15:25,557][97672] Avg episode reward: [(0, '-1.480'), (1, '22.520')] -[2023-10-10 23:15:25,737][98560] Updated weights for policy 1, policy_version 61432 (0.0008) -[2023-10-10 23:15:26,041][98559] Updated weights for policy 0, policy_version 61770 (0.0008) -[2023-10-10 23:15:26,404][98559] Updated weights for policy 0, policy_version 61780 (0.0007) -[2023-10-10 23:15:26,773][98559] Updated weights for policy 0, policy_version 61790 (0.0007) -[2023-10-10 23:15:29,753][98560] Updated weights for policy 1, policy_version 61442 (0.0010) -[2023-10-10 23:15:30,114][98560] Updated weights for policy 1, policy_version 61452 (0.0009) -[2023-10-10 23:15:30,479][98560] Updated weights for policy 1, policy_version 61462 (0.0007) -[2023-10-10 23:15:30,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 126189568. Throughput: 0: 1717.0, 1: 1695.5. Samples: 31562278. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:15:30,556][97672] Avg episode reward: [(0, '-1.480'), (1, '22.580')] -[2023-10-10 23:15:30,598][98559] Updated weights for policy 0, policy_version 61800 (0.0009) -[2023-10-10 23:15:30,836][98560] Updated weights for policy 1, policy_version 61472 (0.0009) -[2023-10-10 23:15:30,957][98559] Updated weights for policy 0, policy_version 61810 (0.0008) -[2023-10-10 23:15:31,334][98559] Updated weights for policy 0, policy_version 61820 (0.0007) -[2023-10-10 23:15:34,868][98560] Updated weights for policy 1, policy_version 61482 (0.0008) -[2023-10-10 23:15:35,207][98559] Updated weights for policy 0, policy_version 61830 (0.0009) -[2023-10-10 23:15:35,226][98560] Updated weights for policy 1, policy_version 61492 (0.0009) -[2023-10-10 23:15:35,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 126255104. Throughput: 0: 1712.9, 1: 1696.7. Samples: 31582918. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:15:35,557][97672] Avg episode reward: [(0, '-1.480'), (1, '22.620')] -[2023-10-10 23:15:35,571][98559] Updated weights for policy 0, policy_version 61840 (0.0007) -[2023-10-10 23:15:35,587][98560] Updated weights for policy 1, policy_version 61502 (0.0009) -[2023-10-10 23:15:35,936][98559] Updated weights for policy 0, policy_version 61850 (0.0007) -[2023-10-10 23:15:39,503][98560] Updated weights for policy 1, policy_version 61512 (0.0008) -[2023-10-10 23:15:39,869][98560] Updated weights for policy 1, policy_version 61522 (0.0009) -[2023-10-10 23:15:40,019][98559] Updated weights for policy 0, policy_version 61860 (0.0008) -[2023-10-10 23:15:40,231][98560] Updated weights for policy 1, policy_version 61532 (0.0008) -[2023-10-10 23:15:40,381][98559] Updated weights for policy 0, policy_version 61870 (0.0008) -[2023-10-10 23:15:40,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 126353408. Throughput: 0: 1720.5, 1: 1702.5. Samples: 31592728. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:15:40,556][97672] Avg episode reward: [(0, '-1.480'), (1, '22.580')] -[2023-10-10 23:15:40,742][98559] Updated weights for policy 0, policy_version 61880 (0.0009) -[2023-10-10 23:15:44,159][98560] Updated weights for policy 1, policy_version 61542 (0.0009) -[2023-10-10 23:15:44,526][98560] Updated weights for policy 1, policy_version 61552 (0.0008) -[2023-10-10 23:15:44,854][98559] Updated weights for policy 0, policy_version 61890 (0.0008) -[2023-10-10 23:15:44,895][98560] Updated weights for policy 1, policy_version 61562 (0.0008) -[2023-10-10 23:15:45,249][98559] Updated weights for policy 0, policy_version 61900 (0.0007) -[2023-10-10 23:15:45,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 126418944. Throughput: 0: 1720.2, 1: 1701.1. Samples: 31613620. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:15:45,557][97672] Avg episode reward: [(0, '-1.540'), (1, '22.620')] -[2023-10-10 23:15:45,609][98559] Updated weights for policy 0, policy_version 61910 (0.0007) -[2023-10-10 23:15:45,965][98559] Updated weights for policy 0, policy_version 61920 (0.0008) -[2023-10-10 23:15:48,912][98560] Updated weights for policy 1, policy_version 61572 (0.0010) -[2023-10-10 23:15:49,276][98560] Updated weights for policy 1, policy_version 61582 (0.0008) -[2023-10-10 23:15:49,642][98560] Updated weights for policy 1, policy_version 61592 (0.0008) -[2023-10-10 23:15:49,997][98559] Updated weights for policy 0, policy_version 61930 (0.0009) -[2023-10-10 23:15:50,348][98559] Updated weights for policy 0, policy_version 61940 (0.0008) -[2023-10-10 23:15:50,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 126484480. Throughput: 0: 1703.0, 1: 1674.8. Samples: 31632704. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:15:50,557][97672] Avg episode reward: [(0, '-1.580'), (1, '22.700')] -[2023-10-10 23:15:50,711][98559] Updated weights for policy 0, policy_version 61950 (0.0009) -[2023-10-10 23:15:53,636][98560] Updated weights for policy 1, policy_version 61602 (0.0010) -[2023-10-10 23:15:53,994][98560] Updated weights for policy 1, policy_version 61612 (0.0009) -[2023-10-10 23:15:54,364][98560] Updated weights for policy 1, policy_version 61622 (0.0009) -[2023-10-10 23:15:54,686][98559] Updated weights for policy 0, policy_version 61960 (0.0010) -[2023-10-10 23:15:54,726][98560] Updated weights for policy 1, policy_version 61632 (0.0009) -[2023-10-10 23:15:55,055][98559] Updated weights for policy 0, policy_version 61970 (0.0009) -[2023-10-10 23:15:55,420][98559] Updated weights for policy 0, policy_version 61980 (0.0011) -[2023-10-10 23:15:55,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 126550016. Throughput: 0: 1718.5, 1: 1697.0. Samples: 31643824. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:15:55,557][97672] Avg episode reward: [(0, '-1.740'), (1, '22.700')] -[2023-10-10 23:15:58,649][98560] Updated weights for policy 1, policy_version 61642 (0.0007) -[2023-10-10 23:15:59,010][98560] Updated weights for policy 1, policy_version 61652 (0.0010) -[2023-10-10 23:15:59,387][98560] Updated weights for policy 1, policy_version 61662 (0.0009) -[2023-10-10 23:15:59,471][98559] Updated weights for policy 0, policy_version 61990 (0.0008) -[2023-10-10 23:15:59,839][98559] Updated weights for policy 0, policy_version 62000 (0.0009) -[2023-10-10 23:16:00,204][98559] Updated weights for policy 0, policy_version 62010 (0.0009) -[2023-10-10 23:16:00,556][97672] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 126648320. Throughput: 0: 1717.8, 1: 1694.4. Samples: 31664572. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:16:00,556][97672] Avg episode reward: [(0, '-1.740'), (1, '22.680')] -[2023-10-10 23:16:03,371][98560] Updated weights for policy 1, policy_version 61672 (0.0009) -[2023-10-10 23:16:03,748][98560] Updated weights for policy 1, policy_version 61682 (0.0008) -[2023-10-10 23:16:04,105][98560] Updated weights for policy 1, policy_version 61692 (0.0010) -[2023-10-10 23:16:04,149][98559] Updated weights for policy 0, policy_version 62020 (0.0007) -[2023-10-10 23:16:04,517][98559] Updated weights for policy 0, policy_version 62030 (0.0009) -[2023-10-10 23:16:04,879][98559] Updated weights for policy 0, policy_version 62040 (0.0009) -[2023-10-10 23:16:05,556][97672] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 126713856. Throughput: 0: 1698.1, 1: 1678.2. Samples: 31683790. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:16:05,557][97672] Avg episode reward: [(0, '-1.740'), (1, '22.700')] -[2023-10-10 23:16:08,293][98560] Updated weights for policy 1, policy_version 61702 (0.0008) -[2023-10-10 23:16:08,652][98560] Updated weights for policy 1, policy_version 61712 (0.0009) -[2023-10-10 23:16:08,699][98559] Updated weights for policy 0, policy_version 62050 (0.0008) -[2023-10-10 23:16:09,022][98560] Updated weights for policy 1, policy_version 61722 (0.0008) -[2023-10-10 23:16:09,061][98559] Updated weights for policy 0, policy_version 62060 (0.0008) -[2023-10-10 23:16:09,429][98559] Updated weights for policy 0, policy_version 62070 (0.0009) -[2023-10-10 23:16:09,786][98559] Updated weights for policy 0, policy_version 62080 (0.0009) -[2023-10-10 23:16:10,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 126779392. Throughput: 0: 1726.6, 1: 1706.8. Samples: 31695688. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:16:10,557][97672] Avg episode reward: [(0, '-1.740'), (1, '22.660')] -[2023-10-10 23:16:13,110][98560] Updated weights for policy 1, policy_version 61732 (0.0007) -[2023-10-10 23:16:13,476][98560] Updated weights for policy 1, policy_version 61742 (0.0009) -[2023-10-10 23:16:13,840][98560] Updated weights for policy 1, policy_version 61752 (0.0008) -[2023-10-10 23:16:13,869][98559] Updated weights for policy 0, policy_version 62090 (0.0009) -[2023-10-10 23:16:14,231][98559] Updated weights for policy 0, policy_version 62100 (0.0009) -[2023-10-10 23:16:14,600][98559] Updated weights for policy 0, policy_version 62110 (0.0011) -[2023-10-10 23:16:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 126844928. Throughput: 0: 1702.3, 1: 1687.3. Samples: 31714810. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:16:15,557][97672] Avg episode reward: [(0, '-1.740'), (1, '22.620')] -[2023-10-10 23:16:17,968][98560] Updated weights for policy 1, policy_version 61762 (0.0008) -[2023-10-10 23:16:18,388][98560] Updated weights for policy 1, policy_version 61772 (0.0009) -[2023-10-10 23:16:18,480][98559] Updated weights for policy 0, policy_version 62120 (0.0008) -[2023-10-10 23:16:18,753][98560] Updated weights for policy 1, policy_version 61782 (0.0008) -[2023-10-10 23:16:18,844][98559] Updated weights for policy 0, policy_version 62130 (0.0008) -[2023-10-10 23:16:19,112][98560] Updated weights for policy 1, policy_version 61792 (0.0008) -[2023-10-10 23:16:19,214][98559] Updated weights for policy 0, policy_version 62140 (0.0009) -[2023-10-10 23:16:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 126910464. Throughput: 0: 1700.7, 1: 1673.4. Samples: 31734752. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-10 23:16:20,556][97672] Avg episode reward: [(0, '-1.740'), (1, '22.620')] -[2023-10-10 23:16:23,110][98560] Updated weights for policy 1, policy_version 61802 (0.0009) -[2023-10-10 23:16:23,164][98559] Updated weights for policy 0, policy_version 62150 (0.0007) -[2023-10-10 23:16:23,473][98560] Updated weights for policy 1, policy_version 61812 (0.0009) -[2023-10-10 23:16:23,531][98559] Updated weights for policy 0, policy_version 62160 (0.0007) -[2023-10-10 23:16:23,844][98560] Updated weights for policy 1, policy_version 61822 (0.0007) -[2023-10-10 23:16:23,896][98559] Updated weights for policy 0, policy_version 62170 (0.0007) -[2023-10-10 23:16:25,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 126976000. Throughput: 0: 1715.8, 1: 1697.6. Samples: 31746330. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-10 23:16:25,557][97672] Avg episode reward: [(0, '-1.740'), (1, '22.560')] -[2023-10-10 23:16:27,905][98560] Updated weights for policy 1, policy_version 61832 (0.0009) -[2023-10-10 23:16:27,913][98559] Updated weights for policy 0, policy_version 62180 (0.0009) -[2023-10-10 23:16:28,263][98560] Updated weights for policy 1, policy_version 61842 (0.0008) -[2023-10-10 23:16:28,280][98559] Updated weights for policy 0, policy_version 62190 (0.0008) -[2023-10-10 23:16:28,631][98560] Updated weights for policy 1, policy_version 61852 (0.0009) -[2023-10-10 23:16:28,653][98559] Updated weights for policy 0, policy_version 62200 (0.0008) -[2023-10-10 23:16:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 127041536. Throughput: 0: 1700.5, 1: 1671.6. Samples: 31765364. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-10 23:16:30,557][97672] Avg episode reward: [(0, '-1.740'), (1, '22.540')] -[2023-10-10 23:16:32,646][98560] Updated weights for policy 1, policy_version 61862 (0.0008) -[2023-10-10 23:16:32,699][98559] Updated weights for policy 0, policy_version 62210 (0.0008) -[2023-10-10 23:16:33,001][98560] Updated weights for policy 1, policy_version 61872 (0.0010) -[2023-10-10 23:16:33,094][98559] Updated weights for policy 0, policy_version 62220 (0.0009) -[2023-10-10 23:16:33,371][98560] Updated weights for policy 1, policy_version 61882 (0.0008) -[2023-10-10 23:16:33,470][98559] Updated weights for policy 0, policy_version 62230 (0.0008) -[2023-10-10 23:16:33,836][98559] Updated weights for policy 0, policy_version 62240 (0.0010) -[2023-10-10 23:16:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 127107072. Throughput: 0: 1719.1, 1: 1692.2. Samples: 31786210. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-10 23:16:35,557][97672] Avg episode reward: [(0, '-1.740'), (1, '22.540')] -[2023-10-10 23:16:35,569][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000061888_63373312.pth... -[2023-10-10 23:16:35,569][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000062240_63733760.pth... -[2023-10-10 23:16:35,608][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000060640_62095360.pth -[2023-10-10 23:16:35,610][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000060320_61767680.pth -[2023-10-10 23:16:37,505][98560] Updated weights for policy 1, policy_version 61892 (0.0008) -[2023-10-10 23:16:37,764][98559] Updated weights for policy 0, policy_version 62250 (0.0008) -[2023-10-10 23:16:37,878][98560] Updated weights for policy 1, policy_version 61902 (0.0009) -[2023-10-10 23:16:38,135][98559] Updated weights for policy 0, policy_version 62260 (0.0009) -[2023-10-10 23:16:38,251][98560] Updated weights for policy 1, policy_version 61912 (0.0009) -[2023-10-10 23:16:38,500][98559] Updated weights for policy 0, policy_version 62270 (0.0008) -[2023-10-10 23:16:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 127172608. Throughput: 0: 1709.6, 1: 1687.4. Samples: 31796688. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-10 23:16:40,557][97672] Avg episode reward: [(0, '-1.740'), (1, '22.520')] -[2023-10-10 23:16:42,377][98560] Updated weights for policy 1, policy_version 61922 (0.0007) -[2023-10-10 23:16:42,522][98559] Updated weights for policy 0, policy_version 62280 (0.0007) -[2023-10-10 23:16:42,745][98560] Updated weights for policy 1, policy_version 61932 (0.0008) -[2023-10-10 23:16:42,888][98559] Updated weights for policy 0, policy_version 62290 (0.0008) -[2023-10-10 23:16:43,108][98560] Updated weights for policy 1, policy_version 61942 (0.0009) -[2023-10-10 23:16:43,249][98559] Updated weights for policy 0, policy_version 62300 (0.0009) -[2023-10-10 23:16:43,471][98560] Updated weights for policy 1, policy_version 61952 (0.0009) -[2023-10-10 23:16:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 127238144. Throughput: 0: 1701.5, 1: 1674.4. Samples: 31816490. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-10 23:16:45,557][97672] Avg episode reward: [(0, '-1.740'), (1, '22.540')] -[2023-10-10 23:16:47,124][98559] Updated weights for policy 0, policy_version 62310 (0.0011) -[2023-10-10 23:16:47,492][98559] Updated weights for policy 0, policy_version 62320 (0.0009) -[2023-10-10 23:16:47,603][98560] Updated weights for policy 1, policy_version 61962 (0.0009) -[2023-10-10 23:16:47,855][98559] Updated weights for policy 0, policy_version 62330 (0.0008) -[2023-10-10 23:16:47,959][98560] Updated weights for policy 1, policy_version 61972 (0.0010) -[2023-10-10 23:16:48,333][98560] Updated weights for policy 1, policy_version 61982 (0.0009) -[2023-10-10 23:16:50,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 127303680. Throughput: 0: 1722.6, 1: 1686.5. Samples: 31837202. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-10 23:16:50,557][97672] Avg episode reward: [(0, '-1.760'), (1, '22.500')] -[2023-10-10 23:16:51,799][98559] Updated weights for policy 0, policy_version 62340 (0.0007) -[2023-10-10 23:16:52,173][98559] Updated weights for policy 0, policy_version 62350 (0.0008) -[2023-10-10 23:16:52,307][98560] Updated weights for policy 1, policy_version 61992 (0.0007) -[2023-10-10 23:16:52,539][98559] Updated weights for policy 0, policy_version 62360 (0.0009) -[2023-10-10 23:16:52,672][98560] Updated weights for policy 1, policy_version 62002 (0.0007) -[2023-10-10 23:16:53,045][98560] Updated weights for policy 1, policy_version 62012 (0.0008) -[2023-10-10 23:16:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 127369216. Throughput: 0: 1693.6, 1: 1673.8. Samples: 31847222. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-10 23:16:55,557][97672] Avg episode reward: [(0, '-1.760'), (1, '22.500')] -[2023-10-10 23:16:56,418][98559] Updated weights for policy 0, policy_version 62370 (0.0009) -[2023-10-10 23:16:56,789][98559] Updated weights for policy 0, policy_version 62380 (0.0009) -[2023-10-10 23:16:57,150][98559] Updated weights for policy 0, policy_version 62390 (0.0009) -[2023-10-10 23:16:57,159][98560] Updated weights for policy 1, policy_version 62022 (0.0008) -[2023-10-10 23:16:57,512][98559] Updated weights for policy 0, policy_version 62400 (0.0008) -[2023-10-10 23:16:57,531][98560] Updated weights for policy 1, policy_version 62032 (0.0007) -[2023-10-10 23:16:57,887][98560] Updated weights for policy 1, policy_version 62042 (0.0010) -[2023-10-10 23:17:00,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 127434752. Throughput: 0: 1719.5, 1: 1677.3. Samples: 31867664. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-10 23:17:00,556][97672] Avg episode reward: [(0, '-1.760'), (1, '22.520')] -[2023-10-10 23:17:01,612][98559] Updated weights for policy 0, policy_version 62410 (0.0010) -[2023-10-10 23:17:01,923][98560] Updated weights for policy 1, policy_version 62052 (0.0008) -[2023-10-10 23:17:01,973][98559] Updated weights for policy 0, policy_version 62420 (0.0008) -[2023-10-10 23:17:02,292][98560] Updated weights for policy 1, policy_version 62062 (0.0007) -[2023-10-10 23:17:02,326][98559] Updated weights for policy 0, policy_version 62430 (0.0008) -[2023-10-10 23:17:02,648][98560] Updated weights for policy 1, policy_version 62072 (0.0008) -[2023-10-10 23:17:05,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 127500288. Throughput: 0: 1726.8, 1: 1694.5. Samples: 31888710. Policy #0 lag: (min: 8.0, avg: 29.3, max: 40.0) -[2023-10-10 23:17:05,557][97672] Avg episode reward: [(0, '-1.740'), (1, '22.520')] -[2023-10-10 23:17:06,248][98559] Updated weights for policy 0, policy_version 62440 (0.0010) -[2023-10-10 23:17:06,599][98560] Updated weights for policy 1, policy_version 62082 (0.0008) -[2023-10-10 23:17:06,619][98559] Updated weights for policy 0, policy_version 62450 (0.0008) -[2023-10-10 23:17:06,983][98559] Updated weights for policy 0, policy_version 62460 (0.0010) -[2023-10-10 23:17:07,004][98560] Updated weights for policy 1, policy_version 62092 (0.0008) -[2023-10-10 23:17:07,375][98560] Updated weights for policy 1, policy_version 62102 (0.0007) -[2023-10-10 23:17:07,741][98560] Updated weights for policy 1, policy_version 62112 (0.0008) -[2023-10-10 23:17:10,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 127565824. Throughput: 0: 1707.7, 1: 1661.2. Samples: 31897926. Policy #0 lag: (min: 8.0, avg: 29.3, max: 40.0) -[2023-10-10 23:17:10,557][97672] Avg episode reward: [(0, '-1.740'), (1, '22.520')] -[2023-10-10 23:17:11,018][98559] Updated weights for policy 0, policy_version 62470 (0.0008) -[2023-10-10 23:17:11,384][98559] Updated weights for policy 0, policy_version 62480 (0.0007) -[2023-10-10 23:17:11,718][98560] Updated weights for policy 1, policy_version 62122 (0.0008) -[2023-10-10 23:17:11,752][98559] Updated weights for policy 0, policy_version 62490 (0.0008) -[2023-10-10 23:17:12,092][98560] Updated weights for policy 1, policy_version 62132 (0.0009) -[2023-10-10 23:17:12,456][98560] Updated weights for policy 1, policy_version 62142 (0.0009) -[2023-10-10 23:17:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 127631360. Throughput: 0: 1724.0, 1: 1687.4. Samples: 31918876. Policy #0 lag: (min: 8.0, avg: 29.3, max: 40.0) -[2023-10-10 23:17:15,556][97672] Avg episode reward: [(0, '-1.700'), (1, '22.520')] -[2023-10-10 23:17:15,753][98559] Updated weights for policy 0, policy_version 62500 (0.0009) -[2023-10-10 23:17:16,133][98559] Updated weights for policy 0, policy_version 62510 (0.0010) -[2023-10-10 23:17:16,503][98559] Updated weights for policy 0, policy_version 62520 (0.0008) -[2023-10-10 23:17:16,539][98560] Updated weights for policy 1, policy_version 62152 (0.0009) -[2023-10-10 23:17:16,905][98560] Updated weights for policy 1, policy_version 62162 (0.0009) -[2023-10-10 23:17:17,283][98560] Updated weights for policy 1, policy_version 62172 (0.0009) -[2023-10-10 23:17:20,401][98559] Updated weights for policy 0, policy_version 62530 (0.0011) -[2023-10-10 23:17:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 127696896. Throughput: 0: 1722.9, 1: 1689.7. Samples: 31939776. Policy #0 lag: (min: 8.0, avg: 29.3, max: 40.0) -[2023-10-10 23:17:20,556][97672] Avg episode reward: [(0, '-1.740'), (1, '22.540')] -[2023-10-10 23:17:20,806][98559] Updated weights for policy 0, policy_version 62540 (0.0009) -[2023-10-10 23:17:21,173][98559] Updated weights for policy 0, policy_version 62550 (0.0009) -[2023-10-10 23:17:21,430][98560] Updated weights for policy 1, policy_version 62182 (0.0007) -[2023-10-10 23:17:21,535][98559] Updated weights for policy 0, policy_version 62560 (0.0008) -[2023-10-10 23:17:21,796][98560] Updated weights for policy 1, policy_version 62192 (0.0008) -[2023-10-10 23:17:22,158][98560] Updated weights for policy 1, policy_version 62202 (0.0011) -[2023-10-10 23:17:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 127762432. Throughput: 0: 1716.4, 1: 1669.1. Samples: 31949038. Policy #0 lag: (min: 8.0, avg: 29.3, max: 40.0) -[2023-10-10 23:17:25,557][97672] Avg episode reward: [(0, '-1.760'), (1, '22.480')] -[2023-10-10 23:17:25,557][98559] Updated weights for policy 0, policy_version 62570 (0.0008) -[2023-10-10 23:17:25,918][98559] Updated weights for policy 0, policy_version 62580 (0.0007) -[2023-10-10 23:17:26,070][98560] Updated weights for policy 1, policy_version 62212 (0.0010) -[2023-10-10 23:17:26,280][98559] Updated weights for policy 0, policy_version 62590 (0.0009) -[2023-10-10 23:17:26,435][98560] Updated weights for policy 1, policy_version 62222 (0.0008) -[2023-10-10 23:17:26,802][98560] Updated weights for policy 1, policy_version 62232 (0.0009) -[2023-10-10 23:17:30,143][98559] Updated weights for policy 0, policy_version 62600 (0.0009) -[2023-10-10 23:17:30,505][98559] Updated weights for policy 0, policy_version 62610 (0.0009) -[2023-10-10 23:17:30,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 127827968. Throughput: 0: 1723.3, 1: 1692.6. Samples: 31970204. Policy #0 lag: (min: 8.0, avg: 29.3, max: 40.0) -[2023-10-10 23:17:30,557][97672] Avg episode reward: [(0, '-1.760'), (1, '22.440')] -[2023-10-10 23:17:30,774][98560] Updated weights for policy 1, policy_version 62242 (0.0007) -[2023-10-10 23:17:30,879][98559] Updated weights for policy 0, policy_version 62620 (0.0009) -[2023-10-10 23:17:31,137][98560] Updated weights for policy 1, policy_version 62252 (0.0007) -[2023-10-10 23:17:31,505][98560] Updated weights for policy 1, policy_version 62262 (0.0007) -[2023-10-10 23:17:31,872][98560] Updated weights for policy 1, policy_version 62272 (0.0007) -[2023-10-10 23:17:34,740][98559] Updated weights for policy 0, policy_version 62630 (0.0007) -[2023-10-10 23:17:35,106][98559] Updated weights for policy 0, policy_version 62640 (0.0009) -[2023-10-10 23:17:35,478][98559] Updated weights for policy 0, policy_version 62650 (0.0008) -[2023-10-10 23:17:35,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 127893504. Throughput: 0: 1708.2, 1: 1700.5. Samples: 31990594. Policy #0 lag: (min: 8.0, avg: 29.3, max: 40.0) -[2023-10-10 23:17:35,557][97672] Avg episode reward: [(0, '-1.760'), (1, '22.460')] -[2023-10-10 23:17:35,947][98560] Updated weights for policy 1, policy_version 62282 (0.0010) -[2023-10-10 23:17:36,316][98560] Updated weights for policy 1, policy_version 62292 (0.0009) -[2023-10-10 23:17:36,675][98560] Updated weights for policy 1, policy_version 62302 (0.0007) -[2023-10-10 23:17:39,326][98559] Updated weights for policy 0, policy_version 62660 (0.0008) -[2023-10-10 23:17:39,687][98559] Updated weights for policy 0, policy_version 62670 (0.0007) -[2023-10-10 23:17:40,054][98559] Updated weights for policy 0, policy_version 62680 (0.0009) -[2023-10-10 23:17:40,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 127991808. Throughput: 0: 1731.0, 1: 1682.8. Samples: 32000842. Policy #0 lag: (min: 8.0, avg: 29.3, max: 40.0) -[2023-10-10 23:17:40,557][97672] Avg episode reward: [(0, '-1.780'), (1, '22.500')] -[2023-10-10 23:17:40,688][98560] Updated weights for policy 1, policy_version 62312 (0.0008) -[2023-10-10 23:17:41,059][98560] Updated weights for policy 1, policy_version 62322 (0.0009) -[2023-10-10 23:17:41,424][98560] Updated weights for policy 1, policy_version 62332 (0.0009) -[2023-10-10 23:17:44,038][98559] Updated weights for policy 0, policy_version 62690 (0.0008) -[2023-10-10 23:17:44,405][98559] Updated weights for policy 0, policy_version 62700 (0.0009) -[2023-10-10 23:17:44,765][98559] Updated weights for policy 0, policy_version 62710 (0.0009) -[2023-10-10 23:17:45,135][98559] Updated weights for policy 0, policy_version 62720 (0.0008) -[2023-10-10 23:17:45,388][98560] Updated weights for policy 1, policy_version 62342 (0.0008) -[2023-10-10 23:17:45,556][97672] Fps is (10 sec: 16384.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 128057344. Throughput: 0: 1724.4, 1: 1701.9. Samples: 32021844. Policy #0 lag: (min: 13.0, avg: 15.8, max: 45.0) -[2023-10-10 23:17:45,556][97672] Avg episode reward: [(0, '-1.780'), (1, '22.500')] -[2023-10-10 23:17:45,758][98560] Updated weights for policy 1, policy_version 62352 (0.0008) -[2023-10-10 23:17:46,123][98560] Updated weights for policy 1, policy_version 62362 (0.0007) -[2023-10-10 23:17:49,135][98559] Updated weights for policy 0, policy_version 62730 (0.0009) -[2023-10-10 23:17:49,498][98559] Updated weights for policy 0, policy_version 62740 (0.0008) -[2023-10-10 23:17:49,870][98559] Updated weights for policy 0, policy_version 62750 (0.0008) -[2023-10-10 23:17:50,106][98560] Updated weights for policy 1, policy_version 62372 (0.0008) -[2023-10-10 23:17:50,478][98560] Updated weights for policy 1, policy_version 62382 (0.0008) -[2023-10-10 23:17:50,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 128122880. Throughput: 0: 1704.3, 1: 1707.1. Samples: 32042224. Policy #0 lag: (min: 13.0, avg: 15.8, max: 45.0) -[2023-10-10 23:17:50,557][97672] Avg episode reward: [(0, '-1.780'), (1, '22.460')] -[2023-10-10 23:17:50,849][98560] Updated weights for policy 1, policy_version 62392 (0.0009) -[2023-10-10 23:17:53,884][98559] Updated weights for policy 0, policy_version 62760 (0.0007) -[2023-10-10 23:17:54,260][98559] Updated weights for policy 0, policy_version 62770 (0.0010) -[2023-10-10 23:17:54,622][98559] Updated weights for policy 0, policy_version 62780 (0.0008) -[2023-10-10 23:17:54,827][98560] Updated weights for policy 1, policy_version 62402 (0.0007) -[2023-10-10 23:17:55,236][98560] Updated weights for policy 1, policy_version 62412 (0.0009) -[2023-10-10 23:17:55,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 128188416. Throughput: 0: 1727.5, 1: 1712.8. Samples: 32052742. Policy #0 lag: (min: 13.0, avg: 15.8, max: 45.0) -[2023-10-10 23:17:55,556][97672] Avg episode reward: [(0, '-1.780'), (1, '22.460')] -[2023-10-10 23:17:55,607][98560] Updated weights for policy 1, policy_version 62422 (0.0008) -[2023-10-10 23:17:55,974][98560] Updated weights for policy 1, policy_version 62432 (0.0009) -[2023-10-10 23:17:58,424][98559] Updated weights for policy 0, policy_version 62790 (0.0008) -[2023-10-10 23:17:58,787][98559] Updated weights for policy 0, policy_version 62800 (0.0008) -[2023-10-10 23:17:59,151][98559] Updated weights for policy 0, policy_version 62810 (0.0008) -[2023-10-10 23:18:00,046][98560] Updated weights for policy 1, policy_version 62442 (0.0007) -[2023-10-10 23:18:00,405][98560] Updated weights for policy 1, policy_version 62452 (0.0008) -[2023-10-10 23:18:00,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 128253952. Throughput: 0: 1707.1, 1: 1709.8. Samples: 32072636. Policy #0 lag: (min: 13.0, avg: 15.8, max: 45.0) -[2023-10-10 23:18:00,557][97672] Avg episode reward: [(0, '-1.780'), (1, '22.400')] -[2023-10-10 23:18:00,772][98560] Updated weights for policy 1, policy_version 62462 (0.0009) -[2023-10-10 23:18:03,133][98559] Updated weights for policy 0, policy_version 62820 (0.0008) -[2023-10-10 23:18:03,504][98559] Updated weights for policy 0, policy_version 62830 (0.0009) -[2023-10-10 23:18:03,880][98559] Updated weights for policy 0, policy_version 62840 (0.0009) -[2023-10-10 23:18:04,776][98560] Updated weights for policy 1, policy_version 62472 (0.0007) -[2023-10-10 23:18:05,136][98560] Updated weights for policy 1, policy_version 62482 (0.0008) -[2023-10-10 23:18:05,506][98560] Updated weights for policy 1, policy_version 62492 (0.0008) -[2023-10-10 23:18:05,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 128319488. Throughput: 0: 1714.6, 1: 1705.2. Samples: 32093670. Policy #0 lag: (min: 13.0, avg: 15.8, max: 45.0) -[2023-10-10 23:18:05,556][97672] Avg episode reward: [(0, '-1.780'), (1, '22.480')] -[2023-10-10 23:18:07,670][98559] Updated weights for policy 0, policy_version 62850 (0.0008) -[2023-10-10 23:18:08,059][98559] Updated weights for policy 0, policy_version 62860 (0.0009) -[2023-10-10 23:18:08,430][98559] Updated weights for policy 0, policy_version 62870 (0.0010) -[2023-10-10 23:18:08,786][98559] Updated weights for policy 0, policy_version 62880 (0.0009) -[2023-10-10 23:18:09,602][98560] Updated weights for policy 1, policy_version 62502 (0.0009) -[2023-10-10 23:18:09,972][98560] Updated weights for policy 1, policy_version 62512 (0.0009) -[2023-10-10 23:18:10,331][98560] Updated weights for policy 1, policy_version 62522 (0.0009) -[2023-10-10 23:18:10,556][97672] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 128417792. Throughput: 0: 1726.4, 1: 1710.4. Samples: 32103696. Policy #0 lag: (min: 13.0, avg: 15.8, max: 45.0) -[2023-10-10 23:18:10,557][97672] Avg episode reward: [(0, '-1.780'), (1, '22.460')] -[2023-10-10 23:18:12,808][98559] Updated weights for policy 0, policy_version 62890 (0.0010) -[2023-10-10 23:18:13,169][98559] Updated weights for policy 0, policy_version 62900 (0.0011) -[2023-10-10 23:18:13,537][98559] Updated weights for policy 0, policy_version 62910 (0.0011) -[2023-10-10 23:18:14,265][98560] Updated weights for policy 1, policy_version 62532 (0.0008) -[2023-10-10 23:18:14,640][98560] Updated weights for policy 1, policy_version 62542 (0.0008) -[2023-10-10 23:18:15,001][98560] Updated weights for policy 1, policy_version 62552 (0.0011) -[2023-10-10 23:18:15,556][97672] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 128483328. Throughput: 0: 1711.9, 1: 1707.3. Samples: 32124066. Policy #0 lag: (min: 13.0, avg: 15.8, max: 45.0) -[2023-10-10 23:18:15,557][97672] Avg episode reward: [(0, '-1.780'), (1, '22.480')] -[2023-10-10 23:18:17,414][98559] Updated weights for policy 0, policy_version 62920 (0.0010) -[2023-10-10 23:18:17,779][98559] Updated weights for policy 0, policy_version 62930 (0.0009) -[2023-10-10 23:18:18,144][98559] Updated weights for policy 0, policy_version 62940 (0.0007) -[2023-10-10 23:18:18,791][98560] Updated weights for policy 1, policy_version 62562 (0.0008) -[2023-10-10 23:18:19,156][98560] Updated weights for policy 1, policy_version 62572 (0.0008) -[2023-10-10 23:18:19,528][98560] Updated weights for policy 1, policy_version 62582 (0.0010) -[2023-10-10 23:18:19,885][98560] Updated weights for policy 1, policy_version 62592 (0.0009) -[2023-10-10 23:18:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 128548864. Throughput: 0: 1735.2, 1: 1689.1. Samples: 32144686. Policy #0 lag: (min: 13.0, avg: 15.8, max: 45.0) -[2023-10-10 23:18:20,556][97672] Avg episode reward: [(0, '-1.780'), (1, '22.460')] -[2023-10-10 23:18:22,107][98559] Updated weights for policy 0, policy_version 62950 (0.0008) -[2023-10-10 23:18:22,481][98559] Updated weights for policy 0, policy_version 62960 (0.0009) -[2023-10-10 23:18:22,847][98559] Updated weights for policy 0, policy_version 62970 (0.0009) -[2023-10-10 23:18:23,747][98560] Updated weights for policy 1, policy_version 62602 (0.0008) -[2023-10-10 23:18:24,114][98560] Updated weights for policy 1, policy_version 62612 (0.0009) -[2023-10-10 23:18:24,483][98560] Updated weights for policy 1, policy_version 62622 (0.0008) -[2023-10-10 23:18:25,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 128614400. Throughput: 0: 1708.3, 1: 1720.4. Samples: 32155134. Policy #0 lag: (min: 13.0, avg: 15.8, max: 45.0) -[2023-10-10 23:18:25,556][97672] Avg episode reward: [(0, '-1.780'), (1, '22.460')] -[2023-10-10 23:18:26,841][98559] Updated weights for policy 0, policy_version 62980 (0.0009) -[2023-10-10 23:18:27,214][98559] Updated weights for policy 0, policy_version 62990 (0.0010) -[2023-10-10 23:18:27,579][98559] Updated weights for policy 0, policy_version 63000 (0.0009) -[2023-10-10 23:18:28,550][98560] Updated weights for policy 1, policy_version 62632 (0.0009) -[2023-10-10 23:18:28,909][98560] Updated weights for policy 1, policy_version 62642 (0.0009) -[2023-10-10 23:18:29,276][98560] Updated weights for policy 1, policy_version 62652 (0.0008) -[2023-10-10 23:18:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 128679936. Throughput: 0: 1714.1, 1: 1708.9. Samples: 32175880. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-10 23:18:30,557][97672] Avg episode reward: [(0, '-1.780'), (1, '22.540')] -[2023-10-10 23:18:31,515][98559] Updated weights for policy 0, policy_version 63010 (0.0009) -[2023-10-10 23:18:31,895][98559] Updated weights for policy 0, policy_version 63020 (0.0009) -[2023-10-10 23:18:32,271][98559] Updated weights for policy 0, policy_version 63030 (0.0008) -[2023-10-10 23:18:32,637][98559] Updated weights for policy 0, policy_version 63040 (0.0009) -[2023-10-10 23:18:33,357][98560] Updated weights for policy 1, policy_version 62662 (0.0007) -[2023-10-10 23:18:33,720][98560] Updated weights for policy 1, policy_version 62672 (0.0009) -[2023-10-10 23:18:34,094][98560] Updated weights for policy 1, policy_version 62682 (0.0009) -[2023-10-10 23:18:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 128745472. Throughput: 0: 1734.4, 1: 1688.2. Samples: 32196238. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-10 23:18:35,556][97672] Avg episode reward: [(0, '-1.780'), (1, '22.600')] -[2023-10-10 23:18:35,567][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000062688_64192512.pth... -[2023-10-10 23:18:35,567][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000063040_64552960.pth... -[2023-10-10 23:18:35,599][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000061088_62554112.pth -[2023-10-10 23:18:35,604][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000061440_62914560.pth -[2023-10-10 23:18:36,614][98559] Updated weights for policy 0, policy_version 63050 (0.0007) -[2023-10-10 23:18:36,977][98559] Updated weights for policy 0, policy_version 63060 (0.0007) -[2023-10-10 23:18:37,338][98559] Updated weights for policy 0, policy_version 63070 (0.0007) -[2023-10-10 23:18:38,121][98560] Updated weights for policy 1, policy_version 62692 (0.0009) -[2023-10-10 23:18:38,488][98560] Updated weights for policy 1, policy_version 62702 (0.0010) -[2023-10-10 23:18:38,855][98560] Updated weights for policy 1, policy_version 62712 (0.0009) -[2023-10-10 23:18:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 128811008. Throughput: 0: 1711.9, 1: 1716.4. Samples: 32207018. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-10 23:18:40,556][97672] Avg episode reward: [(0, '-1.840'), (1, '22.640')] -[2023-10-10 23:18:41,235][98559] Updated weights for policy 0, policy_version 63080 (0.0009) -[2023-10-10 23:18:41,604][98559] Updated weights for policy 0, policy_version 63090 (0.0010) -[2023-10-10 23:18:41,973][98559] Updated weights for policy 0, policy_version 63100 (0.0012) -[2023-10-10 23:18:43,033][98560] Updated weights for policy 1, policy_version 62722 (0.0011) -[2023-10-10 23:18:43,398][98560] Updated weights for policy 1, policy_version 62732 (0.0007) -[2023-10-10 23:18:43,759][98560] Updated weights for policy 1, policy_version 62742 (0.0008) -[2023-10-10 23:18:44,131][98560] Updated weights for policy 1, policy_version 62752 (0.0009) -[2023-10-10 23:18:45,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 128876544. Throughput: 0: 1734.0, 1: 1695.4. Samples: 32226958. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-10 23:18:45,557][97672] Avg episode reward: [(0, '-1.840'), (1, '22.700')] -[2023-10-10 23:18:46,204][98559] Updated weights for policy 0, policy_version 63110 (0.0009) -[2023-10-10 23:18:46,568][98559] Updated weights for policy 0, policy_version 63120 (0.0008) -[2023-10-10 23:18:46,939][98559] Updated weights for policy 0, policy_version 63130 (0.0008) -[2023-10-10 23:18:48,147][98560] Updated weights for policy 1, policy_version 62762 (0.0008) -[2023-10-10 23:18:48,507][98560] Updated weights for policy 1, policy_version 62772 (0.0008) -[2023-10-10 23:18:48,878][98560] Updated weights for policy 1, policy_version 62782 (0.0008) -[2023-10-10 23:18:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 128942080. Throughput: 0: 1726.2, 1: 1691.0. Samples: 32247444. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-10 23:18:50,556][97672] Avg episode reward: [(0, '-1.840'), (1, '22.680')] -[2023-10-10 23:18:50,977][98559] Updated weights for policy 0, policy_version 63140 (0.0007) -[2023-10-10 23:18:51,346][98559] Updated weights for policy 0, policy_version 63150 (0.0008) -[2023-10-10 23:18:51,710][98559] Updated weights for policy 0, policy_version 63160 (0.0008) -[2023-10-10 23:18:53,002][98560] Updated weights for policy 1, policy_version 62792 (0.0009) -[2023-10-10 23:18:53,376][98560] Updated weights for policy 1, policy_version 62802 (0.0009) -[2023-10-10 23:18:53,743][98560] Updated weights for policy 1, policy_version 62812 (0.0007) -[2023-10-10 23:18:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 129007616. Throughput: 0: 1714.8, 1: 1712.0. Samples: 32257904. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-10 23:18:55,557][97672] Avg episode reward: [(0, '-1.840'), (1, '22.700')] -[2023-10-10 23:18:55,799][98559] Updated weights for policy 0, policy_version 63170 (0.0008) -[2023-10-10 23:18:56,207][98559] Updated weights for policy 0, policy_version 63180 (0.0009) -[2023-10-10 23:18:56,567][98559] Updated weights for policy 0, policy_version 63190 (0.0008) -[2023-10-10 23:18:56,935][98559] Updated weights for policy 0, policy_version 63200 (0.0008) -[2023-10-10 23:18:57,810][98560] Updated weights for policy 1, policy_version 62822 (0.0008) -[2023-10-10 23:18:58,182][98560] Updated weights for policy 1, policy_version 62832 (0.0007) -[2023-10-10 23:18:58,550][98560] Updated weights for policy 1, policy_version 62842 (0.0009) -[2023-10-10 23:19:00,556][97672] Fps is (10 sec: 13106.7, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 129073152. Throughput: 0: 1727.5, 1: 1684.1. Samples: 32277586. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-10 23:19:00,557][97672] Avg episode reward: [(0, '-1.860'), (1, '22.660')] -[2023-10-10 23:19:00,915][98559] Updated weights for policy 0, policy_version 63210 (0.0007) -[2023-10-10 23:19:01,276][98559] Updated weights for policy 0, policy_version 63220 (0.0007) -[2023-10-10 23:19:01,645][98559] Updated weights for policy 0, policy_version 63230 (0.0008) -[2023-10-10 23:19:02,559][98560] Updated weights for policy 1, policy_version 62852 (0.0007) -[2023-10-10 23:19:02,916][98560] Updated weights for policy 1, policy_version 62862 (0.0010) -[2023-10-10 23:19:03,285][98560] Updated weights for policy 1, policy_version 62872 (0.0010) -[2023-10-10 23:19:05,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 129138688. Throughput: 0: 1714.8, 1: 1691.6. Samples: 32297970. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-10 23:19:05,556][97672] Avg episode reward: [(0, '-1.860'), (1, '22.620')] -[2023-10-10 23:19:05,607][98559] Updated weights for policy 0, policy_version 63240 (0.0008) -[2023-10-10 23:19:05,984][98559] Updated weights for policy 0, policy_version 63250 (0.0009) -[2023-10-10 23:19:06,350][98559] Updated weights for policy 0, policy_version 63260 (0.0009) -[2023-10-10 23:19:07,288][98560] Updated weights for policy 1, policy_version 62882 (0.0010) -[2023-10-10 23:19:07,653][98560] Updated weights for policy 1, policy_version 62892 (0.0009) -[2023-10-10 23:19:08,020][98560] Updated weights for policy 1, policy_version 62902 (0.0010) -[2023-10-10 23:19:08,384][98560] Updated weights for policy 1, policy_version 62912 (0.0010) -[2023-10-10 23:19:10,223][98559] Updated weights for policy 0, policy_version 63270 (0.0008) -[2023-10-10 23:19:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 129204224. Throughput: 0: 1722.3, 1: 1681.8. Samples: 32308322. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-10 23:19:10,558][97672] Avg episode reward: [(0, '-1.860'), (1, '22.580')] -[2023-10-10 23:19:10,590][98559] Updated weights for policy 0, policy_version 63280 (0.0009) -[2023-10-10 23:19:10,945][98559] Updated weights for policy 0, policy_version 63290 (0.0009) -[2023-10-10 23:19:12,349][98560] Updated weights for policy 1, policy_version 62922 (0.0010) -[2023-10-10 23:19:12,708][98560] Updated weights for policy 1, policy_version 62932 (0.0009) -[2023-10-10 23:19:13,078][98560] Updated weights for policy 1, policy_version 62942 (0.0009) -[2023-10-10 23:19:14,982][98559] Updated weights for policy 0, policy_version 63300 (0.0008) -[2023-10-10 23:19:15,345][98559] Updated weights for policy 0, policy_version 63310 (0.0010) -[2023-10-10 23:19:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 129269760. Throughput: 0: 1722.6, 1: 1678.6. Samples: 32328934. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-10 23:19:15,556][97672] Avg episode reward: [(0, '-1.860'), (1, '22.460')] -[2023-10-10 23:19:15,715][98559] Updated weights for policy 0, policy_version 63320 (0.0011) -[2023-10-10 23:19:17,080][98560] Updated weights for policy 1, policy_version 62952 (0.0009) -[2023-10-10 23:19:17,450][98560] Updated weights for policy 1, policy_version 62962 (0.0008) -[2023-10-10 23:19:17,814][98560] Updated weights for policy 1, policy_version 62972 (0.0008) -[2023-10-10 23:19:19,583][98559] Updated weights for policy 0, policy_version 63330 (0.0010) -[2023-10-10 23:19:19,952][98559] Updated weights for policy 0, policy_version 63340 (0.0009) -[2023-10-10 23:19:20,316][98559] Updated weights for policy 0, policy_version 63350 (0.0010) -[2023-10-10 23:19:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 129335296. Throughput: 0: 1707.8, 1: 1694.9. Samples: 32349360. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-10 23:19:20,557][97672] Avg episode reward: [(0, '-1.860'), (1, '22.380')] -[2023-10-10 23:19:20,684][98559] Updated weights for policy 0, policy_version 63360 (0.0009) -[2023-10-10 23:19:21,768][98560] Updated weights for policy 1, policy_version 62982 (0.0009) -[2023-10-10 23:19:22,137][98560] Updated weights for policy 1, policy_version 62992 (0.0009) -[2023-10-10 23:19:22,509][98560] Updated weights for policy 1, policy_version 63002 (0.0010) -[2023-10-10 23:19:24,831][98559] Updated weights for policy 0, policy_version 63370 (0.0010) -[2023-10-10 23:19:25,193][98559] Updated weights for policy 0, policy_version 63380 (0.0009) -[2023-10-10 23:19:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 129400832. Throughput: 0: 1724.5, 1: 1668.6. Samples: 32359708. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-10 23:19:25,557][97672] Avg episode reward: [(0, '-1.860'), (1, '22.340')] -[2023-10-10 23:19:25,560][98559] Updated weights for policy 0, policy_version 63390 (0.0010) -[2023-10-10 23:19:26,488][98560] Updated weights for policy 1, policy_version 63012 (0.0011) -[2023-10-10 23:19:26,862][98560] Updated weights for policy 1, policy_version 63022 (0.0008) -[2023-10-10 23:19:27,219][98560] Updated weights for policy 1, policy_version 63032 (0.0010) -[2023-10-10 23:19:29,521][98559] Updated weights for policy 0, policy_version 63400 (0.0007) -[2023-10-10 23:19:29,881][98559] Updated weights for policy 0, policy_version 63410 (0.0008) -[2023-10-10 23:19:30,247][98559] Updated weights for policy 0, policy_version 63420 (0.0007) -[2023-10-10 23:19:30,556][97672] Fps is (10 sec: 16384.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 129499136. Throughput: 0: 1721.0, 1: 1693.7. Samples: 32380620. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-10 23:19:30,556][97672] Avg episode reward: [(0, '-1.880'), (1, '22.320')] -[2023-10-10 23:19:31,349][98560] Updated weights for policy 1, policy_version 63042 (0.0009) -[2023-10-10 23:19:31,760][98560] Updated weights for policy 1, policy_version 63052 (0.0010) -[2023-10-10 23:19:32,124][98560] Updated weights for policy 1, policy_version 63062 (0.0010) -[2023-10-10 23:19:32,492][98560] Updated weights for policy 1, policy_version 63072 (0.0011) -[2023-10-10 23:19:34,061][98559] Updated weights for policy 0, policy_version 63430 (0.0008) -[2023-10-10 23:19:34,430][98559] Updated weights for policy 0, policy_version 63440 (0.0007) -[2023-10-10 23:19:34,800][98559] Updated weights for policy 0, policy_version 63450 (0.0011) -[2023-10-10 23:19:35,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 129564672. Throughput: 0: 1698.5, 1: 1700.7. Samples: 32400410. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-10 23:19:35,557][97672] Avg episode reward: [(0, '-1.880'), (1, '22.300')] -[2023-10-10 23:19:36,561][98560] Updated weights for policy 1, policy_version 63082 (0.0008) -[2023-10-10 23:19:36,942][98560] Updated weights for policy 1, policy_version 63092 (0.0010) -[2023-10-10 23:19:37,306][98560] Updated weights for policy 1, policy_version 63102 (0.0010) -[2023-10-10 23:19:38,573][98559] Updated weights for policy 0, policy_version 63460 (0.0010) -[2023-10-10 23:19:38,942][98559] Updated weights for policy 0, policy_version 63470 (0.0008) -[2023-10-10 23:19:39,304][98559] Updated weights for policy 0, policy_version 63480 (0.0009) -[2023-10-10 23:19:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 129630208. Throughput: 0: 1727.7, 1: 1675.2. Samples: 32411034. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-10 23:19:40,556][97672] Avg episode reward: [(0, '-1.880'), (1, '22.220')] -[2023-10-10 23:19:41,408][98560] Updated weights for policy 1, policy_version 63112 (0.0008) -[2023-10-10 23:19:41,774][98560] Updated weights for policy 1, policy_version 63122 (0.0008) -[2023-10-10 23:19:42,141][98560] Updated weights for policy 1, policy_version 63132 (0.0009) -[2023-10-10 23:19:43,154][98559] Updated weights for policy 0, policy_version 63490 (0.0010) -[2023-10-10 23:19:43,519][98559] Updated weights for policy 0, policy_version 63500 (0.0007) -[2023-10-10 23:19:43,884][98559] Updated weights for policy 0, policy_version 63510 (0.0009) -[2023-10-10 23:19:44,240][98559] Updated weights for policy 0, policy_version 63520 (0.0009) -[2023-10-10 23:19:45,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 129695744. Throughput: 0: 1702.9, 1: 1706.2. Samples: 32430994. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-10 23:19:45,557][97672] Avg episode reward: [(0, '-1.880'), (1, '22.240')] -[2023-10-10 23:19:46,027][98560] Updated weights for policy 1, policy_version 63142 (0.0009) -[2023-10-10 23:19:46,401][98560] Updated weights for policy 1, policy_version 63152 (0.0009) -[2023-10-10 23:19:46,762][98560] Updated weights for policy 1, policy_version 63162 (0.0009) -[2023-10-10 23:19:48,349][98559] Updated weights for policy 0, policy_version 63530 (0.0010) -[2023-10-10 23:19:48,715][98559] Updated weights for policy 0, policy_version 63540 (0.0011) -[2023-10-10 23:19:49,076][98559] Updated weights for policy 0, policy_version 63550 (0.0010) -[2023-10-10 23:19:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 129761280. Throughput: 0: 1701.1, 1: 1718.2. Samples: 32451838. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-10 23:19:50,556][97672] Avg episode reward: [(0, '-1.880'), (1, '22.300')] -[2023-10-10 23:19:50,699][98560] Updated weights for policy 1, policy_version 63172 (0.0010) -[2023-10-10 23:19:51,057][98560] Updated weights for policy 1, policy_version 63182 (0.0008) -[2023-10-10 23:19:51,417][98560] Updated weights for policy 1, policy_version 63192 (0.0008) -[2023-10-10 23:19:53,021][98559] Updated weights for policy 0, policy_version 63560 (0.0009) -[2023-10-10 23:19:53,386][98559] Updated weights for policy 0, policy_version 63570 (0.0007) -[2023-10-10 23:19:53,754][98559] Updated weights for policy 0, policy_version 63580 (0.0008) -[2023-10-10 23:19:55,435][98560] Updated weights for policy 1, policy_version 63202 (0.0008) -[2023-10-10 23:19:55,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 129826816. Throughput: 0: 1715.7, 1: 1697.5. Samples: 32461918. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-10 23:19:55,556][97672] Avg episode reward: [(0, '-1.900'), (1, '22.340')] -[2023-10-10 23:19:55,800][98560] Updated weights for policy 1, policy_version 63212 (0.0007) -[2023-10-10 23:19:56,167][98560] Updated weights for policy 1, policy_version 63222 (0.0008) -[2023-10-10 23:19:56,523][98560] Updated weights for policy 1, policy_version 63232 (0.0007) -[2023-10-10 23:19:57,835][98559] Updated weights for policy 0, policy_version 63590 (0.0008) -[2023-10-10 23:19:58,205][98559] Updated weights for policy 0, policy_version 63600 (0.0008) -[2023-10-10 23:19:58,575][98559] Updated weights for policy 0, policy_version 63610 (0.0009) -[2023-10-10 23:20:00,288][98560] Updated weights for policy 1, policy_version 63242 (0.0007) -[2023-10-10 23:20:00,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 129892352. Throughput: 0: 1697.1, 1: 1714.8. Samples: 32482470. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-10 23:20:00,557][97672] Avg episode reward: [(0, '-1.920'), (1, '22.380')] -[2023-10-10 23:20:00,664][98560] Updated weights for policy 1, policy_version 63252 (0.0010) -[2023-10-10 23:20:01,023][98560] Updated weights for policy 1, policy_version 63262 (0.0011) -[2023-10-10 23:20:02,719][98559] Updated weights for policy 0, policy_version 63620 (0.0009) -[2023-10-10 23:20:03,075][98559] Updated weights for policy 0, policy_version 63630 (0.0008) -[2023-10-10 23:20:03,441][98559] Updated weights for policy 0, policy_version 63640 (0.0007) -[2023-10-10 23:20:04,914][98560] Updated weights for policy 1, policy_version 63272 (0.0008) -[2023-10-10 23:20:05,278][98560] Updated weights for policy 1, policy_version 63282 (0.0010) -[2023-10-10 23:20:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 129957888. Throughput: 0: 1712.8, 1: 1716.3. Samples: 32503668. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-10 23:20:05,556][97672] Avg episode reward: [(0, '-1.980'), (1, '22.400')] -[2023-10-10 23:20:05,648][98560] Updated weights for policy 1, policy_version 63292 (0.0008) -[2023-10-10 23:20:07,447][98559] Updated weights for policy 0, policy_version 63650 (0.0007) -[2023-10-10 23:20:07,818][98559] Updated weights for policy 0, policy_version 63660 (0.0008) -[2023-10-10 23:20:08,185][98559] Updated weights for policy 0, policy_version 63670 (0.0008) -[2023-10-10 23:20:08,546][98559] Updated weights for policy 0, policy_version 63680 (0.0010) -[2023-10-10 23:20:09,554][98560] Updated weights for policy 1, policy_version 63302 (0.0008) -[2023-10-10 23:20:09,923][98560] Updated weights for policy 1, policy_version 63312 (0.0008) -[2023-10-10 23:20:10,292][98560] Updated weights for policy 1, policy_version 63322 (0.0007) -[2023-10-10 23:20:10,556][97672] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 130056192. Throughput: 0: 1698.3, 1: 1712.4. Samples: 32513192. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-10 23:20:10,557][97672] Avg episode reward: [(0, '-1.980'), (1, '22.440')] -[2023-10-10 23:20:12,506][98559] Updated weights for policy 0, policy_version 63690 (0.0007) -[2023-10-10 23:20:12,871][98559] Updated weights for policy 0, policy_version 63700 (0.0009) -[2023-10-10 23:20:13,232][98559] Updated weights for policy 0, policy_version 63710 (0.0011) -[2023-10-10 23:20:14,268][98560] Updated weights for policy 1, policy_version 63332 (0.0010) -[2023-10-10 23:20:14,631][98560] Updated weights for policy 1, policy_version 63342 (0.0010) -[2023-10-10 23:20:14,998][98560] Updated weights for policy 1, policy_version 63352 (0.0009) -[2023-10-10 23:20:15,556][97672] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 130121728. Throughput: 0: 1695.4, 1: 1717.2. Samples: 32534190. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-10 23:20:15,557][97672] Avg episode reward: [(0, '-1.980'), (1, '22.420')] -[2023-10-10 23:20:17,256][98559] Updated weights for policy 0, policy_version 63720 (0.0009) -[2023-10-10 23:20:17,634][98559] Updated weights for policy 0, policy_version 63730 (0.0012) -[2023-10-10 23:20:18,004][98559] Updated weights for policy 0, policy_version 63740 (0.0008) -[2023-10-10 23:20:19,198][98560] Updated weights for policy 1, policy_version 63362 (0.0008) -[2023-10-10 23:20:19,620][98560] Updated weights for policy 1, policy_version 63372 (0.0008) -[2023-10-10 23:20:19,987][98560] Updated weights for policy 1, policy_version 63382 (0.0008) -[2023-10-10 23:20:20,356][98560] Updated weights for policy 1, policy_version 63392 (0.0009) -[2023-10-10 23:20:20,556][97672] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 130187264. Throughput: 0: 1716.6, 1: 1703.0. Samples: 32554294. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-10 23:20:20,557][97672] Avg episode reward: [(0, '-1.980'), (1, '22.460')] -[2023-10-10 23:20:21,921][98559] Updated weights for policy 0, policy_version 63750 (0.0008) -[2023-10-10 23:20:22,289][98559] Updated weights for policy 0, policy_version 63760 (0.0007) -[2023-10-10 23:20:22,661][98559] Updated weights for policy 0, policy_version 63770 (0.0007) -[2023-10-10 23:20:24,412][98560] Updated weights for policy 1, policy_version 63402 (0.0010) -[2023-10-10 23:20:24,776][98560] Updated weights for policy 1, policy_version 63412 (0.0007) -[2023-10-10 23:20:25,155][98560] Updated weights for policy 1, policy_version 63422 (0.0007) -[2023-10-10 23:20:25,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 130252800. Throughput: 0: 1690.0, 1: 1713.9. Samples: 32564210. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-10 23:20:25,556][97672] Avg episode reward: [(0, '-1.980'), (1, '22.480')] -[2023-10-10 23:20:26,837][98559] Updated weights for policy 0, policy_version 63780 (0.0007) -[2023-10-10 23:20:27,205][98559] Updated weights for policy 0, policy_version 63790 (0.0008) -[2023-10-10 23:20:27,574][98559] Updated weights for policy 0, policy_version 63800 (0.0008) -[2023-10-10 23:20:29,152][98560] Updated weights for policy 1, policy_version 63432 (0.0009) -[2023-10-10 23:20:29,526][98560] Updated weights for policy 1, policy_version 63442 (0.0007) -[2023-10-10 23:20:29,886][98560] Updated weights for policy 1, policy_version 63452 (0.0008) -[2023-10-10 23:20:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 130318336. Throughput: 0: 1714.3, 1: 1711.2. Samples: 32585138. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-10 23:20:30,557][97672] Avg episode reward: [(0, '-1.980'), (1, '22.580')] -[2023-10-10 23:20:31,738][98559] Updated weights for policy 0, policy_version 63810 (0.0010) -[2023-10-10 23:20:32,147][98559] Updated weights for policy 0, policy_version 63820 (0.0007) -[2023-10-10 23:20:32,515][98559] Updated weights for policy 0, policy_version 63830 (0.0008) -[2023-10-10 23:20:32,885][98559] Updated weights for policy 0, policy_version 63840 (0.0009) -[2023-10-10 23:20:33,779][98560] Updated weights for policy 1, policy_version 63462 (0.0007) -[2023-10-10 23:20:34,152][98560] Updated weights for policy 1, policy_version 63472 (0.0008) -[2023-10-10 23:20:34,512][98560] Updated weights for policy 1, policy_version 63482 (0.0008) -[2023-10-10 23:20:35,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 130383872. Throughput: 0: 1714.9, 1: 1685.0. Samples: 32604834. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-10 23:20:35,557][97672] Avg episode reward: [(0, '-1.980'), (1, '22.520')] -[2023-10-10 23:20:35,567][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000063840_65372160.pth... -[2023-10-10 23:20:35,567][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000063488_65011712.pth... -[2023-10-10 23:20:35,604][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000061888_63373312.pth -[2023-10-10 23:20:35,607][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000062240_63733760.pth -[2023-10-10 23:20:35,608][98439] Saving a milestone ./train_atari/atari_doubledunk_APPO/checkpoint_p1/milestones/checkpoint_000063488_65011712.pth -[2023-10-10 23:20:35,611][98385] Saving a milestone ./train_atari/atari_doubledunk_APPO/checkpoint_p0/milestones/checkpoint_000063840_65372160.pth -[2023-10-10 23:20:36,775][98559] Updated weights for policy 0, policy_version 63850 (0.0010) -[2023-10-10 23:20:37,144][98559] Updated weights for policy 0, policy_version 63860 (0.0011) -[2023-10-10 23:20:37,516][98559] Updated weights for policy 0, policy_version 63870 (0.0010) -[2023-10-10 23:20:38,689][98560] Updated weights for policy 1, policy_version 63492 (0.0007) -[2023-10-10 23:20:39,059][98560] Updated weights for policy 1, policy_version 63502 (0.0008) -[2023-10-10 23:20:39,421][98560] Updated weights for policy 1, policy_version 63512 (0.0008) -[2023-10-10 23:20:40,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 130449408. Throughput: 0: 1695.0, 1: 1713.5. Samples: 32615302. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 23:20:40,557][97672] Avg episode reward: [(0, '-1.980'), (1, '22.500')] -[2023-10-10 23:20:41,475][98559] Updated weights for policy 0, policy_version 63880 (0.0009) -[2023-10-10 23:20:41,843][98559] Updated weights for policy 0, policy_version 63890 (0.0008) -[2023-10-10 23:20:42,214][98559] Updated weights for policy 0, policy_version 63900 (0.0008) -[2023-10-10 23:20:43,648][98560] Updated weights for policy 1, policy_version 63522 (0.0009) -[2023-10-10 23:20:44,011][98560] Updated weights for policy 1, policy_version 63532 (0.0008) -[2023-10-10 23:20:44,367][98560] Updated weights for policy 1, policy_version 63542 (0.0008) -[2023-10-10 23:20:44,737][98560] Updated weights for policy 1, policy_version 63552 (0.0007) -[2023-10-10 23:20:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 130514944. Throughput: 0: 1713.1, 1: 1704.9. Samples: 32636280. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 23:20:45,556][97672] Avg episode reward: [(0, '-1.980'), (1, '22.500')] -[2023-10-10 23:20:46,079][98559] Updated weights for policy 0, policy_version 63910 (0.0008) -[2023-10-10 23:20:46,453][98559] Updated weights for policy 0, policy_version 63920 (0.0009) -[2023-10-10 23:20:46,823][98559] Updated weights for policy 0, policy_version 63930 (0.0007) -[2023-10-10 23:20:48,778][98560] Updated weights for policy 1, policy_version 63562 (0.0010) -[2023-10-10 23:20:49,139][98560] Updated weights for policy 1, policy_version 63572 (0.0008) -[2023-10-10 23:20:49,497][98560] Updated weights for policy 1, policy_version 63582 (0.0007) -[2023-10-10 23:20:50,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.2, 300 sec: 13662.6). Total num frames: 130580480. Throughput: 0: 1711.1, 1: 1676.6. Samples: 32656120. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 23:20:50,558][97672] Avg episode reward: [(0, '-1.980'), (1, '22.540')] -[2023-10-10 23:20:50,842][98559] Updated weights for policy 0, policy_version 63940 (0.0008) -[2023-10-10 23:20:51,212][98559] Updated weights for policy 0, policy_version 63950 (0.0007) -[2023-10-10 23:20:51,570][98559] Updated weights for policy 0, policy_version 63960 (0.0008) -[2023-10-10 23:20:53,280][98560] Updated weights for policy 1, policy_version 63592 (0.0009) -[2023-10-10 23:20:53,650][98560] Updated weights for policy 1, policy_version 63602 (0.0010) -[2023-10-10 23:20:54,025][98560] Updated weights for policy 1, policy_version 63612 (0.0008) -[2023-10-10 23:20:55,545][98559] Updated weights for policy 0, policy_version 63970 (0.0007) -[2023-10-10 23:20:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 130646016. Throughput: 0: 1707.0, 1: 1708.5. Samples: 32666890. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 23:20:55,557][97672] Avg episode reward: [(0, '-1.980'), (1, '22.500')] -[2023-10-10 23:20:55,911][98559] Updated weights for policy 0, policy_version 63980 (0.0007) -[2023-10-10 23:20:56,278][98559] Updated weights for policy 0, policy_version 63990 (0.0008) -[2023-10-10 23:20:56,636][98559] Updated weights for policy 0, policy_version 64000 (0.0008) -[2023-10-10 23:20:57,990][98560] Updated weights for policy 1, policy_version 63622 (0.0010) -[2023-10-10 23:20:58,356][98560] Updated weights for policy 1, policy_version 63632 (0.0009) -[2023-10-10 23:20:58,731][98560] Updated weights for policy 1, policy_version 63642 (0.0008) -[2023-10-10 23:21:00,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 130711552. Throughput: 0: 1715.4, 1: 1679.3. Samples: 32686950. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 23:21:00,557][97672] Avg episode reward: [(0, '-1.980'), (1, '22.500')] -[2023-10-10 23:21:00,604][98559] Updated weights for policy 0, policy_version 64010 (0.0008) -[2023-10-10 23:21:00,969][98559] Updated weights for policy 0, policy_version 64020 (0.0010) -[2023-10-10 23:21:01,327][98559] Updated weights for policy 0, policy_version 64030 (0.0011) -[2023-10-10 23:21:02,927][98560] Updated weights for policy 1, policy_version 63652 (0.0009) -[2023-10-10 23:21:03,285][98560] Updated weights for policy 1, policy_version 63662 (0.0007) -[2023-10-10 23:21:03,656][98560] Updated weights for policy 1, policy_version 63672 (0.0007) -[2023-10-10 23:21:05,295][98559] Updated weights for policy 0, policy_version 64040 (0.0008) -[2023-10-10 23:21:05,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 130777088. Throughput: 0: 1708.0, 1: 1690.2. Samples: 32707212. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 23:21:05,556][97672] Avg episode reward: [(0, '-1.980'), (1, '22.540')] -[2023-10-10 23:21:05,663][98559] Updated weights for policy 0, policy_version 64050 (0.0007) -[2023-10-10 23:21:06,032][98559] Updated weights for policy 0, policy_version 64060 (0.0009) -[2023-10-10 23:21:07,560][98560] Updated weights for policy 1, policy_version 63682 (0.0008) -[2023-10-10 23:21:07,989][98560] Updated weights for policy 1, policy_version 63692 (0.0008) -[2023-10-10 23:21:08,352][98560] Updated weights for policy 1, policy_version 63702 (0.0009) -[2023-10-10 23:21:08,720][98560] Updated weights for policy 1, policy_version 63712 (0.0008) -[2023-10-10 23:21:09,916][98559] Updated weights for policy 0, policy_version 64070 (0.0010) -[2023-10-10 23:21:10,283][98559] Updated weights for policy 0, policy_version 64080 (0.0011) -[2023-10-10 23:21:10,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 130842624. Throughput: 0: 1713.2, 1: 1701.7. Samples: 32717880. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 23:21:10,557][97672] Avg episode reward: [(0, '-1.980'), (1, '22.540')] -[2023-10-10 23:21:10,653][98559] Updated weights for policy 0, policy_version 64090 (0.0009) -[2023-10-10 23:21:12,723][98560] Updated weights for policy 1, policy_version 63722 (0.0008) -[2023-10-10 23:21:13,081][98560] Updated weights for policy 1, policy_version 63732 (0.0007) -[2023-10-10 23:21:13,456][98560] Updated weights for policy 1, policy_version 63742 (0.0008) -[2023-10-10 23:21:14,748][98559] Updated weights for policy 0, policy_version 64100 (0.0009) -[2023-10-10 23:21:15,109][98559] Updated weights for policy 0, policy_version 64110 (0.0010) -[2023-10-10 23:21:15,482][98559] Updated weights for policy 0, policy_version 64120 (0.0010) -[2023-10-10 23:21:15,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 130908160. Throughput: 0: 1714.8, 1: 1677.5. Samples: 32737794. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 23:21:15,557][97672] Avg episode reward: [(0, '-1.980'), (1, '22.560')] -[2023-10-10 23:21:17,530][98560] Updated weights for policy 1, policy_version 63752 (0.0009) -[2023-10-10 23:21:17,896][98560] Updated weights for policy 1, policy_version 63762 (0.0009) -[2023-10-10 23:21:18,266][98560] Updated weights for policy 1, policy_version 63772 (0.0010) -[2023-10-10 23:21:19,555][98559] Updated weights for policy 0, policy_version 64130 (0.0007) -[2023-10-10 23:21:19,946][98559] Updated weights for policy 0, policy_version 64140 (0.0009) -[2023-10-10 23:21:20,317][98559] Updated weights for policy 0, policy_version 64150 (0.0009) -[2023-10-10 23:21:20,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 130973696. Throughput: 0: 1696.4, 1: 1704.7. Samples: 32757882. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 23:21:20,557][97672] Avg episode reward: [(0, '-1.980'), (1, '22.540')] -[2023-10-10 23:21:20,687][98559] Updated weights for policy 0, policy_version 64160 (0.0009) -[2023-10-10 23:21:22,310][98560] Updated weights for policy 1, policy_version 63782 (0.0010) -[2023-10-10 23:21:22,678][98560] Updated weights for policy 1, policy_version 63792 (0.0008) -[2023-10-10 23:21:23,039][98560] Updated weights for policy 1, policy_version 63802 (0.0007) -[2023-10-10 23:21:24,670][98559] Updated weights for policy 0, policy_version 64170 (0.0011) -[2023-10-10 23:21:25,035][98559] Updated weights for policy 0, policy_version 64180 (0.0010) -[2023-10-10 23:21:25,404][98559] Updated weights for policy 0, policy_version 64190 (0.0009) -[2023-10-10 23:21:25,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 131072000. Throughput: 0: 1718.9, 1: 1689.1. Samples: 32768660. Policy #0 lag: (min: 26.0, avg: 26.3, max: 37.0) -[2023-10-10 23:21:25,557][97672] Avg episode reward: [(0, '-1.940'), (1, '22.580')] -[2023-10-10 23:21:27,089][98560] Updated weights for policy 1, policy_version 63812 (0.0008) -[2023-10-10 23:21:27,467][98560] Updated weights for policy 1, policy_version 63822 (0.0010) -[2023-10-10 23:21:27,837][98560] Updated weights for policy 1, policy_version 63832 (0.0011) -[2023-10-10 23:21:29,354][98559] Updated weights for policy 0, policy_version 64200 (0.0008) -[2023-10-10 23:21:29,723][98559] Updated weights for policy 0, policy_version 64210 (0.0010) -[2023-10-10 23:21:30,088][98559] Updated weights for policy 0, policy_version 64220 (0.0008) -[2023-10-10 23:21:30,556][97672] Fps is (10 sec: 16384.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 131137536. Throughput: 0: 1711.3, 1: 1679.3. Samples: 32788858. Policy #0 lag: (min: 26.0, avg: 26.3, max: 37.0) -[2023-10-10 23:21:30,557][97672] Avg episode reward: [(0, '-1.940'), (1, '22.540')] -[2023-10-10 23:21:31,618][98560] Updated weights for policy 1, policy_version 63842 (0.0007) -[2023-10-10 23:21:31,983][98560] Updated weights for policy 1, policy_version 63852 (0.0008) -[2023-10-10 23:21:32,348][98560] Updated weights for policy 1, policy_version 63862 (0.0010) -[2023-10-10 23:21:32,713][98560] Updated weights for policy 1, policy_version 63872 (0.0010) -[2023-10-10 23:21:34,111][98559] Updated weights for policy 0, policy_version 64230 (0.0008) -[2023-10-10 23:21:34,466][98559] Updated weights for policy 0, policy_version 64240 (0.0008) -[2023-10-10 23:21:34,847][98559] Updated weights for policy 0, policy_version 64250 (0.0011) -[2023-10-10 23:21:35,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 131203072. Throughput: 0: 1687.1, 1: 1708.6. Samples: 32808926. Policy #0 lag: (min: 26.0, avg: 26.3, max: 37.0) -[2023-10-10 23:21:35,556][97672] Avg episode reward: [(0, '-1.980'), (1, '22.480')] -[2023-10-10 23:21:36,899][98560] Updated weights for policy 1, policy_version 63882 (0.0007) -[2023-10-10 23:21:37,263][98560] Updated weights for policy 1, policy_version 63892 (0.0009) -[2023-10-10 23:21:37,638][98560] Updated weights for policy 1, policy_version 63902 (0.0008) -[2023-10-10 23:21:38,847][98559] Updated weights for policy 0, policy_version 64260 (0.0010) -[2023-10-10 23:21:39,216][98559] Updated weights for policy 0, policy_version 64270 (0.0009) -[2023-10-10 23:21:39,590][98559] Updated weights for policy 0, policy_version 64280 (0.0008) -[2023-10-10 23:21:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 131268608. Throughput: 0: 1714.6, 1: 1676.9. Samples: 32819508. Policy #0 lag: (min: 26.0, avg: 26.3, max: 37.0) -[2023-10-10 23:21:40,557][97672] Avg episode reward: [(0, '-1.980'), (1, '22.520')] -[2023-10-10 23:21:41,630][98560] Updated weights for policy 1, policy_version 63912 (0.0009) -[2023-10-10 23:21:42,000][98560] Updated weights for policy 1, policy_version 63922 (0.0008) -[2023-10-10 23:21:42,372][98560] Updated weights for policy 1, policy_version 63932 (0.0008) -[2023-10-10 23:21:43,647][98559] Updated weights for policy 0, policy_version 64290 (0.0010) -[2023-10-10 23:21:44,008][98559] Updated weights for policy 0, policy_version 64300 (0.0008) -[2023-10-10 23:21:44,374][98559] Updated weights for policy 0, policy_version 64310 (0.0010) -[2023-10-10 23:21:44,745][98559] Updated weights for policy 0, policy_version 64320 (0.0008) -[2023-10-10 23:21:45,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 131334144. Throughput: 0: 1690.4, 1: 1702.7. Samples: 32839642. Policy #0 lag: (min: 26.0, avg: 26.3, max: 37.0) -[2023-10-10 23:21:45,557][97672] Avg episode reward: [(0, '-1.980'), (1, '22.520')] -[2023-10-10 23:21:46,505][98560] Updated weights for policy 1, policy_version 63942 (0.0008) -[2023-10-10 23:21:46,868][98560] Updated weights for policy 1, policy_version 63952 (0.0010) -[2023-10-10 23:21:47,236][98560] Updated weights for policy 1, policy_version 63962 (0.0009) -[2023-10-10 23:21:48,847][98559] Updated weights for policy 0, policy_version 64330 (0.0011) -[2023-10-10 23:21:49,214][98559] Updated weights for policy 0, policy_version 64340 (0.0010) -[2023-10-10 23:21:49,583][98559] Updated weights for policy 0, policy_version 64350 (0.0011) -[2023-10-10 23:21:50,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 131399680. Throughput: 0: 1682.6, 1: 1709.4. Samples: 32859852. Policy #0 lag: (min: 26.0, avg: 26.3, max: 37.0) -[2023-10-10 23:21:50,558][97672] Avg episode reward: [(0, '-1.980'), (1, '22.500')] -[2023-10-10 23:21:51,197][98560] Updated weights for policy 1, policy_version 63972 (0.0009) -[2023-10-10 23:21:51,565][98560] Updated weights for policy 1, policy_version 63982 (0.0008) -[2023-10-10 23:21:51,931][98560] Updated weights for policy 1, policy_version 63992 (0.0010) -[2023-10-10 23:21:53,523][98559] Updated weights for policy 0, policy_version 64360 (0.0009) -[2023-10-10 23:21:53,890][98559] Updated weights for policy 0, policy_version 64370 (0.0009) -[2023-10-10 23:21:54,250][98559] Updated weights for policy 0, policy_version 64380 (0.0008) -[2023-10-10 23:21:55,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 131465216. Throughput: 0: 1699.8, 1: 1684.2. Samples: 32870162. Policy #0 lag: (min: 26.0, avg: 26.3, max: 37.0) -[2023-10-10 23:21:55,557][97672] Avg episode reward: [(0, '-1.980'), (1, '22.460')] -[2023-10-10 23:21:55,951][98560] Updated weights for policy 1, policy_version 64002 (0.0009) -[2023-10-10 23:21:56,378][98560] Updated weights for policy 1, policy_version 64012 (0.0007) -[2023-10-10 23:21:56,752][98560] Updated weights for policy 1, policy_version 64022 (0.0007) -[2023-10-10 23:21:57,106][98560] Updated weights for policy 1, policy_version 64032 (0.0008) -[2023-10-10 23:21:58,360][98559] Updated weights for policy 0, policy_version 64390 (0.0009) -[2023-10-10 23:21:58,732][98559] Updated weights for policy 0, policy_version 64400 (0.0007) -[2023-10-10 23:21:59,097][98559] Updated weights for policy 0, policy_version 64410 (0.0008) -[2023-10-10 23:22:00,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 131530752. Throughput: 0: 1675.0, 1: 1702.1. Samples: 32889764. Policy #0 lag: (min: 26.0, avg: 26.3, max: 37.0) -[2023-10-10 23:22:00,557][97672] Avg episode reward: [(0, '-1.980'), (1, '22.440')] -[2023-10-10 23:22:01,167][98560] Updated weights for policy 1, policy_version 64042 (0.0008) -[2023-10-10 23:22:01,541][98560] Updated weights for policy 1, policy_version 64052 (0.0010) -[2023-10-10 23:22:01,898][98560] Updated weights for policy 1, policy_version 64062 (0.0008) -[2023-10-10 23:22:03,177][98559] Updated weights for policy 0, policy_version 64420 (0.0008) -[2023-10-10 23:22:03,549][98559] Updated weights for policy 0, policy_version 64430 (0.0009) -[2023-10-10 23:22:03,916][98559] Updated weights for policy 0, policy_version 64440 (0.0011) -[2023-10-10 23:22:05,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 131596288. Throughput: 0: 1694.1, 1: 1704.1. Samples: 32910802. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:22:05,557][97672] Avg episode reward: [(0, '-1.980'), (1, '22.480')] -[2023-10-10 23:22:05,895][98560] Updated weights for policy 1, policy_version 64072 (0.0007) -[2023-10-10 23:22:06,253][98560] Updated weights for policy 1, policy_version 64082 (0.0007) -[2023-10-10 23:22:06,633][98560] Updated weights for policy 1, policy_version 64092 (0.0007) -[2023-10-10 23:22:07,874][98559] Updated weights for policy 0, policy_version 64450 (0.0009) -[2023-10-10 23:22:08,272][98559] Updated weights for policy 0, policy_version 64460 (0.0011) -[2023-10-10 23:22:08,630][98559] Updated weights for policy 0, policy_version 64470 (0.0008) -[2023-10-10 23:22:09,002][98559] Updated weights for policy 0, policy_version 64480 (0.0007) -[2023-10-10 23:22:10,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 131661824. Throughput: 0: 1687.2, 1: 1691.0. Samples: 32920676. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:22:10,557][97672] Avg episode reward: [(0, '-1.980'), (1, '22.460')] -[2023-10-10 23:22:10,770][98560] Updated weights for policy 1, policy_version 64102 (0.0009) -[2023-10-10 23:22:11,126][98560] Updated weights for policy 1, policy_version 64112 (0.0009) -[2023-10-10 23:22:11,488][98560] Updated weights for policy 1, policy_version 64122 (0.0010) -[2023-10-10 23:22:12,972][98559] Updated weights for policy 0, policy_version 64490 (0.0009) -[2023-10-10 23:22:13,345][98559] Updated weights for policy 0, policy_version 64500 (0.0008) -[2023-10-10 23:22:13,713][98559] Updated weights for policy 0, policy_version 64510 (0.0010) -[2023-10-10 23:22:15,523][98560] Updated weights for policy 1, policy_version 64132 (0.0007) -[2023-10-10 23:22:15,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 131727360. Throughput: 0: 1679.7, 1: 1700.7. Samples: 32940976. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:22:15,557][97672] Avg episode reward: [(0, '-1.980'), (1, '22.500')] -[2023-10-10 23:22:15,890][98560] Updated weights for policy 1, policy_version 64142 (0.0007) -[2023-10-10 23:22:16,267][98560] Updated weights for policy 1, policy_version 64152 (0.0008) -[2023-10-10 23:22:17,651][98559] Updated weights for policy 0, policy_version 64520 (0.0008) -[2023-10-10 23:22:18,015][98559] Updated weights for policy 0, policy_version 64530 (0.0008) -[2023-10-10 23:22:18,379][98559] Updated weights for policy 0, policy_version 64540 (0.0007) -[2023-10-10 23:22:20,446][98560] Updated weights for policy 1, policy_version 64162 (0.0009) -[2023-10-10 23:22:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 131792896. Throughput: 0: 1702.8, 1: 1692.8. Samples: 32961726. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:22:20,557][97672] Avg episode reward: [(0, '-1.980'), (1, '22.540')] -[2023-10-10 23:22:20,815][98560] Updated weights for policy 1, policy_version 64172 (0.0007) -[2023-10-10 23:22:21,187][98560] Updated weights for policy 1, policy_version 64182 (0.0007) -[2023-10-10 23:22:21,553][98560] Updated weights for policy 1, policy_version 64192 (0.0008) -[2023-10-10 23:22:22,345][98559] Updated weights for policy 0, policy_version 64550 (0.0007) -[2023-10-10 23:22:22,711][98559] Updated weights for policy 0, policy_version 64560 (0.0008) -[2023-10-10 23:22:23,087][98559] Updated weights for policy 0, policy_version 64570 (0.0009) -[2023-10-10 23:22:25,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 131858432. Throughput: 0: 1677.1, 1: 1692.5. Samples: 32971140. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:22:25,556][97672] Avg episode reward: [(0, '-1.980'), (1, '22.540')] -[2023-10-10 23:22:25,559][98560] Updated weights for policy 1, policy_version 64202 (0.0010) -[2023-10-10 23:22:25,927][98560] Updated weights for policy 1, policy_version 64212 (0.0007) -[2023-10-10 23:22:26,301][98560] Updated weights for policy 1, policy_version 64222 (0.0008) -[2023-10-10 23:22:27,100][98559] Updated weights for policy 0, policy_version 64580 (0.0010) -[2023-10-10 23:22:27,464][98559] Updated weights for policy 0, policy_version 64590 (0.0009) -[2023-10-10 23:22:27,843][98559] Updated weights for policy 0, policy_version 64600 (0.0011) -[2023-10-10 23:22:30,332][98560] Updated weights for policy 1, policy_version 64232 (0.0010) -[2023-10-10 23:22:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 131923968. Throughput: 0: 1702.9, 1: 1690.6. Samples: 32992352. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:22:30,556][97672] Avg episode reward: [(0, '-2.000'), (1, '22.480')] -[2023-10-10 23:22:30,697][98560] Updated weights for policy 1, policy_version 64242 (0.0008) -[2023-10-10 23:22:31,075][98560] Updated weights for policy 1, policy_version 64252 (0.0008) -[2023-10-10 23:22:31,784][98559] Updated weights for policy 0, policy_version 64610 (0.0009) -[2023-10-10 23:22:32,152][98559] Updated weights for policy 0, policy_version 64620 (0.0009) -[2023-10-10 23:22:32,523][98559] Updated weights for policy 0, policy_version 64630 (0.0009) -[2023-10-10 23:22:32,894][98559] Updated weights for policy 0, policy_version 64640 (0.0007) -[2023-10-10 23:22:35,139][98560] Updated weights for policy 1, policy_version 64262 (0.0009) -[2023-10-10 23:22:35,503][98560] Updated weights for policy 1, policy_version 64272 (0.0009) -[2023-10-10 23:22:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 131989504. Throughput: 0: 1724.9, 1: 1689.8. Samples: 33013512. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:22:35,556][97672] Avg episode reward: [(0, '-2.000'), (1, '22.520')] -[2023-10-10 23:22:35,565][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000064640_66191360.pth... -[2023-10-10 23:22:35,599][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000063040_64552960.pth -[2023-10-10 23:22:35,877][98560] Updated weights for policy 1, policy_version 64282 (0.0007) -[2023-10-10 23:22:36,095][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000064288_65830912.pth... -[2023-10-10 23:22:36,137][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000062688_64192512.pth -[2023-10-10 23:22:36,772][98559] Updated weights for policy 0, policy_version 64650 (0.0010) -[2023-10-10 23:22:37,133][98559] Updated weights for policy 0, policy_version 64660 (0.0009) -[2023-10-10 23:22:37,505][98559] Updated weights for policy 0, policy_version 64670 (0.0007) -[2023-10-10 23:22:39,968][98560] Updated weights for policy 1, policy_version 64292 (0.0007) -[2023-10-10 23:22:40,336][98560] Updated weights for policy 1, policy_version 64302 (0.0007) -[2023-10-10 23:22:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 132055040. Throughput: 0: 1700.1, 1: 1691.4. Samples: 33022778. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:22:40,557][97672] Avg episode reward: [(0, '-2.000'), (1, '22.560')] -[2023-10-10 23:22:40,699][98560] Updated weights for policy 1, policy_version 64312 (0.0007) -[2023-10-10 23:22:41,427][98559] Updated weights for policy 0, policy_version 64680 (0.0009) -[2023-10-10 23:22:41,789][98559] Updated weights for policy 0, policy_version 64690 (0.0008) -[2023-10-10 23:22:42,160][98559] Updated weights for policy 0, policy_version 64700 (0.0009) -[2023-10-10 23:22:44,780][98560] Updated weights for policy 1, policy_version 64322 (0.0008) -[2023-10-10 23:22:45,180][98560] Updated weights for policy 1, policy_version 64332 (0.0009) -[2023-10-10 23:22:45,542][98560] Updated weights for policy 1, policy_version 64342 (0.0008) -[2023-10-10 23:22:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 132120576. Throughput: 0: 1730.4, 1: 1697.1. Samples: 33044002. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:22:45,556][97672] Avg episode reward: [(0, '-2.000'), (1, '22.480')] -[2023-10-10 23:22:45,908][98560] Updated weights for policy 1, policy_version 64352 (0.0009) -[2023-10-10 23:22:45,980][98559] Updated weights for policy 0, policy_version 64710 (0.0009) -[2023-10-10 23:22:46,341][98559] Updated weights for policy 0, policy_version 64720 (0.0008) -[2023-10-10 23:22:46,710][98559] Updated weights for policy 0, policy_version 64730 (0.0009) -[2023-10-10 23:22:49,940][98560] Updated weights for policy 1, policy_version 64362 (0.0011) -[2023-10-10 23:22:50,303][98560] Updated weights for policy 1, policy_version 64372 (0.0009) -[2023-10-10 23:22:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 132186112. Throughput: 0: 1738.7, 1: 1686.3. Samples: 33064924. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-10 23:22:50,557][97672] Avg episode reward: [(0, '-2.000'), (1, '22.480')] -[2023-10-10 23:22:50,671][98560] Updated weights for policy 1, policy_version 64382 (0.0009) -[2023-10-10 23:22:50,675][98559] Updated weights for policy 0, policy_version 64740 (0.0008) -[2023-10-10 23:22:51,036][98559] Updated weights for policy 0, policy_version 64750 (0.0008) -[2023-10-10 23:22:51,405][98559] Updated weights for policy 0, policy_version 64760 (0.0007) -[2023-10-10 23:22:54,535][98560] Updated weights for policy 1, policy_version 64392 (0.0010) -[2023-10-10 23:22:54,894][98560] Updated weights for policy 1, policy_version 64402 (0.0009) -[2023-10-10 23:22:55,265][98560] Updated weights for policy 1, policy_version 64412 (0.0011) -[2023-10-10 23:22:55,503][98559] Updated weights for policy 0, policy_version 64770 (0.0007) -[2023-10-10 23:22:55,556][97672] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 132284416. Throughput: 0: 1722.8, 1: 1690.4. Samples: 33074270. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-10 23:22:55,557][97672] Avg episode reward: [(0, '-1.820'), (1, '22.500')] -[2023-10-10 23:22:55,909][98559] Updated weights for policy 0, policy_version 64780 (0.0007) -[2023-10-10 23:22:56,285][98559] Updated weights for policy 0, policy_version 64790 (0.0009) -[2023-10-10 23:22:56,650][98559] Updated weights for policy 0, policy_version 64800 (0.0010) -[2023-10-10 23:22:59,228][98560] Updated weights for policy 1, policy_version 64422 (0.0008) -[2023-10-10 23:22:59,593][98560] Updated weights for policy 1, policy_version 64432 (0.0008) -[2023-10-10 23:22:59,960][98560] Updated weights for policy 1, policy_version 64442 (0.0008) -[2023-10-10 23:23:00,501][98559] Updated weights for policy 0, policy_version 64810 (0.0008) -[2023-10-10 23:23:00,556][97672] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 132349952. Throughput: 0: 1733.9, 1: 1697.9. Samples: 33095408. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-10 23:23:00,556][97672] Avg episode reward: [(0, '-1.820'), (1, '22.440')] -[2023-10-10 23:23:00,856][98559] Updated weights for policy 0, policy_version 64820 (0.0008) -[2023-10-10 23:23:01,229][98559] Updated weights for policy 0, policy_version 64830 (0.0009) -[2023-10-10 23:23:03,952][98560] Updated weights for policy 1, policy_version 64452 (0.0010) -[2023-10-10 23:23:04,308][98560] Updated weights for policy 1, policy_version 64462 (0.0008) -[2023-10-10 23:23:04,679][98560] Updated weights for policy 1, policy_version 64472 (0.0008) -[2023-10-10 23:23:05,177][98559] Updated weights for policy 0, policy_version 64840 (0.0007) -[2023-10-10 23:23:05,546][98559] Updated weights for policy 0, policy_version 64850 (0.0007) -[2023-10-10 23:23:05,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 132415488. Throughput: 0: 1727.7, 1: 1683.0. Samples: 33115210. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-10 23:23:05,556][97672] Avg episode reward: [(0, '-1.820'), (1, '22.500')] -[2023-10-10 23:23:05,909][98559] Updated weights for policy 0, policy_version 64860 (0.0007) -[2023-10-10 23:23:08,746][98560] Updated weights for policy 1, policy_version 64482 (0.0008) -[2023-10-10 23:23:09,120][98560] Updated weights for policy 1, policy_version 64492 (0.0009) -[2023-10-10 23:23:09,484][98560] Updated weights for policy 1, policy_version 64502 (0.0007) -[2023-10-10 23:23:09,844][98560] Updated weights for policy 1, policy_version 64512 (0.0007) -[2023-10-10 23:23:09,874][98559] Updated weights for policy 0, policy_version 64870 (0.0008) -[2023-10-10 23:23:10,239][98559] Updated weights for policy 0, policy_version 64880 (0.0008) -[2023-10-10 23:23:10,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 132481024. Throughput: 0: 1736.4, 1: 1703.3. Samples: 33125930. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-10 23:23:10,558][97672] Avg episode reward: [(0, '-1.820'), (1, '22.480')] -[2023-10-10 23:23:10,602][98559] Updated weights for policy 0, policy_version 64890 (0.0008) -[2023-10-10 23:23:13,767][98560] Updated weights for policy 1, policy_version 64522 (0.0008) -[2023-10-10 23:23:14,132][98560] Updated weights for policy 1, policy_version 64532 (0.0007) -[2023-10-10 23:23:14,503][98560] Updated weights for policy 1, policy_version 64542 (0.0008) -[2023-10-10 23:23:14,609][98559] Updated weights for policy 0, policy_version 64900 (0.0009) -[2023-10-10 23:23:14,973][98559] Updated weights for policy 0, policy_version 64910 (0.0007) -[2023-10-10 23:23:15,335][98559] Updated weights for policy 0, policy_version 64920 (0.0011) -[2023-10-10 23:23:15,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 132546560. Throughput: 0: 1737.6, 1: 1699.6. Samples: 33147028. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-10 23:23:15,557][97672] Avg episode reward: [(0, '-1.820'), (1, '22.500')] -[2023-10-10 23:23:18,425][98560] Updated weights for policy 1, policy_version 64552 (0.0009) -[2023-10-10 23:23:18,797][98560] Updated weights for policy 1, policy_version 64562 (0.0007) -[2023-10-10 23:23:19,163][98560] Updated weights for policy 1, policy_version 64572 (0.0010) -[2023-10-10 23:23:19,435][98559] Updated weights for policy 0, policy_version 64930 (0.0010) -[2023-10-10 23:23:19,808][98559] Updated weights for policy 0, policy_version 64940 (0.0009) -[2023-10-10 23:23:20,168][98559] Updated weights for policy 0, policy_version 64950 (0.0009) -[2023-10-10 23:23:20,539][98559] Updated weights for policy 0, policy_version 64960 (0.0010) -[2023-10-10 23:23:20,556][97672] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 132644864. Throughput: 0: 1708.1, 1: 1677.4. Samples: 33165858. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-10 23:23:20,556][97672] Avg episode reward: [(0, '-1.820'), (1, '22.480')] -[2023-10-10 23:23:23,186][98560] Updated weights for policy 1, policy_version 64582 (0.0010) -[2023-10-10 23:23:23,555][98560] Updated weights for policy 1, policy_version 64592 (0.0007) -[2023-10-10 23:23:23,926][98560] Updated weights for policy 1, policy_version 64602 (0.0007) -[2023-10-10 23:23:24,440][98559] Updated weights for policy 0, policy_version 64970 (0.0010) -[2023-10-10 23:23:24,808][98559] Updated weights for policy 0, policy_version 64980 (0.0008) -[2023-10-10 23:23:25,190][98559] Updated weights for policy 0, policy_version 64990 (0.0008) -[2023-10-10 23:23:25,556][97672] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 132710400. Throughput: 0: 1730.7, 1: 1706.3. Samples: 33177442. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-10 23:23:25,557][97672] Avg episode reward: [(0, '-1.820'), (1, '22.440')] -[2023-10-10 23:23:27,973][98560] Updated weights for policy 1, policy_version 64612 (0.0010) -[2023-10-10 23:23:28,338][98560] Updated weights for policy 1, policy_version 64622 (0.0009) -[2023-10-10 23:23:28,707][98560] Updated weights for policy 1, policy_version 64632 (0.0007) -[2023-10-10 23:23:29,177][98559] Updated weights for policy 0, policy_version 65000 (0.0007) -[2023-10-10 23:23:29,545][98559] Updated weights for policy 0, policy_version 65010 (0.0007) -[2023-10-10 23:23:29,912][98559] Updated weights for policy 0, policy_version 65020 (0.0009) -[2023-10-10 23:23:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 132775936. Throughput: 0: 1717.4, 1: 1685.7. Samples: 33197142. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:23:30,556][97672] Avg episode reward: [(0, '-1.820'), (1, '22.460')] -[2023-10-10 23:23:32,812][98560] Updated weights for policy 1, policy_version 64642 (0.0007) -[2023-10-10 23:23:33,226][98560] Updated weights for policy 1, policy_version 64652 (0.0007) -[2023-10-10 23:23:33,596][98560] Updated weights for policy 1, policy_version 64662 (0.0007) -[2023-10-10 23:23:33,762][98559] Updated weights for policy 0, policy_version 65030 (0.0008) -[2023-10-10 23:23:33,956][98560] Updated weights for policy 1, policy_version 64672 (0.0009) -[2023-10-10 23:23:34,122][98559] Updated weights for policy 0, policy_version 65040 (0.0010) -[2023-10-10 23:23:34,484][98559] Updated weights for policy 0, policy_version 65050 (0.0010) -[2023-10-10 23:23:35,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 132841472. Throughput: 0: 1698.2, 1: 1679.1. Samples: 33216904. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:23:35,557][97672] Avg episode reward: [(0, '-1.780'), (1, '22.460')] -[2023-10-10 23:23:37,959][98560] Updated weights for policy 1, policy_version 64682 (0.0009) -[2023-10-10 23:23:38,323][98560] Updated weights for policy 1, policy_version 64692 (0.0008) -[2023-10-10 23:23:38,422][98559] Updated weights for policy 0, policy_version 65060 (0.0008) -[2023-10-10 23:23:38,684][98560] Updated weights for policy 1, policy_version 64702 (0.0008) -[2023-10-10 23:23:38,783][98559] Updated weights for policy 0, policy_version 65070 (0.0007) -[2023-10-10 23:23:39,152][98559] Updated weights for policy 0, policy_version 65080 (0.0007) -[2023-10-10 23:23:40,556][97672] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 132907008. Throughput: 0: 1728.0, 1: 1705.4. Samples: 33228774. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:23:40,557][97672] Avg episode reward: [(0, '-1.840'), (1, '22.400')] -[2023-10-10 23:23:42,782][98560] Updated weights for policy 1, policy_version 64712 (0.0009) -[2023-10-10 23:23:43,141][98560] Updated weights for policy 1, policy_version 64722 (0.0008) -[2023-10-10 23:23:43,319][98559] Updated weights for policy 0, policy_version 65090 (0.0007) -[2023-10-10 23:23:43,507][98560] Updated weights for policy 1, policy_version 64732 (0.0008) -[2023-10-10 23:23:43,718][98559] Updated weights for policy 0, policy_version 65100 (0.0008) -[2023-10-10 23:23:44,076][98559] Updated weights for policy 0, policy_version 65110 (0.0009) -[2023-10-10 23:23:44,443][98559] Updated weights for policy 0, policy_version 65120 (0.0009) -[2023-10-10 23:23:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 132972544. Throughput: 0: 1704.3, 1: 1673.5. Samples: 33247410. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:23:45,557][97672] Avg episode reward: [(0, '-1.840'), (1, '22.400')] -[2023-10-10 23:23:47,553][98560] Updated weights for policy 1, policy_version 64742 (0.0009) -[2023-10-10 23:23:47,917][98560] Updated weights for policy 1, policy_version 64752 (0.0007) -[2023-10-10 23:23:48,285][98560] Updated weights for policy 1, policy_version 64762 (0.0007) -[2023-10-10 23:23:48,393][98559] Updated weights for policy 0, policy_version 65130 (0.0007) -[2023-10-10 23:23:48,755][98559] Updated weights for policy 0, policy_version 65140 (0.0008) -[2023-10-10 23:23:49,113][98559] Updated weights for policy 0, policy_version 65150 (0.0007) -[2023-10-10 23:23:50,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 133038080. Throughput: 0: 1707.9, 1: 1695.2. Samples: 33268348. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:23:50,557][97672] Avg episode reward: [(0, '-1.840'), (1, '22.380')] -[2023-10-10 23:23:52,281][98560] Updated weights for policy 1, policy_version 64772 (0.0008) -[2023-10-10 23:23:52,638][98560] Updated weights for policy 1, policy_version 64782 (0.0007) -[2023-10-10 23:23:53,008][98560] Updated weights for policy 1, policy_version 64792 (0.0008) -[2023-10-10 23:23:53,038][98559] Updated weights for policy 0, policy_version 65160 (0.0007) -[2023-10-10 23:23:53,396][98559] Updated weights for policy 0, policy_version 65170 (0.0008) -[2023-10-10 23:23:53,761][98559] Updated weights for policy 0, policy_version 65180 (0.0010) -[2023-10-10 23:23:55,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 133103616. Throughput: 0: 1713.2, 1: 1687.9. Samples: 33278978. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:23:55,556][97672] Avg episode reward: [(0, '-1.840'), (1, '22.380')] -[2023-10-10 23:23:57,039][98560] Updated weights for policy 1, policy_version 64802 (0.0008) -[2023-10-10 23:23:57,396][98560] Updated weights for policy 1, policy_version 64812 (0.0008) -[2023-10-10 23:23:57,695][98559] Updated weights for policy 0, policy_version 65190 (0.0009) -[2023-10-10 23:23:57,772][98560] Updated weights for policy 1, policy_version 64822 (0.0007) -[2023-10-10 23:23:58,060][98559] Updated weights for policy 0, policy_version 65200 (0.0008) -[2023-10-10 23:23:58,129][98560] Updated weights for policy 1, policy_version 64832 (0.0008) -[2023-10-10 23:23:58,424][98559] Updated weights for policy 0, policy_version 65210 (0.0010) -[2023-10-10 23:24:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 133169152. Throughput: 0: 1691.9, 1: 1681.6. Samples: 33298838. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:24:00,557][97672] Avg episode reward: [(0, '-1.840'), (1, '22.460')] -[2023-10-10 23:24:02,272][98560] Updated weights for policy 1, policy_version 64842 (0.0009) -[2023-10-10 23:24:02,373][98559] Updated weights for policy 0, policy_version 65220 (0.0009) -[2023-10-10 23:24:02,629][98560] Updated weights for policy 1, policy_version 64852 (0.0008) -[2023-10-10 23:24:02,741][98559] Updated weights for policy 0, policy_version 65230 (0.0009) -[2023-10-10 23:24:02,992][98560] Updated weights for policy 1, policy_version 64862 (0.0007) -[2023-10-10 23:24:03,096][98559] Updated weights for policy 0, policy_version 65240 (0.0008) -[2023-10-10 23:24:05,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 133234688. Throughput: 0: 1716.3, 1: 1706.9. Samples: 33319904. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:24:05,557][97672] Avg episode reward: [(0, '-1.840'), (1, '22.440')] -[2023-10-10 23:24:06,852][98560] Updated weights for policy 1, policy_version 64872 (0.0007) -[2023-10-10 23:24:07,174][98559] Updated weights for policy 0, policy_version 65250 (0.0010) -[2023-10-10 23:24:07,226][98560] Updated weights for policy 1, policy_version 64882 (0.0010) -[2023-10-10 23:24:07,554][98559] Updated weights for policy 0, policy_version 65260 (0.0007) -[2023-10-10 23:24:07,590][98560] Updated weights for policy 1, policy_version 64892 (0.0010) -[2023-10-10 23:24:07,916][98559] Updated weights for policy 0, policy_version 65270 (0.0009) -[2023-10-10 23:24:08,278][98559] Updated weights for policy 0, policy_version 65280 (0.0008) -[2023-10-10 23:24:10,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 133300224. Throughput: 0: 1691.2, 1: 1682.2. Samples: 33329244. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:24:10,557][97672] Avg episode reward: [(0, '-1.600'), (1, '22.400')] -[2023-10-10 23:24:11,535][98560] Updated weights for policy 1, policy_version 64902 (0.0007) -[2023-10-10 23:24:11,892][98560] Updated weights for policy 1, policy_version 64912 (0.0008) -[2023-10-10 23:24:12,199][98559] Updated weights for policy 0, policy_version 65290 (0.0007) -[2023-10-10 23:24:12,257][98560] Updated weights for policy 1, policy_version 64922 (0.0008) -[2023-10-10 23:24:12,555][98559] Updated weights for policy 0, policy_version 65300 (0.0008) -[2023-10-10 23:24:12,925][98559] Updated weights for policy 0, policy_version 65310 (0.0009) -[2023-10-10 23:24:15,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 133365760. Throughput: 0: 1701.3, 1: 1701.6. Samples: 33350272. Policy #0 lag: (min: 27.0, avg: 35.0, max: 59.0) -[2023-10-10 23:24:15,557][97672] Avg episode reward: [(0, '-1.600'), (1, '22.320')] -[2023-10-10 23:24:16,159][98560] Updated weights for policy 1, policy_version 64932 (0.0008) -[2023-10-10 23:24:16,530][98560] Updated weights for policy 1, policy_version 64942 (0.0009) -[2023-10-10 23:24:16,895][98560] Updated weights for policy 1, policy_version 64952 (0.0007) -[2023-10-10 23:24:16,981][98559] Updated weights for policy 0, policy_version 65320 (0.0009) -[2023-10-10 23:24:17,350][98559] Updated weights for policy 0, policy_version 65330 (0.0008) -[2023-10-10 23:24:17,707][98559] Updated weights for policy 0, policy_version 65340 (0.0008) -[2023-10-10 23:24:20,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 133431296. Throughput: 0: 1719.6, 1: 1714.9. Samples: 33371454. Policy #0 lag: (min: 27.0, avg: 35.0, max: 59.0) -[2023-10-10 23:24:20,557][97672] Avg episode reward: [(0, '-1.600'), (1, '22.320')] -[2023-10-10 23:24:21,043][98560] Updated weights for policy 1, policy_version 64962 (0.0008) -[2023-10-10 23:24:21,454][98560] Updated weights for policy 1, policy_version 64972 (0.0007) -[2023-10-10 23:24:21,814][98559] Updated weights for policy 0, policy_version 65350 (0.0009) -[2023-10-10 23:24:21,814][98560] Updated weights for policy 1, policy_version 64982 (0.0008) -[2023-10-10 23:24:22,171][98559] Updated weights for policy 0, policy_version 65360 (0.0007) -[2023-10-10 23:24:22,184][98560] Updated weights for policy 1, policy_version 64992 (0.0011) -[2023-10-10 23:24:22,543][98559] Updated weights for policy 0, policy_version 65370 (0.0011) -[2023-10-10 23:24:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 133496832. Throughput: 0: 1691.8, 1: 1681.4. Samples: 33380568. Policy #0 lag: (min: 27.0, avg: 35.0, max: 59.0) -[2023-10-10 23:24:25,557][97672] Avg episode reward: [(0, '-1.600'), (1, '22.420')] -[2023-10-10 23:24:26,270][98560] Updated weights for policy 1, policy_version 65002 (0.0007) -[2023-10-10 23:24:26,491][98559] Updated weights for policy 0, policy_version 65380 (0.0010) -[2023-10-10 23:24:26,633][98560] Updated weights for policy 1, policy_version 65012 (0.0007) -[2023-10-10 23:24:26,854][98559] Updated weights for policy 0, policy_version 65390 (0.0010) -[2023-10-10 23:24:26,983][98560] Updated weights for policy 1, policy_version 65022 (0.0008) -[2023-10-10 23:24:27,223][98559] Updated weights for policy 0, policy_version 65400 (0.0009) -[2023-10-10 23:24:30,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 133562368. Throughput: 0: 1716.5, 1: 1706.9. Samples: 33401460. Policy #0 lag: (min: 27.0, avg: 35.0, max: 59.0) -[2023-10-10 23:24:30,557][97672] Avg episode reward: [(0, '-1.600'), (1, '22.400')] -[2023-10-10 23:24:31,253][98560] Updated weights for policy 1, policy_version 65032 (0.0008) -[2023-10-10 23:24:31,445][98559] Updated weights for policy 0, policy_version 65410 (0.0009) -[2023-10-10 23:24:31,629][98560] Updated weights for policy 1, policy_version 65042 (0.0008) -[2023-10-10 23:24:31,867][98559] Updated weights for policy 0, policy_version 65420 (0.0008) -[2023-10-10 23:24:31,990][98560] Updated weights for policy 1, policy_version 65052 (0.0008) -[2023-10-10 23:24:32,233][98559] Updated weights for policy 0, policy_version 65430 (0.0009) -[2023-10-10 23:24:32,605][98559] Updated weights for policy 0, policy_version 65440 (0.0008) -[2023-10-10 23:24:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 133627904. Throughput: 0: 1717.7, 1: 1701.9. Samples: 33422232. Policy #0 lag: (min: 27.0, avg: 35.0, max: 59.0) -[2023-10-10 23:24:35,557][97672] Avg episode reward: [(0, '-1.600'), (1, '22.340')] -[2023-10-10 23:24:35,569][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000065056_66617344.pth... -[2023-10-10 23:24:35,570][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000065440_67010560.pth... -[2023-10-10 23:24:35,623][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000063488_65011712.pth -[2023-10-10 23:24:35,623][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000063840_65372160.pth -[2023-10-10 23:24:36,024][98560] Updated weights for policy 1, policy_version 65062 (0.0008) -[2023-10-10 23:24:36,385][98560] Updated weights for policy 1, policy_version 65072 (0.0007) -[2023-10-10 23:24:36,458][98559] Updated weights for policy 0, policy_version 65450 (0.0008) -[2023-10-10 23:24:36,756][98560] Updated weights for policy 1, policy_version 65082 (0.0007) -[2023-10-10 23:24:36,812][98559] Updated weights for policy 0, policy_version 65460 (0.0008) -[2023-10-10 23:24:37,186][98559] Updated weights for policy 0, policy_version 65470 (0.0008) -[2023-10-10 23:24:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 133693440. Throughput: 0: 1698.4, 1: 1686.9. Samples: 33431318. Policy #0 lag: (min: 27.0, avg: 35.0, max: 59.0) -[2023-10-10 23:24:40,556][97672] Avg episode reward: [(0, '-1.600'), (1, '22.360')] -[2023-10-10 23:24:40,660][98560] Updated weights for policy 1, policy_version 65092 (0.0008) -[2023-10-10 23:24:40,945][98559] Updated weights for policy 0, policy_version 65480 (0.0008) -[2023-10-10 23:24:41,029][98560] Updated weights for policy 1, policy_version 65102 (0.0009) -[2023-10-10 23:24:41,307][98559] Updated weights for policy 0, policy_version 65490 (0.0007) -[2023-10-10 23:24:41,401][98560] Updated weights for policy 1, policy_version 65112 (0.0009) -[2023-10-10 23:24:41,669][98559] Updated weights for policy 0, policy_version 65500 (0.0007) -[2023-10-10 23:24:45,502][98560] Updated weights for policy 1, policy_version 65122 (0.0008) -[2023-10-10 23:24:45,556][97672] Fps is (10 sec: 13107.7, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 133758976. Throughput: 0: 1718.6, 1: 1696.4. Samples: 33452510. Policy #0 lag: (min: 27.0, avg: 35.0, max: 59.0) -[2023-10-10 23:24:45,557][97672] Avg episode reward: [(0, '-1.600'), (1, '22.380')] -[2023-10-10 23:24:45,595][98559] Updated weights for policy 0, policy_version 65510 (0.0008) -[2023-10-10 23:24:45,862][98560] Updated weights for policy 1, policy_version 65132 (0.0008) -[2023-10-10 23:24:45,961][98559] Updated weights for policy 0, policy_version 65520 (0.0009) -[2023-10-10 23:24:46,229][98560] Updated weights for policy 1, policy_version 65142 (0.0007) -[2023-10-10 23:24:46,323][98559] Updated weights for policy 0, policy_version 65530 (0.0009) -[2023-10-10 23:24:46,596][98560] Updated weights for policy 1, policy_version 65152 (0.0008) -[2023-10-10 23:24:50,422][98559] Updated weights for policy 0, policy_version 65540 (0.0007) -[2023-10-10 23:24:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 133824512. Throughput: 0: 1713.3, 1: 1691.1. Samples: 33473102. Policy #0 lag: (min: 27.0, avg: 35.0, max: 59.0) -[2023-10-10 23:24:50,557][97672] Avg episode reward: [(0, '-1.600'), (1, '22.300')] -[2023-10-10 23:24:50,747][98560] Updated weights for policy 1, policy_version 65162 (0.0009) -[2023-10-10 23:24:50,786][98559] Updated weights for policy 0, policy_version 65550 (0.0008) -[2023-10-10 23:24:51,104][98560] Updated weights for policy 1, policy_version 65172 (0.0007) -[2023-10-10 23:24:51,147][98559] Updated weights for policy 0, policy_version 65560 (0.0008) -[2023-10-10 23:24:51,470][98560] Updated weights for policy 1, policy_version 65182 (0.0008) -[2023-10-10 23:24:55,055][98559] Updated weights for policy 0, policy_version 65570 (0.0009) -[2023-10-10 23:24:55,422][98559] Updated weights for policy 0, policy_version 65580 (0.0010) -[2023-10-10 23:24:55,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 133890048. Throughput: 0: 1718.6, 1: 1687.3. Samples: 33482512. Policy #0 lag: (min: 27.0, avg: 35.0, max: 59.0) -[2023-10-10 23:24:55,557][97672] Avg episode reward: [(0, '-1.600'), (1, '22.320')] -[2023-10-10 23:24:55,631][98560] Updated weights for policy 1, policy_version 65192 (0.0009) -[2023-10-10 23:24:55,785][98559] Updated weights for policy 0, policy_version 65590 (0.0010) -[2023-10-10 23:24:55,997][98560] Updated weights for policy 1, policy_version 65202 (0.0009) -[2023-10-10 23:24:56,153][98559] Updated weights for policy 0, policy_version 65600 (0.0008) -[2023-10-10 23:24:56,370][98560] Updated weights for policy 1, policy_version 65212 (0.0009) -[2023-10-10 23:25:00,228][98559] Updated weights for policy 0, policy_version 65610 (0.0009) -[2023-10-10 23:25:00,405][98560] Updated weights for policy 1, policy_version 65222 (0.0008) -[2023-10-10 23:25:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 133955584. Throughput: 0: 1717.6, 1: 1681.9. Samples: 33503248. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 23:25:00,557][97672] Avg episode reward: [(0, '-1.580'), (1, '22.360')] -[2023-10-10 23:25:00,588][98559] Updated weights for policy 0, policy_version 65620 (0.0007) -[2023-10-10 23:25:00,762][98560] Updated weights for policy 1, policy_version 65232 (0.0008) -[2023-10-10 23:25:00,956][98559] Updated weights for policy 0, policy_version 65630 (0.0009) -[2023-10-10 23:25:01,136][98560] Updated weights for policy 1, policy_version 65242 (0.0009) -[2023-10-10 23:25:05,083][98559] Updated weights for policy 0, policy_version 65640 (0.0009) -[2023-10-10 23:25:05,217][98560] Updated weights for policy 1, policy_version 65252 (0.0009) -[2023-10-10 23:25:05,451][98559] Updated weights for policy 0, policy_version 65650 (0.0008) -[2023-10-10 23:25:05,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 134021120. Throughput: 0: 1699.1, 1: 1676.3. Samples: 33523344. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 23:25:05,556][97672] Avg episode reward: [(0, '-1.580'), (1, '22.480')] -[2023-10-10 23:25:05,579][98560] Updated weights for policy 1, policy_version 65262 (0.0009) -[2023-10-10 23:25:05,812][98559] Updated weights for policy 0, policy_version 65660 (0.0007) -[2023-10-10 23:25:05,942][98560] Updated weights for policy 1, policy_version 65272 (0.0007) -[2023-10-10 23:25:09,770][98559] Updated weights for policy 0, policy_version 65670 (0.0010) -[2023-10-10 23:25:10,129][98559] Updated weights for policy 0, policy_version 65680 (0.0008) -[2023-10-10 23:25:10,237][98560] Updated weights for policy 1, policy_version 65282 (0.0009) -[2023-10-10 23:25:10,499][98559] Updated weights for policy 0, policy_version 65690 (0.0008) -[2023-10-10 23:25:10,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 134086656. Throughput: 0: 1714.4, 1: 1678.7. Samples: 33533256. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 23:25:10,556][97672] Avg episode reward: [(0, '-1.580'), (1, '22.460')] -[2023-10-10 23:25:10,642][98560] Updated weights for policy 1, policy_version 65292 (0.0008) -[2023-10-10 23:25:11,017][98560] Updated weights for policy 1, policy_version 65302 (0.0007) -[2023-10-10 23:25:11,389][98560] Updated weights for policy 1, policy_version 65312 (0.0009) -[2023-10-10 23:25:14,452][98559] Updated weights for policy 0, policy_version 65700 (0.0009) -[2023-10-10 23:25:14,815][98559] Updated weights for policy 0, policy_version 65710 (0.0008) -[2023-10-10 23:25:15,188][98559] Updated weights for policy 0, policy_version 65720 (0.0009) -[2023-10-10 23:25:15,374][98560] Updated weights for policy 1, policy_version 65322 (0.0008) -[2023-10-10 23:25:15,556][97672] Fps is (10 sec: 16383.8, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 134184960. Throughput: 0: 1711.4, 1: 1679.0. Samples: 33554028. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 23:25:15,557][97672] Avg episode reward: [(0, '-1.580'), (1, '22.460')] -[2023-10-10 23:25:15,727][98560] Updated weights for policy 1, policy_version 65332 (0.0009) -[2023-10-10 23:25:16,107][98560] Updated weights for policy 1, policy_version 65342 (0.0009) -[2023-10-10 23:25:19,220][98559] Updated weights for policy 0, policy_version 65730 (0.0008) -[2023-10-10 23:25:19,619][98559] Updated weights for policy 0, policy_version 65740 (0.0008) -[2023-10-10 23:25:19,979][98559] Updated weights for policy 0, policy_version 65750 (0.0008) -[2023-10-10 23:25:20,017][98560] Updated weights for policy 1, policy_version 65352 (0.0009) -[2023-10-10 23:25:20,337][98559] Updated weights for policy 0, policy_version 65760 (0.0009) -[2023-10-10 23:25:20,382][98560] Updated weights for policy 1, policy_version 65362 (0.0007) -[2023-10-10 23:25:20,556][97672] Fps is (10 sec: 16383.8, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 134250496. Throughput: 0: 1689.0, 1: 1684.7. Samples: 33574046. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 23:25:20,557][97672] Avg episode reward: [(0, '-1.540'), (1, '22.500')] -[2023-10-10 23:25:20,752][98560] Updated weights for policy 1, policy_version 65372 (0.0009) -[2023-10-10 23:25:24,303][98559] Updated weights for policy 0, policy_version 65770 (0.0008) -[2023-10-10 23:25:24,675][98559] Updated weights for policy 0, policy_version 65780 (0.0009) -[2023-10-10 23:25:24,751][98560] Updated weights for policy 1, policy_version 65382 (0.0008) -[2023-10-10 23:25:25,046][98559] Updated weights for policy 0, policy_version 65790 (0.0008) -[2023-10-10 23:25:25,125][98560] Updated weights for policy 1, policy_version 65392 (0.0009) -[2023-10-10 23:25:25,488][98560] Updated weights for policy 1, policy_version 65402 (0.0010) -[2023-10-10 23:25:25,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 134316032. Throughput: 0: 1718.8, 1: 1688.0. Samples: 33584624. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 23:25:25,557][97672] Avg episode reward: [(0, '-1.540'), (1, '22.500')] -[2023-10-10 23:25:28,983][98559] Updated weights for policy 0, policy_version 65800 (0.0008) -[2023-10-10 23:25:29,345][98559] Updated weights for policy 0, policy_version 65810 (0.0009) -[2023-10-10 23:25:29,654][98560] Updated weights for policy 1, policy_version 65412 (0.0009) -[2023-10-10 23:25:29,713][98559] Updated weights for policy 0, policy_version 65820 (0.0009) -[2023-10-10 23:25:30,022][98560] Updated weights for policy 1, policy_version 65422 (0.0008) -[2023-10-10 23:25:30,388][98560] Updated weights for policy 1, policy_version 65432 (0.0010) -[2023-10-10 23:25:30,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 134381568. Throughput: 0: 1705.2, 1: 1685.9. Samples: 33605106. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 23:25:30,556][97672] Avg episode reward: [(0, '-1.540'), (1, '22.440')] -[2023-10-10 23:25:33,631][98559] Updated weights for policy 0, policy_version 65830 (0.0009) -[2023-10-10 23:25:33,994][98559] Updated weights for policy 0, policy_version 65840 (0.0010) -[2023-10-10 23:25:34,156][98560] Updated weights for policy 1, policy_version 65442 (0.0009) -[2023-10-10 23:25:34,357][98559] Updated weights for policy 0, policy_version 65850 (0.0008) -[2023-10-10 23:25:34,516][98560] Updated weights for policy 1, policy_version 65452 (0.0010) -[2023-10-10 23:25:34,877][98560] Updated weights for policy 1, policy_version 65462 (0.0011) -[2023-10-10 23:25:35,247][98560] Updated weights for policy 1, policy_version 65472 (0.0010) -[2023-10-10 23:25:35,556][97672] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 134479872. Throughput: 0: 1699.9, 1: 1675.6. Samples: 33624996. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 23:25:35,557][97672] Avg episode reward: [(0, '-1.440'), (1, '22.500')] -[2023-10-10 23:25:38,413][98559] Updated weights for policy 0, policy_version 65860 (0.0010) -[2023-10-10 23:25:38,778][98559] Updated weights for policy 0, policy_version 65870 (0.0007) -[2023-10-10 23:25:39,098][98560] Updated weights for policy 1, policy_version 65482 (0.0007) -[2023-10-10 23:25:39,144][98559] Updated weights for policy 0, policy_version 65880 (0.0009) -[2023-10-10 23:25:39,452][98560] Updated weights for policy 1, policy_version 65492 (0.0009) -[2023-10-10 23:25:39,825][98560] Updated weights for policy 1, policy_version 65502 (0.0008) -[2023-10-10 23:25:40,556][97672] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 134545408. Throughput: 0: 1723.1, 1: 1694.5. Samples: 33636306. Policy #0 lag: (min: 10.0, avg: 12.9, max: 42.0) -[2023-10-10 23:25:40,557][97672] Avg episode reward: [(0, '-1.440'), (1, '22.520')] -[2023-10-10 23:25:42,992][98559] Updated weights for policy 0, policy_version 65890 (0.0008) -[2023-10-10 23:25:43,357][98559] Updated weights for policy 0, policy_version 65900 (0.0009) -[2023-10-10 23:25:43,720][98559] Updated weights for policy 0, policy_version 65910 (0.0007) -[2023-10-10 23:25:43,790][98560] Updated weights for policy 1, policy_version 65512 (0.0009) -[2023-10-10 23:25:44,074][98559] Updated weights for policy 0, policy_version 65920 (0.0008) -[2023-10-10 23:25:44,152][98560] Updated weights for policy 1, policy_version 65522 (0.0008) -[2023-10-10 23:25:44,524][98560] Updated weights for policy 1, policy_version 65532 (0.0010) -[2023-10-10 23:25:45,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 134610944. Throughput: 0: 1700.0, 1: 1699.7. Samples: 33656238. Policy #0 lag: (min: 10.0, avg: 12.9, max: 42.0) -[2023-10-10 23:25:45,557][97672] Avg episode reward: [(0, '-1.420'), (1, '22.480')] -[2023-10-10 23:25:47,954][98559] Updated weights for policy 0, policy_version 65930 (0.0011) -[2023-10-10 23:25:48,313][98559] Updated weights for policy 0, policy_version 65940 (0.0009) -[2023-10-10 23:25:48,655][98560] Updated weights for policy 1, policy_version 65542 (0.0008) -[2023-10-10 23:25:48,678][98559] Updated weights for policy 0, policy_version 65950 (0.0008) -[2023-10-10 23:25:49,012][98560] Updated weights for policy 1, policy_version 65552 (0.0009) -[2023-10-10 23:25:49,376][98560] Updated weights for policy 1, policy_version 65562 (0.0010) -[2023-10-10 23:25:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 134676480. Throughput: 0: 1715.8, 1: 1676.7. Samples: 33676008. Policy #0 lag: (min: 10.0, avg: 12.9, max: 42.0) -[2023-10-10 23:25:50,557][97672] Avg episode reward: [(0, '-1.420'), (1, '22.440')] -[2023-10-10 23:25:52,756][98559] Updated weights for policy 0, policy_version 65960 (0.0009) -[2023-10-10 23:25:53,127][98559] Updated weights for policy 0, policy_version 65970 (0.0009) -[2023-10-10 23:25:53,490][98559] Updated weights for policy 0, policy_version 65980 (0.0009) -[2023-10-10 23:25:53,552][98560] Updated weights for policy 1, policy_version 65572 (0.0008) -[2023-10-10 23:25:53,926][98560] Updated weights for policy 1, policy_version 65582 (0.0009) -[2023-10-10 23:25:54,291][98560] Updated weights for policy 1, policy_version 65592 (0.0009) -[2023-10-10 23:25:55,556][97672] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 134742016. Throughput: 0: 1705.2, 1: 1707.7. Samples: 33686840. Policy #0 lag: (min: 10.0, avg: 12.9, max: 42.0) -[2023-10-10 23:25:55,556][97672] Avg episode reward: [(0, '-1.460'), (1, '22.440')] -[2023-10-10 23:25:57,484][98559] Updated weights for policy 0, policy_version 65990 (0.0010) -[2023-10-10 23:25:57,850][98559] Updated weights for policy 0, policy_version 66000 (0.0008) -[2023-10-10 23:25:58,214][98559] Updated weights for policy 0, policy_version 66010 (0.0009) -[2023-10-10 23:25:58,278][98560] Updated weights for policy 1, policy_version 65602 (0.0008) -[2023-10-10 23:25:58,697][98560] Updated weights for policy 1, policy_version 65612 (0.0008) -[2023-10-10 23:25:59,076][98560] Updated weights for policy 1, policy_version 65622 (0.0009) -[2023-10-10 23:25:59,444][98560] Updated weights for policy 1, policy_version 65632 (0.0009) -[2023-10-10 23:26:00,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 134807552. Throughput: 0: 1698.9, 1: 1696.1. Samples: 33706804. Policy #0 lag: (min: 10.0, avg: 12.9, max: 42.0) -[2023-10-10 23:26:00,557][97672] Avg episode reward: [(0, '-1.480'), (1, '22.500')] -[2023-10-10 23:26:02,244][98559] Updated weights for policy 0, policy_version 66020 (0.0010) -[2023-10-10 23:26:02,617][98559] Updated weights for policy 0, policy_version 66030 (0.0008) -[2023-10-10 23:26:02,984][98559] Updated weights for policy 0, policy_version 66040 (0.0008) -[2023-10-10 23:26:03,542][98560] Updated weights for policy 1, policy_version 65642 (0.0009) -[2023-10-10 23:26:03,915][98560] Updated weights for policy 1, policy_version 65652 (0.0009) -[2023-10-10 23:26:04,281][98560] Updated weights for policy 1, policy_version 65662 (0.0010) -[2023-10-10 23:26:05,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 134873088. Throughput: 0: 1724.2, 1: 1671.5. Samples: 33726854. Policy #0 lag: (min: 10.0, avg: 12.9, max: 42.0) -[2023-10-10 23:26:05,557][97672] Avg episode reward: [(0, '-1.480'), (1, '22.520')] -[2023-10-10 23:26:07,049][98559] Updated weights for policy 0, policy_version 66050 (0.0008) -[2023-10-10 23:26:07,446][98559] Updated weights for policy 0, policy_version 66060 (0.0007) -[2023-10-10 23:26:07,814][98559] Updated weights for policy 0, policy_version 66070 (0.0007) -[2023-10-10 23:26:08,184][98559] Updated weights for policy 0, policy_version 66080 (0.0010) -[2023-10-10 23:26:08,312][98560] Updated weights for policy 1, policy_version 65672 (0.0008) -[2023-10-10 23:26:08,676][98560] Updated weights for policy 1, policy_version 65682 (0.0009) -[2023-10-10 23:26:09,050][98560] Updated weights for policy 1, policy_version 65692 (0.0011) -[2023-10-10 23:26:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 134938624. Throughput: 0: 1693.3, 1: 1699.9. Samples: 33737318. Policy #0 lag: (min: 10.0, avg: 12.9, max: 42.0) -[2023-10-10 23:26:10,557][97672] Avg episode reward: [(0, '-1.480'), (1, '22.480')] -[2023-10-10 23:26:12,210][98559] Updated weights for policy 0, policy_version 66090 (0.0011) -[2023-10-10 23:26:12,582][98559] Updated weights for policy 0, policy_version 66100 (0.0008) -[2023-10-10 23:26:12,947][98559] Updated weights for policy 0, policy_version 66110 (0.0008) -[2023-10-10 23:26:13,140][98560] Updated weights for policy 1, policy_version 65702 (0.0009) -[2023-10-10 23:26:13,509][98560] Updated weights for policy 1, policy_version 65712 (0.0007) -[2023-10-10 23:26:13,885][98560] Updated weights for policy 1, policy_version 65722 (0.0007) -[2023-10-10 23:26:15,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 135004160. Throughput: 0: 1705.8, 1: 1683.8. Samples: 33757638. Policy #0 lag: (min: 10.0, avg: 12.9, max: 42.0) -[2023-10-10 23:26:15,556][97672] Avg episode reward: [(0, '-1.480'), (1, '22.600')] -[2023-10-10 23:26:16,871][98559] Updated weights for policy 0, policy_version 66120 (0.0008) -[2023-10-10 23:26:17,238][98559] Updated weights for policy 0, policy_version 66130 (0.0009) -[2023-10-10 23:26:17,605][98559] Updated weights for policy 0, policy_version 66140 (0.0007) -[2023-10-10 23:26:17,655][98560] Updated weights for policy 1, policy_version 65732 (0.0007) -[2023-10-10 23:26:18,019][98560] Updated weights for policy 1, policy_version 65742 (0.0009) -[2023-10-10 23:26:18,373][98560] Updated weights for policy 1, policy_version 65752 (0.0010) -[2023-10-10 23:26:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 135069696. Throughput: 0: 1716.9, 1: 1690.3. Samples: 33778320. Policy #0 lag: (min: 10.0, avg: 12.9, max: 42.0) -[2023-10-10 23:26:20,557][97672] Avg episode reward: [(0, '-1.480'), (1, '22.500')] -[2023-10-10 23:26:21,617][98559] Updated weights for policy 0, policy_version 66150 (0.0007) -[2023-10-10 23:26:21,983][98559] Updated weights for policy 0, policy_version 66160 (0.0007) -[2023-10-10 23:26:22,351][98559] Updated weights for policy 0, policy_version 66170 (0.0010) -[2023-10-10 23:26:22,380][98560] Updated weights for policy 1, policy_version 65762 (0.0007) -[2023-10-10 23:26:22,741][98560] Updated weights for policy 1, policy_version 65772 (0.0007) -[2023-10-10 23:26:23,108][98560] Updated weights for policy 1, policy_version 65782 (0.0008) -[2023-10-10 23:26:23,472][98560] Updated weights for policy 1, policy_version 65792 (0.0008) -[2023-10-10 23:26:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 135135232. Throughput: 0: 1693.0, 1: 1694.7. Samples: 33788752. Policy #0 lag: (min: 0.0, avg: 27.1, max: 32.0) -[2023-10-10 23:26:25,557][97672] Avg episode reward: [(0, '-1.480'), (1, '22.480')] -[2023-10-10 23:26:26,255][98559] Updated weights for policy 0, policy_version 66180 (0.0009) -[2023-10-10 23:26:26,623][98559] Updated weights for policy 0, policy_version 66190 (0.0008) -[2023-10-10 23:26:26,980][98559] Updated weights for policy 0, policy_version 66200 (0.0007) -[2023-10-10 23:26:27,484][98560] Updated weights for policy 1, policy_version 65802 (0.0007) -[2023-10-10 23:26:27,844][98560] Updated weights for policy 1, policy_version 65812 (0.0008) -[2023-10-10 23:26:28,207][98560] Updated weights for policy 1, policy_version 65822 (0.0007) -[2023-10-10 23:26:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 135200768. Throughput: 0: 1715.4, 1: 1679.9. Samples: 33809024. Policy #0 lag: (min: 0.0, avg: 27.1, max: 32.0) -[2023-10-10 23:26:30,557][97672] Avg episode reward: [(0, '-1.480'), (1, '22.520')] -[2023-10-10 23:26:30,940][98559] Updated weights for policy 0, policy_version 66210 (0.0008) -[2023-10-10 23:26:31,304][98559] Updated weights for policy 0, policy_version 66220 (0.0010) -[2023-10-10 23:26:31,684][98559] Updated weights for policy 0, policy_version 66230 (0.0009) -[2023-10-10 23:26:32,044][98559] Updated weights for policy 0, policy_version 66240 (0.0008) -[2023-10-10 23:26:32,249][98560] Updated weights for policy 1, policy_version 65832 (0.0009) -[2023-10-10 23:26:32,614][98560] Updated weights for policy 1, policy_version 65842 (0.0010) -[2023-10-10 23:26:32,991][98560] Updated weights for policy 1, policy_version 65852 (0.0010) -[2023-10-10 23:26:35,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 135266304. Throughput: 0: 1716.8, 1: 1705.9. Samples: 33830030. Policy #0 lag: (min: 0.0, avg: 27.1, max: 32.0) -[2023-10-10 23:26:35,557][97672] Avg episode reward: [(0, '-1.480'), (1, '22.540')] -[2023-10-10 23:26:35,568][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000065856_67436544.pth... -[2023-10-10 23:26:35,568][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000066240_67829760.pth... -[2023-10-10 23:26:35,597][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000064288_65830912.pth -[2023-10-10 23:26:35,600][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000064640_66191360.pth -[2023-10-10 23:26:36,115][98559] Updated weights for policy 0, policy_version 66250 (0.0009) -[2023-10-10 23:26:36,477][98559] Updated weights for policy 0, policy_version 66260 (0.0010) -[2023-10-10 23:26:36,858][98559] Updated weights for policy 0, policy_version 66270 (0.0008) -[2023-10-10 23:26:37,080][98560] Updated weights for policy 1, policy_version 65862 (0.0009) -[2023-10-10 23:26:37,449][98560] Updated weights for policy 1, policy_version 65872 (0.0010) -[2023-10-10 23:26:37,805][98560] Updated weights for policy 1, policy_version 65882 (0.0011) -[2023-10-10 23:26:40,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 135331840. Throughput: 0: 1708.8, 1: 1684.4. Samples: 33839538. Policy #0 lag: (min: 0.0, avg: 27.1, max: 32.0) -[2023-10-10 23:26:40,557][97672] Avg episode reward: [(0, '-1.460'), (1, '22.500')] -[2023-10-10 23:26:40,950][98559] Updated weights for policy 0, policy_version 66280 (0.0008) -[2023-10-10 23:26:41,324][98559] Updated weights for policy 0, policy_version 66290 (0.0007) -[2023-10-10 23:26:41,689][98559] Updated weights for policy 0, policy_version 66300 (0.0007) -[2023-10-10 23:26:41,897][98560] Updated weights for policy 1, policy_version 65892 (0.0010) -[2023-10-10 23:26:42,258][98560] Updated weights for policy 1, policy_version 65902 (0.0010) -[2023-10-10 23:26:42,634][98560] Updated weights for policy 1, policy_version 65912 (0.0010) -[2023-10-10 23:26:45,556][97672] Fps is (10 sec: 13107.7, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 135397376. Throughput: 0: 1720.5, 1: 1684.3. Samples: 33860020. Policy #0 lag: (min: 0.0, avg: 27.1, max: 32.0) -[2023-10-10 23:26:45,556][97672] Avg episode reward: [(0, '-1.460'), (1, '22.520')] -[2023-10-10 23:26:45,627][98559] Updated weights for policy 0, policy_version 66310 (0.0009) -[2023-10-10 23:26:45,998][98559] Updated weights for policy 0, policy_version 66320 (0.0009) -[2023-10-10 23:26:46,369][98559] Updated weights for policy 0, policy_version 66330 (0.0008) -[2023-10-10 23:26:46,721][98560] Updated weights for policy 1, policy_version 65922 (0.0009) -[2023-10-10 23:26:47,103][98560] Updated weights for policy 1, policy_version 65932 (0.0008) -[2023-10-10 23:26:47,464][98560] Updated weights for policy 1, policy_version 65942 (0.0008) -[2023-10-10 23:26:47,833][98560] Updated weights for policy 1, policy_version 65952 (0.0010) -[2023-10-10 23:26:50,321][98559] Updated weights for policy 0, policy_version 66340 (0.0007) -[2023-10-10 23:26:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 135462912. Throughput: 0: 1714.6, 1: 1707.6. Samples: 33880852. Policy #0 lag: (min: 0.0, avg: 27.1, max: 32.0) -[2023-10-10 23:26:50,557][97672] Avg episode reward: [(0, '-1.460'), (1, '22.480')] -[2023-10-10 23:26:50,691][98559] Updated weights for policy 0, policy_version 66350 (0.0009) -[2023-10-10 23:26:51,060][98559] Updated weights for policy 0, policy_version 66360 (0.0009) -[2023-10-10 23:26:51,935][98560] Updated weights for policy 1, policy_version 65962 (0.0007) -[2023-10-10 23:26:52,290][98560] Updated weights for policy 1, policy_version 65972 (0.0009) -[2023-10-10 23:26:52,668][98560] Updated weights for policy 1, policy_version 65982 (0.0009) -[2023-10-10 23:26:55,143][98559] Updated weights for policy 0, policy_version 66370 (0.0008) -[2023-10-10 23:26:55,541][98559] Updated weights for policy 0, policy_version 66380 (0.0007) -[2023-10-10 23:26:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 135528448. Throughput: 0: 1724.7, 1: 1683.9. Samples: 33890706. Policy #0 lag: (min: 0.0, avg: 27.1, max: 32.0) -[2023-10-10 23:26:55,556][97672] Avg episode reward: [(0, '-1.460'), (1, '22.420')] -[2023-10-10 23:26:55,908][98559] Updated weights for policy 0, policy_version 66390 (0.0008) -[2023-10-10 23:26:56,267][98559] Updated weights for policy 0, policy_version 66400 (0.0008) -[2023-10-10 23:26:56,787][98560] Updated weights for policy 1, policy_version 65992 (0.0009) -[2023-10-10 23:26:57,151][98560] Updated weights for policy 1, policy_version 66002 (0.0009) -[2023-10-10 23:26:57,530][98560] Updated weights for policy 1, policy_version 66012 (0.0009) -[2023-10-10 23:27:00,265][98559] Updated weights for policy 0, policy_version 66410 (0.0010) -[2023-10-10 23:27:00,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 135593984. Throughput: 0: 1720.1, 1: 1694.5. Samples: 33911296. Policy #0 lag: (min: 0.0, avg: 27.1, max: 32.0) -[2023-10-10 23:27:00,557][97672] Avg episode reward: [(0, '-1.460'), (1, '22.460')] -[2023-10-10 23:27:00,628][98559] Updated weights for policy 0, policy_version 66420 (0.0010) -[2023-10-10 23:27:00,997][98559] Updated weights for policy 0, policy_version 66430 (0.0008) -[2023-10-10 23:27:01,632][98560] Updated weights for policy 1, policy_version 66022 (0.0010) -[2023-10-10 23:27:01,993][98560] Updated weights for policy 1, policy_version 66032 (0.0010) -[2023-10-10 23:27:02,360][98560] Updated weights for policy 1, policy_version 66042 (0.0009) -[2023-10-10 23:27:04,964][98559] Updated weights for policy 0, policy_version 66440 (0.0009) -[2023-10-10 23:27:05,339][98559] Updated weights for policy 0, policy_version 66450 (0.0009) -[2023-10-10 23:27:05,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 135659520. Throughput: 0: 1702.9, 1: 1699.9. Samples: 33931448. Policy #0 lag: (min: 0.0, avg: 27.1, max: 32.0) -[2023-10-10 23:27:05,557][97672] Avg episode reward: [(0, '-1.460'), (1, '22.540')] -[2023-10-10 23:27:05,701][98559] Updated weights for policy 0, policy_version 66460 (0.0008) -[2023-10-10 23:27:06,342][98560] Updated weights for policy 1, policy_version 66052 (0.0008) -[2023-10-10 23:27:06,704][98560] Updated weights for policy 1, policy_version 66062 (0.0009) -[2023-10-10 23:27:07,076][98560] Updated weights for policy 1, policy_version 66072 (0.0008) -[2023-10-10 23:27:09,664][98559] Updated weights for policy 0, policy_version 66470 (0.0009) -[2023-10-10 23:27:10,027][98559] Updated weights for policy 0, policy_version 66480 (0.0010) -[2023-10-10 23:27:10,400][98559] Updated weights for policy 0, policy_version 66490 (0.0010) -[2023-10-10 23:27:10,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 135725056. Throughput: 0: 1716.2, 1: 1676.9. Samples: 33941440. Policy #0 lag: (min: 16.0, avg: 43.6, max: 48.0) -[2023-10-10 23:27:10,556][97672] Avg episode reward: [(0, '-1.400'), (1, '22.600')] -[2023-10-10 23:27:10,996][98560] Updated weights for policy 1, policy_version 66082 (0.0007) -[2023-10-10 23:27:11,372][98560] Updated weights for policy 1, policy_version 66092 (0.0007) -[2023-10-10 23:27:11,748][98560] Updated weights for policy 1, policy_version 66102 (0.0008) -[2023-10-10 23:27:12,111][98560] Updated weights for policy 1, policy_version 66112 (0.0008) -[2023-10-10 23:27:14,462][98559] Updated weights for policy 0, policy_version 66500 (0.0009) -[2023-10-10 23:27:14,825][98559] Updated weights for policy 0, policy_version 66510 (0.0007) -[2023-10-10 23:27:15,183][98559] Updated weights for policy 0, policy_version 66520 (0.0009) -[2023-10-10 23:27:15,556][97672] Fps is (10 sec: 16384.5, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 135823360. Throughput: 0: 1716.5, 1: 1700.1. Samples: 33962770. Policy #0 lag: (min: 16.0, avg: 43.6, max: 48.0) -[2023-10-10 23:27:15,556][97672] Avg episode reward: [(0, '-1.400'), (1, '22.600')] -[2023-10-10 23:27:15,951][98560] Updated weights for policy 1, policy_version 66122 (0.0008) -[2023-10-10 23:27:16,321][98560] Updated weights for policy 1, policy_version 66132 (0.0007) -[2023-10-10 23:27:16,690][98560] Updated weights for policy 1, policy_version 66142 (0.0007) -[2023-10-10 23:27:19,230][98559] Updated weights for policy 0, policy_version 66530 (0.0007) -[2023-10-10 23:27:19,590][98559] Updated weights for policy 0, policy_version 66540 (0.0007) -[2023-10-10 23:27:19,955][98559] Updated weights for policy 0, policy_version 66550 (0.0007) -[2023-10-10 23:27:20,311][98559] Updated weights for policy 0, policy_version 66560 (0.0007) -[2023-10-10 23:27:20,556][97672] Fps is (10 sec: 16383.5, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 135888896. Throughput: 0: 1690.6, 1: 1703.4. Samples: 33982760. Policy #0 lag: (min: 16.0, avg: 43.6, max: 48.0) -[2023-10-10 23:27:20,557][97672] Avg episode reward: [(0, '-1.400'), (1, '22.540')] -[2023-10-10 23:27:20,711][98560] Updated weights for policy 1, policy_version 66152 (0.0009) -[2023-10-10 23:27:21,080][98560] Updated weights for policy 1, policy_version 66162 (0.0009) -[2023-10-10 23:27:21,444][98560] Updated weights for policy 1, policy_version 66172 (0.0008) -[2023-10-10 23:27:24,265][98559] Updated weights for policy 0, policy_version 66570 (0.0008) -[2023-10-10 23:27:24,636][98559] Updated weights for policy 0, policy_version 66580 (0.0007) -[2023-10-10 23:27:25,001][98559] Updated weights for policy 0, policy_version 66590 (0.0008) -[2023-10-10 23:27:25,493][98560] Updated weights for policy 1, policy_version 66182 (0.0010) -[2023-10-10 23:27:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 135954432. Throughput: 0: 1720.0, 1: 1697.4. Samples: 33993320. Policy #0 lag: (min: 16.0, avg: 43.6, max: 48.0) -[2023-10-10 23:27:25,556][97672] Avg episode reward: [(0, '-1.400'), (1, '22.460')] -[2023-10-10 23:27:25,862][98560] Updated weights for policy 1, policy_version 66192 (0.0007) -[2023-10-10 23:27:26,233][98560] Updated weights for policy 1, policy_version 66202 (0.0008) -[2023-10-10 23:27:28,764][98559] Updated weights for policy 0, policy_version 66600 (0.0010) -[2023-10-10 23:27:29,140][98559] Updated weights for policy 0, policy_version 66610 (0.0009) -[2023-10-10 23:27:29,497][98559] Updated weights for policy 0, policy_version 66620 (0.0009) -[2023-10-10 23:27:30,177][98560] Updated weights for policy 1, policy_version 66212 (0.0008) -[2023-10-10 23:27:30,553][98560] Updated weights for policy 1, policy_version 66222 (0.0008) -[2023-10-10 23:27:30,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 136019968. Throughput: 0: 1700.8, 1: 1710.3. Samples: 34013522. Policy #0 lag: (min: 16.0, avg: 43.6, max: 48.0) -[2023-10-10 23:27:30,557][97672] Avg episode reward: [(0, '-1.400'), (1, '22.420')] -[2023-10-10 23:27:30,920][98560] Updated weights for policy 1, policy_version 66232 (0.0010) -[2023-10-10 23:27:33,308][98559] Updated weights for policy 0, policy_version 66630 (0.0007) -[2023-10-10 23:27:33,667][98559] Updated weights for policy 0, policy_version 66640 (0.0007) -[2023-10-10 23:27:34,040][98559] Updated weights for policy 0, policy_version 66650 (0.0010) -[2023-10-10 23:27:35,061][98560] Updated weights for policy 1, policy_version 66242 (0.0008) -[2023-10-10 23:27:35,483][98560] Updated weights for policy 1, policy_version 66252 (0.0007) -[2023-10-10 23:27:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 136085504. Throughput: 0: 1701.8, 1: 1708.1. Samples: 34034298. Policy #0 lag: (min: 16.0, avg: 43.6, max: 48.0) -[2023-10-10 23:27:35,557][97672] Avg episode reward: [(0, '-1.400'), (1, '22.460')] -[2023-10-10 23:27:35,848][98560] Updated weights for policy 1, policy_version 66262 (0.0009) -[2023-10-10 23:27:36,219][98560] Updated weights for policy 1, policy_version 66272 (0.0009) -[2023-10-10 23:27:38,073][98559] Updated weights for policy 0, policy_version 66660 (0.0010) -[2023-10-10 23:27:38,441][98559] Updated weights for policy 0, policy_version 66670 (0.0007) -[2023-10-10 23:27:38,811][98559] Updated weights for policy 0, policy_version 66680 (0.0008) -[2023-10-10 23:27:40,124][98560] Updated weights for policy 1, policy_version 66282 (0.0010) -[2023-10-10 23:27:40,485][98560] Updated weights for policy 1, policy_version 66292 (0.0010) -[2023-10-10 23:27:40,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 136151040. Throughput: 0: 1714.0, 1: 1697.0. Samples: 34044202. Policy #0 lag: (min: 16.0, avg: 43.6, max: 48.0) -[2023-10-10 23:27:40,556][97672] Avg episode reward: [(0, '-1.400'), (1, '22.480')] -[2023-10-10 23:27:40,857][98560] Updated weights for policy 1, policy_version 66302 (0.0009) -[2023-10-10 23:27:42,628][98559] Updated weights for policy 0, policy_version 66690 (0.0008) -[2023-10-10 23:27:43,000][98559] Updated weights for policy 0, policy_version 66700 (0.0009) -[2023-10-10 23:27:43,379][98559] Updated weights for policy 0, policy_version 66710 (0.0009) -[2023-10-10 23:27:43,743][98559] Updated weights for policy 0, policy_version 66720 (0.0010) -[2023-10-10 23:27:44,743][98560] Updated weights for policy 1, policy_version 66312 (0.0008) -[2023-10-10 23:27:45,108][98560] Updated weights for policy 1, policy_version 66322 (0.0008) -[2023-10-10 23:27:45,487][98560] Updated weights for policy 1, policy_version 66332 (0.0009) -[2023-10-10 23:27:45,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 136216576. Throughput: 0: 1700.5, 1: 1705.8. Samples: 34064578. Policy #0 lag: (min: 16.0, avg: 43.6, max: 48.0) -[2023-10-10 23:27:45,557][97672] Avg episode reward: [(0, '-1.400'), (1, '22.420')] -[2023-10-10 23:27:47,782][98559] Updated weights for policy 0, policy_version 66730 (0.0009) -[2023-10-10 23:27:48,144][98559] Updated weights for policy 0, policy_version 66740 (0.0011) -[2023-10-10 23:27:48,510][98559] Updated weights for policy 0, policy_version 66750 (0.0009) -[2023-10-10 23:27:49,534][98560] Updated weights for policy 1, policy_version 66342 (0.0009) -[2023-10-10 23:27:49,897][98560] Updated weights for policy 1, policy_version 66352 (0.0008) -[2023-10-10 23:27:50,263][98560] Updated weights for policy 1, policy_version 66362 (0.0010) -[2023-10-10 23:27:50,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 136314880. Throughput: 0: 1724.1, 1: 1696.5. Samples: 34085374. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 23:27:50,556][97672] Avg episode reward: [(0, '-1.400'), (1, '22.380')] -[2023-10-10 23:27:52,464][98559] Updated weights for policy 0, policy_version 66760 (0.0008) -[2023-10-10 23:27:52,826][98559] Updated weights for policy 0, policy_version 66770 (0.0007) -[2023-10-10 23:27:53,196][98559] Updated weights for policy 0, policy_version 66780 (0.0010) -[2023-10-10 23:27:54,285][98560] Updated weights for policy 1, policy_version 66372 (0.0007) -[2023-10-10 23:27:54,654][98560] Updated weights for policy 1, policy_version 66382 (0.0010) -[2023-10-10 23:27:55,019][98560] Updated weights for policy 1, policy_version 66392 (0.0009) -[2023-10-10 23:27:55,556][97672] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 136380416. Throughput: 0: 1708.8, 1: 1706.4. Samples: 34095128. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 23:27:55,557][97672] Avg episode reward: [(0, '-1.400'), (1, '22.360')] -[2023-10-10 23:27:57,124][98559] Updated weights for policy 0, policy_version 66790 (0.0009) -[2023-10-10 23:27:57,478][98559] Updated weights for policy 0, policy_version 66800 (0.0008) -[2023-10-10 23:27:57,854][98559] Updated weights for policy 0, policy_version 66810 (0.0008) -[2023-10-10 23:27:59,252][98560] Updated weights for policy 1, policy_version 66402 (0.0009) -[2023-10-10 23:27:59,617][98560] Updated weights for policy 1, policy_version 66412 (0.0008) -[2023-10-10 23:27:59,981][98560] Updated weights for policy 1, policy_version 66422 (0.0010) -[2023-10-10 23:28:00,347][98560] Updated weights for policy 1, policy_version 66432 (0.0010) -[2023-10-10 23:28:00,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 136445952. Throughput: 0: 1713.1, 1: 1699.8. Samples: 34116348. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 23:28:00,557][97672] Avg episode reward: [(0, '-1.400'), (1, '22.380')] -[2023-10-10 23:28:01,792][98559] Updated weights for policy 0, policy_version 66820 (0.0008) -[2023-10-10 23:28:02,155][98559] Updated weights for policy 0, policy_version 66830 (0.0010) -[2023-10-10 23:28:02,531][98559] Updated weights for policy 0, policy_version 66840 (0.0008) -[2023-10-10 23:28:04,368][98560] Updated weights for policy 1, policy_version 66442 (0.0009) -[2023-10-10 23:28:04,743][98560] Updated weights for policy 1, policy_version 66452 (0.0008) -[2023-10-10 23:28:05,103][98560] Updated weights for policy 1, policy_version 66462 (0.0007) -[2023-10-10 23:28:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 136511488. Throughput: 0: 1740.6, 1: 1678.2. Samples: 34136604. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 23:28:05,557][97672] Avg episode reward: [(0, '-1.400'), (1, '22.440')] -[2023-10-10 23:28:06,467][98559] Updated weights for policy 0, policy_version 66850 (0.0008) -[2023-10-10 23:28:06,836][98559] Updated weights for policy 0, policy_version 66860 (0.0007) -[2023-10-10 23:28:07,194][98559] Updated weights for policy 0, policy_version 66870 (0.0008) -[2023-10-10 23:28:07,558][98559] Updated weights for policy 0, policy_version 66880 (0.0007) -[2023-10-10 23:28:09,170][98560] Updated weights for policy 1, policy_version 66472 (0.0008) -[2023-10-10 23:28:09,534][98560] Updated weights for policy 1, policy_version 66482 (0.0009) -[2023-10-10 23:28:09,900][98560] Updated weights for policy 1, policy_version 66492 (0.0007) -[2023-10-10 23:28:10,556][97672] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 136577024. Throughput: 0: 1714.6, 1: 1690.4. Samples: 34146542. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 23:28:10,556][97672] Avg episode reward: [(0, '-1.400'), (1, '22.500')] -[2023-10-10 23:28:11,542][98559] Updated weights for policy 0, policy_version 66890 (0.0007) -[2023-10-10 23:28:11,912][98559] Updated weights for policy 0, policy_version 66900 (0.0008) -[2023-10-10 23:28:12,278][98559] Updated weights for policy 0, policy_version 66910 (0.0007) -[2023-10-10 23:28:13,812][98560] Updated weights for policy 1, policy_version 66502 (0.0009) -[2023-10-10 23:28:14,176][98560] Updated weights for policy 1, policy_version 66512 (0.0011) -[2023-10-10 23:28:14,534][98560] Updated weights for policy 1, policy_version 66522 (0.0009) -[2023-10-10 23:28:15,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 136642560. Throughput: 0: 1733.5, 1: 1690.3. Samples: 34167590. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 23:28:15,557][97672] Avg episode reward: [(0, '-1.400'), (1, '22.640')] -[2023-10-10 23:28:16,157][98559] Updated weights for policy 0, policy_version 66920 (0.0008) -[2023-10-10 23:28:16,530][98559] Updated weights for policy 0, policy_version 66930 (0.0009) -[2023-10-10 23:28:16,897][98559] Updated weights for policy 0, policy_version 66940 (0.0008) -[2023-10-10 23:28:18,718][98560] Updated weights for policy 1, policy_version 66532 (0.0008) -[2023-10-10 23:28:19,087][98560] Updated weights for policy 1, policy_version 66542 (0.0007) -[2023-10-10 23:28:19,450][98560] Updated weights for policy 1, policy_version 66552 (0.0010) -[2023-10-10 23:28:20,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 136708096. Throughput: 0: 1740.8, 1: 1665.7. Samples: 34187592. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 23:28:20,557][97672] Avg episode reward: [(0, '-1.420'), (1, '22.660')] -[2023-10-10 23:28:20,781][98559] Updated weights for policy 0, policy_version 66950 (0.0008) -[2023-10-10 23:28:21,147][98559] Updated weights for policy 0, policy_version 66960 (0.0010) -[2023-10-10 23:28:21,509][98559] Updated weights for policy 0, policy_version 66970 (0.0011) -[2023-10-10 23:28:23,495][98560] Updated weights for policy 1, policy_version 66562 (0.0008) -[2023-10-10 23:28:23,889][98560] Updated weights for policy 1, policy_version 66572 (0.0008) -[2023-10-10 23:28:24,265][98560] Updated weights for policy 1, policy_version 66582 (0.0011) -[2023-10-10 23:28:24,631][98560] Updated weights for policy 1, policy_version 66592 (0.0009) -[2023-10-10 23:28:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 136773632. Throughput: 0: 1719.5, 1: 1697.2. Samples: 34197956. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 23:28:25,557][97672] Avg episode reward: [(0, '-1.420'), (1, '22.700')] -[2023-10-10 23:28:25,566][98559] Updated weights for policy 0, policy_version 66980 (0.0009) -[2023-10-10 23:28:25,926][98559] Updated weights for policy 0, policy_version 66990 (0.0007) -[2023-10-10 23:28:26,292][98559] Updated weights for policy 0, policy_version 67000 (0.0011) -[2023-10-10 23:28:28,689][98560] Updated weights for policy 1, policy_version 66602 (0.0009) -[2023-10-10 23:28:29,055][98560] Updated weights for policy 1, policy_version 66612 (0.0009) -[2023-10-10 23:28:29,419][98560] Updated weights for policy 1, policy_version 66622 (0.0008) -[2023-10-10 23:28:30,488][98559] Updated weights for policy 0, policy_version 67010 (0.0009) -[2023-10-10 23:28:30,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 136839168. Throughput: 0: 1735.6, 1: 1684.8. Samples: 34218500. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 23:28:30,557][97672] Avg episode reward: [(0, '-1.420'), (1, '22.740')] -[2023-10-10 23:28:30,911][98559] Updated weights for policy 0, policy_version 67020 (0.0009) -[2023-10-10 23:28:31,281][98559] Updated weights for policy 0, policy_version 67030 (0.0011) -[2023-10-10 23:28:31,640][98559] Updated weights for policy 0, policy_version 67040 (0.0010) -[2023-10-10 23:28:33,493][98560] Updated weights for policy 1, policy_version 66632 (0.0008) -[2023-10-10 23:28:33,859][98560] Updated weights for policy 1, policy_version 66642 (0.0010) -[2023-10-10 23:28:34,231][98560] Updated weights for policy 1, policy_version 66652 (0.0010) -[2023-10-10 23:28:35,535][98559] Updated weights for policy 0, policy_version 67050 (0.0007) -[2023-10-10 23:28:35,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 136904704. Throughput: 0: 1717.6, 1: 1677.8. Samples: 34238168. Policy #0 lag: (min: 10.0, avg: 14.1, max: 42.0) -[2023-10-10 23:28:35,557][97672] Avg episode reward: [(0, '-1.420'), (1, '22.760')] -[2023-10-10 23:28:35,564][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000066656_68255744.pth... -[2023-10-10 23:28:35,595][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000065056_66617344.pth -[2023-10-10 23:28:35,897][98559] Updated weights for policy 0, policy_version 67060 (0.0008) -[2023-10-10 23:28:36,263][98559] Updated weights for policy 0, policy_version 67070 (0.0007) -[2023-10-10 23:28:36,338][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000067072_68681728.pth... -[2023-10-10 23:28:36,378][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000065440_67010560.pth -[2023-10-10 23:28:38,245][98560] Updated weights for policy 1, policy_version 66662 (0.0009) -[2023-10-10 23:28:38,626][98560] Updated weights for policy 1, policy_version 66672 (0.0008) -[2023-10-10 23:28:38,986][98560] Updated weights for policy 1, policy_version 66682 (0.0010) -[2023-10-10 23:28:40,369][98559] Updated weights for policy 0, policy_version 67080 (0.0007) -[2023-10-10 23:28:40,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 136970240. Throughput: 0: 1722.0, 1: 1698.9. Samples: 34249070. Policy #0 lag: (min: 10.0, avg: 14.1, max: 42.0) -[2023-10-10 23:28:40,557][97672] Avg episode reward: [(0, '-1.420'), (1, '22.800')] -[2023-10-10 23:28:40,744][98559] Updated weights for policy 0, policy_version 67090 (0.0009) -[2023-10-10 23:28:41,110][98559] Updated weights for policy 0, policy_version 67100 (0.0010) -[2023-10-10 23:28:43,067][98560] Updated weights for policy 1, policy_version 66692 (0.0011) -[2023-10-10 23:28:43,429][98560] Updated weights for policy 1, policy_version 66702 (0.0007) -[2023-10-10 23:28:43,801][98560] Updated weights for policy 1, policy_version 66712 (0.0007) -[2023-10-10 23:28:45,043][98559] Updated weights for policy 0, policy_version 67110 (0.0009) -[2023-10-10 23:28:45,410][98559] Updated weights for policy 0, policy_version 67120 (0.0007) -[2023-10-10 23:28:45,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 137035776. Throughput: 0: 1721.1, 1: 1679.2. Samples: 34269362. Policy #0 lag: (min: 10.0, avg: 14.1, max: 42.0) -[2023-10-10 23:28:45,557][97672] Avg episode reward: [(0, '-1.420'), (1, '22.760')] -[2023-10-10 23:28:45,783][98559] Updated weights for policy 0, policy_version 67130 (0.0007) -[2023-10-10 23:28:47,765][98560] Updated weights for policy 1, policy_version 66722 (0.0008) -[2023-10-10 23:28:48,134][98560] Updated weights for policy 1, policy_version 66732 (0.0009) -[2023-10-10 23:28:48,495][98560] Updated weights for policy 1, policy_version 66742 (0.0007) -[2023-10-10 23:28:48,860][98560] Updated weights for policy 1, policy_version 66752 (0.0010) -[2023-10-10 23:28:49,842][98559] Updated weights for policy 0, policy_version 67140 (0.0010) -[2023-10-10 23:28:50,211][98559] Updated weights for policy 0, policy_version 67150 (0.0010) -[2023-10-10 23:28:50,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 137101312. Throughput: 0: 1701.7, 1: 1689.7. Samples: 34289216. Policy #0 lag: (min: 10.0, avg: 14.1, max: 42.0) -[2023-10-10 23:28:50,557][97672] Avg episode reward: [(0, '-1.420'), (1, '22.740')] -[2023-10-10 23:28:50,578][98559] Updated weights for policy 0, policy_version 67160 (0.0009) -[2023-10-10 23:28:52,849][98560] Updated weights for policy 1, policy_version 66762 (0.0007) -[2023-10-10 23:28:53,222][98560] Updated weights for policy 1, policy_version 66772 (0.0008) -[2023-10-10 23:28:53,576][98560] Updated weights for policy 1, policy_version 66782 (0.0009) -[2023-10-10 23:28:54,596][98559] Updated weights for policy 0, policy_version 67170 (0.0008) -[2023-10-10 23:28:54,963][98559] Updated weights for policy 0, policy_version 67180 (0.0007) -[2023-10-10 23:28:55,325][98559] Updated weights for policy 0, policy_version 67190 (0.0007) -[2023-10-10 23:28:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 137166848. Throughput: 0: 1716.0, 1: 1702.9. Samples: 34300390. Policy #0 lag: (min: 10.0, avg: 14.1, max: 42.0) -[2023-10-10 23:28:55,556][97672] Avg episode reward: [(0, '-1.420'), (1, '22.780')] -[2023-10-10 23:28:55,694][98559] Updated weights for policy 0, policy_version 67200 (0.0007) -[2023-10-10 23:28:57,552][98560] Updated weights for policy 1, policy_version 66792 (0.0009) -[2023-10-10 23:28:57,922][98560] Updated weights for policy 1, policy_version 66802 (0.0008) -[2023-10-10 23:28:58,292][98560] Updated weights for policy 1, policy_version 66812 (0.0010) -[2023-10-10 23:28:59,608][98559] Updated weights for policy 0, policy_version 67210 (0.0010) -[2023-10-10 23:28:59,962][98559] Updated weights for policy 0, policy_version 67220 (0.0008) -[2023-10-10 23:29:00,329][98559] Updated weights for policy 0, policy_version 67230 (0.0007) -[2023-10-10 23:29:00,556][97672] Fps is (10 sec: 16383.6, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 137265152. Throughput: 0: 1712.2, 1: 1678.4. Samples: 34320164. Policy #0 lag: (min: 10.0, avg: 14.1, max: 42.0) -[2023-10-10 23:29:00,557][97672] Avg episode reward: [(0, '-1.420'), (1, '22.740')] -[2023-10-10 23:29:02,398][98560] Updated weights for policy 1, policy_version 66822 (0.0011) -[2023-10-10 23:29:02,768][98560] Updated weights for policy 1, policy_version 66832 (0.0008) -[2023-10-10 23:29:03,139][98560] Updated weights for policy 1, policy_version 66842 (0.0009) -[2023-10-10 23:29:04,252][98559] Updated weights for policy 0, policy_version 67240 (0.0007) -[2023-10-10 23:29:04,613][98559] Updated weights for policy 0, policy_version 67250 (0.0008) -[2023-10-10 23:29:04,979][98559] Updated weights for policy 0, policy_version 67260 (0.0008) -[2023-10-10 23:29:05,556][97672] Fps is (10 sec: 16383.6, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 137330688. Throughput: 0: 1689.5, 1: 1703.5. Samples: 34340278. Policy #0 lag: (min: 10.0, avg: 14.1, max: 42.0) -[2023-10-10 23:29:05,557][97672] Avg episode reward: [(0, '-1.420'), (1, '22.680')] -[2023-10-10 23:29:07,098][98560] Updated weights for policy 1, policy_version 66852 (0.0007) -[2023-10-10 23:29:07,458][98560] Updated weights for policy 1, policy_version 66862 (0.0007) -[2023-10-10 23:29:07,822][98560] Updated weights for policy 1, policy_version 66872 (0.0008) -[2023-10-10 23:29:08,912][98559] Updated weights for policy 0, policy_version 67270 (0.0009) -[2023-10-10 23:29:09,281][98559] Updated weights for policy 0, policy_version 67280 (0.0009) -[2023-10-10 23:29:09,645][98559] Updated weights for policy 0, policy_version 67290 (0.0007) -[2023-10-10 23:29:10,556][97672] Fps is (10 sec: 13107.7, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 137396224. Throughput: 0: 1722.7, 1: 1688.1. Samples: 34351438. Policy #0 lag: (min: 10.0, avg: 14.1, max: 42.0) -[2023-10-10 23:29:10,556][97672] Avg episode reward: [(0, '-1.420'), (1, '22.640')] -[2023-10-10 23:29:11,800][98560] Updated weights for policy 1, policy_version 66882 (0.0009) -[2023-10-10 23:29:12,166][98560] Updated weights for policy 1, policy_version 66892 (0.0010) -[2023-10-10 23:29:12,530][98560] Updated weights for policy 1, policy_version 66902 (0.0008) -[2023-10-10 23:29:12,903][98560] Updated weights for policy 1, policy_version 66912 (0.0009) -[2023-10-10 23:29:13,670][98559] Updated weights for policy 0, policy_version 67300 (0.0007) -[2023-10-10 23:29:14,038][98559] Updated weights for policy 0, policy_version 67310 (0.0007) -[2023-10-10 23:29:14,397][98559] Updated weights for policy 0, policy_version 67320 (0.0007) -[2023-10-10 23:29:15,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 137461760. Throughput: 0: 1702.6, 1: 1690.0. Samples: 34371164. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:29:15,556][97672] Avg episode reward: [(0, '-1.380'), (1, '22.620')] -[2023-10-10 23:29:17,007][98560] Updated weights for policy 1, policy_version 66922 (0.0007) -[2023-10-10 23:29:17,369][98560] Updated weights for policy 1, policy_version 66932 (0.0007) -[2023-10-10 23:29:17,741][98560] Updated weights for policy 1, policy_version 66942 (0.0008) -[2023-10-10 23:29:18,305][98559] Updated weights for policy 0, policy_version 67330 (0.0009) -[2023-10-10 23:29:18,680][98559] Updated weights for policy 0, policy_version 67340 (0.0008) -[2023-10-10 23:29:19,057][98559] Updated weights for policy 0, policy_version 67350 (0.0010) -[2023-10-10 23:29:19,417][98559] Updated weights for policy 0, policy_version 67360 (0.0011) -[2023-10-10 23:29:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 137527296. Throughput: 0: 1704.3, 1: 1711.0. Samples: 34391854. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:29:20,557][97672] Avg episode reward: [(0, '-1.380'), (1, '22.600')] -[2023-10-10 23:29:21,677][98560] Updated weights for policy 1, policy_version 66952 (0.0008) -[2023-10-10 23:29:22,050][98560] Updated weights for policy 1, policy_version 66962 (0.0007) -[2023-10-10 23:29:22,421][98560] Updated weights for policy 1, policy_version 66972 (0.0008) -[2023-10-10 23:29:23,402][98559] Updated weights for policy 0, policy_version 67370 (0.0007) -[2023-10-10 23:29:23,774][98559] Updated weights for policy 0, policy_version 67380 (0.0007) -[2023-10-10 23:29:24,141][98559] Updated weights for policy 0, policy_version 67390 (0.0010) -[2023-10-10 23:29:25,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 137592832. Throughput: 0: 1723.1, 1: 1676.6. Samples: 34402056. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:29:25,557][97672] Avg episode reward: [(0, '-1.380'), (1, '22.520')] -[2023-10-10 23:29:26,432][98560] Updated weights for policy 1, policy_version 66982 (0.0010) -[2023-10-10 23:29:26,795][98560] Updated weights for policy 1, policy_version 66992 (0.0008) -[2023-10-10 23:29:27,164][98560] Updated weights for policy 1, policy_version 67002 (0.0009) -[2023-10-10 23:29:27,964][98559] Updated weights for policy 0, policy_version 67400 (0.0009) -[2023-10-10 23:29:28,330][98559] Updated weights for policy 0, policy_version 67410 (0.0008) -[2023-10-10 23:29:28,698][98559] Updated weights for policy 0, policy_version 67420 (0.0009) -[2023-10-10 23:29:30,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 137658368. Throughput: 0: 1697.6, 1: 1698.7. Samples: 34422192. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:29:30,556][97672] Avg episode reward: [(0, '-1.380'), (1, '22.500')] -[2023-10-10 23:29:31,217][98560] Updated weights for policy 1, policy_version 67012 (0.0011) -[2023-10-10 23:29:31,597][98560] Updated weights for policy 1, policy_version 67022 (0.0009) -[2023-10-10 23:29:31,960][98560] Updated weights for policy 1, policy_version 67032 (0.0007) -[2023-10-10 23:29:32,720][98559] Updated weights for policy 0, policy_version 67430 (0.0010) -[2023-10-10 23:29:33,084][98559] Updated weights for policy 0, policy_version 67440 (0.0009) -[2023-10-10 23:29:33,458][98559] Updated weights for policy 0, policy_version 67450 (0.0007) -[2023-10-10 23:29:35,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 137723904. Throughput: 0: 1712.3, 1: 1707.7. Samples: 34443114. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:29:35,556][97672] Avg episode reward: [(0, '-1.360'), (1, '22.540')] -[2023-10-10 23:29:35,984][98560] Updated weights for policy 1, policy_version 67042 (0.0007) -[2023-10-10 23:29:36,355][98560] Updated weights for policy 1, policy_version 67052 (0.0009) -[2023-10-10 23:29:36,729][98560] Updated weights for policy 1, policy_version 67062 (0.0009) -[2023-10-10 23:29:37,093][98560] Updated weights for policy 1, policy_version 67072 (0.0009) -[2023-10-10 23:29:37,626][98559] Updated weights for policy 0, policy_version 67460 (0.0007) -[2023-10-10 23:29:37,988][98559] Updated weights for policy 0, policy_version 67470 (0.0009) -[2023-10-10 23:29:38,364][98559] Updated weights for policy 0, policy_version 67480 (0.0007) -[2023-10-10 23:29:40,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 137789440. Throughput: 0: 1705.2, 1: 1679.5. Samples: 34452704. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:29:40,556][97672] Avg episode reward: [(0, '-1.360'), (1, '22.460')] -[2023-10-10 23:29:41,034][98560] Updated weights for policy 1, policy_version 67082 (0.0009) -[2023-10-10 23:29:41,405][98560] Updated weights for policy 1, policy_version 67092 (0.0009) -[2023-10-10 23:29:41,776][98560] Updated weights for policy 1, policy_version 67102 (0.0009) -[2023-10-10 23:29:42,431][98559] Updated weights for policy 0, policy_version 67490 (0.0007) -[2023-10-10 23:29:42,803][98559] Updated weights for policy 0, policy_version 67500 (0.0008) -[2023-10-10 23:29:43,159][98559] Updated weights for policy 0, policy_version 67510 (0.0009) -[2023-10-10 23:29:43,532][98559] Updated weights for policy 0, policy_version 67520 (0.0008) -[2023-10-10 23:29:45,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 137854976. Throughput: 0: 1696.8, 1: 1705.3. Samples: 34473254. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:29:45,557][97672] Avg episode reward: [(0, '-1.440'), (1, '22.400')] -[2023-10-10 23:29:45,808][98560] Updated weights for policy 1, policy_version 67112 (0.0007) -[2023-10-10 23:29:46,177][98560] Updated weights for policy 1, policy_version 67122 (0.0010) -[2023-10-10 23:29:46,557][98560] Updated weights for policy 1, policy_version 67132 (0.0009) -[2023-10-10 23:29:47,499][98559] Updated weights for policy 0, policy_version 67530 (0.0010) -[2023-10-10 23:29:47,860][98559] Updated weights for policy 0, policy_version 67540 (0.0008) -[2023-10-10 23:29:48,232][98559] Updated weights for policy 0, policy_version 67550 (0.0009) -[2023-10-10 23:29:50,446][98560] Updated weights for policy 1, policy_version 67142 (0.0007) -[2023-10-10 23:29:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 137920512. Throughput: 0: 1716.1, 1: 1707.4. Samples: 34494334. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:29:50,557][97672] Avg episode reward: [(0, '-1.660'), (1, '22.440')] -[2023-10-10 23:29:50,821][98560] Updated weights for policy 1, policy_version 67152 (0.0009) -[2023-10-10 23:29:51,194][98560] Updated weights for policy 1, policy_version 67162 (0.0007) -[2023-10-10 23:29:52,142][98559] Updated weights for policy 0, policy_version 67560 (0.0008) -[2023-10-10 23:29:52,514][98559] Updated weights for policy 0, policy_version 67570 (0.0010) -[2023-10-10 23:29:52,880][98559] Updated weights for policy 0, policy_version 67580 (0.0009) -[2023-10-10 23:29:55,060][98560] Updated weights for policy 1, policy_version 67172 (0.0008) -[2023-10-10 23:29:55,425][98560] Updated weights for policy 1, policy_version 67182 (0.0009) -[2023-10-10 23:29:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 137986048. Throughput: 0: 1686.7, 1: 1700.7. Samples: 34503872. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:29:55,557][97672] Avg episode reward: [(0, '-1.660'), (1, '22.420')] -[2023-10-10 23:29:55,799][98560] Updated weights for policy 1, policy_version 67192 (0.0009) -[2023-10-10 23:29:56,899][98559] Updated weights for policy 0, policy_version 67590 (0.0008) -[2023-10-10 23:29:57,264][98559] Updated weights for policy 0, policy_version 67600 (0.0009) -[2023-10-10 23:29:57,623][98559] Updated weights for policy 0, policy_version 67610 (0.0009) -[2023-10-10 23:29:59,842][98560] Updated weights for policy 1, policy_version 67202 (0.0008) -[2023-10-10 23:30:00,201][98560] Updated weights for policy 1, policy_version 67212 (0.0007) -[2023-10-10 23:30:00,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 13662.6). Total num frames: 138051584. Throughput: 0: 1707.3, 1: 1714.9. Samples: 34525162. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:30:00,556][97672] Avg episode reward: [(0, '-1.660'), (1, '22.440')] -[2023-10-10 23:30:00,568][98560] Updated weights for policy 1, policy_version 67222 (0.0008) -[2023-10-10 23:30:00,942][98560] Updated weights for policy 1, policy_version 67232 (0.0007) -[2023-10-10 23:30:01,620][98559] Updated weights for policy 0, policy_version 67620 (0.0008) -[2023-10-10 23:30:01,991][98559] Updated weights for policy 0, policy_version 67630 (0.0009) -[2023-10-10 23:30:02,355][98559] Updated weights for policy 0, policy_version 67640 (0.0007) -[2023-10-10 23:30:05,133][98560] Updated weights for policy 1, policy_version 67242 (0.0010) -[2023-10-10 23:30:05,500][98560] Updated weights for policy 1, policy_version 67252 (0.0008) -[2023-10-10 23:30:05,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 138117120. Throughput: 0: 1719.3, 1: 1709.3. Samples: 34546142. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:30:05,558][97672] Avg episode reward: [(0, '-1.640'), (1, '22.400')] -[2023-10-10 23:30:05,874][98560] Updated weights for policy 1, policy_version 67262 (0.0009) -[2023-10-10 23:30:06,349][98559] Updated weights for policy 0, policy_version 67650 (0.0009) -[2023-10-10 23:30:06,741][98559] Updated weights for policy 0, policy_version 67660 (0.0008) -[2023-10-10 23:30:07,109][98559] Updated weights for policy 0, policy_version 67670 (0.0009) -[2023-10-10 23:30:07,471][98559] Updated weights for policy 0, policy_version 67680 (0.0010) -[2023-10-10 23:30:10,022][98560] Updated weights for policy 1, policy_version 67272 (0.0010) -[2023-10-10 23:30:10,389][98560] Updated weights for policy 1, policy_version 67282 (0.0010) -[2023-10-10 23:30:10,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 138182656. Throughput: 0: 1688.2, 1: 1707.3. Samples: 34554856. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:30:10,557][97672] Avg episode reward: [(0, '-1.640'), (1, '22.460')] -[2023-10-10 23:30:10,757][98560] Updated weights for policy 1, policy_version 67292 (0.0010) -[2023-10-10 23:30:11,449][98559] Updated weights for policy 0, policy_version 67690 (0.0007) -[2023-10-10 23:30:11,811][98559] Updated weights for policy 0, policy_version 67700 (0.0007) -[2023-10-10 23:30:12,169][98559] Updated weights for policy 0, policy_version 67710 (0.0007) -[2023-10-10 23:30:14,752][98560] Updated weights for policy 1, policy_version 67302 (0.0010) -[2023-10-10 23:30:15,128][98560] Updated weights for policy 1, policy_version 67312 (0.0010) -[2023-10-10 23:30:15,493][98560] Updated weights for policy 1, policy_version 67322 (0.0008) -[2023-10-10 23:30:15,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 138248192. Throughput: 0: 1714.6, 1: 1703.9. Samples: 34576024. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:30:15,557][97672] Avg episode reward: [(0, '-1.620'), (1, '22.420')] -[2023-10-10 23:30:16,157][98559] Updated weights for policy 0, policy_version 67720 (0.0008) -[2023-10-10 23:30:16,527][98559] Updated weights for policy 0, policy_version 67730 (0.0008) -[2023-10-10 23:30:16,895][98559] Updated weights for policy 0, policy_version 67740 (0.0010) -[2023-10-10 23:30:19,377][98560] Updated weights for policy 1, policy_version 67332 (0.0008) -[2023-10-10 23:30:19,738][98560] Updated weights for policy 1, policy_version 67342 (0.0008) -[2023-10-10 23:30:20,108][98560] Updated weights for policy 1, policy_version 67352 (0.0008) -[2023-10-10 23:30:20,556][97672] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 138346496. Throughput: 0: 1718.1, 1: 1694.2. Samples: 34596670. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:30:20,556][97672] Avg episode reward: [(0, '-1.620'), (1, '22.460')] -[2023-10-10 23:30:20,846][98559] Updated weights for policy 0, policy_version 67750 (0.0010) -[2023-10-10 23:30:21,212][98559] Updated weights for policy 0, policy_version 67760 (0.0009) -[2023-10-10 23:30:21,584][98559] Updated weights for policy 0, policy_version 67770 (0.0010) -[2023-10-10 23:30:24,107][98560] Updated weights for policy 1, policy_version 67362 (0.0008) -[2023-10-10 23:30:24,480][98560] Updated weights for policy 1, policy_version 67372 (0.0009) -[2023-10-10 23:30:24,839][98560] Updated weights for policy 1, policy_version 67382 (0.0007) -[2023-10-10 23:30:25,214][98560] Updated weights for policy 1, policy_version 67392 (0.0011) -[2023-10-10 23:30:25,514][98559] Updated weights for policy 0, policy_version 67780 (0.0009) -[2023-10-10 23:30:25,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 138412032. Throughput: 0: 1709.0, 1: 1707.6. Samples: 34606450. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:30:25,557][97672] Avg episode reward: [(0, '-1.620'), (1, '22.500')] -[2023-10-10 23:30:25,880][98559] Updated weights for policy 0, policy_version 67790 (0.0009) -[2023-10-10 23:30:26,235][98559] Updated weights for policy 0, policy_version 67800 (0.0007) -[2023-10-10 23:30:29,220][98560] Updated weights for policy 1, policy_version 67402 (0.0009) -[2023-10-10 23:30:29,582][98560] Updated weights for policy 1, policy_version 67412 (0.0009) -[2023-10-10 23:30:29,954][98560] Updated weights for policy 1, policy_version 67422 (0.0008) -[2023-10-10 23:30:30,214][98559] Updated weights for policy 0, policy_version 67810 (0.0007) -[2023-10-10 23:30:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 138477568. Throughput: 0: 1722.2, 1: 1708.5. Samples: 34627636. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:30:30,556][97672] Avg episode reward: [(0, '-1.620'), (1, '22.560')] -[2023-10-10 23:30:30,577][98559] Updated weights for policy 0, policy_version 67820 (0.0008) -[2023-10-10 23:30:30,943][98559] Updated weights for policy 0, policy_version 67830 (0.0008) -[2023-10-10 23:30:31,308][98559] Updated weights for policy 0, policy_version 67840 (0.0009) -[2023-10-10 23:30:33,973][98560] Updated weights for policy 1, policy_version 67432 (0.0007) -[2023-10-10 23:30:34,345][98560] Updated weights for policy 1, policy_version 67442 (0.0007) -[2023-10-10 23:30:34,721][98560] Updated weights for policy 1, policy_version 67452 (0.0008) -[2023-10-10 23:30:35,230][98559] Updated weights for policy 0, policy_version 67850 (0.0009) -[2023-10-10 23:30:35,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 138543104. Throughput: 0: 1713.3, 1: 1686.1. Samples: 34647308. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:30:35,557][97672] Avg episode reward: [(0, '-1.620'), (1, '22.580')] -[2023-10-10 23:30:35,570][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000067456_69074944.pth... -[2023-10-10 23:30:35,595][98559] Updated weights for policy 0, policy_version 67860 (0.0009) -[2023-10-10 23:30:35,606][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000065856_67436544.pth -[2023-10-10 23:30:35,973][98559] Updated weights for policy 0, policy_version 67870 (0.0010) -[2023-10-10 23:30:36,037][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000067872_69500928.pth... -[2023-10-10 23:30:36,077][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000066240_67829760.pth -[2023-10-10 23:30:38,804][98560] Updated weights for policy 1, policy_version 67462 (0.0008) -[2023-10-10 23:30:39,169][98560] Updated weights for policy 1, policy_version 67472 (0.0010) -[2023-10-10 23:30:39,541][98560] Updated weights for policy 1, policy_version 67482 (0.0007) -[2023-10-10 23:30:40,028][98559] Updated weights for policy 0, policy_version 67880 (0.0009) -[2023-10-10 23:30:40,399][98559] Updated weights for policy 0, policy_version 67890 (0.0009) -[2023-10-10 23:30:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 138608640. Throughput: 0: 1722.7, 1: 1705.2. Samples: 34658124. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:30:40,557][97672] Avg episode reward: [(0, '-1.620'), (1, '22.580')] -[2023-10-10 23:30:40,763][98559] Updated weights for policy 0, policy_version 67900 (0.0009) -[2023-10-10 23:30:43,663][98560] Updated weights for policy 1, policy_version 67492 (0.0008) -[2023-10-10 23:30:44,043][98560] Updated weights for policy 1, policy_version 67502 (0.0008) -[2023-10-10 23:30:44,408][98560] Updated weights for policy 1, policy_version 67512 (0.0007) -[2023-10-10 23:30:44,837][98559] Updated weights for policy 0, policy_version 67910 (0.0008) -[2023-10-10 23:30:45,196][98559] Updated weights for policy 0, policy_version 67920 (0.0007) -[2023-10-10 23:30:45,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 138674176. Throughput: 0: 1718.5, 1: 1693.8. Samples: 34678718. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-10 23:30:45,557][97672] Avg episode reward: [(0, '-1.620'), (1, '22.580')] -[2023-10-10 23:30:45,562][98559] Updated weights for policy 0, policy_version 67930 (0.0008) -[2023-10-10 23:30:48,429][98560] Updated weights for policy 1, policy_version 67522 (0.0008) -[2023-10-10 23:30:48,798][98560] Updated weights for policy 1, policy_version 67532 (0.0009) -[2023-10-10 23:30:49,164][98560] Updated weights for policy 1, policy_version 67542 (0.0007) -[2023-10-10 23:30:49,454][98559] Updated weights for policy 0, policy_version 67940 (0.0009) -[2023-10-10 23:30:49,538][98560] Updated weights for policy 1, policy_version 67552 (0.0007) -[2023-10-10 23:30:49,818][98559] Updated weights for policy 0, policy_version 67950 (0.0009) -[2023-10-10 23:30:50,182][98559] Updated weights for policy 0, policy_version 67960 (0.0007) -[2023-10-10 23:30:50,556][97672] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 138772480. Throughput: 0: 1693.1, 1: 1670.8. Samples: 34697516. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-10 23:30:50,557][97672] Avg episode reward: [(0, '-1.620'), (1, '22.620')] -[2023-10-10 23:30:53,600][98560] Updated weights for policy 1, policy_version 67562 (0.0009) -[2023-10-10 23:30:53,973][98560] Updated weights for policy 1, policy_version 67572 (0.0008) -[2023-10-10 23:30:54,093][98559] Updated weights for policy 0, policy_version 67970 (0.0009) -[2023-10-10 23:30:54,342][98560] Updated weights for policy 1, policy_version 67582 (0.0008) -[2023-10-10 23:30:54,471][98559] Updated weights for policy 0, policy_version 67980 (0.0008) -[2023-10-10 23:30:54,846][98559] Updated weights for policy 0, policy_version 67990 (0.0008) -[2023-10-10 23:30:55,216][98559] Updated weights for policy 0, policy_version 68000 (0.0007) -[2023-10-10 23:30:55,556][97672] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 138838016. Throughput: 0: 1723.8, 1: 1706.1. Samples: 34709200. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-10 23:30:55,557][97672] Avg episode reward: [(0, '-1.620'), (1, '22.600')] -[2023-10-10 23:30:58,302][98560] Updated weights for policy 1, policy_version 67592 (0.0008) -[2023-10-10 23:30:58,665][98560] Updated weights for policy 1, policy_version 67602 (0.0008) -[2023-10-10 23:30:59,032][98560] Updated weights for policy 1, policy_version 67612 (0.0007) -[2023-10-10 23:30:59,173][98559] Updated weights for policy 0, policy_version 68010 (0.0009) -[2023-10-10 23:30:59,542][98559] Updated weights for policy 0, policy_version 68020 (0.0010) -[2023-10-10 23:30:59,907][98559] Updated weights for policy 0, policy_version 68030 (0.0009) -[2023-10-10 23:31:00,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 138903552. Throughput: 0: 1708.3, 1: 1688.1. Samples: 34728862. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-10 23:31:00,557][97672] Avg episode reward: [(0, '-1.620'), (1, '22.580')] -[2023-10-10 23:31:02,987][98560] Updated weights for policy 1, policy_version 67622 (0.0009) -[2023-10-10 23:31:03,351][98560] Updated weights for policy 1, policy_version 67632 (0.0007) -[2023-10-10 23:31:03,709][98560] Updated weights for policy 1, policy_version 67642 (0.0008) -[2023-10-10 23:31:03,784][98559] Updated weights for policy 0, policy_version 68040 (0.0008) -[2023-10-10 23:31:04,152][98559] Updated weights for policy 0, policy_version 68050 (0.0007) -[2023-10-10 23:31:04,521][98559] Updated weights for policy 0, policy_version 68060 (0.0008) -[2023-10-10 23:31:05,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.6, 300 sec: 13662.6). Total num frames: 138969088. Throughput: 0: 1694.7, 1: 1687.3. Samples: 34748860. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-10 23:31:05,556][97672] Avg episode reward: [(0, '-1.620'), (1, '22.580')] -[2023-10-10 23:31:07,629][98560] Updated weights for policy 1, policy_version 67652 (0.0007) -[2023-10-10 23:31:07,995][98560] Updated weights for policy 1, policy_version 67662 (0.0010) -[2023-10-10 23:31:08,370][98560] Updated weights for policy 1, policy_version 67672 (0.0010) -[2023-10-10 23:31:08,732][98559] Updated weights for policy 0, policy_version 68070 (0.0008) -[2023-10-10 23:31:09,104][98559] Updated weights for policy 0, policy_version 68080 (0.0007) -[2023-10-10 23:31:09,470][98559] Updated weights for policy 0, policy_version 68090 (0.0007) -[2023-10-10 23:31:10,556][97672] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 139034624. Throughput: 0: 1723.4, 1: 1700.6. Samples: 34760532. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-10 23:31:10,556][97672] Avg episode reward: [(0, '-1.620'), (1, '22.520')] -[2023-10-10 23:31:12,504][98560] Updated weights for policy 1, policy_version 67682 (0.0007) -[2023-10-10 23:31:12,870][98560] Updated weights for policy 1, policy_version 67692 (0.0008) -[2023-10-10 23:31:13,234][98560] Updated weights for policy 1, policy_version 67702 (0.0008) -[2023-10-10 23:31:13,290][98559] Updated weights for policy 0, policy_version 68100 (0.0007) -[2023-10-10 23:31:13,602][98560] Updated weights for policy 1, policy_version 67712 (0.0007) -[2023-10-10 23:31:13,655][98559] Updated weights for policy 0, policy_version 68110 (0.0010) -[2023-10-10 23:31:14,019][98559] Updated weights for policy 0, policy_version 68120 (0.0009) -[2023-10-10 23:31:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 139100160. Throughput: 0: 1698.8, 1: 1673.3. Samples: 34779378. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-10 23:31:15,556][97672] Avg episode reward: [(0, '-1.620'), (1, '22.480')] -[2023-10-10 23:31:17,639][98560] Updated weights for policy 1, policy_version 67722 (0.0008) -[2023-10-10 23:31:17,778][98559] Updated weights for policy 0, policy_version 68130 (0.0009) -[2023-10-10 23:31:18,005][98560] Updated weights for policy 1, policy_version 67732 (0.0008) -[2023-10-10 23:31:18,139][98559] Updated weights for policy 0, policy_version 68140 (0.0008) -[2023-10-10 23:31:18,371][98560] Updated weights for policy 1, policy_version 67742 (0.0008) -[2023-10-10 23:31:18,505][98559] Updated weights for policy 0, policy_version 68150 (0.0007) -[2023-10-10 23:31:18,877][98559] Updated weights for policy 0, policy_version 68160 (0.0008) -[2023-10-10 23:31:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 139165696. Throughput: 0: 1710.5, 1: 1692.5. Samples: 34800446. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-10 23:31:20,557][97672] Avg episode reward: [(0, '-1.620'), (1, '22.540')] -[2023-10-10 23:31:22,460][98560] Updated weights for policy 1, policy_version 67752 (0.0008) -[2023-10-10 23:31:22,817][98560] Updated weights for policy 1, policy_version 67762 (0.0009) -[2023-10-10 23:31:23,027][98559] Updated weights for policy 0, policy_version 68170 (0.0007) -[2023-10-10 23:31:23,185][98560] Updated weights for policy 1, policy_version 67772 (0.0009) -[2023-10-10 23:31:23,389][98559] Updated weights for policy 0, policy_version 68180 (0.0007) -[2023-10-10 23:31:23,752][98559] Updated weights for policy 0, policy_version 68190 (0.0008) -[2023-10-10 23:31:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 139231232. Throughput: 0: 1710.5, 1: 1683.5. Samples: 34810854. Policy #0 lag: (min: 19.0, avg: 23.5, max: 51.0) -[2023-10-10 23:31:25,556][97672] Avg episode reward: [(0, '-1.620'), (1, '22.520')] -[2023-10-10 23:31:27,223][98560] Updated weights for policy 1, policy_version 67782 (0.0007) -[2023-10-10 23:31:27,585][98560] Updated weights for policy 1, policy_version 67792 (0.0009) -[2023-10-10 23:31:27,885][98559] Updated weights for policy 0, policy_version 68200 (0.0010) -[2023-10-10 23:31:27,960][98560] Updated weights for policy 1, policy_version 67802 (0.0009) -[2023-10-10 23:31:28,252][98559] Updated weights for policy 0, policy_version 68210 (0.0010) -[2023-10-10 23:31:28,616][98559] Updated weights for policy 0, policy_version 68220 (0.0009) -[2023-10-10 23:31:30,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 139296768. Throughput: 0: 1688.6, 1: 1668.8. Samples: 34829804. Policy #0 lag: (min: 19.0, avg: 23.5, max: 51.0) -[2023-10-10 23:31:30,556][97672] Avg episode reward: [(0, '-1.620'), (1, '22.540')] -[2023-10-10 23:31:32,330][98560] Updated weights for policy 1, policy_version 67812 (0.0009) -[2023-10-10 23:31:32,687][98560] Updated weights for policy 1, policy_version 67822 (0.0008) -[2023-10-10 23:31:32,954][98559] Updated weights for policy 0, policy_version 68230 (0.0009) -[2023-10-10 23:31:33,052][98560] Updated weights for policy 1, policy_version 67832 (0.0009) -[2023-10-10 23:31:33,310][98559] Updated weights for policy 0, policy_version 68240 (0.0008) -[2023-10-10 23:31:33,676][98559] Updated weights for policy 0, policy_version 68250 (0.0010) -[2023-10-10 23:31:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 139362304. Throughput: 0: 1697.2, 1: 1679.7. Samples: 34849480. Policy #0 lag: (min: 19.0, avg: 23.5, max: 51.0) -[2023-10-10 23:31:35,557][97672] Avg episode reward: [(0, '-1.620'), (1, '22.560')] -[2023-10-10 23:31:37,422][98560] Updated weights for policy 1, policy_version 67842 (0.0008) -[2023-10-10 23:31:37,792][98560] Updated weights for policy 1, policy_version 67852 (0.0008) -[2023-10-10 23:31:37,896][98559] Updated weights for policy 0, policy_version 68260 (0.0010) -[2023-10-10 23:31:38,161][98560] Updated weights for policy 1, policy_version 67862 (0.0008) -[2023-10-10 23:31:38,259][98559] Updated weights for policy 0, policy_version 68270 (0.0009) -[2023-10-10 23:31:38,530][98560] Updated weights for policy 1, policy_version 67872 (0.0008) -[2023-10-10 23:31:38,614][98559] Updated weights for policy 0, policy_version 68280 (0.0008) -[2023-10-10 23:31:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 139427840. Throughput: 0: 1682.8, 1: 1660.4. Samples: 34859648. Policy #0 lag: (min: 19.0, avg: 23.5, max: 51.0) -[2023-10-10 23:31:40,557][97672] Avg episode reward: [(0, '-1.620'), (1, '22.540')] -[2023-10-10 23:31:43,010][98560] Updated weights for policy 1, policy_version 67882 (0.0009) -[2023-10-10 23:31:43,215][98559] Updated weights for policy 0, policy_version 68290 (0.0011) -[2023-10-10 23:31:43,375][98560] Updated weights for policy 1, policy_version 67892 (0.0009) -[2023-10-10 23:31:43,610][98559] Updated weights for policy 0, policy_version 68300 (0.0009) -[2023-10-10 23:31:43,744][98560] Updated weights for policy 1, policy_version 67902 (0.0009) -[2023-10-10 23:31:43,978][98559] Updated weights for policy 0, policy_version 68310 (0.0009) -[2023-10-10 23:31:44,338][98559] Updated weights for policy 0, policy_version 68320 (0.0008) -[2023-10-10 23:31:45,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 139493376. Throughput: 0: 1653.4, 1: 1641.0. Samples: 34877112. Policy #0 lag: (min: 19.0, avg: 23.5, max: 51.0) -[2023-10-10 23:31:45,557][97672] Avg episode reward: [(0, '-1.620'), (1, '22.620')] -[2023-10-10 23:31:48,406][98560] Updated weights for policy 1, policy_version 67912 (0.0009) -[2023-10-10 23:31:48,667][98559] Updated weights for policy 0, policy_version 68330 (0.0009) -[2023-10-10 23:31:48,778][98560] Updated weights for policy 1, policy_version 67922 (0.0009) -[2023-10-10 23:31:49,027][98559] Updated weights for policy 0, policy_version 68340 (0.0008) -[2023-10-10 23:31:49,152][98560] Updated weights for policy 1, policy_version 67932 (0.0009) -[2023-10-10 23:31:49,392][98559] Updated weights for policy 0, policy_version 68350 (0.0009) -[2023-10-10 23:31:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 139558912. Throughput: 0: 1644.0, 1: 1621.7. Samples: 34895820. Policy #0 lag: (min: 19.0, avg: 23.5, max: 51.0) -[2023-10-10 23:31:50,557][97672] Avg episode reward: [(0, '-1.620'), (1, '22.720')] -[2023-10-10 23:31:53,423][98560] Updated weights for policy 1, policy_version 67942 (0.0009) -[2023-10-10 23:31:53,780][98560] Updated weights for policy 1, policy_version 67952 (0.0008) -[2023-10-10 23:31:53,812][98559] Updated weights for policy 0, policy_version 68360 (0.0009) -[2023-10-10 23:31:54,148][98560] Updated weights for policy 1, policy_version 67962 (0.0007) -[2023-10-10 23:31:54,178][98559] Updated weights for policy 0, policy_version 68370 (0.0010) -[2023-10-10 23:31:54,549][98559] Updated weights for policy 0, policy_version 68380 (0.0010) -[2023-10-10 23:31:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 139624448. Throughput: 0: 1636.3, 1: 1614.7. Samples: 34906830. Policy #0 lag: (min: 19.0, avg: 23.5, max: 51.0) -[2023-10-10 23:31:55,557][97672] Avg episode reward: [(0, '-1.620'), (1, '22.700')] -[2023-10-10 23:31:58,417][98560] Updated weights for policy 1, policy_version 67972 (0.0008) -[2023-10-10 23:31:58,781][98560] Updated weights for policy 1, policy_version 67982 (0.0008) -[2023-10-10 23:31:58,907][98559] Updated weights for policy 0, policy_version 68390 (0.0009) -[2023-10-10 23:31:59,146][98560] Updated weights for policy 1, policy_version 67992 (0.0009) -[2023-10-10 23:31:59,272][98559] Updated weights for policy 0, policy_version 68400 (0.0007) -[2023-10-10 23:31:59,648][98559] Updated weights for policy 0, policy_version 68410 (0.0008) -[2023-10-10 23:32:00,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 13662.6). Total num frames: 139689984. Throughput: 0: 1628.1, 1: 1618.7. Samples: 34925484. Policy #0 lag: (min: 19.0, avg: 23.5, max: 51.0) -[2023-10-10 23:32:00,556][97672] Avg episode reward: [(0, '-1.620'), (1, '22.760')] -[2023-10-10 23:32:03,654][98560] Updated weights for policy 1, policy_version 68002 (0.0008) -[2023-10-10 23:32:04,015][98559] Updated weights for policy 0, policy_version 68420 (0.0008) -[2023-10-10 23:32:04,019][98560] Updated weights for policy 1, policy_version 68012 (0.0009) -[2023-10-10 23:32:04,378][98559] Updated weights for policy 0, policy_version 68430 (0.0007) -[2023-10-10 23:32:04,388][98560] Updated weights for policy 1, policy_version 68022 (0.0008) -[2023-10-10 23:32:04,747][98559] Updated weights for policy 0, policy_version 68440 (0.0009) -[2023-10-10 23:32:04,750][98560] Updated weights for policy 1, policy_version 68032 (0.0010) -[2023-10-10 23:32:05,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 139755520. Throughput: 0: 1593.3, 1: 1586.8. Samples: 34943552. Policy #0 lag: (min: 19.0, avg: 23.5, max: 51.0) -[2023-10-10 23:32:05,556][97672] Avg episode reward: [(0, '-1.620'), (1, '22.760')] -[2023-10-10 23:32:08,749][98560] Updated weights for policy 1, policy_version 68042 (0.0009) -[2023-10-10 23:32:08,785][98559] Updated weights for policy 0, policy_version 68450 (0.0009) -[2023-10-10 23:32:09,123][98560] Updated weights for policy 1, policy_version 68052 (0.0008) -[2023-10-10 23:32:09,153][98559] Updated weights for policy 0, policy_version 68460 (0.0007) -[2023-10-10 23:32:09,489][98560] Updated weights for policy 1, policy_version 68062 (0.0007) -[2023-10-10 23:32:09,514][98559] Updated weights for policy 0, policy_version 68470 (0.0007) -[2023-10-10 23:32:09,888][98559] Updated weights for policy 0, policy_version 68480 (0.0009) -[2023-10-10 23:32:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 139821056. Throughput: 0: 1609.2, 1: 1601.4. Samples: 34955330. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:32:10,556][97672] Avg episode reward: [(0, '-1.620'), (1, '22.780')] -[2023-10-10 23:32:13,462][98560] Updated weights for policy 1, policy_version 68072 (0.0010) -[2023-10-10 23:32:13,826][98560] Updated weights for policy 1, policy_version 68082 (0.0010) -[2023-10-10 23:32:13,996][98559] Updated weights for policy 0, policy_version 68490 (0.0008) -[2023-10-10 23:32:14,188][98560] Updated weights for policy 1, policy_version 68092 (0.0008) -[2023-10-10 23:32:14,368][98559] Updated weights for policy 0, policy_version 68500 (0.0009) -[2023-10-10 23:32:14,723][98559] Updated weights for policy 0, policy_version 68510 (0.0009) -[2023-10-10 23:32:15,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 139886592. Throughput: 0: 1614.7, 1: 1609.2. Samples: 34974882. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:32:15,557][97672] Avg episode reward: [(0, '-1.600'), (1, '22.800')] -[2023-10-10 23:32:18,272][98560] Updated weights for policy 1, policy_version 68102 (0.0009) -[2023-10-10 23:32:18,599][98559] Updated weights for policy 0, policy_version 68520 (0.0008) -[2023-10-10 23:32:18,633][98560] Updated weights for policy 1, policy_version 68112 (0.0009) -[2023-10-10 23:32:18,970][98559] Updated weights for policy 0, policy_version 68530 (0.0007) -[2023-10-10 23:32:18,990][98560] Updated weights for policy 1, policy_version 68122 (0.0009) -[2023-10-10 23:32:19,333][98559] Updated weights for policy 0, policy_version 68540 (0.0008) -[2023-10-10 23:32:20,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 139952128. Throughput: 0: 1620.8, 1: 1607.3. Samples: 34994742. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:32:20,557][97672] Avg episode reward: [(0, '-1.600'), (1, '22.780')] -[2023-10-10 23:32:23,071][98560] Updated weights for policy 1, policy_version 68132 (0.0009) -[2023-10-10 23:32:23,285][98559] Updated weights for policy 0, policy_version 68550 (0.0009) -[2023-10-10 23:32:23,439][98560] Updated weights for policy 1, policy_version 68142 (0.0009) -[2023-10-10 23:32:23,646][98559] Updated weights for policy 0, policy_version 68560 (0.0009) -[2023-10-10 23:32:23,806][98560] Updated weights for policy 1, policy_version 68152 (0.0007) -[2023-10-10 23:32:24,015][98559] Updated weights for policy 0, policy_version 68570 (0.0007) -[2023-10-10 23:32:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 140017664. Throughput: 0: 1634.7, 1: 1623.7. Samples: 35006276. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:32:25,557][97672] Avg episode reward: [(0, '-1.600'), (1, '22.720')] -[2023-10-10 23:32:27,801][98560] Updated weights for policy 1, policy_version 68162 (0.0008) -[2023-10-10 23:32:27,891][98559] Updated weights for policy 0, policy_version 68580 (0.0008) -[2023-10-10 23:32:28,160][98560] Updated weights for policy 1, policy_version 68172 (0.0008) -[2023-10-10 23:32:28,256][98559] Updated weights for policy 0, policy_version 68590 (0.0008) -[2023-10-10 23:32:28,528][98560] Updated weights for policy 1, policy_version 68182 (0.0009) -[2023-10-10 23:32:28,626][98559] Updated weights for policy 0, policy_version 68600 (0.0008) -[2023-10-10 23:32:28,892][98560] Updated weights for policy 1, policy_version 68192 (0.0007) -[2023-10-10 23:32:30,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 140083200. Throughput: 0: 1657.2, 1: 1640.3. Samples: 35025498. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:32:30,556][97672] Avg episode reward: [(0, '-1.600'), (1, '22.720')] -[2023-10-10 23:32:32,635][98559] Updated weights for policy 0, policy_version 68610 (0.0008) -[2023-10-10 23:32:33,000][98560] Updated weights for policy 1, policy_version 68202 (0.0008) -[2023-10-10 23:32:33,048][98559] Updated weights for policy 0, policy_version 68620 (0.0009) -[2023-10-10 23:32:33,383][98560] Updated weights for policy 1, policy_version 68212 (0.0008) -[2023-10-10 23:32:33,413][98559] Updated weights for policy 0, policy_version 68630 (0.0008) -[2023-10-10 23:32:33,744][98560] Updated weights for policy 1, policy_version 68222 (0.0009) -[2023-10-10 23:32:33,770][98559] Updated weights for policy 0, policy_version 68640 (0.0007) -[2023-10-10 23:32:35,556][97672] Fps is (10 sec: 13106.7, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 140148736. Throughput: 0: 1676.7, 1: 1662.2. Samples: 35046072. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:32:35,558][97672] Avg episode reward: [(0, '-1.600'), (1, '22.560')] -[2023-10-10 23:32:35,569][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000068224_69861376.pth... -[2023-10-10 23:32:35,569][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000068640_70287360.pth... -[2023-10-10 23:32:35,601][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000066656_68255744.pth -[2023-10-10 23:32:35,612][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000067072_68681728.pth -[2023-10-10 23:32:37,658][98559] Updated weights for policy 0, policy_version 68650 (0.0008) -[2023-10-10 23:32:37,801][98560] Updated weights for policy 1, policy_version 68232 (0.0007) -[2023-10-10 23:32:38,029][98559] Updated weights for policy 0, policy_version 68660 (0.0008) -[2023-10-10 23:32:38,163][98560] Updated weights for policy 1, policy_version 68242 (0.0007) -[2023-10-10 23:32:38,390][98559] Updated weights for policy 0, policy_version 68670 (0.0009) -[2023-10-10 23:32:38,525][98560] Updated weights for policy 1, policy_version 68252 (0.0010) -[2023-10-10 23:32:40,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 140214272. Throughput: 0: 1660.9, 1: 1665.2. Samples: 35056504. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:32:40,557][97672] Avg episode reward: [(0, '-1.600'), (1, '22.560')] -[2023-10-10 23:32:42,442][98559] Updated weights for policy 0, policy_version 68680 (0.0007) -[2023-10-10 23:32:42,542][98560] Updated weights for policy 1, policy_version 68262 (0.0007) -[2023-10-10 23:32:42,808][98559] Updated weights for policy 0, policy_version 68690 (0.0008) -[2023-10-10 23:32:42,906][98560] Updated weights for policy 1, policy_version 68272 (0.0008) -[2023-10-10 23:32:43,164][98559] Updated weights for policy 0, policy_version 68700 (0.0008) -[2023-10-10 23:32:43,273][98560] Updated weights for policy 1, policy_version 68282 (0.0007) -[2023-10-10 23:32:45,556][97672] Fps is (10 sec: 13108.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 140279808. Throughput: 0: 1682.4, 1: 1662.9. Samples: 35076024. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:32:45,556][97672] Avg episode reward: [(0, '-1.600'), (1, '22.560')] -[2023-10-10 23:32:47,203][98560] Updated weights for policy 1, policy_version 68292 (0.0008) -[2023-10-10 23:32:47,235][98559] Updated weights for policy 0, policy_version 68710 (0.0008) -[2023-10-10 23:32:47,561][98560] Updated weights for policy 1, policy_version 68302 (0.0008) -[2023-10-10 23:32:47,605][98559] Updated weights for policy 0, policy_version 68720 (0.0009) -[2023-10-10 23:32:47,924][98560] Updated weights for policy 1, policy_version 68312 (0.0009) -[2023-10-10 23:32:47,969][98559] Updated weights for policy 0, policy_version 68730 (0.0009) -[2023-10-10 23:32:50,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 140345344. Throughput: 0: 1715.7, 1: 1699.9. Samples: 35097256. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:32:50,557][97672] Avg episode reward: [(0, '-1.600'), (1, '22.520')] -[2023-10-10 23:32:51,827][98560] Updated weights for policy 1, policy_version 68322 (0.0008) -[2023-10-10 23:32:52,114][98559] Updated weights for policy 0, policy_version 68740 (0.0007) -[2023-10-10 23:32:52,195][98560] Updated weights for policy 1, policy_version 68332 (0.0009) -[2023-10-10 23:32:52,483][98559] Updated weights for policy 0, policy_version 68750 (0.0008) -[2023-10-10 23:32:52,562][98560] Updated weights for policy 1, policy_version 68342 (0.0009) -[2023-10-10 23:32:52,841][98559] Updated weights for policy 0, policy_version 68760 (0.0007) -[2023-10-10 23:32:52,927][98560] Updated weights for policy 1, policy_version 68352 (0.0009) -[2023-10-10 23:32:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 140410880. Throughput: 0: 1688.4, 1: 1680.0. Samples: 35106904. Policy #0 lag: (min: 5.0, avg: 12.1, max: 37.0) -[2023-10-10 23:32:55,556][97672] Avg episode reward: [(0, '-1.600'), (1, '22.500')] -[2023-10-10 23:32:56,872][98559] Updated weights for policy 0, policy_version 68770 (0.0010) -[2023-10-10 23:32:56,881][98560] Updated weights for policy 1, policy_version 68362 (0.0008) -[2023-10-10 23:32:57,233][98559] Updated weights for policy 0, policy_version 68780 (0.0008) -[2023-10-10 23:32:57,251][98560] Updated weights for policy 1, policy_version 68372 (0.0009) -[2023-10-10 23:32:57,604][98559] Updated weights for policy 0, policy_version 68790 (0.0009) -[2023-10-10 23:32:57,607][98560] Updated weights for policy 1, policy_version 68382 (0.0008) -[2023-10-10 23:32:57,964][98559] Updated weights for policy 0, policy_version 68800 (0.0008) -[2023-10-10 23:33:00,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 140476416. Throughput: 0: 1708.5, 1: 1692.9. Samples: 35127946. Policy #0 lag: (min: 5.0, avg: 12.1, max: 37.0) -[2023-10-10 23:33:00,557][97672] Avg episode reward: [(0, '-1.600'), (1, '22.600')] -[2023-10-10 23:33:01,622][98560] Updated weights for policy 1, policy_version 68392 (0.0008) -[2023-10-10 23:33:01,986][98560] Updated weights for policy 1, policy_version 68402 (0.0007) -[2023-10-10 23:33:02,091][98559] Updated weights for policy 0, policy_version 68810 (0.0007) -[2023-10-10 23:33:02,345][98560] Updated weights for policy 1, policy_version 68412 (0.0007) -[2023-10-10 23:33:02,442][98559] Updated weights for policy 0, policy_version 68820 (0.0007) -[2023-10-10 23:33:02,816][98559] Updated weights for policy 0, policy_version 68830 (0.0007) -[2023-10-10 23:33:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 140541952. Throughput: 0: 1715.0, 1: 1707.5. Samples: 35148756. Policy #0 lag: (min: 5.0, avg: 12.1, max: 37.0) -[2023-10-10 23:33:05,556][97672] Avg episode reward: [(0, '-1.600'), (1, '22.580')] -[2023-10-10 23:33:06,491][98560] Updated weights for policy 1, policy_version 68422 (0.0008) -[2023-10-10 23:33:06,692][98559] Updated weights for policy 0, policy_version 68840 (0.0007) -[2023-10-10 23:33:06,845][98560] Updated weights for policy 1, policy_version 68432 (0.0009) -[2023-10-10 23:33:07,057][98559] Updated weights for policy 0, policy_version 68850 (0.0007) -[2023-10-10 23:33:07,207][98560] Updated weights for policy 1, policy_version 68442 (0.0007) -[2023-10-10 23:33:07,421][98559] Updated weights for policy 0, policy_version 68860 (0.0008) -[2023-10-10 23:33:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 140607488. Throughput: 0: 1689.3, 1: 1679.4. Samples: 35157868. Policy #0 lag: (min: 5.0, avg: 12.1, max: 37.0) -[2023-10-10 23:33:10,557][97672] Avg episode reward: [(0, '-1.600'), (1, '22.580')] -[2023-10-10 23:33:11,260][98560] Updated weights for policy 1, policy_version 68452 (0.0009) -[2023-10-10 23:33:11,458][98559] Updated weights for policy 0, policy_version 68870 (0.0008) -[2023-10-10 23:33:11,622][98560] Updated weights for policy 1, policy_version 68462 (0.0007) -[2023-10-10 23:33:11,814][98559] Updated weights for policy 0, policy_version 68880 (0.0008) -[2023-10-10 23:33:11,994][98560] Updated weights for policy 1, policy_version 68472 (0.0007) -[2023-10-10 23:33:12,182][98559] Updated weights for policy 0, policy_version 68890 (0.0008) -[2023-10-10 23:33:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 140673024. Throughput: 0: 1704.7, 1: 1702.2. Samples: 35178810. Policy #0 lag: (min: 5.0, avg: 12.1, max: 37.0) -[2023-10-10 23:33:15,556][97672] Avg episode reward: [(0, '-1.600'), (1, '22.600')] -[2023-10-10 23:33:15,972][98560] Updated weights for policy 1, policy_version 68482 (0.0009) -[2023-10-10 23:33:16,089][98559] Updated weights for policy 0, policy_version 68900 (0.0007) -[2023-10-10 23:33:16,345][98560] Updated weights for policy 1, policy_version 68492 (0.0010) -[2023-10-10 23:33:16,454][98559] Updated weights for policy 0, policy_version 68910 (0.0007) -[2023-10-10 23:33:16,699][98560] Updated weights for policy 1, policy_version 68502 (0.0008) -[2023-10-10 23:33:16,822][98559] Updated weights for policy 0, policy_version 68920 (0.0008) -[2023-10-10 23:33:17,062][98560] Updated weights for policy 1, policy_version 68512 (0.0008) -[2023-10-10 23:33:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13440.4). Total num frames: 140738560. Throughput: 0: 1708.1, 1: 1711.5. Samples: 35199954. Policy #0 lag: (min: 5.0, avg: 12.1, max: 37.0) -[2023-10-10 23:33:20,556][97672] Avg episode reward: [(0, '-1.600'), (1, '22.660')] -[2023-10-10 23:33:20,859][98559] Updated weights for policy 0, policy_version 68930 (0.0009) -[2023-10-10 23:33:21,208][98560] Updated weights for policy 1, policy_version 68522 (0.0007) -[2023-10-10 23:33:21,232][98559] Updated weights for policy 0, policy_version 68940 (0.0008) -[2023-10-10 23:33:21,568][98560] Updated weights for policy 1, policy_version 68532 (0.0007) -[2023-10-10 23:33:21,588][98559] Updated weights for policy 0, policy_version 68950 (0.0009) -[2023-10-10 23:33:21,940][98560] Updated weights for policy 1, policy_version 68542 (0.0007) -[2023-10-10 23:33:21,957][98559] Updated weights for policy 0, policy_version 68960 (0.0007) -[2023-10-10 23:33:25,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 140804096. Throughput: 0: 1704.7, 1: 1686.4. Samples: 35209102. Policy #0 lag: (min: 5.0, avg: 12.1, max: 37.0) -[2023-10-10 23:33:25,557][97672] Avg episode reward: [(0, '-1.600'), (1, '22.660')] -[2023-10-10 23:33:25,893][98560] Updated weights for policy 1, policy_version 68552 (0.0007) -[2023-10-10 23:33:26,094][98559] Updated weights for policy 0, policy_version 68970 (0.0007) -[2023-10-10 23:33:26,260][98560] Updated weights for policy 1, policy_version 68562 (0.0007) -[2023-10-10 23:33:26,448][98559] Updated weights for policy 0, policy_version 68980 (0.0007) -[2023-10-10 23:33:26,630][98560] Updated weights for policy 1, policy_version 68572 (0.0008) -[2023-10-10 23:33:26,815][98559] Updated weights for policy 0, policy_version 68990 (0.0007) -[2023-10-10 23:33:30,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 140869632. Throughput: 0: 1713.4, 1: 1714.6. Samples: 35230284. Policy #0 lag: (min: 5.0, avg: 12.1, max: 37.0) -[2023-10-10 23:33:30,557][97672] Avg episode reward: [(0, '-1.600'), (1, '22.660')] -[2023-10-10 23:33:30,624][98560] Updated weights for policy 1, policy_version 68582 (0.0009) -[2023-10-10 23:33:30,686][98559] Updated weights for policy 0, policy_version 69000 (0.0007) -[2023-10-10 23:33:30,988][98560] Updated weights for policy 1, policy_version 68592 (0.0009) -[2023-10-10 23:33:31,046][98559] Updated weights for policy 0, policy_version 69010 (0.0009) -[2023-10-10 23:33:31,351][98560] Updated weights for policy 1, policy_version 68602 (0.0008) -[2023-10-10 23:33:31,409][98559] Updated weights for policy 0, policy_version 69020 (0.0008) -[2023-10-10 23:33:35,310][98559] Updated weights for policy 0, policy_version 69030 (0.0008) -[2023-10-10 23:33:35,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.3, 300 sec: 13440.4). Total num frames: 140935168. Throughput: 0: 1709.8, 1: 1705.3. Samples: 35250938. Policy #0 lag: (min: 5.0, avg: 12.1, max: 37.0) -[2023-10-10 23:33:35,557][97672] Avg episode reward: [(0, '-1.600'), (1, '22.640')] -[2023-10-10 23:33:35,585][98560] Updated weights for policy 1, policy_version 68612 (0.0008) -[2023-10-10 23:33:35,676][98559] Updated weights for policy 0, policy_version 69040 (0.0008) -[2023-10-10 23:33:35,954][98560] Updated weights for policy 1, policy_version 68622 (0.0009) -[2023-10-10 23:33:36,043][98559] Updated weights for policy 0, policy_version 69050 (0.0007) -[2023-10-10 23:33:36,312][98560] Updated weights for policy 1, policy_version 68632 (0.0007) -[2023-10-10 23:33:39,988][98559] Updated weights for policy 0, policy_version 69060 (0.0009) -[2023-10-10 23:33:40,355][98559] Updated weights for policy 0, policy_version 69070 (0.0008) -[2023-10-10 23:33:40,447][98560] Updated weights for policy 1, policy_version 68642 (0.0007) -[2023-10-10 23:33:40,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 141000704. Throughput: 0: 1716.4, 1: 1694.0. Samples: 35260370. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:33:40,556][97672] Avg episode reward: [(0, '-1.600'), (1, '22.600')] -[2023-10-10 23:33:40,732][98559] Updated weights for policy 0, policy_version 69080 (0.0008) -[2023-10-10 23:33:40,809][98560] Updated weights for policy 1, policy_version 68652 (0.0007) -[2023-10-10 23:33:41,179][98560] Updated weights for policy 1, policy_version 68662 (0.0009) -[2023-10-10 23:33:41,544][98560] Updated weights for policy 1, policy_version 68672 (0.0008) -[2023-10-10 23:33:44,814][98559] Updated weights for policy 0, policy_version 69090 (0.0009) -[2023-10-10 23:33:45,178][98559] Updated weights for policy 0, policy_version 69100 (0.0008) -[2023-10-10 23:33:45,503][98560] Updated weights for policy 1, policy_version 68682 (0.0007) -[2023-10-10 23:33:45,550][98559] Updated weights for policy 0, policy_version 69110 (0.0008) -[2023-10-10 23:33:45,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 141066240. Throughput: 0: 1711.3, 1: 1694.0. Samples: 35281184. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:33:45,556][97672] Avg episode reward: [(0, '-1.600'), (1, '22.540')] -[2023-10-10 23:33:45,863][98560] Updated weights for policy 1, policy_version 68692 (0.0007) -[2023-10-10 23:33:45,911][98559] Updated weights for policy 0, policy_version 69120 (0.0007) -[2023-10-10 23:33:46,237][98560] Updated weights for policy 1, policy_version 68702 (0.0007) -[2023-10-10 23:33:49,917][98559] Updated weights for policy 0, policy_version 69130 (0.0008) -[2023-10-10 23:33:50,257][98560] Updated weights for policy 1, policy_version 68712 (0.0009) -[2023-10-10 23:33:50,289][98559] Updated weights for policy 0, policy_version 69140 (0.0008) -[2023-10-10 23:33:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.3, 300 sec: 13440.4). Total num frames: 141131776. Throughput: 0: 1694.5, 1: 1700.0. Samples: 35301512. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:33:50,556][97672] Avg episode reward: [(0, '-1.600'), (1, '22.520')] -[2023-10-10 23:33:50,627][98560] Updated weights for policy 1, policy_version 68722 (0.0007) -[2023-10-10 23:33:50,645][98559] Updated weights for policy 0, policy_version 69150 (0.0008) -[2023-10-10 23:33:50,981][98560] Updated weights for policy 1, policy_version 68732 (0.0007) -[2023-10-10 23:33:54,610][98559] Updated weights for policy 0, policy_version 69160 (0.0008) -[2023-10-10 23:33:54,975][98559] Updated weights for policy 0, policy_version 69170 (0.0008) -[2023-10-10 23:33:55,118][98560] Updated weights for policy 1, policy_version 68742 (0.0008) -[2023-10-10 23:33:55,350][98559] Updated weights for policy 0, policy_version 69180 (0.0007) -[2023-10-10 23:33:55,494][98560] Updated weights for policy 1, policy_version 68752 (0.0007) -[2023-10-10 23:33:55,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 141230080. Throughput: 0: 1718.0, 1: 1698.8. Samples: 35311624. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:33:55,557][97672] Avg episode reward: [(0, '-1.600'), (1, '22.520')] -[2023-10-10 23:33:55,860][98560] Updated weights for policy 1, policy_version 68762 (0.0009) -[2023-10-10 23:33:59,095][98559] Updated weights for policy 0, policy_version 69190 (0.0009) -[2023-10-10 23:33:59,465][98559] Updated weights for policy 0, policy_version 69200 (0.0009) -[2023-10-10 23:33:59,784][98560] Updated weights for policy 1, policy_version 68772 (0.0008) -[2023-10-10 23:33:59,826][98559] Updated weights for policy 0, policy_version 69210 (0.0009) -[2023-10-10 23:34:00,150][98560] Updated weights for policy 1, policy_version 68782 (0.0009) -[2023-10-10 23:34:00,517][98560] Updated weights for policy 1, policy_version 68792 (0.0008) -[2023-10-10 23:34:00,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 141295616. Throughput: 0: 1715.6, 1: 1698.2. Samples: 35332430. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:34:00,557][97672] Avg episode reward: [(0, '-1.580'), (1, '22.500')] -[2023-10-10 23:34:03,842][98559] Updated weights for policy 0, policy_version 69220 (0.0009) -[2023-10-10 23:34:04,217][98559] Updated weights for policy 0, policy_version 69230 (0.0007) -[2023-10-10 23:34:04,466][98560] Updated weights for policy 1, policy_version 68802 (0.0009) -[2023-10-10 23:34:04,585][98559] Updated weights for policy 0, policy_version 69240 (0.0008) -[2023-10-10 23:34:04,841][98560] Updated weights for policy 1, policy_version 68812 (0.0009) -[2023-10-10 23:34:05,209][98560] Updated weights for policy 1, policy_version 68822 (0.0009) -[2023-10-10 23:34:05,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 141361152. Throughput: 0: 1699.4, 1: 1689.4. Samples: 35352452. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:34:05,557][97672] Avg episode reward: [(0, '-1.580'), (1, '22.480')] -[2023-10-10 23:34:05,582][98560] Updated weights for policy 1, policy_version 68832 (0.0007) -[2023-10-10 23:34:08,731][98559] Updated weights for policy 0, policy_version 69250 (0.0009) -[2023-10-10 23:34:09,128][98559] Updated weights for policy 0, policy_version 69260 (0.0008) -[2023-10-10 23:34:09,480][98559] Updated weights for policy 0, policy_version 69270 (0.0009) -[2023-10-10 23:34:09,816][98560] Updated weights for policy 1, policy_version 68842 (0.0009) -[2023-10-10 23:34:09,846][98559] Updated weights for policy 0, policy_version 69280 (0.0008) -[2023-10-10 23:34:10,176][98560] Updated weights for policy 1, policy_version 68852 (0.0010) -[2023-10-10 23:34:10,543][98560] Updated weights for policy 1, policy_version 68862 (0.0011) -[2023-10-10 23:34:10,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 141426688. Throughput: 0: 1726.7, 1: 1702.3. Samples: 35363404. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:34:10,556][97672] Avg episode reward: [(0, '-1.540'), (1, '22.420')] -[2023-10-10 23:34:13,875][98559] Updated weights for policy 0, policy_version 69290 (0.0008) -[2023-10-10 23:34:14,245][98559] Updated weights for policy 0, policy_version 69300 (0.0009) -[2023-10-10 23:34:14,450][98560] Updated weights for policy 1, policy_version 68872 (0.0008) -[2023-10-10 23:34:14,598][98559] Updated weights for policy 0, policy_version 69310 (0.0010) -[2023-10-10 23:34:14,819][98560] Updated weights for policy 1, policy_version 68882 (0.0009) -[2023-10-10 23:34:15,183][98560] Updated weights for policy 1, policy_version 68892 (0.0008) -[2023-10-10 23:34:15,556][97672] Fps is (10 sec: 16384.4, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 141524992. Throughput: 0: 1704.0, 1: 1691.6. Samples: 35383086. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:34:15,557][97672] Avg episode reward: [(0, '-1.540'), (1, '22.400')] -[2023-10-10 23:34:18,545][98559] Updated weights for policy 0, policy_version 69320 (0.0008) -[2023-10-10 23:34:18,906][98559] Updated weights for policy 0, policy_version 69330 (0.0007) -[2023-10-10 23:34:19,267][98559] Updated weights for policy 0, policy_version 69340 (0.0008) -[2023-10-10 23:34:19,291][98560] Updated weights for policy 1, policy_version 68902 (0.0008) -[2023-10-10 23:34:19,651][98560] Updated weights for policy 1, policy_version 68912 (0.0007) -[2023-10-10 23:34:20,017][98560] Updated weights for policy 1, policy_version 68922 (0.0009) -[2023-10-10 23:34:20,556][97672] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 141590528. Throughput: 0: 1702.1, 1: 1683.9. Samples: 35403308. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:34:20,557][97672] Avg episode reward: [(0, '-1.540'), (1, '22.420')] -[2023-10-10 23:34:23,251][98559] Updated weights for policy 0, policy_version 69350 (0.0007) -[2023-10-10 23:34:23,621][98559] Updated weights for policy 0, policy_version 69360 (0.0010) -[2023-10-10 23:34:23,960][98560] Updated weights for policy 1, policy_version 68932 (0.0010) -[2023-10-10 23:34:23,981][98559] Updated weights for policy 0, policy_version 69370 (0.0008) -[2023-10-10 23:34:24,327][98560] Updated weights for policy 1, policy_version 68942 (0.0009) -[2023-10-10 23:34:24,692][98560] Updated weights for policy 1, policy_version 68952 (0.0007) -[2023-10-10 23:34:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 141656064. Throughput: 0: 1716.1, 1: 1704.1. Samples: 35414278. Policy #0 lag: (min: 6.0, avg: 29.3, max: 38.0) -[2023-10-10 23:34:25,557][97672] Avg episode reward: [(0, '-1.520'), (1, '22.380')] -[2023-10-10 23:34:27,930][98559] Updated weights for policy 0, policy_version 69380 (0.0009) -[2023-10-10 23:34:28,290][98559] Updated weights for policy 0, policy_version 69390 (0.0009) -[2023-10-10 23:34:28,657][98559] Updated weights for policy 0, policy_version 69400 (0.0008) -[2023-10-10 23:34:28,761][98560] Updated weights for policy 1, policy_version 68962 (0.0007) -[2023-10-10 23:34:29,134][98560] Updated weights for policy 1, policy_version 68972 (0.0008) -[2023-10-10 23:34:29,505][98560] Updated weights for policy 1, policy_version 68982 (0.0008) -[2023-10-10 23:34:29,869][98560] Updated weights for policy 1, policy_version 68992 (0.0008) -[2023-10-10 23:34:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 141721600. Throughput: 0: 1702.1, 1: 1706.8. Samples: 35434582. Policy #0 lag: (min: 6.0, avg: 29.3, max: 38.0) -[2023-10-10 23:34:30,557][97672] Avg episode reward: [(0, '-1.520'), (1, '22.460')] -[2023-10-10 23:34:32,631][98559] Updated weights for policy 0, policy_version 69410 (0.0007) -[2023-10-10 23:34:33,008][98559] Updated weights for policy 0, policy_version 69420 (0.0008) -[2023-10-10 23:34:33,370][98559] Updated weights for policy 0, policy_version 69430 (0.0009) -[2023-10-10 23:34:33,701][98560] Updated weights for policy 1, policy_version 69002 (0.0009) -[2023-10-10 23:34:33,735][98559] Updated weights for policy 0, policy_version 69440 (0.0007) -[2023-10-10 23:34:34,068][98560] Updated weights for policy 1, policy_version 69012 (0.0009) -[2023-10-10 23:34:34,432][98560] Updated weights for policy 1, policy_version 69022 (0.0009) -[2023-10-10 23:34:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 141787136. Throughput: 0: 1721.9, 1: 1677.1. Samples: 35454470. Policy #0 lag: (min: 6.0, avg: 29.3, max: 38.0) -[2023-10-10 23:34:35,557][97672] Avg episode reward: [(0, '-1.520'), (1, '22.400')] -[2023-10-10 23:34:35,567][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000069024_70680576.pth... -[2023-10-10 23:34:35,567][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000069440_71106560.pth... -[2023-10-10 23:34:35,597][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000067872_69500928.pth -[2023-10-10 23:34:35,598][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000067456_69074944.pth -[2023-10-10 23:34:37,842][98559] Updated weights for policy 0, policy_version 69450 (0.0009) -[2023-10-10 23:34:38,218][98559] Updated weights for policy 0, policy_version 69460 (0.0010) -[2023-10-10 23:34:38,434][98560] Updated weights for policy 1, policy_version 69032 (0.0010) -[2023-10-10 23:34:38,581][98559] Updated weights for policy 0, policy_version 69470 (0.0008) -[2023-10-10 23:34:38,809][98560] Updated weights for policy 1, policy_version 69042 (0.0008) -[2023-10-10 23:34:39,176][98560] Updated weights for policy 1, policy_version 69052 (0.0009) -[2023-10-10 23:34:40,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 141852672. Throughput: 0: 1706.7, 1: 1709.8. Samples: 35465364. Policy #0 lag: (min: 6.0, avg: 29.3, max: 38.0) -[2023-10-10 23:34:40,557][97672] Avg episode reward: [(0, '-1.520'), (1, '22.440')] -[2023-10-10 23:34:42,647][98559] Updated weights for policy 0, policy_version 69480 (0.0010) -[2023-10-10 23:34:43,016][98559] Updated weights for policy 0, policy_version 69490 (0.0010) -[2023-10-10 23:34:43,191][98560] Updated weights for policy 1, policy_version 69062 (0.0008) -[2023-10-10 23:34:43,385][98559] Updated weights for policy 0, policy_version 69500 (0.0009) -[2023-10-10 23:34:43,556][98560] Updated weights for policy 1, policy_version 69072 (0.0007) -[2023-10-10 23:34:43,933][98560] Updated weights for policy 1, policy_version 69082 (0.0008) -[2023-10-10 23:34:45,556][97672] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 141918208. Throughput: 0: 1701.0, 1: 1692.1. Samples: 35485122. Policy #0 lag: (min: 6.0, avg: 29.3, max: 38.0) -[2023-10-10 23:34:45,556][97672] Avg episode reward: [(0, '-1.520'), (1, '22.480')] -[2023-10-10 23:34:47,308][98559] Updated weights for policy 0, policy_version 69510 (0.0008) -[2023-10-10 23:34:47,677][98559] Updated weights for policy 0, policy_version 69520 (0.0008) -[2023-10-10 23:34:48,018][98560] Updated weights for policy 1, policy_version 69092 (0.0008) -[2023-10-10 23:34:48,038][98559] Updated weights for policy 0, policy_version 69530 (0.0009) -[2023-10-10 23:34:48,392][98560] Updated weights for policy 1, policy_version 69102 (0.0010) -[2023-10-10 23:34:48,757][98560] Updated weights for policy 1, policy_version 69112 (0.0010) -[2023-10-10 23:34:50,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 141983744. Throughput: 0: 1718.9, 1: 1682.0. Samples: 35505496. Policy #0 lag: (min: 6.0, avg: 29.3, max: 38.0) -[2023-10-10 23:34:50,557][97672] Avg episode reward: [(0, '-1.520'), (1, '22.580')] -[2023-10-10 23:34:51,927][98559] Updated weights for policy 0, policy_version 69540 (0.0009) -[2023-10-10 23:34:52,291][98559] Updated weights for policy 0, policy_version 69550 (0.0007) -[2023-10-10 23:34:52,658][98559] Updated weights for policy 0, policy_version 69560 (0.0007) -[2023-10-10 23:34:52,803][98560] Updated weights for policy 1, policy_version 69122 (0.0007) -[2023-10-10 23:34:53,166][98560] Updated weights for policy 1, policy_version 69132 (0.0008) -[2023-10-10 23:34:53,525][98560] Updated weights for policy 1, policy_version 69142 (0.0009) -[2023-10-10 23:34:53,892][98560] Updated weights for policy 1, policy_version 69152 (0.0009) -[2023-10-10 23:34:55,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 142049280. Throughput: 0: 1690.4, 1: 1702.4. Samples: 35516084. Policy #0 lag: (min: 6.0, avg: 29.3, max: 38.0) -[2023-10-10 23:34:55,556][97672] Avg episode reward: [(0, '-1.520'), (1, '22.620')] -[2023-10-10 23:34:56,620][98559] Updated weights for policy 0, policy_version 69570 (0.0008) -[2023-10-10 23:34:57,011][98559] Updated weights for policy 0, policy_version 69580 (0.0008) -[2023-10-10 23:34:57,371][98559] Updated weights for policy 0, policy_version 69590 (0.0007) -[2023-10-10 23:34:57,738][98559] Updated weights for policy 0, policy_version 69600 (0.0007) -[2023-10-10 23:34:58,033][98560] Updated weights for policy 1, policy_version 69162 (0.0009) -[2023-10-10 23:34:58,393][98560] Updated weights for policy 1, policy_version 69172 (0.0011) -[2023-10-10 23:34:58,745][98560] Updated weights for policy 1, policy_version 69182 (0.0010) -[2023-10-10 23:35:00,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 142114816. Throughput: 0: 1718.2, 1: 1680.8. Samples: 35536044. Policy #0 lag: (min: 6.0, avg: 29.3, max: 38.0) -[2023-10-10 23:35:00,557][97672] Avg episode reward: [(0, '-1.520'), (1, '22.600')] -[2023-10-10 23:35:01,723][98559] Updated weights for policy 0, policy_version 69610 (0.0008) -[2023-10-10 23:35:02,080][98559] Updated weights for policy 0, policy_version 69620 (0.0011) -[2023-10-10 23:35:02,441][98559] Updated weights for policy 0, policy_version 69630 (0.0010) -[2023-10-10 23:35:02,788][98560] Updated weights for policy 1, policy_version 69192 (0.0008) -[2023-10-10 23:35:03,163][98560] Updated weights for policy 1, policy_version 69202 (0.0009) -[2023-10-10 23:35:03,532][98560] Updated weights for policy 1, policy_version 69212 (0.0007) -[2023-10-10 23:35:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 142180352. Throughput: 0: 1720.4, 1: 1688.6. Samples: 35556710. Policy #0 lag: (min: 6.0, avg: 29.3, max: 38.0) -[2023-10-10 23:35:05,556][97672] Avg episode reward: [(0, '-1.520'), (1, '22.640')] -[2023-10-10 23:35:06,546][98559] Updated weights for policy 0, policy_version 69640 (0.0009) -[2023-10-10 23:35:06,912][98559] Updated weights for policy 0, policy_version 69650 (0.0008) -[2023-10-10 23:35:07,281][98559] Updated weights for policy 0, policy_version 69660 (0.0008) -[2023-10-10 23:35:07,619][98560] Updated weights for policy 1, policy_version 69222 (0.0007) -[2023-10-10 23:35:07,991][98560] Updated weights for policy 1, policy_version 69232 (0.0009) -[2023-10-10 23:35:08,366][98560] Updated weights for policy 1, policy_version 69242 (0.0010) -[2023-10-10 23:35:10,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 142245888. Throughput: 0: 1699.6, 1: 1695.1. Samples: 35567038. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 23:35:10,556][97672] Avg episode reward: [(0, '-1.520'), (1, '22.660')] -[2023-10-10 23:35:11,307][98559] Updated weights for policy 0, policy_version 69670 (0.0007) -[2023-10-10 23:35:11,672][98559] Updated weights for policy 0, policy_version 69680 (0.0007) -[2023-10-10 23:35:12,040][98559] Updated weights for policy 0, policy_version 69690 (0.0007) -[2023-10-10 23:35:12,312][98560] Updated weights for policy 1, policy_version 69252 (0.0008) -[2023-10-10 23:35:12,684][98560] Updated weights for policy 1, policy_version 69262 (0.0008) -[2023-10-10 23:35:13,042][98560] Updated weights for policy 1, policy_version 69272 (0.0009) -[2023-10-10 23:35:15,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 142311424. Throughput: 0: 1715.8, 1: 1671.8. Samples: 35587022. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 23:35:15,557][97672] Avg episode reward: [(0, '-1.520'), (1, '22.600')] -[2023-10-10 23:35:16,075][98559] Updated weights for policy 0, policy_version 69700 (0.0008) -[2023-10-10 23:35:16,441][98559] Updated weights for policy 0, policy_version 69710 (0.0009) -[2023-10-10 23:35:16,810][98559] Updated weights for policy 0, policy_version 69720 (0.0009) -[2023-10-10 23:35:16,902][98560] Updated weights for policy 1, policy_version 69282 (0.0008) -[2023-10-10 23:35:17,261][98560] Updated weights for policy 1, policy_version 69292 (0.0008) -[2023-10-10 23:35:17,620][98560] Updated weights for policy 1, policy_version 69302 (0.0010) -[2023-10-10 23:35:17,987][98560] Updated weights for policy 1, policy_version 69312 (0.0011) -[2023-10-10 23:35:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 142376960. Throughput: 0: 1713.5, 1: 1698.1. Samples: 35607992. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 23:35:20,556][97672] Avg episode reward: [(0, '-1.520'), (1, '22.640')] -[2023-10-10 23:35:20,944][98559] Updated weights for policy 0, policy_version 69730 (0.0008) -[2023-10-10 23:35:21,313][98559] Updated weights for policy 0, policy_version 69740 (0.0011) -[2023-10-10 23:35:21,676][98559] Updated weights for policy 0, policy_version 69750 (0.0008) -[2023-10-10 23:35:22,037][98559] Updated weights for policy 0, policy_version 69760 (0.0008) -[2023-10-10 23:35:22,041][98560] Updated weights for policy 1, policy_version 69322 (0.0008) -[2023-10-10 23:35:22,407][98560] Updated weights for policy 1, policy_version 69332 (0.0008) -[2023-10-10 23:35:22,768][98560] Updated weights for policy 1, policy_version 69342 (0.0008) -[2023-10-10 23:35:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 142442496. Throughput: 0: 1708.9, 1: 1672.5. Samples: 35617526. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 23:35:25,557][97672] Avg episode reward: [(0, '-1.520'), (1, '22.580')] -[2023-10-10 23:35:25,916][98559] Updated weights for policy 0, policy_version 69770 (0.0007) -[2023-10-10 23:35:26,277][98559] Updated weights for policy 0, policy_version 69780 (0.0007) -[2023-10-10 23:35:26,637][98559] Updated weights for policy 0, policy_version 69790 (0.0008) -[2023-10-10 23:35:26,916][98560] Updated weights for policy 1, policy_version 69352 (0.0007) -[2023-10-10 23:35:27,279][98560] Updated weights for policy 1, policy_version 69362 (0.0009) -[2023-10-10 23:35:27,647][98560] Updated weights for policy 1, policy_version 69372 (0.0008) -[2023-10-10 23:35:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 142508032. Throughput: 0: 1718.9, 1: 1685.6. Samples: 35638322. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 23:35:30,557][97672] Avg episode reward: [(0, '-1.520'), (1, '22.580')] -[2023-10-10 23:35:30,600][98559] Updated weights for policy 0, policy_version 69800 (0.0009) -[2023-10-10 23:35:30,976][98559] Updated weights for policy 0, policy_version 69810 (0.0008) -[2023-10-10 23:35:31,337][98559] Updated weights for policy 0, policy_version 69820 (0.0008) -[2023-10-10 23:35:31,651][98560] Updated weights for policy 1, policy_version 69382 (0.0009) -[2023-10-10 23:35:32,022][98560] Updated weights for policy 1, policy_version 69392 (0.0009) -[2023-10-10 23:35:32,387][98560] Updated weights for policy 1, policy_version 69402 (0.0008) -[2023-10-10 23:35:35,239][98559] Updated weights for policy 0, policy_version 69830 (0.0007) -[2023-10-10 23:35:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 142573568. Throughput: 0: 1710.2, 1: 1700.6. Samples: 35658984. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 23:35:35,557][97672] Avg episode reward: [(0, '-1.520'), (1, '22.520')] -[2023-10-10 23:35:35,600][98559] Updated weights for policy 0, policy_version 69840 (0.0007) -[2023-10-10 23:35:35,976][98559] Updated weights for policy 0, policy_version 69850 (0.0008) -[2023-10-10 23:35:36,396][98560] Updated weights for policy 1, policy_version 69412 (0.0009) -[2023-10-10 23:35:36,769][98560] Updated weights for policy 1, policy_version 69422 (0.0009) -[2023-10-10 23:35:37,129][98560] Updated weights for policy 1, policy_version 69432 (0.0009) -[2023-10-10 23:35:39,768][98559] Updated weights for policy 0, policy_version 69860 (0.0009) -[2023-10-10 23:35:40,139][98559] Updated weights for policy 0, policy_version 69870 (0.0011) -[2023-10-10 23:35:40,504][98559] Updated weights for policy 0, policy_version 69880 (0.0008) -[2023-10-10 23:35:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 142639104. Throughput: 0: 1720.6, 1: 1672.4. Samples: 35668770. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 23:35:40,556][97672] Avg episode reward: [(0, '-1.520'), (1, '22.500')] -[2023-10-10 23:35:41,312][98560] Updated weights for policy 1, policy_version 69442 (0.0009) -[2023-10-10 23:35:41,684][98560] Updated weights for policy 1, policy_version 69452 (0.0008) -[2023-10-10 23:35:42,053][98560] Updated weights for policy 1, policy_version 69462 (0.0008) -[2023-10-10 23:35:42,423][98560] Updated weights for policy 1, policy_version 69472 (0.0009) -[2023-10-10 23:35:44,652][98559] Updated weights for policy 0, policy_version 69890 (0.0009) -[2023-10-10 23:35:45,046][98559] Updated weights for policy 0, policy_version 69900 (0.0009) -[2023-10-10 23:35:45,412][98559] Updated weights for policy 0, policy_version 69910 (0.0010) -[2023-10-10 23:35:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 142704640. Throughput: 0: 1715.2, 1: 1697.6. Samples: 35689622. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 23:35:45,557][97672] Avg episode reward: [(0, '-1.520'), (1, '22.500')] -[2023-10-10 23:35:45,780][98559] Updated weights for policy 0, policy_version 69920 (0.0008) -[2023-10-10 23:35:46,534][98560] Updated weights for policy 1, policy_version 69482 (0.0009) -[2023-10-10 23:35:46,906][98560] Updated weights for policy 1, policy_version 69492 (0.0009) -[2023-10-10 23:35:47,272][98560] Updated weights for policy 1, policy_version 69502 (0.0008) -[2023-10-10 23:35:49,754][98559] Updated weights for policy 0, policy_version 69930 (0.0009) -[2023-10-10 23:35:50,115][98559] Updated weights for policy 0, policy_version 69940 (0.0008) -[2023-10-10 23:35:50,483][98559] Updated weights for policy 0, policy_version 69950 (0.0009) -[2023-10-10 23:35:50,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 142802944. Throughput: 0: 1689.2, 1: 1700.0. Samples: 35709228. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 23:35:50,556][97672] Avg episode reward: [(0, '-1.520'), (1, '22.400')] -[2023-10-10 23:35:51,326][98560] Updated weights for policy 1, policy_version 69512 (0.0008) -[2023-10-10 23:35:51,691][98560] Updated weights for policy 1, policy_version 69522 (0.0008) -[2023-10-10 23:35:52,067][98560] Updated weights for policy 1, policy_version 69532 (0.0008) -[2023-10-10 23:35:54,487][98559] Updated weights for policy 0, policy_version 69960 (0.0009) -[2023-10-10 23:35:54,862][98559] Updated weights for policy 0, policy_version 69970 (0.0009) -[2023-10-10 23:35:55,228][98559] Updated weights for policy 0, policy_version 69980 (0.0009) -[2023-10-10 23:35:55,556][97672] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 142868480. Throughput: 0: 1711.5, 1: 1676.6. Samples: 35719504. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-10 23:35:55,557][97672] Avg episode reward: [(0, '-1.520'), (1, '22.340')] -[2023-10-10 23:35:56,040][98560] Updated weights for policy 1, policy_version 69542 (0.0008) -[2023-10-10 23:35:56,412][98560] Updated weights for policy 1, policy_version 69552 (0.0008) -[2023-10-10 23:35:56,781][98560] Updated weights for policy 1, policy_version 69562 (0.0007) -[2023-10-10 23:35:59,209][98559] Updated weights for policy 0, policy_version 69990 (0.0009) -[2023-10-10 23:35:59,574][98559] Updated weights for policy 0, policy_version 70000 (0.0010) -[2023-10-10 23:35:59,938][98559] Updated weights for policy 0, policy_version 70010 (0.0011) -[2023-10-10 23:36:00,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 142934016. Throughput: 0: 1706.3, 1: 1694.6. Samples: 35740060. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-10 23:36:00,557][97672] Avg episode reward: [(0, '-1.520'), (1, '22.360')] -[2023-10-10 23:36:00,779][98560] Updated weights for policy 1, policy_version 69572 (0.0009) -[2023-10-10 23:36:01,154][98560] Updated weights for policy 1, policy_version 69582 (0.0009) -[2023-10-10 23:36:01,527][98560] Updated weights for policy 1, policy_version 69592 (0.0008) -[2023-10-10 23:36:03,958][98559] Updated weights for policy 0, policy_version 70020 (0.0009) -[2023-10-10 23:36:04,333][98559] Updated weights for policy 0, policy_version 70030 (0.0008) -[2023-10-10 23:36:04,694][98559] Updated weights for policy 0, policy_version 70040 (0.0008) -[2023-10-10 23:36:05,341][98560] Updated weights for policy 1, policy_version 69602 (0.0008) -[2023-10-10 23:36:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 142999552. Throughput: 0: 1689.3, 1: 1700.9. Samples: 35760554. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-10 23:36:05,557][97672] Avg episode reward: [(0, '-1.560'), (1, '22.400')] -[2023-10-10 23:36:05,705][98560] Updated weights for policy 1, policy_version 69612 (0.0008) -[2023-10-10 23:36:06,068][98560] Updated weights for policy 1, policy_version 69622 (0.0007) -[2023-10-10 23:36:06,439][98560] Updated weights for policy 1, policy_version 69632 (0.0009) -[2023-10-10 23:36:08,778][98559] Updated weights for policy 0, policy_version 70050 (0.0008) -[2023-10-10 23:36:09,134][98559] Updated weights for policy 0, policy_version 70060 (0.0009) -[2023-10-10 23:36:09,501][98559] Updated weights for policy 0, policy_version 70070 (0.0009) -[2023-10-10 23:36:09,877][98559] Updated weights for policy 0, policy_version 70080 (0.0009) -[2023-10-10 23:36:10,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 143065088. Throughput: 0: 1718.9, 1: 1695.7. Samples: 35771184. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-10 23:36:10,557][97672] Avg episode reward: [(0, '-1.560'), (1, '22.380')] -[2023-10-10 23:36:10,605][98560] Updated weights for policy 1, policy_version 69642 (0.0008) -[2023-10-10 23:36:10,974][98560] Updated weights for policy 1, policy_version 69652 (0.0009) -[2023-10-10 23:36:11,348][98560] Updated weights for policy 1, policy_version 69662 (0.0007) -[2023-10-10 23:36:13,837][98559] Updated weights for policy 0, policy_version 70090 (0.0009) -[2023-10-10 23:36:14,212][98559] Updated weights for policy 0, policy_version 70100 (0.0010) -[2023-10-10 23:36:14,568][98559] Updated weights for policy 0, policy_version 70110 (0.0009) -[2023-10-10 23:36:15,309][98560] Updated weights for policy 1, policy_version 69672 (0.0009) -[2023-10-10 23:36:15,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 143130624. Throughput: 0: 1700.0, 1: 1705.2. Samples: 35791558. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-10 23:36:15,556][97672] Avg episode reward: [(0, '-1.560'), (1, '22.360')] -[2023-10-10 23:36:15,685][98560] Updated weights for policy 1, policy_version 69682 (0.0009) -[2023-10-10 23:36:16,040][98560] Updated weights for policy 1, policy_version 69692 (0.0009) -[2023-10-10 23:36:18,404][98559] Updated weights for policy 0, policy_version 70120 (0.0010) -[2023-10-10 23:36:18,774][98559] Updated weights for policy 0, policy_version 70130 (0.0011) -[2023-10-10 23:36:19,143][98559] Updated weights for policy 0, policy_version 70140 (0.0007) -[2023-10-10 23:36:19,959][98560] Updated weights for policy 1, policy_version 69702 (0.0010) -[2023-10-10 23:36:20,331][98560] Updated weights for policy 1, policy_version 69712 (0.0010) -[2023-10-10 23:36:20,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 143196160. Throughput: 0: 1699.3, 1: 1706.8. Samples: 35812260. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-10 23:36:20,557][97672] Avg episode reward: [(0, '-1.560'), (1, '22.380')] -[2023-10-10 23:36:20,706][98560] Updated weights for policy 1, policy_version 69722 (0.0011) -[2023-10-10 23:36:23,140][98559] Updated weights for policy 0, policy_version 70150 (0.0007) -[2023-10-10 23:36:23,510][98559] Updated weights for policy 0, policy_version 70160 (0.0008) -[2023-10-10 23:36:23,880][98559] Updated weights for policy 0, policy_version 70170 (0.0008) -[2023-10-10 23:36:24,797][98560] Updated weights for policy 1, policy_version 69732 (0.0009) -[2023-10-10 23:36:25,170][98560] Updated weights for policy 1, policy_version 69742 (0.0007) -[2023-10-10 23:36:25,533][98560] Updated weights for policy 1, policy_version 69752 (0.0007) -[2023-10-10 23:36:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 143261696. Throughput: 0: 1708.1, 1: 1703.7. Samples: 35822302. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-10 23:36:25,557][97672] Avg episode reward: [(0, '-1.560'), (1, '22.420')] -[2023-10-10 23:36:27,666][98559] Updated weights for policy 0, policy_version 70180 (0.0008) -[2023-10-10 23:36:28,032][98559] Updated weights for policy 0, policy_version 70190 (0.0007) -[2023-10-10 23:36:28,387][98559] Updated weights for policy 0, policy_version 70200 (0.0007) -[2023-10-10 23:36:29,381][98560] Updated weights for policy 1, policy_version 69762 (0.0007) -[2023-10-10 23:36:29,749][98560] Updated weights for policy 1, policy_version 69772 (0.0007) -[2023-10-10 23:36:30,111][98560] Updated weights for policy 1, policy_version 69782 (0.0009) -[2023-10-10 23:36:30,475][98560] Updated weights for policy 1, policy_version 69792 (0.0011) -[2023-10-10 23:36:30,556][97672] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 143360000. Throughput: 0: 1690.3, 1: 1709.8. Samples: 35842628. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-10 23:36:30,557][97672] Avg episode reward: [(0, '-1.640'), (1, '22.440')] -[2023-10-10 23:36:32,288][98559] Updated weights for policy 0, policy_version 70210 (0.0010) -[2023-10-10 23:36:32,688][98559] Updated weights for policy 0, policy_version 70220 (0.0012) -[2023-10-10 23:36:33,059][98559] Updated weights for policy 0, policy_version 70230 (0.0008) -[2023-10-10 23:36:33,423][98559] Updated weights for policy 0, policy_version 70240 (0.0007) -[2023-10-10 23:36:34,588][98560] Updated weights for policy 1, policy_version 69802 (0.0009) -[2023-10-10 23:36:34,946][98560] Updated weights for policy 1, policy_version 69812 (0.0009) -[2023-10-10 23:36:35,324][98560] Updated weights for policy 1, policy_version 69822 (0.0010) -[2023-10-10 23:36:35,556][97672] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 143425536. Throughput: 0: 1719.8, 1: 1701.4. Samples: 35863180. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-10 23:36:35,556][97672] Avg episode reward: [(0, '-1.640'), (1, '22.440')] -[2023-10-10 23:36:35,568][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000069824_71499776.pth... -[2023-10-10 23:36:35,568][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000070240_71925760.pth... -[2023-10-10 23:36:35,602][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000068224_69861376.pth -[2023-10-10 23:36:35,604][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000068640_70287360.pth -[2023-10-10 23:36:37,380][98559] Updated weights for policy 0, policy_version 70250 (0.0008) -[2023-10-10 23:36:37,753][98559] Updated weights for policy 0, policy_version 70260 (0.0010) -[2023-10-10 23:36:38,118][98559] Updated weights for policy 0, policy_version 70270 (0.0010) -[2023-10-10 23:36:39,216][98560] Updated weights for policy 1, policy_version 69832 (0.0008) -[2023-10-10 23:36:39,573][98560] Updated weights for policy 1, policy_version 69842 (0.0008) -[2023-10-10 23:36:39,944][98560] Updated weights for policy 1, policy_version 69852 (0.0008) -[2023-10-10 23:36:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 143491072. Throughput: 0: 1699.2, 1: 1714.4. Samples: 35873114. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-10 23:36:40,557][97672] Avg episode reward: [(0, '-1.640'), (1, '22.500')] -[2023-10-10 23:36:41,973][98559] Updated weights for policy 0, policy_version 70280 (0.0010) -[2023-10-10 23:36:42,329][98559] Updated weights for policy 0, policy_version 70290 (0.0009) -[2023-10-10 23:36:42,695][98559] Updated weights for policy 0, policy_version 70300 (0.0011) -[2023-10-10 23:36:43,817][98560] Updated weights for policy 1, policy_version 69862 (0.0009) -[2023-10-10 23:36:44,181][98560] Updated weights for policy 1, policy_version 69872 (0.0009) -[2023-10-10 23:36:44,542][98560] Updated weights for policy 1, policy_version 69882 (0.0010) -[2023-10-10 23:36:45,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 143556608. Throughput: 0: 1708.0, 1: 1723.1. Samples: 35894462. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:36:45,557][97672] Avg episode reward: [(0, '-1.680'), (1, '22.500')] -[2023-10-10 23:36:46,693][98559] Updated weights for policy 0, policy_version 70310 (0.0009) -[2023-10-10 23:36:47,056][98559] Updated weights for policy 0, policy_version 70320 (0.0009) -[2023-10-10 23:36:47,432][98559] Updated weights for policy 0, policy_version 70330 (0.0008) -[2023-10-10 23:36:48,673][98560] Updated weights for policy 1, policy_version 69892 (0.0010) -[2023-10-10 23:36:49,046][98560] Updated weights for policy 1, policy_version 69902 (0.0007) -[2023-10-10 23:36:49,412][98560] Updated weights for policy 1, policy_version 69912 (0.0007) -[2023-10-10 23:36:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 143622144. Throughput: 0: 1731.8, 1: 1691.5. Samples: 35914602. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:36:50,557][97672] Avg episode reward: [(0, '-1.680'), (1, '22.460')] -[2023-10-10 23:36:51,567][98559] Updated weights for policy 0, policy_version 70340 (0.0009) -[2023-10-10 23:36:51,946][98559] Updated weights for policy 0, policy_version 70350 (0.0009) -[2023-10-10 23:36:52,314][98559] Updated weights for policy 0, policy_version 70360 (0.0008) -[2023-10-10 23:36:53,409][98560] Updated weights for policy 1, policy_version 69922 (0.0008) -[2023-10-10 23:36:53,776][98560] Updated weights for policy 1, policy_version 69932 (0.0008) -[2023-10-10 23:36:54,147][98560] Updated weights for policy 1, policy_version 69942 (0.0009) -[2023-10-10 23:36:54,517][98560] Updated weights for policy 1, policy_version 69952 (0.0009) -[2023-10-10 23:36:55,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 143687680. Throughput: 0: 1699.8, 1: 1719.7. Samples: 35925058. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:36:55,557][97672] Avg episode reward: [(0, '-1.640'), (1, '22.520')] -[2023-10-10 23:36:56,307][98559] Updated weights for policy 0, policy_version 70370 (0.0007) -[2023-10-10 23:36:56,659][98559] Updated weights for policy 0, policy_version 70380 (0.0007) -[2023-10-10 23:36:57,026][98559] Updated weights for policy 0, policy_version 70390 (0.0008) -[2023-10-10 23:36:57,395][98559] Updated weights for policy 0, policy_version 70400 (0.0009) -[2023-10-10 23:36:58,473][98560] Updated weights for policy 1, policy_version 69962 (0.0007) -[2023-10-10 23:36:58,840][98560] Updated weights for policy 1, policy_version 69972 (0.0007) -[2023-10-10 23:36:59,197][98560] Updated weights for policy 1, policy_version 69982 (0.0009) -[2023-10-10 23:37:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 143753216. Throughput: 0: 1725.0, 1: 1703.5. Samples: 35945842. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:37:00,557][97672] Avg episode reward: [(0, '-1.640'), (1, '22.580')] -[2023-10-10 23:37:01,501][98559] Updated weights for policy 0, policy_version 70410 (0.0010) -[2023-10-10 23:37:01,864][98559] Updated weights for policy 0, policy_version 70420 (0.0009) -[2023-10-10 23:37:02,233][98559] Updated weights for policy 0, policy_version 70430 (0.0008) -[2023-10-10 23:37:03,254][98560] Updated weights for policy 1, policy_version 69992 (0.0008) -[2023-10-10 23:37:03,621][98560] Updated weights for policy 1, policy_version 70002 (0.0008) -[2023-10-10 23:37:03,977][98560] Updated weights for policy 1, policy_version 70012 (0.0010) -[2023-10-10 23:37:05,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 143818752. Throughput: 0: 1732.0, 1: 1687.3. Samples: 35966130. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:37:05,557][97672] Avg episode reward: [(0, '-1.640'), (1, '22.600')] -[2023-10-10 23:37:06,166][98559] Updated weights for policy 0, policy_version 70440 (0.0009) -[2023-10-10 23:37:06,527][98559] Updated weights for policy 0, policy_version 70450 (0.0008) -[2023-10-10 23:37:06,900][98559] Updated weights for policy 0, policy_version 70460 (0.0009) -[2023-10-10 23:37:07,975][98560] Updated weights for policy 1, policy_version 70022 (0.0007) -[2023-10-10 23:37:08,342][98560] Updated weights for policy 1, policy_version 70032 (0.0009) -[2023-10-10 23:37:08,717][98560] Updated weights for policy 1, policy_version 70042 (0.0009) -[2023-10-10 23:37:10,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 143884288. Throughput: 0: 1713.4, 1: 1720.2. Samples: 35976814. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:37:10,557][97672] Avg episode reward: [(0, '-1.640'), (1, '22.540')] -[2023-10-10 23:37:10,930][98559] Updated weights for policy 0, policy_version 70470 (0.0007) -[2023-10-10 23:37:11,296][98559] Updated weights for policy 0, policy_version 70480 (0.0009) -[2023-10-10 23:37:11,664][98559] Updated weights for policy 0, policy_version 70490 (0.0007) -[2023-10-10 23:37:12,656][98560] Updated weights for policy 1, policy_version 70052 (0.0010) -[2023-10-10 23:37:13,016][98560] Updated weights for policy 1, policy_version 70062 (0.0010) -[2023-10-10 23:37:13,380][98560] Updated weights for policy 1, policy_version 70072 (0.0011) -[2023-10-10 23:37:15,463][98559] Updated weights for policy 0, policy_version 70500 (0.0008) -[2023-10-10 23:37:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 143949824. Throughput: 0: 1731.1, 1: 1689.5. Samples: 35996556. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:37:15,557][97672] Avg episode reward: [(0, '-1.640'), (1, '22.500')] -[2023-10-10 23:37:15,830][98559] Updated weights for policy 0, policy_version 70510 (0.0009) -[2023-10-10 23:37:16,191][98559] Updated weights for policy 0, policy_version 70520 (0.0007) -[2023-10-10 23:37:17,416][98560] Updated weights for policy 1, policy_version 70082 (0.0009) -[2023-10-10 23:37:17,777][98560] Updated weights for policy 1, policy_version 70092 (0.0008) -[2023-10-10 23:37:18,140][98560] Updated weights for policy 1, policy_version 70102 (0.0008) -[2023-10-10 23:37:18,511][98560] Updated weights for policy 1, policy_version 70112 (0.0008) -[2023-10-10 23:37:20,263][98559] Updated weights for policy 0, policy_version 70530 (0.0011) -[2023-10-10 23:37:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 144015360. Throughput: 0: 1724.2, 1: 1704.3. Samples: 36017464. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:37:20,556][97672] Avg episode reward: [(0, '-1.640'), (1, '22.480')] -[2023-10-10 23:37:20,623][98559] Updated weights for policy 0, policy_version 70540 (0.0008) -[2023-10-10 23:37:20,994][98559] Updated weights for policy 0, policy_version 70550 (0.0008) -[2023-10-10 23:37:21,353][98559] Updated weights for policy 0, policy_version 70560 (0.0011) -[2023-10-10 23:37:22,700][98560] Updated weights for policy 1, policy_version 70122 (0.0008) -[2023-10-10 23:37:23,077][98560] Updated weights for policy 1, policy_version 70132 (0.0007) -[2023-10-10 23:37:23,448][98560] Updated weights for policy 1, policy_version 70142 (0.0008) -[2023-10-10 23:37:25,410][98559] Updated weights for policy 0, policy_version 70570 (0.0011) -[2023-10-10 23:37:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 144080896. Throughput: 0: 1728.5, 1: 1706.5. Samples: 36027690. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:37:25,557][97672] Avg episode reward: [(0, '-1.640'), (1, '22.460')] -[2023-10-10 23:37:25,767][98559] Updated weights for policy 0, policy_version 70580 (0.0007) -[2023-10-10 23:37:26,135][98559] Updated weights for policy 0, policy_version 70590 (0.0007) -[2023-10-10 23:37:27,645][98560] Updated weights for policy 1, policy_version 70152 (0.0008) -[2023-10-10 23:37:27,998][98560] Updated weights for policy 1, policy_version 70162 (0.0009) -[2023-10-10 23:37:28,366][98560] Updated weights for policy 1, policy_version 70172 (0.0008) -[2023-10-10 23:37:30,079][98559] Updated weights for policy 0, policy_version 70600 (0.0009) -[2023-10-10 23:37:30,453][98559] Updated weights for policy 0, policy_version 70610 (0.0008) -[2023-10-10 23:37:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 144146432. Throughput: 0: 1727.9, 1: 1679.1. Samples: 36047776. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:37:30,557][97672] Avg episode reward: [(0, '-1.640'), (1, '22.540')] -[2023-10-10 23:37:30,821][98559] Updated weights for policy 0, policy_version 70620 (0.0008) -[2023-10-10 23:37:32,370][98560] Updated weights for policy 1, policy_version 70182 (0.0009) -[2023-10-10 23:37:32,731][98560] Updated weights for policy 1, policy_version 70192 (0.0008) -[2023-10-10 23:37:33,095][98560] Updated weights for policy 1, policy_version 70202 (0.0011) -[2023-10-10 23:37:34,661][98559] Updated weights for policy 0, policy_version 70630 (0.0008) -[2023-10-10 23:37:35,041][98559] Updated weights for policy 0, policy_version 70640 (0.0009) -[2023-10-10 23:37:35,396][98559] Updated weights for policy 0, policy_version 70650 (0.0009) -[2023-10-10 23:37:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 144211968. Throughput: 0: 1704.5, 1: 1707.0. Samples: 36068118. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-10 23:37:35,557][97672] Avg episode reward: [(0, '-1.640'), (1, '22.580')] -[2023-10-10 23:37:36,942][98560] Updated weights for policy 1, policy_version 70212 (0.0009) -[2023-10-10 23:37:37,311][98560] Updated weights for policy 1, policy_version 70222 (0.0009) -[2023-10-10 23:37:37,675][98560] Updated weights for policy 1, policy_version 70232 (0.0010) -[2023-10-10 23:37:39,400][98559] Updated weights for policy 0, policy_version 70660 (0.0008) -[2023-10-10 23:37:39,760][98559] Updated weights for policy 0, policy_version 70670 (0.0009) -[2023-10-10 23:37:40,139][98559] Updated weights for policy 0, policy_version 70680 (0.0009) -[2023-10-10 23:37:40,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 144310272. Throughput: 0: 1728.4, 1: 1690.7. Samples: 36078916. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-10 23:37:40,556][97672] Avg episode reward: [(0, '-1.620'), (1, '22.540')] -[2023-10-10 23:37:41,646][98560] Updated weights for policy 1, policy_version 70242 (0.0008) -[2023-10-10 23:37:42,012][98560] Updated weights for policy 1, policy_version 70252 (0.0008) -[2023-10-10 23:37:42,383][98560] Updated weights for policy 1, policy_version 70262 (0.0008) -[2023-10-10 23:37:42,747][98560] Updated weights for policy 1, policy_version 70272 (0.0010) -[2023-10-10 23:37:44,028][98559] Updated weights for policy 0, policy_version 70690 (0.0007) -[2023-10-10 23:37:44,397][98559] Updated weights for policy 0, policy_version 70700 (0.0008) -[2023-10-10 23:37:44,758][98559] Updated weights for policy 0, policy_version 70710 (0.0008) -[2023-10-10 23:37:45,123][98559] Updated weights for policy 0, policy_version 70720 (0.0010) -[2023-10-10 23:37:45,556][97672] Fps is (10 sec: 16384.4, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 144375808. Throughput: 0: 1716.7, 1: 1696.6. Samples: 36099438. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-10 23:37:45,557][97672] Avg episode reward: [(0, '-1.680'), (1, '22.500')] -[2023-10-10 23:37:46,648][98560] Updated weights for policy 1, policy_version 70282 (0.0007) -[2023-10-10 23:37:47,019][98560] Updated weights for policy 1, policy_version 70292 (0.0009) -[2023-10-10 23:37:47,390][98560] Updated weights for policy 1, policy_version 70302 (0.0007) -[2023-10-10 23:37:48,980][98559] Updated weights for policy 0, policy_version 70730 (0.0007) -[2023-10-10 23:37:49,346][98559] Updated weights for policy 0, policy_version 70740 (0.0009) -[2023-10-10 23:37:49,705][98559] Updated weights for policy 0, policy_version 70750 (0.0009) -[2023-10-10 23:37:50,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 144441344. Throughput: 0: 1701.9, 1: 1712.5. Samples: 36119780. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-10 23:37:50,557][97672] Avg episode reward: [(0, '-1.680'), (1, '22.480')] -[2023-10-10 23:37:51,597][98560] Updated weights for policy 1, policy_version 70312 (0.0009) -[2023-10-10 23:37:51,957][98560] Updated weights for policy 1, policy_version 70322 (0.0010) -[2023-10-10 23:37:52,316][98560] Updated weights for policy 1, policy_version 70332 (0.0010) -[2023-10-10 23:37:53,567][98559] Updated weights for policy 0, policy_version 70760 (0.0009) -[2023-10-10 23:37:53,943][98559] Updated weights for policy 0, policy_version 70770 (0.0007) -[2023-10-10 23:37:54,309][98559] Updated weights for policy 0, policy_version 70780 (0.0007) -[2023-10-10 23:37:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 144506880. Throughput: 0: 1734.7, 1: 1675.4. Samples: 36130266. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-10 23:37:55,557][97672] Avg episode reward: [(0, '-1.680'), (1, '22.480')] -[2023-10-10 23:37:56,379][98560] Updated weights for policy 1, policy_version 70342 (0.0009) -[2023-10-10 23:37:56,737][98560] Updated weights for policy 1, policy_version 70352 (0.0008) -[2023-10-10 23:37:57,109][98560] Updated weights for policy 1, policy_version 70362 (0.0010) -[2023-10-10 23:37:58,305][98559] Updated weights for policy 0, policy_version 70790 (0.0010) -[2023-10-10 23:37:58,665][98559] Updated weights for policy 0, policy_version 70800 (0.0010) -[2023-10-10 23:37:59,027][98559] Updated weights for policy 0, policy_version 70810 (0.0008) -[2023-10-10 23:38:00,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 144572416. Throughput: 0: 1707.8, 1: 1703.8. Samples: 36150078. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-10 23:38:00,556][97672] Avg episode reward: [(0, '-1.680'), (1, '22.480')] -[2023-10-10 23:38:01,095][98560] Updated weights for policy 1, policy_version 70372 (0.0009) -[2023-10-10 23:38:01,465][98560] Updated weights for policy 1, policy_version 70382 (0.0009) -[2023-10-10 23:38:01,831][98560] Updated weights for policy 1, policy_version 70392 (0.0008) -[2023-10-10 23:38:02,992][98559] Updated weights for policy 0, policy_version 70820 (0.0009) -[2023-10-10 23:38:03,366][98559] Updated weights for policy 0, policy_version 70830 (0.0010) -[2023-10-10 23:38:03,732][98559] Updated weights for policy 0, policy_version 70840 (0.0009) -[2023-10-10 23:38:05,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 144637952. Throughput: 0: 1713.8, 1: 1703.3. Samples: 36171236. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-10 23:38:05,556][97672] Avg episode reward: [(0, '-1.680'), (1, '22.520')] -[2023-10-10 23:38:05,614][98560] Updated weights for policy 1, policy_version 70402 (0.0007) -[2023-10-10 23:38:05,984][98560] Updated weights for policy 1, policy_version 70412 (0.0007) -[2023-10-10 23:38:06,354][98560] Updated weights for policy 1, policy_version 70422 (0.0007) -[2023-10-10 23:38:06,719][98560] Updated weights for policy 1, policy_version 70432 (0.0007) -[2023-10-10 23:38:07,811][98559] Updated weights for policy 0, policy_version 70850 (0.0008) -[2023-10-10 23:38:08,209][98559] Updated weights for policy 0, policy_version 70860 (0.0010) -[2023-10-10 23:38:08,573][98559] Updated weights for policy 0, policy_version 70870 (0.0010) -[2023-10-10 23:38:08,945][98559] Updated weights for policy 0, policy_version 70880 (0.0008) -[2023-10-10 23:38:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 144703488. Throughput: 0: 1721.2, 1: 1689.7. Samples: 36181178. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-10 23:38:10,556][97672] Avg episode reward: [(0, '-1.460'), (1, '22.540')] -[2023-10-10 23:38:10,712][98560] Updated weights for policy 1, policy_version 70442 (0.0008) -[2023-10-10 23:38:11,073][98560] Updated weights for policy 1, policy_version 70452 (0.0008) -[2023-10-10 23:38:11,436][98560] Updated weights for policy 1, policy_version 70462 (0.0008) -[2023-10-10 23:38:12,903][98559] Updated weights for policy 0, policy_version 70890 (0.0010) -[2023-10-10 23:38:13,275][98559] Updated weights for policy 0, policy_version 70900 (0.0008) -[2023-10-10 23:38:13,639][98559] Updated weights for policy 0, policy_version 70910 (0.0008) -[2023-10-10 23:38:15,340][98560] Updated weights for policy 1, policy_version 70472 (0.0010) -[2023-10-10 23:38:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 144769024. Throughput: 0: 1702.9, 1: 1714.5. Samples: 36201560. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-10 23:38:15,556][97672] Avg episode reward: [(0, '-1.460'), (1, '22.520')] -[2023-10-10 23:38:15,707][98560] Updated weights for policy 1, policy_version 70482 (0.0009) -[2023-10-10 23:38:16,077][98560] Updated weights for policy 1, policy_version 70492 (0.0008) -[2023-10-10 23:38:17,725][98559] Updated weights for policy 0, policy_version 70920 (0.0008) -[2023-10-10 23:38:18,099][98559] Updated weights for policy 0, policy_version 70930 (0.0008) -[2023-10-10 23:38:18,464][98559] Updated weights for policy 0, policy_version 70940 (0.0008) -[2023-10-10 23:38:20,059][98560] Updated weights for policy 1, policy_version 70502 (0.0008) -[2023-10-10 23:38:20,431][98560] Updated weights for policy 1, policy_version 70512 (0.0009) -[2023-10-10 23:38:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 144834560. Throughput: 0: 1721.1, 1: 1717.2. Samples: 36222842. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-10-10 23:38:20,556][97672] Avg episode reward: [(0, '-1.460'), (1, '22.500')] -[2023-10-10 23:38:20,800][98560] Updated weights for policy 1, policy_version 70522 (0.0008) -[2023-10-10 23:38:22,484][98559] Updated weights for policy 0, policy_version 70950 (0.0008) -[2023-10-10 23:38:22,857][98559] Updated weights for policy 0, policy_version 70960 (0.0008) -[2023-10-10 23:38:23,216][98559] Updated weights for policy 0, policy_version 70970 (0.0007) -[2023-10-10 23:38:24,835][98560] Updated weights for policy 1, policy_version 70532 (0.0009) -[2023-10-10 23:38:25,187][98560] Updated weights for policy 1, policy_version 70542 (0.0008) -[2023-10-10 23:38:25,548][98560] Updated weights for policy 1, policy_version 70552 (0.0008) -[2023-10-10 23:38:25,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 144900096. Throughput: 0: 1701.2, 1: 1705.8. Samples: 36232232. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-10-10 23:38:25,556][97672] Avg episode reward: [(0, '-1.500'), (1, '22.400')] -[2023-10-10 23:38:27,214][98559] Updated weights for policy 0, policy_version 70980 (0.0007) -[2023-10-10 23:38:27,569][98559] Updated weights for policy 0, policy_version 70990 (0.0011) -[2023-10-10 23:38:27,935][98559] Updated weights for policy 0, policy_version 71000 (0.0007) -[2023-10-10 23:38:29,617][98560] Updated weights for policy 1, policy_version 70562 (0.0007) -[2023-10-10 23:38:29,974][98560] Updated weights for policy 1, policy_version 70572 (0.0011) -[2023-10-10 23:38:30,338][98560] Updated weights for policy 1, policy_version 70582 (0.0009) -[2023-10-10 23:38:30,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 144965632. Throughput: 0: 1702.4, 1: 1715.0. Samples: 36253220. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-10-10 23:38:30,557][97672] Avg episode reward: [(0, '-1.500'), (1, '22.460')] -[2023-10-10 23:38:30,707][98560] Updated weights for policy 1, policy_version 70592 (0.0007) -[2023-10-10 23:38:31,849][98559] Updated weights for policy 0, policy_version 71010 (0.0008) -[2023-10-10 23:38:32,220][98559] Updated weights for policy 0, policy_version 71020 (0.0008) -[2023-10-10 23:38:32,583][98559] Updated weights for policy 0, policy_version 71030 (0.0009) -[2023-10-10 23:38:32,957][98559] Updated weights for policy 0, policy_version 71040 (0.0009) -[2023-10-10 23:38:34,733][98560] Updated weights for policy 1, policy_version 70602 (0.0008) -[2023-10-10 23:38:35,095][98560] Updated weights for policy 1, policy_version 70612 (0.0008) -[2023-10-10 23:38:35,461][98560] Updated weights for policy 1, policy_version 70622 (0.0008) -[2023-10-10 23:38:35,556][97672] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 145063936. Throughput: 0: 1719.7, 1: 1705.0. Samples: 36273892. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-10-10 23:38:35,556][97672] Avg episode reward: [(0, '-1.500'), (1, '22.440')] -[2023-10-10 23:38:35,564][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000070624_72318976.pth... -[2023-10-10 23:38:35,565][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000071040_72744960.pth... -[2023-10-10 23:38:35,595][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000069024_70680576.pth -[2023-10-10 23:38:35,605][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000069440_71106560.pth -[2023-10-10 23:38:36,856][98559] Updated weights for policy 0, policy_version 71050 (0.0009) -[2023-10-10 23:38:37,213][98559] Updated weights for policy 0, policy_version 71060 (0.0011) -[2023-10-10 23:38:37,583][98559] Updated weights for policy 0, policy_version 71070 (0.0008) -[2023-10-10 23:38:39,394][98560] Updated weights for policy 1, policy_version 70632 (0.0009) -[2023-10-10 23:38:39,756][98560] Updated weights for policy 1, policy_version 70642 (0.0007) -[2023-10-10 23:38:40,119][98560] Updated weights for policy 1, policy_version 70652 (0.0008) -[2023-10-10 23:38:40,556][97672] Fps is (10 sec: 16384.3, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 145129472. Throughput: 0: 1686.1, 1: 1718.6. Samples: 36283478. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-10-10 23:38:40,556][97672] Avg episode reward: [(0, '-1.500'), (1, '22.500')] -[2023-10-10 23:38:41,616][98559] Updated weights for policy 0, policy_version 71080 (0.0009) -[2023-10-10 23:38:41,979][98559] Updated weights for policy 0, policy_version 71090 (0.0008) -[2023-10-10 23:38:42,340][98559] Updated weights for policy 0, policy_version 71100 (0.0008) -[2023-10-10 23:38:44,179][98560] Updated weights for policy 1, policy_version 70662 (0.0009) -[2023-10-10 23:38:44,539][98560] Updated weights for policy 1, policy_version 70672 (0.0009) -[2023-10-10 23:38:44,904][98560] Updated weights for policy 1, policy_version 70682 (0.0009) -[2023-10-10 23:38:45,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 145195008. Throughput: 0: 1711.9, 1: 1720.6. Samples: 36304540. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-10-10 23:38:45,557][97672] Avg episode reward: [(0, '-1.500'), (1, '22.520')] -[2023-10-10 23:38:46,331][98559] Updated weights for policy 0, policy_version 71110 (0.0008) -[2023-10-10 23:38:46,703][98559] Updated weights for policy 0, policy_version 71120 (0.0009) -[2023-10-10 23:38:47,074][98559] Updated weights for policy 0, policy_version 71130 (0.0009) -[2023-10-10 23:38:49,103][98560] Updated weights for policy 1, policy_version 70692 (0.0009) -[2023-10-10 23:38:49,479][98560] Updated weights for policy 1, policy_version 70702 (0.0009) -[2023-10-10 23:38:49,843][98560] Updated weights for policy 1, policy_version 70712 (0.0009) -[2023-10-10 23:38:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 145260544. Throughput: 0: 1710.5, 1: 1695.7. Samples: 36324516. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-10-10 23:38:50,557][97672] Avg episode reward: [(0, '-1.500'), (1, '22.480')] -[2023-10-10 23:38:51,063][98559] Updated weights for policy 0, policy_version 71140 (0.0009) -[2023-10-10 23:38:51,428][98559] Updated weights for policy 0, policy_version 71150 (0.0007) -[2023-10-10 23:38:51,791][98559] Updated weights for policy 0, policy_version 71160 (0.0009) -[2023-10-10 23:38:53,896][98560] Updated weights for policy 1, policy_version 70722 (0.0008) -[2023-10-10 23:38:54,260][98560] Updated weights for policy 1, policy_version 70732 (0.0007) -[2023-10-10 23:38:54,638][98560] Updated weights for policy 1, policy_version 70742 (0.0011) -[2023-10-10 23:38:55,001][98560] Updated weights for policy 1, policy_version 70752 (0.0007) -[2023-10-10 23:38:55,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 145326080. Throughput: 0: 1698.0, 1: 1711.6. Samples: 36334610. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-10-10 23:38:55,556][97672] Avg episode reward: [(0, '-1.500'), (1, '22.500')] -[2023-10-10 23:38:55,850][98559] Updated weights for policy 0, policy_version 71170 (0.0009) -[2023-10-10 23:38:56,220][98559] Updated weights for policy 0, policy_version 71180 (0.0007) -[2023-10-10 23:38:56,578][98559] Updated weights for policy 0, policy_version 71190 (0.0008) -[2023-10-10 23:38:56,943][98559] Updated weights for policy 0, policy_version 71200 (0.0010) -[2023-10-10 23:38:59,161][98560] Updated weights for policy 1, policy_version 70762 (0.0007) -[2023-10-10 23:38:59,546][98560] Updated weights for policy 1, policy_version 70772 (0.0007) -[2023-10-10 23:38:59,904][98560] Updated weights for policy 1, policy_version 70782 (0.0009) -[2023-10-10 23:39:00,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 145391616. Throughput: 0: 1718.4, 1: 1709.9. Samples: 36355834. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-10-10 23:39:00,557][97672] Avg episode reward: [(0, '-1.500'), (1, '22.500')] -[2023-10-10 23:39:00,953][98559] Updated weights for policy 0, policy_version 71210 (0.0010) -[2023-10-10 23:39:01,320][98559] Updated weights for policy 0, policy_version 71220 (0.0009) -[2023-10-10 23:39:01,689][98559] Updated weights for policy 0, policy_version 71230 (0.0007) -[2023-10-10 23:39:03,957][98560] Updated weights for policy 1, policy_version 70792 (0.0009) -[2023-10-10 23:39:04,322][98560] Updated weights for policy 1, policy_version 70802 (0.0011) -[2023-10-10 23:39:04,697][98560] Updated weights for policy 1, policy_version 70812 (0.0009) -[2023-10-10 23:39:05,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 145457152. Throughput: 0: 1718.0, 1: 1673.6. Samples: 36375466. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-10-10 23:39:05,557][97672] Avg episode reward: [(0, '-1.500'), (1, '22.480')] -[2023-10-10 23:39:05,599][98559] Updated weights for policy 0, policy_version 71240 (0.0008) -[2023-10-10 23:39:05,963][98559] Updated weights for policy 0, policy_version 71250 (0.0010) -[2023-10-10 23:39:06,334][98559] Updated weights for policy 0, policy_version 71260 (0.0009) -[2023-10-10 23:39:08,484][98560] Updated weights for policy 1, policy_version 70822 (0.0009) -[2023-10-10 23:39:08,850][98560] Updated weights for policy 1, policy_version 70832 (0.0007) -[2023-10-10 23:39:09,210][98560] Updated weights for policy 1, policy_version 70842 (0.0008) -[2023-10-10 23:39:10,321][98559] Updated weights for policy 0, policy_version 71270 (0.0011) -[2023-10-10 23:39:10,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 145522688. Throughput: 0: 1715.7, 1: 1702.9. Samples: 36386070. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 23:39:10,556][97672] Avg episode reward: [(0, '-1.500'), (1, '22.480')] -[2023-10-10 23:39:10,683][98559] Updated weights for policy 0, policy_version 71280 (0.0010) -[2023-10-10 23:39:11,044][98559] Updated weights for policy 0, policy_version 71290 (0.0010) -[2023-10-10 23:39:12,969][98560] Updated weights for policy 1, policy_version 70852 (0.0008) -[2023-10-10 23:39:13,334][98560] Updated weights for policy 1, policy_version 70862 (0.0009) -[2023-10-10 23:39:13,702][98560] Updated weights for policy 1, policy_version 70872 (0.0009) -[2023-10-10 23:39:15,230][98559] Updated weights for policy 0, policy_version 71300 (0.0010) -[2023-10-10 23:39:15,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 145588224. Throughput: 0: 1719.9, 1: 1684.7. Samples: 36406426. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 23:39:15,557][97672] Avg episode reward: [(0, '-1.500'), (1, '22.440')] -[2023-10-10 23:39:15,606][98559] Updated weights for policy 0, policy_version 71310 (0.0009) -[2023-10-10 23:39:15,957][98559] Updated weights for policy 0, policy_version 71320 (0.0011) -[2023-10-10 23:39:17,737][98560] Updated weights for policy 1, policy_version 70882 (0.0008) -[2023-10-10 23:39:18,109][98560] Updated weights for policy 1, policy_version 70892 (0.0007) -[2023-10-10 23:39:18,473][98560] Updated weights for policy 1, policy_version 70902 (0.0007) -[2023-10-10 23:39:18,841][98560] Updated weights for policy 1, policy_version 70912 (0.0008) -[2023-10-10 23:39:19,944][98559] Updated weights for policy 0, policy_version 71330 (0.0009) -[2023-10-10 23:39:20,302][98559] Updated weights for policy 0, policy_version 71340 (0.0008) -[2023-10-10 23:39:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 145653760. Throughput: 0: 1704.8, 1: 1690.0. Samples: 36426656. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 23:39:20,556][97672] Avg episode reward: [(0, '-1.500'), (1, '22.400')] -[2023-10-10 23:39:20,672][98559] Updated weights for policy 0, policy_version 71350 (0.0007) -[2023-10-10 23:39:21,030][98559] Updated weights for policy 0, policy_version 71360 (0.0007) -[2023-10-10 23:39:22,916][98560] Updated weights for policy 1, policy_version 70922 (0.0009) -[2023-10-10 23:39:23,286][98560] Updated weights for policy 1, policy_version 70932 (0.0008) -[2023-10-10 23:39:23,652][98560] Updated weights for policy 1, policy_version 70942 (0.0010) -[2023-10-10 23:39:25,025][98559] Updated weights for policy 0, policy_version 71370 (0.0008) -[2023-10-10 23:39:25,400][98559] Updated weights for policy 0, policy_version 71380 (0.0008) -[2023-10-10 23:39:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 145719296. Throughput: 0: 1716.6, 1: 1705.8. Samples: 36437488. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 23:39:25,557][97672] Avg episode reward: [(0, '-1.500'), (1, '22.380')] -[2023-10-10 23:39:25,764][98559] Updated weights for policy 0, policy_version 71390 (0.0007) -[2023-10-10 23:39:27,608][98560] Updated weights for policy 1, policy_version 70952 (0.0010) -[2023-10-10 23:39:27,973][98560] Updated weights for policy 1, policy_version 70962 (0.0010) -[2023-10-10 23:39:28,340][98560] Updated weights for policy 1, policy_version 70972 (0.0009) -[2023-10-10 23:39:29,750][98559] Updated weights for policy 0, policy_version 71400 (0.0008) -[2023-10-10 23:39:30,119][98559] Updated weights for policy 0, policy_version 71410 (0.0009) -[2023-10-10 23:39:30,490][98559] Updated weights for policy 0, policy_version 71420 (0.0008) -[2023-10-10 23:39:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 145784832. Throughput: 0: 1720.1, 1: 1680.7. Samples: 36457576. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 23:39:30,557][97672] Avg episode reward: [(0, '-1.500'), (1, '22.380')] -[2023-10-10 23:39:32,407][98560] Updated weights for policy 1, policy_version 70982 (0.0009) -[2023-10-10 23:39:32,772][98560] Updated weights for policy 1, policy_version 70992 (0.0008) -[2023-10-10 23:39:33,140][98560] Updated weights for policy 1, policy_version 71002 (0.0009) -[2023-10-10 23:39:34,355][98559] Updated weights for policy 0, policy_version 71430 (0.0008) -[2023-10-10 23:39:34,713][98559] Updated weights for policy 0, policy_version 71440 (0.0009) -[2023-10-10 23:39:35,081][98559] Updated weights for policy 0, policy_version 71450 (0.0010) -[2023-10-10 23:39:35,556][97672] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 145883136. Throughput: 0: 1698.6, 1: 1704.6. Samples: 36477658. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 23:39:35,557][97672] Avg episode reward: [(0, '-1.500'), (1, '22.380')] -[2023-10-10 23:39:37,211][98560] Updated weights for policy 1, policy_version 71012 (0.0008) -[2023-10-10 23:39:37,574][98560] Updated weights for policy 1, policy_version 71022 (0.0009) -[2023-10-10 23:39:37,932][98560] Updated weights for policy 1, policy_version 71032 (0.0007) -[2023-10-10 23:39:39,035][98559] Updated weights for policy 0, policy_version 71460 (0.0009) -[2023-10-10 23:39:39,397][98559] Updated weights for policy 0, policy_version 71470 (0.0010) -[2023-10-10 23:39:39,758][98559] Updated weights for policy 0, policy_version 71480 (0.0009) -[2023-10-10 23:39:40,556][97672] Fps is (10 sec: 16383.6, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 145948672. Throughput: 0: 1730.9, 1: 1702.5. Samples: 36489114. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 23:39:40,557][97672] Avg episode reward: [(0, '-1.500'), (1, '22.400')] -[2023-10-10 23:39:42,048][98560] Updated weights for policy 1, policy_version 71042 (0.0008) -[2023-10-10 23:39:42,422][98560] Updated weights for policy 1, policy_version 71052 (0.0007) -[2023-10-10 23:39:42,788][98560] Updated weights for policy 1, policy_version 71062 (0.0007) -[2023-10-10 23:39:43,146][98560] Updated weights for policy 1, policy_version 71072 (0.0009) -[2023-10-10 23:39:43,841][98559] Updated weights for policy 0, policy_version 71490 (0.0010) -[2023-10-10 23:39:44,217][98559] Updated weights for policy 0, policy_version 71500 (0.0011) -[2023-10-10 23:39:44,584][98559] Updated weights for policy 0, policy_version 71510 (0.0010) -[2023-10-10 23:39:44,941][98559] Updated weights for policy 0, policy_version 71520 (0.0011) -[2023-10-10 23:39:45,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 146014208. Throughput: 0: 1713.3, 1: 1682.8. Samples: 36508660. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 23:39:45,557][97672] Avg episode reward: [(0, '-1.500'), (1, '22.340')] -[2023-10-10 23:39:47,190][98560] Updated weights for policy 1, policy_version 71082 (0.0008) -[2023-10-10 23:39:47,563][98560] Updated weights for policy 1, policy_version 71092 (0.0009) -[2023-10-10 23:39:47,924][98560] Updated weights for policy 1, policy_version 71102 (0.0009) -[2023-10-10 23:39:49,015][98559] Updated weights for policy 0, policy_version 71530 (0.0010) -[2023-10-10 23:39:49,378][98559] Updated weights for policy 0, policy_version 71540 (0.0008) -[2023-10-10 23:39:49,743][98559] Updated weights for policy 0, policy_version 71550 (0.0009) -[2023-10-10 23:39:50,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 146079744. Throughput: 0: 1696.1, 1: 1717.4. Samples: 36529076. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 23:39:50,557][97672] Avg episode reward: [(0, '-1.500'), (1, '22.420')] -[2023-10-10 23:39:51,813][98560] Updated weights for policy 1, policy_version 71112 (0.0009) -[2023-10-10 23:39:52,183][98560] Updated weights for policy 1, policy_version 71122 (0.0010) -[2023-10-10 23:39:52,544][98560] Updated weights for policy 1, policy_version 71132 (0.0009) -[2023-10-10 23:39:53,594][98559] Updated weights for policy 0, policy_version 71560 (0.0010) -[2023-10-10 23:39:53,957][98559] Updated weights for policy 0, policy_version 71570 (0.0011) -[2023-10-10 23:39:54,320][98559] Updated weights for policy 0, policy_version 71580 (0.0010) -[2023-10-10 23:39:55,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 146145280. Throughput: 0: 1724.9, 1: 1686.8. Samples: 36539594. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 23:39:55,556][97672] Avg episode reward: [(0, '-1.500'), (1, '22.420')] -[2023-10-10 23:39:56,450][98560] Updated weights for policy 1, policy_version 71142 (0.0009) -[2023-10-10 23:39:56,817][98560] Updated weights for policy 1, policy_version 71152 (0.0007) -[2023-10-10 23:39:57,183][98560] Updated weights for policy 1, policy_version 71162 (0.0008) -[2023-10-10 23:39:58,168][98559] Updated weights for policy 0, policy_version 71590 (0.0009) -[2023-10-10 23:39:58,538][98559] Updated weights for policy 0, policy_version 71600 (0.0008) -[2023-10-10 23:39:58,907][98559] Updated weights for policy 0, policy_version 71610 (0.0009) -[2023-10-10 23:40:00,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 146210816. Throughput: 0: 1699.4, 1: 1701.9. Samples: 36559486. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 23:40:00,557][97672] Avg episode reward: [(0, '-1.500'), (1, '22.480')] -[2023-10-10 23:40:01,336][98560] Updated weights for policy 1, policy_version 71172 (0.0010) -[2023-10-10 23:40:01,703][98560] Updated weights for policy 1, policy_version 71182 (0.0009) -[2023-10-10 23:40:02,059][98560] Updated weights for policy 1, policy_version 71192 (0.0008) -[2023-10-10 23:40:02,878][98559] Updated weights for policy 0, policy_version 71620 (0.0010) -[2023-10-10 23:40:03,238][98559] Updated weights for policy 0, policy_version 71630 (0.0009) -[2023-10-10 23:40:03,608][98559] Updated weights for policy 0, policy_version 71640 (0.0010) -[2023-10-10 23:40:05,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 146276352. Throughput: 0: 1713.6, 1: 1705.9. Samples: 36580536. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 23:40:05,557][97672] Avg episode reward: [(0, '-1.500'), (1, '22.500')] -[2023-10-10 23:40:06,162][98560] Updated weights for policy 1, policy_version 71202 (0.0007) -[2023-10-10 23:40:06,525][98560] Updated weights for policy 1, policy_version 71212 (0.0009) -[2023-10-10 23:40:06,896][98560] Updated weights for policy 1, policy_version 71222 (0.0010) -[2023-10-10 23:40:07,263][98560] Updated weights for policy 1, policy_version 71232 (0.0010) -[2023-10-10 23:40:07,576][98559] Updated weights for policy 0, policy_version 71650 (0.0010) -[2023-10-10 23:40:07,933][98559] Updated weights for policy 0, policy_version 71660 (0.0008) -[2023-10-10 23:40:08,298][98559] Updated weights for policy 0, policy_version 71670 (0.0007) -[2023-10-10 23:40:08,671][98559] Updated weights for policy 0, policy_version 71680 (0.0009) -[2023-10-10 23:40:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 146341888. Throughput: 0: 1710.1, 1: 1680.9. Samples: 36590084. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 23:40:10,557][97672] Avg episode reward: [(0, '-1.500'), (1, '22.560')] -[2023-10-10 23:40:11,297][98560] Updated weights for policy 1, policy_version 71242 (0.0007) -[2023-10-10 23:40:11,656][98560] Updated weights for policy 1, policy_version 71252 (0.0011) -[2023-10-10 23:40:12,023][98560] Updated weights for policy 1, policy_version 71262 (0.0011) -[2023-10-10 23:40:12,612][98559] Updated weights for policy 0, policy_version 71690 (0.0009) -[2023-10-10 23:40:12,967][98559] Updated weights for policy 0, policy_version 71700 (0.0008) -[2023-10-10 23:40:13,340][98559] Updated weights for policy 0, policy_version 71710 (0.0009) -[2023-10-10 23:40:15,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 146407424. Throughput: 0: 1705.3, 1: 1706.1. Samples: 36611090. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 23:40:15,557][97672] Avg episode reward: [(0, '-1.500'), (1, '22.540')] -[2023-10-10 23:40:16,110][98560] Updated weights for policy 1, policy_version 71272 (0.0008) -[2023-10-10 23:40:16,479][98560] Updated weights for policy 1, policy_version 71282 (0.0008) -[2023-10-10 23:40:16,856][98560] Updated weights for policy 1, policy_version 71292 (0.0009) -[2023-10-10 23:40:17,337][98559] Updated weights for policy 0, policy_version 71720 (0.0008) -[2023-10-10 23:40:17,703][98559] Updated weights for policy 0, policy_version 71730 (0.0009) -[2023-10-10 23:40:18,064][98559] Updated weights for policy 0, policy_version 71740 (0.0008) -[2023-10-10 23:40:20,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.2, 300 sec: 13662.6). Total num frames: 146472960. Throughput: 0: 1730.1, 1: 1708.8. Samples: 36632408. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 23:40:20,557][97672] Avg episode reward: [(0, '-1.500'), (1, '22.480')] -[2023-10-10 23:40:20,665][98560] Updated weights for policy 1, policy_version 71302 (0.0007) -[2023-10-10 23:40:21,031][98560] Updated weights for policy 1, policy_version 71312 (0.0010) -[2023-10-10 23:40:21,403][98560] Updated weights for policy 1, policy_version 71322 (0.0009) -[2023-10-10 23:40:22,009][98559] Updated weights for policy 0, policy_version 71750 (0.0008) -[2023-10-10 23:40:22,374][98559] Updated weights for policy 0, policy_version 71760 (0.0007) -[2023-10-10 23:40:22,735][98559] Updated weights for policy 0, policy_version 71770 (0.0008) -[2023-10-10 23:40:25,414][98560] Updated weights for policy 1, policy_version 71332 (0.0008) -[2023-10-10 23:40:25,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 146538496. Throughput: 0: 1699.6, 1: 1691.9. Samples: 36641732. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 23:40:25,556][97672] Avg episode reward: [(0, '-1.500'), (1, '22.480')] -[2023-10-10 23:40:25,778][98560] Updated weights for policy 1, policy_version 71342 (0.0008) -[2023-10-10 23:40:26,147][98560] Updated weights for policy 1, policy_version 71352 (0.0010) -[2023-10-10 23:40:26,681][98559] Updated weights for policy 0, policy_version 71780 (0.0009) -[2023-10-10 23:40:27,038][98559] Updated weights for policy 0, policy_version 71790 (0.0010) -[2023-10-10 23:40:27,407][98559] Updated weights for policy 0, policy_version 71800 (0.0010) -[2023-10-10 23:40:30,226][98560] Updated weights for policy 1, policy_version 71362 (0.0009) -[2023-10-10 23:40:30,556][97672] Fps is (10 sec: 13107.8, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 146604032. Throughput: 0: 1710.6, 1: 1712.8. Samples: 36662714. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 23:40:30,556][97672] Avg episode reward: [(0, '-1.500'), (1, '22.440')] -[2023-10-10 23:40:30,594][98560] Updated weights for policy 1, policy_version 71372 (0.0009) -[2023-10-10 23:40:30,962][98560] Updated weights for policy 1, policy_version 71382 (0.0009) -[2023-10-10 23:40:31,333][98560] Updated weights for policy 1, policy_version 71392 (0.0010) -[2023-10-10 23:40:31,539][98559] Updated weights for policy 0, policy_version 71810 (0.0010) -[2023-10-10 23:40:31,947][98559] Updated weights for policy 0, policy_version 71820 (0.0009) -[2023-10-10 23:40:32,308][98559] Updated weights for policy 0, policy_version 71830 (0.0010) -[2023-10-10 23:40:32,671][98559] Updated weights for policy 0, policy_version 71840 (0.0007) -[2023-10-10 23:40:35,260][98560] Updated weights for policy 1, policy_version 71402 (0.0009) -[2023-10-10 23:40:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 146669568. Throughput: 0: 1727.9, 1: 1712.8. Samples: 36683904. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 23:40:35,557][97672] Avg episode reward: [(0, '-1.500'), (1, '22.500')] -[2023-10-10 23:40:35,567][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000071840_73564160.pth... -[2023-10-10 23:40:35,601][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000070240_71925760.pth -[2023-10-10 23:40:35,605][98385] Saving a milestone ./train_atari/atari_doubledunk_APPO/checkpoint_p0/milestones/checkpoint_000071840_73564160.pth -[2023-10-10 23:40:35,628][98560] Updated weights for policy 1, policy_version 71412 (0.0007) -[2023-10-10 23:40:35,995][98560] Updated weights for policy 1, policy_version 71422 (0.0008) -[2023-10-10 23:40:36,064][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000071424_73138176.pth... -[2023-10-10 23:40:36,093][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000069824_71499776.pth -[2023-10-10 23:40:36,097][98439] Saving a milestone ./train_atari/atari_doubledunk_APPO/checkpoint_p1/milestones/checkpoint_000071424_73138176.pth -[2023-10-10 23:40:36,641][98559] Updated weights for policy 0, policy_version 71850 (0.0009) -[2023-10-10 23:40:37,010][98559] Updated weights for policy 0, policy_version 71860 (0.0009) -[2023-10-10 23:40:37,383][98559] Updated weights for policy 0, policy_version 71870 (0.0008) -[2023-10-10 23:40:40,053][98560] Updated weights for policy 1, policy_version 71432 (0.0009) -[2023-10-10 23:40:40,412][98560] Updated weights for policy 1, policy_version 71442 (0.0007) -[2023-10-10 23:40:40,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 146735104. Throughput: 0: 1699.5, 1: 1710.9. Samples: 36693060. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 23:40:40,556][97672] Avg episode reward: [(0, '-1.480'), (1, '22.440')] -[2023-10-10 23:40:40,788][98560] Updated weights for policy 1, policy_version 71452 (0.0010) -[2023-10-10 23:40:41,320][98559] Updated weights for policy 0, policy_version 71880 (0.0009) -[2023-10-10 23:40:41,688][98559] Updated weights for policy 0, policy_version 71890 (0.0009) -[2023-10-10 23:40:42,058][98559] Updated weights for policy 0, policy_version 71900 (0.0008) -[2023-10-10 23:40:44,963][98560] Updated weights for policy 1, policy_version 71462 (0.0010) -[2023-10-10 23:40:45,326][98560] Updated weights for policy 1, policy_version 71472 (0.0009) -[2023-10-10 23:40:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 146800640. Throughput: 0: 1727.6, 1: 1705.8. Samples: 36713988. Policy #0 lag: (min: 6.0, avg: 6.2, max: 15.0) -[2023-10-10 23:40:45,556][97672] Avg episode reward: [(0, '-1.480'), (1, '22.400')] -[2023-10-10 23:40:45,688][98560] Updated weights for policy 1, policy_version 71482 (0.0009) -[2023-10-10 23:40:45,982][98559] Updated weights for policy 0, policy_version 71910 (0.0009) -[2023-10-10 23:40:46,355][98559] Updated weights for policy 0, policy_version 71920 (0.0010) -[2023-10-10 23:40:46,720][98559] Updated weights for policy 0, policy_version 71930 (0.0008) -[2023-10-10 23:40:49,765][98560] Updated weights for policy 1, policy_version 71492 (0.0008) -[2023-10-10 23:40:50,129][98560] Updated weights for policy 1, policy_version 71502 (0.0007) -[2023-10-10 23:40:50,491][98560] Updated weights for policy 1, policy_version 71512 (0.0007) -[2023-10-10 23:40:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 146866176. Throughput: 0: 1726.4, 1: 1705.2. Samples: 36734954. Policy #0 lag: (min: 6.0, avg: 6.2, max: 15.0) -[2023-10-10 23:40:50,557][97672] Avg episode reward: [(0, '-1.480'), (1, '22.320')] -[2023-10-10 23:40:50,747][98559] Updated weights for policy 0, policy_version 71940 (0.0007) -[2023-10-10 23:40:51,099][98559] Updated weights for policy 0, policy_version 71950 (0.0008) -[2023-10-10 23:40:51,473][98559] Updated weights for policy 0, policy_version 71960 (0.0010) -[2023-10-10 23:40:54,497][98560] Updated weights for policy 1, policy_version 71522 (0.0008) -[2023-10-10 23:40:54,852][98560] Updated weights for policy 1, policy_version 71532 (0.0008) -[2023-10-10 23:40:55,224][98560] Updated weights for policy 1, policy_version 71542 (0.0007) -[2023-10-10 23:40:55,441][98559] Updated weights for policy 0, policy_version 71970 (0.0010) -[2023-10-10 23:40:55,556][97672] Fps is (10 sec: 13106.7, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 146931712. Throughput: 0: 1717.5, 1: 1708.4. Samples: 36744248. Policy #0 lag: (min: 6.0, avg: 6.2, max: 15.0) -[2023-10-10 23:40:55,558][97672] Avg episode reward: [(0, '-1.340'), (1, '22.280')] -[2023-10-10 23:40:55,585][98560] Updated weights for policy 1, policy_version 71552 (0.0009) -[2023-10-10 23:40:55,804][98559] Updated weights for policy 0, policy_version 71980 (0.0007) -[2023-10-10 23:40:56,182][98559] Updated weights for policy 0, policy_version 71990 (0.0007) -[2023-10-10 23:40:56,548][98559] Updated weights for policy 0, policy_version 72000 (0.0007) -[2023-10-10 23:40:59,631][98560] Updated weights for policy 1, policy_version 71562 (0.0009) -[2023-10-10 23:40:59,995][98560] Updated weights for policy 1, policy_version 71572 (0.0010) -[2023-10-10 23:41:00,357][98560] Updated weights for policy 1, policy_version 71582 (0.0008) -[2023-10-10 23:41:00,364][98559] Updated weights for policy 0, policy_version 72010 (0.0008) -[2023-10-10 23:41:00,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 147030016. Throughput: 0: 1724.3, 1: 1702.3. Samples: 36765288. Policy #0 lag: (min: 6.0, avg: 6.2, max: 15.0) -[2023-10-10 23:41:00,557][97672] Avg episode reward: [(0, '-1.340'), (1, '22.260')] -[2023-10-10 23:41:00,731][98559] Updated weights for policy 0, policy_version 72020 (0.0009) -[2023-10-10 23:41:01,084][98559] Updated weights for policy 0, policy_version 72030 (0.0010) -[2023-10-10 23:41:04,332][98560] Updated weights for policy 1, policy_version 71592 (0.0009) -[2023-10-10 23:41:04,697][98560] Updated weights for policy 1, policy_version 71602 (0.0009) -[2023-10-10 23:41:05,067][98560] Updated weights for policy 1, policy_version 71612 (0.0007) -[2023-10-10 23:41:05,177][98559] Updated weights for policy 0, policy_version 72040 (0.0010) -[2023-10-10 23:41:05,545][98559] Updated weights for policy 0, policy_version 72050 (0.0008) -[2023-10-10 23:41:05,556][97672] Fps is (10 sec: 16384.6, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 147095552. Throughput: 0: 1709.0, 1: 1683.2. Samples: 36785056. Policy #0 lag: (min: 6.0, avg: 6.2, max: 15.0) -[2023-10-10 23:41:05,556][97672] Avg episode reward: [(0, '-1.320'), (1, '22.260')] -[2023-10-10 23:41:05,903][98559] Updated weights for policy 0, policy_version 72060 (0.0007) -[2023-10-10 23:41:09,194][98560] Updated weights for policy 1, policy_version 71622 (0.0009) -[2023-10-10 23:41:09,567][98560] Updated weights for policy 1, policy_version 71632 (0.0009) -[2023-10-10 23:41:09,929][98560] Updated weights for policy 1, policy_version 71642 (0.0008) -[2023-10-10 23:41:09,978][98559] Updated weights for policy 0, policy_version 72070 (0.0008) -[2023-10-10 23:41:10,343][98559] Updated weights for policy 0, policy_version 72080 (0.0008) -[2023-10-10 23:41:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 147161088. Throughput: 0: 1716.0, 1: 1697.5. Samples: 36795338. Policy #0 lag: (min: 6.0, avg: 6.2, max: 15.0) -[2023-10-10 23:41:10,557][97672] Avg episode reward: [(0, '-1.320'), (1, '22.360')] -[2023-10-10 23:41:10,712][98559] Updated weights for policy 0, policy_version 72090 (0.0008) -[2023-10-10 23:41:13,879][98560] Updated weights for policy 1, policy_version 71652 (0.0007) -[2023-10-10 23:41:14,255][98560] Updated weights for policy 1, policy_version 71662 (0.0009) -[2023-10-10 23:41:14,620][98560] Updated weights for policy 1, policy_version 71672 (0.0008) -[2023-10-10 23:41:14,761][98559] Updated weights for policy 0, policy_version 72100 (0.0009) -[2023-10-10 23:41:15,123][98559] Updated weights for policy 0, policy_version 72110 (0.0009) -[2023-10-10 23:41:15,488][98559] Updated weights for policy 0, policy_version 72120 (0.0009) -[2023-10-10 23:41:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 147226624. Throughput: 0: 1722.2, 1: 1694.4. Samples: 36816462. Policy #0 lag: (min: 6.0, avg: 6.2, max: 15.0) -[2023-10-10 23:41:15,556][97672] Avg episode reward: [(0, '-1.320'), (1, '22.440')] -[2023-10-10 23:41:18,541][98560] Updated weights for policy 1, policy_version 71682 (0.0010) -[2023-10-10 23:41:18,902][98560] Updated weights for policy 1, policy_version 71692 (0.0010) -[2023-10-10 23:41:19,273][98560] Updated weights for policy 1, policy_version 71702 (0.0010) -[2023-10-10 23:41:19,472][98559] Updated weights for policy 0, policy_version 72130 (0.0008) -[2023-10-10 23:41:19,652][98560] Updated weights for policy 1, policy_version 71712 (0.0009) -[2023-10-10 23:41:19,873][98559] Updated weights for policy 0, policy_version 72140 (0.0010) -[2023-10-10 23:41:20,231][98559] Updated weights for policy 0, policy_version 72150 (0.0009) -[2023-10-10 23:41:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 147292160. Throughput: 0: 1699.9, 1: 1661.7. Samples: 36835174. Policy #0 lag: (min: 6.0, avg: 6.2, max: 15.0) -[2023-10-10 23:41:20,556][97672] Avg episode reward: [(0, '-1.320'), (1, '22.440')] -[2023-10-10 23:41:20,601][98559] Updated weights for policy 0, policy_version 72160 (0.0009) -[2023-10-10 23:41:23,816][98560] Updated weights for policy 1, policy_version 71722 (0.0009) -[2023-10-10 23:41:24,183][98560] Updated weights for policy 1, policy_version 71732 (0.0010) -[2023-10-10 23:41:24,543][98560] Updated weights for policy 1, policy_version 71742 (0.0009) -[2023-10-10 23:41:24,587][98559] Updated weights for policy 0, policy_version 72170 (0.0009) -[2023-10-10 23:41:24,951][98559] Updated weights for policy 0, policy_version 72180 (0.0008) -[2023-10-10 23:41:25,309][98559] Updated weights for policy 0, policy_version 72190 (0.0009) -[2023-10-10 23:41:25,556][97672] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 147390464. Throughput: 0: 1718.0, 1: 1694.5. Samples: 36846626. Policy #0 lag: (min: 6.0, avg: 6.2, max: 15.0) -[2023-10-10 23:41:25,557][97672] Avg episode reward: [(0, '-1.320'), (1, '22.420')] -[2023-10-10 23:41:28,575][98560] Updated weights for policy 1, policy_version 71752 (0.0007) -[2023-10-10 23:41:28,934][98560] Updated weights for policy 1, policy_version 71762 (0.0008) -[2023-10-10 23:41:29,306][98560] Updated weights for policy 1, policy_version 71772 (0.0008) -[2023-10-10 23:41:29,345][98559] Updated weights for policy 0, policy_version 72200 (0.0007) -[2023-10-10 23:41:29,709][98559] Updated weights for policy 0, policy_version 72210 (0.0010) -[2023-10-10 23:41:30,079][98559] Updated weights for policy 0, policy_version 72220 (0.0007) -[2023-10-10 23:41:30,556][97672] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 147456000. Throughput: 0: 1711.4, 1: 1685.0. Samples: 36866826. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:41:30,556][97672] Avg episode reward: [(0, '-1.320'), (1, '22.520')] -[2023-10-10 23:41:33,351][98560] Updated weights for policy 1, policy_version 71782 (0.0009) -[2023-10-10 23:41:33,714][98560] Updated weights for policy 1, policy_version 71792 (0.0007) -[2023-10-10 23:41:33,971][98559] Updated weights for policy 0, policy_version 72230 (0.0007) -[2023-10-10 23:41:34,089][98560] Updated weights for policy 1, policy_version 71802 (0.0007) -[2023-10-10 23:41:34,339][98559] Updated weights for policy 0, policy_version 72240 (0.0008) -[2023-10-10 23:41:34,705][98559] Updated weights for policy 0, policy_version 72250 (0.0008) -[2023-10-10 23:41:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 147521536. Throughput: 0: 1689.5, 1: 1664.7. Samples: 36885894. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:41:35,557][97672] Avg episode reward: [(0, '-1.320'), (1, '22.540')] -[2023-10-10 23:41:38,107][98560] Updated weights for policy 1, policy_version 71812 (0.0008) -[2023-10-10 23:41:38,487][98560] Updated weights for policy 1, policy_version 71822 (0.0008) -[2023-10-10 23:41:38,622][98559] Updated weights for policy 0, policy_version 72260 (0.0008) -[2023-10-10 23:41:38,847][98560] Updated weights for policy 1, policy_version 71832 (0.0008) -[2023-10-10 23:41:38,991][98559] Updated weights for policy 0, policy_version 72270 (0.0009) -[2023-10-10 23:41:39,360][98559] Updated weights for policy 0, policy_version 72280 (0.0009) -[2023-10-10 23:41:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 147587072. Throughput: 0: 1720.8, 1: 1688.1. Samples: 36897648. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:41:40,556][97672] Avg episode reward: [(0, '-1.320'), (1, '22.640')] -[2023-10-10 23:41:42,912][98560] Updated weights for policy 1, policy_version 71842 (0.0007) -[2023-10-10 23:41:43,271][98560] Updated weights for policy 1, policy_version 71852 (0.0007) -[2023-10-10 23:41:43,358][98559] Updated weights for policy 0, policy_version 72290 (0.0009) -[2023-10-10 23:41:43,641][98560] Updated weights for policy 1, policy_version 71862 (0.0007) -[2023-10-10 23:41:43,721][98559] Updated weights for policy 0, policy_version 72300 (0.0008) -[2023-10-10 23:41:44,005][98560] Updated weights for policy 1, policy_version 71872 (0.0008) -[2023-10-10 23:41:44,078][98559] Updated weights for policy 0, policy_version 72310 (0.0008) -[2023-10-10 23:41:44,446][98559] Updated weights for policy 0, policy_version 72320 (0.0011) -[2023-10-10 23:41:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 147652608. Throughput: 0: 1688.7, 1: 1672.4. Samples: 36916540. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:41:45,557][97672] Avg episode reward: [(0, '-1.320'), (1, '22.640')] -[2023-10-10 23:41:48,027][98560] Updated weights for policy 1, policy_version 71882 (0.0008) -[2023-10-10 23:41:48,385][98560] Updated weights for policy 1, policy_version 71892 (0.0008) -[2023-10-10 23:41:48,462][98559] Updated weights for policy 0, policy_version 72330 (0.0007) -[2023-10-10 23:41:48,758][98560] Updated weights for policy 1, policy_version 71902 (0.0008) -[2023-10-10 23:41:48,824][98559] Updated weights for policy 0, policy_version 72340 (0.0009) -[2023-10-10 23:41:49,183][98559] Updated weights for policy 0, policy_version 72350 (0.0009) -[2023-10-10 23:41:50,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 147718144. Throughput: 0: 1699.2, 1: 1681.6. Samples: 36937188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:41:50,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.580')] -[2023-10-10 23:41:52,864][98560] Updated weights for policy 1, policy_version 71912 (0.0009) -[2023-10-10 23:41:53,116][98559] Updated weights for policy 0, policy_version 72360 (0.0008) -[2023-10-10 23:41:53,220][98560] Updated weights for policy 1, policy_version 71922 (0.0009) -[2023-10-10 23:41:53,483][98559] Updated weights for policy 0, policy_version 72370 (0.0007) -[2023-10-10 23:41:53,588][98560] Updated weights for policy 1, policy_version 71932 (0.0008) -[2023-10-10 23:41:53,843][98559] Updated weights for policy 0, policy_version 72380 (0.0010) -[2023-10-10 23:41:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 147783680. Throughput: 0: 1709.9, 1: 1694.1. Samples: 36948518. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:41:55,557][97672] Avg episode reward: [(0, '-1.260'), (1, '22.540')] -[2023-10-10 23:41:57,603][98560] Updated weights for policy 1, policy_version 71942 (0.0007) -[2023-10-10 23:41:57,844][98559] Updated weights for policy 0, policy_version 72390 (0.0008) -[2023-10-10 23:41:57,972][98560] Updated weights for policy 1, policy_version 71952 (0.0007) -[2023-10-10 23:41:58,208][98559] Updated weights for policy 0, policy_version 72400 (0.0007) -[2023-10-10 23:41:58,341][98560] Updated weights for policy 1, policy_version 71962 (0.0007) -[2023-10-10 23:41:58,578][98559] Updated weights for policy 0, policy_version 72410 (0.0007) -[2023-10-10 23:42:00,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 147849216. Throughput: 0: 1691.3, 1: 1670.3. Samples: 36967736. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:42:00,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.580')] -[2023-10-10 23:42:02,369][98560] Updated weights for policy 1, policy_version 71972 (0.0007) -[2023-10-10 23:42:02,443][98559] Updated weights for policy 0, policy_version 72420 (0.0007) -[2023-10-10 23:42:02,735][98560] Updated weights for policy 1, policy_version 71982 (0.0007) -[2023-10-10 23:42:02,809][98559] Updated weights for policy 0, policy_version 72430 (0.0009) -[2023-10-10 23:42:03,100][98560] Updated weights for policy 1, policy_version 71992 (0.0008) -[2023-10-10 23:42:03,172][98559] Updated weights for policy 0, policy_version 72440 (0.0010) -[2023-10-10 23:42:05,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 147914752. Throughput: 0: 1723.0, 1: 1699.7. Samples: 36989196. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:42:05,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.560')] -[2023-10-10 23:42:07,087][98560] Updated weights for policy 1, policy_version 72002 (0.0008) -[2023-10-10 23:42:07,236][98559] Updated weights for policy 0, policy_version 72450 (0.0007) -[2023-10-10 23:42:07,457][98560] Updated weights for policy 1, policy_version 72012 (0.0007) -[2023-10-10 23:42:07,633][98559] Updated weights for policy 0, policy_version 72460 (0.0008) -[2023-10-10 23:42:07,820][98560] Updated weights for policy 1, policy_version 72022 (0.0008) -[2023-10-10 23:42:07,995][98559] Updated weights for policy 0, policy_version 72470 (0.0008) -[2023-10-10 23:42:08,182][98560] Updated weights for policy 1, policy_version 72032 (0.0008) -[2023-10-10 23:42:08,355][98559] Updated weights for policy 0, policy_version 72480 (0.0008) -[2023-10-10 23:42:10,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 147980288. Throughput: 0: 1701.5, 1: 1680.4. Samples: 36998812. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:42:10,557][97672] Avg episode reward: [(0, '-1.200'), (1, '22.600')] -[2023-10-10 23:42:12,223][98560] Updated weights for policy 1, policy_version 72042 (0.0010) -[2023-10-10 23:42:12,453][98559] Updated weights for policy 0, policy_version 72490 (0.0007) -[2023-10-10 23:42:12,583][98560] Updated weights for policy 1, policy_version 72052 (0.0008) -[2023-10-10 23:42:12,812][98559] Updated weights for policy 0, policy_version 72500 (0.0007) -[2023-10-10 23:42:12,949][98560] Updated weights for policy 1, policy_version 72062 (0.0008) -[2023-10-10 23:42:13,176][98559] Updated weights for policy 0, policy_version 72510 (0.0009) -[2023-10-10 23:42:15,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 148045824. Throughput: 0: 1699.8, 1: 1685.2. Samples: 37019150. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:42:15,557][97672] Avg episode reward: [(0, '-1.160'), (1, '22.540')] -[2023-10-10 23:42:17,028][98560] Updated weights for policy 1, policy_version 72072 (0.0008) -[2023-10-10 23:42:17,328][98559] Updated weights for policy 0, policy_version 72520 (0.0008) -[2023-10-10 23:42:17,396][98560] Updated weights for policy 1, policy_version 72082 (0.0008) -[2023-10-10 23:42:17,700][98559] Updated weights for policy 0, policy_version 72530 (0.0008) -[2023-10-10 23:42:17,770][98560] Updated weights for policy 1, policy_version 72092 (0.0008) -[2023-10-10 23:42:18,056][98559] Updated weights for policy 0, policy_version 72540 (0.0008) -[2023-10-10 23:42:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 148111360. Throughput: 0: 1723.8, 1: 1709.0. Samples: 37040370. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-10 23:42:20,557][97672] Avg episode reward: [(0, '-1.160'), (1, '22.540')] -[2023-10-10 23:42:21,695][98560] Updated weights for policy 1, policy_version 72102 (0.0009) -[2023-10-10 23:42:21,883][98559] Updated weights for policy 0, policy_version 72550 (0.0007) -[2023-10-10 23:42:22,056][98560] Updated weights for policy 1, policy_version 72112 (0.0011) -[2023-10-10 23:42:22,246][98559] Updated weights for policy 0, policy_version 72560 (0.0007) -[2023-10-10 23:42:22,422][98560] Updated weights for policy 1, policy_version 72122 (0.0010) -[2023-10-10 23:42:22,612][98559] Updated weights for policy 0, policy_version 72570 (0.0008) -[2023-10-10 23:42:25,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 148176896. Throughput: 0: 1692.5, 1: 1681.4. Samples: 37049474. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-10 23:42:25,556][97672] Avg episode reward: [(0, '-1.000'), (1, '22.560')] -[2023-10-10 23:42:26,505][98560] Updated weights for policy 1, policy_version 72132 (0.0008) -[2023-10-10 23:42:26,655][98559] Updated weights for policy 0, policy_version 72580 (0.0010) -[2023-10-10 23:42:26,870][98560] Updated weights for policy 1, policy_version 72142 (0.0008) -[2023-10-10 23:42:27,021][98559] Updated weights for policy 0, policy_version 72590 (0.0009) -[2023-10-10 23:42:27,239][98560] Updated weights for policy 1, policy_version 72152 (0.0008) -[2023-10-10 23:42:27,372][98559] Updated weights for policy 0, policy_version 72600 (0.0008) -[2023-10-10 23:42:30,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 148242432. Throughput: 0: 1719.2, 1: 1700.3. Samples: 37070420. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-10 23:42:30,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.480')] -[2023-10-10 23:42:31,287][98559] Updated weights for policy 0, policy_version 72610 (0.0008) -[2023-10-10 23:42:31,369][98560] Updated weights for policy 1, policy_version 72162 (0.0008) -[2023-10-10 23:42:31,648][98559] Updated weights for policy 0, policy_version 72620 (0.0007) -[2023-10-10 23:42:31,733][98560] Updated weights for policy 1, policy_version 72172 (0.0008) -[2023-10-10 23:42:32,012][98559] Updated weights for policy 0, policy_version 72630 (0.0007) -[2023-10-10 23:42:32,097][98560] Updated weights for policy 1, policy_version 72182 (0.0008) -[2023-10-10 23:42:32,373][98559] Updated weights for policy 0, policy_version 72640 (0.0007) -[2023-10-10 23:42:32,464][98560] Updated weights for policy 1, policy_version 72192 (0.0009) -[2023-10-10 23:42:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 148307968. Throughput: 0: 1724.9, 1: 1706.8. Samples: 37091614. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-10 23:42:35,556][97672] Avg episode reward: [(0, '-0.980'), (1, '22.520')] -[2023-10-10 23:42:35,570][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000072192_73924608.pth... -[2023-10-10 23:42:35,570][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000072640_74383360.pth... -[2023-10-10 23:42:35,607][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000070624_72318976.pth -[2023-10-10 23:42:35,607][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000071040_72744960.pth -[2023-10-10 23:42:36,245][98559] Updated weights for policy 0, policy_version 72650 (0.0007) -[2023-10-10 23:42:36,378][98560] Updated weights for policy 1, policy_version 72202 (0.0008) -[2023-10-10 23:42:36,612][98559] Updated weights for policy 0, policy_version 72660 (0.0007) -[2023-10-10 23:42:36,740][98560] Updated weights for policy 1, policy_version 72212 (0.0007) -[2023-10-10 23:42:36,970][98559] Updated weights for policy 0, policy_version 72670 (0.0008) -[2023-10-10 23:42:37,101][98560] Updated weights for policy 1, policy_version 72222 (0.0007) -[2023-10-10 23:42:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 148373504. Throughput: 0: 1703.7, 1: 1679.2. Samples: 37100748. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-10 23:42:40,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.520')] -[2023-10-10 23:42:41,041][98559] Updated weights for policy 0, policy_version 72680 (0.0009) -[2023-10-10 23:42:41,176][98560] Updated weights for policy 1, policy_version 72232 (0.0007) -[2023-10-10 23:42:41,401][98559] Updated weights for policy 0, policy_version 72690 (0.0009) -[2023-10-10 23:42:41,535][98560] Updated weights for policy 1, policy_version 72242 (0.0009) -[2023-10-10 23:42:41,763][98559] Updated weights for policy 0, policy_version 72700 (0.0009) -[2023-10-10 23:42:41,908][98560] Updated weights for policy 1, policy_version 72252 (0.0009) -[2023-10-10 23:42:45,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 148439040. Throughput: 0: 1721.0, 1: 1704.1. Samples: 37121864. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-10 23:42:45,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.540')] -[2023-10-10 23:42:45,797][98559] Updated weights for policy 0, policy_version 72710 (0.0008) -[2023-10-10 23:42:45,913][98560] Updated weights for policy 1, policy_version 72262 (0.0009) -[2023-10-10 23:42:46,160][98559] Updated weights for policy 0, policy_version 72720 (0.0007) -[2023-10-10 23:42:46,280][98560] Updated weights for policy 1, policy_version 72272 (0.0007) -[2023-10-10 23:42:46,535][98559] Updated weights for policy 0, policy_version 72730 (0.0007) -[2023-10-10 23:42:46,655][98560] Updated weights for policy 1, policy_version 72282 (0.0009) -[2023-10-10 23:42:50,543][98559] Updated weights for policy 0, policy_version 72740 (0.0009) -[2023-10-10 23:42:50,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 148504576. Throughput: 0: 1713.1, 1: 1705.1. Samples: 37143016. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-10 23:42:50,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.540')] -[2023-10-10 23:42:50,731][98560] Updated weights for policy 1, policy_version 72292 (0.0008) -[2023-10-10 23:42:50,901][98559] Updated weights for policy 0, policy_version 72750 (0.0010) -[2023-10-10 23:42:51,088][98560] Updated weights for policy 1, policy_version 72302 (0.0008) -[2023-10-10 23:42:51,269][98559] Updated weights for policy 0, policy_version 72760 (0.0009) -[2023-10-10 23:42:51,458][98560] Updated weights for policy 1, policy_version 72312 (0.0008) -[2023-10-10 23:42:55,377][98559] Updated weights for policy 0, policy_version 72770 (0.0008) -[2023-10-10 23:42:55,431][98560] Updated weights for policy 1, policy_version 72322 (0.0010) -[2023-10-10 23:42:55,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 148570112. Throughput: 0: 1716.2, 1: 1690.0. Samples: 37152092. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-10 23:42:55,556][97672] Avg episode reward: [(0, '-1.000'), (1, '22.520')] -[2023-10-10 23:42:55,782][98559] Updated weights for policy 0, policy_version 72780 (0.0007) -[2023-10-10 23:42:55,794][98560] Updated weights for policy 1, policy_version 72332 (0.0007) -[2023-10-10 23:42:56,143][98559] Updated weights for policy 0, policy_version 72790 (0.0007) -[2023-10-10 23:42:56,162][98560] Updated weights for policy 1, policy_version 72342 (0.0008) -[2023-10-10 23:42:56,499][98559] Updated weights for policy 0, policy_version 72800 (0.0007) -[2023-10-10 23:42:56,525][98560] Updated weights for policy 1, policy_version 72352 (0.0007) -[2023-10-10 23:43:00,435][98559] Updated weights for policy 0, policy_version 72810 (0.0009) -[2023-10-10 23:43:00,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 148635648. Throughput: 0: 1720.5, 1: 1697.1. Samples: 37172942. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-10 23:43:00,556][97672] Avg episode reward: [(0, '-1.000'), (1, '22.440')] -[2023-10-10 23:43:00,731][98560] Updated weights for policy 1, policy_version 72362 (0.0008) -[2023-10-10 23:43:00,796][98559] Updated weights for policy 0, policy_version 72820 (0.0008) -[2023-10-10 23:43:01,102][98560] Updated weights for policy 1, policy_version 72372 (0.0008) -[2023-10-10 23:43:01,157][98559] Updated weights for policy 0, policy_version 72830 (0.0007) -[2023-10-10 23:43:01,478][98560] Updated weights for policy 1, policy_version 72382 (0.0008) -[2023-10-10 23:43:05,140][98559] Updated weights for policy 0, policy_version 72840 (0.0007) -[2023-10-10 23:43:05,398][98560] Updated weights for policy 1, policy_version 72392 (0.0008) -[2023-10-10 23:43:05,504][98559] Updated weights for policy 0, policy_version 72850 (0.0008) -[2023-10-10 23:43:05,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 148701184. Throughput: 0: 1708.7, 1: 1693.1. Samples: 37193450. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-10 23:43:05,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.440')] -[2023-10-10 23:43:05,768][98560] Updated weights for policy 1, policy_version 72402 (0.0007) -[2023-10-10 23:43:05,876][98559] Updated weights for policy 0, policy_version 72860 (0.0008) -[2023-10-10 23:43:06,128][98560] Updated weights for policy 1, policy_version 72412 (0.0008) -[2023-10-10 23:43:09,881][98559] Updated weights for policy 0, policy_version 72870 (0.0009) -[2023-10-10 23:43:10,158][98560] Updated weights for policy 1, policy_version 72422 (0.0008) -[2023-10-10 23:43:10,243][98559] Updated weights for policy 0, policy_version 72880 (0.0008) -[2023-10-10 23:43:10,527][98560] Updated weights for policy 1, policy_version 72432 (0.0007) -[2023-10-10 23:43:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 148766720. Throughput: 0: 1720.4, 1: 1695.2. Samples: 37203176. Policy #0 lag: (min: 9.0, avg: 14.2, max: 41.0) -[2023-10-10 23:43:10,556][97672] Avg episode reward: [(0, '-1.000'), (1, '22.420')] -[2023-10-10 23:43:10,604][98559] Updated weights for policy 0, policy_version 72890 (0.0009) -[2023-10-10 23:43:10,893][98560] Updated weights for policy 1, policy_version 72442 (0.0009) -[2023-10-10 23:43:14,592][98559] Updated weights for policy 0, policy_version 72900 (0.0008) -[2023-10-10 23:43:14,925][98560] Updated weights for policy 1, policy_version 72452 (0.0009) -[2023-10-10 23:43:14,962][98559] Updated weights for policy 0, policy_version 72910 (0.0008) -[2023-10-10 23:43:15,293][98560] Updated weights for policy 1, policy_version 72462 (0.0008) -[2023-10-10 23:43:15,316][98559] Updated weights for policy 0, policy_version 72920 (0.0009) -[2023-10-10 23:43:15,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 148832256. Throughput: 0: 1721.7, 1: 1693.3. Samples: 37224094. Policy #0 lag: (min: 9.0, avg: 14.2, max: 41.0) -[2023-10-10 23:43:15,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.500')] -[2023-10-10 23:43:15,664][98560] Updated weights for policy 1, policy_version 72472 (0.0008) -[2023-10-10 23:43:19,195][98559] Updated weights for policy 0, policy_version 72930 (0.0007) -[2023-10-10 23:43:19,556][98559] Updated weights for policy 0, policy_version 72940 (0.0008) -[2023-10-10 23:43:19,647][98560] Updated weights for policy 1, policy_version 72482 (0.0007) -[2023-10-10 23:43:19,929][98559] Updated weights for policy 0, policy_version 72950 (0.0008) -[2023-10-10 23:43:20,010][98560] Updated weights for policy 1, policy_version 72492 (0.0008) -[2023-10-10 23:43:20,284][98559] Updated weights for policy 0, policy_version 72960 (0.0009) -[2023-10-10 23:43:20,374][98560] Updated weights for policy 1, policy_version 72502 (0.0009) -[2023-10-10 23:43:20,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 148930560. Throughput: 0: 1692.7, 1: 1688.9. Samples: 37243784. Policy #0 lag: (min: 9.0, avg: 14.2, max: 41.0) -[2023-10-10 23:43:20,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.520')] -[2023-10-10 23:43:20,744][98560] Updated weights for policy 1, policy_version 72512 (0.0010) -[2023-10-10 23:43:24,267][98559] Updated weights for policy 0, policy_version 72970 (0.0008) -[2023-10-10 23:43:24,621][98559] Updated weights for policy 0, policy_version 72980 (0.0008) -[2023-10-10 23:43:24,761][98560] Updated weights for policy 1, policy_version 72522 (0.0009) -[2023-10-10 23:43:24,988][98559] Updated weights for policy 0, policy_version 72990 (0.0008) -[2023-10-10 23:43:25,132][98560] Updated weights for policy 1, policy_version 72532 (0.0007) -[2023-10-10 23:43:25,505][98560] Updated weights for policy 1, policy_version 72542 (0.0007) -[2023-10-10 23:43:25,556][97672] Fps is (10 sec: 16384.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 148996096. Throughput: 0: 1724.8, 1: 1690.5. Samples: 37254436. Policy #0 lag: (min: 9.0, avg: 14.2, max: 41.0) -[2023-10-10 23:43:25,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.620')] -[2023-10-10 23:43:29,054][98559] Updated weights for policy 0, policy_version 73000 (0.0009) -[2023-10-10 23:43:29,424][98559] Updated weights for policy 0, policy_version 73010 (0.0008) -[2023-10-10 23:43:29,573][98560] Updated weights for policy 1, policy_version 72552 (0.0008) -[2023-10-10 23:43:29,798][98559] Updated weights for policy 0, policy_version 73020 (0.0009) -[2023-10-10 23:43:29,941][98560] Updated weights for policy 1, policy_version 72562 (0.0008) -[2023-10-10 23:43:30,302][98560] Updated weights for policy 1, policy_version 72572 (0.0008) -[2023-10-10 23:43:30,556][97672] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 149094400. Throughput: 0: 1704.4, 1: 1694.7. Samples: 37274824. Policy #0 lag: (min: 9.0, avg: 14.2, max: 41.0) -[2023-10-10 23:43:30,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.620')] -[2023-10-10 23:43:33,764][98559] Updated weights for policy 0, policy_version 73030 (0.0008) -[2023-10-10 23:43:34,136][98559] Updated weights for policy 0, policy_version 73040 (0.0007) -[2023-10-10 23:43:34,426][98560] Updated weights for policy 1, policy_version 72582 (0.0007) -[2023-10-10 23:43:34,494][98559] Updated weights for policy 0, policy_version 73050 (0.0009) -[2023-10-10 23:43:34,791][98560] Updated weights for policy 1, policy_version 72592 (0.0009) -[2023-10-10 23:43:35,155][98560] Updated weights for policy 1, policy_version 72602 (0.0008) -[2023-10-10 23:43:35,556][97672] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 149159936. Throughput: 0: 1691.4, 1: 1686.3. Samples: 37295014. Policy #0 lag: (min: 9.0, avg: 14.2, max: 41.0) -[2023-10-10 23:43:35,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.580')] -[2023-10-10 23:43:38,275][98559] Updated weights for policy 0, policy_version 73060 (0.0010) -[2023-10-10 23:43:38,647][98559] Updated weights for policy 0, policy_version 73070 (0.0008) -[2023-10-10 23:43:39,006][98559] Updated weights for policy 0, policy_version 73080 (0.0007) -[2023-10-10 23:43:39,231][98560] Updated weights for policy 1, policy_version 72612 (0.0007) -[2023-10-10 23:43:39,608][98560] Updated weights for policy 1, policy_version 72622 (0.0010) -[2023-10-10 23:43:39,970][98560] Updated weights for policy 1, policy_version 72632 (0.0009) -[2023-10-10 23:43:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 149225472. Throughput: 0: 1718.3, 1: 1700.7. Samples: 37305946. Policy #0 lag: (min: 9.0, avg: 14.2, max: 41.0) -[2023-10-10 23:43:40,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.640')] -[2023-10-10 23:43:43,049][98559] Updated weights for policy 0, policy_version 73090 (0.0010) -[2023-10-10 23:43:43,429][98559] Updated weights for policy 0, policy_version 73100 (0.0009) -[2023-10-10 23:43:43,798][98559] Updated weights for policy 0, policy_version 73110 (0.0009) -[2023-10-10 23:43:44,073][98560] Updated weights for policy 1, policy_version 72642 (0.0008) -[2023-10-10 23:43:44,161][98559] Updated weights for policy 0, policy_version 73120 (0.0010) -[2023-10-10 23:43:44,437][98560] Updated weights for policy 1, policy_version 72652 (0.0008) -[2023-10-10 23:43:44,812][98560] Updated weights for policy 1, policy_version 72662 (0.0010) -[2023-10-10 23:43:45,189][98560] Updated weights for policy 1, policy_version 72672 (0.0010) -[2023-10-10 23:43:45,556][97672] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 149291008. Throughput: 0: 1693.9, 1: 1701.1. Samples: 37325716. Policy #0 lag: (min: 9.0, avg: 14.2, max: 41.0) -[2023-10-10 23:43:45,556][97672] Avg episode reward: [(0, '-1.000'), (1, '22.660')] -[2023-10-10 23:43:48,030][98559] Updated weights for policy 0, policy_version 73130 (0.0011) -[2023-10-10 23:43:48,392][98559] Updated weights for policy 0, policy_version 73140 (0.0011) -[2023-10-10 23:43:48,766][98559] Updated weights for policy 0, policy_version 73150 (0.0009) -[2023-10-10 23:43:49,170][98560] Updated weights for policy 1, policy_version 72682 (0.0009) -[2023-10-10 23:43:49,538][98560] Updated weights for policy 1, policy_version 72692 (0.0007) -[2023-10-10 23:43:49,908][98560] Updated weights for policy 1, policy_version 72702 (0.0008) -[2023-10-10 23:43:50,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 149356544. Throughput: 0: 1707.1, 1: 1682.8. Samples: 37345994. Policy #0 lag: (min: 9.0, avg: 14.2, max: 41.0) -[2023-10-10 23:43:50,557][97672] Avg episode reward: [(0, '-1.000'), (1, '22.720')] -[2023-10-10 23:43:52,752][98559] Updated weights for policy 0, policy_version 73160 (0.0010) -[2023-10-10 23:43:53,114][98559] Updated weights for policy 0, policy_version 73170 (0.0007) -[2023-10-10 23:43:53,483][98559] Updated weights for policy 0, policy_version 73180 (0.0008) -[2023-10-10 23:43:53,925][98560] Updated weights for policy 1, policy_version 72712 (0.0009) -[2023-10-10 23:43:54,299][98560] Updated weights for policy 1, policy_version 72722 (0.0009) -[2023-10-10 23:43:54,664][98560] Updated weights for policy 1, policy_version 72732 (0.0010) -[2023-10-10 23:43:55,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 149422080. Throughput: 0: 1703.6, 1: 1703.1. Samples: 37356480. Policy #0 lag: (min: 19.0, avg: 19.4, max: 32.0) -[2023-10-10 23:43:55,556][97672] Avg episode reward: [(0, '-1.000'), (1, '22.640')] -[2023-10-10 23:43:57,543][98559] Updated weights for policy 0, policy_version 73190 (0.0007) -[2023-10-10 23:43:57,911][98559] Updated weights for policy 0, policy_version 73200 (0.0007) -[2023-10-10 23:43:58,266][98559] Updated weights for policy 0, policy_version 73210 (0.0010) -[2023-10-10 23:43:58,582][98560] Updated weights for policy 1, policy_version 72742 (0.0009) -[2023-10-10 23:43:58,941][98560] Updated weights for policy 1, policy_version 72752 (0.0008) -[2023-10-10 23:43:59,308][98560] Updated weights for policy 1, policy_version 72762 (0.0007) -[2023-10-10 23:44:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 149487616. Throughput: 0: 1697.4, 1: 1700.8. Samples: 37377012. Policy #0 lag: (min: 19.0, avg: 19.4, max: 32.0) -[2023-10-10 23:44:00,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.640')] -[2023-10-10 23:44:02,243][98559] Updated weights for policy 0, policy_version 73220 (0.0009) -[2023-10-10 23:44:02,611][98559] Updated weights for policy 0, policy_version 73230 (0.0009) -[2023-10-10 23:44:02,979][98559] Updated weights for policy 0, policy_version 73240 (0.0009) -[2023-10-10 23:44:03,334][98560] Updated weights for policy 1, policy_version 72772 (0.0009) -[2023-10-10 23:44:03,711][98560] Updated weights for policy 1, policy_version 72782 (0.0007) -[2023-10-10 23:44:04,071][98560] Updated weights for policy 1, policy_version 72792 (0.0007) -[2023-10-10 23:44:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 149553152. Throughput: 0: 1725.3, 1: 1682.7. Samples: 37397142. Policy #0 lag: (min: 19.0, avg: 19.4, max: 32.0) -[2023-10-10 23:44:05,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.640')] -[2023-10-10 23:44:06,945][98559] Updated weights for policy 0, policy_version 73250 (0.0008) -[2023-10-10 23:44:07,318][98559] Updated weights for policy 0, policy_version 73260 (0.0011) -[2023-10-10 23:44:07,688][98559] Updated weights for policy 0, policy_version 73270 (0.0010) -[2023-10-10 23:44:08,024][98560] Updated weights for policy 1, policy_version 72802 (0.0009) -[2023-10-10 23:44:08,056][98559] Updated weights for policy 0, policy_version 73280 (0.0009) -[2023-10-10 23:44:08,395][98560] Updated weights for policy 1, policy_version 72812 (0.0007) -[2023-10-10 23:44:08,761][98560] Updated weights for policy 1, policy_version 72822 (0.0007) -[2023-10-10 23:44:09,134][98560] Updated weights for policy 1, policy_version 72832 (0.0008) -[2023-10-10 23:44:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 149618688. Throughput: 0: 1692.6, 1: 1716.0. Samples: 37407826. Policy #0 lag: (min: 19.0, avg: 19.4, max: 32.0) -[2023-10-10 23:44:10,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.500')] -[2023-10-10 23:44:12,078][98559] Updated weights for policy 0, policy_version 73290 (0.0008) -[2023-10-10 23:44:12,452][98559] Updated weights for policy 0, policy_version 73300 (0.0008) -[2023-10-10 23:44:12,816][98559] Updated weights for policy 0, policy_version 73310 (0.0009) -[2023-10-10 23:44:12,953][98560] Updated weights for policy 1, policy_version 72842 (0.0009) -[2023-10-10 23:44:13,318][98560] Updated weights for policy 1, policy_version 72852 (0.0008) -[2023-10-10 23:44:13,680][98560] Updated weights for policy 1, policy_version 72862 (0.0009) -[2023-10-10 23:44:15,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 149684224. Throughput: 0: 1707.4, 1: 1690.3. Samples: 37427722. Policy #0 lag: (min: 19.0, avg: 19.4, max: 32.0) -[2023-10-10 23:44:15,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.480')] -[2023-10-10 23:44:16,752][98559] Updated weights for policy 0, policy_version 73320 (0.0008) -[2023-10-10 23:44:17,119][98559] Updated weights for policy 0, policy_version 73330 (0.0008) -[2023-10-10 23:44:17,476][98559] Updated weights for policy 0, policy_version 73340 (0.0007) -[2023-10-10 23:44:17,751][98560] Updated weights for policy 1, policy_version 72872 (0.0010) -[2023-10-10 23:44:18,122][98560] Updated weights for policy 1, policy_version 72882 (0.0007) -[2023-10-10 23:44:18,487][98560] Updated weights for policy 1, policy_version 72892 (0.0008) -[2023-10-10 23:44:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 149749760. Throughput: 0: 1718.2, 1: 1693.1. Samples: 37448524. Policy #0 lag: (min: 19.0, avg: 19.4, max: 32.0) -[2023-10-10 23:44:20,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.420')] -[2023-10-10 23:44:21,437][98559] Updated weights for policy 0, policy_version 73350 (0.0009) -[2023-10-10 23:44:21,800][98559] Updated weights for policy 0, policy_version 73360 (0.0011) -[2023-10-10 23:44:22,164][98559] Updated weights for policy 0, policy_version 73370 (0.0008) -[2023-10-10 23:44:22,389][98560] Updated weights for policy 1, policy_version 72902 (0.0008) -[2023-10-10 23:44:22,751][98560] Updated weights for policy 1, policy_version 72912 (0.0008) -[2023-10-10 23:44:23,118][98560] Updated weights for policy 1, policy_version 72922 (0.0010) -[2023-10-10 23:44:25,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 149815296. Throughput: 0: 1690.0, 1: 1701.2. Samples: 37458548. Policy #0 lag: (min: 19.0, avg: 19.4, max: 32.0) -[2023-10-10 23:44:25,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.320')] -[2023-10-10 23:44:26,234][98559] Updated weights for policy 0, policy_version 73380 (0.0008) -[2023-10-10 23:44:26,598][98559] Updated weights for policy 0, policy_version 73390 (0.0010) -[2023-10-10 23:44:26,962][98559] Updated weights for policy 0, policy_version 73400 (0.0010) -[2023-10-10 23:44:27,064][98560] Updated weights for policy 1, policy_version 72932 (0.0011) -[2023-10-10 23:44:27,438][98560] Updated weights for policy 1, policy_version 72942 (0.0011) -[2023-10-10 23:44:27,800][98560] Updated weights for policy 1, policy_version 72952 (0.0009) -[2023-10-10 23:44:30,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 149880832. Throughput: 0: 1715.0, 1: 1689.5. Samples: 37478918. Policy #0 lag: (min: 19.0, avg: 19.4, max: 32.0) -[2023-10-10 23:44:30,556][97672] Avg episode reward: [(0, '-0.980'), (1, '22.340')] -[2023-10-10 23:44:31,122][98559] Updated weights for policy 0, policy_version 73410 (0.0008) -[2023-10-10 23:44:31,537][98559] Updated weights for policy 0, policy_version 73420 (0.0009) -[2023-10-10 23:44:31,893][98559] Updated weights for policy 0, policy_version 73430 (0.0007) -[2023-10-10 23:44:31,941][98560] Updated weights for policy 1, policy_version 72962 (0.0008) -[2023-10-10 23:44:32,258][98559] Updated weights for policy 0, policy_version 73440 (0.0008) -[2023-10-10 23:44:32,309][98560] Updated weights for policy 1, policy_version 72972 (0.0007) -[2023-10-10 23:44:32,671][98560] Updated weights for policy 1, policy_version 72982 (0.0010) -[2023-10-10 23:44:33,047][98560] Updated weights for policy 1, policy_version 72992 (0.0010) -[2023-10-10 23:44:35,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 149946368. Throughput: 0: 1707.5, 1: 1705.6. Samples: 37499584. Policy #0 lag: (min: 19.0, avg: 19.4, max: 32.0) -[2023-10-10 23:44:35,556][97672] Avg episode reward: [(0, '-0.960'), (1, '22.360')] -[2023-10-10 23:44:35,563][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000072992_74743808.pth... -[2023-10-10 23:44:35,563][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000073440_75202560.pth... -[2023-10-10 23:44:35,600][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000071840_73564160.pth -[2023-10-10 23:44:35,606][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000071424_73138176.pth -[2023-10-10 23:44:36,334][98559] Updated weights for policy 0, policy_version 73450 (0.0009) -[2023-10-10 23:44:36,695][98559] Updated weights for policy 0, policy_version 73460 (0.0008) -[2023-10-10 23:44:37,059][98559] Updated weights for policy 0, policy_version 73470 (0.0008) -[2023-10-10 23:44:37,199][98560] Updated weights for policy 1, policy_version 73002 (0.0009) -[2023-10-10 23:44:37,570][98560] Updated weights for policy 1, policy_version 73012 (0.0008) -[2023-10-10 23:44:37,939][98560] Updated weights for policy 1, policy_version 73022 (0.0007) -[2023-10-10 23:44:40,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 150011904. Throughput: 0: 1702.0, 1: 1690.0. Samples: 37509116. Policy #0 lag: (min: 19.0, avg: 19.4, max: 32.0) -[2023-10-10 23:44:40,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.400')] -[2023-10-10 23:44:41,127][98559] Updated weights for policy 0, policy_version 73480 (0.0008) -[2023-10-10 23:44:41,492][98559] Updated weights for policy 0, policy_version 73490 (0.0008) -[2023-10-10 23:44:41,849][98559] Updated weights for policy 0, policy_version 73500 (0.0008) -[2023-10-10 23:44:42,036][98560] Updated weights for policy 1, policy_version 73032 (0.0007) -[2023-10-10 23:44:42,408][98560] Updated weights for policy 1, policy_version 73042 (0.0008) -[2023-10-10 23:44:42,765][98560] Updated weights for policy 1, policy_version 73052 (0.0008) -[2023-10-10 23:44:45,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 150077440. Throughput: 0: 1704.0, 1: 1678.4. Samples: 37529220. Policy #0 lag: (min: 31.0, avg: 31.3, max: 41.0) -[2023-10-10 23:44:45,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.400')] -[2023-10-10 23:44:45,959][98559] Updated weights for policy 0, policy_version 73510 (0.0007) -[2023-10-10 23:44:46,329][98559] Updated weights for policy 0, policy_version 73520 (0.0008) -[2023-10-10 23:44:46,691][98559] Updated weights for policy 0, policy_version 73530 (0.0007) -[2023-10-10 23:44:46,817][98560] Updated weights for policy 1, policy_version 73062 (0.0007) -[2023-10-10 23:44:47,173][98560] Updated weights for policy 1, policy_version 73072 (0.0008) -[2023-10-10 23:44:47,548][98560] Updated weights for policy 1, policy_version 73082 (0.0009) -[2023-10-10 23:44:50,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 150142976. Throughput: 0: 1700.7, 1: 1703.6. Samples: 37550338. Policy #0 lag: (min: 31.0, avg: 31.3, max: 41.0) -[2023-10-10 23:44:50,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.380')] -[2023-10-10 23:44:50,715][98559] Updated weights for policy 0, policy_version 73540 (0.0007) -[2023-10-10 23:44:51,084][98559] Updated weights for policy 0, policy_version 73550 (0.0009) -[2023-10-10 23:44:51,449][98559] Updated weights for policy 0, policy_version 73560 (0.0009) -[2023-10-10 23:44:51,593][98560] Updated weights for policy 1, policy_version 73092 (0.0008) -[2023-10-10 23:44:51,964][98560] Updated weights for policy 1, policy_version 73102 (0.0009) -[2023-10-10 23:44:52,340][98560] Updated weights for policy 1, policy_version 73112 (0.0009) -[2023-10-10 23:44:55,410][98559] Updated weights for policy 0, policy_version 73570 (0.0007) -[2023-10-10 23:44:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 150208512. Throughput: 0: 1699.9, 1: 1668.2. Samples: 37559390. Policy #0 lag: (min: 31.0, avg: 31.3, max: 41.0) -[2023-10-10 23:44:55,557][97672] Avg episode reward: [(0, '-0.920'), (1, '22.360')] -[2023-10-10 23:44:55,779][98559] Updated weights for policy 0, policy_version 73580 (0.0008) -[2023-10-10 23:44:56,146][98559] Updated weights for policy 0, policy_version 73590 (0.0011) -[2023-10-10 23:44:56,500][98560] Updated weights for policy 1, policy_version 73122 (0.0009) -[2023-10-10 23:44:56,505][98559] Updated weights for policy 0, policy_version 73600 (0.0010) -[2023-10-10 23:44:56,860][98560] Updated weights for policy 1, policy_version 73132 (0.0009) -[2023-10-10 23:44:57,235][98560] Updated weights for policy 1, policy_version 73142 (0.0009) -[2023-10-10 23:44:57,591][98560] Updated weights for policy 1, policy_version 73152 (0.0011) -[2023-10-10 23:45:00,420][98559] Updated weights for policy 0, policy_version 73610 (0.0007) -[2023-10-10 23:45:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 150274048. Throughput: 0: 1708.2, 1: 1686.3. Samples: 37580472. Policy #0 lag: (min: 31.0, avg: 31.3, max: 41.0) -[2023-10-10 23:45:00,556][97672] Avg episode reward: [(0, '-0.920'), (1, '22.380')] -[2023-10-10 23:45:00,776][98559] Updated weights for policy 0, policy_version 73620 (0.0009) -[2023-10-10 23:45:01,136][98559] Updated weights for policy 0, policy_version 73630 (0.0009) -[2023-10-10 23:45:01,651][98560] Updated weights for policy 1, policy_version 73162 (0.0008) -[2023-10-10 23:45:02,014][98560] Updated weights for policy 1, policy_version 73172 (0.0007) -[2023-10-10 23:45:02,388][98560] Updated weights for policy 1, policy_version 73182 (0.0008) -[2023-10-10 23:45:04,943][98559] Updated weights for policy 0, policy_version 73640 (0.0010) -[2023-10-10 23:45:05,306][98559] Updated weights for policy 0, policy_version 73650 (0.0008) -[2023-10-10 23:45:05,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 150339584. Throughput: 0: 1696.2, 1: 1687.2. Samples: 37600780. Policy #0 lag: (min: 31.0, avg: 31.3, max: 41.0) -[2023-10-10 23:45:05,557][97672] Avg episode reward: [(0, '-0.860'), (1, '22.340')] -[2023-10-10 23:45:05,674][98559] Updated weights for policy 0, policy_version 73660 (0.0008) -[2023-10-10 23:45:06,461][98560] Updated weights for policy 1, policy_version 73192 (0.0008) -[2023-10-10 23:45:06,831][98560] Updated weights for policy 1, policy_version 73202 (0.0009) -[2023-10-10 23:45:07,189][98560] Updated weights for policy 1, policy_version 73212 (0.0008) -[2023-10-10 23:45:09,607][98559] Updated weights for policy 0, policy_version 73670 (0.0007) -[2023-10-10 23:45:09,976][98559] Updated weights for policy 0, policy_version 73680 (0.0009) -[2023-10-10 23:45:10,342][98559] Updated weights for policy 0, policy_version 73690 (0.0008) -[2023-10-10 23:45:10,556][97672] Fps is (10 sec: 13106.7, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 150405120. Throughput: 0: 1714.7, 1: 1667.5. Samples: 37610748. Policy #0 lag: (min: 31.0, avg: 31.3, max: 41.0) -[2023-10-10 23:45:10,558][97672] Avg episode reward: [(0, '-0.860'), (1, '22.420')] -[2023-10-10 23:45:11,152][98560] Updated weights for policy 1, policy_version 73222 (0.0009) -[2023-10-10 23:45:11,523][98560] Updated weights for policy 1, policy_version 73232 (0.0010) -[2023-10-10 23:45:11,880][98560] Updated weights for policy 1, policy_version 73242 (0.0010) -[2023-10-10 23:45:14,426][98559] Updated weights for policy 0, policy_version 73700 (0.0010) -[2023-10-10 23:45:14,797][98559] Updated weights for policy 0, policy_version 73710 (0.0011) -[2023-10-10 23:45:15,161][98559] Updated weights for policy 0, policy_version 73720 (0.0009) -[2023-10-10 23:45:15,556][97672] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 150503424. Throughput: 0: 1715.2, 1: 1687.0. Samples: 37632016. Policy #0 lag: (min: 31.0, avg: 31.3, max: 41.0) -[2023-10-10 23:45:15,557][97672] Avg episode reward: [(0, '-0.860'), (1, '22.480')] -[2023-10-10 23:45:15,957][98560] Updated weights for policy 1, policy_version 73252 (0.0007) -[2023-10-10 23:45:16,324][98560] Updated weights for policy 1, policy_version 73262 (0.0008) -[2023-10-10 23:45:16,696][98560] Updated weights for policy 1, policy_version 73272 (0.0007) -[2023-10-10 23:45:19,196][98559] Updated weights for policy 0, policy_version 73730 (0.0009) -[2023-10-10 23:45:19,589][98559] Updated weights for policy 0, policy_version 73740 (0.0009) -[2023-10-10 23:45:19,959][98559] Updated weights for policy 0, policy_version 73750 (0.0009) -[2023-10-10 23:45:20,326][98559] Updated weights for policy 0, policy_version 73760 (0.0008) -[2023-10-10 23:45:20,556][97672] Fps is (10 sec: 16384.6, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 150568960. Throughput: 0: 1692.1, 1: 1691.7. Samples: 37651858. Policy #0 lag: (min: 31.0, avg: 31.3, max: 41.0) -[2023-10-10 23:45:20,556][97672] Avg episode reward: [(0, '-0.860'), (1, '22.560')] -[2023-10-10 23:45:20,795][98560] Updated weights for policy 1, policy_version 73282 (0.0009) -[2023-10-10 23:45:21,157][98560] Updated weights for policy 1, policy_version 73292 (0.0008) -[2023-10-10 23:45:21,520][98560] Updated weights for policy 1, policy_version 73302 (0.0008) -[2023-10-10 23:45:21,887][98560] Updated weights for policy 1, policy_version 73312 (0.0011) -[2023-10-10 23:45:24,197][98559] Updated weights for policy 0, policy_version 73770 (0.0008) -[2023-10-10 23:45:24,565][98559] Updated weights for policy 0, policy_version 73780 (0.0008) -[2023-10-10 23:45:24,926][98559] Updated weights for policy 0, policy_version 73790 (0.0008) -[2023-10-10 23:45:25,556][97672] Fps is (10 sec: 13107.7, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 150634496. Throughput: 0: 1721.1, 1: 1688.3. Samples: 37662538. Policy #0 lag: (min: 31.0, avg: 31.3, max: 41.0) -[2023-10-10 23:45:25,556][97672] Avg episode reward: [(0, '-0.860'), (1, '22.580')] -[2023-10-10 23:45:25,915][98560] Updated weights for policy 1, policy_version 73322 (0.0010) -[2023-10-10 23:45:26,270][98560] Updated weights for policy 1, policy_version 73332 (0.0011) -[2023-10-10 23:45:26,640][98560] Updated weights for policy 1, policy_version 73342 (0.0010) -[2023-10-10 23:45:28,709][98559] Updated weights for policy 0, policy_version 73800 (0.0008) -[2023-10-10 23:45:29,079][98559] Updated weights for policy 0, policy_version 73810 (0.0007) -[2023-10-10 23:45:29,444][98559] Updated weights for policy 0, policy_version 73820 (0.0010) -[2023-10-10 23:45:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 150700032. Throughput: 0: 1711.3, 1: 1700.4. Samples: 37682750. Policy #0 lag: (min: 30.0, avg: 30.5, max: 46.0) -[2023-10-10 23:45:30,556][97672] Avg episode reward: [(0, '-0.860'), (1, '22.600')] -[2023-10-10 23:45:30,631][98560] Updated weights for policy 1, policy_version 73352 (0.0009) -[2023-10-10 23:45:31,005][98560] Updated weights for policy 1, policy_version 73362 (0.0012) -[2023-10-10 23:45:31,360][98560] Updated weights for policy 1, policy_version 73372 (0.0011) -[2023-10-10 23:45:33,599][98559] Updated weights for policy 0, policy_version 73830 (0.0008) -[2023-10-10 23:45:33,969][98559] Updated weights for policy 0, policy_version 73840 (0.0008) -[2023-10-10 23:45:34,332][98559] Updated weights for policy 0, policy_version 73850 (0.0008) -[2023-10-10 23:45:35,322][98560] Updated weights for policy 1, policy_version 73382 (0.0010) -[2023-10-10 23:45:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 150765568. Throughput: 0: 1706.1, 1: 1700.8. Samples: 37703650. Policy #0 lag: (min: 30.0, avg: 30.5, max: 46.0) -[2023-10-10 23:45:35,556][97672] Avg episode reward: [(0, '-0.860'), (1, '22.600')] -[2023-10-10 23:45:35,698][98560] Updated weights for policy 1, policy_version 73392 (0.0010) -[2023-10-10 23:45:36,064][98560] Updated weights for policy 1, policy_version 73402 (0.0009) -[2023-10-10 23:45:38,320][98559] Updated weights for policy 0, policy_version 73860 (0.0009) -[2023-10-10 23:45:38,687][98559] Updated weights for policy 0, policy_version 73870 (0.0010) -[2023-10-10 23:45:39,054][98559] Updated weights for policy 0, policy_version 73880 (0.0008) -[2023-10-10 23:45:40,159][98560] Updated weights for policy 1, policy_version 73412 (0.0008) -[2023-10-10 23:45:40,529][98560] Updated weights for policy 1, policy_version 73422 (0.0007) -[2023-10-10 23:45:40,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 150831104. Throughput: 0: 1731.2, 1: 1706.3. Samples: 37714078. Policy #0 lag: (min: 30.0, avg: 30.5, max: 46.0) -[2023-10-10 23:45:40,556][97672] Avg episode reward: [(0, '-0.860'), (1, '22.540')] -[2023-10-10 23:45:40,895][98560] Updated weights for policy 1, policy_version 73432 (0.0007) -[2023-10-10 23:45:42,952][98559] Updated weights for policy 0, policy_version 73890 (0.0010) -[2023-10-10 23:45:43,315][98559] Updated weights for policy 0, policy_version 73900 (0.0009) -[2023-10-10 23:45:43,675][98559] Updated weights for policy 0, policy_version 73910 (0.0009) -[2023-10-10 23:45:44,045][98559] Updated weights for policy 0, policy_version 73920 (0.0008) -[2023-10-10 23:45:44,924][98560] Updated weights for policy 1, policy_version 73442 (0.0007) -[2023-10-10 23:45:45,297][98560] Updated weights for policy 1, policy_version 73452 (0.0009) -[2023-10-10 23:45:45,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 150896640. Throughput: 0: 1704.9, 1: 1710.7. Samples: 37734172. Policy #0 lag: (min: 30.0, avg: 30.5, max: 46.0) -[2023-10-10 23:45:45,557][97672] Avg episode reward: [(0, '-0.860'), (1, '22.460')] -[2023-10-10 23:45:45,667][98560] Updated weights for policy 1, policy_version 73462 (0.0009) -[2023-10-10 23:45:46,045][98560] Updated weights for policy 1, policy_version 73472 (0.0009) -[2023-10-10 23:45:47,808][98559] Updated weights for policy 0, policy_version 73930 (0.0009) -[2023-10-10 23:45:48,173][98559] Updated weights for policy 0, policy_version 73940 (0.0010) -[2023-10-10 23:45:48,540][98559] Updated weights for policy 0, policy_version 73950 (0.0010) -[2023-10-10 23:45:50,080][98560] Updated weights for policy 1, policy_version 73482 (0.0008) -[2023-10-10 23:45:50,442][98560] Updated weights for policy 1, policy_version 73492 (0.0007) -[2023-10-10 23:45:50,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 150962176. Throughput: 0: 1718.4, 1: 1713.7. Samples: 37755226. Policy #0 lag: (min: 30.0, avg: 30.5, max: 46.0) -[2023-10-10 23:45:50,556][97672] Avg episode reward: [(0, '-0.860'), (1, '22.380')] -[2023-10-10 23:45:50,806][98560] Updated weights for policy 1, policy_version 73502 (0.0009) -[2023-10-10 23:45:52,645][98559] Updated weights for policy 0, policy_version 73960 (0.0007) -[2023-10-10 23:45:53,011][98559] Updated weights for policy 0, policy_version 73970 (0.0007) -[2023-10-10 23:45:53,381][98559] Updated weights for policy 0, policy_version 73980 (0.0008) -[2023-10-10 23:45:54,675][98560] Updated weights for policy 1, policy_version 73512 (0.0009) -[2023-10-10 23:45:55,045][98560] Updated weights for policy 1, policy_version 73522 (0.0007) -[2023-10-10 23:45:55,416][98560] Updated weights for policy 1, policy_version 73532 (0.0009) -[2023-10-10 23:45:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 151027712. Throughput: 0: 1705.8, 1: 1714.4. Samples: 37764658. Policy #0 lag: (min: 30.0, avg: 30.5, max: 46.0) -[2023-10-10 23:45:55,557][97672] Avg episode reward: [(0, '-0.860'), (1, '22.360')] -[2023-10-10 23:45:57,524][98559] Updated weights for policy 0, policy_version 73990 (0.0008) -[2023-10-10 23:45:57,894][98559] Updated weights for policy 0, policy_version 74000 (0.0007) -[2023-10-10 23:45:58,262][98559] Updated weights for policy 0, policy_version 74010 (0.0009) -[2023-10-10 23:45:59,372][98560] Updated weights for policy 1, policy_version 73542 (0.0009) -[2023-10-10 23:45:59,741][98560] Updated weights for policy 1, policy_version 73552 (0.0008) -[2023-10-10 23:46:00,110][98560] Updated weights for policy 1, policy_version 73562 (0.0007) -[2023-10-10 23:46:00,556][97672] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 151126016. Throughput: 0: 1698.6, 1: 1710.2. Samples: 37785414. Policy #0 lag: (min: 30.0, avg: 30.5, max: 46.0) -[2023-10-10 23:46:00,557][97672] Avg episode reward: [(0, '-0.860'), (1, '22.380')] -[2023-10-10 23:46:02,226][98559] Updated weights for policy 0, policy_version 74020 (0.0009) -[2023-10-10 23:46:02,590][98559] Updated weights for policy 0, policy_version 74030 (0.0007) -[2023-10-10 23:46:02,945][98559] Updated weights for policy 0, policy_version 74040 (0.0007) -[2023-10-10 23:46:04,155][98560] Updated weights for policy 1, policy_version 73572 (0.0008) -[2023-10-10 23:46:04,533][98560] Updated weights for policy 1, policy_version 73582 (0.0011) -[2023-10-10 23:46:04,900][98560] Updated weights for policy 1, policy_version 73592 (0.0010) -[2023-10-10 23:46:05,556][97672] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 151191552. Throughput: 0: 1725.4, 1: 1691.2. Samples: 37805606. Policy #0 lag: (min: 30.0, avg: 30.5, max: 46.0) -[2023-10-10 23:46:05,557][97672] Avg episode reward: [(0, '-0.860'), (1, '22.360')] -[2023-10-10 23:46:06,954][98559] Updated weights for policy 0, policy_version 74050 (0.0008) -[2023-10-10 23:46:07,344][98559] Updated weights for policy 0, policy_version 74060 (0.0009) -[2023-10-10 23:46:07,706][98559] Updated weights for policy 0, policy_version 74070 (0.0010) -[2023-10-10 23:46:08,075][98559] Updated weights for policy 0, policy_version 74080 (0.0007) -[2023-10-10 23:46:09,054][98560] Updated weights for policy 1, policy_version 73602 (0.0008) -[2023-10-10 23:46:09,422][98560] Updated weights for policy 1, policy_version 73612 (0.0007) -[2023-10-10 23:46:09,790][98560] Updated weights for policy 1, policy_version 73622 (0.0009) -[2023-10-10 23:46:10,155][98560] Updated weights for policy 1, policy_version 73632 (0.0007) -[2023-10-10 23:46:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 151257088. Throughput: 0: 1691.7, 1: 1706.7. Samples: 37815468. Policy #0 lag: (min: 30.0, avg: 30.5, max: 46.0) -[2023-10-10 23:46:10,557][97672] Avg episode reward: [(0, '-0.860'), (1, '22.240')] -[2023-10-10 23:46:12,104][98559] Updated weights for policy 0, policy_version 74090 (0.0008) -[2023-10-10 23:46:12,473][98559] Updated weights for policy 0, policy_version 74100 (0.0007) -[2023-10-10 23:46:12,835][98559] Updated weights for policy 0, policy_version 74110 (0.0008) -[2023-10-10 23:46:14,276][98560] Updated weights for policy 1, policy_version 73642 (0.0008) -[2023-10-10 23:46:14,643][98560] Updated weights for policy 1, policy_version 73652 (0.0007) -[2023-10-10 23:46:15,001][98560] Updated weights for policy 1, policy_version 73662 (0.0007) -[2023-10-10 23:46:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 151322624. Throughput: 0: 1708.4, 1: 1711.6. Samples: 37836652. Policy #0 lag: (min: 30.0, avg: 30.5, max: 46.0) -[2023-10-10 23:46:15,556][97672] Avg episode reward: [(0, '-0.880'), (1, '22.260')] -[2023-10-10 23:46:16,743][98559] Updated weights for policy 0, policy_version 74120 (0.0008) -[2023-10-10 23:46:17,111][98559] Updated weights for policy 0, policy_version 74130 (0.0008) -[2023-10-10 23:46:17,480][98559] Updated weights for policy 0, policy_version 74140 (0.0007) -[2023-10-10 23:46:18,791][98560] Updated weights for policy 1, policy_version 73672 (0.0007) -[2023-10-10 23:46:19,167][98560] Updated weights for policy 1, policy_version 73682 (0.0009) -[2023-10-10 23:46:19,532][98560] Updated weights for policy 1, policy_version 73692 (0.0007) -[2023-10-10 23:46:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 151388160. Throughput: 0: 1722.8, 1: 1682.0. Samples: 37856866. Policy #0 lag: (min: 8.0, avg: 29.1, max: 40.0) -[2023-10-10 23:46:20,556][97672] Avg episode reward: [(0, '-0.880'), (1, '22.200')] -[2023-10-10 23:46:21,527][98559] Updated weights for policy 0, policy_version 74150 (0.0008) -[2023-10-10 23:46:21,895][98559] Updated weights for policy 0, policy_version 74160 (0.0009) -[2023-10-10 23:46:22,257][98559] Updated weights for policy 0, policy_version 74170 (0.0009) -[2023-10-10 23:46:23,498][98560] Updated weights for policy 1, policy_version 73702 (0.0008) -[2023-10-10 23:46:23,861][98560] Updated weights for policy 1, policy_version 73712 (0.0009) -[2023-10-10 23:46:24,226][98560] Updated weights for policy 1, policy_version 73722 (0.0009) -[2023-10-10 23:46:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 151453696. Throughput: 0: 1699.5, 1: 1708.2. Samples: 37867422. Policy #0 lag: (min: 8.0, avg: 29.1, max: 40.0) -[2023-10-10 23:46:25,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.280')] -[2023-10-10 23:46:25,933][98559] Updated weights for policy 0, policy_version 74180 (0.0008) -[2023-10-10 23:46:26,300][98559] Updated weights for policy 0, policy_version 74190 (0.0008) -[2023-10-10 23:46:26,665][98559] Updated weights for policy 0, policy_version 74200 (0.0008) -[2023-10-10 23:46:28,191][98560] Updated weights for policy 1, policy_version 73732 (0.0011) -[2023-10-10 23:46:28,554][98560] Updated weights for policy 1, policy_version 73742 (0.0008) -[2023-10-10 23:46:28,920][98560] Updated weights for policy 1, policy_version 73752 (0.0007) -[2023-10-10 23:46:30,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 151519232. Throughput: 0: 1727.5, 1: 1692.8. Samples: 37888084. Policy #0 lag: (min: 8.0, avg: 29.1, max: 40.0) -[2023-10-10 23:46:30,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.340')] -[2023-10-10 23:46:30,676][98559] Updated weights for policy 0, policy_version 74210 (0.0008) -[2023-10-10 23:46:31,044][98559] Updated weights for policy 0, policy_version 74220 (0.0011) -[2023-10-10 23:46:31,410][98559] Updated weights for policy 0, policy_version 74230 (0.0010) -[2023-10-10 23:46:31,772][98559] Updated weights for policy 0, policy_version 74240 (0.0009) -[2023-10-10 23:46:32,985][98560] Updated weights for policy 1, policy_version 73762 (0.0009) -[2023-10-10 23:46:33,344][98560] Updated weights for policy 1, policy_version 73772 (0.0007) -[2023-10-10 23:46:33,719][98560] Updated weights for policy 1, policy_version 73782 (0.0007) -[2023-10-10 23:46:34,081][98560] Updated weights for policy 1, policy_version 73792 (0.0007) -[2023-10-10 23:46:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 151584768. Throughput: 0: 1725.2, 1: 1678.9. Samples: 37908410. Policy #0 lag: (min: 8.0, avg: 29.1, max: 40.0) -[2023-10-10 23:46:35,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.360')] -[2023-10-10 23:46:35,567][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000073792_75563008.pth... -[2023-10-10 23:46:35,606][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000072192_73924608.pth -[2023-10-10 23:46:35,735][98559] Updated weights for policy 0, policy_version 74250 (0.0009) -[2023-10-10 23:46:36,104][98559] Updated weights for policy 0, policy_version 74260 (0.0008) -[2023-10-10 23:46:36,484][98559] Updated weights for policy 0, policy_version 74270 (0.0010) -[2023-10-10 23:46:36,551][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000074272_76054528.pth... -[2023-10-10 23:46:36,589][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000072640_74383360.pth -[2023-10-10 23:46:38,082][98560] Updated weights for policy 1, policy_version 73802 (0.0009) -[2023-10-10 23:46:38,451][98560] Updated weights for policy 1, policy_version 73812 (0.0008) -[2023-10-10 23:46:38,827][98560] Updated weights for policy 1, policy_version 73822 (0.0007) -[2023-10-10 23:46:40,510][98559] Updated weights for policy 0, policy_version 74280 (0.0009) -[2023-10-10 23:46:40,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 151650304. Throughput: 0: 1721.0, 1: 1711.0. Samples: 37919096. Policy #0 lag: (min: 8.0, avg: 29.1, max: 40.0) -[2023-10-10 23:46:40,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.320')] -[2023-10-10 23:46:40,877][98559] Updated weights for policy 0, policy_version 74290 (0.0010) -[2023-10-10 23:46:41,244][98559] Updated weights for policy 0, policy_version 74300 (0.0009) -[2023-10-10 23:46:42,787][98560] Updated weights for policy 1, policy_version 73832 (0.0009) -[2023-10-10 23:46:43,151][98560] Updated weights for policy 1, policy_version 73842 (0.0010) -[2023-10-10 23:46:43,521][98560] Updated weights for policy 1, policy_version 73852 (0.0008) -[2023-10-10 23:46:45,284][98559] Updated weights for policy 0, policy_version 74310 (0.0010) -[2023-10-10 23:46:45,556][97672] Fps is (10 sec: 13107.7, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 151715840. Throughput: 0: 1729.8, 1: 1678.4. Samples: 37938782. Policy #0 lag: (min: 8.0, avg: 29.1, max: 40.0) -[2023-10-10 23:46:45,556][97672] Avg episode reward: [(0, '-0.820'), (1, '22.420')] -[2023-10-10 23:46:45,650][98559] Updated weights for policy 0, policy_version 74320 (0.0008) -[2023-10-10 23:46:46,017][98559] Updated weights for policy 0, policy_version 74330 (0.0007) -[2023-10-10 23:46:47,701][98560] Updated weights for policy 1, policy_version 73862 (0.0008) -[2023-10-10 23:46:48,063][98560] Updated weights for policy 1, policy_version 73872 (0.0010) -[2023-10-10 23:46:48,428][98560] Updated weights for policy 1, policy_version 73882 (0.0010) -[2023-10-10 23:46:49,992][98559] Updated weights for policy 0, policy_version 74340 (0.0008) -[2023-10-10 23:46:50,374][98559] Updated weights for policy 0, policy_version 74350 (0.0009) -[2023-10-10 23:46:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 151781376. Throughput: 0: 1717.0, 1: 1693.4. Samples: 37959074. Policy #0 lag: (min: 8.0, avg: 29.1, max: 40.0) -[2023-10-10 23:46:50,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.280')] -[2023-10-10 23:46:50,725][98559] Updated weights for policy 0, policy_version 74360 (0.0009) -[2023-10-10 23:46:52,377][98560] Updated weights for policy 1, policy_version 73892 (0.0007) -[2023-10-10 23:46:52,744][98560] Updated weights for policy 1, policy_version 73902 (0.0007) -[2023-10-10 23:46:53,117][98560] Updated weights for policy 1, policy_version 73912 (0.0009) -[2023-10-10 23:46:54,808][98559] Updated weights for policy 0, policy_version 74370 (0.0009) -[2023-10-10 23:46:55,216][98559] Updated weights for policy 0, policy_version 74380 (0.0007) -[2023-10-10 23:46:55,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 151846912. Throughput: 0: 1733.7, 1: 1697.2. Samples: 37969860. Policy #0 lag: (min: 8.0, avg: 29.1, max: 40.0) -[2023-10-10 23:46:55,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.380')] -[2023-10-10 23:46:55,576][98559] Updated weights for policy 0, policy_version 74390 (0.0009) -[2023-10-10 23:46:55,936][98559] Updated weights for policy 0, policy_version 74400 (0.0008) -[2023-10-10 23:46:57,231][98560] Updated weights for policy 1, policy_version 73922 (0.0007) -[2023-10-10 23:46:57,603][98560] Updated weights for policy 1, policy_version 73932 (0.0007) -[2023-10-10 23:46:57,970][98560] Updated weights for policy 1, policy_version 73942 (0.0008) -[2023-10-10 23:46:58,329][98560] Updated weights for policy 1, policy_version 73952 (0.0009) -[2023-10-10 23:46:59,721][98559] Updated weights for policy 0, policy_version 74410 (0.0009) -[2023-10-10 23:47:00,075][98559] Updated weights for policy 0, policy_version 74420 (0.0011) -[2023-10-10 23:47:00,441][98559] Updated weights for policy 0, policy_version 74430 (0.0010) -[2023-10-10 23:47:00,556][97672] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 151945216. Throughput: 0: 1732.2, 1: 1678.3. Samples: 37990124. Policy #0 lag: (min: 8.0, avg: 29.1, max: 40.0) -[2023-10-10 23:47:00,556][97672] Avg episode reward: [(0, '-0.840'), (1, '22.400')] -[2023-10-10 23:47:02,593][98560] Updated weights for policy 1, policy_version 73962 (0.0007) -[2023-10-10 23:47:02,969][98560] Updated weights for policy 1, policy_version 73972 (0.0007) -[2023-10-10 23:47:03,337][98560] Updated weights for policy 1, policy_version 73982 (0.0007) -[2023-10-10 23:47:04,452][98559] Updated weights for policy 0, policy_version 74440 (0.0012) -[2023-10-10 23:47:04,820][98559] Updated weights for policy 0, policy_version 74450 (0.0010) -[2023-10-10 23:47:05,188][98559] Updated weights for policy 0, policy_version 74460 (0.0008) -[2023-10-10 23:47:05,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 152010752. Throughput: 0: 1700.0, 1: 1695.3. Samples: 38009654. Policy #0 lag: (min: 20.0, avg: 31.7, max: 52.0) -[2023-10-10 23:47:05,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.440')] -[2023-10-10 23:47:07,286][98560] Updated weights for policy 1, policy_version 73992 (0.0010) -[2023-10-10 23:47:07,656][98560] Updated weights for policy 1, policy_version 74002 (0.0011) -[2023-10-10 23:47:08,015][98560] Updated weights for policy 1, policy_version 74012 (0.0009) -[2023-10-10 23:47:09,156][98559] Updated weights for policy 0, policy_version 74470 (0.0007) -[2023-10-10 23:47:09,521][98559] Updated weights for policy 0, policy_version 74480 (0.0007) -[2023-10-10 23:47:09,888][98559] Updated weights for policy 0, policy_version 74490 (0.0009) -[2023-10-10 23:47:10,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 152076288. Throughput: 0: 1730.4, 1: 1680.4. Samples: 38020906. Policy #0 lag: (min: 20.0, avg: 31.7, max: 52.0) -[2023-10-10 23:47:10,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.520')] -[2023-10-10 23:47:12,065][98560] Updated weights for policy 1, policy_version 74022 (0.0010) -[2023-10-10 23:47:12,428][98560] Updated weights for policy 1, policy_version 74032 (0.0010) -[2023-10-10 23:47:12,795][98560] Updated weights for policy 1, policy_version 74042 (0.0009) -[2023-10-10 23:47:13,868][98559] Updated weights for policy 0, policy_version 74500 (0.0008) -[2023-10-10 23:47:14,232][98559] Updated weights for policy 0, policy_version 74510 (0.0007) -[2023-10-10 23:47:14,605][98559] Updated weights for policy 0, policy_version 74520 (0.0009) -[2023-10-10 23:47:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 152141824. Throughput: 0: 1713.0, 1: 1680.4. Samples: 38040788. Policy #0 lag: (min: 20.0, avg: 31.7, max: 52.0) -[2023-10-10 23:47:15,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.480')] -[2023-10-10 23:47:16,877][98560] Updated weights for policy 1, policy_version 74052 (0.0009) -[2023-10-10 23:47:17,243][98560] Updated weights for policy 1, policy_version 74062 (0.0008) -[2023-10-10 23:47:17,617][98560] Updated weights for policy 1, policy_version 74072 (0.0008) -[2023-10-10 23:47:18,626][98559] Updated weights for policy 0, policy_version 74530 (0.0009) -[2023-10-10 23:47:18,995][98559] Updated weights for policy 0, policy_version 74540 (0.0008) -[2023-10-10 23:47:19,352][98559] Updated weights for policy 0, policy_version 74550 (0.0008) -[2023-10-10 23:47:19,719][98559] Updated weights for policy 0, policy_version 74560 (0.0009) -[2023-10-10 23:47:20,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13653.2, 300 sec: 13662.6). Total num frames: 152207360. Throughput: 0: 1699.7, 1: 1691.1. Samples: 38060994. Policy #0 lag: (min: 20.0, avg: 31.7, max: 52.0) -[2023-10-10 23:47:20,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.500')] -[2023-10-10 23:47:21,712][98560] Updated weights for policy 1, policy_version 74082 (0.0008) -[2023-10-10 23:47:22,088][98560] Updated weights for policy 1, policy_version 74092 (0.0009) -[2023-10-10 23:47:22,463][98560] Updated weights for policy 1, policy_version 74102 (0.0008) -[2023-10-10 23:47:22,829][98560] Updated weights for policy 1, policy_version 74112 (0.0009) -[2023-10-10 23:47:23,617][98559] Updated weights for policy 0, policy_version 74570 (0.0008) -[2023-10-10 23:47:23,998][98559] Updated weights for policy 0, policy_version 74580 (0.0008) -[2023-10-10 23:47:24,355][98559] Updated weights for policy 0, policy_version 74590 (0.0008) -[2023-10-10 23:47:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 152272896. Throughput: 0: 1728.2, 1: 1662.1. Samples: 38071660. Policy #0 lag: (min: 20.0, avg: 31.7, max: 52.0) -[2023-10-10 23:47:25,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.500')] -[2023-10-10 23:47:27,049][98560] Updated weights for policy 1, policy_version 74122 (0.0008) -[2023-10-10 23:47:27,422][98560] Updated weights for policy 1, policy_version 74132 (0.0009) -[2023-10-10 23:47:27,795][98560] Updated weights for policy 1, policy_version 74142 (0.0007) -[2023-10-10 23:47:28,341][98559] Updated weights for policy 0, policy_version 74600 (0.0008) -[2023-10-10 23:47:28,713][98559] Updated weights for policy 0, policy_version 74610 (0.0009) -[2023-10-10 23:47:29,077][98559] Updated weights for policy 0, policy_version 74620 (0.0009) -[2023-10-10 23:47:30,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 152338432. Throughput: 0: 1703.8, 1: 1688.9. Samples: 38091456. Policy #0 lag: (min: 20.0, avg: 31.7, max: 52.0) -[2023-10-10 23:47:30,556][97672] Avg episode reward: [(0, '-0.820'), (1, '22.480')] -[2023-10-10 23:47:31,669][98560] Updated weights for policy 1, policy_version 74152 (0.0010) -[2023-10-10 23:47:32,050][98560] Updated weights for policy 1, policy_version 74162 (0.0011) -[2023-10-10 23:47:32,410][98560] Updated weights for policy 1, policy_version 74172 (0.0007) -[2023-10-10 23:47:33,099][98559] Updated weights for policy 0, policy_version 74630 (0.0009) -[2023-10-10 23:47:33,473][98559] Updated weights for policy 0, policy_version 74640 (0.0009) -[2023-10-10 23:47:33,837][98559] Updated weights for policy 0, policy_version 74650 (0.0010) -[2023-10-10 23:47:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 152403968. Throughput: 0: 1718.1, 1: 1692.2. Samples: 38112538. Policy #0 lag: (min: 20.0, avg: 31.7, max: 52.0) -[2023-10-10 23:47:35,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.500')] -[2023-10-10 23:47:36,448][98560] Updated weights for policy 1, policy_version 74182 (0.0007) -[2023-10-10 23:47:36,824][98560] Updated weights for policy 1, policy_version 74192 (0.0008) -[2023-10-10 23:47:37,186][98560] Updated weights for policy 1, policy_version 74202 (0.0009) -[2023-10-10 23:47:37,699][98559] Updated weights for policy 0, policy_version 74660 (0.0008) -[2023-10-10 23:47:38,067][98559] Updated weights for policy 0, policy_version 74670 (0.0009) -[2023-10-10 23:47:38,433][98559] Updated weights for policy 0, policy_version 74680 (0.0008) -[2023-10-10 23:47:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 152469504. Throughput: 0: 1717.7, 1: 1668.8. Samples: 38122254. Policy #0 lag: (min: 20.0, avg: 31.7, max: 52.0) -[2023-10-10 23:47:40,556][97672] Avg episode reward: [(0, '-0.820'), (1, '22.460')] -[2023-10-10 23:47:41,293][98560] Updated weights for policy 1, policy_version 74212 (0.0009) -[2023-10-10 23:47:41,661][98560] Updated weights for policy 1, policy_version 74222 (0.0009) -[2023-10-10 23:47:42,030][98560] Updated weights for policy 1, policy_version 74232 (0.0008) -[2023-10-10 23:47:42,425][98559] Updated weights for policy 0, policy_version 74690 (0.0008) -[2023-10-10 23:47:42,809][98559] Updated weights for policy 0, policy_version 74700 (0.0009) -[2023-10-10 23:47:43,163][98559] Updated weights for policy 0, policy_version 74710 (0.0011) -[2023-10-10 23:47:43,529][98559] Updated weights for policy 0, policy_version 74720 (0.0009) -[2023-10-10 23:47:45,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 152535040. Throughput: 0: 1706.9, 1: 1689.6. Samples: 38142966. Policy #0 lag: (min: 20.0, avg: 31.7, max: 52.0) -[2023-10-10 23:47:45,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.380')] -[2023-10-10 23:47:45,939][98560] Updated weights for policy 1, policy_version 74242 (0.0009) -[2023-10-10 23:47:46,312][98560] Updated weights for policy 1, policy_version 74252 (0.0010) -[2023-10-10 23:47:46,680][98560] Updated weights for policy 1, policy_version 74262 (0.0010) -[2023-10-10 23:47:47,046][98560] Updated weights for policy 1, policy_version 74272 (0.0007) -[2023-10-10 23:47:47,430][98559] Updated weights for policy 0, policy_version 74730 (0.0008) -[2023-10-10 23:47:47,803][98559] Updated weights for policy 0, policy_version 74740 (0.0008) -[2023-10-10 23:47:48,162][98559] Updated weights for policy 0, policy_version 74750 (0.0007) -[2023-10-10 23:47:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 152600576. Throughput: 0: 1730.1, 1: 1701.3. Samples: 38164068. Policy #0 lag: (min: 20.0, avg: 31.7, max: 52.0) -[2023-10-10 23:47:50,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.460')] -[2023-10-10 23:47:50,974][98560] Updated weights for policy 1, policy_version 74282 (0.0008) -[2023-10-10 23:47:51,353][98560] Updated weights for policy 1, policy_version 74292 (0.0008) -[2023-10-10 23:47:51,720][98560] Updated weights for policy 1, policy_version 74302 (0.0008) -[2023-10-10 23:47:52,128][98559] Updated weights for policy 0, policy_version 74760 (0.0008) -[2023-10-10 23:47:52,505][98559] Updated weights for policy 0, policy_version 74770 (0.0007) -[2023-10-10 23:47:52,863][98559] Updated weights for policy 0, policy_version 74780 (0.0010) -[2023-10-10 23:47:55,444][98560] Updated weights for policy 1, policy_version 74312 (0.0009) -[2023-10-10 23:47:55,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 152666112. Throughput: 0: 1703.3, 1: 1685.2. Samples: 38173392. Policy #0 lag: (min: 21.0, avg: 28.5, max: 53.0) -[2023-10-10 23:47:55,556][97672] Avg episode reward: [(0, '-0.820'), (1, '22.400')] -[2023-10-10 23:47:55,818][98560] Updated weights for policy 1, policy_version 74322 (0.0008) -[2023-10-10 23:47:56,177][98560] Updated weights for policy 1, policy_version 74332 (0.0009) -[2023-10-10 23:47:56,840][98559] Updated weights for policy 0, policy_version 74790 (0.0008) -[2023-10-10 23:47:57,207][98559] Updated weights for policy 0, policy_version 74800 (0.0007) -[2023-10-10 23:47:57,570][98559] Updated weights for policy 0, policy_version 74810 (0.0008) -[2023-10-10 23:48:00,072][98560] Updated weights for policy 1, policy_version 74342 (0.0009) -[2023-10-10 23:48:00,435][98560] Updated weights for policy 1, policy_version 74352 (0.0008) -[2023-10-10 23:48:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 152731648. Throughput: 0: 1716.1, 1: 1703.2. Samples: 38194654. Policy #0 lag: (min: 21.0, avg: 28.5, max: 53.0) -[2023-10-10 23:48:00,556][97672] Avg episode reward: [(0, '-0.820'), (1, '22.340')] -[2023-10-10 23:48:00,809][98560] Updated weights for policy 1, policy_version 74362 (0.0008) -[2023-10-10 23:48:01,541][98559] Updated weights for policy 0, policy_version 74820 (0.0009) -[2023-10-10 23:48:01,904][98559] Updated weights for policy 0, policy_version 74830 (0.0009) -[2023-10-10 23:48:02,268][98559] Updated weights for policy 0, policy_version 74840 (0.0011) -[2023-10-10 23:48:04,730][98560] Updated weights for policy 1, policy_version 74372 (0.0009) -[2023-10-10 23:48:05,108][98560] Updated weights for policy 1, policy_version 74382 (0.0009) -[2023-10-10 23:48:05,468][98560] Updated weights for policy 1, policy_version 74392 (0.0007) -[2023-10-10 23:48:05,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 152797184. Throughput: 0: 1726.2, 1: 1707.0. Samples: 38215488. Policy #0 lag: (min: 21.0, avg: 28.5, max: 53.0) -[2023-10-10 23:48:05,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.380')] -[2023-10-10 23:48:06,420][98559] Updated weights for policy 0, policy_version 74850 (0.0010) -[2023-10-10 23:48:06,779][98559] Updated weights for policy 0, policy_version 74860 (0.0007) -[2023-10-10 23:48:07,144][98559] Updated weights for policy 0, policy_version 74870 (0.0010) -[2023-10-10 23:48:07,520][98559] Updated weights for policy 0, policy_version 74880 (0.0010) -[2023-10-10 23:48:09,622][98560] Updated weights for policy 1, policy_version 74402 (0.0008) -[2023-10-10 23:48:09,988][98560] Updated weights for policy 1, policy_version 74412 (0.0010) -[2023-10-10 23:48:10,367][98560] Updated weights for policy 1, policy_version 74422 (0.0008) -[2023-10-10 23:48:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 152862720. Throughput: 0: 1696.1, 1: 1706.7. Samples: 38224782. Policy #0 lag: (min: 21.0, avg: 28.5, max: 53.0) -[2023-10-10 23:48:10,556][97672] Avg episode reward: [(0, '-0.800'), (1, '22.360')] -[2023-10-10 23:48:10,738][98560] Updated weights for policy 1, policy_version 74432 (0.0008) -[2023-10-10 23:48:11,480][98559] Updated weights for policy 0, policy_version 74890 (0.0008) -[2023-10-10 23:48:11,841][98559] Updated weights for policy 0, policy_version 74900 (0.0008) -[2023-10-10 23:48:12,211][98559] Updated weights for policy 0, policy_version 74910 (0.0008) -[2023-10-10 23:48:14,857][98560] Updated weights for policy 1, policy_version 74442 (0.0008) -[2023-10-10 23:48:15,231][98560] Updated weights for policy 1, policy_version 74452 (0.0011) -[2023-10-10 23:48:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 152928256. Throughput: 0: 1726.4, 1: 1708.8. Samples: 38246040. Policy #0 lag: (min: 21.0, avg: 28.5, max: 53.0) -[2023-10-10 23:48:15,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.400')] -[2023-10-10 23:48:15,591][98560] Updated weights for policy 1, policy_version 74462 (0.0007) -[2023-10-10 23:48:16,031][98559] Updated weights for policy 0, policy_version 74920 (0.0009) -[2023-10-10 23:48:16,400][98559] Updated weights for policy 0, policy_version 74930 (0.0007) -[2023-10-10 23:48:16,772][98559] Updated weights for policy 0, policy_version 74940 (0.0007) -[2023-10-10 23:48:19,500][98560] Updated weights for policy 1, policy_version 74472 (0.0008) -[2023-10-10 23:48:19,858][98560] Updated weights for policy 1, policy_version 74482 (0.0008) -[2023-10-10 23:48:20,218][98560] Updated weights for policy 1, policy_version 74492 (0.0008) -[2023-10-10 23:48:20,556][97672] Fps is (10 sec: 16383.8, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 153026560. Throughput: 0: 1731.0, 1: 1702.6. Samples: 38267048. Policy #0 lag: (min: 21.0, avg: 28.5, max: 53.0) -[2023-10-10 23:48:20,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.380')] -[2023-10-10 23:48:20,606][98559] Updated weights for policy 0, policy_version 74950 (0.0007) -[2023-10-10 23:48:20,974][98559] Updated weights for policy 0, policy_version 74960 (0.0007) -[2023-10-10 23:48:21,336][98559] Updated weights for policy 0, policy_version 74970 (0.0009) -[2023-10-10 23:48:24,176][98560] Updated weights for policy 1, policy_version 74502 (0.0008) -[2023-10-10 23:48:24,542][98560] Updated weights for policy 1, policy_version 74512 (0.0010) -[2023-10-10 23:48:24,909][98560] Updated weights for policy 1, policy_version 74522 (0.0010) -[2023-10-10 23:48:25,248][98559] Updated weights for policy 0, policy_version 74980 (0.0009) -[2023-10-10 23:48:25,556][97672] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 153092096. Throughput: 0: 1717.6, 1: 1719.5. Samples: 38276920. Policy #0 lag: (min: 21.0, avg: 28.5, max: 53.0) -[2023-10-10 23:48:25,556][97672] Avg episode reward: [(0, '-0.800'), (1, '22.420')] -[2023-10-10 23:48:25,614][98559] Updated weights for policy 0, policy_version 74990 (0.0011) -[2023-10-10 23:48:25,971][98559] Updated weights for policy 0, policy_version 75000 (0.0007) -[2023-10-10 23:48:28,877][98560] Updated weights for policy 1, policy_version 74532 (0.0009) -[2023-10-10 23:48:29,239][98560] Updated weights for policy 1, policy_version 74542 (0.0007) -[2023-10-10 23:48:29,607][98560] Updated weights for policy 1, policy_version 74552 (0.0007) -[2023-10-10 23:48:29,941][98559] Updated weights for policy 0, policy_version 75010 (0.0007) -[2023-10-10 23:48:30,332][98559] Updated weights for policy 0, policy_version 75020 (0.0009) -[2023-10-10 23:48:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 153157632. Throughput: 0: 1733.0, 1: 1718.3. Samples: 38298274. Policy #0 lag: (min: 21.0, avg: 28.5, max: 53.0) -[2023-10-10 23:48:30,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.420')] -[2023-10-10 23:48:30,696][98559] Updated weights for policy 0, policy_version 75030 (0.0007) -[2023-10-10 23:48:31,070][98559] Updated weights for policy 0, policy_version 75040 (0.0011) -[2023-10-10 23:48:33,797][98560] Updated weights for policy 1, policy_version 74562 (0.0009) -[2023-10-10 23:48:34,158][98560] Updated weights for policy 1, policy_version 74572 (0.0009) -[2023-10-10 23:48:34,528][98560] Updated weights for policy 1, policy_version 74582 (0.0009) -[2023-10-10 23:48:34,894][98560] Updated weights for policy 1, policy_version 74592 (0.0008) -[2023-10-10 23:48:35,013][98559] Updated weights for policy 0, policy_version 75050 (0.0010) -[2023-10-10 23:48:35,387][98559] Updated weights for policy 0, policy_version 75060 (0.0011) -[2023-10-10 23:48:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 153223168. Throughput: 0: 1715.9, 1: 1690.0. Samples: 38317334. Policy #0 lag: (min: 21.0, avg: 28.5, max: 53.0) -[2023-10-10 23:48:35,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.420')] -[2023-10-10 23:48:35,565][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000074592_76382208.pth... -[2023-10-10 23:48:35,603][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000072992_74743808.pth -[2023-10-10 23:48:35,742][98559] Updated weights for policy 0, policy_version 75070 (0.0009) -[2023-10-10 23:48:35,816][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000075072_76873728.pth... -[2023-10-10 23:48:35,854][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000073440_75202560.pth -[2023-10-10 23:48:39,033][98560] Updated weights for policy 1, policy_version 74602 (0.0008) -[2023-10-10 23:48:39,406][98560] Updated weights for policy 1, policy_version 74612 (0.0009) -[2023-10-10 23:48:39,724][98559] Updated weights for policy 0, policy_version 75080 (0.0008) -[2023-10-10 23:48:39,769][98560] Updated weights for policy 1, policy_version 74622 (0.0009) -[2023-10-10 23:48:40,084][98559] Updated weights for policy 0, policy_version 75090 (0.0010) -[2023-10-10 23:48:40,456][98559] Updated weights for policy 0, policy_version 75100 (0.0007) -[2023-10-10 23:48:40,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 153288704. Throughput: 0: 1728.9, 1: 1717.7. Samples: 38328488. Policy #0 lag: (min: 21.0, avg: 28.5, max: 53.0) -[2023-10-10 23:48:40,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.340')] -[2023-10-10 23:48:40,604][98385] Saving new best policy, reward=-0.780! -[2023-10-10 23:48:43,783][98560] Updated weights for policy 1, policy_version 74632 (0.0008) -[2023-10-10 23:48:44,146][98560] Updated weights for policy 1, policy_version 74642 (0.0009) -[2023-10-10 23:48:44,432][98559] Updated weights for policy 0, policy_version 75110 (0.0007) -[2023-10-10 23:48:44,518][98560] Updated weights for policy 1, policy_version 74652 (0.0008) -[2023-10-10 23:48:44,803][98559] Updated weights for policy 0, policy_version 75120 (0.0010) -[2023-10-10 23:48:45,170][98559] Updated weights for policy 0, policy_version 75130 (0.0010) -[2023-10-10 23:48:45,556][97672] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 153387008. Throughput: 0: 1727.4, 1: 1705.8. Samples: 38349150. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:48:45,556][97672] Avg episode reward: [(0, '-0.780'), (1, '22.280')] -[2023-10-10 23:48:48,586][98560] Updated weights for policy 1, policy_version 74662 (0.0009) -[2023-10-10 23:48:48,963][98560] Updated weights for policy 1, policy_version 74672 (0.0009) -[2023-10-10 23:48:49,227][98559] Updated weights for policy 0, policy_version 75140 (0.0008) -[2023-10-10 23:48:49,337][98560] Updated weights for policy 1, policy_version 74682 (0.0010) -[2023-10-10 23:48:49,587][98559] Updated weights for policy 0, policy_version 75150 (0.0008) -[2023-10-10 23:48:49,949][98559] Updated weights for policy 0, policy_version 75160 (0.0009) -[2023-10-10 23:48:50,556][97672] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 153452544. Throughput: 0: 1708.2, 1: 1678.5. Samples: 38367892. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:48:50,558][97672] Avg episode reward: [(0, '-0.800'), (1, '22.320')] -[2023-10-10 23:48:53,311][98560] Updated weights for policy 1, policy_version 74692 (0.0009) -[2023-10-10 23:48:53,677][98560] Updated weights for policy 1, policy_version 74702 (0.0008) -[2023-10-10 23:48:53,934][98559] Updated weights for policy 0, policy_version 75170 (0.0010) -[2023-10-10 23:48:54,040][98560] Updated weights for policy 1, policy_version 74712 (0.0008) -[2023-10-10 23:48:54,301][98559] Updated weights for policy 0, policy_version 75180 (0.0007) -[2023-10-10 23:48:54,668][98559] Updated weights for policy 0, policy_version 75190 (0.0010) -[2023-10-10 23:48:55,033][98559] Updated weights for policy 0, policy_version 75200 (0.0009) -[2023-10-10 23:48:55,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 153518080. Throughput: 0: 1736.4, 1: 1709.4. Samples: 38379842. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:48:55,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.340')] -[2023-10-10 23:48:58,047][98560] Updated weights for policy 1, policy_version 74722 (0.0009) -[2023-10-10 23:48:58,413][98560] Updated weights for policy 1, policy_version 74732 (0.0009) -[2023-10-10 23:48:58,790][98560] Updated weights for policy 1, policy_version 74742 (0.0008) -[2023-10-10 23:48:58,854][98559] Updated weights for policy 0, policy_version 75210 (0.0009) -[2023-10-10 23:48:59,157][98560] Updated weights for policy 1, policy_version 74752 (0.0008) -[2023-10-10 23:48:59,229][98559] Updated weights for policy 0, policy_version 75220 (0.0008) -[2023-10-10 23:48:59,587][98559] Updated weights for policy 0, policy_version 75230 (0.0010) -[2023-10-10 23:49:00,556][97672] Fps is (10 sec: 13107.6, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 153583616. Throughput: 0: 1707.3, 1: 1692.4. Samples: 38399028. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:49:00,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.300')] -[2023-10-10 23:49:03,153][98560] Updated weights for policy 1, policy_version 74762 (0.0010) -[2023-10-10 23:49:03,523][98560] Updated weights for policy 1, policy_version 74772 (0.0009) -[2023-10-10 23:49:03,711][98559] Updated weights for policy 0, policy_version 75240 (0.0007) -[2023-10-10 23:49:03,894][98560] Updated weights for policy 1, policy_version 74782 (0.0008) -[2023-10-10 23:49:04,085][98559] Updated weights for policy 0, policy_version 75250 (0.0010) -[2023-10-10 23:49:04,449][98559] Updated weights for policy 0, policy_version 75260 (0.0011) -[2023-10-10 23:49:05,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 153649152. Throughput: 0: 1691.8, 1: 1686.6. Samples: 38419074. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:49:05,556][97672] Avg episode reward: [(0, '-0.800'), (1, '22.340')] -[2023-10-10 23:49:07,995][98560] Updated weights for policy 1, policy_version 74792 (0.0008) -[2023-10-10 23:49:08,359][98560] Updated weights for policy 1, policy_version 74802 (0.0008) -[2023-10-10 23:49:08,596][98559] Updated weights for policy 0, policy_version 75270 (0.0007) -[2023-10-10 23:49:08,726][98560] Updated weights for policy 1, policy_version 74812 (0.0009) -[2023-10-10 23:49:08,954][98559] Updated weights for policy 0, policy_version 75280 (0.0007) -[2023-10-10 23:49:09,323][98559] Updated weights for policy 0, policy_version 75290 (0.0011) -[2023-10-10 23:49:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 153714688. Throughput: 0: 1719.6, 1: 1699.6. Samples: 38430782. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:49:10,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.340')] -[2023-10-10 23:49:12,666][98560] Updated weights for policy 1, policy_version 74822 (0.0007) -[2023-10-10 23:49:13,035][98560] Updated weights for policy 1, policy_version 74832 (0.0010) -[2023-10-10 23:49:13,192][98559] Updated weights for policy 0, policy_version 75300 (0.0009) -[2023-10-10 23:49:13,399][98560] Updated weights for policy 1, policy_version 74842 (0.0010) -[2023-10-10 23:49:13,552][98559] Updated weights for policy 0, policy_version 75310 (0.0007) -[2023-10-10 23:49:13,916][98559] Updated weights for policy 0, policy_version 75320 (0.0007) -[2023-10-10 23:49:15,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 153780224. Throughput: 0: 1686.9, 1: 1668.3. Samples: 38449260. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:49:15,556][97672] Avg episode reward: [(0, '-0.780'), (1, '22.360')] -[2023-10-10 23:49:17,465][98560] Updated weights for policy 1, policy_version 74852 (0.0009) -[2023-10-10 23:49:17,827][98560] Updated weights for policy 1, policy_version 74862 (0.0010) -[2023-10-10 23:49:17,993][98559] Updated weights for policy 0, policy_version 75330 (0.0008) -[2023-10-10 23:49:18,185][98560] Updated weights for policy 1, policy_version 74872 (0.0009) -[2023-10-10 23:49:18,386][98559] Updated weights for policy 0, policy_version 75340 (0.0009) -[2023-10-10 23:49:18,746][98559] Updated weights for policy 0, policy_version 75350 (0.0011) -[2023-10-10 23:49:19,112][98559] Updated weights for policy 0, policy_version 75360 (0.0010) -[2023-10-10 23:49:20,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 153845760. Throughput: 0: 1703.7, 1: 1698.4. Samples: 38470430. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:49:20,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.380')] -[2023-10-10 23:49:22,116][98560] Updated weights for policy 1, policy_version 74882 (0.0008) -[2023-10-10 23:49:22,480][98560] Updated weights for policy 1, policy_version 74892 (0.0010) -[2023-10-10 23:49:22,853][98560] Updated weights for policy 1, policy_version 74902 (0.0009) -[2023-10-10 23:49:23,123][98559] Updated weights for policy 0, policy_version 75370 (0.0007) -[2023-10-10 23:49:23,215][98560] Updated weights for policy 1, policy_version 74912 (0.0007) -[2023-10-10 23:49:23,485][98559] Updated weights for policy 0, policy_version 75380 (0.0007) -[2023-10-10 23:49:23,849][98559] Updated weights for policy 0, policy_version 75390 (0.0007) -[2023-10-10 23:49:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 153911296. Throughput: 0: 1702.7, 1: 1683.9. Samples: 38480882. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:49:25,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.380')] -[2023-10-10 23:49:27,352][98560] Updated weights for policy 1, policy_version 74922 (0.0011) -[2023-10-10 23:49:27,713][98560] Updated weights for policy 1, policy_version 74932 (0.0009) -[2023-10-10 23:49:27,930][98559] Updated weights for policy 0, policy_version 75400 (0.0009) -[2023-10-10 23:49:28,085][98560] Updated weights for policy 1, policy_version 74942 (0.0010) -[2023-10-10 23:49:28,295][98559] Updated weights for policy 0, policy_version 75410 (0.0010) -[2023-10-10 23:49:28,654][98559] Updated weights for policy 0, policy_version 75420 (0.0008) -[2023-10-10 23:49:30,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 153976832. Throughput: 0: 1686.4, 1: 1676.5. Samples: 38500482. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-10 23:49:30,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.440')] -[2023-10-10 23:49:32,359][98560] Updated weights for policy 1, policy_version 74952 (0.0008) -[2023-10-10 23:49:32,715][98560] Updated weights for policy 1, policy_version 74962 (0.0009) -[2023-10-10 23:49:32,807][98559] Updated weights for policy 0, policy_version 75430 (0.0007) -[2023-10-10 23:49:33,083][98560] Updated weights for policy 1, policy_version 74972 (0.0008) -[2023-10-10 23:49:33,163][98559] Updated weights for policy 0, policy_version 75440 (0.0007) -[2023-10-10 23:49:33,524][98559] Updated weights for policy 0, policy_version 75450 (0.0009) -[2023-10-10 23:49:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 154042368. Throughput: 0: 1706.3, 1: 1695.7. Samples: 38520980. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-10 23:49:35,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.500')] -[2023-10-10 23:49:37,396][98560] Updated weights for policy 1, policy_version 74982 (0.0008) -[2023-10-10 23:49:37,642][98559] Updated weights for policy 0, policy_version 75460 (0.0009) -[2023-10-10 23:49:37,760][98560] Updated weights for policy 1, policy_version 74992 (0.0007) -[2023-10-10 23:49:38,009][98559] Updated weights for policy 0, policy_version 75470 (0.0008) -[2023-10-10 23:49:38,128][98560] Updated weights for policy 1, policy_version 75002 (0.0009) -[2023-10-10 23:49:38,378][98559] Updated weights for policy 0, policy_version 75480 (0.0008) -[2023-10-10 23:49:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 154107904. Throughput: 0: 1688.8, 1: 1673.6. Samples: 38531148. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-10 23:49:40,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.440')] -[2023-10-10 23:49:41,999][98560] Updated weights for policy 1, policy_version 75012 (0.0008) -[2023-10-10 23:49:42,299][98559] Updated weights for policy 0, policy_version 75490 (0.0007) -[2023-10-10 23:49:42,373][98560] Updated weights for policy 1, policy_version 75022 (0.0010) -[2023-10-10 23:49:42,665][98559] Updated weights for policy 0, policy_version 75500 (0.0008) -[2023-10-10 23:49:42,735][98560] Updated weights for policy 1, policy_version 75032 (0.0008) -[2023-10-10 23:49:43,031][98559] Updated weights for policy 0, policy_version 75510 (0.0007) -[2023-10-10 23:49:43,396][98559] Updated weights for policy 0, policy_version 75520 (0.0007) -[2023-10-10 23:49:45,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.1, 300 sec: 13662.6). Total num frames: 154173440. Throughput: 0: 1703.8, 1: 1679.8. Samples: 38551288. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-10 23:49:45,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.500')] -[2023-10-10 23:49:46,641][98560] Updated weights for policy 1, policy_version 75042 (0.0008) -[2023-10-10 23:49:47,006][98560] Updated weights for policy 1, policy_version 75052 (0.0008) -[2023-10-10 23:49:47,254][98559] Updated weights for policy 0, policy_version 75530 (0.0009) -[2023-10-10 23:49:47,373][98560] Updated weights for policy 1, policy_version 75062 (0.0008) -[2023-10-10 23:49:47,621][98559] Updated weights for policy 0, policy_version 75540 (0.0008) -[2023-10-10 23:49:47,735][98560] Updated weights for policy 1, policy_version 75072 (0.0007) -[2023-10-10 23:49:47,977][98559] Updated weights for policy 0, policy_version 75550 (0.0009) -[2023-10-10 23:49:50,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 154238976. Throughput: 0: 1714.7, 1: 1690.7. Samples: 38572314. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-10 23:49:50,558][97672] Avg episode reward: [(0, '-0.840'), (1, '22.520')] -[2023-10-10 23:49:51,896][98560] Updated weights for policy 1, policy_version 75082 (0.0009) -[2023-10-10 23:49:51,920][98559] Updated weights for policy 0, policy_version 75560 (0.0008) -[2023-10-10 23:49:52,254][98560] Updated weights for policy 1, policy_version 75092 (0.0008) -[2023-10-10 23:49:52,281][98559] Updated weights for policy 0, policy_version 75570 (0.0007) -[2023-10-10 23:49:52,617][98560] Updated weights for policy 1, policy_version 75102 (0.0009) -[2023-10-10 23:49:52,640][98559] Updated weights for policy 0, policy_version 75580 (0.0008) -[2023-10-10 23:49:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 154304512. Throughput: 0: 1686.2, 1: 1662.4. Samples: 38581470. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-10 23:49:55,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.480')] -[2023-10-10 23:49:56,654][98560] Updated weights for policy 1, policy_version 75112 (0.0007) -[2023-10-10 23:49:56,681][98559] Updated weights for policy 0, policy_version 75590 (0.0008) -[2023-10-10 23:49:57,025][98560] Updated weights for policy 1, policy_version 75122 (0.0010) -[2023-10-10 23:49:57,051][98559] Updated weights for policy 0, policy_version 75600 (0.0009) -[2023-10-10 23:49:57,391][98560] Updated weights for policy 1, policy_version 75132 (0.0007) -[2023-10-10 23:49:57,408][98559] Updated weights for policy 0, policy_version 75610 (0.0007) -[2023-10-10 23:50:00,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 154370048. Throughput: 0: 1718.5, 1: 1687.9. Samples: 38602546. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-10 23:50:00,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.440')] -[2023-10-10 23:50:01,312][98559] Updated weights for policy 0, policy_version 75620 (0.0007) -[2023-10-10 23:50:01,565][98560] Updated weights for policy 1, policy_version 75142 (0.0008) -[2023-10-10 23:50:01,678][98559] Updated weights for policy 0, policy_version 75630 (0.0008) -[2023-10-10 23:50:01,932][98560] Updated weights for policy 1, policy_version 75152 (0.0008) -[2023-10-10 23:50:02,042][98559] Updated weights for policy 0, policy_version 75640 (0.0007) -[2023-10-10 23:50:02,295][98560] Updated weights for policy 1, policy_version 75162 (0.0008) -[2023-10-10 23:50:05,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.1, 300 sec: 13662.6). Total num frames: 154435584. Throughput: 0: 1716.5, 1: 1681.3. Samples: 38623330. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-10 23:50:05,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.400')] -[2023-10-10 23:50:06,107][98559] Updated weights for policy 0, policy_version 75650 (0.0008) -[2023-10-10 23:50:06,297][98560] Updated weights for policy 1, policy_version 75172 (0.0009) -[2023-10-10 23:50:06,519][98559] Updated weights for policy 0, policy_version 75660 (0.0007) -[2023-10-10 23:50:06,669][98560] Updated weights for policy 1, policy_version 75182 (0.0008) -[2023-10-10 23:50:06,880][98559] Updated weights for policy 0, policy_version 75670 (0.0007) -[2023-10-10 23:50:07,037][98560] Updated weights for policy 1, policy_version 75192 (0.0008) -[2023-10-10 23:50:07,240][98559] Updated weights for policy 0, policy_version 75680 (0.0008) -[2023-10-10 23:50:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 154501120. Throughput: 0: 1698.8, 1: 1668.9. Samples: 38632430. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-10 23:50:10,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.440')] -[2023-10-10 23:50:11,186][98560] Updated weights for policy 1, policy_version 75202 (0.0010) -[2023-10-10 23:50:11,249][98559] Updated weights for policy 0, policy_version 75690 (0.0009) -[2023-10-10 23:50:11,556][98560] Updated weights for policy 1, policy_version 75212 (0.0010) -[2023-10-10 23:50:11,621][98559] Updated weights for policy 0, policy_version 75700 (0.0007) -[2023-10-10 23:50:11,922][98560] Updated weights for policy 1, policy_version 75222 (0.0008) -[2023-10-10 23:50:11,980][98559] Updated weights for policy 0, policy_version 75710 (0.0007) -[2023-10-10 23:50:12,293][98560] Updated weights for policy 1, policy_version 75232 (0.0007) -[2023-10-10 23:50:15,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 154566656. Throughput: 0: 1711.2, 1: 1685.5. Samples: 38653330. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-10 23:50:15,556][97672] Avg episode reward: [(0, '-0.780'), (1, '22.440')] -[2023-10-10 23:50:15,808][98559] Updated weights for policy 0, policy_version 75720 (0.0007) -[2023-10-10 23:50:16,177][98559] Updated weights for policy 0, policy_version 75730 (0.0007) -[2023-10-10 23:50:16,482][98560] Updated weights for policy 1, policy_version 75242 (0.0009) -[2023-10-10 23:50:16,538][98559] Updated weights for policy 0, policy_version 75740 (0.0009) -[2023-10-10 23:50:16,856][98560] Updated weights for policy 1, policy_version 75252 (0.0007) -[2023-10-10 23:50:17,227][98560] Updated weights for policy 1, policy_version 75262 (0.0008) -[2023-10-10 23:50:20,411][98559] Updated weights for policy 0, policy_version 75750 (0.0008) -[2023-10-10 23:50:20,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 154632192. Throughput: 0: 1718.3, 1: 1686.0. Samples: 38674174. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-10 23:50:20,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.360')] -[2023-10-10 23:50:20,777][98559] Updated weights for policy 0, policy_version 75760 (0.0008) -[2023-10-10 23:50:21,135][98559] Updated weights for policy 0, policy_version 75770 (0.0009) -[2023-10-10 23:50:21,181][98560] Updated weights for policy 1, policy_version 75272 (0.0007) -[2023-10-10 23:50:21,549][98560] Updated weights for policy 1, policy_version 75282 (0.0007) -[2023-10-10 23:50:21,915][98560] Updated weights for policy 1, policy_version 75292 (0.0007) -[2023-10-10 23:50:25,121][98559] Updated weights for policy 0, policy_version 75780 (0.0008) -[2023-10-10 23:50:25,486][98559] Updated weights for policy 0, policy_version 75790 (0.0011) -[2023-10-10 23:50:25,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 154697728. Throughput: 0: 1714.3, 1: 1672.1. Samples: 38683534. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-10 23:50:25,556][97672] Avg episode reward: [(0, '-0.800'), (1, '22.380')] -[2023-10-10 23:50:25,851][98559] Updated weights for policy 0, policy_version 75800 (0.0008) -[2023-10-10 23:50:26,011][98560] Updated weights for policy 1, policy_version 75302 (0.0007) -[2023-10-10 23:50:26,376][98560] Updated weights for policy 1, policy_version 75312 (0.0007) -[2023-10-10 23:50:26,749][98560] Updated weights for policy 1, policy_version 75322 (0.0007) -[2023-10-10 23:50:29,794][98559] Updated weights for policy 0, policy_version 75810 (0.0008) -[2023-10-10 23:50:30,176][98559] Updated weights for policy 0, policy_version 75820 (0.0008) -[2023-10-10 23:50:30,534][98559] Updated weights for policy 0, policy_version 75830 (0.0007) -[2023-10-10 23:50:30,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 154763264. Throughput: 0: 1727.5, 1: 1683.2. Samples: 38704766. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-10 23:50:30,556][97672] Avg episode reward: [(0, '-0.800'), (1, '22.460')] -[2023-10-10 23:50:30,622][98560] Updated weights for policy 1, policy_version 75332 (0.0008) -[2023-10-10 23:50:30,900][98559] Updated weights for policy 0, policy_version 75840 (0.0008) -[2023-10-10 23:50:30,990][98560] Updated weights for policy 1, policy_version 75342 (0.0009) -[2023-10-10 23:50:31,347][98560] Updated weights for policy 1, policy_version 75352 (0.0010) -[2023-10-10 23:50:34,908][98559] Updated weights for policy 0, policy_version 75850 (0.0008) -[2023-10-10 23:50:35,267][98559] Updated weights for policy 0, policy_version 75860 (0.0007) -[2023-10-10 23:50:35,409][98560] Updated weights for policy 1, policy_version 75362 (0.0011) -[2023-10-10 23:50:35,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 154828800. Throughput: 0: 1705.3, 1: 1687.1. Samples: 38724970. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-10 23:50:35,556][97672] Avg episode reward: [(0, '-0.800'), (1, '22.440')] -[2023-10-10 23:50:35,625][98559] Updated weights for policy 0, policy_version 75870 (0.0008) -[2023-10-10 23:50:35,699][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000075872_77692928.pth... -[2023-10-10 23:50:35,728][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000074272_76054528.pth -[2023-10-10 23:50:35,773][98560] Updated weights for policy 1, policy_version 75372 (0.0009) -[2023-10-10 23:50:36,140][98560] Updated weights for policy 1, policy_version 75382 (0.0010) -[2023-10-10 23:50:36,508][98560] Updated weights for policy 1, policy_version 75392 (0.0010) -[2023-10-10 23:50:36,508][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000075392_77201408.pth... -[2023-10-10 23:50:36,546][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000073792_75563008.pth -[2023-10-10 23:50:39,779][98559] Updated weights for policy 0, policy_version 75880 (0.0008) -[2023-10-10 23:50:40,149][98559] Updated weights for policy 0, policy_version 75890 (0.0007) -[2023-10-10 23:50:40,508][98559] Updated weights for policy 0, policy_version 75900 (0.0007) -[2023-10-10 23:50:40,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 154894336. Throughput: 0: 1726.4, 1: 1686.0. Samples: 38735028. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-10 23:50:40,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.480')] -[2023-10-10 23:50:40,726][98560] Updated weights for policy 1, policy_version 75402 (0.0010) -[2023-10-10 23:50:41,100][98560] Updated weights for policy 1, policy_version 75412 (0.0010) -[2023-10-10 23:50:41,464][98560] Updated weights for policy 1, policy_version 75422 (0.0007) -[2023-10-10 23:50:44,407][98559] Updated weights for policy 0, policy_version 75910 (0.0009) -[2023-10-10 23:50:44,774][98559] Updated weights for policy 0, policy_version 75920 (0.0008) -[2023-10-10 23:50:45,150][98559] Updated weights for policy 0, policy_version 75930 (0.0009) -[2023-10-10 23:50:45,556][97672] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 154992640. Throughput: 0: 1720.4, 1: 1684.2. Samples: 38755752. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-10 23:50:45,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.340')] -[2023-10-10 23:50:45,607][98560] Updated weights for policy 1, policy_version 75432 (0.0010) -[2023-10-10 23:50:45,974][98560] Updated weights for policy 1, policy_version 75442 (0.0009) -[2023-10-10 23:50:46,348][98560] Updated weights for policy 1, policy_version 75452 (0.0008) -[2023-10-10 23:50:49,021][98559] Updated weights for policy 0, policy_version 75940 (0.0007) -[2023-10-10 23:50:49,387][98559] Updated weights for policy 0, policy_version 75950 (0.0007) -[2023-10-10 23:50:49,745][98559] Updated weights for policy 0, policy_version 75960 (0.0007) -[2023-10-10 23:50:50,346][98560] Updated weights for policy 1, policy_version 75462 (0.0008) -[2023-10-10 23:50:50,556][97672] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 155058176. Throughput: 0: 1699.2, 1: 1685.8. Samples: 38775652. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-10 23:50:50,556][97672] Avg episode reward: [(0, '-0.800'), (1, '22.360')] -[2023-10-10 23:50:50,707][98560] Updated weights for policy 1, policy_version 75472 (0.0008) -[2023-10-10 23:50:51,069][98560] Updated weights for policy 1, policy_version 75482 (0.0007) -[2023-10-10 23:50:53,743][98559] Updated weights for policy 0, policy_version 75970 (0.0008) -[2023-10-10 23:50:54,136][98559] Updated weights for policy 0, policy_version 75980 (0.0010) -[2023-10-10 23:50:54,500][98559] Updated weights for policy 0, policy_version 75990 (0.0011) -[2023-10-10 23:50:54,866][98559] Updated weights for policy 0, policy_version 76000 (0.0010) -[2023-10-10 23:50:55,134][98560] Updated weights for policy 1, policy_version 75492 (0.0009) -[2023-10-10 23:50:55,506][98560] Updated weights for policy 1, policy_version 75502 (0.0008) -[2023-10-10 23:50:55,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 155123712. Throughput: 0: 1732.2, 1: 1687.2. Samples: 38786306. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-10 23:50:55,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.360')] -[2023-10-10 23:50:55,878][98560] Updated weights for policy 1, policy_version 75512 (0.0007) -[2023-10-10 23:50:58,849][98559] Updated weights for policy 0, policy_version 76010 (0.0008) -[2023-10-10 23:50:59,217][98559] Updated weights for policy 0, policy_version 76020 (0.0008) -[2023-10-10 23:50:59,577][98559] Updated weights for policy 0, policy_version 76030 (0.0007) -[2023-10-10 23:50:59,885][98560] Updated weights for policy 1, policy_version 75522 (0.0008) -[2023-10-10 23:51:00,253][98560] Updated weights for policy 1, policy_version 75532 (0.0007) -[2023-10-10 23:51:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 155189248. Throughput: 0: 1716.2, 1: 1686.0. Samples: 38806428. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-10 23:51:00,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.340')] -[2023-10-10 23:51:00,626][98560] Updated weights for policy 1, policy_version 75542 (0.0008) -[2023-10-10 23:51:00,995][98560] Updated weights for policy 1, policy_version 75552 (0.0011) -[2023-10-10 23:51:03,526][98559] Updated weights for policy 0, policy_version 76040 (0.0008) -[2023-10-10 23:51:03,889][98559] Updated weights for policy 0, policy_version 76050 (0.0007) -[2023-10-10 23:51:04,260][98559] Updated weights for policy 0, policy_version 76060 (0.0007) -[2023-10-10 23:51:05,058][98560] Updated weights for policy 1, policy_version 75562 (0.0009) -[2023-10-10 23:51:05,421][98560] Updated weights for policy 1, policy_version 75572 (0.0009) -[2023-10-10 23:51:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 155254784. Throughput: 0: 1703.0, 1: 1689.8. Samples: 38826848. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-10 23:51:05,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.400')] -[2023-10-10 23:51:05,788][98560] Updated weights for policy 1, policy_version 75582 (0.0007) -[2023-10-10 23:51:08,316][98559] Updated weights for policy 0, policy_version 76070 (0.0009) -[2023-10-10 23:51:08,690][98559] Updated weights for policy 0, policy_version 76080 (0.0007) -[2023-10-10 23:51:09,050][98559] Updated weights for policy 0, policy_version 76090 (0.0008) -[2023-10-10 23:51:09,718][98560] Updated weights for policy 1, policy_version 75592 (0.0010) -[2023-10-10 23:51:10,094][98560] Updated weights for policy 1, policy_version 75602 (0.0011) -[2023-10-10 23:51:10,459][98560] Updated weights for policy 1, policy_version 75612 (0.0009) -[2023-10-10 23:51:10,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 155320320. Throughput: 0: 1721.0, 1: 1693.0. Samples: 38837164. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-10 23:51:10,558][97672] Avg episode reward: [(0, '-0.780'), (1, '22.380')] -[2023-10-10 23:51:13,115][98559] Updated weights for policy 0, policy_version 76100 (0.0010) -[2023-10-10 23:51:13,478][98559] Updated weights for policy 0, policy_version 76110 (0.0010) -[2023-10-10 23:51:13,851][98559] Updated weights for policy 0, policy_version 76120 (0.0008) -[2023-10-10 23:51:14,550][98560] Updated weights for policy 1, policy_version 75622 (0.0009) -[2023-10-10 23:51:14,912][98560] Updated weights for policy 1, policy_version 75632 (0.0007) -[2023-10-10 23:51:15,277][98560] Updated weights for policy 1, policy_version 75642 (0.0009) -[2023-10-10 23:51:15,556][97672] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 155418624. Throughput: 0: 1690.6, 1: 1694.8. Samples: 38857106. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-10 23:51:15,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.360')] -[2023-10-10 23:51:17,927][98559] Updated weights for policy 0, policy_version 76130 (0.0010) -[2023-10-10 23:51:18,292][98559] Updated weights for policy 0, policy_version 76140 (0.0008) -[2023-10-10 23:51:18,651][98559] Updated weights for policy 0, policy_version 76150 (0.0008) -[2023-10-10 23:51:19,023][98559] Updated weights for policy 0, policy_version 76160 (0.0007) -[2023-10-10 23:51:19,353][98560] Updated weights for policy 1, policy_version 75652 (0.0007) -[2023-10-10 23:51:19,713][98560] Updated weights for policy 1, policy_version 75662 (0.0007) -[2023-10-10 23:51:20,086][98560] Updated weights for policy 1, policy_version 75672 (0.0008) -[2023-10-10 23:51:20,556][97672] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 155484160. Throughput: 0: 1715.2, 1: 1682.3. Samples: 38877860. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-10 23:51:20,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.340')] -[2023-10-10 23:51:22,917][98559] Updated weights for policy 0, policy_version 76170 (0.0010) -[2023-10-10 23:51:23,281][98559] Updated weights for policy 0, policy_version 76180 (0.0011) -[2023-10-10 23:51:23,644][98559] Updated weights for policy 0, policy_version 76190 (0.0008) -[2023-10-10 23:51:24,088][98560] Updated weights for policy 1, policy_version 75682 (0.0009) -[2023-10-10 23:51:24,450][98560] Updated weights for policy 1, policy_version 75692 (0.0010) -[2023-10-10 23:51:24,812][98560] Updated weights for policy 1, policy_version 75702 (0.0009) -[2023-10-10 23:51:25,171][98560] Updated weights for policy 1, policy_version 75712 (0.0008) -[2023-10-10 23:51:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 155549696. Throughput: 0: 1704.2, 1: 1696.4. Samples: 38888052. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-10 23:51:25,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.340')] -[2023-10-10 23:51:27,539][98559] Updated weights for policy 0, policy_version 76200 (0.0008) -[2023-10-10 23:51:27,906][98559] Updated weights for policy 0, policy_version 76210 (0.0008) -[2023-10-10 23:51:28,272][98559] Updated weights for policy 0, policy_version 76220 (0.0007) -[2023-10-10 23:51:29,163][98560] Updated weights for policy 1, policy_version 75722 (0.0009) -[2023-10-10 23:51:29,531][98560] Updated weights for policy 1, policy_version 75732 (0.0007) -[2023-10-10 23:51:29,901][98560] Updated weights for policy 1, policy_version 75742 (0.0009) -[2023-10-10 23:51:30,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 155615232. Throughput: 0: 1696.7, 1: 1705.8. Samples: 38908864. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-10 23:51:30,557][97672] Avg episode reward: [(0, '-0.860'), (1, '22.360')] -[2023-10-10 23:51:32,109][98559] Updated weights for policy 0, policy_version 76230 (0.0008) -[2023-10-10 23:51:32,465][98559] Updated weights for policy 0, policy_version 76240 (0.0009) -[2023-10-10 23:51:32,826][98559] Updated weights for policy 0, policy_version 76250 (0.0010) -[2023-10-10 23:51:33,931][98560] Updated weights for policy 1, policy_version 75752 (0.0008) -[2023-10-10 23:51:34,292][98560] Updated weights for policy 1, policy_version 75762 (0.0008) -[2023-10-10 23:51:34,656][98560] Updated weights for policy 1, policy_version 75772 (0.0010) -[2023-10-10 23:51:35,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 155680768. Throughput: 0: 1724.1, 1: 1683.4. Samples: 38928988. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-10 23:51:35,556][97672] Avg episode reward: [(0, '-0.860'), (1, '22.440')] -[2023-10-10 23:51:36,762][98559] Updated weights for policy 0, policy_version 76260 (0.0009) -[2023-10-10 23:51:37,127][98559] Updated weights for policy 0, policy_version 76270 (0.0008) -[2023-10-10 23:51:37,491][98559] Updated weights for policy 0, policy_version 76280 (0.0008) -[2023-10-10 23:51:38,654][98560] Updated weights for policy 1, policy_version 75782 (0.0007) -[2023-10-10 23:51:39,031][98560] Updated weights for policy 1, policy_version 75792 (0.0007) -[2023-10-10 23:51:39,400][98560] Updated weights for policy 1, policy_version 75802 (0.0007) -[2023-10-10 23:51:40,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 155746304. Throughput: 0: 1693.9, 1: 1709.3. Samples: 38939452. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-10 23:51:40,558][97672] Avg episode reward: [(0, '-0.860'), (1, '22.480')] -[2023-10-10 23:51:41,600][98559] Updated weights for policy 0, policy_version 76290 (0.0008) -[2023-10-10 23:51:41,962][98559] Updated weights for policy 0, policy_version 76300 (0.0008) -[2023-10-10 23:51:42,316][98559] Updated weights for policy 0, policy_version 76310 (0.0010) -[2023-10-10 23:51:42,690][98559] Updated weights for policy 0, policy_version 76320 (0.0009) -[2023-10-10 23:51:43,366][98560] Updated weights for policy 1, policy_version 75812 (0.0008) -[2023-10-10 23:51:43,737][98560] Updated weights for policy 1, policy_version 75822 (0.0009) -[2023-10-10 23:51:44,101][98560] Updated weights for policy 1, policy_version 75832 (0.0010) -[2023-10-10 23:51:45,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 155811840. Throughput: 0: 1715.1, 1: 1699.9. Samples: 38960102. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-10 23:51:45,557][97672] Avg episode reward: [(0, '-0.860'), (1, '22.460')] -[2023-10-10 23:51:46,704][98559] Updated weights for policy 0, policy_version 76330 (0.0008) -[2023-10-10 23:51:47,072][98559] Updated weights for policy 0, policy_version 76340 (0.0009) -[2023-10-10 23:51:47,441][98559] Updated weights for policy 0, policy_version 76350 (0.0009) -[2023-10-10 23:51:48,111][98560] Updated weights for policy 1, policy_version 75842 (0.0010) -[2023-10-10 23:51:48,484][98560] Updated weights for policy 1, policy_version 75852 (0.0008) -[2023-10-10 23:51:48,852][98560] Updated weights for policy 1, policy_version 75862 (0.0008) -[2023-10-10 23:51:49,218][98560] Updated weights for policy 1, policy_version 75872 (0.0010) -[2023-10-10 23:51:50,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 155877376. Throughput: 0: 1727.8, 1: 1684.9. Samples: 38980420. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-10 23:51:50,557][97672] Avg episode reward: [(0, '-0.860'), (1, '22.420')] -[2023-10-10 23:51:51,363][98559] Updated weights for policy 0, policy_version 76360 (0.0011) -[2023-10-10 23:51:51,733][98559] Updated weights for policy 0, policy_version 76370 (0.0009) -[2023-10-10 23:51:52,106][98559] Updated weights for policy 0, policy_version 76380 (0.0009) -[2023-10-10 23:51:53,439][98560] Updated weights for policy 1, policy_version 75882 (0.0009) -[2023-10-10 23:51:53,809][98560] Updated weights for policy 1, policy_version 75892 (0.0008) -[2023-10-10 23:51:54,182][98560] Updated weights for policy 1, policy_version 75902 (0.0007) -[2023-10-10 23:51:55,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 155942912. Throughput: 0: 1704.0, 1: 1713.4. Samples: 38990946. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:51:55,557][97672] Avg episode reward: [(0, '-0.860'), (1, '22.500')] -[2023-10-10 23:51:56,123][98559] Updated weights for policy 0, policy_version 76390 (0.0009) -[2023-10-10 23:51:56,487][98559] Updated weights for policy 0, policy_version 76400 (0.0009) -[2023-10-10 23:51:56,859][98559] Updated weights for policy 0, policy_version 76410 (0.0007) -[2023-10-10 23:51:58,091][98560] Updated weights for policy 1, policy_version 75912 (0.0008) -[2023-10-10 23:51:58,474][98560] Updated weights for policy 1, policy_version 75922 (0.0007) -[2023-10-10 23:51:58,844][98560] Updated weights for policy 1, policy_version 75932 (0.0008) -[2023-10-10 23:52:00,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 156008448. Throughput: 0: 1732.1, 1: 1689.4. Samples: 39011074. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:52:00,558][97672] Avg episode reward: [(0, '-0.860'), (1, '22.460')] -[2023-10-10 23:52:00,867][98559] Updated weights for policy 0, policy_version 76420 (0.0010) -[2023-10-10 23:52:01,229][98559] Updated weights for policy 0, policy_version 76430 (0.0010) -[2023-10-10 23:52:01,596][98559] Updated weights for policy 0, policy_version 76440 (0.0010) -[2023-10-10 23:52:02,928][98560] Updated weights for policy 1, policy_version 75942 (0.0008) -[2023-10-10 23:52:03,294][98560] Updated weights for policy 1, policy_version 75952 (0.0008) -[2023-10-10 23:52:03,673][98560] Updated weights for policy 1, policy_version 75962 (0.0007) -[2023-10-10 23:52:05,489][98559] Updated weights for policy 0, policy_version 76450 (0.0008) -[2023-10-10 23:52:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 156073984. Throughput: 0: 1724.8, 1: 1687.0. Samples: 39031390. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:52:05,557][97672] Avg episode reward: [(0, '-0.860'), (1, '22.480')] -[2023-10-10 23:52:05,857][98559] Updated weights for policy 0, policy_version 76460 (0.0009) -[2023-10-10 23:52:06,224][98559] Updated weights for policy 0, policy_version 76470 (0.0007) -[2023-10-10 23:52:06,593][98559] Updated weights for policy 0, policy_version 76480 (0.0009) -[2023-10-10 23:52:07,618][98560] Updated weights for policy 1, policy_version 75972 (0.0008) -[2023-10-10 23:52:07,983][98560] Updated weights for policy 1, policy_version 75982 (0.0010) -[2023-10-10 23:52:08,356][98560] Updated weights for policy 1, policy_version 75992 (0.0010) -[2023-10-10 23:52:10,455][98559] Updated weights for policy 0, policy_version 76490 (0.0012) -[2023-10-10 23:52:10,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 156139520. Throughput: 0: 1716.3, 1: 1698.2. Samples: 39041704. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:52:10,557][97672] Avg episode reward: [(0, '-0.860'), (1, '22.520')] -[2023-10-10 23:52:10,820][98559] Updated weights for policy 0, policy_version 76500 (0.0010) -[2023-10-10 23:52:11,185][98559] Updated weights for policy 0, policy_version 76510 (0.0010) -[2023-10-10 23:52:12,462][98560] Updated weights for policy 1, policy_version 76002 (0.0009) -[2023-10-10 23:52:12,817][98560] Updated weights for policy 1, policy_version 76012 (0.0008) -[2023-10-10 23:52:13,193][98560] Updated weights for policy 1, policy_version 76022 (0.0007) -[2023-10-10 23:52:13,560][98560] Updated weights for policy 1, policy_version 76032 (0.0007) -[2023-10-10 23:52:15,169][98559] Updated weights for policy 0, policy_version 76520 (0.0008) -[2023-10-10 23:52:15,534][98559] Updated weights for policy 0, policy_version 76530 (0.0009) -[2023-10-10 23:52:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 156205056. Throughput: 0: 1729.2, 1: 1671.1. Samples: 39061878. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:52:15,556][97672] Avg episode reward: [(0, '-0.860'), (1, '22.420')] -[2023-10-10 23:52:15,902][98559] Updated weights for policy 0, policy_version 76540 (0.0011) -[2023-10-10 23:52:17,383][98560] Updated weights for policy 1, policy_version 76042 (0.0009) -[2023-10-10 23:52:17,748][98560] Updated weights for policy 1, policy_version 76052 (0.0008) -[2023-10-10 23:52:18,113][98560] Updated weights for policy 1, policy_version 76062 (0.0009) -[2023-10-10 23:52:19,831][98559] Updated weights for policy 0, policy_version 76550 (0.0011) -[2023-10-10 23:52:20,189][98559] Updated weights for policy 0, policy_version 76560 (0.0010) -[2023-10-10 23:52:20,554][98559] Updated weights for policy 0, policy_version 76570 (0.0010) -[2023-10-10 23:52:20,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 156270592. Throughput: 0: 1710.5, 1: 1701.1. Samples: 39082508. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:52:20,556][97672] Avg episode reward: [(0, '-0.880'), (1, '22.500')] -[2023-10-10 23:52:22,079][98560] Updated weights for policy 1, policy_version 76072 (0.0007) -[2023-10-10 23:52:22,444][98560] Updated weights for policy 1, policy_version 76082 (0.0008) -[2023-10-10 23:52:22,813][98560] Updated weights for policy 1, policy_version 76092 (0.0007) -[2023-10-10 23:52:24,502][98559] Updated weights for policy 0, policy_version 76580 (0.0008) -[2023-10-10 23:52:24,870][98559] Updated weights for policy 0, policy_version 76590 (0.0007) -[2023-10-10 23:52:25,236][98559] Updated weights for policy 0, policy_version 76600 (0.0007) -[2023-10-10 23:52:25,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 156368896. Throughput: 0: 1731.3, 1: 1685.2. Samples: 39093190. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:52:25,556][97672] Avg episode reward: [(0, '-0.880'), (1, '22.500')] -[2023-10-10 23:52:26,729][98560] Updated weights for policy 1, policy_version 76102 (0.0008) -[2023-10-10 23:52:27,102][98560] Updated weights for policy 1, policy_version 76112 (0.0009) -[2023-10-10 23:52:27,459][98560] Updated weights for policy 1, policy_version 76122 (0.0010) -[2023-10-10 23:52:29,209][98559] Updated weights for policy 0, policy_version 76610 (0.0008) -[2023-10-10 23:52:29,577][98559] Updated weights for policy 0, policy_version 76620 (0.0010) -[2023-10-10 23:52:29,953][98559] Updated weights for policy 0, policy_version 76630 (0.0009) -[2023-10-10 23:52:30,316][98559] Updated weights for policy 0, policy_version 76640 (0.0007) -[2023-10-10 23:52:30,556][97672] Fps is (10 sec: 16383.8, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 156434432. Throughput: 0: 1728.4, 1: 1684.6. Samples: 39113686. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:52:30,557][97672] Avg episode reward: [(0, '-0.880'), (1, '22.500')] -[2023-10-10 23:52:31,497][98560] Updated weights for policy 1, policy_version 76132 (0.0009) -[2023-10-10 23:52:31,855][98560] Updated weights for policy 1, policy_version 76142 (0.0007) -[2023-10-10 23:52:32,226][98560] Updated weights for policy 1, policy_version 76152 (0.0008) -[2023-10-10 23:52:34,432][98559] Updated weights for policy 0, policy_version 76650 (0.0011) -[2023-10-10 23:52:34,798][98559] Updated weights for policy 0, policy_version 76660 (0.0008) -[2023-10-10 23:52:35,164][98559] Updated weights for policy 0, policy_version 76670 (0.0007) -[2023-10-10 23:52:35,556][97672] Fps is (10 sec: 13106.7, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 156499968. Throughput: 0: 1697.0, 1: 1705.9. Samples: 39133552. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:52:35,557][97672] Avg episode reward: [(0, '-0.880'), (1, '22.500')] -[2023-10-10 23:52:35,568][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000076672_78512128.pth... -[2023-10-10 23:52:35,568][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000076160_77987840.pth... -[2023-10-10 23:52:35,603][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000074592_76382208.pth -[2023-10-10 23:52:35,604][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000075072_76873728.pth -[2023-10-10 23:52:36,201][98560] Updated weights for policy 1, policy_version 76162 (0.0009) -[2023-10-10 23:52:36,557][98560] Updated weights for policy 1, policy_version 76172 (0.0011) -[2023-10-10 23:52:36,934][98560] Updated weights for policy 1, policy_version 76182 (0.0011) -[2023-10-10 23:52:37,294][98560] Updated weights for policy 1, policy_version 76192 (0.0008) -[2023-10-10 23:52:39,215][98559] Updated weights for policy 0, policy_version 76680 (0.0009) -[2023-10-10 23:52:39,577][98559] Updated weights for policy 0, policy_version 76690 (0.0009) -[2023-10-10 23:52:39,941][98559] Updated weights for policy 0, policy_version 76700 (0.0008) -[2023-10-10 23:52:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 156565504. Throughput: 0: 1726.7, 1: 1676.3. Samples: 39144078. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:52:40,557][97672] Avg episode reward: [(0, '-0.880'), (1, '22.480')] -[2023-10-10 23:52:41,432][98560] Updated weights for policy 1, policy_version 76202 (0.0008) -[2023-10-10 23:52:41,799][98560] Updated weights for policy 1, policy_version 76212 (0.0007) -[2023-10-10 23:52:42,170][98560] Updated weights for policy 1, policy_version 76222 (0.0008) -[2023-10-10 23:52:43,956][98559] Updated weights for policy 0, policy_version 76710 (0.0010) -[2023-10-10 23:52:44,325][98559] Updated weights for policy 0, policy_version 76720 (0.0011) -[2023-10-10 23:52:44,694][98559] Updated weights for policy 0, policy_version 76730 (0.0009) -[2023-10-10 23:52:45,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 156631040. Throughput: 0: 1704.0, 1: 1701.5. Samples: 39164322. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:52:45,557][97672] Avg episode reward: [(0, '-0.880'), (1, '22.540')] -[2023-10-10 23:52:46,087][98560] Updated weights for policy 1, policy_version 76232 (0.0009) -[2023-10-10 23:52:46,451][98560] Updated weights for policy 1, policy_version 76242 (0.0010) -[2023-10-10 23:52:46,815][98560] Updated weights for policy 1, policy_version 76252 (0.0011) -[2023-10-10 23:52:48,674][98559] Updated weights for policy 0, policy_version 76740 (0.0009) -[2023-10-10 23:52:49,042][98559] Updated weights for policy 0, policy_version 76750 (0.0008) -[2023-10-10 23:52:49,419][98559] Updated weights for policy 0, policy_version 76760 (0.0009) -[2023-10-10 23:52:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 156696576. Throughput: 0: 1692.0, 1: 1716.6. Samples: 39184778. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:52:50,556][97672] Avg episode reward: [(0, '-0.880'), (1, '22.520')] -[2023-10-10 23:52:50,868][98560] Updated weights for policy 1, policy_version 76262 (0.0009) -[2023-10-10 23:52:51,234][98560] Updated weights for policy 1, policy_version 76272 (0.0007) -[2023-10-10 23:52:51,611][98560] Updated weights for policy 1, policy_version 76282 (0.0009) -[2023-10-10 23:52:53,412][98559] Updated weights for policy 0, policy_version 76770 (0.0009) -[2023-10-10 23:52:53,778][98559] Updated weights for policy 0, policy_version 76780 (0.0010) -[2023-10-10 23:52:54,147][98559] Updated weights for policy 0, policy_version 76790 (0.0010) -[2023-10-10 23:52:54,508][98559] Updated weights for policy 0, policy_version 76800 (0.0009) -[2023-10-10 23:52:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 156762112. Throughput: 0: 1721.0, 1: 1694.6. Samples: 39195404. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:52:55,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.540')] -[2023-10-10 23:52:55,593][98560] Updated weights for policy 1, policy_version 76292 (0.0009) -[2023-10-10 23:52:55,971][98560] Updated weights for policy 1, policy_version 76302 (0.0007) -[2023-10-10 23:52:56,336][98560] Updated weights for policy 1, policy_version 76312 (0.0008) -[2023-10-10 23:52:58,692][98559] Updated weights for policy 0, policy_version 76810 (0.0011) -[2023-10-10 23:52:59,063][98559] Updated weights for policy 0, policy_version 76820 (0.0007) -[2023-10-10 23:52:59,429][98559] Updated weights for policy 0, policy_version 76830 (0.0007) -[2023-10-10 23:53:00,270][98560] Updated weights for policy 1, policy_version 76322 (0.0008) -[2023-10-10 23:53:00,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 156827648. Throughput: 0: 1690.9, 1: 1715.2. Samples: 39215152. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:53:00,556][97672] Avg episode reward: [(0, '-0.840'), (1, '22.620')] -[2023-10-10 23:53:00,632][98560] Updated weights for policy 1, policy_version 76332 (0.0007) -[2023-10-10 23:53:01,002][98560] Updated weights for policy 1, policy_version 76342 (0.0007) -[2023-10-10 23:53:01,366][98560] Updated weights for policy 1, policy_version 76352 (0.0008) -[2023-10-10 23:53:03,432][98559] Updated weights for policy 0, policy_version 76840 (0.0008) -[2023-10-10 23:53:03,798][98559] Updated weights for policy 0, policy_version 76850 (0.0007) -[2023-10-10 23:53:04,174][98559] Updated weights for policy 0, policy_version 76860 (0.0008) -[2023-10-10 23:53:05,340][98560] Updated weights for policy 1, policy_version 76362 (0.0008) -[2023-10-10 23:53:05,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 156893184. Throughput: 0: 1702.6, 1: 1708.1. Samples: 39235990. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:53:05,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.640')] -[2023-10-10 23:53:05,696][98560] Updated weights for policy 1, policy_version 76372 (0.0008) -[2023-10-10 23:53:06,074][98560] Updated weights for policy 1, policy_version 76382 (0.0010) -[2023-10-10 23:53:08,013][98559] Updated weights for policy 0, policy_version 76870 (0.0008) -[2023-10-10 23:53:08,375][98559] Updated weights for policy 0, policy_version 76880 (0.0007) -[2023-10-10 23:53:08,749][98559] Updated weights for policy 0, policy_version 76890 (0.0007) -[2023-10-10 23:53:10,070][98560] Updated weights for policy 1, policy_version 76392 (0.0007) -[2023-10-10 23:53:10,442][98560] Updated weights for policy 1, policy_version 76402 (0.0007) -[2023-10-10 23:53:10,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 156958720. Throughput: 0: 1701.7, 1: 1693.3. Samples: 39245968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:53:10,557][97672] Avg episode reward: [(0, '-0.880'), (1, '22.600')] -[2023-10-10 23:53:10,813][98560] Updated weights for policy 1, policy_version 76412 (0.0008) -[2023-10-10 23:53:12,648][98559] Updated weights for policy 0, policy_version 76900 (0.0008) -[2023-10-10 23:53:13,017][98559] Updated weights for policy 0, policy_version 76910 (0.0009) -[2023-10-10 23:53:13,377][98559] Updated weights for policy 0, policy_version 76920 (0.0008) -[2023-10-10 23:53:14,880][98560] Updated weights for policy 1, policy_version 76422 (0.0009) -[2023-10-10 23:53:15,251][98560] Updated weights for policy 1, policy_version 76432 (0.0008) -[2023-10-10 23:53:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 157024256. Throughput: 0: 1686.6, 1: 1707.4. Samples: 39266416. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:53:15,557][97672] Avg episode reward: [(0, '-0.880'), (1, '22.540')] -[2023-10-10 23:53:15,619][98560] Updated weights for policy 1, policy_version 76442 (0.0007) -[2023-10-10 23:53:17,339][98559] Updated weights for policy 0, policy_version 76930 (0.0008) -[2023-10-10 23:53:17,707][98559] Updated weights for policy 0, policy_version 76940 (0.0008) -[2023-10-10 23:53:18,077][98559] Updated weights for policy 0, policy_version 76950 (0.0008) -[2023-10-10 23:53:18,444][98559] Updated weights for policy 0, policy_version 76960 (0.0008) -[2023-10-10 23:53:19,649][98560] Updated weights for policy 1, policy_version 76452 (0.0007) -[2023-10-10 23:53:20,017][98560] Updated weights for policy 1, policy_version 76462 (0.0009) -[2023-10-10 23:53:20,384][98560] Updated weights for policy 1, policy_version 76472 (0.0011) -[2023-10-10 23:53:20,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 157089792. Throughput: 0: 1714.7, 1: 1703.2. Samples: 39287358. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:53:20,557][97672] Avg episode reward: [(0, '-0.880'), (1, '22.580')] -[2023-10-10 23:53:22,505][98559] Updated weights for policy 0, policy_version 76970 (0.0010) -[2023-10-10 23:53:22,873][98559] Updated weights for policy 0, policy_version 76980 (0.0009) -[2023-10-10 23:53:23,240][98559] Updated weights for policy 0, policy_version 76990 (0.0010) -[2023-10-10 23:53:24,271][98560] Updated weights for policy 1, policy_version 76482 (0.0011) -[2023-10-10 23:53:24,639][98560] Updated weights for policy 1, policy_version 76492 (0.0011) -[2023-10-10 23:53:25,015][98560] Updated weights for policy 1, policy_version 76502 (0.0009) -[2023-10-10 23:53:25,376][98560] Updated weights for policy 1, policy_version 76512 (0.0007) -[2023-10-10 23:53:25,556][97672] Fps is (10 sec: 16384.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 157188096. Throughput: 0: 1685.4, 1: 1708.0. Samples: 39296782. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:53:25,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.620')] -[2023-10-10 23:53:27,267][98559] Updated weights for policy 0, policy_version 77000 (0.0008) -[2023-10-10 23:53:27,627][98559] Updated weights for policy 0, policy_version 77010 (0.0009) -[2023-10-10 23:53:27,993][98559] Updated weights for policy 0, policy_version 77020 (0.0007) -[2023-10-10 23:53:29,331][98560] Updated weights for policy 1, policy_version 76522 (0.0007) -[2023-10-10 23:53:29,708][98560] Updated weights for policy 1, policy_version 76532 (0.0008) -[2023-10-10 23:53:30,084][98560] Updated weights for policy 1, policy_version 76542 (0.0008) -[2023-10-10 23:53:30,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 157253632. Throughput: 0: 1707.9, 1: 1717.1. Samples: 39318446. Policy #0 lag: (min: 31.0, avg: 31.4, max: 46.0) -[2023-10-10 23:53:30,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.660')] -[2023-10-10 23:53:31,767][98559] Updated weights for policy 0, policy_version 77030 (0.0008) -[2023-10-10 23:53:32,141][98559] Updated weights for policy 0, policy_version 77040 (0.0008) -[2023-10-10 23:53:32,507][98559] Updated weights for policy 0, policy_version 77050 (0.0009) -[2023-10-10 23:53:34,057][98560] Updated weights for policy 1, policy_version 76552 (0.0008) -[2023-10-10 23:53:34,423][98560] Updated weights for policy 1, policy_version 76562 (0.0008) -[2023-10-10 23:53:34,789][98560] Updated weights for policy 1, policy_version 76572 (0.0009) -[2023-10-10 23:53:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 157319168. Throughput: 0: 1730.1, 1: 1686.6. Samples: 39338530. Policy #0 lag: (min: 31.0, avg: 31.4, max: 46.0) -[2023-10-10 23:53:35,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.660')] -[2023-10-10 23:53:36,340][98559] Updated weights for policy 0, policy_version 77060 (0.0009) -[2023-10-10 23:53:36,696][98559] Updated weights for policy 0, policy_version 77070 (0.0008) -[2023-10-10 23:53:37,066][98559] Updated weights for policy 0, policy_version 77080 (0.0007) -[2023-10-10 23:53:38,794][98560] Updated weights for policy 1, policy_version 76582 (0.0009) -[2023-10-10 23:53:39,171][98560] Updated weights for policy 1, policy_version 76592 (0.0008) -[2023-10-10 23:53:39,546][98560] Updated weights for policy 1, policy_version 76602 (0.0009) -[2023-10-10 23:53:40,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 157384704. Throughput: 0: 1699.9, 1: 1712.8. Samples: 39348974. Policy #0 lag: (min: 31.0, avg: 31.4, max: 46.0) -[2023-10-10 23:53:40,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.620')] -[2023-10-10 23:53:41,021][98559] Updated weights for policy 0, policy_version 77090 (0.0009) -[2023-10-10 23:53:41,378][98559] Updated weights for policy 0, policy_version 77100 (0.0008) -[2023-10-10 23:53:41,734][98559] Updated weights for policy 0, policy_version 77110 (0.0008) -[2023-10-10 23:53:42,102][98559] Updated weights for policy 0, policy_version 77120 (0.0009) -[2023-10-10 23:53:43,802][98560] Updated weights for policy 1, policy_version 76612 (0.0010) -[2023-10-10 23:53:44,169][98560] Updated weights for policy 1, policy_version 76622 (0.0011) -[2023-10-10 23:53:44,534][98560] Updated weights for policy 1, policy_version 76632 (0.0009) -[2023-10-10 23:53:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 157450240. Throughput: 0: 1735.2, 1: 1710.4. Samples: 39370202. Policy #0 lag: (min: 31.0, avg: 31.4, max: 46.0) -[2023-10-10 23:53:45,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.600')] -[2023-10-10 23:53:46,165][98559] Updated weights for policy 0, policy_version 77130 (0.0011) -[2023-10-10 23:53:46,531][98559] Updated weights for policy 0, policy_version 77140 (0.0011) -[2023-10-10 23:53:46,891][98559] Updated weights for policy 0, policy_version 77150 (0.0010) -[2023-10-10 23:53:48,485][98560] Updated weights for policy 1, policy_version 76642 (0.0010) -[2023-10-10 23:53:48,854][98560] Updated weights for policy 1, policy_version 76652 (0.0007) -[2023-10-10 23:53:49,214][98560] Updated weights for policy 1, policy_version 76662 (0.0009) -[2023-10-10 23:53:49,589][98560] Updated weights for policy 1, policy_version 76672 (0.0008) -[2023-10-10 23:53:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 157515776. Throughput: 0: 1741.5, 1: 1681.8. Samples: 39390038. Policy #0 lag: (min: 31.0, avg: 31.4, max: 46.0) -[2023-10-10 23:53:50,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.620')] -[2023-10-10 23:53:50,755][98559] Updated weights for policy 0, policy_version 77160 (0.0007) -[2023-10-10 23:53:51,133][98559] Updated weights for policy 0, policy_version 77170 (0.0007) -[2023-10-10 23:53:51,499][98559] Updated weights for policy 0, policy_version 77180 (0.0007) -[2023-10-10 23:53:53,711][98560] Updated weights for policy 1, policy_version 76682 (0.0009) -[2023-10-10 23:53:54,078][98560] Updated weights for policy 1, policy_version 76692 (0.0009) -[2023-10-10 23:53:54,437][98560] Updated weights for policy 1, policy_version 76702 (0.0010) -[2023-10-10 23:53:55,451][98559] Updated weights for policy 0, policy_version 77190 (0.0008) -[2023-10-10 23:53:55,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 157581312. Throughput: 0: 1722.6, 1: 1716.2. Samples: 39400714. Policy #0 lag: (min: 31.0, avg: 31.4, max: 46.0) -[2023-10-10 23:53:55,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.640')] -[2023-10-10 23:53:55,813][98559] Updated weights for policy 0, policy_version 77200 (0.0008) -[2023-10-10 23:53:56,186][98559] Updated weights for policy 0, policy_version 77210 (0.0008) -[2023-10-10 23:53:58,454][98560] Updated weights for policy 1, policy_version 76712 (0.0009) -[2023-10-10 23:53:58,818][98560] Updated weights for policy 1, policy_version 76722 (0.0007) -[2023-10-10 23:53:59,186][98560] Updated weights for policy 1, policy_version 76732 (0.0007) -[2023-10-10 23:54:00,142][98559] Updated weights for policy 0, policy_version 77220 (0.0009) -[2023-10-10 23:54:00,499][98559] Updated weights for policy 0, policy_version 77230 (0.0010) -[2023-10-10 23:54:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 157646848. Throughput: 0: 1740.7, 1: 1700.3. Samples: 39421260. Policy #0 lag: (min: 31.0, avg: 31.4, max: 46.0) -[2023-10-10 23:54:00,556][97672] Avg episode reward: [(0, '-0.980'), (1, '22.640')] -[2023-10-10 23:54:00,861][98559] Updated weights for policy 0, policy_version 77240 (0.0010) -[2023-10-10 23:54:03,206][98560] Updated weights for policy 1, policy_version 76742 (0.0008) -[2023-10-10 23:54:03,581][98560] Updated weights for policy 1, policy_version 76752 (0.0007) -[2023-10-10 23:54:03,942][98560] Updated weights for policy 1, policy_version 76762 (0.0007) -[2023-10-10 23:54:04,884][98559] Updated weights for policy 0, policy_version 77250 (0.0008) -[2023-10-10 23:54:05,253][98559] Updated weights for policy 0, policy_version 77260 (0.0007) -[2023-10-10 23:54:05,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 157712384. Throughput: 0: 1730.8, 1: 1686.0. Samples: 39441112. Policy #0 lag: (min: 31.0, avg: 31.4, max: 46.0) -[2023-10-10 23:54:05,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.600')] -[2023-10-10 23:54:05,612][98559] Updated weights for policy 0, policy_version 77270 (0.0009) -[2023-10-10 23:54:05,981][98559] Updated weights for policy 0, policy_version 77280 (0.0008) -[2023-10-10 23:54:07,835][98560] Updated weights for policy 1, policy_version 76772 (0.0008) -[2023-10-10 23:54:08,203][98560] Updated weights for policy 1, policy_version 76782 (0.0008) -[2023-10-10 23:54:08,574][98560] Updated weights for policy 1, policy_version 76792 (0.0008) -[2023-10-10 23:54:09,973][98559] Updated weights for policy 0, policy_version 77290 (0.0008) -[2023-10-10 23:54:10,341][98559] Updated weights for policy 0, policy_version 77300 (0.0007) -[2023-10-10 23:54:10,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 157777920. Throughput: 0: 1741.2, 1: 1713.4. Samples: 39452242. Policy #0 lag: (min: 31.0, avg: 31.4, max: 46.0) -[2023-10-10 23:54:10,557][97672] Avg episode reward: [(0, '-0.980'), (1, '22.580')] -[2023-10-10 23:54:10,718][98559] Updated weights for policy 0, policy_version 77310 (0.0008) -[2023-10-10 23:54:12,525][98560] Updated weights for policy 1, policy_version 76802 (0.0007) -[2023-10-10 23:54:12,891][98560] Updated weights for policy 1, policy_version 76812 (0.0009) -[2023-10-10 23:54:13,257][98560] Updated weights for policy 1, policy_version 76822 (0.0008) -[2023-10-10 23:54:13,622][98560] Updated weights for policy 1, policy_version 76832 (0.0008) -[2023-10-10 23:54:14,824][98559] Updated weights for policy 0, policy_version 77320 (0.0009) -[2023-10-10 23:54:15,195][98559] Updated weights for policy 0, policy_version 77330 (0.0008) -[2023-10-10 23:54:15,549][98559] Updated weights for policy 0, policy_version 77340 (0.0009) -[2023-10-10 23:54:15,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 157843456. Throughput: 0: 1738.4, 1: 1676.9. Samples: 39472134. Policy #0 lag: (min: 31.0, avg: 31.4, max: 46.0) -[2023-10-10 23:54:15,556][97672] Avg episode reward: [(0, '-0.980'), (1, '22.540')] -[2023-10-10 23:54:17,742][98560] Updated weights for policy 1, policy_version 76842 (0.0007) -[2023-10-10 23:54:18,109][98560] Updated weights for policy 1, policy_version 76852 (0.0008) -[2023-10-10 23:54:18,469][98560] Updated weights for policy 1, policy_version 76862 (0.0009) -[2023-10-10 23:54:19,478][98559] Updated weights for policy 0, policy_version 77350 (0.0009) -[2023-10-10 23:54:19,849][98559] Updated weights for policy 0, policy_version 77360 (0.0008) -[2023-10-10 23:54:20,217][98559] Updated weights for policy 0, policy_version 77370 (0.0007) -[2023-10-10 23:54:20,556][97672] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 157941760. Throughput: 0: 1707.3, 1: 1702.9. Samples: 39491990. Policy #0 lag: (min: 2.0, avg: 17.0, max: 34.0) -[2023-10-10 23:54:20,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.540')] -[2023-10-10 23:54:22,347][98560] Updated weights for policy 1, policy_version 76872 (0.0008) -[2023-10-10 23:54:22,717][98560] Updated weights for policy 1, policy_version 76882 (0.0007) -[2023-10-10 23:54:23,087][98560] Updated weights for policy 1, policy_version 76892 (0.0007) -[2023-10-10 23:54:24,191][98559] Updated weights for policy 0, policy_version 77380 (0.0011) -[2023-10-10 23:54:24,559][98559] Updated weights for policy 0, policy_version 77390 (0.0010) -[2023-10-10 23:54:24,924][98559] Updated weights for policy 0, policy_version 77400 (0.0009) -[2023-10-10 23:54:25,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 158007296. Throughput: 0: 1733.9, 1: 1692.5. Samples: 39503162. Policy #0 lag: (min: 2.0, avg: 17.0, max: 34.0) -[2023-10-10 23:54:25,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.560')] -[2023-10-10 23:54:27,228][98560] Updated weights for policy 1, policy_version 76902 (0.0007) -[2023-10-10 23:54:27,592][98560] Updated weights for policy 1, policy_version 76912 (0.0009) -[2023-10-10 23:54:27,955][98560] Updated weights for policy 1, policy_version 76922 (0.0011) -[2023-10-10 23:54:28,717][98559] Updated weights for policy 0, policy_version 77410 (0.0007) -[2023-10-10 23:54:29,076][98559] Updated weights for policy 0, policy_version 77420 (0.0009) -[2023-10-10 23:54:29,446][98559] Updated weights for policy 0, policy_version 77430 (0.0011) -[2023-10-10 23:54:29,810][98559] Updated weights for policy 0, policy_version 77440 (0.0011) -[2023-10-10 23:54:30,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 158072832. Throughput: 0: 1714.0, 1: 1682.4. Samples: 39523040. Policy #0 lag: (min: 2.0, avg: 17.0, max: 34.0) -[2023-10-10 23:54:30,556][97672] Avg episode reward: [(0, '-0.960'), (1, '22.560')] -[2023-10-10 23:54:32,059][98560] Updated weights for policy 1, policy_version 76932 (0.0008) -[2023-10-10 23:54:32,417][98560] Updated weights for policy 1, policy_version 76942 (0.0008) -[2023-10-10 23:54:32,794][98560] Updated weights for policy 1, policy_version 76952 (0.0007) -[2023-10-10 23:54:33,726][98559] Updated weights for policy 0, policy_version 77450 (0.0010) -[2023-10-10 23:54:34,093][98559] Updated weights for policy 0, policy_version 77460 (0.0008) -[2023-10-10 23:54:34,454][98559] Updated weights for policy 0, policy_version 77470 (0.0009) -[2023-10-10 23:54:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 158138368. Throughput: 0: 1698.6, 1: 1715.8. Samples: 39543684. Policy #0 lag: (min: 2.0, avg: 17.0, max: 34.0) -[2023-10-10 23:54:35,557][97672] Avg episode reward: [(0, '-0.960'), (1, '22.580')] -[2023-10-10 23:54:35,566][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000077472_79331328.pth... -[2023-10-10 23:54:35,567][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000076960_78807040.pth... -[2023-10-10 23:54:35,604][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000075872_77692928.pth -[2023-10-10 23:54:35,608][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000075392_77201408.pth -[2023-10-10 23:54:36,711][98560] Updated weights for policy 1, policy_version 76962 (0.0008) -[2023-10-10 23:54:37,080][98560] Updated weights for policy 1, policy_version 76972 (0.0009) -[2023-10-10 23:54:37,451][98560] Updated weights for policy 1, policy_version 76982 (0.0009) -[2023-10-10 23:54:37,817][98560] Updated weights for policy 1, policy_version 76992 (0.0010) -[2023-10-10 23:54:38,420][98559] Updated weights for policy 0, policy_version 77480 (0.0007) -[2023-10-10 23:54:38,787][98559] Updated weights for policy 0, policy_version 77490 (0.0007) -[2023-10-10 23:54:39,149][98559] Updated weights for policy 0, policy_version 77500 (0.0007) -[2023-10-10 23:54:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 158203904. Throughput: 0: 1720.9, 1: 1687.2. Samples: 39554078. Policy #0 lag: (min: 2.0, avg: 17.0, max: 34.0) -[2023-10-10 23:54:40,556][97672] Avg episode reward: [(0, '-0.960'), (1, '22.600')] -[2023-10-10 23:54:41,874][98560] Updated weights for policy 1, policy_version 77002 (0.0010) -[2023-10-10 23:54:42,242][98560] Updated weights for policy 1, policy_version 77012 (0.0010) -[2023-10-10 23:54:42,608][98560] Updated weights for policy 1, policy_version 77022 (0.0008) -[2023-10-10 23:54:43,012][98559] Updated weights for policy 0, policy_version 77510 (0.0009) -[2023-10-10 23:54:43,375][98559] Updated weights for policy 0, policy_version 77520 (0.0009) -[2023-10-10 23:54:43,742][98559] Updated weights for policy 0, policy_version 77530 (0.0009) -[2023-10-10 23:54:45,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 158269440. Throughput: 0: 1701.1, 1: 1698.0. Samples: 39574222. Policy #0 lag: (min: 2.0, avg: 17.0, max: 34.0) -[2023-10-10 23:54:45,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.640')] -[2023-10-10 23:54:46,565][98560] Updated weights for policy 1, policy_version 77032 (0.0008) -[2023-10-10 23:54:46,934][98560] Updated weights for policy 1, policy_version 77042 (0.0007) -[2023-10-10 23:54:47,301][98560] Updated weights for policy 1, policy_version 77052 (0.0008) -[2023-10-10 23:54:47,777][98559] Updated weights for policy 0, policy_version 77540 (0.0007) -[2023-10-10 23:54:48,140][98559] Updated weights for policy 0, policy_version 77550 (0.0009) -[2023-10-10 23:54:48,505][98559] Updated weights for policy 0, policy_version 77560 (0.0007) -[2023-10-10 23:54:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 158334976. Throughput: 0: 1709.0, 1: 1716.9. Samples: 39595274. Policy #0 lag: (min: 2.0, avg: 17.0, max: 34.0) -[2023-10-10 23:54:50,556][97672] Avg episode reward: [(0, '-0.940'), (1, '22.660')] -[2023-10-10 23:54:51,158][98560] Updated weights for policy 1, policy_version 77062 (0.0009) -[2023-10-10 23:54:51,525][98560] Updated weights for policy 1, policy_version 77072 (0.0011) -[2023-10-10 23:54:51,895][98560] Updated weights for policy 1, policy_version 77082 (0.0011) -[2023-10-10 23:54:52,563][98559] Updated weights for policy 0, policy_version 77570 (0.0009) -[2023-10-10 23:54:52,928][98559] Updated weights for policy 0, policy_version 77580 (0.0011) -[2023-10-10 23:54:53,295][98559] Updated weights for policy 0, policy_version 77590 (0.0010) -[2023-10-10 23:54:53,657][98559] Updated weights for policy 0, policy_version 77600 (0.0009) -[2023-10-10 23:54:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 158400512. Throughput: 0: 1705.6, 1: 1683.8. Samples: 39604764. Policy #0 lag: (min: 2.0, avg: 17.0, max: 34.0) -[2023-10-10 23:54:55,557][97672] Avg episode reward: [(0, '-0.940'), (1, '22.720')] -[2023-10-10 23:54:55,951][98560] Updated weights for policy 1, policy_version 77092 (0.0011) -[2023-10-10 23:54:56,328][98560] Updated weights for policy 1, policy_version 77102 (0.0008) -[2023-10-10 23:54:56,684][98560] Updated weights for policy 1, policy_version 77112 (0.0010) -[2023-10-10 23:54:57,862][98559] Updated weights for policy 0, policy_version 77610 (0.0009) -[2023-10-10 23:54:58,233][98559] Updated weights for policy 0, policy_version 77620 (0.0010) -[2023-10-10 23:54:58,604][98559] Updated weights for policy 0, policy_version 77630 (0.0009) -[2023-10-10 23:55:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 158466048. Throughput: 0: 1697.0, 1: 1713.4. Samples: 39625604. Policy #0 lag: (min: 2.0, avg: 17.0, max: 34.0) -[2023-10-10 23:55:00,556][97672] Avg episode reward: [(0, '-0.920'), (1, '22.720')] -[2023-10-10 23:55:00,735][98560] Updated weights for policy 1, policy_version 77122 (0.0009) -[2023-10-10 23:55:01,103][98560] Updated weights for policy 1, policy_version 77132 (0.0007) -[2023-10-10 23:55:01,472][98560] Updated weights for policy 1, policy_version 77142 (0.0008) -[2023-10-10 23:55:01,842][98560] Updated weights for policy 1, policy_version 77152 (0.0007) -[2023-10-10 23:55:02,486][98559] Updated weights for policy 0, policy_version 77640 (0.0010) -[2023-10-10 23:55:02,853][98559] Updated weights for policy 0, policy_version 77650 (0.0008) -[2023-10-10 23:55:03,219][98559] Updated weights for policy 0, policy_version 77660 (0.0008) -[2023-10-10 23:55:05,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 158531584. Throughput: 0: 1716.7, 1: 1714.9. Samples: 39646412. Policy #0 lag: (min: 2.0, avg: 17.0, max: 34.0) -[2023-10-10 23:55:05,558][97672] Avg episode reward: [(0, '-0.920'), (1, '22.760')] -[2023-10-10 23:55:05,940][98560] Updated weights for policy 1, policy_version 77162 (0.0007) -[2023-10-10 23:55:06,310][98560] Updated weights for policy 1, policy_version 77172 (0.0007) -[2023-10-10 23:55:06,672][98560] Updated weights for policy 1, policy_version 77182 (0.0007) -[2023-10-10 23:55:07,331][98559] Updated weights for policy 0, policy_version 77670 (0.0009) -[2023-10-10 23:55:07,698][98559] Updated weights for policy 0, policy_version 77680 (0.0007) -[2023-10-10 23:55:08,055][98559] Updated weights for policy 0, policy_version 77690 (0.0007) -[2023-10-10 23:55:10,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 158597120. Throughput: 0: 1690.9, 1: 1698.1. Samples: 39655668. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-10 23:55:10,556][97672] Avg episode reward: [(0, '-0.920'), (1, '22.740')] -[2023-10-10 23:55:10,585][98560] Updated weights for policy 1, policy_version 77192 (0.0010) -[2023-10-10 23:55:10,958][98560] Updated weights for policy 1, policy_version 77202 (0.0009) -[2023-10-10 23:55:11,330][98560] Updated weights for policy 1, policy_version 77212 (0.0008) -[2023-10-10 23:55:11,988][98559] Updated weights for policy 0, policy_version 77700 (0.0009) -[2023-10-10 23:55:12,351][98559] Updated weights for policy 0, policy_version 77710 (0.0009) -[2023-10-10 23:55:12,721][98559] Updated weights for policy 0, policy_version 77720 (0.0007) -[2023-10-10 23:55:15,232][98560] Updated weights for policy 1, policy_version 77222 (0.0009) -[2023-10-10 23:55:15,556][97672] Fps is (10 sec: 13107.7, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 158662656. Throughput: 0: 1707.8, 1: 1720.9. Samples: 39677332. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-10 23:55:15,557][97672] Avg episode reward: [(0, '-0.920'), (1, '22.740')] -[2023-10-10 23:55:15,600][98560] Updated weights for policy 1, policy_version 77232 (0.0011) -[2023-10-10 23:55:15,975][98560] Updated weights for policy 1, policy_version 77242 (0.0008) -[2023-10-10 23:55:16,686][98559] Updated weights for policy 0, policy_version 77730 (0.0010) -[2023-10-10 23:55:17,045][98559] Updated weights for policy 0, policy_version 77740 (0.0008) -[2023-10-10 23:55:17,410][98559] Updated weights for policy 0, policy_version 77750 (0.0009) -[2023-10-10 23:55:17,762][98559] Updated weights for policy 0, policy_version 77760 (0.0008) -[2023-10-10 23:55:20,024][98560] Updated weights for policy 1, policy_version 77252 (0.0008) -[2023-10-10 23:55:20,393][98560] Updated weights for policy 1, policy_version 77262 (0.0009) -[2023-10-10 23:55:20,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 158728192. Throughput: 0: 1728.2, 1: 1711.3. Samples: 39698462. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-10 23:55:20,557][97672] Avg episode reward: [(0, '-0.920'), (1, '22.740')] -[2023-10-10 23:55:20,752][98560] Updated weights for policy 1, policy_version 77272 (0.0008) -[2023-10-10 23:55:21,623][98559] Updated weights for policy 0, policy_version 77770 (0.0008) -[2023-10-10 23:55:21,988][98559] Updated weights for policy 0, policy_version 77780 (0.0009) -[2023-10-10 23:55:22,349][98559] Updated weights for policy 0, policy_version 77790 (0.0008) -[2023-10-10 23:55:24,691][98560] Updated weights for policy 1, policy_version 77282 (0.0008) -[2023-10-10 23:55:25,064][98560] Updated weights for policy 1, policy_version 77292 (0.0008) -[2023-10-10 23:55:25,429][98560] Updated weights for policy 1, policy_version 77302 (0.0008) -[2023-10-10 23:55:25,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 158793728. Throughput: 0: 1706.4, 1: 1712.8. Samples: 39707940. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-10 23:55:25,556][97672] Avg episode reward: [(0, '-0.920'), (1, '22.700')] -[2023-10-10 23:55:25,793][98560] Updated weights for policy 1, policy_version 77312 (0.0009) -[2023-10-10 23:55:26,361][98559] Updated weights for policy 0, policy_version 77800 (0.0009) -[2023-10-10 23:55:26,730][98559] Updated weights for policy 0, policy_version 77810 (0.0008) -[2023-10-10 23:55:27,099][98559] Updated weights for policy 0, policy_version 77820 (0.0008) -[2023-10-10 23:55:29,635][98560] Updated weights for policy 1, policy_version 77322 (0.0008) -[2023-10-10 23:55:29,999][98560] Updated weights for policy 1, policy_version 77332 (0.0009) -[2023-10-10 23:55:30,375][98560] Updated weights for policy 1, policy_version 77342 (0.0008) -[2023-10-10 23:55:30,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 158892032. Throughput: 0: 1730.4, 1: 1721.9. Samples: 39729574. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-10 23:55:30,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.660')] -[2023-10-10 23:55:30,942][98559] Updated weights for policy 0, policy_version 77830 (0.0010) -[2023-10-10 23:55:31,312][98559] Updated weights for policy 0, policy_version 77840 (0.0007) -[2023-10-10 23:55:31,685][98559] Updated weights for policy 0, policy_version 77850 (0.0007) -[2023-10-10 23:55:34,374][98560] Updated weights for policy 1, policy_version 77352 (0.0008) -[2023-10-10 23:55:34,737][98560] Updated weights for policy 1, policy_version 77362 (0.0009) -[2023-10-10 23:55:35,099][98560] Updated weights for policy 1, policy_version 77372 (0.0009) -[2023-10-10 23:55:35,556][97672] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 158957568. Throughput: 0: 1737.4, 1: 1706.4. Samples: 39750244. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-10 23:55:35,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.700')] -[2023-10-10 23:55:35,562][98559] Updated weights for policy 0, policy_version 77860 (0.0009) -[2023-10-10 23:55:35,923][98559] Updated weights for policy 0, policy_version 77870 (0.0010) -[2023-10-10 23:55:36,287][98559] Updated weights for policy 0, policy_version 77880 (0.0011) -[2023-10-10 23:55:39,147][98560] Updated weights for policy 1, policy_version 77382 (0.0008) -[2023-10-10 23:55:39,505][98560] Updated weights for policy 1, policy_version 77392 (0.0007) -[2023-10-10 23:55:39,870][98560] Updated weights for policy 1, policy_version 77402 (0.0009) -[2023-10-10 23:55:40,287][98559] Updated weights for policy 0, policy_version 77890 (0.0008) -[2023-10-10 23:55:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 159023104. Throughput: 0: 1727.7, 1: 1727.2. Samples: 39760236. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-10 23:55:40,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.660')] -[2023-10-10 23:55:40,652][98559] Updated weights for policy 0, policy_version 77900 (0.0007) -[2023-10-10 23:55:41,015][98559] Updated weights for policy 0, policy_version 77910 (0.0007) -[2023-10-10 23:55:41,385][98559] Updated weights for policy 0, policy_version 77920 (0.0007) -[2023-10-10 23:55:43,770][98560] Updated weights for policy 1, policy_version 77412 (0.0008) -[2023-10-10 23:55:44,139][98560] Updated weights for policy 1, policy_version 77422 (0.0007) -[2023-10-10 23:55:44,509][98560] Updated weights for policy 1, policy_version 77432 (0.0009) -[2023-10-10 23:55:45,344][98559] Updated weights for policy 0, policy_version 77930 (0.0008) -[2023-10-10 23:55:45,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 159088640. Throughput: 0: 1736.3, 1: 1719.5. Samples: 39781116. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-10 23:55:45,557][97672] Avg episode reward: [(0, '-0.680'), (1, '22.700')] -[2023-10-10 23:55:45,709][98559] Updated weights for policy 0, policy_version 77940 (0.0009) -[2023-10-10 23:55:46,073][98559] Updated weights for policy 0, policy_version 77950 (0.0007) -[2023-10-10 23:55:46,135][98385] Saving new best policy, reward=-0.680! -[2023-10-10 23:55:48,403][98560] Updated weights for policy 1, policy_version 77442 (0.0008) -[2023-10-10 23:55:48,766][98560] Updated weights for policy 1, policy_version 77452 (0.0007) -[2023-10-10 23:55:49,143][98560] Updated weights for policy 1, policy_version 77462 (0.0007) -[2023-10-10 23:55:49,503][98560] Updated weights for policy 1, policy_version 77472 (0.0009) -[2023-10-10 23:55:50,081][98559] Updated weights for policy 0, policy_version 77960 (0.0009) -[2023-10-10 23:55:50,457][98559] Updated weights for policy 0, policy_version 77970 (0.0009) -[2023-10-10 23:55:50,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 159154176. Throughput: 0: 1726.8, 1: 1696.1. Samples: 39800438. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-10 23:55:50,556][97672] Avg episode reward: [(0, '-0.680'), (1, '22.660')] -[2023-10-10 23:55:50,817][98559] Updated weights for policy 0, policy_version 77980 (0.0009) -[2023-10-10 23:55:53,802][98560] Updated weights for policy 1, policy_version 77482 (0.0009) -[2023-10-10 23:55:54,172][98560] Updated weights for policy 1, policy_version 77492 (0.0011) -[2023-10-10 23:55:54,540][98560] Updated weights for policy 1, policy_version 77502 (0.0010) -[2023-10-10 23:55:54,831][98559] Updated weights for policy 0, policy_version 77990 (0.0009) -[2023-10-10 23:55:55,199][98559] Updated weights for policy 0, policy_version 78000 (0.0010) -[2023-10-10 23:55:55,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 159219712. Throughput: 0: 1739.1, 1: 1725.8. Samples: 39811590. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-10 23:55:55,557][97672] Avg episode reward: [(0, '-0.680'), (1, '22.640')] -[2023-10-10 23:55:55,558][98559] Updated weights for policy 0, policy_version 78010 (0.0011) -[2023-10-10 23:55:58,515][98560] Updated weights for policy 1, policy_version 77512 (0.0007) -[2023-10-10 23:55:58,885][98560] Updated weights for policy 1, policy_version 77522 (0.0008) -[2023-10-10 23:55:59,252][98560] Updated weights for policy 1, policy_version 77532 (0.0008) -[2023-10-10 23:55:59,590][98559] Updated weights for policy 0, policy_version 78020 (0.0008) -[2023-10-10 23:55:59,958][98559] Updated weights for policy 0, policy_version 78030 (0.0011) -[2023-10-10 23:56:00,317][98559] Updated weights for policy 0, policy_version 78040 (0.0011) -[2023-10-10 23:56:00,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 159285248. Throughput: 0: 1734.1, 1: 1706.1. Samples: 39832144. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-10 23:56:00,557][97672] Avg episode reward: [(0, '-0.680'), (1, '22.620')] -[2023-10-10 23:56:03,230][98560] Updated weights for policy 1, policy_version 77542 (0.0007) -[2023-10-10 23:56:03,595][98560] Updated weights for policy 1, policy_version 77552 (0.0007) -[2023-10-10 23:56:03,965][98560] Updated weights for policy 1, policy_version 77562 (0.0007) -[2023-10-10 23:56:04,381][98559] Updated weights for policy 0, policy_version 78050 (0.0011) -[2023-10-10 23:56:04,748][98559] Updated weights for policy 0, policy_version 78060 (0.0012) -[2023-10-10 23:56:05,117][98559] Updated weights for policy 0, policy_version 78070 (0.0007) -[2023-10-10 23:56:05,478][98559] Updated weights for policy 0, policy_version 78080 (0.0008) -[2023-10-10 23:56:05,556][97672] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 159383552. Throughput: 0: 1698.3, 1: 1694.5. Samples: 39851136. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-10 23:56:05,557][97672] Avg episode reward: [(0, '-0.680'), (1, '22.580')] -[2023-10-10 23:56:07,913][98560] Updated weights for policy 1, policy_version 77572 (0.0008) -[2023-10-10 23:56:08,284][98560] Updated weights for policy 1, policy_version 77582 (0.0008) -[2023-10-10 23:56:08,656][98560] Updated weights for policy 1, policy_version 77592 (0.0007) -[2023-10-10 23:56:09,463][98559] Updated weights for policy 0, policy_version 78090 (0.0009) -[2023-10-10 23:56:09,826][98559] Updated weights for policy 0, policy_version 78100 (0.0010) -[2023-10-10 23:56:10,200][98559] Updated weights for policy 0, policy_version 78110 (0.0009) -[2023-10-10 23:56:10,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 159449088. Throughput: 0: 1719.0, 1: 1720.8. Samples: 39862730. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-10 23:56:10,556][97672] Avg episode reward: [(0, '-0.680'), (1, '22.580')] -[2023-10-10 23:56:12,697][98560] Updated weights for policy 1, policy_version 77602 (0.0007) -[2023-10-10 23:56:13,069][98560] Updated weights for policy 1, policy_version 77612 (0.0008) -[2023-10-10 23:56:13,431][98560] Updated weights for policy 1, policy_version 77622 (0.0009) -[2023-10-10 23:56:13,794][98560] Updated weights for policy 1, policy_version 77632 (0.0008) -[2023-10-10 23:56:14,382][98559] Updated weights for policy 0, policy_version 78120 (0.0007) -[2023-10-10 23:56:14,743][98559] Updated weights for policy 0, policy_version 78130 (0.0008) -[2023-10-10 23:56:15,108][98559] Updated weights for policy 0, policy_version 78140 (0.0011) -[2023-10-10 23:56:15,556][97672] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 159514624. Throughput: 0: 1702.8, 1: 1687.4. Samples: 39882136. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-10 23:56:15,557][97672] Avg episode reward: [(0, '-0.680'), (1, '22.540')] -[2023-10-10 23:56:17,684][98560] Updated weights for policy 1, policy_version 77642 (0.0007) -[2023-10-10 23:56:18,052][98560] Updated weights for policy 1, policy_version 77652 (0.0007) -[2023-10-10 23:56:18,419][98560] Updated weights for policy 1, policy_version 77662 (0.0007) -[2023-10-10 23:56:18,913][98559] Updated weights for policy 0, policy_version 78150 (0.0009) -[2023-10-10 23:56:19,276][98559] Updated weights for policy 0, policy_version 78160 (0.0009) -[2023-10-10 23:56:19,642][98559] Updated weights for policy 0, policy_version 78170 (0.0011) -[2023-10-10 23:56:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 159580160. Throughput: 0: 1677.3, 1: 1693.3. Samples: 39901918. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-10 23:56:20,556][97672] Avg episode reward: [(0, '-0.680'), (1, '22.480')] -[2023-10-10 23:56:22,640][98560] Updated weights for policy 1, policy_version 77672 (0.0007) -[2023-10-10 23:56:23,004][98560] Updated weights for policy 1, policy_version 77682 (0.0009) -[2023-10-10 23:56:23,369][98560] Updated weights for policy 1, policy_version 77692 (0.0009) -[2023-10-10 23:56:23,770][98559] Updated weights for policy 0, policy_version 78180 (0.0010) -[2023-10-10 23:56:24,125][98559] Updated weights for policy 0, policy_version 78190 (0.0007) -[2023-10-10 23:56:24,492][98559] Updated weights for policy 0, policy_version 78200 (0.0009) -[2023-10-10 23:56:25,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 159645696. Throughput: 0: 1707.6, 1: 1696.1. Samples: 39913402. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-10 23:56:25,556][97672] Avg episode reward: [(0, '-0.680'), (1, '22.500')] -[2023-10-10 23:56:27,325][98560] Updated weights for policy 1, policy_version 77702 (0.0009) -[2023-10-10 23:56:27,692][98560] Updated weights for policy 1, policy_version 77712 (0.0010) -[2023-10-10 23:56:28,061][98560] Updated weights for policy 1, policy_version 77722 (0.0009) -[2023-10-10 23:56:28,471][98559] Updated weights for policy 0, policy_version 78210 (0.0008) -[2023-10-10 23:56:28,831][98559] Updated weights for policy 0, policy_version 78220 (0.0007) -[2023-10-10 23:56:29,197][98559] Updated weights for policy 0, policy_version 78230 (0.0007) -[2023-10-10 23:56:29,562][98559] Updated weights for policy 0, policy_version 78240 (0.0010) -[2023-10-10 23:56:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 159711232. Throughput: 0: 1687.4, 1: 1680.0. Samples: 39932646. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-10 23:56:30,557][97672] Avg episode reward: [(0, '-0.620'), (1, '22.440')] -[2023-10-10 23:56:30,558][98385] Saving new best policy, reward=-0.620! -[2023-10-10 23:56:32,257][98560] Updated weights for policy 1, policy_version 77732 (0.0008) -[2023-10-10 23:56:32,629][98560] Updated weights for policy 1, policy_version 77742 (0.0010) -[2023-10-10 23:56:32,997][98560] Updated weights for policy 1, policy_version 77752 (0.0008) -[2023-10-10 23:56:33,704][98559] Updated weights for policy 0, policy_version 78250 (0.0009) -[2023-10-10 23:56:34,070][98559] Updated weights for policy 0, policy_version 78260 (0.0009) -[2023-10-10 23:56:34,439][98559] Updated weights for policy 0, policy_version 78270 (0.0009) -[2023-10-10 23:56:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 159776768. Throughput: 0: 1688.7, 1: 1701.3. Samples: 39952992. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-10 23:56:35,557][97672] Avg episode reward: [(0, '-0.620'), (1, '22.460')] -[2023-10-10 23:56:35,565][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000077760_79626240.pth... -[2023-10-10 23:56:35,566][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000078272_80150528.pth... -[2023-10-10 23:56:35,596][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000076160_77987840.pth -[2023-10-10 23:56:35,605][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000076672_78512128.pth -[2023-10-10 23:56:37,062][98560] Updated weights for policy 1, policy_version 77762 (0.0008) -[2023-10-10 23:56:37,425][98560] Updated weights for policy 1, policy_version 77772 (0.0009) -[2023-10-10 23:56:37,784][98560] Updated weights for policy 1, policy_version 77782 (0.0007) -[2023-10-10 23:56:38,154][98560] Updated weights for policy 1, policy_version 77792 (0.0007) -[2023-10-10 23:56:38,370][98559] Updated weights for policy 0, policy_version 78280 (0.0008) -[2023-10-10 23:56:38,735][98559] Updated weights for policy 0, policy_version 78290 (0.0009) -[2023-10-10 23:56:39,101][98559] Updated weights for policy 0, policy_version 78300 (0.0009) -[2023-10-10 23:56:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 159842304. Throughput: 0: 1700.6, 1: 1682.8. Samples: 39963844. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-10 23:56:40,557][97672] Avg episode reward: [(0, '-0.620'), (1, '22.460')] -[2023-10-10 23:56:42,102][98560] Updated weights for policy 1, policy_version 77802 (0.0011) -[2023-10-10 23:56:42,464][98560] Updated weights for policy 1, policy_version 77812 (0.0010) -[2023-10-10 23:56:42,836][98560] Updated weights for policy 1, policy_version 77822 (0.0008) -[2023-10-10 23:56:42,952][98559] Updated weights for policy 0, policy_version 78310 (0.0010) -[2023-10-10 23:56:43,323][98559] Updated weights for policy 0, policy_version 78320 (0.0010) -[2023-10-10 23:56:43,678][98559] Updated weights for policy 0, policy_version 78330 (0.0008) -[2023-10-10 23:56:45,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 159907840. Throughput: 0: 1678.9, 1: 1686.7. Samples: 39983596. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-10 23:56:45,557][97672] Avg episode reward: [(0, '-0.620'), (1, '22.420')] -[2023-10-10 23:56:46,836][98560] Updated weights for policy 1, policy_version 77832 (0.0007) -[2023-10-10 23:56:47,202][98560] Updated weights for policy 1, policy_version 77842 (0.0009) -[2023-10-10 23:56:47,577][98560] Updated weights for policy 1, policy_version 77852 (0.0008) -[2023-10-10 23:56:47,598][98559] Updated weights for policy 0, policy_version 78340 (0.0009) -[2023-10-10 23:56:47,961][98559] Updated weights for policy 0, policy_version 78350 (0.0010) -[2023-10-10 23:56:48,325][98559] Updated weights for policy 0, policy_version 78360 (0.0010) -[2023-10-10 23:56:50,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 159973376. Throughput: 0: 1710.0, 1: 1701.0. Samples: 40004632. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-10 23:56:50,557][97672] Avg episode reward: [(0, '-0.620'), (1, '22.400')] -[2023-10-10 23:56:51,604][98560] Updated weights for policy 1, policy_version 77862 (0.0008) -[2023-10-10 23:56:51,963][98560] Updated weights for policy 1, policy_version 77872 (0.0008) -[2023-10-10 23:56:52,231][98559] Updated weights for policy 0, policy_version 78370 (0.0008) -[2023-10-10 23:56:52,334][98560] Updated weights for policy 1, policy_version 77882 (0.0008) -[2023-10-10 23:56:52,596][98559] Updated weights for policy 0, policy_version 78380 (0.0008) -[2023-10-10 23:56:52,962][98559] Updated weights for policy 0, policy_version 78390 (0.0009) -[2023-10-10 23:56:53,336][98559] Updated weights for policy 0, policy_version 78400 (0.0011) -[2023-10-10 23:56:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 160038912. Throughput: 0: 1690.7, 1: 1668.7. Samples: 40013904. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-10 23:56:55,557][97672] Avg episode reward: [(0, '-0.620'), (1, '22.380')] -[2023-10-10 23:56:56,386][98560] Updated weights for policy 1, policy_version 77892 (0.0008) -[2023-10-10 23:56:56,758][98560] Updated weights for policy 1, policy_version 77902 (0.0007) -[2023-10-10 23:56:57,120][98560] Updated weights for policy 1, policy_version 77912 (0.0009) -[2023-10-10 23:56:57,274][98559] Updated weights for policy 0, policy_version 78410 (0.0009) -[2023-10-10 23:56:57,646][98559] Updated weights for policy 0, policy_version 78420 (0.0009) -[2023-10-10 23:56:58,016][98559] Updated weights for policy 0, policy_version 78430 (0.0008) -[2023-10-10 23:57:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 160104448. Throughput: 0: 1705.2, 1: 1698.5. Samples: 40035304. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-10 23:57:00,557][97672] Avg episode reward: [(0, '-0.660'), (1, '22.440')] -[2023-10-10 23:57:01,155][98560] Updated weights for policy 1, policy_version 77922 (0.0009) -[2023-10-10 23:57:01,521][98560] Updated weights for policy 1, policy_version 77932 (0.0009) -[2023-10-10 23:57:01,894][98560] Updated weights for policy 1, policy_version 77942 (0.0009) -[2023-10-10 23:57:02,027][98559] Updated weights for policy 0, policy_version 78440 (0.0008) -[2023-10-10 23:57:02,263][98560] Updated weights for policy 1, policy_version 77952 (0.0010) -[2023-10-10 23:57:02,398][98559] Updated weights for policy 0, policy_version 78450 (0.0007) -[2023-10-10 23:57:02,776][98559] Updated weights for policy 0, policy_version 78460 (0.0009) -[2023-10-10 23:57:05,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 160169984. Throughput: 0: 1727.7, 1: 1699.4. Samples: 40056138. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-10 23:57:05,557][97672] Avg episode reward: [(0, '-0.660'), (1, '22.500')] -[2023-10-10 23:57:06,270][98560] Updated weights for policy 1, policy_version 77962 (0.0009) -[2023-10-10 23:57:06,646][98560] Updated weights for policy 1, policy_version 77972 (0.0008) -[2023-10-10 23:57:06,768][98559] Updated weights for policy 0, policy_version 78470 (0.0009) -[2023-10-10 23:57:07,007][98560] Updated weights for policy 1, policy_version 77982 (0.0009) -[2023-10-10 23:57:07,127][98559] Updated weights for policy 0, policy_version 78480 (0.0008) -[2023-10-10 23:57:07,494][98559] Updated weights for policy 0, policy_version 78490 (0.0007) -[2023-10-10 23:57:10,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 160235520. Throughput: 0: 1698.9, 1: 1677.7. Samples: 40065350. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-10 23:57:10,556][97672] Avg episode reward: [(0, '-0.660'), (1, '22.540')] -[2023-10-10 23:57:11,064][98560] Updated weights for policy 1, policy_version 77992 (0.0008) -[2023-10-10 23:57:11,435][98560] Updated weights for policy 1, policy_version 78002 (0.0007) -[2023-10-10 23:57:11,470][98559] Updated weights for policy 0, policy_version 78500 (0.0008) -[2023-10-10 23:57:11,795][98560] Updated weights for policy 1, policy_version 78012 (0.0007) -[2023-10-10 23:57:11,835][98559] Updated weights for policy 0, policy_version 78510 (0.0008) -[2023-10-10 23:57:12,210][98559] Updated weights for policy 0, policy_version 78520 (0.0008) -[2023-10-10 23:57:15,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 160301056. Throughput: 0: 1719.1, 1: 1698.0. Samples: 40086416. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-10 23:57:15,556][97672] Avg episode reward: [(0, '-0.660'), (1, '22.520')] -[2023-10-10 23:57:15,886][98560] Updated weights for policy 1, policy_version 78022 (0.0007) -[2023-10-10 23:57:16,253][98560] Updated weights for policy 1, policy_version 78032 (0.0007) -[2023-10-10 23:57:16,275][98559] Updated weights for policy 0, policy_version 78530 (0.0009) -[2023-10-10 23:57:16,622][98560] Updated weights for policy 1, policy_version 78042 (0.0009) -[2023-10-10 23:57:16,641][98559] Updated weights for policy 0, policy_version 78540 (0.0007) -[2023-10-10 23:57:16,991][98559] Updated weights for policy 0, policy_version 78550 (0.0010) -[2023-10-10 23:57:17,352][98559] Updated weights for policy 0, policy_version 78560 (0.0010) -[2023-10-10 23:57:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 160366592. Throughput: 0: 1728.4, 1: 1700.1. Samples: 40107274. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-10 23:57:20,556][97672] Avg episode reward: [(0, '-0.660'), (1, '22.520')] -[2023-10-10 23:57:20,602][98560] Updated weights for policy 1, policy_version 78052 (0.0007) -[2023-10-10 23:57:20,963][98560] Updated weights for policy 1, policy_version 78062 (0.0009) -[2023-10-10 23:57:21,333][98560] Updated weights for policy 1, policy_version 78072 (0.0007) -[2023-10-10 23:57:21,369][98559] Updated weights for policy 0, policy_version 78570 (0.0008) -[2023-10-10 23:57:21,729][98559] Updated weights for policy 0, policy_version 78580 (0.0009) -[2023-10-10 23:57:22,101][98559] Updated weights for policy 0, policy_version 78590 (0.0008) -[2023-10-10 23:57:25,321][98560] Updated weights for policy 1, policy_version 78082 (0.0007) -[2023-10-10 23:57:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 160432128. Throughput: 0: 1702.2, 1: 1689.2. Samples: 40116456. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-10 23:57:25,557][97672] Avg episode reward: [(0, '-0.660'), (1, '22.460')] -[2023-10-10 23:57:25,696][98560] Updated weights for policy 1, policy_version 78092 (0.0007) -[2023-10-10 23:57:26,062][98559] Updated weights for policy 0, policy_version 78600 (0.0008) -[2023-10-10 23:57:26,063][98560] Updated weights for policy 1, policy_version 78102 (0.0007) -[2023-10-10 23:57:26,417][98559] Updated weights for policy 0, policy_version 78610 (0.0007) -[2023-10-10 23:57:26,432][98560] Updated weights for policy 1, policy_version 78112 (0.0007) -[2023-10-10 23:57:26,792][98559] Updated weights for policy 0, policy_version 78620 (0.0009) -[2023-10-10 23:57:30,543][98560] Updated weights for policy 1, policy_version 78122 (0.0008) -[2023-10-10 23:57:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 160497664. Throughput: 0: 1725.3, 1: 1698.5. Samples: 40137664. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-10 23:57:30,556][97672] Avg episode reward: [(0, '-0.660'), (1, '22.460')] -[2023-10-10 23:57:30,672][98559] Updated weights for policy 0, policy_version 78630 (0.0008) -[2023-10-10 23:57:30,898][98560] Updated weights for policy 1, policy_version 78132 (0.0007) -[2023-10-10 23:57:31,028][98559] Updated weights for policy 0, policy_version 78640 (0.0007) -[2023-10-10 23:57:31,273][98560] Updated weights for policy 1, policy_version 78142 (0.0007) -[2023-10-10 23:57:31,395][98559] Updated weights for policy 0, policy_version 78650 (0.0008) -[2023-10-10 23:57:35,165][98560] Updated weights for policy 1, policy_version 78152 (0.0008) -[2023-10-10 23:57:35,417][98559] Updated weights for policy 0, policy_version 78660 (0.0011) -[2023-10-10 23:57:35,543][98560] Updated weights for policy 1, policy_version 78162 (0.0007) -[2023-10-10 23:57:35,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 160563200. Throughput: 0: 1719.5, 1: 1702.5. Samples: 40158620. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-10 23:57:35,556][97672] Avg episode reward: [(0, '-0.660'), (1, '22.500')] -[2023-10-10 23:57:35,771][98559] Updated weights for policy 0, policy_version 78670 (0.0007) -[2023-10-10 23:57:35,911][98560] Updated weights for policy 1, policy_version 78172 (0.0009) -[2023-10-10 23:57:36,135][98559] Updated weights for policy 0, policy_version 78680 (0.0008) -[2023-10-10 23:57:40,005][98560] Updated weights for policy 1, policy_version 78182 (0.0010) -[2023-10-10 23:57:40,175][98559] Updated weights for policy 0, policy_version 78690 (0.0010) -[2023-10-10 23:57:40,367][98560] Updated weights for policy 1, policy_version 78192 (0.0008) -[2023-10-10 23:57:40,534][98559] Updated weights for policy 0, policy_version 78700 (0.0009) -[2023-10-10 23:57:40,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 160628736. Throughput: 0: 1718.0, 1: 1706.2. Samples: 40167994. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-10 23:57:40,557][97672] Avg episode reward: [(0, '-0.680'), (1, '22.500')] -[2023-10-10 23:57:40,733][98560] Updated weights for policy 1, policy_version 78202 (0.0011) -[2023-10-10 23:57:40,913][98559] Updated weights for policy 0, policy_version 78710 (0.0007) -[2023-10-10 23:57:41,276][98559] Updated weights for policy 0, policy_version 78720 (0.0010) -[2023-10-10 23:57:44,649][98560] Updated weights for policy 1, policy_version 78212 (0.0009) -[2023-10-10 23:57:45,022][98560] Updated weights for policy 1, policy_version 78222 (0.0008) -[2023-10-10 23:57:45,382][98560] Updated weights for policy 1, policy_version 78232 (0.0009) -[2023-10-10 23:57:45,408][98559] Updated weights for policy 0, policy_version 78730 (0.0008) -[2023-10-10 23:57:45,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 160694272. Throughput: 0: 1709.8, 1: 1699.9. Samples: 40188742. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-10 23:57:45,556][97672] Avg episode reward: [(0, '-0.720'), (1, '22.480')] -[2023-10-10 23:57:45,775][98559] Updated weights for policy 0, policy_version 78740 (0.0008) -[2023-10-10 23:57:46,138][98559] Updated weights for policy 0, policy_version 78750 (0.0008) -[2023-10-10 23:57:49,405][98560] Updated weights for policy 1, policy_version 78242 (0.0007) -[2023-10-10 23:57:49,766][98560] Updated weights for policy 1, policy_version 78252 (0.0011) -[2023-10-10 23:57:50,138][98560] Updated weights for policy 1, policy_version 78262 (0.0010) -[2023-10-10 23:57:50,229][98559] Updated weights for policy 0, policy_version 78760 (0.0009) -[2023-10-10 23:57:50,502][98560] Updated weights for policy 1, policy_version 78272 (0.0009) -[2023-10-10 23:57:50,556][97672] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 160792576. Throughput: 0: 1695.1, 1: 1695.4. Samples: 40208710. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-10 23:57:50,556][97672] Avg episode reward: [(0, '-0.720'), (1, '22.480')] -[2023-10-10 23:57:50,601][98559] Updated weights for policy 0, policy_version 78770 (0.0008) -[2023-10-10 23:57:50,960][98559] Updated weights for policy 0, policy_version 78780 (0.0008) -[2023-10-10 23:57:54,438][98560] Updated weights for policy 1, policy_version 78282 (0.0008) -[2023-10-10 23:57:54,808][98560] Updated weights for policy 1, policy_version 78292 (0.0009) -[2023-10-10 23:57:54,975][98559] Updated weights for policy 0, policy_version 78790 (0.0008) -[2023-10-10 23:57:55,175][98560] Updated weights for policy 1, policy_version 78302 (0.0008) -[2023-10-10 23:57:55,347][98559] Updated weights for policy 0, policy_version 78800 (0.0009) -[2023-10-10 23:57:55,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 160858112. Throughput: 0: 1705.2, 1: 1706.5. Samples: 40218876. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-10 23:57:55,556][97672] Avg episode reward: [(0, '-0.720'), (1, '22.520')] -[2023-10-10 23:57:55,705][98559] Updated weights for policy 0, policy_version 78810 (0.0008) -[2023-10-10 23:57:59,254][98560] Updated weights for policy 1, policy_version 78312 (0.0007) -[2023-10-10 23:57:59,625][98560] Updated weights for policy 1, policy_version 78322 (0.0009) -[2023-10-10 23:57:59,746][98559] Updated weights for policy 0, policy_version 78820 (0.0009) -[2023-10-10 23:57:59,988][98560] Updated weights for policy 1, policy_version 78332 (0.0008) -[2023-10-10 23:58:00,113][98559] Updated weights for policy 0, policy_version 78830 (0.0007) -[2023-10-10 23:58:00,477][98559] Updated weights for policy 0, policy_version 78840 (0.0008) -[2023-10-10 23:58:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 160923648. Throughput: 0: 1706.3, 1: 1705.8. Samples: 40239962. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-10 23:58:00,556][97672] Avg episode reward: [(0, '-0.720'), (1, '22.500')] -[2023-10-10 23:58:03,973][98560] Updated weights for policy 1, policy_version 78342 (0.0008) -[2023-10-10 23:58:04,336][98560] Updated weights for policy 1, policy_version 78352 (0.0008) -[2023-10-10 23:58:04,352][98559] Updated weights for policy 0, policy_version 78850 (0.0008) -[2023-10-10 23:58:04,700][98560] Updated weights for policy 1, policy_version 78362 (0.0009) -[2023-10-10 23:58:04,722][98559] Updated weights for policy 0, policy_version 78860 (0.0009) -[2023-10-10 23:58:05,079][98559] Updated weights for policy 0, policy_version 78870 (0.0007) -[2023-10-10 23:58:05,440][98559] Updated weights for policy 0, policy_version 78880 (0.0009) -[2023-10-10 23:58:05,556][97672] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 161021952. Throughput: 0: 1687.7, 1: 1681.1. Samples: 40258870. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-10 23:58:05,556][97672] Avg episode reward: [(0, '-0.720'), (1, '22.600')] -[2023-10-10 23:58:08,794][98560] Updated weights for policy 1, policy_version 78372 (0.0008) -[2023-10-10 23:58:09,159][98560] Updated weights for policy 1, policy_version 78382 (0.0009) -[2023-10-10 23:58:09,520][98560] Updated weights for policy 1, policy_version 78392 (0.0008) -[2023-10-10 23:58:09,590][98559] Updated weights for policy 0, policy_version 78890 (0.0009) -[2023-10-10 23:58:09,949][98559] Updated weights for policy 0, policy_version 78900 (0.0010) -[2023-10-10 23:58:10,317][98559] Updated weights for policy 0, policy_version 78910 (0.0010) -[2023-10-10 23:58:10,556][97672] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 161087488. Throughput: 0: 1714.2, 1: 1702.2. Samples: 40270194. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-10 23:58:10,557][97672] Avg episode reward: [(0, '-0.720'), (1, '22.600')] -[2023-10-10 23:58:13,756][98560] Updated weights for policy 1, policy_version 78402 (0.0008) -[2023-10-10 23:58:14,117][98560] Updated weights for policy 1, policy_version 78412 (0.0009) -[2023-10-10 23:58:14,294][98559] Updated weights for policy 0, policy_version 78920 (0.0007) -[2023-10-10 23:58:14,478][98560] Updated weights for policy 1, policy_version 78422 (0.0010) -[2023-10-10 23:58:14,648][98559] Updated weights for policy 0, policy_version 78930 (0.0008) -[2023-10-10 23:58:14,846][98560] Updated weights for policy 1, policy_version 78432 (0.0008) -[2023-10-10 23:58:15,029][98559] Updated weights for policy 0, policy_version 78940 (0.0009) -[2023-10-10 23:58:15,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 161153024. Throughput: 0: 1701.1, 1: 1698.4. Samples: 40290644. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-10 23:58:15,557][97672] Avg episode reward: [(0, '-0.720'), (1, '22.740')] -[2023-10-10 23:58:18,770][98560] Updated weights for policy 1, policy_version 78442 (0.0007) -[2023-10-10 23:58:18,980][98559] Updated weights for policy 0, policy_version 78950 (0.0010) -[2023-10-10 23:58:19,135][98560] Updated weights for policy 1, policy_version 78452 (0.0009) -[2023-10-10 23:58:19,336][98559] Updated weights for policy 0, policy_version 78960 (0.0007) -[2023-10-10 23:58:19,499][98560] Updated weights for policy 1, policy_version 78462 (0.0009) -[2023-10-10 23:58:19,696][98559] Updated weights for policy 0, policy_version 78970 (0.0008) -[2023-10-10 23:58:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 161218560. Throughput: 0: 1687.7, 1: 1669.6. Samples: 40309696. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-10 23:58:20,556][97672] Avg episode reward: [(0, '-0.720'), (1, '22.700')] -[2023-10-10 23:58:23,722][98560] Updated weights for policy 1, policy_version 78472 (0.0007) -[2023-10-10 23:58:23,730][98559] Updated weights for policy 0, policy_version 78980 (0.0008) -[2023-10-10 23:58:24,082][98560] Updated weights for policy 1, policy_version 78482 (0.0008) -[2023-10-10 23:58:24,087][98559] Updated weights for policy 0, policy_version 78990 (0.0008) -[2023-10-10 23:58:24,441][98560] Updated weights for policy 1, policy_version 78492 (0.0009) -[2023-10-10 23:58:24,461][98559] Updated weights for policy 0, policy_version 79000 (0.0010) -[2023-10-10 23:58:25,556][97672] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 161284096. Throughput: 0: 1716.0, 1: 1696.8. Samples: 40321572. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-10 23:58:25,557][97672] Avg episode reward: [(0, '-0.720'), (1, '22.700')] -[2023-10-10 23:58:28,400][98560] Updated weights for policy 1, policy_version 78502 (0.0007) -[2023-10-10 23:58:28,554][98559] Updated weights for policy 0, policy_version 79010 (0.0009) -[2023-10-10 23:58:28,756][98560] Updated weights for policy 1, policy_version 78512 (0.0009) -[2023-10-10 23:58:28,914][98559] Updated weights for policy 0, policy_version 79020 (0.0008) -[2023-10-10 23:58:29,130][98560] Updated weights for policy 1, policy_version 78522 (0.0008) -[2023-10-10 23:58:29,282][98559] Updated weights for policy 0, policy_version 79030 (0.0008) -[2023-10-10 23:58:29,642][98559] Updated weights for policy 0, policy_version 79040 (0.0008) -[2023-10-10 23:58:30,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 161349632. Throughput: 0: 1696.8, 1: 1686.4. Samples: 40340990. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-10 23:58:30,557][97672] Avg episode reward: [(0, '-0.720'), (1, '22.720')] -[2023-10-10 23:58:33,090][98560] Updated weights for policy 1, policy_version 78532 (0.0008) -[2023-10-10 23:58:33,446][98560] Updated weights for policy 1, policy_version 78542 (0.0007) -[2023-10-10 23:58:33,589][98559] Updated weights for policy 0, policy_version 79050 (0.0007) -[2023-10-10 23:58:33,812][98560] Updated weights for policy 1, policy_version 78552 (0.0007) -[2023-10-10 23:58:33,955][98559] Updated weights for policy 0, policy_version 79060 (0.0007) -[2023-10-10 23:58:34,325][98559] Updated weights for policy 0, policy_version 79070 (0.0010) -[2023-10-10 23:58:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 161415168. Throughput: 0: 1704.9, 1: 1681.6. Samples: 40361104. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-10 23:58:35,557][97672] Avg episode reward: [(0, '-0.720'), (1, '22.700')] -[2023-10-10 23:58:35,564][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000078560_80445440.pth... -[2023-10-10 23:58:35,564][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000079072_80969728.pth... -[2023-10-10 23:58:35,594][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000076960_78807040.pth -[2023-10-10 23:58:35,607][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000077472_79331328.pth -[2023-10-10 23:58:37,873][98560] Updated weights for policy 1, policy_version 78562 (0.0007) -[2023-10-10 23:58:38,234][98560] Updated weights for policy 1, policy_version 78572 (0.0009) -[2023-10-10 23:58:38,239][98559] Updated weights for policy 0, policy_version 79080 (0.0009) -[2023-10-10 23:58:38,599][98559] Updated weights for policy 0, policy_version 79090 (0.0009) -[2023-10-10 23:58:38,601][98560] Updated weights for policy 1, policy_version 78582 (0.0008) -[2023-10-10 23:58:38,965][98559] Updated weights for policy 0, policy_version 79100 (0.0008) -[2023-10-10 23:58:38,977][98560] Updated weights for policy 1, policy_version 78592 (0.0009) -[2023-10-10 23:58:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 161480704. Throughput: 0: 1713.5, 1: 1700.2. Samples: 40372490. Policy #0 lag: (min: 31.0, avg: 31.9, max: 53.0) -[2023-10-10 23:58:40,557][97672] Avg episode reward: [(0, '-0.720'), (1, '22.720')] -[2023-10-10 23:58:42,967][98560] Updated weights for policy 1, policy_version 78602 (0.0008) -[2023-10-10 23:58:43,051][98559] Updated weights for policy 0, policy_version 79110 (0.0010) -[2023-10-10 23:58:43,340][98560] Updated weights for policy 1, policy_version 78612 (0.0009) -[2023-10-10 23:58:43,423][98559] Updated weights for policy 0, policy_version 79120 (0.0009) -[2023-10-10 23:58:43,705][98560] Updated weights for policy 1, policy_version 78622 (0.0009) -[2023-10-10 23:58:43,787][98559] Updated weights for policy 0, policy_version 79130 (0.0009) -[2023-10-10 23:58:45,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 161546240. Throughput: 0: 1694.0, 1: 1676.1. Samples: 40391618. Policy #0 lag: (min: 31.0, avg: 31.9, max: 53.0) -[2023-10-10 23:58:45,557][97672] Avg episode reward: [(0, '-0.720'), (1, '22.700')] -[2023-10-10 23:58:47,684][98559] Updated weights for policy 0, policy_version 79140 (0.0010) -[2023-10-10 23:58:47,776][98560] Updated weights for policy 1, policy_version 78632 (0.0007) -[2023-10-10 23:58:48,051][98559] Updated weights for policy 0, policy_version 79150 (0.0008) -[2023-10-10 23:58:48,145][98560] Updated weights for policy 1, policy_version 78642 (0.0007) -[2023-10-10 23:58:48,413][98559] Updated weights for policy 0, policy_version 79160 (0.0007) -[2023-10-10 23:58:48,512][98560] Updated weights for policy 1, policy_version 78652 (0.0007) -[2023-10-10 23:58:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 161611776. Throughput: 0: 1718.3, 1: 1699.2. Samples: 40412660. Policy #0 lag: (min: 31.0, avg: 31.9, max: 53.0) -[2023-10-10 23:58:50,557][97672] Avg episode reward: [(0, '-0.720'), (1, '22.660')] -[2023-10-10 23:58:52,295][98559] Updated weights for policy 0, policy_version 79170 (0.0008) -[2023-10-10 23:58:52,612][98560] Updated weights for policy 1, policy_version 78662 (0.0009) -[2023-10-10 23:58:52,672][98559] Updated weights for policy 0, policy_version 79180 (0.0009) -[2023-10-10 23:58:52,972][98560] Updated weights for policy 1, policy_version 78672 (0.0007) -[2023-10-10 23:58:53,032][98559] Updated weights for policy 0, policy_version 79190 (0.0008) -[2023-10-10 23:58:53,336][98560] Updated weights for policy 1, policy_version 78682 (0.0008) -[2023-10-10 23:58:53,399][98559] Updated weights for policy 0, policy_version 79200 (0.0009) -[2023-10-10 23:58:55,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 161677312. Throughput: 0: 1695.8, 1: 1699.6. Samples: 40422986. Policy #0 lag: (min: 31.0, avg: 31.9, max: 53.0) -[2023-10-10 23:58:55,556][97672] Avg episode reward: [(0, '-0.700'), (1, '22.620')] -[2023-10-10 23:58:57,215][98560] Updated weights for policy 1, policy_version 78692 (0.0008) -[2023-10-10 23:58:57,524][98559] Updated weights for policy 0, policy_version 79210 (0.0008) -[2023-10-10 23:58:57,568][98560] Updated weights for policy 1, policy_version 78702 (0.0007) -[2023-10-10 23:58:57,890][98559] Updated weights for policy 0, policy_version 79220 (0.0008) -[2023-10-10 23:58:57,939][98560] Updated weights for policy 1, policy_version 78712 (0.0009) -[2023-10-10 23:58:58,247][98559] Updated weights for policy 0, policy_version 79230 (0.0008) -[2023-10-10 23:59:00,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 161742848. Throughput: 0: 1702.4, 1: 1684.7. Samples: 40443060. Policy #0 lag: (min: 31.0, avg: 31.9, max: 53.0) -[2023-10-10 23:59:00,557][97672] Avg episode reward: [(0, '-0.700'), (1, '22.640')] -[2023-10-10 23:59:01,828][98560] Updated weights for policy 1, policy_version 78722 (0.0008) -[2023-10-10 23:59:02,101][98559] Updated weights for policy 0, policy_version 79240 (0.0009) -[2023-10-10 23:59:02,196][98560] Updated weights for policy 1, policy_version 78732 (0.0008) -[2023-10-10 23:59:02,462][98559] Updated weights for policy 0, policy_version 79250 (0.0009) -[2023-10-10 23:59:02,559][98560] Updated weights for policy 1, policy_version 78742 (0.0008) -[2023-10-10 23:59:02,825][98559] Updated weights for policy 0, policy_version 79260 (0.0009) -[2023-10-10 23:59:02,925][98560] Updated weights for policy 1, policy_version 78752 (0.0007) -[2023-10-10 23:59:05,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 161808384. Throughput: 0: 1720.6, 1: 1715.9. Samples: 40464342. Policy #0 lag: (min: 31.0, avg: 31.9, max: 53.0) -[2023-10-10 23:59:05,557][97672] Avg episode reward: [(0, '-0.700'), (1, '22.660')] -[2023-10-10 23:59:06,746][98559] Updated weights for policy 0, policy_version 79270 (0.0007) -[2023-10-10 23:59:07,047][98560] Updated weights for policy 1, policy_version 78762 (0.0009) -[2023-10-10 23:59:07,112][98559] Updated weights for policy 0, policy_version 79280 (0.0008) -[2023-10-10 23:59:07,414][98560] Updated weights for policy 1, policy_version 78772 (0.0009) -[2023-10-10 23:59:07,479][98559] Updated weights for policy 0, policy_version 79290 (0.0007) -[2023-10-10 23:59:07,786][98560] Updated weights for policy 1, policy_version 78782 (0.0009) -[2023-10-10 23:59:10,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 161873920. Throughput: 0: 1691.7, 1: 1690.7. Samples: 40473780. Policy #0 lag: (min: 31.0, avg: 31.9, max: 53.0) -[2023-10-10 23:59:10,556][97672] Avg episode reward: [(0, '-0.700'), (1, '22.680')] -[2023-10-10 23:59:11,443][98559] Updated weights for policy 0, policy_version 79300 (0.0008) -[2023-10-10 23:59:11,808][98559] Updated weights for policy 0, policy_version 79310 (0.0007) -[2023-10-10 23:59:11,971][98560] Updated weights for policy 1, policy_version 78792 (0.0008) -[2023-10-10 23:59:12,173][98559] Updated weights for policy 0, policy_version 79320 (0.0007) -[2023-10-10 23:59:12,346][98560] Updated weights for policy 1, policy_version 78802 (0.0007) -[2023-10-10 23:59:12,708][98560] Updated weights for policy 1, policy_version 78812 (0.0008) -[2023-10-10 23:59:15,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 161939456. Throughput: 0: 1715.8, 1: 1697.8. Samples: 40494602. Policy #0 lag: (min: 31.0, avg: 31.9, max: 53.0) -[2023-10-10 23:59:15,557][97672] Avg episode reward: [(0, '-0.700'), (1, '22.680')] -[2023-10-10 23:59:16,180][98559] Updated weights for policy 0, policy_version 79330 (0.0007) -[2023-10-10 23:59:16,555][98559] Updated weights for policy 0, policy_version 79340 (0.0008) -[2023-10-10 23:59:16,584][98560] Updated weights for policy 1, policy_version 78822 (0.0007) -[2023-10-10 23:59:16,926][98559] Updated weights for policy 0, policy_version 79350 (0.0009) -[2023-10-10 23:59:16,957][98560] Updated weights for policy 1, policy_version 78832 (0.0008) -[2023-10-10 23:59:17,280][98559] Updated weights for policy 0, policy_version 79360 (0.0008) -[2023-10-10 23:59:17,313][98560] Updated weights for policy 1, policy_version 78842 (0.0009) -[2023-10-10 23:59:20,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 162004992. Throughput: 0: 1723.8, 1: 1711.5. Samples: 40515692. Policy #0 lag: (min: 31.0, avg: 31.9, max: 53.0) -[2023-10-10 23:59:20,557][97672] Avg episode reward: [(0, '-0.700'), (1, '22.700')] -[2023-10-10 23:59:21,251][98559] Updated weights for policy 0, policy_version 79370 (0.0009) -[2023-10-10 23:59:21,432][98560] Updated weights for policy 1, policy_version 78852 (0.0009) -[2023-10-10 23:59:21,620][98559] Updated weights for policy 0, policy_version 79380 (0.0008) -[2023-10-10 23:59:21,796][98560] Updated weights for policy 1, policy_version 78862 (0.0008) -[2023-10-10 23:59:21,980][98559] Updated weights for policy 0, policy_version 79390 (0.0009) -[2023-10-10 23:59:22,158][98560] Updated weights for policy 1, policy_version 78872 (0.0008) -[2023-10-10 23:59:25,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 162070528. Throughput: 0: 1706.7, 1: 1679.7. Samples: 40524878. Policy #0 lag: (min: 31.0, avg: 31.9, max: 53.0) -[2023-10-10 23:59:25,557][97672] Avg episode reward: [(0, '-0.700'), (1, '22.680')] -[2023-10-10 23:59:25,924][98559] Updated weights for policy 0, policy_version 79400 (0.0008) -[2023-10-10 23:59:26,114][98560] Updated weights for policy 1, policy_version 78882 (0.0009) -[2023-10-10 23:59:26,286][98559] Updated weights for policy 0, policy_version 79410 (0.0007) -[2023-10-10 23:59:26,483][98560] Updated weights for policy 1, policy_version 78892 (0.0008) -[2023-10-10 23:59:26,654][98559] Updated weights for policy 0, policy_version 79420 (0.0007) -[2023-10-10 23:59:26,845][98560] Updated weights for policy 1, policy_version 78902 (0.0007) -[2023-10-10 23:59:27,205][98560] Updated weights for policy 1, policy_version 78912 (0.0009) -[2023-10-10 23:59:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 162136064. Throughput: 0: 1726.7, 1: 1711.0. Samples: 40546314. Policy #0 lag: (min: 31.0, avg: 31.9, max: 53.0) -[2023-10-10 23:59:30,558][97672] Avg episode reward: [(0, '-0.720'), (1, '22.700')] -[2023-10-10 23:59:30,791][98559] Updated weights for policy 0, policy_version 79430 (0.0010) -[2023-10-10 23:59:31,151][98559] Updated weights for policy 0, policy_version 79440 (0.0009) -[2023-10-10 23:59:31,232][98560] Updated weights for policy 1, policy_version 78922 (0.0007) -[2023-10-10 23:59:31,510][98559] Updated weights for policy 0, policy_version 79450 (0.0007) -[2023-10-10 23:59:31,596][98560] Updated weights for policy 1, policy_version 78932 (0.0007) -[2023-10-10 23:59:31,957][98560] Updated weights for policy 1, policy_version 78942 (0.0007) -[2023-10-10 23:59:35,390][98559] Updated weights for policy 0, policy_version 79460 (0.0009) -[2023-10-10 23:59:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 162201600. Throughput: 0: 1722.2, 1: 1710.8. Samples: 40567142. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:59:35,557][97672] Avg episode reward: [(0, '-0.720'), (1, '22.700')] -[2023-10-10 23:59:35,752][98559] Updated weights for policy 0, policy_version 79470 (0.0010) -[2023-10-10 23:59:36,118][98559] Updated weights for policy 0, policy_version 79480 (0.0008) -[2023-10-10 23:59:36,126][98560] Updated weights for policy 1, policy_version 78952 (0.0008) -[2023-10-10 23:59:36,483][98560] Updated weights for policy 1, policy_version 78962 (0.0008) -[2023-10-10 23:59:36,854][98560] Updated weights for policy 1, policy_version 78972 (0.0011) -[2023-10-10 23:59:40,146][98559] Updated weights for policy 0, policy_version 79490 (0.0009) -[2023-10-10 23:59:40,500][98559] Updated weights for policy 0, policy_version 79500 (0.0008) -[2023-10-10 23:59:40,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 162267136. Throughput: 0: 1723.7, 1: 1687.8. Samples: 40576506. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:59:40,557][97672] Avg episode reward: [(0, '-0.720'), (1, '22.580')] -[2023-10-10 23:59:40,869][98559] Updated weights for policy 0, policy_version 79510 (0.0008) -[2023-10-10 23:59:40,945][98560] Updated weights for policy 1, policy_version 78982 (0.0009) -[2023-10-10 23:59:41,231][98559] Updated weights for policy 0, policy_version 79520 (0.0008) -[2023-10-10 23:59:41,310][98560] Updated weights for policy 1, policy_version 78992 (0.0008) -[2023-10-10 23:59:41,666][98560] Updated weights for policy 1, policy_version 79002 (0.0009) -[2023-10-10 23:59:45,379][98559] Updated weights for policy 0, policy_version 79530 (0.0009) -[2023-10-10 23:59:45,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 162332672. Throughput: 0: 1726.1, 1: 1701.1. Samples: 40597284. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:59:45,557][97672] Avg episode reward: [(0, '-0.740'), (1, '22.640')] -[2023-10-10 23:59:45,757][98559] Updated weights for policy 0, policy_version 79540 (0.0007) -[2023-10-10 23:59:45,819][98560] Updated weights for policy 1, policy_version 79012 (0.0007) -[2023-10-10 23:59:46,117][98559] Updated weights for policy 0, policy_version 79550 (0.0007) -[2023-10-10 23:59:46,177][98560] Updated weights for policy 1, policy_version 79022 (0.0007) -[2023-10-10 23:59:46,538][98560] Updated weights for policy 1, policy_version 79032 (0.0008) -[2023-10-10 23:59:50,050][98559] Updated weights for policy 0, policy_version 79560 (0.0008) -[2023-10-10 23:59:50,407][98559] Updated weights for policy 0, policy_version 79570 (0.0010) -[2023-10-10 23:59:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 162398208. Throughput: 0: 1706.7, 1: 1695.3. Samples: 40617430. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:59:50,556][97672] Avg episode reward: [(0, '-0.740'), (1, '22.620')] -[2023-10-10 23:59:50,626][98560] Updated weights for policy 1, policy_version 79042 (0.0008) -[2023-10-10 23:59:50,774][98559] Updated weights for policy 0, policy_version 79580 (0.0008) -[2023-10-10 23:59:50,978][98560] Updated weights for policy 1, policy_version 79052 (0.0007) -[2023-10-10 23:59:51,345][98560] Updated weights for policy 1, policy_version 79062 (0.0007) -[2023-10-10 23:59:51,716][98560] Updated weights for policy 1, policy_version 79072 (0.0007) -[2023-10-10 23:59:54,889][98559] Updated weights for policy 0, policy_version 79590 (0.0008) -[2023-10-10 23:59:55,249][98559] Updated weights for policy 0, policy_version 79600 (0.0009) -[2023-10-10 23:59:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 162463744. Throughput: 0: 1717.4, 1: 1695.6. Samples: 40627368. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 23:59:55,556][97672] Avg episode reward: [(0, '-0.740'), (1, '22.600')] -[2023-10-10 23:59:55,611][98559] Updated weights for policy 0, policy_version 79610 (0.0008) -[2023-10-10 23:59:55,774][98560] Updated weights for policy 1, policy_version 79082 (0.0007) -[2023-10-10 23:59:56,140][98560] Updated weights for policy 1, policy_version 79092 (0.0007) -[2023-10-10 23:59:56,497][98560] Updated weights for policy 1, policy_version 79102 (0.0008) -[2023-10-10 23:59:59,593][98559] Updated weights for policy 0, policy_version 79620 (0.0009) -[2023-10-10 23:59:59,949][98559] Updated weights for policy 0, policy_version 79630 (0.0010) -[2023-10-11 00:00:00,313][98559] Updated weights for policy 0, policy_version 79640 (0.0007) -[2023-10-11 00:00:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 162529280. Throughput: 0: 1721.5, 1: 1695.6. Samples: 40648372. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:00:00,557][97672] Avg episode reward: [(0, '-0.740'), (1, '22.620')] -[2023-10-11 00:00:00,668][98560] Updated weights for policy 1, policy_version 79112 (0.0007) -[2023-10-11 00:00:01,047][98560] Updated weights for policy 1, policy_version 79122 (0.0007) -[2023-10-11 00:00:01,413][98560] Updated weights for policy 1, policy_version 79132 (0.0010) -[2023-10-11 00:00:04,432][98559] Updated weights for policy 0, policy_version 79650 (0.0008) -[2023-10-11 00:00:04,796][98559] Updated weights for policy 0, policy_version 79660 (0.0009) -[2023-10-11 00:00:05,170][98559] Updated weights for policy 0, policy_version 79670 (0.0010) -[2023-10-11 00:00:05,397][98560] Updated weights for policy 1, policy_version 79142 (0.0010) -[2023-10-11 00:00:05,532][98559] Updated weights for policy 0, policy_version 79680 (0.0009) -[2023-10-11 00:00:05,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 162627584. Throughput: 0: 1690.8, 1: 1693.8. Samples: 40667998. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:00:05,556][97672] Avg episode reward: [(0, '-0.740'), (1, '22.620')] -[2023-10-11 00:00:05,767][98560] Updated weights for policy 1, policy_version 79152 (0.0009) -[2023-10-11 00:00:06,129][98560] Updated weights for policy 1, policy_version 79162 (0.0008) -[2023-10-11 00:00:09,533][98559] Updated weights for policy 0, policy_version 79690 (0.0009) -[2023-10-11 00:00:09,894][98559] Updated weights for policy 0, policy_version 79700 (0.0008) -[2023-10-11 00:00:10,188][98560] Updated weights for policy 1, policy_version 79172 (0.0008) -[2023-10-11 00:00:10,255][98559] Updated weights for policy 0, policy_version 79710 (0.0008) -[2023-10-11 00:00:10,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 162693120. Throughput: 0: 1712.2, 1: 1692.7. Samples: 40678098. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:00:10,556][97672] Avg episode reward: [(0, '-0.740'), (1, '22.620')] -[2023-10-11 00:00:10,558][98560] Updated weights for policy 1, policy_version 79182 (0.0010) -[2023-10-11 00:00:10,926][98560] Updated weights for policy 1, policy_version 79192 (0.0009) -[2023-10-11 00:00:14,320][98559] Updated weights for policy 0, policy_version 79720 (0.0007) -[2023-10-11 00:00:14,684][98559] Updated weights for policy 0, policy_version 79730 (0.0008) -[2023-10-11 00:00:14,941][98560] Updated weights for policy 1, policy_version 79202 (0.0009) -[2023-10-11 00:00:15,053][98559] Updated weights for policy 0, policy_version 79740 (0.0009) -[2023-10-11 00:00:15,311][98560] Updated weights for policy 1, policy_version 79212 (0.0009) -[2023-10-11 00:00:15,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 162758656. Throughput: 0: 1698.3, 1: 1680.9. Samples: 40698378. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:00:15,557][97672] Avg episode reward: [(0, '-0.740'), (1, '22.540')] -[2023-10-11 00:00:15,679][98560] Updated weights for policy 1, policy_version 79222 (0.0007) -[2023-10-11 00:00:16,046][98560] Updated weights for policy 1, policy_version 79232 (0.0007) -[2023-10-11 00:00:19,112][98559] Updated weights for policy 0, policy_version 79750 (0.0009) -[2023-10-11 00:00:19,475][98559] Updated weights for policy 0, policy_version 79760 (0.0009) -[2023-10-11 00:00:19,831][98559] Updated weights for policy 0, policy_version 79770 (0.0009) -[2023-10-11 00:00:20,027][98560] Updated weights for policy 1, policy_version 79242 (0.0007) -[2023-10-11 00:00:20,390][98560] Updated weights for policy 1, policy_version 79252 (0.0007) -[2023-10-11 00:00:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 162824192. Throughput: 0: 1676.0, 1: 1681.2. Samples: 40718214. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:00:20,556][97672] Avg episode reward: [(0, '-0.740'), (1, '22.500')] -[2023-10-11 00:00:20,755][98560] Updated weights for policy 1, policy_version 79262 (0.0008) -[2023-10-11 00:00:23,881][98559] Updated weights for policy 0, policy_version 79780 (0.0007) -[2023-10-11 00:00:24,251][98559] Updated weights for policy 0, policy_version 79790 (0.0008) -[2023-10-11 00:00:24,534][98560] Updated weights for policy 1, policy_version 79272 (0.0009) -[2023-10-11 00:00:24,623][98559] Updated weights for policy 0, policy_version 79800 (0.0009) -[2023-10-11 00:00:24,906][98560] Updated weights for policy 1, policy_version 79282 (0.0008) -[2023-10-11 00:00:25,266][98560] Updated weights for policy 1, policy_version 79292 (0.0009) -[2023-10-11 00:00:25,556][97672] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 162922496. Throughput: 0: 1701.8, 1: 1683.9. Samples: 40728864. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:00:25,557][97672] Avg episode reward: [(0, '-0.740'), (1, '22.540')] -[2023-10-11 00:00:28,677][98559] Updated weights for policy 0, policy_version 79810 (0.0009) -[2023-10-11 00:00:29,049][98559] Updated weights for policy 0, policy_version 79820 (0.0012) -[2023-10-11 00:00:29,214][98560] Updated weights for policy 1, policy_version 79302 (0.0008) -[2023-10-11 00:00:29,407][98559] Updated weights for policy 0, policy_version 79830 (0.0010) -[2023-10-11 00:00:29,580][98560] Updated weights for policy 1, policy_version 79312 (0.0007) -[2023-10-11 00:00:29,770][98559] Updated weights for policy 0, policy_version 79840 (0.0009) -[2023-10-11 00:00:29,946][98560] Updated weights for policy 1, policy_version 79322 (0.0010) -[2023-10-11 00:00:30,556][97672] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 162988032. Throughput: 0: 1677.2, 1: 1696.5. Samples: 40749102. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:00:30,557][97672] Avg episode reward: [(0, '-0.740'), (1, '22.580')] -[2023-10-11 00:00:33,645][98559] Updated weights for policy 0, policy_version 79850 (0.0009) -[2023-10-11 00:00:34,015][98559] Updated weights for policy 0, policy_version 79860 (0.0008) -[2023-10-11 00:00:34,073][98560] Updated weights for policy 1, policy_version 79332 (0.0008) -[2023-10-11 00:00:34,372][98559] Updated weights for policy 0, policy_version 79870 (0.0009) -[2023-10-11 00:00:34,434][98560] Updated weights for policy 1, policy_version 79342 (0.0007) -[2023-10-11 00:00:34,810][98560] Updated weights for policy 1, policy_version 79352 (0.0008) -[2023-10-11 00:00:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 163053568. Throughput: 0: 1692.3, 1: 1684.5. Samples: 40769386. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:00:35,557][97672] Avg episode reward: [(0, '-0.740'), (1, '22.560')] -[2023-10-11 00:00:35,568][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000079360_81264640.pth... -[2023-10-11 00:00:35,568][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000079872_81788928.pth... -[2023-10-11 00:00:35,608][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000077760_79626240.pth -[2023-10-11 00:00:35,609][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000078272_80150528.pth -[2023-10-11 00:00:35,613][98439] Saving a milestone ./train_atari/atari_doubledunk_APPO/checkpoint_p1/milestones/checkpoint_000079360_81264640.pth -[2023-10-11 00:00:35,615][98385] Saving a milestone ./train_atari/atari_doubledunk_APPO/checkpoint_p0/milestones/checkpoint_000079872_81788928.pth -[2023-10-11 00:00:38,208][98559] Updated weights for policy 0, policy_version 79880 (0.0009) -[2023-10-11 00:00:38,583][98559] Updated weights for policy 0, policy_version 79890 (0.0007) -[2023-10-11 00:00:38,799][98560] Updated weights for policy 1, policy_version 79362 (0.0008) -[2023-10-11 00:00:38,951][98559] Updated weights for policy 0, policy_version 79900 (0.0008) -[2023-10-11 00:00:39,164][98560] Updated weights for policy 1, policy_version 79372 (0.0007) -[2023-10-11 00:00:39,529][98560] Updated weights for policy 1, policy_version 79382 (0.0007) -[2023-10-11 00:00:39,894][98560] Updated weights for policy 1, policy_version 79392 (0.0009) -[2023-10-11 00:00:40,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 163119104. Throughput: 0: 1700.7, 1: 1698.6. Samples: 40780338. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:00:40,557][97672] Avg episode reward: [(0, '-0.740'), (1, '22.560')] -[2023-10-11 00:00:42,823][98559] Updated weights for policy 0, policy_version 79910 (0.0009) -[2023-10-11 00:00:43,198][98559] Updated weights for policy 0, policy_version 79920 (0.0009) -[2023-10-11 00:00:43,569][98559] Updated weights for policy 0, policy_version 79930 (0.0008) -[2023-10-11 00:00:43,963][98560] Updated weights for policy 1, policy_version 79402 (0.0007) -[2023-10-11 00:00:44,329][98560] Updated weights for policy 1, policy_version 79412 (0.0008) -[2023-10-11 00:00:44,698][98560] Updated weights for policy 1, policy_version 79422 (0.0007) -[2023-10-11 00:00:45,556][97672] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 163184640. Throughput: 0: 1677.4, 1: 1703.3. Samples: 40800502. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:00:45,557][97672] Avg episode reward: [(0, '-0.740'), (1, '22.640')] -[2023-10-11 00:00:47,635][98559] Updated weights for policy 0, policy_version 79940 (0.0008) -[2023-10-11 00:00:48,003][98559] Updated weights for policy 0, policy_version 79950 (0.0008) -[2023-10-11 00:00:48,374][98559] Updated weights for policy 0, policy_version 79960 (0.0008) -[2023-10-11 00:00:48,863][98560] Updated weights for policy 1, policy_version 79432 (0.0008) -[2023-10-11 00:00:49,246][98560] Updated weights for policy 1, policy_version 79442 (0.0009) -[2023-10-11 00:00:49,603][98560] Updated weights for policy 1, policy_version 79452 (0.0009) -[2023-10-11 00:00:50,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 163250176. Throughput: 0: 1707.2, 1: 1682.8. Samples: 40820546. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:00:50,557][97672] Avg episode reward: [(0, '-0.740'), (1, '22.620')] -[2023-10-11 00:00:52,507][98559] Updated weights for policy 0, policy_version 79970 (0.0007) -[2023-10-11 00:00:52,875][98559] Updated weights for policy 0, policy_version 79980 (0.0008) -[2023-10-11 00:00:53,239][98559] Updated weights for policy 0, policy_version 79990 (0.0009) -[2023-10-11 00:00:53,487][98560] Updated weights for policy 1, policy_version 79462 (0.0008) -[2023-10-11 00:00:53,603][98559] Updated weights for policy 0, policy_version 80000 (0.0008) -[2023-10-11 00:00:53,853][98560] Updated weights for policy 1, policy_version 79472 (0.0008) -[2023-10-11 00:00:54,228][98560] Updated weights for policy 1, policy_version 79482 (0.0009) -[2023-10-11 00:00:55,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 163315712. Throughput: 0: 1688.4, 1: 1715.4. Samples: 40831268. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:00:55,557][97672] Avg episode reward: [(0, '-0.740'), (1, '22.560')] -[2023-10-11 00:00:57,591][98559] Updated weights for policy 0, policy_version 80010 (0.0007) -[2023-10-11 00:00:57,954][98559] Updated weights for policy 0, policy_version 80020 (0.0008) -[2023-10-11 00:00:58,138][98560] Updated weights for policy 1, policy_version 79492 (0.0009) -[2023-10-11 00:00:58,321][98559] Updated weights for policy 0, policy_version 80030 (0.0007) -[2023-10-11 00:00:58,512][98560] Updated weights for policy 1, policy_version 79502 (0.0008) -[2023-10-11 00:00:58,880][98560] Updated weights for policy 1, policy_version 79512 (0.0007) -[2023-10-11 00:01:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 163381248. Throughput: 0: 1694.9, 1: 1704.4. Samples: 40851350. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:01:00,557][97672] Avg episode reward: [(0, '-0.740'), (1, '22.560')] -[2023-10-11 00:01:02,329][98559] Updated weights for policy 0, policy_version 80040 (0.0008) -[2023-10-11 00:01:02,685][98559] Updated weights for policy 0, policy_version 80050 (0.0007) -[2023-10-11 00:01:02,732][98560] Updated weights for policy 1, policy_version 79522 (0.0009) -[2023-10-11 00:01:03,052][98559] Updated weights for policy 0, policy_version 80060 (0.0008) -[2023-10-11 00:01:03,100][98560] Updated weights for policy 1, policy_version 79532 (0.0008) -[2023-10-11 00:01:03,469][98560] Updated weights for policy 1, policy_version 79542 (0.0009) -[2023-10-11 00:01:03,841][98560] Updated weights for policy 1, policy_version 79552 (0.0009) -[2023-10-11 00:01:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 163446784. Throughput: 0: 1721.2, 1: 1697.9. Samples: 40872076. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:01:05,557][97672] Avg episode reward: [(0, '-0.740'), (1, '22.540')] -[2023-10-11 00:01:06,968][98559] Updated weights for policy 0, policy_version 80070 (0.0009) -[2023-10-11 00:01:07,337][98559] Updated weights for policy 0, policy_version 80080 (0.0009) -[2023-10-11 00:01:07,698][98559] Updated weights for policy 0, policy_version 80090 (0.0007) -[2023-10-11 00:01:07,855][98560] Updated weights for policy 1, policy_version 79562 (0.0008) -[2023-10-11 00:01:08,226][98560] Updated weights for policy 1, policy_version 79572 (0.0009) -[2023-10-11 00:01:08,596][98560] Updated weights for policy 1, policy_version 79582 (0.0008) -[2023-10-11 00:01:10,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 163512320. Throughput: 0: 1692.2, 1: 1719.6. Samples: 40882396. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:01:10,557][97672] Avg episode reward: [(0, '-0.740'), (1, '22.520')] -[2023-10-11 00:01:11,689][98559] Updated weights for policy 0, policy_version 80100 (0.0008) -[2023-10-11 00:01:12,066][98559] Updated weights for policy 0, policy_version 80110 (0.0009) -[2023-10-11 00:01:12,430][98559] Updated weights for policy 0, policy_version 80120 (0.0007) -[2023-10-11 00:01:12,691][98560] Updated weights for policy 1, policy_version 79592 (0.0008) -[2023-10-11 00:01:13,059][98560] Updated weights for policy 1, policy_version 79602 (0.0008) -[2023-10-11 00:01:13,427][98560] Updated weights for policy 1, policy_version 79612 (0.0008) -[2023-10-11 00:01:15,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 163577856. Throughput: 0: 1723.0, 1: 1685.6. Samples: 40902486. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:01:15,557][97672] Avg episode reward: [(0, '-0.740'), (1, '22.520')] -[2023-10-11 00:01:16,304][98559] Updated weights for policy 0, policy_version 80130 (0.0008) -[2023-10-11 00:01:16,669][98559] Updated weights for policy 0, policy_version 80140 (0.0010) -[2023-10-11 00:01:17,035][98559] Updated weights for policy 0, policy_version 80150 (0.0008) -[2023-10-11 00:01:17,342][98560] Updated weights for policy 1, policy_version 79622 (0.0010) -[2023-10-11 00:01:17,400][98559] Updated weights for policy 0, policy_version 80160 (0.0008) -[2023-10-11 00:01:17,707][98560] Updated weights for policy 1, policy_version 79632 (0.0008) -[2023-10-11 00:01:18,082][98560] Updated weights for policy 1, policy_version 79642 (0.0009) -[2023-10-11 00:01:20,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 163643392. Throughput: 0: 1729.0, 1: 1700.9. Samples: 40923730. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:01:20,556][97672] Avg episode reward: [(0, '-0.740'), (1, '22.500')] -[2023-10-11 00:01:21,544][98559] Updated weights for policy 0, policy_version 80170 (0.0010) -[2023-10-11 00:01:21,909][98559] Updated weights for policy 0, policy_version 80180 (0.0008) -[2023-10-11 00:01:22,279][98559] Updated weights for policy 0, policy_version 80190 (0.0009) -[2023-10-11 00:01:22,281][98560] Updated weights for policy 1, policy_version 79652 (0.0009) -[2023-10-11 00:01:22,651][98560] Updated weights for policy 1, policy_version 79662 (0.0007) -[2023-10-11 00:01:23,014][98560] Updated weights for policy 1, policy_version 79672 (0.0007) -[2023-10-11 00:01:25,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 163708928. Throughput: 0: 1708.1, 1: 1693.8. Samples: 40933424. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:01:25,556][97672] Avg episode reward: [(0, '-0.740'), (1, '22.620')] -[2023-10-11 00:01:26,089][98559] Updated weights for policy 0, policy_version 80200 (0.0008) -[2023-10-11 00:01:26,459][98559] Updated weights for policy 0, policy_version 80210 (0.0007) -[2023-10-11 00:01:26,824][98559] Updated weights for policy 0, policy_version 80220 (0.0010) -[2023-10-11 00:01:26,919][98560] Updated weights for policy 1, policy_version 79682 (0.0007) -[2023-10-11 00:01:27,283][98560] Updated weights for policy 1, policy_version 79692 (0.0008) -[2023-10-11 00:01:27,660][98560] Updated weights for policy 1, policy_version 79702 (0.0007) -[2023-10-11 00:01:28,021][98560] Updated weights for policy 1, policy_version 79712 (0.0010) -[2023-10-11 00:01:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 163774464. Throughput: 0: 1725.6, 1: 1684.7. Samples: 40953966. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:01:30,557][97672] Avg episode reward: [(0, '-0.740'), (1, '22.600')] -[2023-10-11 00:01:30,765][98559] Updated weights for policy 0, policy_version 80230 (0.0009) -[2023-10-11 00:01:31,134][98559] Updated weights for policy 0, policy_version 80240 (0.0008) -[2023-10-11 00:01:31,507][98559] Updated weights for policy 0, policy_version 80250 (0.0009) -[2023-10-11 00:01:31,787][98560] Updated weights for policy 1, policy_version 79722 (0.0009) -[2023-10-11 00:01:32,152][98560] Updated weights for policy 1, policy_version 79732 (0.0008) -[2023-10-11 00:01:32,516][98560] Updated weights for policy 1, policy_version 79742 (0.0009) -[2023-10-11 00:01:35,413][98559] Updated weights for policy 0, policy_version 80260 (0.0009) -[2023-10-11 00:01:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 163840000. Throughput: 0: 1726.0, 1: 1711.5. Samples: 40975234. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:01:35,557][97672] Avg episode reward: [(0, '-0.740'), (1, '22.620')] -[2023-10-11 00:01:35,781][98559] Updated weights for policy 0, policy_version 80270 (0.0009) -[2023-10-11 00:01:36,142][98559] Updated weights for policy 0, policy_version 80280 (0.0007) -[2023-10-11 00:01:36,614][98560] Updated weights for policy 1, policy_version 79752 (0.0008) -[2023-10-11 00:01:36,992][98560] Updated weights for policy 1, policy_version 79762 (0.0008) -[2023-10-11 00:01:37,355][98560] Updated weights for policy 1, policy_version 79772 (0.0010) -[2023-10-11 00:01:40,026][98559] Updated weights for policy 0, policy_version 80290 (0.0008) -[2023-10-11 00:01:40,404][98559] Updated weights for policy 0, policy_version 80300 (0.0009) -[2023-10-11 00:01:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 163905536. Throughput: 0: 1727.1, 1: 1680.9. Samples: 40984628. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:01:40,556][97672] Avg episode reward: [(0, '-0.800'), (1, '22.680')] -[2023-10-11 00:01:40,776][98559] Updated weights for policy 0, policy_version 80310 (0.0007) -[2023-10-11 00:01:41,142][98559] Updated weights for policy 0, policy_version 80320 (0.0007) -[2023-10-11 00:01:41,348][98560] Updated weights for policy 1, policy_version 79782 (0.0009) -[2023-10-11 00:01:41,727][98560] Updated weights for policy 1, policy_version 79792 (0.0007) -[2023-10-11 00:01:42,095][98560] Updated weights for policy 1, policy_version 79802 (0.0009) -[2023-10-11 00:01:44,926][98559] Updated weights for policy 0, policy_version 80330 (0.0007) -[2023-10-11 00:01:45,284][98559] Updated weights for policy 0, policy_version 80340 (0.0007) -[2023-10-11 00:01:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 163971072. Throughput: 0: 1737.0, 1: 1692.8. Samples: 41005694. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:01:45,556][97672] Avg episode reward: [(0, '-0.800'), (1, '22.720')] -[2023-10-11 00:01:45,657][98559] Updated weights for policy 0, policy_version 80350 (0.0009) -[2023-10-11 00:01:45,996][98560] Updated weights for policy 1, policy_version 79812 (0.0008) -[2023-10-11 00:01:46,368][98560] Updated weights for policy 1, policy_version 79822 (0.0010) -[2023-10-11 00:01:46,738][98560] Updated weights for policy 1, policy_version 79832 (0.0008) -[2023-10-11 00:01:49,620][98559] Updated weights for policy 0, policy_version 80360 (0.0008) -[2023-10-11 00:01:49,991][98559] Updated weights for policy 0, policy_version 80370 (0.0010) -[2023-10-11 00:01:50,362][98559] Updated weights for policy 0, policy_version 80380 (0.0007) -[2023-10-11 00:01:50,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 164069376. Throughput: 0: 1712.4, 1: 1698.6. Samples: 41025568. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:01:50,557][97672] Avg episode reward: [(0, '-0.760'), (1, '22.740')] -[2023-10-11 00:01:50,975][98560] Updated weights for policy 1, policy_version 79842 (0.0008) -[2023-10-11 00:01:51,340][98560] Updated weights for policy 1, policy_version 79852 (0.0008) -[2023-10-11 00:01:51,699][98560] Updated weights for policy 1, policy_version 79862 (0.0009) -[2023-10-11 00:01:52,063][98560] Updated weights for policy 1, policy_version 79872 (0.0010) -[2023-10-11 00:01:54,390][98559] Updated weights for policy 0, policy_version 80390 (0.0008) -[2023-10-11 00:01:54,755][98559] Updated weights for policy 0, policy_version 80400 (0.0009) -[2023-10-11 00:01:55,112][98559] Updated weights for policy 0, policy_version 80410 (0.0010) -[2023-10-11 00:01:55,556][97672] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 164134912. Throughput: 0: 1734.5, 1: 1673.7. Samples: 41035766. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:01:55,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.740')] -[2023-10-11 00:01:56,161][98560] Updated weights for policy 1, policy_version 79882 (0.0010) -[2023-10-11 00:01:56,539][98560] Updated weights for policy 1, policy_version 79892 (0.0009) -[2023-10-11 00:01:56,903][98560] Updated weights for policy 1, policy_version 79902 (0.0008) -[2023-10-11 00:01:59,121][98559] Updated weights for policy 0, policy_version 80420 (0.0011) -[2023-10-11 00:01:59,492][98559] Updated weights for policy 0, policy_version 80430 (0.0010) -[2023-10-11 00:01:59,854][98559] Updated weights for policy 0, policy_version 80440 (0.0009) -[2023-10-11 00:02:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 164200448. Throughput: 0: 1722.0, 1: 1699.0. Samples: 41056430. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:02:00,556][97672] Avg episode reward: [(0, '-0.780'), (1, '22.740')] -[2023-10-11 00:02:00,764][98560] Updated weights for policy 1, policy_version 79912 (0.0008) -[2023-10-11 00:02:01,138][98560] Updated weights for policy 1, policy_version 79922 (0.0010) -[2023-10-11 00:02:01,507][98560] Updated weights for policy 1, policy_version 79932 (0.0008) -[2023-10-11 00:02:03,715][98559] Updated weights for policy 0, policy_version 80450 (0.0010) -[2023-10-11 00:02:04,082][98559] Updated weights for policy 0, policy_version 80460 (0.0007) -[2023-10-11 00:02:04,448][98559] Updated weights for policy 0, policy_version 80470 (0.0009) -[2023-10-11 00:02:04,807][98559] Updated weights for policy 0, policy_version 80480 (0.0010) -[2023-10-11 00:02:05,466][98560] Updated weights for policy 1, policy_version 79942 (0.0008) -[2023-10-11 00:02:05,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 164265984. Throughput: 0: 1706.0, 1: 1701.9. Samples: 41077082. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:02:05,556][97672] Avg episode reward: [(0, '-0.780'), (1, '22.740')] -[2023-10-11 00:02:05,831][98560] Updated weights for policy 1, policy_version 79952 (0.0007) -[2023-10-11 00:02:06,197][98560] Updated weights for policy 1, policy_version 79962 (0.0007) -[2023-10-11 00:02:08,932][98559] Updated weights for policy 0, policy_version 80490 (0.0009) -[2023-10-11 00:02:09,302][98559] Updated weights for policy 0, policy_version 80500 (0.0011) -[2023-10-11 00:02:09,671][98559] Updated weights for policy 0, policy_version 80510 (0.0009) -[2023-10-11 00:02:10,353][98560] Updated weights for policy 1, policy_version 79972 (0.0009) -[2023-10-11 00:02:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 164331520. Throughput: 0: 1734.0, 1: 1687.6. Samples: 41087394. Policy #0 lag: (min: 10.0, avg: 13.8, max: 42.0) -[2023-10-11 00:02:10,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.600')] -[2023-10-11 00:02:10,721][98560] Updated weights for policy 1, policy_version 79982 (0.0010) -[2023-10-11 00:02:11,086][98560] Updated weights for policy 1, policy_version 79992 (0.0010) -[2023-10-11 00:02:13,686][98559] Updated weights for policy 0, policy_version 80520 (0.0008) -[2023-10-11 00:02:14,051][98559] Updated weights for policy 0, policy_version 80530 (0.0007) -[2023-10-11 00:02:14,421][98559] Updated weights for policy 0, policy_version 80540 (0.0009) -[2023-10-11 00:02:14,974][98560] Updated weights for policy 1, policy_version 80002 (0.0009) -[2023-10-11 00:02:15,341][98560] Updated weights for policy 1, policy_version 80012 (0.0007) -[2023-10-11 00:02:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 164397056. Throughput: 0: 1708.9, 1: 1700.8. Samples: 41107402. Policy #0 lag: (min: 10.0, avg: 13.8, max: 42.0) -[2023-10-11 00:02:15,556][97672] Avg episode reward: [(0, '-0.780'), (1, '22.560')] -[2023-10-11 00:02:15,700][98560] Updated weights for policy 1, policy_version 80022 (0.0007) -[2023-10-11 00:02:16,077][98560] Updated weights for policy 1, policy_version 80032 (0.0007) -[2023-10-11 00:02:18,329][98559] Updated weights for policy 0, policy_version 80550 (0.0008) -[2023-10-11 00:02:18,692][98559] Updated weights for policy 0, policy_version 80560 (0.0008) -[2023-10-11 00:02:19,062][98559] Updated weights for policy 0, policy_version 80570 (0.0007) -[2023-10-11 00:02:20,094][98560] Updated weights for policy 1, policy_version 80042 (0.0008) -[2023-10-11 00:02:20,465][98560] Updated weights for policy 1, policy_version 80052 (0.0008) -[2023-10-11 00:02:20,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 164462592. Throughput: 0: 1706.7, 1: 1702.6. Samples: 41128650. Policy #0 lag: (min: 10.0, avg: 13.8, max: 42.0) -[2023-10-11 00:02:20,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.600')] -[2023-10-11 00:02:20,827][98560] Updated weights for policy 1, policy_version 80062 (0.0009) -[2023-10-11 00:02:23,035][98559] Updated weights for policy 0, policy_version 80580 (0.0009) -[2023-10-11 00:02:23,402][98559] Updated weights for policy 0, policy_version 80590 (0.0007) -[2023-10-11 00:02:23,765][98559] Updated weights for policy 0, policy_version 80600 (0.0007) -[2023-10-11 00:02:25,011][98560] Updated weights for policy 1, policy_version 80072 (0.0010) -[2023-10-11 00:02:25,391][98560] Updated weights for policy 1, policy_version 80082 (0.0011) -[2023-10-11 00:02:25,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 164528128. Throughput: 0: 1723.7, 1: 1699.9. Samples: 41138690. Policy #0 lag: (min: 10.0, avg: 13.8, max: 42.0) -[2023-10-11 00:02:25,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.560')] -[2023-10-11 00:02:25,769][98560] Updated weights for policy 1, policy_version 80092 (0.0008) -[2023-10-11 00:02:27,858][98559] Updated weights for policy 0, policy_version 80610 (0.0007) -[2023-10-11 00:02:28,218][98559] Updated weights for policy 0, policy_version 80620 (0.0007) -[2023-10-11 00:02:28,579][98559] Updated weights for policy 0, policy_version 80630 (0.0008) -[2023-10-11 00:02:28,953][98559] Updated weights for policy 0, policy_version 80640 (0.0009) -[2023-10-11 00:02:29,905][98560] Updated weights for policy 1, policy_version 80102 (0.0010) -[2023-10-11 00:02:30,275][98560] Updated weights for policy 1, policy_version 80112 (0.0008) -[2023-10-11 00:02:30,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 164593664. Throughput: 0: 1700.4, 1: 1700.8. Samples: 41158750. Policy #0 lag: (min: 10.0, avg: 13.8, max: 42.0) -[2023-10-11 00:02:30,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.600')] -[2023-10-11 00:02:30,647][98560] Updated weights for policy 1, policy_version 80122 (0.0009) -[2023-10-11 00:02:32,903][98559] Updated weights for policy 0, policy_version 80650 (0.0007) -[2023-10-11 00:02:33,263][98559] Updated weights for policy 0, policy_version 80660 (0.0008) -[2023-10-11 00:02:33,628][98559] Updated weights for policy 0, policy_version 80670 (0.0010) -[2023-10-11 00:02:34,822][98560] Updated weights for policy 1, policy_version 80132 (0.0009) -[2023-10-11 00:02:35,188][98560] Updated weights for policy 1, policy_version 80142 (0.0008) -[2023-10-11 00:02:35,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 164659200. Throughput: 0: 1726.0, 1: 1703.2. Samples: 41179882. Policy #0 lag: (min: 10.0, avg: 13.8, max: 42.0) -[2023-10-11 00:02:35,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.560')] -[2023-10-11 00:02:35,560][98560] Updated weights for policy 1, policy_version 80152 (0.0007) -[2023-10-11 00:02:35,565][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000080672_82608128.pth... -[2023-10-11 00:02:35,604][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000079072_80969728.pth -[2023-10-11 00:02:35,848][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000080160_82083840.pth... -[2023-10-11 00:02:35,886][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000078560_80445440.pth -[2023-10-11 00:02:37,558][98559] Updated weights for policy 0, policy_version 80680 (0.0008) -[2023-10-11 00:02:37,923][98559] Updated weights for policy 0, policy_version 80690 (0.0007) -[2023-10-11 00:02:38,293][98559] Updated weights for policy 0, policy_version 80700 (0.0007) -[2023-10-11 00:02:39,534][98560] Updated weights for policy 1, policy_version 80162 (0.0009) -[2023-10-11 00:02:39,894][98560] Updated weights for policy 1, policy_version 80172 (0.0009) -[2023-10-11 00:02:40,259][98560] Updated weights for policy 1, policy_version 80182 (0.0010) -[2023-10-11 00:02:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 164724736. Throughput: 0: 1708.6, 1: 1708.1. Samples: 41189520. Policy #0 lag: (min: 10.0, avg: 13.8, max: 42.0) -[2023-10-11 00:02:40,557][97672] Avg episode reward: [(0, '-0.660'), (1, '22.480')] -[2023-10-11 00:02:40,633][98560] Updated weights for policy 1, policy_version 80192 (0.0007) -[2023-10-11 00:02:42,368][98559] Updated weights for policy 0, policy_version 80710 (0.0010) -[2023-10-11 00:02:42,745][98559] Updated weights for policy 0, policy_version 80720 (0.0008) -[2023-10-11 00:02:43,108][98559] Updated weights for policy 0, policy_version 80730 (0.0008) -[2023-10-11 00:02:44,535][98560] Updated weights for policy 1, policy_version 80202 (0.0007) -[2023-10-11 00:02:44,904][98560] Updated weights for policy 1, policy_version 80212 (0.0007) -[2023-10-11 00:02:45,271][98560] Updated weights for policy 1, policy_version 80222 (0.0009) -[2023-10-11 00:02:45,556][97672] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 164823040. Throughput: 0: 1712.7, 1: 1713.2. Samples: 41210594. Policy #0 lag: (min: 10.0, avg: 13.8, max: 42.0) -[2023-10-11 00:02:45,556][97672] Avg episode reward: [(0, '-0.660'), (1, '22.520')] -[2023-10-11 00:02:47,069][98559] Updated weights for policy 0, policy_version 80740 (0.0008) -[2023-10-11 00:02:47,432][98559] Updated weights for policy 0, policy_version 80750 (0.0008) -[2023-10-11 00:02:47,798][98559] Updated weights for policy 0, policy_version 80760 (0.0010) -[2023-10-11 00:02:49,347][98560] Updated weights for policy 1, policy_version 80232 (0.0009) -[2023-10-11 00:02:49,716][98560] Updated weights for policy 1, policy_version 80242 (0.0009) -[2023-10-11 00:02:50,075][98560] Updated weights for policy 1, policy_version 80252 (0.0009) -[2023-10-11 00:02:50,556][97672] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 164888576. Throughput: 0: 1725.8, 1: 1692.8. Samples: 41230922. Policy #0 lag: (min: 10.0, avg: 13.8, max: 42.0) -[2023-10-11 00:02:50,556][97672] Avg episode reward: [(0, '-0.660'), (1, '22.580')] -[2023-10-11 00:02:51,795][98559] Updated weights for policy 0, policy_version 80770 (0.0008) -[2023-10-11 00:02:52,154][98559] Updated weights for policy 0, policy_version 80780 (0.0010) -[2023-10-11 00:02:52,513][98559] Updated weights for policy 0, policy_version 80790 (0.0009) -[2023-10-11 00:02:52,875][98559] Updated weights for policy 0, policy_version 80800 (0.0010) -[2023-10-11 00:02:53,976][98560] Updated weights for policy 1, policy_version 80262 (0.0008) -[2023-10-11 00:02:54,352][98560] Updated weights for policy 1, policy_version 80272 (0.0007) -[2023-10-11 00:02:54,717][98560] Updated weights for policy 1, policy_version 80282 (0.0010) -[2023-10-11 00:02:55,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 164954112. Throughput: 0: 1697.9, 1: 1714.0. Samples: 41240930. Policy #0 lag: (min: 10.0, avg: 13.8, max: 42.0) -[2023-10-11 00:02:55,557][97672] Avg episode reward: [(0, '-0.660'), (1, '22.620')] -[2023-10-11 00:02:56,802][98559] Updated weights for policy 0, policy_version 80810 (0.0010) -[2023-10-11 00:02:57,164][98559] Updated weights for policy 0, policy_version 80820 (0.0011) -[2023-10-11 00:02:57,532][98559] Updated weights for policy 0, policy_version 80830 (0.0008) -[2023-10-11 00:02:58,598][98560] Updated weights for policy 1, policy_version 80292 (0.0008) -[2023-10-11 00:02:58,966][98560] Updated weights for policy 1, policy_version 80302 (0.0007) -[2023-10-11 00:02:59,322][98560] Updated weights for policy 1, policy_version 80312 (0.0007) -[2023-10-11 00:03:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 165019648. Throughput: 0: 1726.7, 1: 1707.9. Samples: 41261956. Policy #0 lag: (min: 10.0, avg: 13.8, max: 42.0) -[2023-10-11 00:03:00,556][97672] Avg episode reward: [(0, '-0.660'), (1, '22.660')] -[2023-10-11 00:03:01,563][98559] Updated weights for policy 0, policy_version 80840 (0.0008) -[2023-10-11 00:03:01,930][98559] Updated weights for policy 0, policy_version 80850 (0.0009) -[2023-10-11 00:03:02,290][98559] Updated weights for policy 0, policy_version 80860 (0.0009) -[2023-10-11 00:03:03,452][98560] Updated weights for policy 1, policy_version 80322 (0.0007) -[2023-10-11 00:03:03,820][98560] Updated weights for policy 1, policy_version 80332 (0.0008) -[2023-10-11 00:03:04,189][98560] Updated weights for policy 1, policy_version 80342 (0.0008) -[2023-10-11 00:03:04,556][98560] Updated weights for policy 1, policy_version 80352 (0.0008) -[2023-10-11 00:03:05,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 165085184. Throughput: 0: 1729.6, 1: 1677.2. Samples: 41281956. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-11 00:03:05,557][97672] Avg episode reward: [(0, '-0.660'), (1, '22.620')] -[2023-10-11 00:03:06,374][98559] Updated weights for policy 0, policy_version 80870 (0.0008) -[2023-10-11 00:03:06,738][98559] Updated weights for policy 0, policy_version 80880 (0.0008) -[2023-10-11 00:03:07,101][98559] Updated weights for policy 0, policy_version 80890 (0.0009) -[2023-10-11 00:03:08,495][98560] Updated weights for policy 1, policy_version 80362 (0.0010) -[2023-10-11 00:03:08,863][98560] Updated weights for policy 1, policy_version 80372 (0.0008) -[2023-10-11 00:03:09,241][98560] Updated weights for policy 1, policy_version 80382 (0.0008) -[2023-10-11 00:03:10,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 165150720. Throughput: 0: 1704.7, 1: 1711.8. Samples: 41292434. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-11 00:03:10,557][97672] Avg episode reward: [(0, '-0.660'), (1, '22.620')] -[2023-10-11 00:03:11,047][98559] Updated weights for policy 0, policy_version 80900 (0.0008) -[2023-10-11 00:03:11,419][98559] Updated weights for policy 0, policy_version 80910 (0.0008) -[2023-10-11 00:03:11,793][98559] Updated weights for policy 0, policy_version 80920 (0.0008) -[2023-10-11 00:03:13,499][98560] Updated weights for policy 1, policy_version 80392 (0.0008) -[2023-10-11 00:03:13,883][98560] Updated weights for policy 1, policy_version 80402 (0.0007) -[2023-10-11 00:03:14,239][98560] Updated weights for policy 1, policy_version 80412 (0.0007) -[2023-10-11 00:03:15,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 165216256. Throughput: 0: 1724.4, 1: 1694.3. Samples: 41312590. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-11 00:03:15,557][97672] Avg episode reward: [(0, '-0.660'), (1, '22.580')] -[2023-10-11 00:03:15,634][98559] Updated weights for policy 0, policy_version 80930 (0.0008) -[2023-10-11 00:03:16,001][98559] Updated weights for policy 0, policy_version 80940 (0.0007) -[2023-10-11 00:03:16,370][98559] Updated weights for policy 0, policy_version 80950 (0.0007) -[2023-10-11 00:03:16,736][98559] Updated weights for policy 0, policy_version 80960 (0.0007) -[2023-10-11 00:03:18,349][98560] Updated weights for policy 1, policy_version 80422 (0.0010) -[2023-10-11 00:03:18,714][98560] Updated weights for policy 1, policy_version 80432 (0.0010) -[2023-10-11 00:03:19,085][98560] Updated weights for policy 1, policy_version 80442 (0.0010) -[2023-10-11 00:03:20,508][98559] Updated weights for policy 0, policy_version 80970 (0.0008) -[2023-10-11 00:03:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 165281792. Throughput: 0: 1718.8, 1: 1675.6. Samples: 41332628. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-11 00:03:20,557][97672] Avg episode reward: [(0, '-0.660'), (1, '22.660')] -[2023-10-11 00:03:20,879][98559] Updated weights for policy 0, policy_version 80980 (0.0010) -[2023-10-11 00:03:21,247][98559] Updated weights for policy 0, policy_version 80990 (0.0007) -[2023-10-11 00:03:22,929][98560] Updated weights for policy 1, policy_version 80452 (0.0009) -[2023-10-11 00:03:23,297][98560] Updated weights for policy 1, policy_version 80462 (0.0010) -[2023-10-11 00:03:23,674][98560] Updated weights for policy 1, policy_version 80472 (0.0007) -[2023-10-11 00:03:25,266][98559] Updated weights for policy 0, policy_version 81000 (0.0008) -[2023-10-11 00:03:25,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 165347328. Throughput: 0: 1720.0, 1: 1706.4. Samples: 41343710. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-11 00:03:25,557][97672] Avg episode reward: [(0, '-0.760'), (1, '22.780')] -[2023-10-11 00:03:25,629][98559] Updated weights for policy 0, policy_version 81010 (0.0008) -[2023-10-11 00:03:25,991][98559] Updated weights for policy 0, policy_version 81020 (0.0007) -[2023-10-11 00:03:27,738][98560] Updated weights for policy 1, policy_version 80482 (0.0010) -[2023-10-11 00:03:28,108][98560] Updated weights for policy 1, policy_version 80492 (0.0007) -[2023-10-11 00:03:28,472][98560] Updated weights for policy 1, policy_version 80502 (0.0008) -[2023-10-11 00:03:28,833][98560] Updated weights for policy 1, policy_version 80512 (0.0008) -[2023-10-11 00:03:29,879][98559] Updated weights for policy 0, policy_version 81030 (0.0010) -[2023-10-11 00:03:30,246][98559] Updated weights for policy 0, policy_version 81040 (0.0009) -[2023-10-11 00:03:30,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 165412864. Throughput: 0: 1729.9, 1: 1680.2. Samples: 41364048. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-11 00:03:30,556][97672] Avg episode reward: [(0, '-0.760'), (1, '22.760')] -[2023-10-11 00:03:30,608][98559] Updated weights for policy 0, policy_version 81050 (0.0011) -[2023-10-11 00:03:32,842][98560] Updated weights for policy 1, policy_version 80522 (0.0008) -[2023-10-11 00:03:33,208][98560] Updated weights for policy 1, policy_version 80532 (0.0010) -[2023-10-11 00:03:33,574][98560] Updated weights for policy 1, policy_version 80542 (0.0009) -[2023-10-11 00:03:34,483][98559] Updated weights for policy 0, policy_version 81060 (0.0010) -[2023-10-11 00:03:34,846][98559] Updated weights for policy 0, policy_version 81070 (0.0010) -[2023-10-11 00:03:35,206][98559] Updated weights for policy 0, policy_version 81080 (0.0011) -[2023-10-11 00:03:35,556][97672] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 165511168. Throughput: 0: 1706.8, 1: 1689.1. Samples: 41383736. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-11 00:03:35,557][97672] Avg episode reward: [(0, '-0.760'), (1, '22.720')] -[2023-10-11 00:03:37,680][98560] Updated weights for policy 1, policy_version 80552 (0.0009) -[2023-10-11 00:03:38,036][98560] Updated weights for policy 1, policy_version 80562 (0.0009) -[2023-10-11 00:03:38,412][98560] Updated weights for policy 1, policy_version 80572 (0.0008) -[2023-10-11 00:03:39,177][98559] Updated weights for policy 0, policy_version 81090 (0.0007) -[2023-10-11 00:03:39,545][98559] Updated weights for policy 0, policy_version 81100 (0.0008) -[2023-10-11 00:03:39,903][98559] Updated weights for policy 0, policy_version 81110 (0.0008) -[2023-10-11 00:03:40,264][98559] Updated weights for policy 0, policy_version 81120 (0.0007) -[2023-10-11 00:03:40,556][97672] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 165576704. Throughput: 0: 1734.4, 1: 1691.4. Samples: 41395092. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-11 00:03:40,557][97672] Avg episode reward: [(0, '-0.760'), (1, '22.720')] -[2023-10-11 00:03:42,285][98560] Updated weights for policy 1, policy_version 80582 (0.0007) -[2023-10-11 00:03:42,651][98560] Updated weights for policy 1, policy_version 80592 (0.0007) -[2023-10-11 00:03:43,017][98560] Updated weights for policy 1, policy_version 80602 (0.0009) -[2023-10-11 00:03:44,443][98559] Updated weights for policy 0, policy_version 81130 (0.0009) -[2023-10-11 00:03:44,804][98559] Updated weights for policy 0, policy_version 81140 (0.0008) -[2023-10-11 00:03:45,183][98559] Updated weights for policy 0, policy_version 81150 (0.0008) -[2023-10-11 00:03:45,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 165642240. Throughput: 0: 1725.8, 1: 1674.9. Samples: 41414988. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-11 00:03:45,557][97672] Avg episode reward: [(0, '-0.720'), (1, '22.620')] -[2023-10-11 00:03:46,990][98560] Updated weights for policy 1, policy_version 80612 (0.0008) -[2023-10-11 00:03:47,353][98560] Updated weights for policy 1, policy_version 80622 (0.0009) -[2023-10-11 00:03:47,724][98560] Updated weights for policy 1, policy_version 80632 (0.0009) -[2023-10-11 00:03:49,158][98559] Updated weights for policy 0, policy_version 81160 (0.0007) -[2023-10-11 00:03:49,523][98559] Updated weights for policy 0, policy_version 81170 (0.0009) -[2023-10-11 00:03:49,880][98559] Updated weights for policy 0, policy_version 81180 (0.0010) -[2023-10-11 00:03:50,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 165707776. Throughput: 0: 1703.6, 1: 1699.6. Samples: 41435100. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-11 00:03:50,556][97672] Avg episode reward: [(0, '-0.720'), (1, '22.620')] -[2023-10-11 00:03:51,666][98560] Updated weights for policy 1, policy_version 80642 (0.0008) -[2023-10-11 00:03:52,029][98560] Updated weights for policy 1, policy_version 80652 (0.0007) -[2023-10-11 00:03:52,399][98560] Updated weights for policy 1, policy_version 80662 (0.0007) -[2023-10-11 00:03:52,768][98560] Updated weights for policy 1, policy_version 80672 (0.0007) -[2023-10-11 00:03:53,836][98559] Updated weights for policy 0, policy_version 81190 (0.0008) -[2023-10-11 00:03:54,194][98559] Updated weights for policy 0, policy_version 81200 (0.0009) -[2023-10-11 00:03:54,562][98559] Updated weights for policy 0, policy_version 81210 (0.0011) -[2023-10-11 00:03:55,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 165773312. Throughput: 0: 1738.0, 1: 1674.3. Samples: 41445986. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-11 00:03:55,556][97672] Avg episode reward: [(0, '-0.720'), (1, '22.520')] -[2023-10-11 00:03:56,894][98560] Updated weights for policy 1, policy_version 80682 (0.0008) -[2023-10-11 00:03:57,263][98560] Updated weights for policy 1, policy_version 80692 (0.0007) -[2023-10-11 00:03:57,623][98560] Updated weights for policy 1, policy_version 80702 (0.0007) -[2023-10-11 00:03:58,498][98559] Updated weights for policy 0, policy_version 81220 (0.0010) -[2023-10-11 00:03:58,867][98559] Updated weights for policy 0, policy_version 81230 (0.0010) -[2023-10-11 00:03:59,236][98559] Updated weights for policy 0, policy_version 81240 (0.0009) -[2023-10-11 00:04:00,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 165838848. Throughput: 0: 1709.5, 1: 1689.2. Samples: 41465532. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-11 00:04:00,557][97672] Avg episode reward: [(0, '-0.720'), (1, '22.480')] -[2023-10-11 00:04:01,921][98560] Updated weights for policy 1, policy_version 80712 (0.0008) -[2023-10-11 00:04:02,303][98560] Updated weights for policy 1, policy_version 80722 (0.0007) -[2023-10-11 00:04:02,674][98560] Updated weights for policy 1, policy_version 80732 (0.0008) -[2023-10-11 00:04:03,313][98559] Updated weights for policy 0, policy_version 81250 (0.0009) -[2023-10-11 00:04:03,674][98559] Updated weights for policy 0, policy_version 81260 (0.0008) -[2023-10-11 00:04:04,040][98559] Updated weights for policy 0, policy_version 81270 (0.0009) -[2023-10-11 00:04:04,405][98559] Updated weights for policy 0, policy_version 81280 (0.0011) -[2023-10-11 00:04:05,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 165904384. Throughput: 0: 1701.5, 1: 1704.1. Samples: 41485878. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-11 00:04:05,557][97672] Avg episode reward: [(0, '-0.720'), (1, '22.420')] -[2023-10-11 00:04:06,604][98560] Updated weights for policy 1, policy_version 80742 (0.0008) -[2023-10-11 00:04:06,962][98560] Updated weights for policy 1, policy_version 80752 (0.0008) -[2023-10-11 00:04:07,336][98560] Updated weights for policy 1, policy_version 80762 (0.0010) -[2023-10-11 00:04:08,324][98559] Updated weights for policy 0, policy_version 81290 (0.0007) -[2023-10-11 00:04:08,698][98559] Updated weights for policy 0, policy_version 81300 (0.0007) -[2023-10-11 00:04:09,064][98559] Updated weights for policy 0, policy_version 81310 (0.0007) -[2023-10-11 00:04:10,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 165969920. Throughput: 0: 1718.3, 1: 1670.3. Samples: 41496194. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-11 00:04:10,557][97672] Avg episode reward: [(0, '-0.720'), (1, '22.420')] -[2023-10-11 00:04:11,515][98560] Updated weights for policy 1, policy_version 80772 (0.0009) -[2023-10-11 00:04:11,880][98560] Updated weights for policy 1, policy_version 80782 (0.0008) -[2023-10-11 00:04:12,255][98560] Updated weights for policy 1, policy_version 80792 (0.0009) -[2023-10-11 00:04:13,193][98559] Updated weights for policy 0, policy_version 81320 (0.0009) -[2023-10-11 00:04:13,557][98559] Updated weights for policy 0, policy_version 81330 (0.0010) -[2023-10-11 00:04:13,924][98559] Updated weights for policy 0, policy_version 81340 (0.0009) -[2023-10-11 00:04:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 166035456. Throughput: 0: 1685.7, 1: 1693.1. Samples: 41516094. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-11 00:04:15,557][97672] Avg episode reward: [(0, '-0.720'), (1, '22.360')] -[2023-10-11 00:04:16,225][98560] Updated weights for policy 1, policy_version 80802 (0.0008) -[2023-10-11 00:04:16,596][98560] Updated weights for policy 1, policy_version 80812 (0.0007) -[2023-10-11 00:04:16,963][98560] Updated weights for policy 1, policy_version 80822 (0.0008) -[2023-10-11 00:04:17,326][98560] Updated weights for policy 1, policy_version 80832 (0.0008) -[2023-10-11 00:04:18,056][98559] Updated weights for policy 0, policy_version 81350 (0.0009) -[2023-10-11 00:04:18,425][98559] Updated weights for policy 0, policy_version 81360 (0.0010) -[2023-10-11 00:04:18,799][98559] Updated weights for policy 0, policy_version 81370 (0.0007) -[2023-10-11 00:04:20,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 166100992. Throughput: 0: 1705.0, 1: 1700.8. Samples: 41536994. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-11 00:04:20,556][97672] Avg episode reward: [(0, '-0.720'), (1, '22.320')] -[2023-10-11 00:04:21,237][98560] Updated weights for policy 1, policy_version 80842 (0.0008) -[2023-10-11 00:04:21,612][98560] Updated weights for policy 1, policy_version 80852 (0.0007) -[2023-10-11 00:04:21,985][98560] Updated weights for policy 1, policy_version 80862 (0.0010) -[2023-10-11 00:04:22,734][98559] Updated weights for policy 0, policy_version 81380 (0.0008) -[2023-10-11 00:04:23,092][98559] Updated weights for policy 0, policy_version 81390 (0.0007) -[2023-10-11 00:04:23,460][98559] Updated weights for policy 0, policy_version 81400 (0.0008) -[2023-10-11 00:04:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 166166528. Throughput: 0: 1687.6, 1: 1684.0. Samples: 41546812. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-11 00:04:25,557][97672] Avg episode reward: [(0, '-0.720'), (1, '22.320')] -[2023-10-11 00:04:26,141][98560] Updated weights for policy 1, policy_version 80872 (0.0008) -[2023-10-11 00:04:26,507][98560] Updated weights for policy 1, policy_version 80882 (0.0010) -[2023-10-11 00:04:26,878][98560] Updated weights for policy 1, policy_version 80892 (0.0011) -[2023-10-11 00:04:27,421][98559] Updated weights for policy 0, policy_version 81410 (0.0008) -[2023-10-11 00:04:27,779][98559] Updated weights for policy 0, policy_version 81420 (0.0008) -[2023-10-11 00:04:28,154][98559] Updated weights for policy 0, policy_version 81430 (0.0009) -[2023-10-11 00:04:28,520][98559] Updated weights for policy 0, policy_version 81440 (0.0008) -[2023-10-11 00:04:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 166232064. Throughput: 0: 1685.0, 1: 1700.0. Samples: 41567312. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-11 00:04:30,556][97672] Avg episode reward: [(0, '-0.720'), (1, '22.320')] -[2023-10-11 00:04:30,886][98560] Updated weights for policy 1, policy_version 80902 (0.0009) -[2023-10-11 00:04:31,255][98560] Updated weights for policy 1, policy_version 80912 (0.0010) -[2023-10-11 00:04:31,627][98560] Updated weights for policy 1, policy_version 80922 (0.0011) -[2023-10-11 00:04:32,476][98559] Updated weights for policy 0, policy_version 81450 (0.0007) -[2023-10-11 00:04:32,855][98559] Updated weights for policy 0, policy_version 81460 (0.0008) -[2023-10-11 00:04:33,232][98559] Updated weights for policy 0, policy_version 81470 (0.0008) -[2023-10-11 00:04:35,406][98560] Updated weights for policy 1, policy_version 80932 (0.0009) -[2023-10-11 00:04:35,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 13662.6). Total num frames: 166297600. Throughput: 0: 1704.8, 1: 1701.6. Samples: 41588388. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-11 00:04:35,556][97672] Avg episode reward: [(0, '-0.720'), (1, '22.340')] -[2023-10-11 00:04:35,567][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000081472_83427328.pth... -[2023-10-11 00:04:35,600][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000079872_81788928.pth -[2023-10-11 00:04:35,775][98560] Updated weights for policy 1, policy_version 80942 (0.0009) -[2023-10-11 00:04:36,153][98560] Updated weights for policy 1, policy_version 80952 (0.0011) -[2023-10-11 00:04:36,442][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000080960_82903040.pth... -[2023-10-11 00:04:36,472][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000079360_81264640.pth -[2023-10-11 00:04:37,254][98559] Updated weights for policy 0, policy_version 81480 (0.0010) -[2023-10-11 00:04:37,626][98559] Updated weights for policy 0, policy_version 81490 (0.0010) -[2023-10-11 00:04:37,981][98559] Updated weights for policy 0, policy_version 81500 (0.0011) -[2023-10-11 00:04:40,009][98560] Updated weights for policy 1, policy_version 80962 (0.0010) -[2023-10-11 00:04:40,370][98560] Updated weights for policy 1, policy_version 80972 (0.0011) -[2023-10-11 00:04:40,556][97672] Fps is (10 sec: 13106.7, 60 sec: 13107.1, 300 sec: 13662.6). Total num frames: 166363136. Throughput: 0: 1671.2, 1: 1699.7. Samples: 41597676. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-11 00:04:40,557][97672] Avg episode reward: [(0, '-0.720'), (1, '22.340')] -[2023-10-11 00:04:40,744][98560] Updated weights for policy 1, policy_version 80982 (0.0008) -[2023-10-11 00:04:41,103][98560] Updated weights for policy 1, policy_version 80992 (0.0007) -[2023-10-11 00:04:42,092][98559] Updated weights for policy 0, policy_version 81510 (0.0009) -[2023-10-11 00:04:42,459][98559] Updated weights for policy 0, policy_version 81520 (0.0008) -[2023-10-11 00:04:42,821][98559] Updated weights for policy 0, policy_version 81530 (0.0007) -[2023-10-11 00:04:45,092][98560] Updated weights for policy 1, policy_version 81002 (0.0007) -[2023-10-11 00:04:45,465][98560] Updated weights for policy 1, policy_version 81012 (0.0008) -[2023-10-11 00:04:45,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 166428672. Throughput: 0: 1694.8, 1: 1709.4. Samples: 41618722. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-11 00:04:45,557][97672] Avg episode reward: [(0, '-0.720'), (1, '22.400')] -[2023-10-11 00:04:45,840][98560] Updated weights for policy 1, policy_version 81022 (0.0008) -[2023-10-11 00:04:46,749][98559] Updated weights for policy 0, policy_version 81540 (0.0009) -[2023-10-11 00:04:47,112][98559] Updated weights for policy 0, policy_version 81550 (0.0010) -[2023-10-11 00:04:47,485][98559] Updated weights for policy 0, policy_version 81560 (0.0008) -[2023-10-11 00:04:50,024][98560] Updated weights for policy 1, policy_version 81032 (0.0008) -[2023-10-11 00:04:50,404][98560] Updated weights for policy 1, policy_version 81042 (0.0008) -[2023-10-11 00:04:50,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 166494208. Throughput: 0: 1703.3, 1: 1712.9. Samples: 41639602. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-10-11 00:04:50,557][97672] Avg episode reward: [(0, '-0.720'), (1, '22.400')] -[2023-10-11 00:04:50,769][98560] Updated weights for policy 1, policy_version 81052 (0.0010) -[2023-10-11 00:04:51,603][98559] Updated weights for policy 0, policy_version 81570 (0.0010) -[2023-10-11 00:04:51,964][98559] Updated weights for policy 0, policy_version 81580 (0.0007) -[2023-10-11 00:04:52,325][98559] Updated weights for policy 0, policy_version 81590 (0.0009) -[2023-10-11 00:04:52,684][98559] Updated weights for policy 0, policy_version 81600 (0.0007) -[2023-10-11 00:04:54,704][98560] Updated weights for policy 1, policy_version 81062 (0.0009) -[2023-10-11 00:04:55,066][98560] Updated weights for policy 1, policy_version 81072 (0.0009) -[2023-10-11 00:04:55,439][98560] Updated weights for policy 1, policy_version 81082 (0.0007) -[2023-10-11 00:04:55,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.1, 300 sec: 13662.6). Total num frames: 166559744. Throughput: 0: 1678.2, 1: 1711.8. Samples: 41648742. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-10-11 00:04:55,557][97672] Avg episode reward: [(0, '-0.700'), (1, '22.420')] -[2023-10-11 00:04:56,676][98559] Updated weights for policy 0, policy_version 81610 (0.0011) -[2023-10-11 00:04:57,043][98559] Updated weights for policy 0, policy_version 81620 (0.0010) -[2023-10-11 00:04:57,403][98559] Updated weights for policy 0, policy_version 81630 (0.0009) -[2023-10-11 00:04:59,621][98560] Updated weights for policy 1, policy_version 81092 (0.0010) -[2023-10-11 00:04:59,989][98560] Updated weights for policy 1, policy_version 81102 (0.0008) -[2023-10-11 00:05:00,351][98560] Updated weights for policy 1, policy_version 81112 (0.0007) -[2023-10-11 00:05:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 166625280. Throughput: 0: 1705.6, 1: 1710.1. Samples: 41669800. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-10-11 00:05:00,557][97672] Avg episode reward: [(0, '-0.700'), (1, '22.460')] -[2023-10-11 00:05:01,514][98559] Updated weights for policy 0, policy_version 81640 (0.0009) -[2023-10-11 00:05:01,872][98559] Updated weights for policy 0, policy_version 81650 (0.0010) -[2023-10-11 00:05:02,243][98559] Updated weights for policy 0, policy_version 81660 (0.0010) -[2023-10-11 00:05:04,273][98560] Updated weights for policy 1, policy_version 81122 (0.0008) -[2023-10-11 00:05:04,626][98560] Updated weights for policy 1, policy_version 81132 (0.0009) -[2023-10-11 00:05:04,999][98560] Updated weights for policy 1, policy_version 81142 (0.0008) -[2023-10-11 00:05:05,367][98560] Updated weights for policy 1, policy_version 81152 (0.0008) -[2023-10-11 00:05:05,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 166723584. Throughput: 0: 1710.6, 1: 1699.8. Samples: 41690460. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-10-11 00:05:05,557][97672] Avg episode reward: [(0, '-0.700'), (1, '22.500')] -[2023-10-11 00:05:06,264][98559] Updated weights for policy 0, policy_version 81670 (0.0009) -[2023-10-11 00:05:06,623][98559] Updated weights for policy 0, policy_version 81680 (0.0007) -[2023-10-11 00:05:06,982][98559] Updated weights for policy 0, policy_version 81690 (0.0007) -[2023-10-11 00:05:09,311][98560] Updated weights for policy 1, policy_version 81162 (0.0009) -[2023-10-11 00:05:09,674][98560] Updated weights for policy 1, policy_version 81172 (0.0008) -[2023-10-11 00:05:10,034][98560] Updated weights for policy 1, policy_version 81182 (0.0010) -[2023-10-11 00:05:10,556][97672] Fps is (10 sec: 16383.6, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 166789120. Throughput: 0: 1696.8, 1: 1711.4. Samples: 41700182. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-10-11 00:05:10,558][97672] Avg episode reward: [(0, '-0.700'), (1, '22.520')] -[2023-10-11 00:05:10,947][98559] Updated weights for policy 0, policy_version 81700 (0.0009) -[2023-10-11 00:05:11,311][98559] Updated weights for policy 0, policy_version 81710 (0.0008) -[2023-10-11 00:05:11,675][98559] Updated weights for policy 0, policy_version 81720 (0.0007) -[2023-10-11 00:05:13,988][98560] Updated weights for policy 1, policy_version 81192 (0.0007) -[2023-10-11 00:05:14,353][98560] Updated weights for policy 1, policy_version 81202 (0.0009) -[2023-10-11 00:05:14,720][98560] Updated weights for policy 1, policy_version 81212 (0.0010) -[2023-10-11 00:05:15,551][98559] Updated weights for policy 0, policy_version 81730 (0.0008) -[2023-10-11 00:05:15,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 166854656. Throughput: 0: 1711.6, 1: 1718.2. Samples: 41721652. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-10-11 00:05:15,556][97672] Avg episode reward: [(0, '-0.700'), (1, '22.560')] -[2023-10-11 00:05:15,921][98559] Updated weights for policy 0, policy_version 81740 (0.0010) -[2023-10-11 00:05:16,285][98559] Updated weights for policy 0, policy_version 81750 (0.0010) -[2023-10-11 00:05:16,661][98559] Updated weights for policy 0, policy_version 81760 (0.0010) -[2023-10-11 00:05:18,509][98560] Updated weights for policy 1, policy_version 81222 (0.0007) -[2023-10-11 00:05:18,882][98560] Updated weights for policy 1, policy_version 81232 (0.0009) -[2023-10-11 00:05:19,250][98560] Updated weights for policy 1, policy_version 81242 (0.0009) -[2023-10-11 00:05:20,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 166920192. Throughput: 0: 1708.5, 1: 1688.6. Samples: 41741256. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-10-11 00:05:20,557][97672] Avg episode reward: [(0, '-0.700'), (1, '22.580')] -[2023-10-11 00:05:20,734][98559] Updated weights for policy 0, policy_version 81770 (0.0011) -[2023-10-11 00:05:21,090][98559] Updated weights for policy 0, policy_version 81780 (0.0009) -[2023-10-11 00:05:21,461][98559] Updated weights for policy 0, policy_version 81790 (0.0009) -[2023-10-11 00:05:23,278][98560] Updated weights for policy 1, policy_version 81252 (0.0008) -[2023-10-11 00:05:23,632][98560] Updated weights for policy 1, policy_version 81262 (0.0011) -[2023-10-11 00:05:23,995][98560] Updated weights for policy 1, policy_version 81272 (0.0011) -[2023-10-11 00:05:25,526][98559] Updated weights for policy 0, policy_version 81800 (0.0008) -[2023-10-11 00:05:25,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 166985728. Throughput: 0: 1710.0, 1: 1715.3. Samples: 41751814. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-10-11 00:05:25,557][97672] Avg episode reward: [(0, '-0.720'), (1, '22.580')] -[2023-10-11 00:05:25,894][98559] Updated weights for policy 0, policy_version 81810 (0.0008) -[2023-10-11 00:05:26,269][98559] Updated weights for policy 0, policy_version 81820 (0.0008) -[2023-10-11 00:05:28,062][98560] Updated weights for policy 1, policy_version 81282 (0.0009) -[2023-10-11 00:05:28,422][98560] Updated weights for policy 1, policy_version 81292 (0.0008) -[2023-10-11 00:05:28,780][98560] Updated weights for policy 1, policy_version 81302 (0.0008) -[2023-10-11 00:05:29,141][98560] Updated weights for policy 1, policy_version 81312 (0.0008) -[2023-10-11 00:05:30,291][98559] Updated weights for policy 0, policy_version 81830 (0.0008) -[2023-10-11 00:05:30,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 167051264. Throughput: 0: 1715.4, 1: 1694.6. Samples: 41772170. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-10-11 00:05:30,557][97672] Avg episode reward: [(0, '-0.720'), (1, '22.580')] -[2023-10-11 00:05:30,655][98559] Updated weights for policy 0, policy_version 81840 (0.0009) -[2023-10-11 00:05:31,014][98559] Updated weights for policy 0, policy_version 81850 (0.0010) -[2023-10-11 00:05:33,343][98560] Updated weights for policy 1, policy_version 81322 (0.0009) -[2023-10-11 00:05:33,718][98560] Updated weights for policy 1, policy_version 81332 (0.0010) -[2023-10-11 00:05:34,087][98560] Updated weights for policy 1, policy_version 81342 (0.0009) -[2023-10-11 00:05:35,020][98559] Updated weights for policy 0, policy_version 81860 (0.0008) -[2023-10-11 00:05:35,382][98559] Updated weights for policy 0, policy_version 81870 (0.0008) -[2023-10-11 00:05:35,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 167116800. Throughput: 0: 1706.0, 1: 1680.9. Samples: 41792012. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-10-11 00:05:35,557][97672] Avg episode reward: [(0, '-0.720'), (1, '22.540')] -[2023-10-11 00:05:35,736][98559] Updated weights for policy 0, policy_version 81880 (0.0008) -[2023-10-11 00:05:38,183][98560] Updated weights for policy 1, policy_version 81352 (0.0008) -[2023-10-11 00:05:38,560][98560] Updated weights for policy 1, policy_version 81362 (0.0010) -[2023-10-11 00:05:38,922][98560] Updated weights for policy 1, policy_version 81372 (0.0011) -[2023-10-11 00:05:39,700][98559] Updated weights for policy 0, policy_version 81890 (0.0010) -[2023-10-11 00:05:40,065][98559] Updated weights for policy 0, policy_version 81900 (0.0009) -[2023-10-11 00:05:40,435][98559] Updated weights for policy 0, policy_version 81910 (0.0007) -[2023-10-11 00:05:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 167182336. Throughput: 0: 1719.2, 1: 1711.6. Samples: 41803126. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-10-11 00:05:40,557][97672] Avg episode reward: [(0, '-0.720'), (1, '22.560')] -[2023-10-11 00:05:40,798][98559] Updated weights for policy 0, policy_version 81920 (0.0009) -[2023-10-11 00:05:42,905][98560] Updated weights for policy 1, policy_version 81382 (0.0009) -[2023-10-11 00:05:43,273][98560] Updated weights for policy 1, policy_version 81392 (0.0010) -[2023-10-11 00:05:43,648][98560] Updated weights for policy 1, policy_version 81402 (0.0008) -[2023-10-11 00:05:44,714][98559] Updated weights for policy 0, policy_version 81930 (0.0010) -[2023-10-11 00:05:45,083][98559] Updated weights for policy 0, policy_version 81940 (0.0008) -[2023-10-11 00:05:45,444][98559] Updated weights for policy 0, policy_version 81950 (0.0007) -[2023-10-11 00:05:45,556][97672] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 167280640. Throughput: 0: 1721.7, 1: 1682.3. Samples: 41822978. Policy #0 lag: (min: 4.0, avg: 11.3, max: 36.0) -[2023-10-11 00:05:45,557][97672] Avg episode reward: [(0, '-0.720'), (1, '22.540')] -[2023-10-11 00:05:47,574][98560] Updated weights for policy 1, policy_version 81412 (0.0008) -[2023-10-11 00:05:47,931][98560] Updated weights for policy 1, policy_version 81422 (0.0009) -[2023-10-11 00:05:48,296][98560] Updated weights for policy 1, policy_version 81432 (0.0007) -[2023-10-11 00:05:49,496][98559] Updated weights for policy 0, policy_version 81960 (0.0008) -[2023-10-11 00:05:49,859][98559] Updated weights for policy 0, policy_version 81970 (0.0009) -[2023-10-11 00:05:50,231][98559] Updated weights for policy 0, policy_version 81980 (0.0009) -[2023-10-11 00:05:50,556][97672] Fps is (10 sec: 16383.4, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 167346176. Throughput: 0: 1696.0, 1: 1691.2. Samples: 41842886. Policy #0 lag: (min: 4.0, avg: 11.3, max: 36.0) -[2023-10-11 00:05:50,558][97672] Avg episode reward: [(0, '-0.720'), (1, '22.480')] -[2023-10-11 00:05:52,392][98560] Updated weights for policy 1, policy_version 81442 (0.0008) -[2023-10-11 00:05:52,762][98560] Updated weights for policy 1, policy_version 81452 (0.0008) -[2023-10-11 00:05:53,134][98560] Updated weights for policy 1, policy_version 81462 (0.0008) -[2023-10-11 00:05:53,501][98560] Updated weights for policy 1, policy_version 81472 (0.0009) -[2023-10-11 00:05:54,188][98559] Updated weights for policy 0, policy_version 81990 (0.0009) -[2023-10-11 00:05:54,552][98559] Updated weights for policy 0, policy_version 82000 (0.0011) -[2023-10-11 00:05:54,929][98559] Updated weights for policy 0, policy_version 82010 (0.0010) -[2023-10-11 00:05:55,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 167411712. Throughput: 0: 1726.3, 1: 1697.2. Samples: 41854240. Policy #0 lag: (min: 4.0, avg: 11.3, max: 36.0) -[2023-10-11 00:05:55,556][97672] Avg episode reward: [(0, '-0.720'), (1, '22.440')] -[2023-10-11 00:05:57,345][98560] Updated weights for policy 1, policy_version 81482 (0.0008) -[2023-10-11 00:05:57,725][98560] Updated weights for policy 1, policy_version 81492 (0.0010) -[2023-10-11 00:05:58,086][98560] Updated weights for policy 1, policy_version 81502 (0.0009) -[2023-10-11 00:05:58,925][98559] Updated weights for policy 0, policy_version 82020 (0.0009) -[2023-10-11 00:05:59,292][98559] Updated weights for policy 0, policy_version 82030 (0.0010) -[2023-10-11 00:05:59,654][98559] Updated weights for policy 0, policy_version 82040 (0.0008) -[2023-10-11 00:06:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 167477248. Throughput: 0: 1707.3, 1: 1680.3. Samples: 41874096. Policy #0 lag: (min: 4.0, avg: 11.3, max: 36.0) -[2023-10-11 00:06:00,558][97672] Avg episode reward: [(0, '-0.720'), (1, '22.440')] -[2023-10-11 00:06:02,043][98560] Updated weights for policy 1, policy_version 81512 (0.0008) -[2023-10-11 00:06:02,426][98560] Updated weights for policy 1, policy_version 81522 (0.0010) -[2023-10-11 00:06:02,792][98560] Updated weights for policy 1, policy_version 81532 (0.0010) -[2023-10-11 00:06:03,594][98559] Updated weights for policy 0, policy_version 82050 (0.0008) -[2023-10-11 00:06:03,953][98559] Updated weights for policy 0, policy_version 82060 (0.0009) -[2023-10-11 00:06:04,307][98559] Updated weights for policy 0, policy_version 82070 (0.0008) -[2023-10-11 00:06:04,676][98559] Updated weights for policy 0, policy_version 82080 (0.0009) -[2023-10-11 00:06:05,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 167542784. Throughput: 0: 1698.0, 1: 1711.0. Samples: 41894660. Policy #0 lag: (min: 4.0, avg: 11.3, max: 36.0) -[2023-10-11 00:06:05,556][97672] Avg episode reward: [(0, '-0.740'), (1, '22.440')] -[2023-10-11 00:06:06,790][98560] Updated weights for policy 1, policy_version 81542 (0.0009) -[2023-10-11 00:06:07,155][98560] Updated weights for policy 1, policy_version 81552 (0.0008) -[2023-10-11 00:06:07,523][98560] Updated weights for policy 1, policy_version 81562 (0.0008) -[2023-10-11 00:06:08,558][98559] Updated weights for policy 0, policy_version 82090 (0.0007) -[2023-10-11 00:06:08,936][98559] Updated weights for policy 0, policy_version 82100 (0.0008) -[2023-10-11 00:06:09,297][98559] Updated weights for policy 0, policy_version 82110 (0.0008) -[2023-10-11 00:06:10,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 167608320. Throughput: 0: 1725.3, 1: 1682.9. Samples: 41905184. Policy #0 lag: (min: 4.0, avg: 11.3, max: 36.0) -[2023-10-11 00:06:10,557][97672] Avg episode reward: [(0, '-0.740'), (1, '22.460')] -[2023-10-11 00:06:11,799][98560] Updated weights for policy 1, policy_version 81572 (0.0009) -[2023-10-11 00:06:12,172][98560] Updated weights for policy 1, policy_version 81582 (0.0009) -[2023-10-11 00:06:12,536][98560] Updated weights for policy 1, policy_version 81592 (0.0008) -[2023-10-11 00:06:13,207][98559] Updated weights for policy 0, policy_version 82120 (0.0010) -[2023-10-11 00:06:13,576][98559] Updated weights for policy 0, policy_version 82130 (0.0007) -[2023-10-11 00:06:13,936][98559] Updated weights for policy 0, policy_version 82140 (0.0008) -[2023-10-11 00:06:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 167673856. Throughput: 0: 1699.3, 1: 1696.0. Samples: 41924956. Policy #0 lag: (min: 4.0, avg: 11.3, max: 36.0) -[2023-10-11 00:06:15,556][97672] Avg episode reward: [(0, '-0.740'), (1, '22.520')] -[2023-10-11 00:06:16,595][98560] Updated weights for policy 1, policy_version 81602 (0.0009) -[2023-10-11 00:06:16,964][98560] Updated weights for policy 1, policy_version 81612 (0.0008) -[2023-10-11 00:06:17,322][98560] Updated weights for policy 1, policy_version 81622 (0.0010) -[2023-10-11 00:06:17,689][98560] Updated weights for policy 1, policy_version 81632 (0.0007) -[2023-10-11 00:06:17,956][98559] Updated weights for policy 0, policy_version 82150 (0.0010) -[2023-10-11 00:06:18,334][98559] Updated weights for policy 0, policy_version 82160 (0.0010) -[2023-10-11 00:06:18,691][98559] Updated weights for policy 0, policy_version 82170 (0.0009) -[2023-10-11 00:06:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 167739392. Throughput: 0: 1709.6, 1: 1711.7. Samples: 41945972. Policy #0 lag: (min: 4.0, avg: 11.3, max: 36.0) -[2023-10-11 00:06:20,556][97672] Avg episode reward: [(0, '-0.740'), (1, '22.580')] -[2023-10-11 00:06:21,883][98560] Updated weights for policy 1, policy_version 81642 (0.0009) -[2023-10-11 00:06:22,251][98560] Updated weights for policy 1, policy_version 81652 (0.0009) -[2023-10-11 00:06:22,459][98559] Updated weights for policy 0, policy_version 82180 (0.0010) -[2023-10-11 00:06:22,624][98560] Updated weights for policy 1, policy_version 81662 (0.0008) -[2023-10-11 00:06:22,835][98559] Updated weights for policy 0, policy_version 82190 (0.0009) -[2023-10-11 00:06:23,195][98559] Updated weights for policy 0, policy_version 82200 (0.0007) -[2023-10-11 00:06:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 167804928. Throughput: 0: 1706.6, 1: 1678.5. Samples: 41955456. Policy #0 lag: (min: 4.0, avg: 11.3, max: 36.0) -[2023-10-11 00:06:25,556][97672] Avg episode reward: [(0, '-0.740'), (1, '22.600')] -[2023-10-11 00:06:26,533][98560] Updated weights for policy 1, policy_version 81672 (0.0009) -[2023-10-11 00:06:26,920][98560] Updated weights for policy 1, policy_version 81682 (0.0007) -[2023-10-11 00:06:27,162][98559] Updated weights for policy 0, policy_version 82210 (0.0008) -[2023-10-11 00:06:27,279][98560] Updated weights for policy 1, policy_version 81692 (0.0009) -[2023-10-11 00:06:27,532][98559] Updated weights for policy 0, policy_version 82220 (0.0008) -[2023-10-11 00:06:27,906][98559] Updated weights for policy 0, policy_version 82230 (0.0009) -[2023-10-11 00:06:28,264][98559] Updated weights for policy 0, policy_version 82240 (0.0008) -[2023-10-11 00:06:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 167870464. Throughput: 0: 1697.9, 1: 1707.9. Samples: 41976238. Policy #0 lag: (min: 4.0, avg: 11.3, max: 36.0) -[2023-10-11 00:06:30,556][97672] Avg episode reward: [(0, '-0.740'), (1, '22.580')] -[2023-10-11 00:06:31,204][98560] Updated weights for policy 1, policy_version 81702 (0.0008) -[2023-10-11 00:06:31,571][98560] Updated weights for policy 1, policy_version 81712 (0.0009) -[2023-10-11 00:06:31,931][98560] Updated weights for policy 1, policy_version 81722 (0.0009) -[2023-10-11 00:06:32,304][98559] Updated weights for policy 0, policy_version 82250 (0.0009) -[2023-10-11 00:06:32,676][98559] Updated weights for policy 0, policy_version 82260 (0.0009) -[2023-10-11 00:06:33,045][98559] Updated weights for policy 0, policy_version 82270 (0.0008) -[2023-10-11 00:06:35,556][97672] Fps is (10 sec: 13106.7, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 167936000. Throughput: 0: 1723.1, 1: 1701.2. Samples: 41996982. Policy #0 lag: (min: 9.0, avg: 14.9, max: 41.0) -[2023-10-11 00:06:35,557][97672] Avg episode reward: [(0, '-0.740'), (1, '22.680')] -[2023-10-11 00:06:35,566][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000081728_83689472.pth... -[2023-10-11 00:06:35,566][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000082272_84246528.pth... -[2023-10-11 00:06:35,605][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000080672_82608128.pth -[2023-10-11 00:06:35,608][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000080160_82083840.pth -[2023-10-11 00:06:35,979][98560] Updated weights for policy 1, policy_version 81732 (0.0008) -[2023-10-11 00:06:36,344][98560] Updated weights for policy 1, policy_version 81742 (0.0009) -[2023-10-11 00:06:36,715][98560] Updated weights for policy 1, policy_version 81752 (0.0010) -[2023-10-11 00:06:36,978][98559] Updated weights for policy 0, policy_version 82280 (0.0008) -[2023-10-11 00:06:37,349][98559] Updated weights for policy 0, policy_version 82290 (0.0008) -[2023-10-11 00:06:37,711][98559] Updated weights for policy 0, policy_version 82300 (0.0007) -[2023-10-11 00:06:40,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 168001536. Throughput: 0: 1699.2, 1: 1682.2. Samples: 42006404. Policy #0 lag: (min: 9.0, avg: 14.9, max: 41.0) -[2023-10-11 00:06:40,557][97672] Avg episode reward: [(0, '-0.740'), (1, '22.720')] -[2023-10-11 00:06:40,888][98560] Updated weights for policy 1, policy_version 81762 (0.0008) -[2023-10-11 00:06:41,254][98560] Updated weights for policy 1, policy_version 81772 (0.0009) -[2023-10-11 00:06:41,622][98560] Updated weights for policy 1, policy_version 81782 (0.0009) -[2023-10-11 00:06:41,826][98559] Updated weights for policy 0, policy_version 82310 (0.0008) -[2023-10-11 00:06:41,986][98560] Updated weights for policy 1, policy_version 81792 (0.0008) -[2023-10-11 00:06:42,200][98559] Updated weights for policy 0, policy_version 82320 (0.0010) -[2023-10-11 00:06:42,572][98559] Updated weights for policy 0, policy_version 82330 (0.0011) -[2023-10-11 00:06:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 168067072. Throughput: 0: 1711.9, 1: 1693.3. Samples: 42027328. Policy #0 lag: (min: 9.0, avg: 14.9, max: 41.0) -[2023-10-11 00:06:45,557][97672] Avg episode reward: [(0, '-0.740'), (1, '22.700')] -[2023-10-11 00:06:46,029][98560] Updated weights for policy 1, policy_version 81802 (0.0009) -[2023-10-11 00:06:46,387][98560] Updated weights for policy 1, policy_version 81812 (0.0010) -[2023-10-11 00:06:46,519][98559] Updated weights for policy 0, policy_version 82340 (0.0008) -[2023-10-11 00:06:46,754][98560] Updated weights for policy 1, policy_version 81822 (0.0008) -[2023-10-11 00:06:46,882][98559] Updated weights for policy 0, policy_version 82350 (0.0007) -[2023-10-11 00:06:47,252][98559] Updated weights for policy 0, policy_version 82360 (0.0007) -[2023-10-11 00:06:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 168132608. Throughput: 0: 1725.8, 1: 1689.0. Samples: 42048324. Policy #0 lag: (min: 9.0, avg: 14.9, max: 41.0) -[2023-10-11 00:06:50,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.640')] -[2023-10-11 00:06:50,788][98560] Updated weights for policy 1, policy_version 81832 (0.0009) -[2023-10-11 00:06:51,162][98560] Updated weights for policy 1, policy_version 81842 (0.0009) -[2023-10-11 00:06:51,247][98559] Updated weights for policy 0, policy_version 82370 (0.0010) -[2023-10-11 00:06:51,530][98560] Updated weights for policy 1, policy_version 81852 (0.0009) -[2023-10-11 00:06:51,614][98559] Updated weights for policy 0, policy_version 82380 (0.0008) -[2023-10-11 00:06:51,991][98559] Updated weights for policy 0, policy_version 82390 (0.0009) -[2023-10-11 00:06:52,353][98559] Updated weights for policy 0, policy_version 82400 (0.0009) -[2023-10-11 00:06:55,471][98560] Updated weights for policy 1, policy_version 81862 (0.0007) -[2023-10-11 00:06:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 168198144. Throughput: 0: 1703.6, 1: 1688.3. Samples: 42057816. Policy #0 lag: (min: 9.0, avg: 14.9, max: 41.0) -[2023-10-11 00:06:55,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.600')] -[2023-10-11 00:06:55,829][98560] Updated weights for policy 1, policy_version 81872 (0.0011) -[2023-10-11 00:06:56,200][98560] Updated weights for policy 1, policy_version 81882 (0.0008) -[2023-10-11 00:06:56,304][98559] Updated weights for policy 0, policy_version 82410 (0.0007) -[2023-10-11 00:06:56,669][98559] Updated weights for policy 0, policy_version 82420 (0.0008) -[2023-10-11 00:06:57,035][98559] Updated weights for policy 0, policy_version 82430 (0.0009) -[2023-10-11 00:07:00,251][98560] Updated weights for policy 1, policy_version 81892 (0.0007) -[2023-10-11 00:07:00,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 168263680. Throughput: 0: 1728.8, 1: 1694.9. Samples: 42079026. Policy #0 lag: (min: 9.0, avg: 14.9, max: 41.0) -[2023-10-11 00:07:00,558][97672] Avg episode reward: [(0, '-0.780'), (1, '22.660')] -[2023-10-11 00:07:00,626][98560] Updated weights for policy 1, policy_version 81902 (0.0007) -[2023-10-11 00:07:00,961][98559] Updated weights for policy 0, policy_version 82440 (0.0010) -[2023-10-11 00:07:00,990][98560] Updated weights for policy 1, policy_version 81912 (0.0009) -[2023-10-11 00:07:01,326][98559] Updated weights for policy 0, policy_version 82450 (0.0009) -[2023-10-11 00:07:01,695][98559] Updated weights for policy 0, policy_version 82460 (0.0007) -[2023-10-11 00:07:04,900][98560] Updated weights for policy 1, policy_version 81922 (0.0007) -[2023-10-11 00:07:05,268][98560] Updated weights for policy 1, policy_version 81932 (0.0008) -[2023-10-11 00:07:05,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 168329216. Throughput: 0: 1729.1, 1: 1700.9. Samples: 42100320. Policy #0 lag: (min: 9.0, avg: 14.9, max: 41.0) -[2023-10-11 00:07:05,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.620')] -[2023-10-11 00:07:05,630][98560] Updated weights for policy 1, policy_version 81942 (0.0007) -[2023-10-11 00:07:05,766][98559] Updated weights for policy 0, policy_version 82470 (0.0008) -[2023-10-11 00:07:05,996][98560] Updated weights for policy 1, policy_version 81952 (0.0007) -[2023-10-11 00:07:06,138][98559] Updated weights for policy 0, policy_version 82480 (0.0007) -[2023-10-11 00:07:06,505][98559] Updated weights for policy 0, policy_version 82490 (0.0008) -[2023-10-11 00:07:09,924][98560] Updated weights for policy 1, policy_version 81962 (0.0010) -[2023-10-11 00:07:10,297][98560] Updated weights for policy 1, policy_version 81972 (0.0009) -[2023-10-11 00:07:10,417][98559] Updated weights for policy 0, policy_version 82500 (0.0008) -[2023-10-11 00:07:10,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 168394752. Throughput: 0: 1718.4, 1: 1701.3. Samples: 42109342. Policy #0 lag: (min: 9.0, avg: 14.9, max: 41.0) -[2023-10-11 00:07:10,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.640')] -[2023-10-11 00:07:10,656][98560] Updated weights for policy 1, policy_version 81982 (0.0007) -[2023-10-11 00:07:10,780][98559] Updated weights for policy 0, policy_version 82510 (0.0009) -[2023-10-11 00:07:11,152][98559] Updated weights for policy 0, policy_version 82520 (0.0007) -[2023-10-11 00:07:14,766][98560] Updated weights for policy 1, policy_version 81992 (0.0009) -[2023-10-11 00:07:15,043][98559] Updated weights for policy 0, policy_version 82530 (0.0008) -[2023-10-11 00:07:15,147][98560] Updated weights for policy 1, policy_version 82002 (0.0008) -[2023-10-11 00:07:15,412][98559] Updated weights for policy 0, policy_version 82540 (0.0010) -[2023-10-11 00:07:15,514][98560] Updated weights for policy 1, policy_version 82012 (0.0009) -[2023-10-11 00:07:15,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 168460288. Throughput: 0: 1728.0, 1: 1706.0. Samples: 42130768. Policy #0 lag: (min: 9.0, avg: 14.9, max: 41.0) -[2023-10-11 00:07:15,556][97672] Avg episode reward: [(0, '-0.780'), (1, '22.660')] -[2023-10-11 00:07:15,787][98559] Updated weights for policy 0, policy_version 82550 (0.0009) -[2023-10-11 00:07:16,144][98559] Updated weights for policy 0, policy_version 82560 (0.0011) -[2023-10-11 00:07:19,507][98560] Updated weights for policy 1, policy_version 82022 (0.0008) -[2023-10-11 00:07:19,873][98560] Updated weights for policy 1, policy_version 82032 (0.0009) -[2023-10-11 00:07:20,067][98559] Updated weights for policy 0, policy_version 82570 (0.0010) -[2023-10-11 00:07:20,244][98560] Updated weights for policy 1, policy_version 82042 (0.0007) -[2023-10-11 00:07:20,434][98559] Updated weights for policy 0, policy_version 82580 (0.0008) -[2023-10-11 00:07:20,556][97672] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 168558592. Throughput: 0: 1714.5, 1: 1702.1. Samples: 42150730. Policy #0 lag: (min: 9.0, avg: 14.9, max: 41.0) -[2023-10-11 00:07:20,556][97672] Avg episode reward: [(0, '-0.760'), (1, '22.600')] -[2023-10-11 00:07:20,807][98559] Updated weights for policy 0, policy_version 82590 (0.0008) -[2023-10-11 00:07:24,231][98560] Updated weights for policy 1, policy_version 82052 (0.0009) -[2023-10-11 00:07:24,589][98560] Updated weights for policy 1, policy_version 82062 (0.0010) -[2023-10-11 00:07:24,782][98559] Updated weights for policy 0, policy_version 82600 (0.0008) -[2023-10-11 00:07:24,962][98560] Updated weights for policy 1, policy_version 82072 (0.0008) -[2023-10-11 00:07:25,147][98559] Updated weights for policy 0, policy_version 82610 (0.0008) -[2023-10-11 00:07:25,524][98559] Updated weights for policy 0, policy_version 82620 (0.0008) -[2023-10-11 00:07:25,556][97672] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 168624128. Throughput: 0: 1726.0, 1: 1710.0. Samples: 42161022. Policy #0 lag: (min: 9.0, avg: 14.9, max: 41.0) -[2023-10-11 00:07:25,557][97672] Avg episode reward: [(0, '-0.760'), (1, '22.600')] -[2023-10-11 00:07:28,845][98560] Updated weights for policy 1, policy_version 82082 (0.0008) -[2023-10-11 00:07:29,209][98560] Updated weights for policy 1, policy_version 82092 (0.0009) -[2023-10-11 00:07:29,575][98560] Updated weights for policy 1, policy_version 82102 (0.0007) -[2023-10-11 00:07:29,604][98559] Updated weights for policy 0, policy_version 82630 (0.0007) -[2023-10-11 00:07:29,943][98560] Updated weights for policy 1, policy_version 82112 (0.0008) -[2023-10-11 00:07:29,963][98559] Updated weights for policy 0, policy_version 82640 (0.0008) -[2023-10-11 00:07:30,327][98559] Updated weights for policy 0, policy_version 82650 (0.0010) -[2023-10-11 00:07:30,556][97672] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 168722432. Throughput: 0: 1723.4, 1: 1714.9. Samples: 42182048. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:07:30,556][97672] Avg episode reward: [(0, '-0.760'), (1, '22.600')] -[2023-10-11 00:07:33,926][98560] Updated weights for policy 1, policy_version 82122 (0.0007) -[2023-10-11 00:07:34,280][98559] Updated weights for policy 0, policy_version 82660 (0.0008) -[2023-10-11 00:07:34,300][98560] Updated weights for policy 1, policy_version 82132 (0.0008) -[2023-10-11 00:07:34,651][98559] Updated weights for policy 0, policy_version 82670 (0.0008) -[2023-10-11 00:07:34,658][98560] Updated weights for policy 1, policy_version 82142 (0.0008) -[2023-10-11 00:07:35,010][98559] Updated weights for policy 0, policy_version 82680 (0.0008) -[2023-10-11 00:07:35,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 168787968. Throughput: 0: 1694.0, 1: 1695.1. Samples: 42200832. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:07:35,557][97672] Avg episode reward: [(0, '-0.760'), (1, '22.600')] -[2023-10-11 00:07:38,711][98560] Updated weights for policy 1, policy_version 82152 (0.0009) -[2023-10-11 00:07:38,857][98559] Updated weights for policy 0, policy_version 82690 (0.0007) -[2023-10-11 00:07:39,082][98560] Updated weights for policy 1, policy_version 82162 (0.0008) -[2023-10-11 00:07:39,214][98559] Updated weights for policy 0, policy_version 82700 (0.0007) -[2023-10-11 00:07:39,445][98560] Updated weights for policy 1, policy_version 82172 (0.0008) -[2023-10-11 00:07:39,585][98559] Updated weights for policy 0, policy_version 82710 (0.0009) -[2023-10-11 00:07:39,943][98559] Updated weights for policy 0, policy_version 82720 (0.0009) -[2023-10-11 00:07:40,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 168853504. Throughput: 0: 1721.6, 1: 1721.2. Samples: 42212742. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:07:40,557][97672] Avg episode reward: [(0, '-0.740'), (1, '22.600')] -[2023-10-11 00:07:43,434][98560] Updated weights for policy 1, policy_version 82182 (0.0007) -[2023-10-11 00:07:43,799][98560] Updated weights for policy 1, policy_version 82192 (0.0008) -[2023-10-11 00:07:44,163][98560] Updated weights for policy 1, policy_version 82202 (0.0009) -[2023-10-11 00:07:44,236][98559] Updated weights for policy 0, policy_version 82730 (0.0008) -[2023-10-11 00:07:44,606][98559] Updated weights for policy 0, policy_version 82740 (0.0008) -[2023-10-11 00:07:44,963][98559] Updated weights for policy 0, policy_version 82750 (0.0009) -[2023-10-11 00:07:45,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 168919040. Throughput: 0: 1704.6, 1: 1706.8. Samples: 42232538. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:07:45,557][97672] Avg episode reward: [(0, '-0.740'), (1, '22.560')] -[2023-10-11 00:07:48,140][98560] Updated weights for policy 1, policy_version 82212 (0.0009) -[2023-10-11 00:07:48,511][98560] Updated weights for policy 1, policy_version 82222 (0.0010) -[2023-10-11 00:07:48,878][98560] Updated weights for policy 1, policy_version 82232 (0.0008) -[2023-10-11 00:07:48,985][98559] Updated weights for policy 0, policy_version 82760 (0.0007) -[2023-10-11 00:07:49,344][98559] Updated weights for policy 0, policy_version 82770 (0.0010) -[2023-10-11 00:07:49,712][98559] Updated weights for policy 0, policy_version 82780 (0.0008) -[2023-10-11 00:07:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 168984576. Throughput: 0: 1684.4, 1: 1682.0. Samples: 42251808. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:07:50,557][97672] Avg episode reward: [(0, '-0.740'), (1, '22.540')] -[2023-10-11 00:07:52,952][98560] Updated weights for policy 1, policy_version 82242 (0.0007) -[2023-10-11 00:07:53,320][98560] Updated weights for policy 1, policy_version 82252 (0.0008) -[2023-10-11 00:07:53,683][98560] Updated weights for policy 1, policy_version 82262 (0.0008) -[2023-10-11 00:07:53,784][98559] Updated weights for policy 0, policy_version 82790 (0.0007) -[2023-10-11 00:07:54,044][98560] Updated weights for policy 1, policy_version 82272 (0.0008) -[2023-10-11 00:07:54,150][98559] Updated weights for policy 0, policy_version 82800 (0.0008) -[2023-10-11 00:07:54,520][98559] Updated weights for policy 0, policy_version 82810 (0.0009) -[2023-10-11 00:07:55,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 169050112. Throughput: 0: 1716.4, 1: 1713.2. Samples: 42263674. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:07:55,556][97672] Avg episode reward: [(0, '-0.760'), (1, '22.520')] -[2023-10-11 00:07:58,024][98560] Updated weights for policy 1, policy_version 82282 (0.0009) -[2023-10-11 00:07:58,388][98560] Updated weights for policy 1, policy_version 82292 (0.0008) -[2023-10-11 00:07:58,548][98559] Updated weights for policy 0, policy_version 82820 (0.0009) -[2023-10-11 00:07:58,765][98560] Updated weights for policy 1, policy_version 82302 (0.0007) -[2023-10-11 00:07:58,912][98559] Updated weights for policy 0, policy_version 82830 (0.0009) -[2023-10-11 00:07:59,280][98559] Updated weights for policy 0, policy_version 82840 (0.0009) -[2023-10-11 00:08:00,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 169115648. Throughput: 0: 1693.2, 1: 1686.2. Samples: 42282840. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:08:00,556][97672] Avg episode reward: [(0, '-0.760'), (1, '22.500')] -[2023-10-11 00:08:02,684][98560] Updated weights for policy 1, policy_version 82312 (0.0008) -[2023-10-11 00:08:03,058][98560] Updated weights for policy 1, policy_version 82322 (0.0009) -[2023-10-11 00:08:03,200][98559] Updated weights for policy 0, policy_version 82850 (0.0011) -[2023-10-11 00:08:03,423][98560] Updated weights for policy 1, policy_version 82332 (0.0009) -[2023-10-11 00:08:03,560][98559] Updated weights for policy 0, policy_version 82860 (0.0008) -[2023-10-11 00:08:03,923][98559] Updated weights for policy 0, policy_version 82870 (0.0010) -[2023-10-11 00:08:04,290][98559] Updated weights for policy 0, policy_version 82880 (0.0009) -[2023-10-11 00:08:05,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 169181184. Throughput: 0: 1701.0, 1: 1694.3. Samples: 42303518. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:08:05,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.520')] -[2023-10-11 00:08:07,487][98560] Updated weights for policy 1, policy_version 82342 (0.0008) -[2023-10-11 00:08:07,860][98560] Updated weights for policy 1, policy_version 82352 (0.0009) -[2023-10-11 00:08:08,227][98560] Updated weights for policy 1, policy_version 82362 (0.0007) -[2023-10-11 00:08:08,341][98559] Updated weights for policy 0, policy_version 82890 (0.0009) -[2023-10-11 00:08:08,704][98559] Updated weights for policy 0, policy_version 82900 (0.0009) -[2023-10-11 00:08:09,075][98559] Updated weights for policy 0, policy_version 82910 (0.0009) -[2023-10-11 00:08:10,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 169246720. Throughput: 0: 1703.6, 1: 1702.0. Samples: 42314274. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:08:10,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.460')] -[2023-10-11 00:08:12,175][98560] Updated weights for policy 1, policy_version 82372 (0.0008) -[2023-10-11 00:08:12,531][98560] Updated weights for policy 1, policy_version 82382 (0.0008) -[2023-10-11 00:08:12,900][98560] Updated weights for policy 1, policy_version 82392 (0.0007) -[2023-10-11 00:08:13,051][98559] Updated weights for policy 0, policy_version 82920 (0.0008) -[2023-10-11 00:08:13,420][98559] Updated weights for policy 0, policy_version 82930 (0.0009) -[2023-10-11 00:08:13,780][98559] Updated weights for policy 0, policy_version 82940 (0.0010) -[2023-10-11 00:08:15,556][97672] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 169312256. Throughput: 0: 1684.5, 1: 1683.0. Samples: 42333586. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:08:15,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.540')] -[2023-10-11 00:08:16,967][98560] Updated weights for policy 1, policy_version 82402 (0.0007) -[2023-10-11 00:08:17,335][98560] Updated weights for policy 1, policy_version 82412 (0.0007) -[2023-10-11 00:08:17,699][98560] Updated weights for policy 1, policy_version 82422 (0.0007) -[2023-10-11 00:08:17,757][98559] Updated weights for policy 0, policy_version 82950 (0.0009) -[2023-10-11 00:08:18,067][98560] Updated weights for policy 1, policy_version 82432 (0.0009) -[2023-10-11 00:08:18,123][98559] Updated weights for policy 0, policy_version 82960 (0.0009) -[2023-10-11 00:08:18,489][98559] Updated weights for policy 0, policy_version 82970 (0.0009) -[2023-10-11 00:08:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 169377792. Throughput: 0: 1714.5, 1: 1708.5. Samples: 42354868. Policy #0 lag: (min: 9.0, avg: 15.8, max: 41.0) -[2023-10-11 00:08:20,556][97672] Avg episode reward: [(0, '-0.820'), (1, '22.520')] -[2023-10-11 00:08:22,066][98560] Updated weights for policy 1, policy_version 82442 (0.0010) -[2023-10-11 00:08:22,345][98559] Updated weights for policy 0, policy_version 82980 (0.0008) -[2023-10-11 00:08:22,438][98560] Updated weights for policy 1, policy_version 82452 (0.0008) -[2023-10-11 00:08:22,710][98559] Updated weights for policy 0, policy_version 82990 (0.0008) -[2023-10-11 00:08:22,810][98560] Updated weights for policy 1, policy_version 82462 (0.0007) -[2023-10-11 00:08:23,083][98559] Updated weights for policy 0, policy_version 83000 (0.0007) -[2023-10-11 00:08:25,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 169443328. Throughput: 0: 1685.2, 1: 1686.7. Samples: 42364480. Policy #0 lag: (min: 9.0, avg: 15.8, max: 41.0) -[2023-10-11 00:08:25,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.500')] -[2023-10-11 00:08:26,890][98559] Updated weights for policy 0, policy_version 83010 (0.0008) -[2023-10-11 00:08:26,929][98560] Updated weights for policy 1, policy_version 82472 (0.0009) -[2023-10-11 00:08:27,265][98559] Updated weights for policy 0, policy_version 83020 (0.0010) -[2023-10-11 00:08:27,297][98560] Updated weights for policy 1, policy_version 82482 (0.0007) -[2023-10-11 00:08:27,620][98559] Updated weights for policy 0, policy_version 83030 (0.0009) -[2023-10-11 00:08:27,656][98560] Updated weights for policy 1, policy_version 82492 (0.0008) -[2023-10-11 00:08:27,985][98559] Updated weights for policy 0, policy_version 83040 (0.0010) -[2023-10-11 00:08:30,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 169508864. Throughput: 0: 1704.1, 1: 1689.8. Samples: 42385266. Policy #0 lag: (min: 9.0, avg: 15.8, max: 41.0) -[2023-10-11 00:08:30,556][97672] Avg episode reward: [(0, '-0.820'), (1, '22.440')] -[2023-10-11 00:08:31,750][98560] Updated weights for policy 1, policy_version 82502 (0.0009) -[2023-10-11 00:08:32,115][98560] Updated weights for policy 1, policy_version 82512 (0.0008) -[2023-10-11 00:08:32,168][98559] Updated weights for policy 0, policy_version 83050 (0.0009) -[2023-10-11 00:08:32,486][98560] Updated weights for policy 1, policy_version 82522 (0.0009) -[2023-10-11 00:08:32,532][98559] Updated weights for policy 0, policy_version 83060 (0.0008) -[2023-10-11 00:08:32,892][98559] Updated weights for policy 0, policy_version 83070 (0.0007) -[2023-10-11 00:08:35,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 169574400. Throughput: 0: 1723.3, 1: 1705.2. Samples: 42406092. Policy #0 lag: (min: 9.0, avg: 15.8, max: 41.0) -[2023-10-11 00:08:35,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.460')] -[2023-10-11 00:08:35,566][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000083072_85065728.pth... -[2023-10-11 00:08:35,566][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000082528_84508672.pth... -[2023-10-11 00:08:35,607][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000081472_83427328.pth -[2023-10-11 00:08:35,607][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000080960_82903040.pth -[2023-10-11 00:08:36,475][98560] Updated weights for policy 1, policy_version 82532 (0.0008) -[2023-10-11 00:08:36,842][98560] Updated weights for policy 1, policy_version 82542 (0.0010) -[2023-10-11 00:08:36,896][98559] Updated weights for policy 0, policy_version 83080 (0.0009) -[2023-10-11 00:08:37,208][98560] Updated weights for policy 1, policy_version 82552 (0.0007) -[2023-10-11 00:08:37,268][98559] Updated weights for policy 0, policy_version 83090 (0.0009) -[2023-10-11 00:08:37,637][98559] Updated weights for policy 0, policy_version 83100 (0.0009) -[2023-10-11 00:08:40,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 169639936. Throughput: 0: 1691.9, 1: 1676.3. Samples: 42415246. Policy #0 lag: (min: 9.0, avg: 15.8, max: 41.0) -[2023-10-11 00:08:40,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.480')] -[2023-10-11 00:08:41,286][98560] Updated weights for policy 1, policy_version 82562 (0.0007) -[2023-10-11 00:08:41,643][98560] Updated weights for policy 1, policy_version 82572 (0.0007) -[2023-10-11 00:08:41,731][98559] Updated weights for policy 0, policy_version 83110 (0.0009) -[2023-10-11 00:08:42,011][98560] Updated weights for policy 1, policy_version 82582 (0.0007) -[2023-10-11 00:08:42,100][98559] Updated weights for policy 0, policy_version 83120 (0.0008) -[2023-10-11 00:08:42,364][98560] Updated weights for policy 1, policy_version 82592 (0.0007) -[2023-10-11 00:08:42,460][98559] Updated weights for policy 0, policy_version 83130 (0.0010) -[2023-10-11 00:08:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 169705472. Throughput: 0: 1706.9, 1: 1701.9. Samples: 42436236. Policy #0 lag: (min: 9.0, avg: 15.8, max: 41.0) -[2023-10-11 00:08:45,556][97672] Avg episode reward: [(0, '-0.800'), (1, '22.440')] -[2023-10-11 00:08:46,506][98559] Updated weights for policy 0, policy_version 83140 (0.0008) -[2023-10-11 00:08:46,573][98560] Updated weights for policy 1, policy_version 82602 (0.0009) -[2023-10-11 00:08:46,863][98559] Updated weights for policy 0, policy_version 83150 (0.0008) -[2023-10-11 00:08:46,940][98560] Updated weights for policy 1, policy_version 82612 (0.0008) -[2023-10-11 00:08:47,232][98559] Updated weights for policy 0, policy_version 83160 (0.0008) -[2023-10-11 00:08:47,299][98560] Updated weights for policy 1, policy_version 82622 (0.0008) -[2023-10-11 00:08:50,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 169771008. Throughput: 0: 1709.6, 1: 1701.8. Samples: 42457032. Policy #0 lag: (min: 9.0, avg: 15.8, max: 41.0) -[2023-10-11 00:08:50,556][97672] Avg episode reward: [(0, '-0.800'), (1, '22.360')] -[2023-10-11 00:08:51,305][98559] Updated weights for policy 0, policy_version 83170 (0.0009) -[2023-10-11 00:08:51,472][98560] Updated weights for policy 1, policy_version 82632 (0.0008) -[2023-10-11 00:08:51,678][98559] Updated weights for policy 0, policy_version 83180 (0.0007) -[2023-10-11 00:08:51,859][98560] Updated weights for policy 1, policy_version 82642 (0.0007) -[2023-10-11 00:08:52,038][98559] Updated weights for policy 0, policy_version 83190 (0.0007) -[2023-10-11 00:08:52,219][98560] Updated weights for policy 1, policy_version 82652 (0.0009) -[2023-10-11 00:08:52,402][98559] Updated weights for policy 0, policy_version 83200 (0.0009) -[2023-10-11 00:08:55,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 169836544. Throughput: 0: 1691.0, 1: 1678.3. Samples: 42465892. Policy #0 lag: (min: 9.0, avg: 15.8, max: 41.0) -[2023-10-11 00:08:55,556][97672] Avg episode reward: [(0, '-0.800'), (1, '22.420')] -[2023-10-11 00:08:56,367][98560] Updated weights for policy 1, policy_version 82662 (0.0007) -[2023-10-11 00:08:56,388][98559] Updated weights for policy 0, policy_version 83210 (0.0007) -[2023-10-11 00:08:56,736][98560] Updated weights for policy 1, policy_version 82672 (0.0007) -[2023-10-11 00:08:56,751][98559] Updated weights for policy 0, policy_version 83220 (0.0007) -[2023-10-11 00:08:57,091][98560] Updated weights for policy 1, policy_version 82682 (0.0008) -[2023-10-11 00:08:57,121][98559] Updated weights for policy 0, policy_version 83230 (0.0007) -[2023-10-11 00:09:00,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 169902080. Throughput: 0: 1714.3, 1: 1688.9. Samples: 42486734. Policy #0 lag: (min: 9.0, avg: 15.8, max: 41.0) -[2023-10-11 00:09:00,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.420')] -[2023-10-11 00:09:01,073][98560] Updated weights for policy 1, policy_version 82692 (0.0009) -[2023-10-11 00:09:01,224][98559] Updated weights for policy 0, policy_version 83240 (0.0009) -[2023-10-11 00:09:01,428][98560] Updated weights for policy 1, policy_version 82702 (0.0008) -[2023-10-11 00:09:01,593][98559] Updated weights for policy 0, policy_version 83250 (0.0007) -[2023-10-11 00:09:01,794][98560] Updated weights for policy 1, policy_version 82712 (0.0007) -[2023-10-11 00:09:01,956][98559] Updated weights for policy 0, policy_version 83260 (0.0009) -[2023-10-11 00:09:05,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 169967616. Throughput: 0: 1708.4, 1: 1686.2. Samples: 42507622. Policy #0 lag: (min: 9.0, avg: 15.8, max: 41.0) -[2023-10-11 00:09:05,556][97672] Avg episode reward: [(0, '-0.800'), (1, '22.480')] -[2023-10-11 00:09:05,798][98560] Updated weights for policy 1, policy_version 82722 (0.0010) -[2023-10-11 00:09:05,953][98559] Updated weights for policy 0, policy_version 83270 (0.0009) -[2023-10-11 00:09:06,168][98560] Updated weights for policy 1, policy_version 82732 (0.0009) -[2023-10-11 00:09:06,319][98559] Updated weights for policy 0, policy_version 83280 (0.0009) -[2023-10-11 00:09:06,529][98560] Updated weights for policy 1, policy_version 82742 (0.0009) -[2023-10-11 00:09:06,674][98559] Updated weights for policy 0, policy_version 83290 (0.0008) -[2023-10-11 00:09:06,888][98560] Updated weights for policy 1, policy_version 82752 (0.0010) -[2023-10-11 00:09:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 170033152. Throughput: 0: 1705.2, 1: 1677.5. Samples: 42516700. Policy #0 lag: (min: 9.0, avg: 15.8, max: 41.0) -[2023-10-11 00:09:10,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.500')] -[2023-10-11 00:09:10,734][98559] Updated weights for policy 0, policy_version 83300 (0.0010) -[2023-10-11 00:09:11,037][98560] Updated weights for policy 1, policy_version 82762 (0.0008) -[2023-10-11 00:09:11,091][98559] Updated weights for policy 0, policy_version 83310 (0.0009) -[2023-10-11 00:09:11,395][98560] Updated weights for policy 1, policy_version 82772 (0.0007) -[2023-10-11 00:09:11,458][98559] Updated weights for policy 0, policy_version 83320 (0.0007) -[2023-10-11 00:09:11,765][98560] Updated weights for policy 1, policy_version 82782 (0.0008) -[2023-10-11 00:09:15,379][98559] Updated weights for policy 0, policy_version 83330 (0.0010) -[2023-10-11 00:09:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 170098688. Throughput: 0: 1703.2, 1: 1682.1. Samples: 42537604. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:09:15,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.460')] -[2023-10-11 00:09:15,743][98559] Updated weights for policy 0, policy_version 83340 (0.0009) -[2023-10-11 00:09:15,774][98560] Updated weights for policy 1, policy_version 82792 (0.0008) -[2023-10-11 00:09:16,113][98559] Updated weights for policy 0, policy_version 83350 (0.0009) -[2023-10-11 00:09:16,144][98560] Updated weights for policy 1, policy_version 82802 (0.0008) -[2023-10-11 00:09:16,473][98559] Updated weights for policy 0, policy_version 83360 (0.0008) -[2023-10-11 00:09:16,512][98560] Updated weights for policy 1, policy_version 82812 (0.0008) -[2023-10-11 00:09:20,485][98559] Updated weights for policy 0, policy_version 83370 (0.0009) -[2023-10-11 00:09:20,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 170164224. Throughput: 0: 1699.5, 1: 1684.7. Samples: 42558380. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:09:20,556][97672] Avg episode reward: [(0, '-0.800'), (1, '22.480')] -[2023-10-11 00:09:20,563][98560] Updated weights for policy 1, policy_version 82822 (0.0008) -[2023-10-11 00:09:20,838][98559] Updated weights for policy 0, policy_version 83380 (0.0007) -[2023-10-11 00:09:20,931][98560] Updated weights for policy 1, policy_version 82832 (0.0009) -[2023-10-11 00:09:21,209][98559] Updated weights for policy 0, policy_version 83390 (0.0008) -[2023-10-11 00:09:21,298][98560] Updated weights for policy 1, policy_version 82842 (0.0007) -[2023-10-11 00:09:25,291][98559] Updated weights for policy 0, policy_version 83400 (0.0008) -[2023-10-11 00:09:25,398][98560] Updated weights for policy 1, policy_version 82852 (0.0007) -[2023-10-11 00:09:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 170229760. Throughput: 0: 1707.7, 1: 1681.6. Samples: 42567764. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:09:25,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.520')] -[2023-10-11 00:09:25,656][98559] Updated weights for policy 0, policy_version 83410 (0.0008) -[2023-10-11 00:09:25,769][98560] Updated weights for policy 1, policy_version 82862 (0.0008) -[2023-10-11 00:09:26,021][98559] Updated weights for policy 0, policy_version 83420 (0.0008) -[2023-10-11 00:09:26,126][98560] Updated weights for policy 1, policy_version 82872 (0.0007) -[2023-10-11 00:09:29,951][98559] Updated weights for policy 0, policy_version 83430 (0.0008) -[2023-10-11 00:09:30,305][98560] Updated weights for policy 1, policy_version 82882 (0.0009) -[2023-10-11 00:09:30,318][98559] Updated weights for policy 0, policy_version 83440 (0.0009) -[2023-10-11 00:09:30,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 170295296. Throughput: 0: 1714.2, 1: 1674.7. Samples: 42588734. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:09:30,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.500')] -[2023-10-11 00:09:30,663][98560] Updated weights for policy 1, policy_version 82892 (0.0007) -[2023-10-11 00:09:30,685][98559] Updated weights for policy 0, policy_version 83450 (0.0009) -[2023-10-11 00:09:31,027][98560] Updated weights for policy 1, policy_version 82902 (0.0009) -[2023-10-11 00:09:31,394][98560] Updated weights for policy 1, policy_version 82912 (0.0009) -[2023-10-11 00:09:34,481][98559] Updated weights for policy 0, policy_version 83460 (0.0007) -[2023-10-11 00:09:34,837][98559] Updated weights for policy 0, policy_version 83470 (0.0011) -[2023-10-11 00:09:35,208][98559] Updated weights for policy 0, policy_version 83480 (0.0008) -[2023-10-11 00:09:35,319][98560] Updated weights for policy 1, policy_version 82922 (0.0007) -[2023-10-11 00:09:35,556][97672] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 170393600. Throughput: 0: 1695.9, 1: 1677.6. Samples: 42608838. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:09:35,556][97672] Avg episode reward: [(0, '-0.800'), (1, '22.560')] -[2023-10-11 00:09:35,690][98560] Updated weights for policy 1, policy_version 82932 (0.0007) -[2023-10-11 00:09:36,050][98560] Updated weights for policy 1, policy_version 82942 (0.0010) -[2023-10-11 00:09:39,260][98559] Updated weights for policy 0, policy_version 83490 (0.0008) -[2023-10-11 00:09:39,612][98559] Updated weights for policy 0, policy_version 83500 (0.0008) -[2023-10-11 00:09:39,986][98559] Updated weights for policy 0, policy_version 83510 (0.0007) -[2023-10-11 00:09:40,264][98560] Updated weights for policy 1, policy_version 82952 (0.0009) -[2023-10-11 00:09:40,344][98559] Updated weights for policy 0, policy_version 83520 (0.0009) -[2023-10-11 00:09:40,556][97672] Fps is (10 sec: 16384.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 170459136. Throughput: 0: 1721.8, 1: 1683.2. Samples: 42619118. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:09:40,556][97672] Avg episode reward: [(0, '-0.800'), (1, '22.600')] -[2023-10-11 00:09:40,647][98560] Updated weights for policy 1, policy_version 82962 (0.0010) -[2023-10-11 00:09:41,022][98560] Updated weights for policy 1, policy_version 82972 (0.0010) -[2023-10-11 00:09:44,172][98559] Updated weights for policy 0, policy_version 83530 (0.0008) -[2023-10-11 00:09:44,539][98559] Updated weights for policy 0, policy_version 83540 (0.0007) -[2023-10-11 00:09:44,904][98559] Updated weights for policy 0, policy_version 83550 (0.0007) -[2023-10-11 00:09:45,046][98560] Updated weights for policy 1, policy_version 82982 (0.0009) -[2023-10-11 00:09:45,412][98560] Updated weights for policy 1, policy_version 82992 (0.0007) -[2023-10-11 00:09:45,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 170524672. Throughput: 0: 1711.2, 1: 1682.8. Samples: 42639462. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:09:45,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.620')] -[2023-10-11 00:09:45,777][98560] Updated weights for policy 1, policy_version 83002 (0.0007) -[2023-10-11 00:09:48,921][98559] Updated weights for policy 0, policy_version 83560 (0.0007) -[2023-10-11 00:09:49,293][98559] Updated weights for policy 0, policy_version 83570 (0.0008) -[2023-10-11 00:09:49,647][98559] Updated weights for policy 0, policy_version 83580 (0.0007) -[2023-10-11 00:09:49,945][98560] Updated weights for policy 1, policy_version 83012 (0.0008) -[2023-10-11 00:09:50,306][98560] Updated weights for policy 1, policy_version 83022 (0.0010) -[2023-10-11 00:09:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 170590208. Throughput: 0: 1700.9, 1: 1682.1. Samples: 42659858. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:09:50,556][97672] Avg episode reward: [(0, '-0.800'), (1, '22.600')] -[2023-10-11 00:09:50,674][98560] Updated weights for policy 1, policy_version 83032 (0.0008) -[2023-10-11 00:09:53,703][98559] Updated weights for policy 0, policy_version 83590 (0.0008) -[2023-10-11 00:09:54,078][98559] Updated weights for policy 0, policy_version 83600 (0.0008) -[2023-10-11 00:09:54,448][98559] Updated weights for policy 0, policy_version 83610 (0.0009) -[2023-10-11 00:09:54,753][98560] Updated weights for policy 1, policy_version 83042 (0.0008) -[2023-10-11 00:09:55,123][98560] Updated weights for policy 1, policy_version 83052 (0.0010) -[2023-10-11 00:09:55,486][98560] Updated weights for policy 1, policy_version 83062 (0.0008) -[2023-10-11 00:09:55,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 170655744. Throughput: 0: 1728.5, 1: 1685.7. Samples: 42670340. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:09:55,556][97672] Avg episode reward: [(0, '-0.800'), (1, '22.600')] -[2023-10-11 00:09:55,860][98560] Updated weights for policy 1, policy_version 83072 (0.0007) -[2023-10-11 00:09:58,397][98559] Updated weights for policy 0, policy_version 83620 (0.0008) -[2023-10-11 00:09:58,757][98559] Updated weights for policy 0, policy_version 83630 (0.0009) -[2023-10-11 00:09:59,132][98559] Updated weights for policy 0, policy_version 83640 (0.0009) -[2023-10-11 00:09:59,694][98560] Updated weights for policy 1, policy_version 83082 (0.0010) -[2023-10-11 00:10:00,057][98560] Updated weights for policy 1, policy_version 83092 (0.0010) -[2023-10-11 00:10:00,428][98560] Updated weights for policy 1, policy_version 83102 (0.0009) -[2023-10-11 00:10:00,556][97672] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 170754048. Throughput: 0: 1704.8, 1: 1685.6. Samples: 42690174. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:10:00,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.600')] -[2023-10-11 00:10:03,068][98559] Updated weights for policy 0, policy_version 83650 (0.0009) -[2023-10-11 00:10:03,428][98559] Updated weights for policy 0, policy_version 83660 (0.0008) -[2023-10-11 00:10:03,805][98559] Updated weights for policy 0, policy_version 83670 (0.0009) -[2023-10-11 00:10:04,166][98559] Updated weights for policy 0, policy_version 83680 (0.0010) -[2023-10-11 00:10:04,291][98560] Updated weights for policy 1, policy_version 83112 (0.0007) -[2023-10-11 00:10:04,656][98560] Updated weights for policy 1, policy_version 83122 (0.0011) -[2023-10-11 00:10:05,021][98560] Updated weights for policy 1, policy_version 83132 (0.0010) -[2023-10-11 00:10:05,556][97672] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 170819584. Throughput: 0: 1712.3, 1: 1676.6. Samples: 42710882. Policy #0 lag: (min: 15.0, avg: 28.7, max: 47.0) -[2023-10-11 00:10:05,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.640')] -[2023-10-11 00:10:08,139][98559] Updated weights for policy 0, policy_version 83690 (0.0008) -[2023-10-11 00:10:08,505][98559] Updated weights for policy 0, policy_version 83700 (0.0011) -[2023-10-11 00:10:08,869][98559] Updated weights for policy 0, policy_version 83710 (0.0009) -[2023-10-11 00:10:09,303][98560] Updated weights for policy 1, policy_version 83142 (0.0009) -[2023-10-11 00:10:09,664][98560] Updated weights for policy 1, policy_version 83152 (0.0008) -[2023-10-11 00:10:10,032][98560] Updated weights for policy 1, policy_version 83162 (0.0009) -[2023-10-11 00:10:10,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 170885120. Throughput: 0: 1716.4, 1: 1696.0. Samples: 42721320. Policy #0 lag: (min: 15.0, avg: 28.7, max: 47.0) -[2023-10-11 00:10:10,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.600')] -[2023-10-11 00:10:12,962][98559] Updated weights for policy 0, policy_version 83720 (0.0009) -[2023-10-11 00:10:13,330][98559] Updated weights for policy 0, policy_version 83730 (0.0007) -[2023-10-11 00:10:13,699][98559] Updated weights for policy 0, policy_version 83740 (0.0007) -[2023-10-11 00:10:14,168][98560] Updated weights for policy 1, policy_version 83172 (0.0008) -[2023-10-11 00:10:14,533][98560] Updated weights for policy 1, policy_version 83182 (0.0007) -[2023-10-11 00:10:14,902][98560] Updated weights for policy 1, policy_version 83192 (0.0008) -[2023-10-11 00:10:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 170950656. Throughput: 0: 1699.9, 1: 1701.2. Samples: 42741784. Policy #0 lag: (min: 15.0, avg: 28.7, max: 47.0) -[2023-10-11 00:10:15,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.660')] -[2023-10-11 00:10:17,555][98559] Updated weights for policy 0, policy_version 83750 (0.0007) -[2023-10-11 00:10:17,916][98559] Updated weights for policy 0, policy_version 83760 (0.0008) -[2023-10-11 00:10:18,286][98559] Updated weights for policy 0, policy_version 83770 (0.0009) -[2023-10-11 00:10:18,760][98560] Updated weights for policy 1, policy_version 83202 (0.0009) -[2023-10-11 00:10:19,129][98560] Updated weights for policy 1, policy_version 83212 (0.0008) -[2023-10-11 00:10:19,499][98560] Updated weights for policy 1, policy_version 83222 (0.0010) -[2023-10-11 00:10:19,864][98560] Updated weights for policy 1, policy_version 83232 (0.0009) -[2023-10-11 00:10:20,556][97672] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 171016192. Throughput: 0: 1720.1, 1: 1681.8. Samples: 42761924. Policy #0 lag: (min: 15.0, avg: 28.7, max: 47.0) -[2023-10-11 00:10:20,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.720')] -[2023-10-11 00:10:22,350][98559] Updated weights for policy 0, policy_version 83780 (0.0009) -[2023-10-11 00:10:22,711][98559] Updated weights for policy 0, policy_version 83790 (0.0007) -[2023-10-11 00:10:23,077][98559] Updated weights for policy 0, policy_version 83800 (0.0008) -[2023-10-11 00:10:23,899][98560] Updated weights for policy 1, policy_version 83242 (0.0009) -[2023-10-11 00:10:24,266][98560] Updated weights for policy 1, policy_version 83252 (0.0009) -[2023-10-11 00:10:24,627][98560] Updated weights for policy 1, policy_version 83262 (0.0009) -[2023-10-11 00:10:25,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 171081728. Throughput: 0: 1701.2, 1: 1704.4. Samples: 42772368. Policy #0 lag: (min: 15.0, avg: 28.7, max: 47.0) -[2023-10-11 00:10:25,556][97672] Avg episode reward: [(0, '-0.780'), (1, '22.660')] -[2023-10-11 00:10:27,048][98559] Updated weights for policy 0, policy_version 83810 (0.0009) -[2023-10-11 00:10:27,417][98559] Updated weights for policy 0, policy_version 83820 (0.0007) -[2023-10-11 00:10:27,775][98559] Updated weights for policy 0, policy_version 83830 (0.0010) -[2023-10-11 00:10:28,142][98559] Updated weights for policy 0, policy_version 83840 (0.0010) -[2023-10-11 00:10:28,775][98560] Updated weights for policy 1, policy_version 83272 (0.0009) -[2023-10-11 00:10:29,154][98560] Updated weights for policy 1, policy_version 83282 (0.0009) -[2023-10-11 00:10:29,511][98560] Updated weights for policy 1, policy_version 83292 (0.0011) -[2023-10-11 00:10:30,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 171147264. Throughput: 0: 1708.5, 1: 1699.8. Samples: 42792836. Policy #0 lag: (min: 15.0, avg: 28.7, max: 47.0) -[2023-10-11 00:10:30,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.600')] -[2023-10-11 00:10:32,156][98559] Updated weights for policy 0, policy_version 83850 (0.0007) -[2023-10-11 00:10:32,517][98559] Updated weights for policy 0, policy_version 83860 (0.0007) -[2023-10-11 00:10:32,888][98559] Updated weights for policy 0, policy_version 83870 (0.0011) -[2023-10-11 00:10:33,483][98560] Updated weights for policy 1, policy_version 83302 (0.0008) -[2023-10-11 00:10:33,845][98560] Updated weights for policy 1, policy_version 83312 (0.0008) -[2023-10-11 00:10:34,221][98560] Updated weights for policy 1, policy_version 83322 (0.0009) -[2023-10-11 00:10:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 171212800. Throughput: 0: 1728.5, 1: 1672.3. Samples: 42812894. Policy #0 lag: (min: 15.0, avg: 28.7, max: 47.0) -[2023-10-11 00:10:35,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.600')] -[2023-10-11 00:10:35,564][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000083872_85884928.pth... -[2023-10-11 00:10:35,565][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000083328_85327872.pth... -[2023-10-11 00:10:35,594][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000082272_84246528.pth -[2023-10-11 00:10:35,603][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000081728_83689472.pth -[2023-10-11 00:10:36,833][98559] Updated weights for policy 0, policy_version 83880 (0.0008) -[2023-10-11 00:10:37,204][98559] Updated weights for policy 0, policy_version 83890 (0.0009) -[2023-10-11 00:10:37,576][98559] Updated weights for policy 0, policy_version 83900 (0.0009) -[2023-10-11 00:10:38,268][98560] Updated weights for policy 1, policy_version 83332 (0.0008) -[2023-10-11 00:10:38,639][98560] Updated weights for policy 1, policy_version 83342 (0.0007) -[2023-10-11 00:10:38,994][98560] Updated weights for policy 1, policy_version 83352 (0.0009) -[2023-10-11 00:10:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 171278336. Throughput: 0: 1703.0, 1: 1702.1. Samples: 42823568. Policy #0 lag: (min: 15.0, avg: 28.7, max: 47.0) -[2023-10-11 00:10:40,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.600')] -[2023-10-11 00:10:41,475][98559] Updated weights for policy 0, policy_version 83910 (0.0008) -[2023-10-11 00:10:41,837][98559] Updated weights for policy 0, policy_version 83920 (0.0009) -[2023-10-11 00:10:42,208][98559] Updated weights for policy 0, policy_version 83930 (0.0009) -[2023-10-11 00:10:43,085][98560] Updated weights for policy 1, policy_version 83362 (0.0010) -[2023-10-11 00:10:43,454][98560] Updated weights for policy 1, policy_version 83372 (0.0009) -[2023-10-11 00:10:43,813][98560] Updated weights for policy 1, policy_version 83382 (0.0007) -[2023-10-11 00:10:44,175][98560] Updated weights for policy 1, policy_version 83392 (0.0007) -[2023-10-11 00:10:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 171343872. Throughput: 0: 1728.0, 1: 1686.0. Samples: 42843802. Policy #0 lag: (min: 15.0, avg: 28.7, max: 47.0) -[2023-10-11 00:10:45,556][97672] Avg episode reward: [(0, '-0.780'), (1, '22.580')] -[2023-10-11 00:10:46,249][98559] Updated weights for policy 0, policy_version 83940 (0.0007) -[2023-10-11 00:10:46,606][98559] Updated weights for policy 0, policy_version 83950 (0.0009) -[2023-10-11 00:10:46,977][98559] Updated weights for policy 0, policy_version 83960 (0.0008) -[2023-10-11 00:10:48,111][98560] Updated weights for policy 1, policy_version 83402 (0.0010) -[2023-10-11 00:10:48,487][98560] Updated weights for policy 1, policy_version 83412 (0.0007) -[2023-10-11 00:10:48,850][98560] Updated weights for policy 1, policy_version 83422 (0.0007) -[2023-10-11 00:10:50,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 171409408. Throughput: 0: 1729.9, 1: 1683.3. Samples: 42864474. Policy #0 lag: (min: 15.0, avg: 28.7, max: 47.0) -[2023-10-11 00:10:50,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.580')] -[2023-10-11 00:10:50,906][98559] Updated weights for policy 0, policy_version 83970 (0.0008) -[2023-10-11 00:10:51,271][98559] Updated weights for policy 0, policy_version 83980 (0.0009) -[2023-10-11 00:10:51,632][98559] Updated weights for policy 0, policy_version 83990 (0.0008) -[2023-10-11 00:10:51,995][98559] Updated weights for policy 0, policy_version 84000 (0.0009) -[2023-10-11 00:10:52,870][98560] Updated weights for policy 1, policy_version 83432 (0.0007) -[2023-10-11 00:10:53,239][98560] Updated weights for policy 1, policy_version 83442 (0.0008) -[2023-10-11 00:10:53,600][98560] Updated weights for policy 1, policy_version 83452 (0.0007) -[2023-10-11 00:10:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 171474944. Throughput: 0: 1719.7, 1: 1695.0. Samples: 42874980. Policy #0 lag: (min: 15.0, avg: 28.7, max: 47.0) -[2023-10-11 00:10:55,556][97672] Avg episode reward: [(0, '-0.780'), (1, '22.620')] -[2023-10-11 00:10:55,962][98559] Updated weights for policy 0, policy_version 84010 (0.0011) -[2023-10-11 00:10:56,325][98559] Updated weights for policy 0, policy_version 84020 (0.0010) -[2023-10-11 00:10:56,686][98559] Updated weights for policy 0, policy_version 84030 (0.0007) -[2023-10-11 00:10:57,627][98560] Updated weights for policy 1, policy_version 83462 (0.0007) -[2023-10-11 00:10:57,990][98560] Updated weights for policy 1, policy_version 83472 (0.0008) -[2023-10-11 00:10:58,369][98560] Updated weights for policy 1, policy_version 83482 (0.0008) -[2023-10-11 00:11:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 171540480. Throughput: 0: 1729.1, 1: 1669.3. Samples: 42894714. Policy #0 lag: (min: 22.0, avg: 29.9, max: 54.0) -[2023-10-11 00:11:00,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.580')] -[2023-10-11 00:11:00,724][98559] Updated weights for policy 0, policy_version 84040 (0.0008) -[2023-10-11 00:11:01,094][98559] Updated weights for policy 0, policy_version 84050 (0.0007) -[2023-10-11 00:11:01,459][98559] Updated weights for policy 0, policy_version 84060 (0.0008) -[2023-10-11 00:11:02,383][98560] Updated weights for policy 1, policy_version 83492 (0.0009) -[2023-10-11 00:11:02,759][98560] Updated weights for policy 1, policy_version 83502 (0.0009) -[2023-10-11 00:11:03,125][98560] Updated weights for policy 1, policy_version 83512 (0.0010) -[2023-10-11 00:11:05,236][98559] Updated weights for policy 0, policy_version 84070 (0.0009) -[2023-10-11 00:11:05,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 171606016. Throughput: 0: 1724.9, 1: 1688.9. Samples: 42915544. Policy #0 lag: (min: 22.0, avg: 29.9, max: 54.0) -[2023-10-11 00:11:05,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.480')] -[2023-10-11 00:11:05,599][98559] Updated weights for policy 0, policy_version 84080 (0.0008) -[2023-10-11 00:11:05,960][98559] Updated weights for policy 0, policy_version 84090 (0.0009) -[2023-10-11 00:11:07,097][98560] Updated weights for policy 1, policy_version 83522 (0.0011) -[2023-10-11 00:11:07,460][98560] Updated weights for policy 1, policy_version 83532 (0.0008) -[2023-10-11 00:11:07,836][98560] Updated weights for policy 1, policy_version 83542 (0.0008) -[2023-10-11 00:11:08,197][98560] Updated weights for policy 1, policy_version 83552 (0.0008) -[2023-10-11 00:11:10,011][98559] Updated weights for policy 0, policy_version 84100 (0.0009) -[2023-10-11 00:11:10,371][98559] Updated weights for policy 0, policy_version 84110 (0.0009) -[2023-10-11 00:11:10,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 171671552. Throughput: 0: 1728.6, 1: 1678.9. Samples: 42925708. Policy #0 lag: (min: 22.0, avg: 29.9, max: 54.0) -[2023-10-11 00:11:10,556][97672] Avg episode reward: [(0, '-0.780'), (1, '22.440')] -[2023-10-11 00:11:10,731][98559] Updated weights for policy 0, policy_version 84120 (0.0009) -[2023-10-11 00:11:12,289][98560] Updated weights for policy 1, policy_version 83562 (0.0007) -[2023-10-11 00:11:12,651][98560] Updated weights for policy 1, policy_version 83572 (0.0007) -[2023-10-11 00:11:13,007][98560] Updated weights for policy 1, policy_version 83582 (0.0010) -[2023-10-11 00:11:14,697][98559] Updated weights for policy 0, policy_version 84130 (0.0007) -[2023-10-11 00:11:15,065][98559] Updated weights for policy 0, policy_version 84140 (0.0008) -[2023-10-11 00:11:15,442][98559] Updated weights for policy 0, policy_version 84150 (0.0010) -[2023-10-11 00:11:15,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 171737088. Throughput: 0: 1729.1, 1: 1677.7. Samples: 42946142. Policy #0 lag: (min: 22.0, avg: 29.9, max: 54.0) -[2023-10-11 00:11:15,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.520')] -[2023-10-11 00:11:15,803][98559] Updated weights for policy 0, policy_version 84160 (0.0011) -[2023-10-11 00:11:17,130][98560] Updated weights for policy 1, policy_version 83592 (0.0008) -[2023-10-11 00:11:17,519][98560] Updated weights for policy 1, policy_version 83602 (0.0007) -[2023-10-11 00:11:17,878][98560] Updated weights for policy 1, policy_version 83612 (0.0007) -[2023-10-11 00:11:19,700][98559] Updated weights for policy 0, policy_version 84170 (0.0010) -[2023-10-11 00:11:20,058][98559] Updated weights for policy 0, policy_version 84180 (0.0010) -[2023-10-11 00:11:20,427][98559] Updated weights for policy 0, policy_version 84190 (0.0010) -[2023-10-11 00:11:20,556][97672] Fps is (10 sec: 16383.6, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 171835392. Throughput: 0: 1698.2, 1: 1707.4. Samples: 42966146. Policy #0 lag: (min: 22.0, avg: 29.9, max: 54.0) -[2023-10-11 00:11:20,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.480')] -[2023-10-11 00:11:21,909][98560] Updated weights for policy 1, policy_version 83622 (0.0009) -[2023-10-11 00:11:22,278][98560] Updated weights for policy 1, policy_version 83632 (0.0008) -[2023-10-11 00:11:22,654][98560] Updated weights for policy 1, policy_version 83642 (0.0007) -[2023-10-11 00:11:24,506][98559] Updated weights for policy 0, policy_version 84200 (0.0010) -[2023-10-11 00:11:24,874][98559] Updated weights for policy 0, policy_version 84210 (0.0010) -[2023-10-11 00:11:25,238][98559] Updated weights for policy 0, policy_version 84220 (0.0008) -[2023-10-11 00:11:25,556][97672] Fps is (10 sec: 16384.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 171900928. Throughput: 0: 1725.1, 1: 1682.1. Samples: 42976894. Policy #0 lag: (min: 22.0, avg: 29.9, max: 54.0) -[2023-10-11 00:11:25,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.460')] -[2023-10-11 00:11:26,628][98560] Updated weights for policy 1, policy_version 83652 (0.0009) -[2023-10-11 00:11:26,999][98560] Updated weights for policy 1, policy_version 83662 (0.0008) -[2023-10-11 00:11:27,371][98560] Updated weights for policy 1, policy_version 83672 (0.0009) -[2023-10-11 00:11:29,096][98559] Updated weights for policy 0, policy_version 84230 (0.0009) -[2023-10-11 00:11:29,468][98559] Updated weights for policy 0, policy_version 84240 (0.0007) -[2023-10-11 00:11:29,824][98559] Updated weights for policy 0, policy_version 84250 (0.0007) -[2023-10-11 00:11:30,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 171966464. Throughput: 0: 1716.1, 1: 1695.3. Samples: 42997314. Policy #0 lag: (min: 22.0, avg: 29.9, max: 54.0) -[2023-10-11 00:11:30,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.500')] -[2023-10-11 00:11:31,445][98560] Updated weights for policy 1, policy_version 83682 (0.0008) -[2023-10-11 00:11:31,827][98560] Updated weights for policy 1, policy_version 83692 (0.0008) -[2023-10-11 00:11:32,204][98560] Updated weights for policy 1, policy_version 83702 (0.0009) -[2023-10-11 00:11:32,561][98560] Updated weights for policy 1, policy_version 83712 (0.0009) -[2023-10-11 00:11:33,686][98559] Updated weights for policy 0, policy_version 84260 (0.0008) -[2023-10-11 00:11:34,041][98559] Updated weights for policy 0, policy_version 84270 (0.0009) -[2023-10-11 00:11:34,400][98559] Updated weights for policy 0, policy_version 84280 (0.0010) -[2023-10-11 00:11:35,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 172032000. Throughput: 0: 1696.5, 1: 1703.6. Samples: 43017478. Policy #0 lag: (min: 22.0, avg: 29.9, max: 54.0) -[2023-10-11 00:11:35,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.460')] -[2023-10-11 00:11:36,654][98560] Updated weights for policy 1, policy_version 83722 (0.0009) -[2023-10-11 00:11:37,028][98560] Updated weights for policy 1, policy_version 83732 (0.0007) -[2023-10-11 00:11:37,387][98560] Updated weights for policy 1, policy_version 83742 (0.0009) -[2023-10-11 00:11:38,354][98559] Updated weights for policy 0, policy_version 84290 (0.0010) -[2023-10-11 00:11:38,716][98559] Updated weights for policy 0, policy_version 84300 (0.0011) -[2023-10-11 00:11:39,086][98559] Updated weights for policy 0, policy_version 84310 (0.0010) -[2023-10-11 00:11:39,454][98559] Updated weights for policy 0, policy_version 84320 (0.0010) -[2023-10-11 00:11:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 172097536. Throughput: 0: 1722.5, 1: 1673.8. Samples: 43027812. Policy #0 lag: (min: 22.0, avg: 29.9, max: 54.0) -[2023-10-11 00:11:40,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.440')] -[2023-10-11 00:11:41,349][98560] Updated weights for policy 1, policy_version 83752 (0.0010) -[2023-10-11 00:11:41,716][98560] Updated weights for policy 1, policy_version 83762 (0.0009) -[2023-10-11 00:11:42,082][98560] Updated weights for policy 1, policy_version 83772 (0.0011) -[2023-10-11 00:11:43,588][98559] Updated weights for policy 0, policy_version 84330 (0.0008) -[2023-10-11 00:11:43,959][98559] Updated weights for policy 0, policy_version 84340 (0.0009) -[2023-10-11 00:11:44,319][98559] Updated weights for policy 0, policy_version 84350 (0.0008) -[2023-10-11 00:11:45,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 172163072. Throughput: 0: 1696.9, 1: 1701.1. Samples: 43047624. Policy #0 lag: (min: 22.0, avg: 29.9, max: 54.0) -[2023-10-11 00:11:45,556][97672] Avg episode reward: [(0, '-0.820'), (1, '22.400')] -[2023-10-11 00:11:46,112][98560] Updated weights for policy 1, policy_version 83782 (0.0011) -[2023-10-11 00:11:46,476][98560] Updated weights for policy 1, policy_version 83792 (0.0009) -[2023-10-11 00:11:46,841][98560] Updated weights for policy 1, policy_version 83802 (0.0010) -[2023-10-11 00:11:48,331][98559] Updated weights for policy 0, policy_version 84360 (0.0009) -[2023-10-11 00:11:48,707][98559] Updated weights for policy 0, policy_version 84370 (0.0010) -[2023-10-11 00:11:49,068][98559] Updated weights for policy 0, policy_version 84380 (0.0010) -[2023-10-11 00:11:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 172228608. Throughput: 0: 1699.1, 1: 1702.2. Samples: 43068602. Policy #0 lag: (min: 24.0, avg: 45.0, max: 56.0) -[2023-10-11 00:11:50,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.480')] -[2023-10-11 00:11:50,717][98560] Updated weights for policy 1, policy_version 83812 (0.0010) -[2023-10-11 00:11:51,087][98560] Updated weights for policy 1, policy_version 83822 (0.0009) -[2023-10-11 00:11:51,461][98560] Updated weights for policy 1, policy_version 83832 (0.0007) -[2023-10-11 00:11:53,051][98559] Updated weights for policy 0, policy_version 84390 (0.0008) -[2023-10-11 00:11:53,413][98559] Updated weights for policy 0, policy_version 84400 (0.0007) -[2023-10-11 00:11:53,780][98559] Updated weights for policy 0, policy_version 84410 (0.0009) -[2023-10-11 00:11:55,505][98560] Updated weights for policy 1, policy_version 83842 (0.0008) -[2023-10-11 00:11:55,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 172294144. Throughput: 0: 1710.3, 1: 1690.1. Samples: 43078730. Policy #0 lag: (min: 24.0, avg: 45.0, max: 56.0) -[2023-10-11 00:11:55,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.520')] -[2023-10-11 00:11:55,878][98560] Updated weights for policy 1, policy_version 83852 (0.0008) -[2023-10-11 00:11:56,247][98560] Updated weights for policy 1, policy_version 83862 (0.0009) -[2023-10-11 00:11:56,617][98560] Updated weights for policy 1, policy_version 83872 (0.0010) -[2023-10-11 00:11:57,687][98559] Updated weights for policy 0, policy_version 84420 (0.0009) -[2023-10-11 00:11:58,053][98559] Updated weights for policy 0, policy_version 84430 (0.0008) -[2023-10-11 00:11:58,425][98559] Updated weights for policy 0, policy_version 84440 (0.0009) -[2023-10-11 00:12:00,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 172359680. Throughput: 0: 1700.0, 1: 1701.4. Samples: 43099208. Policy #0 lag: (min: 24.0, avg: 45.0, max: 56.0) -[2023-10-11 00:12:00,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.480')] -[2023-10-11 00:12:00,685][98560] Updated weights for policy 1, policy_version 83882 (0.0010) -[2023-10-11 00:12:01,057][98560] Updated weights for policy 1, policy_version 83892 (0.0010) -[2023-10-11 00:12:01,423][98560] Updated weights for policy 1, policy_version 83902 (0.0008) -[2023-10-11 00:12:02,438][98559] Updated weights for policy 0, policy_version 84450 (0.0008) -[2023-10-11 00:12:02,793][98559] Updated weights for policy 0, policy_version 84460 (0.0008) -[2023-10-11 00:12:03,166][98559] Updated weights for policy 0, policy_version 84470 (0.0009) -[2023-10-11 00:12:03,530][98559] Updated weights for policy 0, policy_version 84480 (0.0008) -[2023-10-11 00:12:05,283][98560] Updated weights for policy 1, policy_version 83912 (0.0008) -[2023-10-11 00:12:05,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 172425216. Throughput: 0: 1725.5, 1: 1701.9. Samples: 43120380. Policy #0 lag: (min: 24.0, avg: 45.0, max: 56.0) -[2023-10-11 00:12:05,556][97672] Avg episode reward: [(0, '-0.780'), (1, '22.480')] -[2023-10-11 00:12:05,657][98560] Updated weights for policy 1, policy_version 83922 (0.0008) -[2023-10-11 00:12:06,024][98560] Updated weights for policy 1, policy_version 83932 (0.0007) -[2023-10-11 00:12:07,586][98559] Updated weights for policy 0, policy_version 84490 (0.0009) -[2023-10-11 00:12:07,944][98559] Updated weights for policy 0, policy_version 84500 (0.0009) -[2023-10-11 00:12:08,313][98559] Updated weights for policy 0, policy_version 84510 (0.0009) -[2023-10-11 00:12:10,071][98560] Updated weights for policy 1, policy_version 83942 (0.0008) -[2023-10-11 00:12:10,436][98560] Updated weights for policy 1, policy_version 83952 (0.0007) -[2023-10-11 00:12:10,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 172490752. Throughput: 0: 1699.9, 1: 1693.9. Samples: 43129614. Policy #0 lag: (min: 24.0, avg: 45.0, max: 56.0) -[2023-10-11 00:12:10,556][97672] Avg episode reward: [(0, '-0.780'), (1, '22.560')] -[2023-10-11 00:12:10,808][98560] Updated weights for policy 1, policy_version 83962 (0.0008) -[2023-10-11 00:12:12,254][98559] Updated weights for policy 0, policy_version 84520 (0.0008) -[2023-10-11 00:12:12,625][98559] Updated weights for policy 0, policy_version 84530 (0.0009) -[2023-10-11 00:12:12,981][98559] Updated weights for policy 0, policy_version 84540 (0.0011) -[2023-10-11 00:12:14,867][98560] Updated weights for policy 1, policy_version 83972 (0.0009) -[2023-10-11 00:12:15,241][98560] Updated weights for policy 1, policy_version 83982 (0.0008) -[2023-10-11 00:12:15,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 172556288. Throughput: 0: 1705.4, 1: 1698.0. Samples: 43150466. Policy #0 lag: (min: 24.0, avg: 45.0, max: 56.0) -[2023-10-11 00:12:15,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.440')] -[2023-10-11 00:12:15,606][98560] Updated weights for policy 1, policy_version 83992 (0.0008) -[2023-10-11 00:12:17,108][98559] Updated weights for policy 0, policy_version 84550 (0.0009) -[2023-10-11 00:12:17,472][98559] Updated weights for policy 0, policy_version 84560 (0.0011) -[2023-10-11 00:12:17,839][98559] Updated weights for policy 0, policy_version 84570 (0.0012) -[2023-10-11 00:12:19,603][98560] Updated weights for policy 1, policy_version 84002 (0.0007) -[2023-10-11 00:12:19,964][98560] Updated weights for policy 1, policy_version 84012 (0.0008) -[2023-10-11 00:12:20,329][98560] Updated weights for policy 1, policy_version 84022 (0.0010) -[2023-10-11 00:12:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 172621824. Throughput: 0: 1720.9, 1: 1699.4. Samples: 43171392. Policy #0 lag: (min: 24.0, avg: 45.0, max: 56.0) -[2023-10-11 00:12:20,556][97672] Avg episode reward: [(0, '-0.760'), (1, '22.500')] -[2023-10-11 00:12:20,696][98560] Updated weights for policy 1, policy_version 84032 (0.0011) -[2023-10-11 00:12:21,749][98559] Updated weights for policy 0, policy_version 84580 (0.0009) -[2023-10-11 00:12:22,122][98559] Updated weights for policy 0, policy_version 84590 (0.0008) -[2023-10-11 00:12:22,493][98559] Updated weights for policy 0, policy_version 84600 (0.0007) -[2023-10-11 00:12:24,818][98560] Updated weights for policy 1, policy_version 84042 (0.0008) -[2023-10-11 00:12:25,189][98560] Updated weights for policy 1, policy_version 84052 (0.0008) -[2023-10-11 00:12:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 172687360. Throughput: 0: 1693.8, 1: 1707.7. Samples: 43180882. Policy #0 lag: (min: 24.0, avg: 45.0, max: 56.0) -[2023-10-11 00:12:25,557][97672] Avg episode reward: [(0, '-0.760'), (1, '22.460')] -[2023-10-11 00:12:25,564][98560] Updated weights for policy 1, policy_version 84062 (0.0007) -[2023-10-11 00:12:26,524][98559] Updated weights for policy 0, policy_version 84610 (0.0008) -[2023-10-11 00:12:26,904][98559] Updated weights for policy 0, policy_version 84620 (0.0009) -[2023-10-11 00:12:27,267][98559] Updated weights for policy 0, policy_version 84630 (0.0007) -[2023-10-11 00:12:27,627][98559] Updated weights for policy 0, policy_version 84640 (0.0009) -[2023-10-11 00:12:29,657][98560] Updated weights for policy 1, policy_version 84072 (0.0009) -[2023-10-11 00:12:30,020][98560] Updated weights for policy 1, policy_version 84082 (0.0010) -[2023-10-11 00:12:30,384][98560] Updated weights for policy 1, policy_version 84092 (0.0011) -[2023-10-11 00:12:30,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 172785664. Throughput: 0: 1724.5, 1: 1700.5. Samples: 43201748. Policy #0 lag: (min: 24.0, avg: 45.0, max: 56.0) -[2023-10-11 00:12:30,556][97672] Avg episode reward: [(0, '-0.760'), (1, '22.460')] -[2023-10-11 00:12:31,624][98559] Updated weights for policy 0, policy_version 84650 (0.0007) -[2023-10-11 00:12:32,003][98559] Updated weights for policy 0, policy_version 84660 (0.0007) -[2023-10-11 00:12:32,372][98559] Updated weights for policy 0, policy_version 84670 (0.0007) -[2023-10-11 00:12:34,556][98560] Updated weights for policy 1, policy_version 84102 (0.0011) -[2023-10-11 00:12:34,920][98560] Updated weights for policy 1, policy_version 84112 (0.0010) -[2023-10-11 00:12:35,283][98560] Updated weights for policy 1, policy_version 84122 (0.0010) -[2023-10-11 00:12:35,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 172851200. Throughput: 0: 1729.6, 1: 1683.9. Samples: 43222210. Policy #0 lag: (min: 24.0, avg: 45.0, max: 56.0) -[2023-10-11 00:12:35,557][97672] Avg episode reward: [(0, '-0.760'), (1, '22.440')] -[2023-10-11 00:12:35,565][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000084128_86147072.pth... -[2023-10-11 00:12:35,565][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000084672_86704128.pth... -[2023-10-11 00:12:35,602][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000083072_85065728.pth -[2023-10-11 00:12:35,606][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000082528_84508672.pth -[2023-10-11 00:12:36,288][98559] Updated weights for policy 0, policy_version 84680 (0.0008) -[2023-10-11 00:12:36,651][98559] Updated weights for policy 0, policy_version 84690 (0.0010) -[2023-10-11 00:12:37,015][98559] Updated weights for policy 0, policy_version 84700 (0.0010) -[2023-10-11 00:12:39,211][98560] Updated weights for policy 1, policy_version 84132 (0.0009) -[2023-10-11 00:12:39,565][98560] Updated weights for policy 1, policy_version 84142 (0.0010) -[2023-10-11 00:12:39,933][98560] Updated weights for policy 1, policy_version 84152 (0.0010) -[2023-10-11 00:12:40,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 172916736. Throughput: 0: 1711.1, 1: 1694.3. Samples: 43231972. Policy #0 lag: (min: 24.0, avg: 45.0, max: 56.0) -[2023-10-11 00:12:40,558][97672] Avg episode reward: [(0, '-0.760'), (1, '22.460')] -[2023-10-11 00:12:41,102][98559] Updated weights for policy 0, policy_version 84710 (0.0008) -[2023-10-11 00:12:41,475][98559] Updated weights for policy 0, policy_version 84720 (0.0010) -[2023-10-11 00:12:41,837][98559] Updated weights for policy 0, policy_version 84730 (0.0007) -[2023-10-11 00:12:44,087][98560] Updated weights for policy 1, policy_version 84162 (0.0010) -[2023-10-11 00:12:44,458][98560] Updated weights for policy 1, policy_version 84172 (0.0010) -[2023-10-11 00:12:44,828][98560] Updated weights for policy 1, policy_version 84182 (0.0009) -[2023-10-11 00:12:45,200][98560] Updated weights for policy 1, policy_version 84192 (0.0010) -[2023-10-11 00:12:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 172982272. Throughput: 0: 1718.4, 1: 1695.6. Samples: 43252838. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-11 00:12:45,557][97672] Avg episode reward: [(0, '-0.760'), (1, '22.460')] -[2023-10-11 00:12:45,880][98559] Updated weights for policy 0, policy_version 84740 (0.0009) -[2023-10-11 00:12:46,253][98559] Updated weights for policy 0, policy_version 84750 (0.0009) -[2023-10-11 00:12:46,611][98559] Updated weights for policy 0, policy_version 84760 (0.0011) -[2023-10-11 00:12:49,347][98560] Updated weights for policy 1, policy_version 84202 (0.0009) -[2023-10-11 00:12:49,725][98560] Updated weights for policy 1, policy_version 84212 (0.0007) -[2023-10-11 00:12:50,097][98560] Updated weights for policy 1, policy_version 84222 (0.0008) -[2023-10-11 00:12:50,526][98559] Updated weights for policy 0, policy_version 84770 (0.0010) -[2023-10-11 00:12:50,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 173047808. Throughput: 0: 1721.8, 1: 1673.7. Samples: 43273178. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-11 00:12:50,556][97672] Avg episode reward: [(0, '-0.800'), (1, '22.480')] -[2023-10-11 00:12:50,890][98559] Updated weights for policy 0, policy_version 84780 (0.0011) -[2023-10-11 00:12:51,252][98559] Updated weights for policy 0, policy_version 84790 (0.0007) -[2023-10-11 00:12:51,605][98559] Updated weights for policy 0, policy_version 84800 (0.0007) -[2023-10-11 00:12:54,082][98560] Updated weights for policy 1, policy_version 84232 (0.0008) -[2023-10-11 00:12:54,455][98560] Updated weights for policy 1, policy_version 84242 (0.0009) -[2023-10-11 00:12:54,817][98560] Updated weights for policy 1, policy_version 84252 (0.0008) -[2023-10-11 00:12:55,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 173113344. Throughput: 0: 1718.7, 1: 1694.8. Samples: 43283222. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-11 00:12:55,556][97672] Avg episode reward: [(0, '-0.800'), (1, '22.420')] -[2023-10-11 00:12:55,655][98559] Updated weights for policy 0, policy_version 84810 (0.0008) -[2023-10-11 00:12:56,023][98559] Updated weights for policy 0, policy_version 84820 (0.0009) -[2023-10-11 00:12:56,393][98559] Updated weights for policy 0, policy_version 84830 (0.0009) -[2023-10-11 00:12:58,833][98560] Updated weights for policy 1, policy_version 84262 (0.0008) -[2023-10-11 00:12:59,194][98560] Updated weights for policy 1, policy_version 84272 (0.0009) -[2023-10-11 00:12:59,568][98560] Updated weights for policy 1, policy_version 84282 (0.0009) -[2023-10-11 00:13:00,300][98559] Updated weights for policy 0, policy_version 84840 (0.0009) -[2023-10-11 00:13:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 173178880. Throughput: 0: 1724.9, 1: 1691.4. Samples: 43304200. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-11 00:13:00,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.440')] -[2023-10-11 00:13:00,666][98559] Updated weights for policy 0, policy_version 84850 (0.0009) -[2023-10-11 00:13:01,033][98559] Updated weights for policy 0, policy_version 84860 (0.0008) -[2023-10-11 00:13:03,453][98560] Updated weights for policy 1, policy_version 84292 (0.0009) -[2023-10-11 00:13:03,816][98560] Updated weights for policy 1, policy_version 84302 (0.0008) -[2023-10-11 00:13:04,185][98560] Updated weights for policy 1, policy_version 84312 (0.0007) -[2023-10-11 00:13:04,781][98559] Updated weights for policy 0, policy_version 84870 (0.0007) -[2023-10-11 00:13:05,149][98559] Updated weights for policy 0, policy_version 84880 (0.0009) -[2023-10-11 00:13:05,509][98559] Updated weights for policy 0, policy_version 84890 (0.0007) -[2023-10-11 00:13:05,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 173244416. Throughput: 0: 1711.3, 1: 1671.2. Samples: 43323604. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-11 00:13:05,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.420')] -[2023-10-11 00:13:08,113][98560] Updated weights for policy 1, policy_version 84322 (0.0009) -[2023-10-11 00:13:08,483][98560] Updated weights for policy 1, policy_version 84332 (0.0009) -[2023-10-11 00:13:08,840][98560] Updated weights for policy 1, policy_version 84342 (0.0010) -[2023-10-11 00:13:09,207][98560] Updated weights for policy 1, policy_version 84352 (0.0010) -[2023-10-11 00:13:09,487][98559] Updated weights for policy 0, policy_version 84900 (0.0008) -[2023-10-11 00:13:09,854][98559] Updated weights for policy 0, policy_version 84910 (0.0008) -[2023-10-11 00:13:10,218][98559] Updated weights for policy 0, policy_version 84920 (0.0008) -[2023-10-11 00:13:10,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 173342720. Throughput: 0: 1730.0, 1: 1697.1. Samples: 43335102. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-11 00:13:10,556][97672] Avg episode reward: [(0, '-0.800'), (1, '22.480')] -[2023-10-11 00:13:13,157][98560] Updated weights for policy 1, policy_version 84362 (0.0008) -[2023-10-11 00:13:13,527][98560] Updated weights for policy 1, policy_version 84372 (0.0009) -[2023-10-11 00:13:13,885][98560] Updated weights for policy 1, policy_version 84382 (0.0010) -[2023-10-11 00:13:14,232][98559] Updated weights for policy 0, policy_version 84930 (0.0008) -[2023-10-11 00:13:14,602][98559] Updated weights for policy 0, policy_version 84940 (0.0008) -[2023-10-11 00:13:14,961][98559] Updated weights for policy 0, policy_version 84950 (0.0009) -[2023-10-11 00:13:15,332][98559] Updated weights for policy 0, policy_version 84960 (0.0009) -[2023-10-11 00:13:15,556][97672] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 173408256. Throughput: 0: 1725.4, 1: 1678.2. Samples: 43354912. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-11 00:13:15,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.560')] -[2023-10-11 00:13:17,843][98560] Updated weights for policy 1, policy_version 84392 (0.0009) -[2023-10-11 00:13:18,218][98560] Updated weights for policy 1, policy_version 84402 (0.0007) -[2023-10-11 00:13:18,592][98560] Updated weights for policy 1, policy_version 84412 (0.0008) -[2023-10-11 00:13:19,477][98559] Updated weights for policy 0, policy_version 84970 (0.0010) -[2023-10-11 00:13:19,851][98559] Updated weights for policy 0, policy_version 84980 (0.0009) -[2023-10-11 00:13:20,208][98559] Updated weights for policy 0, policy_version 84990 (0.0010) -[2023-10-11 00:13:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 173473792. Throughput: 0: 1693.5, 1: 1690.1. Samples: 43374470. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-11 00:13:20,556][97672] Avg episode reward: [(0, '-0.780'), (1, '22.520')] -[2023-10-11 00:13:22,647][98560] Updated weights for policy 1, policy_version 84422 (0.0010) -[2023-10-11 00:13:23,024][98560] Updated weights for policy 1, policy_version 84432 (0.0010) -[2023-10-11 00:13:23,395][98560] Updated weights for policy 1, policy_version 84442 (0.0007) -[2023-10-11 00:13:24,121][98559] Updated weights for policy 0, policy_version 85000 (0.0008) -[2023-10-11 00:13:24,487][98559] Updated weights for policy 0, policy_version 85010 (0.0011) -[2023-10-11 00:13:24,843][98559] Updated weights for policy 0, policy_version 85020 (0.0010) -[2023-10-11 00:13:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 173539328. Throughput: 0: 1723.4, 1: 1704.0. Samples: 43386208. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-11 00:13:25,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.460')] -[2023-10-11 00:13:27,293][98560] Updated weights for policy 1, policy_version 84452 (0.0007) -[2023-10-11 00:13:27,655][98560] Updated weights for policy 1, policy_version 84462 (0.0008) -[2023-10-11 00:13:28,027][98560] Updated weights for policy 1, policy_version 84472 (0.0008) -[2023-10-11 00:13:28,819][98559] Updated weights for policy 0, policy_version 85030 (0.0008) -[2023-10-11 00:13:29,183][98559] Updated weights for policy 0, policy_version 85040 (0.0008) -[2023-10-11 00:13:29,542][98559] Updated weights for policy 0, policy_version 85050 (0.0009) -[2023-10-11 00:13:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 173604864. Throughput: 0: 1711.4, 1: 1683.8. Samples: 43405622. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-11 00:13:30,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.460')] -[2023-10-11 00:13:32,046][98560] Updated weights for policy 1, policy_version 84482 (0.0009) -[2023-10-11 00:13:32,417][98560] Updated weights for policy 1, policy_version 84492 (0.0009) -[2023-10-11 00:13:32,780][98560] Updated weights for policy 1, policy_version 84502 (0.0008) -[2023-10-11 00:13:33,146][98560] Updated weights for policy 1, policy_version 84512 (0.0007) -[2023-10-11 00:13:33,513][98559] Updated weights for policy 0, policy_version 85060 (0.0008) -[2023-10-11 00:13:33,880][98559] Updated weights for policy 0, policy_version 85070 (0.0008) -[2023-10-11 00:13:34,248][98559] Updated weights for policy 0, policy_version 85080 (0.0008) -[2023-10-11 00:13:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 173670400. Throughput: 0: 1694.0, 1: 1708.9. Samples: 43426310. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:13:35,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.480')] -[2023-10-11 00:13:37,057][98560] Updated weights for policy 1, policy_version 84522 (0.0009) -[2023-10-11 00:13:37,422][98560] Updated weights for policy 1, policy_version 84532 (0.0009) -[2023-10-11 00:13:37,775][98560] Updated weights for policy 1, policy_version 84542 (0.0009) -[2023-10-11 00:13:38,192][98559] Updated weights for policy 0, policy_version 85090 (0.0010) -[2023-10-11 00:13:38,562][98559] Updated weights for policy 0, policy_version 85100 (0.0010) -[2023-10-11 00:13:38,935][98559] Updated weights for policy 0, policy_version 85110 (0.0009) -[2023-10-11 00:13:39,303][98559] Updated weights for policy 0, policy_version 85120 (0.0008) -[2023-10-11 00:13:40,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 173735936. Throughput: 0: 1721.5, 1: 1695.7. Samples: 43436998. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:13:40,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.480')] -[2023-10-11 00:13:42,047][98560] Updated weights for policy 1, policy_version 84552 (0.0008) -[2023-10-11 00:13:42,406][98560] Updated weights for policy 1, policy_version 84562 (0.0008) -[2023-10-11 00:13:42,779][98560] Updated weights for policy 1, policy_version 84572 (0.0009) -[2023-10-11 00:13:43,404][98559] Updated weights for policy 0, policy_version 85130 (0.0008) -[2023-10-11 00:13:43,775][98559] Updated weights for policy 0, policy_version 85140 (0.0008) -[2023-10-11 00:13:44,145][98559] Updated weights for policy 0, policy_version 85150 (0.0009) -[2023-10-11 00:13:45,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 173801472. Throughput: 0: 1693.0, 1: 1694.5. Samples: 43456638. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:13:45,557][97672] Avg episode reward: [(0, '-0.900'), (1, '22.500')] -[2023-10-11 00:13:47,209][98560] Updated weights for policy 1, policy_version 84582 (0.0009) -[2023-10-11 00:13:47,600][98560] Updated weights for policy 1, policy_version 84592 (0.0008) -[2023-10-11 00:13:47,966][98560] Updated weights for policy 1, policy_version 84602 (0.0009) -[2023-10-11 00:13:48,159][98559] Updated weights for policy 0, policy_version 85160 (0.0009) -[2023-10-11 00:13:48,522][98559] Updated weights for policy 0, policy_version 85170 (0.0007) -[2023-10-11 00:13:48,893][98559] Updated weights for policy 0, policy_version 85180 (0.0009) -[2023-10-11 00:13:50,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 173867008. Throughput: 0: 1707.4, 1: 1708.1. Samples: 43477304. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:13:50,557][97672] Avg episode reward: [(0, '-0.900'), (1, '22.500')] -[2023-10-11 00:13:51,945][98560] Updated weights for policy 1, policy_version 84612 (0.0007) -[2023-10-11 00:13:52,307][98560] Updated weights for policy 1, policy_version 84622 (0.0008) -[2023-10-11 00:13:52,683][98560] Updated weights for policy 1, policy_version 84632 (0.0009) -[2023-10-11 00:13:52,882][98559] Updated weights for policy 0, policy_version 85190 (0.0007) -[2023-10-11 00:13:53,252][98559] Updated weights for policy 0, policy_version 85200 (0.0009) -[2023-10-11 00:13:53,627][98559] Updated weights for policy 0, policy_version 85210 (0.0008) -[2023-10-11 00:13:55,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 173932544. Throughput: 0: 1702.4, 1: 1680.7. Samples: 43487342. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:13:55,556][97672] Avg episode reward: [(0, '-0.900'), (1, '22.520')] -[2023-10-11 00:13:56,552][98560] Updated weights for policy 1, policy_version 84642 (0.0009) -[2023-10-11 00:13:56,919][98560] Updated weights for policy 1, policy_version 84652 (0.0009) -[2023-10-11 00:13:57,284][98560] Updated weights for policy 1, policy_version 84662 (0.0008) -[2023-10-11 00:13:57,558][98559] Updated weights for policy 0, policy_version 85220 (0.0009) -[2023-10-11 00:13:57,651][98560] Updated weights for policy 1, policy_version 84672 (0.0007) -[2023-10-11 00:13:57,920][98559] Updated weights for policy 0, policy_version 85230 (0.0009) -[2023-10-11 00:13:58,282][98559] Updated weights for policy 0, policy_version 85240 (0.0009) -[2023-10-11 00:14:00,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 173998080. Throughput: 0: 1694.5, 1: 1696.8. Samples: 43507522. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:14:00,557][97672] Avg episode reward: [(0, '-0.900'), (1, '22.400')] -[2023-10-11 00:14:01,741][98560] Updated weights for policy 1, policy_version 84682 (0.0007) -[2023-10-11 00:14:02,115][98560] Updated weights for policy 1, policy_version 84692 (0.0008) -[2023-10-11 00:14:02,300][98559] Updated weights for policy 0, policy_version 85250 (0.0007) -[2023-10-11 00:14:02,476][98560] Updated weights for policy 1, policy_version 84702 (0.0009) -[2023-10-11 00:14:02,660][98559] Updated weights for policy 0, policy_version 85260 (0.0007) -[2023-10-11 00:14:03,031][98559] Updated weights for policy 0, policy_version 85270 (0.0010) -[2023-10-11 00:14:03,393][98559] Updated weights for policy 0, policy_version 85280 (0.0007) -[2023-10-11 00:14:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 174063616. Throughput: 0: 1724.7, 1: 1697.2. Samples: 43528456. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:14:05,556][97672] Avg episode reward: [(0, '-0.900'), (1, '22.480')] -[2023-10-11 00:14:06,495][98560] Updated weights for policy 1, policy_version 84712 (0.0009) -[2023-10-11 00:14:06,859][98560] Updated weights for policy 1, policy_version 84722 (0.0008) -[2023-10-11 00:14:07,227][98560] Updated weights for policy 1, policy_version 84732 (0.0009) -[2023-10-11 00:14:07,461][98559] Updated weights for policy 0, policy_version 85290 (0.0008) -[2023-10-11 00:14:07,822][98559] Updated weights for policy 0, policy_version 85300 (0.0009) -[2023-10-11 00:14:08,180][98559] Updated weights for policy 0, policy_version 85310 (0.0008) -[2023-10-11 00:14:10,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 174129152. Throughput: 0: 1691.6, 1: 1672.3. Samples: 43537582. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:14:10,556][97672] Avg episode reward: [(0, '-0.900'), (1, '22.400')] -[2023-10-11 00:14:11,281][98560] Updated weights for policy 1, policy_version 84742 (0.0007) -[2023-10-11 00:14:11,643][98560] Updated weights for policy 1, policy_version 84752 (0.0009) -[2023-10-11 00:14:12,013][98560] Updated weights for policy 1, policy_version 84762 (0.0009) -[2023-10-11 00:14:12,204][98559] Updated weights for policy 0, policy_version 85320 (0.0008) -[2023-10-11 00:14:12,572][98559] Updated weights for policy 0, policy_version 85330 (0.0008) -[2023-10-11 00:14:12,935][98559] Updated weights for policy 0, policy_version 85340 (0.0010) -[2023-10-11 00:14:15,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 174194688. Throughput: 0: 1709.6, 1: 1690.9. Samples: 43558646. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:14:15,557][97672] Avg episode reward: [(0, '-0.860'), (1, '22.400')] -[2023-10-11 00:14:16,027][98560] Updated weights for policy 1, policy_version 84772 (0.0007) -[2023-10-11 00:14:16,391][98560] Updated weights for policy 1, policy_version 84782 (0.0007) -[2023-10-11 00:14:16,754][98560] Updated weights for policy 1, policy_version 84792 (0.0008) -[2023-10-11 00:14:17,010][98559] Updated weights for policy 0, policy_version 85350 (0.0009) -[2023-10-11 00:14:17,373][98559] Updated weights for policy 0, policy_version 85360 (0.0007) -[2023-10-11 00:14:17,741][98559] Updated weights for policy 0, policy_version 85370 (0.0008) -[2023-10-11 00:14:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 174260224. Throughput: 0: 1723.7, 1: 1684.5. Samples: 43579680. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:14:20,557][97672] Avg episode reward: [(0, '-0.860'), (1, '22.340')] -[2023-10-11 00:14:20,744][98560] Updated weights for policy 1, policy_version 84802 (0.0007) -[2023-10-11 00:14:21,111][98560] Updated weights for policy 1, policy_version 84812 (0.0007) -[2023-10-11 00:14:21,484][98560] Updated weights for policy 1, policy_version 84822 (0.0008) -[2023-10-11 00:14:21,532][98559] Updated weights for policy 0, policy_version 85380 (0.0009) -[2023-10-11 00:14:21,852][98560] Updated weights for policy 1, policy_version 84832 (0.0008) -[2023-10-11 00:14:21,907][98559] Updated weights for policy 0, policy_version 85390 (0.0009) -[2023-10-11 00:14:22,272][98559] Updated weights for policy 0, policy_version 85400 (0.0007) -[2023-10-11 00:14:25,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 174325760. Throughput: 0: 1697.8, 1: 1682.8. Samples: 43589122. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:14:25,557][97672] Avg episode reward: [(0, '-0.860'), (1, '22.320')] -[2023-10-11 00:14:25,911][98560] Updated weights for policy 1, policy_version 84842 (0.0007) -[2023-10-11 00:14:25,988][98559] Updated weights for policy 0, policy_version 85410 (0.0008) -[2023-10-11 00:14:26,280][98560] Updated weights for policy 1, policy_version 84852 (0.0007) -[2023-10-11 00:14:26,359][98559] Updated weights for policy 0, policy_version 85420 (0.0007) -[2023-10-11 00:14:26,636][98560] Updated weights for policy 1, policy_version 84862 (0.0009) -[2023-10-11 00:14:26,720][98559] Updated weights for policy 0, policy_version 85430 (0.0007) -[2023-10-11 00:14:27,082][98559] Updated weights for policy 0, policy_version 85440 (0.0009) -[2023-10-11 00:14:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 174391296. Throughput: 0: 1723.5, 1: 1691.1. Samples: 43610292. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:14:30,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.340')] -[2023-10-11 00:14:30,634][98560] Updated weights for policy 1, policy_version 84872 (0.0008) -[2023-10-11 00:14:30,991][98560] Updated weights for policy 1, policy_version 84882 (0.0008) -[2023-10-11 00:14:31,030][98559] Updated weights for policy 0, policy_version 85450 (0.0009) -[2023-10-11 00:14:31,359][98560] Updated weights for policy 1, policy_version 84892 (0.0009) -[2023-10-11 00:14:31,400][98559] Updated weights for policy 0, policy_version 85460 (0.0008) -[2023-10-11 00:14:31,770][98559] Updated weights for policy 0, policy_version 85470 (0.0009) -[2023-10-11 00:14:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 174456832. Throughput: 0: 1717.5, 1: 1696.7. Samples: 43630940. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-11 00:14:35,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.340')] -[2023-10-11 00:14:35,565][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000085472_87523328.pth... -[2023-10-11 00:14:35,598][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000083872_85884928.pth -[2023-10-11 00:14:35,618][98560] Updated weights for policy 1, policy_version 84902 (0.0008) -[2023-10-11 00:14:36,009][98560] Updated weights for policy 1, policy_version 84912 (0.0008) -[2023-10-11 00:14:36,066][98559] Updated weights for policy 0, policy_version 85480 (0.0008) -[2023-10-11 00:14:36,375][98560] Updated weights for policy 1, policy_version 84922 (0.0007) -[2023-10-11 00:14:36,432][98559] Updated weights for policy 0, policy_version 85490 (0.0007) -[2023-10-11 00:14:36,594][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000084928_86966272.pth... -[2023-10-11 00:14:36,622][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000083328_85327872.pth -[2023-10-11 00:14:36,801][98559] Updated weights for policy 0, policy_version 85500 (0.0008) -[2023-10-11 00:14:40,130][98560] Updated weights for policy 1, policy_version 84932 (0.0008) -[2023-10-11 00:14:40,495][98560] Updated weights for policy 1, policy_version 84942 (0.0008) -[2023-10-11 00:14:40,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 174522368. Throughput: 0: 1703.1, 1: 1690.0. Samples: 43640032. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-11 00:14:40,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.320')] -[2023-10-11 00:14:40,820][98559] Updated weights for policy 0, policy_version 85510 (0.0009) -[2023-10-11 00:14:40,857][98560] Updated weights for policy 1, policy_version 84952 (0.0009) -[2023-10-11 00:14:41,190][98559] Updated weights for policy 0, policy_version 85520 (0.0008) -[2023-10-11 00:14:41,556][98559] Updated weights for policy 0, policy_version 85530 (0.0007) -[2023-10-11 00:14:45,050][98560] Updated weights for policy 1, policy_version 84962 (0.0008) -[2023-10-11 00:14:45,417][98560] Updated weights for policy 1, policy_version 84972 (0.0009) -[2023-10-11 00:14:45,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 174587904. Throughput: 0: 1711.2, 1: 1699.2. Samples: 43660994. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-11 00:14:45,556][97672] Avg episode reward: [(0, '-0.840'), (1, '22.340')] -[2023-10-11 00:14:45,625][98559] Updated weights for policy 0, policy_version 85540 (0.0007) -[2023-10-11 00:14:45,790][98560] Updated weights for policy 1, policy_version 84982 (0.0009) -[2023-10-11 00:14:46,000][98559] Updated weights for policy 0, policy_version 85550 (0.0008) -[2023-10-11 00:14:46,162][98560] Updated weights for policy 1, policy_version 84992 (0.0009) -[2023-10-11 00:14:46,370][98559] Updated weights for policy 0, policy_version 85560 (0.0008) -[2023-10-11 00:14:50,117][98560] Updated weights for policy 1, policy_version 85002 (0.0008) -[2023-10-11 00:14:50,405][98559] Updated weights for policy 0, policy_version 85570 (0.0009) -[2023-10-11 00:14:50,490][98560] Updated weights for policy 1, policy_version 85012 (0.0008) -[2023-10-11 00:14:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 174653440. Throughput: 0: 1706.2, 1: 1703.1. Samples: 43681878. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-11 00:14:50,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.280')] -[2023-10-11 00:14:50,762][98559] Updated weights for policy 0, policy_version 85580 (0.0007) -[2023-10-11 00:14:50,848][98560] Updated weights for policy 1, policy_version 85022 (0.0008) -[2023-10-11 00:14:51,138][98559] Updated weights for policy 0, policy_version 85590 (0.0010) -[2023-10-11 00:14:51,501][98559] Updated weights for policy 0, policy_version 85600 (0.0009) -[2023-10-11 00:14:54,619][98560] Updated weights for policy 1, policy_version 85032 (0.0010) -[2023-10-11 00:14:54,987][98560] Updated weights for policy 1, policy_version 85042 (0.0010) -[2023-10-11 00:14:55,353][98560] Updated weights for policy 1, policy_version 85052 (0.0007) -[2023-10-11 00:14:55,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 174751744. Throughput: 0: 1705.2, 1: 1706.2. Samples: 43691096. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-11 00:14:55,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.400')] -[2023-10-11 00:14:55,636][98559] Updated weights for policy 0, policy_version 85610 (0.0010) -[2023-10-11 00:14:56,004][98559] Updated weights for policy 0, policy_version 85620 (0.0009) -[2023-10-11 00:14:56,378][98559] Updated weights for policy 0, policy_version 85630 (0.0010) -[2023-10-11 00:14:59,225][98560] Updated weights for policy 1, policy_version 85062 (0.0009) -[2023-10-11 00:14:59,582][98560] Updated weights for policy 1, policy_version 85072 (0.0009) -[2023-10-11 00:14:59,951][98560] Updated weights for policy 1, policy_version 85082 (0.0009) -[2023-10-11 00:15:00,191][98559] Updated weights for policy 0, policy_version 85640 (0.0008) -[2023-10-11 00:15:00,552][98559] Updated weights for policy 0, policy_version 85650 (0.0010) -[2023-10-11 00:15:00,556][97672] Fps is (10 sec: 16384.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 174817280. Throughput: 0: 1703.8, 1: 1711.0. Samples: 43712314. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-11 00:15:00,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.420')] -[2023-10-11 00:15:00,919][98559] Updated weights for policy 0, policy_version 85660 (0.0008) -[2023-10-11 00:15:03,958][98560] Updated weights for policy 1, policy_version 85092 (0.0008) -[2023-10-11 00:15:04,322][98560] Updated weights for policy 1, policy_version 85102 (0.0008) -[2023-10-11 00:15:04,686][98560] Updated weights for policy 1, policy_version 85112 (0.0008) -[2023-10-11 00:15:04,877][98559] Updated weights for policy 0, policy_version 85670 (0.0008) -[2023-10-11 00:15:05,257][98559] Updated weights for policy 0, policy_version 85680 (0.0008) -[2023-10-11 00:15:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 174882816. Throughput: 0: 1694.1, 1: 1693.6. Samples: 43732130. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-11 00:15:05,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.500')] -[2023-10-11 00:15:05,618][98559] Updated weights for policy 0, policy_version 85690 (0.0009) -[2023-10-11 00:15:08,674][98560] Updated weights for policy 1, policy_version 85122 (0.0009) -[2023-10-11 00:15:09,045][98560] Updated weights for policy 1, policy_version 85132 (0.0009) -[2023-10-11 00:15:09,410][98560] Updated weights for policy 1, policy_version 85142 (0.0007) -[2023-10-11 00:15:09,629][98559] Updated weights for policy 0, policy_version 85700 (0.0008) -[2023-10-11 00:15:09,770][98560] Updated weights for policy 1, policy_version 85152 (0.0007) -[2023-10-11 00:15:09,987][98559] Updated weights for policy 0, policy_version 85710 (0.0008) -[2023-10-11 00:15:10,360][98559] Updated weights for policy 0, policy_version 85720 (0.0009) -[2023-10-11 00:15:10,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 174948352. Throughput: 0: 1709.5, 1: 1713.3. Samples: 43743148. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-11 00:15:10,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.540')] -[2023-10-11 00:15:13,810][98560] Updated weights for policy 1, policy_version 85162 (0.0010) -[2023-10-11 00:15:14,183][98560] Updated weights for policy 1, policy_version 85172 (0.0008) -[2023-10-11 00:15:14,433][98559] Updated weights for policy 0, policy_version 85730 (0.0009) -[2023-10-11 00:15:14,545][98560] Updated weights for policy 1, policy_version 85182 (0.0008) -[2023-10-11 00:15:14,803][98559] Updated weights for policy 0, policy_version 85740 (0.0007) -[2023-10-11 00:15:15,165][98559] Updated weights for policy 0, policy_version 85750 (0.0007) -[2023-10-11 00:15:15,530][98559] Updated weights for policy 0, policy_version 85760 (0.0007) -[2023-10-11 00:15:15,556][97672] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 175046656. Throughput: 0: 1705.2, 1: 1704.4. Samples: 43763726. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-11 00:15:15,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.580')] -[2023-10-11 00:15:18,506][98560] Updated weights for policy 1, policy_version 85192 (0.0008) -[2023-10-11 00:15:18,857][98560] Updated weights for policy 1, policy_version 85202 (0.0010) -[2023-10-11 00:15:19,217][98560] Updated weights for policy 1, policy_version 85212 (0.0009) -[2023-10-11 00:15:19,372][98559] Updated weights for policy 0, policy_version 85770 (0.0007) -[2023-10-11 00:15:19,743][98559] Updated weights for policy 0, policy_version 85780 (0.0008) -[2023-10-11 00:15:20,101][98559] Updated weights for policy 0, policy_version 85790 (0.0008) -[2023-10-11 00:15:20,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 175112192. Throughput: 0: 1685.7, 1: 1689.8. Samples: 43782836. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-11 00:15:20,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.500')] -[2023-10-11 00:15:23,379][98560] Updated weights for policy 1, policy_version 85222 (0.0008) -[2023-10-11 00:15:23,774][98560] Updated weights for policy 1, policy_version 85232 (0.0008) -[2023-10-11 00:15:24,137][98560] Updated weights for policy 1, policy_version 85242 (0.0007) -[2023-10-11 00:15:24,139][98559] Updated weights for policy 0, policy_version 85800 (0.0007) -[2023-10-11 00:15:24,508][98559] Updated weights for policy 0, policy_version 85810 (0.0009) -[2023-10-11 00:15:24,869][98559] Updated weights for policy 0, policy_version 85820 (0.0011) -[2023-10-11 00:15:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 175177728. Throughput: 0: 1717.1, 1: 1720.4. Samples: 43794720. Policy #0 lag: (min: 25.0, avg: 40.4, max: 57.0) -[2023-10-11 00:15:25,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.520')] -[2023-10-11 00:15:28,162][98560] Updated weights for policy 1, policy_version 85252 (0.0010) -[2023-10-11 00:15:28,534][98560] Updated weights for policy 1, policy_version 85262 (0.0009) -[2023-10-11 00:15:28,822][98559] Updated weights for policy 0, policy_version 85830 (0.0009) -[2023-10-11 00:15:28,911][98560] Updated weights for policy 1, policy_version 85272 (0.0008) -[2023-10-11 00:15:29,198][98559] Updated weights for policy 0, policy_version 85840 (0.0009) -[2023-10-11 00:15:29,568][98559] Updated weights for policy 0, policy_version 85850 (0.0007) -[2023-10-11 00:15:30,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 175243264. Throughput: 0: 1700.6, 1: 1696.6. Samples: 43813870. Policy #0 lag: (min: 25.0, avg: 40.4, max: 57.0) -[2023-10-11 00:15:30,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.520')] -[2023-10-11 00:15:32,853][98560] Updated weights for policy 1, policy_version 85282 (0.0009) -[2023-10-11 00:15:33,220][98560] Updated weights for policy 1, policy_version 85292 (0.0008) -[2023-10-11 00:15:33,587][98559] Updated weights for policy 0, policy_version 85860 (0.0007) -[2023-10-11 00:15:33,593][98560] Updated weights for policy 1, policy_version 85302 (0.0007) -[2023-10-11 00:15:33,940][98559] Updated weights for policy 0, policy_version 85870 (0.0007) -[2023-10-11 00:15:33,957][98560] Updated weights for policy 1, policy_version 85312 (0.0008) -[2023-10-11 00:15:34,312][98559] Updated weights for policy 0, policy_version 85880 (0.0008) -[2023-10-11 00:15:35,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 175308800. Throughput: 0: 1692.8, 1: 1684.2. Samples: 43833840. Policy #0 lag: (min: 25.0, avg: 40.4, max: 57.0) -[2023-10-11 00:15:35,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.560')] -[2023-10-11 00:15:38,093][98560] Updated weights for policy 1, policy_version 85322 (0.0008) -[2023-10-11 00:15:38,246][98559] Updated weights for policy 0, policy_version 85890 (0.0007) -[2023-10-11 00:15:38,464][98560] Updated weights for policy 1, policy_version 85332 (0.0008) -[2023-10-11 00:15:38,618][98559] Updated weights for policy 0, policy_version 85900 (0.0009) -[2023-10-11 00:15:38,835][98560] Updated weights for policy 1, policy_version 85342 (0.0007) -[2023-10-11 00:15:38,983][98559] Updated weights for policy 0, policy_version 85910 (0.0010) -[2023-10-11 00:15:39,348][98559] Updated weights for policy 0, policy_version 85920 (0.0008) -[2023-10-11 00:15:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 175374336. Throughput: 0: 1722.8, 1: 1713.7. Samples: 43845738. Policy #0 lag: (min: 25.0, avg: 40.4, max: 57.0) -[2023-10-11 00:15:40,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.600')] -[2023-10-11 00:15:42,949][98560] Updated weights for policy 1, policy_version 85352 (0.0008) -[2023-10-11 00:15:43,238][98559] Updated weights for policy 0, policy_version 85930 (0.0009) -[2023-10-11 00:15:43,328][98560] Updated weights for policy 1, policy_version 85362 (0.0009) -[2023-10-11 00:15:43,594][98559] Updated weights for policy 0, policy_version 85940 (0.0008) -[2023-10-11 00:15:43,692][98560] Updated weights for policy 1, policy_version 85372 (0.0008) -[2023-10-11 00:15:43,960][98559] Updated weights for policy 0, policy_version 85950 (0.0009) -[2023-10-11 00:15:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 175439872. Throughput: 0: 1699.5, 1: 1688.0. Samples: 43864750. Policy #0 lag: (min: 25.0, avg: 40.4, max: 57.0) -[2023-10-11 00:15:45,556][97672] Avg episode reward: [(0, '-0.820'), (1, '22.600')] -[2023-10-11 00:15:47,717][98560] Updated weights for policy 1, policy_version 85382 (0.0007) -[2023-10-11 00:15:47,918][98559] Updated weights for policy 0, policy_version 85960 (0.0008) -[2023-10-11 00:15:48,085][98560] Updated weights for policy 1, policy_version 85392 (0.0009) -[2023-10-11 00:15:48,286][98559] Updated weights for policy 0, policy_version 85970 (0.0007) -[2023-10-11 00:15:48,453][98560] Updated weights for policy 1, policy_version 85402 (0.0008) -[2023-10-11 00:15:48,652][98559] Updated weights for policy 0, policy_version 85980 (0.0009) -[2023-10-11 00:15:50,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 175505408. Throughput: 0: 1711.1, 1: 1697.9. Samples: 43885540. Policy #0 lag: (min: 25.0, avg: 40.4, max: 57.0) -[2023-10-11 00:15:50,558][97672] Avg episode reward: [(0, '-0.760'), (1, '22.560')] -[2023-10-11 00:15:52,469][98560] Updated weights for policy 1, policy_version 85412 (0.0008) -[2023-10-11 00:15:52,671][98559] Updated weights for policy 0, policy_version 85990 (0.0008) -[2023-10-11 00:15:52,825][98560] Updated weights for policy 1, policy_version 85422 (0.0008) -[2023-10-11 00:15:53,035][98559] Updated weights for policy 0, policy_version 86000 (0.0007) -[2023-10-11 00:15:53,188][98560] Updated weights for policy 1, policy_version 85432 (0.0010) -[2023-10-11 00:15:53,400][98559] Updated weights for policy 0, policy_version 86010 (0.0008) -[2023-10-11 00:15:55,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 175570944. Throughput: 0: 1702.4, 1: 1694.3. Samples: 43895996. Policy #0 lag: (min: 25.0, avg: 40.4, max: 57.0) -[2023-10-11 00:15:55,557][97672] Avg episode reward: [(0, '-0.760'), (1, '22.460')] -[2023-10-11 00:15:57,163][98560] Updated weights for policy 1, policy_version 85442 (0.0008) -[2023-10-11 00:15:57,462][98559] Updated weights for policy 0, policy_version 86020 (0.0008) -[2023-10-11 00:15:57,526][98560] Updated weights for policy 1, policy_version 85452 (0.0009) -[2023-10-11 00:15:57,830][98559] Updated weights for policy 0, policy_version 86030 (0.0008) -[2023-10-11 00:15:57,882][98560] Updated weights for policy 1, policy_version 85462 (0.0008) -[2023-10-11 00:15:58,200][98559] Updated weights for policy 0, policy_version 86040 (0.0011) -[2023-10-11 00:15:58,247][98560] Updated weights for policy 1, policy_version 85472 (0.0007) -[2023-10-11 00:16:00,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 175636480. Throughput: 0: 1697.0, 1: 1684.2. Samples: 43915882. Policy #0 lag: (min: 25.0, avg: 40.4, max: 57.0) -[2023-10-11 00:16:00,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.440')] -[2023-10-11 00:16:02,143][98559] Updated weights for policy 0, policy_version 86050 (0.0011) -[2023-10-11 00:16:02,325][98560] Updated weights for policy 1, policy_version 85482 (0.0007) -[2023-10-11 00:16:02,504][98559] Updated weights for policy 0, policy_version 86060 (0.0010) -[2023-10-11 00:16:02,690][98560] Updated weights for policy 1, policy_version 85492 (0.0007) -[2023-10-11 00:16:02,876][98559] Updated weights for policy 0, policy_version 86070 (0.0009) -[2023-10-11 00:16:03,061][98560] Updated weights for policy 1, policy_version 85502 (0.0008) -[2023-10-11 00:16:03,237][98559] Updated weights for policy 0, policy_version 86080 (0.0008) -[2023-10-11 00:16:05,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 175702016. Throughput: 0: 1721.7, 1: 1699.3. Samples: 43936782. Policy #0 lag: (min: 25.0, avg: 40.4, max: 57.0) -[2023-10-11 00:16:05,556][97672] Avg episode reward: [(0, '-0.780'), (1, '22.460')] -[2023-10-11 00:16:06,965][98560] Updated weights for policy 1, policy_version 85512 (0.0008) -[2023-10-11 00:16:07,212][98559] Updated weights for policy 0, policy_version 86090 (0.0009) -[2023-10-11 00:16:07,326][98560] Updated weights for policy 1, policy_version 85522 (0.0007) -[2023-10-11 00:16:07,574][98559] Updated weights for policy 0, policy_version 86100 (0.0009) -[2023-10-11 00:16:07,697][98560] Updated weights for policy 1, policy_version 85532 (0.0008) -[2023-10-11 00:16:07,942][98559] Updated weights for policy 0, policy_version 86110 (0.0007) -[2023-10-11 00:16:10,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 175767552. Throughput: 0: 1693.0, 1: 1679.3. Samples: 43946474. Policy #0 lag: (min: 25.0, avg: 40.4, max: 57.0) -[2023-10-11 00:16:10,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.500')] -[2023-10-11 00:16:11,648][98560] Updated weights for policy 1, policy_version 85542 (0.0008) -[2023-10-11 00:16:11,944][98559] Updated weights for policy 0, policy_version 86120 (0.0007) -[2023-10-11 00:16:12,015][98560] Updated weights for policy 1, policy_version 85552 (0.0008) -[2023-10-11 00:16:12,309][98559] Updated weights for policy 0, policy_version 86130 (0.0008) -[2023-10-11 00:16:12,384][98560] Updated weights for policy 1, policy_version 85562 (0.0008) -[2023-10-11 00:16:12,670][98559] Updated weights for policy 0, policy_version 86140 (0.0007) -[2023-10-11 00:16:15,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 175833088. Throughput: 0: 1713.0, 1: 1698.1. Samples: 43967370. Policy #0 lag: (min: 25.0, avg: 40.4, max: 57.0) -[2023-10-11 00:16:15,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.520')] -[2023-10-11 00:16:16,560][98560] Updated weights for policy 1, policy_version 85572 (0.0009) -[2023-10-11 00:16:16,689][98559] Updated weights for policy 0, policy_version 86150 (0.0009) -[2023-10-11 00:16:16,940][98560] Updated weights for policy 1, policy_version 85582 (0.0009) -[2023-10-11 00:16:17,051][98559] Updated weights for policy 0, policy_version 86160 (0.0010) -[2023-10-11 00:16:17,307][98560] Updated weights for policy 1, policy_version 85592 (0.0008) -[2023-10-11 00:16:17,422][98559] Updated weights for policy 0, policy_version 86170 (0.0008) -[2023-10-11 00:16:20,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 175898624. Throughput: 0: 1722.3, 1: 1708.6. Samples: 43988230. Policy #0 lag: (min: 25.0, avg: 40.4, max: 57.0) -[2023-10-11 00:16:20,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.540')] -[2023-10-11 00:16:21,403][98560] Updated weights for policy 1, policy_version 85602 (0.0009) -[2023-10-11 00:16:21,537][98559] Updated weights for policy 0, policy_version 86180 (0.0009) -[2023-10-11 00:16:21,768][98560] Updated weights for policy 1, policy_version 85612 (0.0007) -[2023-10-11 00:16:21,903][98559] Updated weights for policy 0, policy_version 86190 (0.0010) -[2023-10-11 00:16:22,133][98560] Updated weights for policy 1, policy_version 85622 (0.0009) -[2023-10-11 00:16:22,270][98559] Updated weights for policy 0, policy_version 86200 (0.0009) -[2023-10-11 00:16:22,504][98560] Updated weights for policy 1, policy_version 85632 (0.0008) -[2023-10-11 00:16:25,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 175964160. Throughput: 0: 1694.1, 1: 1674.9. Samples: 43997346. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:16:25,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.500')] -[2023-10-11 00:16:26,220][98559] Updated weights for policy 0, policy_version 86210 (0.0007) -[2023-10-11 00:16:26,420][98560] Updated weights for policy 1, policy_version 85642 (0.0008) -[2023-10-11 00:16:26,581][98559] Updated weights for policy 0, policy_version 86220 (0.0007) -[2023-10-11 00:16:26,777][98560] Updated weights for policy 1, policy_version 85652 (0.0009) -[2023-10-11 00:16:26,952][98559] Updated weights for policy 0, policy_version 86230 (0.0008) -[2023-10-11 00:16:27,139][98560] Updated weights for policy 1, policy_version 85662 (0.0009) -[2023-10-11 00:16:27,307][98559] Updated weights for policy 0, policy_version 86240 (0.0008) -[2023-10-11 00:16:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 176029696. Throughput: 0: 1719.2, 1: 1702.7. Samples: 44018732. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:16:30,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.480')] -[2023-10-11 00:16:31,141][98560] Updated weights for policy 1, policy_version 85672 (0.0008) -[2023-10-11 00:16:31,198][98559] Updated weights for policy 0, policy_version 86250 (0.0008) -[2023-10-11 00:16:31,508][98560] Updated weights for policy 1, policy_version 85682 (0.0007) -[2023-10-11 00:16:31,569][98559] Updated weights for policy 0, policy_version 86260 (0.0009) -[2023-10-11 00:16:31,870][98560] Updated weights for policy 1, policy_version 85692 (0.0007) -[2023-10-11 00:16:31,925][98559] Updated weights for policy 0, policy_version 86270 (0.0009) -[2023-10-11 00:16:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 176095232. Throughput: 0: 1714.9, 1: 1709.9. Samples: 44039656. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:16:35,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.560')] -[2023-10-11 00:16:35,570][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000085696_87752704.pth... -[2023-10-11 00:16:35,571][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000086272_88342528.pth... -[2023-10-11 00:16:35,609][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000084128_86147072.pth -[2023-10-11 00:16:35,615][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000084672_86704128.pth -[2023-10-11 00:16:35,985][98560] Updated weights for policy 1, policy_version 85702 (0.0010) -[2023-10-11 00:16:36,026][98559] Updated weights for policy 0, policy_version 86280 (0.0007) -[2023-10-11 00:16:36,345][98560] Updated weights for policy 1, policy_version 85712 (0.0009) -[2023-10-11 00:16:36,389][98559] Updated weights for policy 0, policy_version 86290 (0.0008) -[2023-10-11 00:16:36,705][98560] Updated weights for policy 1, policy_version 85722 (0.0008) -[2023-10-11 00:16:36,755][98559] Updated weights for policy 0, policy_version 86300 (0.0009) -[2023-10-11 00:16:40,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 176160768. Throughput: 0: 1706.8, 1: 1690.3. Samples: 44048866. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:16:40,558][97672] Avg episode reward: [(0, '-0.780'), (1, '22.620')] -[2023-10-11 00:16:40,755][98559] Updated weights for policy 0, policy_version 86310 (0.0009) -[2023-10-11 00:16:40,768][98560] Updated weights for policy 1, policy_version 85732 (0.0007) -[2023-10-11 00:16:41,125][98559] Updated weights for policy 0, policy_version 86320 (0.0007) -[2023-10-11 00:16:41,132][98560] Updated weights for policy 1, policy_version 85742 (0.0007) -[2023-10-11 00:16:41,482][98559] Updated weights for policy 0, policy_version 86330 (0.0007) -[2023-10-11 00:16:41,500][98560] Updated weights for policy 1, policy_version 85752 (0.0007) -[2023-10-11 00:16:45,442][98559] Updated weights for policy 0, policy_version 86340 (0.0010) -[2023-10-11 00:16:45,551][98560] Updated weights for policy 1, policy_version 85762 (0.0008) -[2023-10-11 00:16:45,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 176226304. Throughput: 0: 1718.5, 1: 1708.7. Samples: 44070108. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:16:45,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.560')] -[2023-10-11 00:16:45,811][98559] Updated weights for policy 0, policy_version 86350 (0.0008) -[2023-10-11 00:16:45,924][98560] Updated weights for policy 1, policy_version 85772 (0.0009) -[2023-10-11 00:16:46,176][98559] Updated weights for policy 0, policy_version 86360 (0.0009) -[2023-10-11 00:16:46,289][98560] Updated weights for policy 1, policy_version 85782 (0.0007) -[2023-10-11 00:16:46,645][98560] Updated weights for policy 1, policy_version 85792 (0.0008) -[2023-10-11 00:16:50,420][98559] Updated weights for policy 0, policy_version 86370 (0.0008) -[2023-10-11 00:16:50,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 176291840. Throughput: 0: 1712.7, 1: 1711.5. Samples: 44090870. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:16:50,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.540')] -[2023-10-11 00:16:50,658][98560] Updated weights for policy 1, policy_version 85802 (0.0008) -[2023-10-11 00:16:50,779][98559] Updated weights for policy 0, policy_version 86380 (0.0009) -[2023-10-11 00:16:51,019][98560] Updated weights for policy 1, policy_version 85812 (0.0009) -[2023-10-11 00:16:51,146][98559] Updated weights for policy 0, policy_version 86390 (0.0007) -[2023-10-11 00:16:51,385][98560] Updated weights for policy 1, policy_version 85822 (0.0009) -[2023-10-11 00:16:51,504][98559] Updated weights for policy 0, policy_version 86400 (0.0007) -[2023-10-11 00:16:55,415][98560] Updated weights for policy 1, policy_version 85832 (0.0007) -[2023-10-11 00:16:55,541][98559] Updated weights for policy 0, policy_version 86410 (0.0008) -[2023-10-11 00:16:55,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 176357376. Throughput: 0: 1714.1, 1: 1704.7. Samples: 44100320. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:16:55,556][97672] Avg episode reward: [(0, '-0.800'), (1, '22.580')] -[2023-10-11 00:16:55,793][98560] Updated weights for policy 1, policy_version 85842 (0.0007) -[2023-10-11 00:16:55,910][98559] Updated weights for policy 0, policy_version 86420 (0.0009) -[2023-10-11 00:16:56,149][98560] Updated weights for policy 1, policy_version 85852 (0.0008) -[2023-10-11 00:16:56,264][98559] Updated weights for policy 0, policy_version 86430 (0.0008) -[2023-10-11 00:17:00,109][98560] Updated weights for policy 1, policy_version 85862 (0.0009) -[2023-10-11 00:17:00,234][98559] Updated weights for policy 0, policy_version 86440 (0.0008) -[2023-10-11 00:17:00,473][98560] Updated weights for policy 1, policy_version 85872 (0.0008) -[2023-10-11 00:17:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 176422912. Throughput: 0: 1709.1, 1: 1704.3. Samples: 44120970. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:17:00,556][97672] Avg episode reward: [(0, '-0.800'), (1, '22.600')] -[2023-10-11 00:17:00,601][98559] Updated weights for policy 0, policy_version 86450 (0.0008) -[2023-10-11 00:17:00,841][98560] Updated weights for policy 1, policy_version 85882 (0.0007) -[2023-10-11 00:17:00,967][98559] Updated weights for policy 0, policy_version 86460 (0.0009) -[2023-10-11 00:17:04,921][98559] Updated weights for policy 0, policy_version 86470 (0.0008) -[2023-10-11 00:17:05,009][98560] Updated weights for policy 1, policy_version 85892 (0.0008) -[2023-10-11 00:17:05,290][98559] Updated weights for policy 0, policy_version 86480 (0.0007) -[2023-10-11 00:17:05,380][98560] Updated weights for policy 1, policy_version 85902 (0.0010) -[2023-10-11 00:17:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 176488448. Throughput: 0: 1698.9, 1: 1704.2. Samples: 44141372. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:17:05,556][97672] Avg episode reward: [(0, '-0.840'), (1, '22.600')] -[2023-10-11 00:17:05,651][98559] Updated weights for policy 0, policy_version 86490 (0.0007) -[2023-10-11 00:17:05,752][98560] Updated weights for policy 1, policy_version 85912 (0.0008) -[2023-10-11 00:17:09,494][98559] Updated weights for policy 0, policy_version 86500 (0.0008) -[2023-10-11 00:17:09,757][98560] Updated weights for policy 1, policy_version 85922 (0.0009) -[2023-10-11 00:17:09,859][98559] Updated weights for policy 0, policy_version 86510 (0.0008) -[2023-10-11 00:17:10,125][98560] Updated weights for policy 1, policy_version 85932 (0.0009) -[2023-10-11 00:17:10,222][98559] Updated weights for policy 0, policy_version 86520 (0.0008) -[2023-10-11 00:17:10,480][98560] Updated weights for policy 1, policy_version 85942 (0.0008) -[2023-10-11 00:17:10,556][97672] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 176586752. Throughput: 0: 1714.8, 1: 1704.6. Samples: 44151220. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:17:10,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.620')] -[2023-10-11 00:17:10,850][98560] Updated weights for policy 1, policy_version 85952 (0.0008) -[2023-10-11 00:17:14,016][98559] Updated weights for policy 0, policy_version 86530 (0.0008) -[2023-10-11 00:17:14,386][98559] Updated weights for policy 0, policy_version 86540 (0.0009) -[2023-10-11 00:17:14,749][98559] Updated weights for policy 0, policy_version 86550 (0.0010) -[2023-10-11 00:17:14,905][98560] Updated weights for policy 1, policy_version 85962 (0.0007) -[2023-10-11 00:17:15,118][98559] Updated weights for policy 0, policy_version 86560 (0.0009) -[2023-10-11 00:17:15,268][98560] Updated weights for policy 1, policy_version 85972 (0.0007) -[2023-10-11 00:17:15,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 176652288. Throughput: 0: 1710.5, 1: 1700.1. Samples: 44172210. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:17:15,556][97672] Avg episode reward: [(0, '-0.840'), (1, '22.560')] -[2023-10-11 00:17:15,623][98560] Updated weights for policy 1, policy_version 85982 (0.0007) -[2023-10-11 00:17:19,087][98559] Updated weights for policy 0, policy_version 86570 (0.0009) -[2023-10-11 00:17:19,450][98559] Updated weights for policy 0, policy_version 86580 (0.0009) -[2023-10-11 00:17:19,722][98560] Updated weights for policy 1, policy_version 85992 (0.0008) -[2023-10-11 00:17:19,818][98559] Updated weights for policy 0, policy_version 86590 (0.0008) -[2023-10-11 00:17:20,089][98560] Updated weights for policy 1, policy_version 86002 (0.0007) -[2023-10-11 00:17:20,456][98560] Updated weights for policy 1, policy_version 86012 (0.0009) -[2023-10-11 00:17:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 176717824. Throughput: 0: 1694.6, 1: 1692.6. Samples: 44192078. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:17:20,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.540')] -[2023-10-11 00:17:23,721][98559] Updated weights for policy 0, policy_version 86600 (0.0008) -[2023-10-11 00:17:24,097][98559] Updated weights for policy 0, policy_version 86610 (0.0009) -[2023-10-11 00:17:24,430][98560] Updated weights for policy 1, policy_version 86022 (0.0009) -[2023-10-11 00:17:24,461][98559] Updated weights for policy 0, policy_version 86620 (0.0009) -[2023-10-11 00:17:24,801][98560] Updated weights for policy 1, policy_version 86032 (0.0008) -[2023-10-11 00:17:25,167][98560] Updated weights for policy 1, policy_version 86042 (0.0009) -[2023-10-11 00:17:25,556][97672] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 176816128. Throughput: 0: 1721.2, 1: 1699.8. Samples: 44202810. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:17:25,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.300')] -[2023-10-11 00:17:28,581][98559] Updated weights for policy 0, policy_version 86630 (0.0008) -[2023-10-11 00:17:28,948][98559] Updated weights for policy 0, policy_version 86640 (0.0009) -[2023-10-11 00:17:29,309][98559] Updated weights for policy 0, policy_version 86650 (0.0008) -[2023-10-11 00:17:29,322][98560] Updated weights for policy 1, policy_version 86052 (0.0009) -[2023-10-11 00:17:29,694][98560] Updated weights for policy 1, policy_version 86062 (0.0008) -[2023-10-11 00:17:30,059][98560] Updated weights for policy 1, policy_version 86072 (0.0008) -[2023-10-11 00:17:30,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 176881664. Throughput: 0: 1694.9, 1: 1694.0. Samples: 44222606. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:17:30,556][97672] Avg episode reward: [(0, '-0.840'), (1, '22.300')] -[2023-10-11 00:17:33,326][98559] Updated weights for policy 0, policy_version 86660 (0.0008) -[2023-10-11 00:17:33,688][98559] Updated weights for policy 0, policy_version 86670 (0.0008) -[2023-10-11 00:17:34,048][98559] Updated weights for policy 0, policy_version 86680 (0.0007) -[2023-10-11 00:17:34,139][98560] Updated weights for policy 1, policy_version 86082 (0.0009) -[2023-10-11 00:17:34,509][98560] Updated weights for policy 1, policy_version 86092 (0.0007) -[2023-10-11 00:17:34,871][98560] Updated weights for policy 1, policy_version 86102 (0.0008) -[2023-10-11 00:17:35,244][98560] Updated weights for policy 1, policy_version 86112 (0.0010) -[2023-10-11 00:17:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 176947200. Throughput: 0: 1698.1, 1: 1676.6. Samples: 44242732. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:17:35,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.140')] -[2023-10-11 00:17:38,076][98559] Updated weights for policy 0, policy_version 86690 (0.0009) -[2023-10-11 00:17:38,449][98559] Updated weights for policy 0, policy_version 86700 (0.0009) -[2023-10-11 00:17:38,816][98559] Updated weights for policy 0, policy_version 86710 (0.0008) -[2023-10-11 00:17:39,181][98559] Updated weights for policy 0, policy_version 86720 (0.0009) -[2023-10-11 00:17:39,289][98560] Updated weights for policy 1, policy_version 86122 (0.0008) -[2023-10-11 00:17:39,661][98560] Updated weights for policy 1, policy_version 86132 (0.0008) -[2023-10-11 00:17:40,031][98560] Updated weights for policy 1, policy_version 86142 (0.0009) -[2023-10-11 00:17:40,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 177012736. Throughput: 0: 1713.9, 1: 1689.7. Samples: 44253486. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:17:40,557][97672] Avg episode reward: [(0, '-0.840'), (1, '21.840')] -[2023-10-11 00:17:43,223][98559] Updated weights for policy 0, policy_version 86730 (0.0011) -[2023-10-11 00:17:43,582][98559] Updated weights for policy 0, policy_version 86740 (0.0011) -[2023-10-11 00:17:43,946][98559] Updated weights for policy 0, policy_version 86750 (0.0008) -[2023-10-11 00:17:44,034][98560] Updated weights for policy 1, policy_version 86152 (0.0009) -[2023-10-11 00:17:44,402][98560] Updated weights for policy 1, policy_version 86162 (0.0010) -[2023-10-11 00:17:44,767][98560] Updated weights for policy 1, policy_version 86172 (0.0007) -[2023-10-11 00:17:45,556][97672] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 177078272. Throughput: 0: 1699.2, 1: 1692.5. Samples: 44273594. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:17:45,556][97672] Avg episode reward: [(0, '-0.840'), (1, '21.320')] -[2023-10-11 00:17:47,865][98559] Updated weights for policy 0, policy_version 86760 (0.0009) -[2023-10-11 00:17:48,231][98559] Updated weights for policy 0, policy_version 86770 (0.0010) -[2023-10-11 00:17:48,601][98559] Updated weights for policy 0, policy_version 86780 (0.0007) -[2023-10-11 00:17:48,619][98560] Updated weights for policy 1, policy_version 86182 (0.0007) -[2023-10-11 00:17:48,984][98560] Updated weights for policy 1, policy_version 86192 (0.0010) -[2023-10-11 00:17:49,348][98560] Updated weights for policy 1, policy_version 86202 (0.0010) -[2023-10-11 00:17:50,556][97672] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 177143808. Throughput: 0: 1717.6, 1: 1667.4. Samples: 44293696. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:17:50,556][97672] Avg episode reward: [(0, '-0.840'), (1, '20.640')] -[2023-10-11 00:17:52,537][98559] Updated weights for policy 0, policy_version 86790 (0.0007) -[2023-10-11 00:17:52,901][98559] Updated weights for policy 0, policy_version 86800 (0.0009) -[2023-10-11 00:17:53,264][98559] Updated weights for policy 0, policy_version 86810 (0.0008) -[2023-10-11 00:17:53,272][98560] Updated weights for policy 1, policy_version 86212 (0.0009) -[2023-10-11 00:17:53,672][98560] Updated weights for policy 1, policy_version 86222 (0.0007) -[2023-10-11 00:17:54,044][98560] Updated weights for policy 1, policy_version 86232 (0.0008) -[2023-10-11 00:17:55,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 177209344. Throughput: 0: 1707.5, 1: 1700.3. Samples: 44304572. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:17:55,557][97672] Avg episode reward: [(0, '-0.840'), (1, '20.120')] -[2023-10-11 00:17:57,316][98559] Updated weights for policy 0, policy_version 86820 (0.0008) -[2023-10-11 00:17:57,677][98559] Updated weights for policy 0, policy_version 86830 (0.0007) -[2023-10-11 00:17:57,983][98560] Updated weights for policy 1, policy_version 86242 (0.0010) -[2023-10-11 00:17:58,050][98559] Updated weights for policy 0, policy_version 86840 (0.0007) -[2023-10-11 00:17:58,349][98560] Updated weights for policy 1, policy_version 86252 (0.0007) -[2023-10-11 00:17:58,713][98560] Updated weights for policy 1, policy_version 86262 (0.0009) -[2023-10-11 00:17:59,083][98560] Updated weights for policy 1, policy_version 86272 (0.0008) -[2023-10-11 00:18:00,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 177274880. Throughput: 0: 1705.8, 1: 1680.4. Samples: 44324590. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:18:00,557][97672] Avg episode reward: [(0, '-0.840'), (1, '19.800')] -[2023-10-11 00:18:01,890][98559] Updated weights for policy 0, policy_version 86850 (0.0007) -[2023-10-11 00:18:02,253][98559] Updated weights for policy 0, policy_version 86860 (0.0008) -[2023-10-11 00:18:02,623][98559] Updated weights for policy 0, policy_version 86870 (0.0008) -[2023-10-11 00:18:02,983][98559] Updated weights for policy 0, policy_version 86880 (0.0008) -[2023-10-11 00:18:03,194][98560] Updated weights for policy 1, policy_version 86282 (0.0009) -[2023-10-11 00:18:03,561][98560] Updated weights for policy 1, policy_version 86292 (0.0011) -[2023-10-11 00:18:03,926][98560] Updated weights for policy 1, policy_version 86302 (0.0008) -[2023-10-11 00:18:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 177340416. Throughput: 0: 1720.7, 1: 1677.7. Samples: 44345006. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:18:05,557][97672] Avg episode reward: [(0, '-0.840'), (1, '19.120')] -[2023-10-11 00:18:07,196][98559] Updated weights for policy 0, policy_version 86890 (0.0010) -[2023-10-11 00:18:07,553][98559] Updated weights for policy 0, policy_version 86900 (0.0008) -[2023-10-11 00:18:07,913][98559] Updated weights for policy 0, policy_version 86910 (0.0008) -[2023-10-11 00:18:07,975][98560] Updated weights for policy 1, policy_version 86312 (0.0009) -[2023-10-11 00:18:08,337][98560] Updated weights for policy 1, policy_version 86322 (0.0008) -[2023-10-11 00:18:08,703][98560] Updated weights for policy 1, policy_version 86332 (0.0008) -[2023-10-11 00:18:10,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 177405952. Throughput: 0: 1691.3, 1: 1700.0. Samples: 44355420. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:18:10,557][97672] Avg episode reward: [(0, '-0.840'), (1, '18.800')] -[2023-10-11 00:18:11,940][98559] Updated weights for policy 0, policy_version 86920 (0.0008) -[2023-10-11 00:18:12,312][98559] Updated weights for policy 0, policy_version 86930 (0.0007) -[2023-10-11 00:18:12,637][98560] Updated weights for policy 1, policy_version 86342 (0.0010) -[2023-10-11 00:18:12,679][98559] Updated weights for policy 0, policy_version 86940 (0.0008) -[2023-10-11 00:18:13,007][98560] Updated weights for policy 1, policy_version 86352 (0.0007) -[2023-10-11 00:18:13,378][98560] Updated weights for policy 1, policy_version 86362 (0.0007) -[2023-10-11 00:18:15,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 177471488. Throughput: 0: 1715.3, 1: 1680.2. Samples: 44375406. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:18:15,557][97672] Avg episode reward: [(0, '-0.840'), (1, '18.280')] -[2023-10-11 00:18:16,537][98559] Updated weights for policy 0, policy_version 86950 (0.0009) -[2023-10-11 00:18:16,907][98559] Updated weights for policy 0, policy_version 86960 (0.0009) -[2023-10-11 00:18:17,232][98560] Updated weights for policy 1, policy_version 86372 (0.0007) -[2023-10-11 00:18:17,279][98559] Updated weights for policy 0, policy_version 86970 (0.0009) -[2023-10-11 00:18:17,595][98560] Updated weights for policy 1, policy_version 86382 (0.0009) -[2023-10-11 00:18:17,960][98560] Updated weights for policy 1, policy_version 86392 (0.0010) -[2023-10-11 00:18:20,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 177537024. Throughput: 0: 1719.4, 1: 1700.6. Samples: 44396634. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:18:20,556][97672] Avg episode reward: [(0, '-0.840'), (1, '18.100')] -[2023-10-11 00:18:21,284][98559] Updated weights for policy 0, policy_version 86980 (0.0010) -[2023-10-11 00:18:21,662][98559] Updated weights for policy 0, policy_version 86990 (0.0010) -[2023-10-11 00:18:21,971][98560] Updated weights for policy 1, policy_version 86402 (0.0007) -[2023-10-11 00:18:22,026][98559] Updated weights for policy 0, policy_version 87000 (0.0008) -[2023-10-11 00:18:22,336][98560] Updated weights for policy 1, policy_version 86412 (0.0007) -[2023-10-11 00:18:22,697][98560] Updated weights for policy 1, policy_version 86422 (0.0010) -[2023-10-11 00:18:23,068][98560] Updated weights for policy 1, policy_version 86432 (0.0007) -[2023-10-11 00:18:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 177602560. Throughput: 0: 1701.2, 1: 1694.0. Samples: 44406268. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:18:25,557][97672] Avg episode reward: [(0, '-0.840'), (1, '17.840')] -[2023-10-11 00:18:25,925][98559] Updated weights for policy 0, policy_version 87010 (0.0008) -[2023-10-11 00:18:26,282][98559] Updated weights for policy 0, policy_version 87020 (0.0008) -[2023-10-11 00:18:26,649][98559] Updated weights for policy 0, policy_version 87030 (0.0008) -[2023-10-11 00:18:27,014][98559] Updated weights for policy 0, policy_version 87040 (0.0008) -[2023-10-11 00:18:27,135][98560] Updated weights for policy 1, policy_version 86442 (0.0008) -[2023-10-11 00:18:27,506][98560] Updated weights for policy 1, policy_version 86452 (0.0009) -[2023-10-11 00:18:27,868][98560] Updated weights for policy 1, policy_version 86462 (0.0008) -[2023-10-11 00:18:30,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 177668096. Throughput: 0: 1720.8, 1: 1686.9. Samples: 44426942. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:18:30,557][97672] Avg episode reward: [(0, '-0.820'), (1, '17.640')] -[2023-10-11 00:18:31,019][98559] Updated weights for policy 0, policy_version 87050 (0.0010) -[2023-10-11 00:18:31,377][98559] Updated weights for policy 0, policy_version 87060 (0.0010) -[2023-10-11 00:18:31,753][98559] Updated weights for policy 0, policy_version 87070 (0.0008) -[2023-10-11 00:18:31,814][98560] Updated weights for policy 1, policy_version 86472 (0.0008) -[2023-10-11 00:18:32,178][98560] Updated weights for policy 1, policy_version 86482 (0.0007) -[2023-10-11 00:18:32,542][98560] Updated weights for policy 1, policy_version 86492 (0.0008) -[2023-10-11 00:18:35,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 177733632. Throughput: 0: 1711.4, 1: 1713.5. Samples: 44447820. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:18:35,558][97672] Avg episode reward: [(0, '-0.820'), (1, '17.460')] -[2023-10-11 00:18:35,566][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000086496_88571904.pth... -[2023-10-11 00:18:35,604][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000084928_86966272.pth -[2023-10-11 00:18:35,869][98559] Updated weights for policy 0, policy_version 87080 (0.0009) -[2023-10-11 00:18:36,238][98559] Updated weights for policy 0, policy_version 87090 (0.0009) -[2023-10-11 00:18:36,489][98560] Updated weights for policy 1, policy_version 86502 (0.0010) -[2023-10-11 00:18:36,609][98559] Updated weights for policy 0, policy_version 87100 (0.0007) -[2023-10-11 00:18:36,750][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000087104_89194496.pth... -[2023-10-11 00:18:36,779][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000085472_87523328.pth -[2023-10-11 00:18:36,855][98560] Updated weights for policy 1, policy_version 86512 (0.0010) -[2023-10-11 00:18:37,228][98560] Updated weights for policy 1, policy_version 86522 (0.0011) -[2023-10-11 00:18:40,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 177799168. Throughput: 0: 1704.3, 1: 1683.9. Samples: 44457038. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:18:40,557][97672] Avg episode reward: [(0, '-0.820'), (1, '17.380')] -[2023-10-11 00:18:40,856][98559] Updated weights for policy 0, policy_version 87110 (0.0008) -[2023-10-11 00:18:41,230][98559] Updated weights for policy 0, policy_version 87120 (0.0008) -[2023-10-11 00:18:41,375][98560] Updated weights for policy 1, policy_version 86532 (0.0008) -[2023-10-11 00:18:41,592][98559] Updated weights for policy 0, policy_version 87130 (0.0007) -[2023-10-11 00:18:41,739][98560] Updated weights for policy 1, policy_version 86542 (0.0009) -[2023-10-11 00:18:42,098][98560] Updated weights for policy 1, policy_version 86552 (0.0010) -[2023-10-11 00:18:45,519][98559] Updated weights for policy 0, policy_version 87140 (0.0008) -[2023-10-11 00:18:45,556][97672] Fps is (10 sec: 13107.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 177864704. Throughput: 0: 1706.0, 1: 1697.5. Samples: 44477746. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:18:45,556][97672] Avg episode reward: [(0, '-0.780'), (1, '17.220')] -[2023-10-11 00:18:45,876][98559] Updated weights for policy 0, policy_version 87150 (0.0008) -[2023-10-11 00:18:46,239][98559] Updated weights for policy 0, policy_version 87160 (0.0008) -[2023-10-11 00:18:46,239][98560] Updated weights for policy 1, policy_version 86562 (0.0010) -[2023-10-11 00:18:46,656][98560] Updated weights for policy 1, policy_version 86572 (0.0008) -[2023-10-11 00:18:47,020][98560] Updated weights for policy 1, policy_version 86582 (0.0008) -[2023-10-11 00:18:47,394][98560] Updated weights for policy 1, policy_version 86592 (0.0008) -[2023-10-11 00:18:50,149][98559] Updated weights for policy 0, policy_version 87170 (0.0008) -[2023-10-11 00:18:50,509][98559] Updated weights for policy 0, policy_version 87180 (0.0010) -[2023-10-11 00:18:50,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 177930240. Throughput: 0: 1702.6, 1: 1705.9. Samples: 44498388. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:18:50,558][97672] Avg episode reward: [(0, '-0.780'), (1, '17.360')] -[2023-10-11 00:18:50,874][98559] Updated weights for policy 0, policy_version 87190 (0.0010) -[2023-10-11 00:18:51,240][98559] Updated weights for policy 0, policy_version 87200 (0.0008) -[2023-10-11 00:18:51,384][98560] Updated weights for policy 1, policy_version 86602 (0.0008) -[2023-10-11 00:18:51,749][98560] Updated weights for policy 1, policy_version 86612 (0.0009) -[2023-10-11 00:18:52,116][98560] Updated weights for policy 1, policy_version 86622 (0.0008) -[2023-10-11 00:18:55,286][98559] Updated weights for policy 0, policy_version 87210 (0.0009) -[2023-10-11 00:18:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 177995776. Throughput: 0: 1712.5, 1: 1676.7. Samples: 44507932. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:18:55,556][97672] Avg episode reward: [(0, '-0.780'), (1, '18.720')] -[2023-10-11 00:18:55,648][98559] Updated weights for policy 0, policy_version 87220 (0.0009) -[2023-10-11 00:18:56,023][98559] Updated weights for policy 0, policy_version 87230 (0.0008) -[2023-10-11 00:18:56,196][98560] Updated weights for policy 1, policy_version 86632 (0.0009) -[2023-10-11 00:18:56,560][98560] Updated weights for policy 1, policy_version 86642 (0.0010) -[2023-10-11 00:18:56,924][98560] Updated weights for policy 1, policy_version 86652 (0.0007) -[2023-10-11 00:19:00,089][98559] Updated weights for policy 0, policy_version 87240 (0.0011) -[2023-10-11 00:19:00,449][98559] Updated weights for policy 0, policy_version 87250 (0.0010) -[2023-10-11 00:19:00,556][97672] Fps is (10 sec: 13107.7, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 178061312. Throughput: 0: 1706.4, 1: 1699.9. Samples: 44528686. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:19:00,556][97672] Avg episode reward: [(0, '-0.780'), (1, '19.880')] -[2023-10-11 00:19:00,807][98559] Updated weights for policy 0, policy_version 87260 (0.0011) -[2023-10-11 00:19:01,157][98560] Updated weights for policy 1, policy_version 86662 (0.0010) -[2023-10-11 00:19:01,522][98560] Updated weights for policy 1, policy_version 86672 (0.0007) -[2023-10-11 00:19:01,904][98560] Updated weights for policy 1, policy_version 86682 (0.0008) -[2023-10-11 00:19:04,939][98559] Updated weights for policy 0, policy_version 87270 (0.0009) -[2023-10-11 00:19:05,306][98559] Updated weights for policy 0, policy_version 87280 (0.0009) -[2023-10-11 00:19:05,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 178126848. Throughput: 0: 1692.0, 1: 1691.8. Samples: 44548908. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:19:05,557][97672] Avg episode reward: [(0, '-0.780'), (1, '20.640')] -[2023-10-11 00:19:05,678][98559] Updated weights for policy 0, policy_version 87290 (0.0009) -[2023-10-11 00:19:05,969][98560] Updated weights for policy 1, policy_version 86692 (0.0009) -[2023-10-11 00:19:06,344][98560] Updated weights for policy 1, policy_version 86702 (0.0009) -[2023-10-11 00:19:06,719][98560] Updated weights for policy 1, policy_version 86712 (0.0008) -[2023-10-11 00:19:09,514][98559] Updated weights for policy 0, policy_version 87300 (0.0008) -[2023-10-11 00:19:09,885][98559] Updated weights for policy 0, policy_version 87310 (0.0008) -[2023-10-11 00:19:10,249][98559] Updated weights for policy 0, policy_version 87320 (0.0008) -[2023-10-11 00:19:10,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 178225152. Throughput: 0: 1709.5, 1: 1683.4. Samples: 44558948. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:19:10,556][97672] Avg episode reward: [(0, '-0.780'), (1, '21.260')] -[2023-10-11 00:19:10,621][98560] Updated weights for policy 1, policy_version 86722 (0.0009) -[2023-10-11 00:19:10,989][98560] Updated weights for policy 1, policy_version 86732 (0.0009) -[2023-10-11 00:19:11,363][98560] Updated weights for policy 1, policy_version 86742 (0.0009) -[2023-10-11 00:19:11,723][98560] Updated weights for policy 1, policy_version 86752 (0.0008) -[2023-10-11 00:19:14,141][98559] Updated weights for policy 0, policy_version 87330 (0.0007) -[2023-10-11 00:19:14,502][98559] Updated weights for policy 0, policy_version 87340 (0.0010) -[2023-10-11 00:19:14,882][98559] Updated weights for policy 0, policy_version 87350 (0.0009) -[2023-10-11 00:19:15,247][98559] Updated weights for policy 0, policy_version 87360 (0.0008) -[2023-10-11 00:19:15,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 178290688. Throughput: 0: 1705.8, 1: 1697.0. Samples: 44580068. Policy #0 lag: (min: 29.0, avg: 32.6, max: 61.0) -[2023-10-11 00:19:15,557][97672] Avg episode reward: [(0, '-0.780'), (1, '21.680')] -[2023-10-11 00:19:15,723][98560] Updated weights for policy 1, policy_version 86762 (0.0009) -[2023-10-11 00:19:16,081][98560] Updated weights for policy 1, policy_version 86772 (0.0008) -[2023-10-11 00:19:16,449][98560] Updated weights for policy 1, policy_version 86782 (0.0008) -[2023-10-11 00:19:18,996][98559] Updated weights for policy 0, policy_version 87370 (0.0007) -[2023-10-11 00:19:19,359][98559] Updated weights for policy 0, policy_version 87380 (0.0009) -[2023-10-11 00:19:19,722][98559] Updated weights for policy 0, policy_version 87390 (0.0008) -[2023-10-11 00:19:20,471][98560] Updated weights for policy 1, policy_version 86792 (0.0008) -[2023-10-11 00:19:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 178356224. Throughput: 0: 1693.6, 1: 1699.4. Samples: 44600500. Policy #0 lag: (min: 29.0, avg: 32.6, max: 61.0) -[2023-10-11 00:19:20,556][97672] Avg episode reward: [(0, '-0.800'), (1, '21.860')] -[2023-10-11 00:19:20,830][98560] Updated weights for policy 1, policy_version 86802 (0.0007) -[2023-10-11 00:19:21,196][98560] Updated weights for policy 1, policy_version 86812 (0.0007) -[2023-10-11 00:19:23,857][98559] Updated weights for policy 0, policy_version 87400 (0.0010) -[2023-10-11 00:19:24,225][98559] Updated weights for policy 0, policy_version 87410 (0.0011) -[2023-10-11 00:19:24,604][98559] Updated weights for policy 0, policy_version 87420 (0.0010) -[2023-10-11 00:19:25,222][98560] Updated weights for policy 1, policy_version 86822 (0.0008) -[2023-10-11 00:19:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 178421760. Throughput: 0: 1721.7, 1: 1695.6. Samples: 44610816. Policy #0 lag: (min: 29.0, avg: 32.6, max: 61.0) -[2023-10-11 00:19:25,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.080')] -[2023-10-11 00:19:25,592][98560] Updated weights for policy 1, policy_version 86832 (0.0008) -[2023-10-11 00:19:25,965][98560] Updated weights for policy 1, policy_version 86842 (0.0008) -[2023-10-11 00:19:28,637][98559] Updated weights for policy 0, policy_version 87430 (0.0007) -[2023-10-11 00:19:29,002][98559] Updated weights for policy 0, policy_version 87440 (0.0007) -[2023-10-11 00:19:29,363][98559] Updated weights for policy 0, policy_version 87450 (0.0007) -[2023-10-11 00:19:30,036][98560] Updated weights for policy 1, policy_version 86852 (0.0008) -[2023-10-11 00:19:30,413][98560] Updated weights for policy 1, policy_version 86862 (0.0009) -[2023-10-11 00:19:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 178487296. Throughput: 0: 1702.4, 1: 1705.0. Samples: 44631076. Policy #0 lag: (min: 29.0, avg: 32.6, max: 61.0) -[2023-10-11 00:19:30,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.240')] -[2023-10-11 00:19:30,783][98560] Updated weights for policy 1, policy_version 86872 (0.0009) -[2023-10-11 00:19:33,415][98559] Updated weights for policy 0, policy_version 87460 (0.0007) -[2023-10-11 00:19:33,784][98559] Updated weights for policy 0, policy_version 87470 (0.0010) -[2023-10-11 00:19:34,147][98559] Updated weights for policy 0, policy_version 87480 (0.0010) -[2023-10-11 00:19:34,752][98560] Updated weights for policy 1, policy_version 86882 (0.0010) -[2023-10-11 00:19:35,165][98560] Updated weights for policy 1, policy_version 86892 (0.0008) -[2023-10-11 00:19:35,541][98560] Updated weights for policy 1, policy_version 86902 (0.0009) -[2023-10-11 00:19:35,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 178552832. Throughput: 0: 1705.2, 1: 1705.7. Samples: 44651876. Policy #0 lag: (min: 29.0, avg: 32.6, max: 61.0) -[2023-10-11 00:19:35,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.320')] -[2023-10-11 00:19:35,906][98560] Updated weights for policy 1, policy_version 86912 (0.0008) -[2023-10-11 00:19:38,070][98559] Updated weights for policy 0, policy_version 87490 (0.0010) -[2023-10-11 00:19:38,439][98559] Updated weights for policy 0, policy_version 87500 (0.0008) -[2023-10-11 00:19:38,806][98559] Updated weights for policy 0, policy_version 87510 (0.0008) -[2023-10-11 00:19:39,174][98559] Updated weights for policy 0, policy_version 87520 (0.0008) -[2023-10-11 00:19:39,943][98560] Updated weights for policy 1, policy_version 86922 (0.0009) -[2023-10-11 00:19:40,310][98560] Updated weights for policy 1, policy_version 86932 (0.0008) -[2023-10-11 00:19:40,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 178618368. Throughput: 0: 1721.2, 1: 1701.9. Samples: 44661970. Policy #0 lag: (min: 29.0, avg: 32.6, max: 61.0) -[2023-10-11 00:19:40,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.360')] -[2023-10-11 00:19:40,682][98560] Updated weights for policy 1, policy_version 86942 (0.0008) -[2023-10-11 00:19:43,108][98559] Updated weights for policy 0, policy_version 87530 (0.0010) -[2023-10-11 00:19:43,474][98559] Updated weights for policy 0, policy_version 87540 (0.0007) -[2023-10-11 00:19:43,841][98559] Updated weights for policy 0, policy_version 87550 (0.0007) -[2023-10-11 00:19:44,714][98560] Updated weights for policy 1, policy_version 86952 (0.0008) -[2023-10-11 00:19:45,072][98560] Updated weights for policy 1, policy_version 86962 (0.0009) -[2023-10-11 00:19:45,444][98560] Updated weights for policy 1, policy_version 86972 (0.0009) -[2023-10-11 00:19:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 178683904. Throughput: 0: 1705.6, 1: 1703.9. Samples: 44682112. Policy #0 lag: (min: 29.0, avg: 32.6, max: 61.0) -[2023-10-11 00:19:45,556][97672] Avg episode reward: [(0, '-0.760'), (1, '22.380')] -[2023-10-11 00:19:47,975][98559] Updated weights for policy 0, policy_version 87560 (0.0010) -[2023-10-11 00:19:48,356][98559] Updated weights for policy 0, policy_version 87570 (0.0011) -[2023-10-11 00:19:48,729][98559] Updated weights for policy 0, policy_version 87580 (0.0011) -[2023-10-11 00:19:49,443][98560] Updated weights for policy 1, policy_version 86982 (0.0009) -[2023-10-11 00:19:49,816][98560] Updated weights for policy 1, policy_version 86992 (0.0009) -[2023-10-11 00:19:50,191][98560] Updated weights for policy 1, policy_version 87002 (0.0010) -[2023-10-11 00:19:50,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 178782208. Throughput: 0: 1714.3, 1: 1702.8. Samples: 44702676. Policy #0 lag: (min: 29.0, avg: 32.6, max: 61.0) -[2023-10-11 00:19:50,557][97672] Avg episode reward: [(0, '-0.760'), (1, '22.340')] -[2023-10-11 00:19:52,787][98559] Updated weights for policy 0, policy_version 87590 (0.0011) -[2023-10-11 00:19:53,165][98559] Updated weights for policy 0, policy_version 87600 (0.0009) -[2023-10-11 00:19:53,533][98559] Updated weights for policy 0, policy_version 87610 (0.0009) -[2023-10-11 00:19:54,054][98560] Updated weights for policy 1, policy_version 87012 (0.0008) -[2023-10-11 00:19:54,419][98560] Updated weights for policy 1, policy_version 87022 (0.0008) -[2023-10-11 00:19:54,789][98560] Updated weights for policy 1, policy_version 87032 (0.0007) -[2023-10-11 00:19:55,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 178847744. Throughput: 0: 1705.9, 1: 1715.4. Samples: 44712904. Policy #0 lag: (min: 29.0, avg: 32.6, max: 61.0) -[2023-10-11 00:19:55,556][97672] Avg episode reward: [(0, '-0.760'), (1, '22.340')] -[2023-10-11 00:19:57,338][98559] Updated weights for policy 0, policy_version 87620 (0.0008) -[2023-10-11 00:19:57,717][98559] Updated weights for policy 0, policy_version 87630 (0.0008) -[2023-10-11 00:19:58,070][98559] Updated weights for policy 0, policy_version 87640 (0.0010) -[2023-10-11 00:19:58,815][98560] Updated weights for policy 1, policy_version 87042 (0.0008) -[2023-10-11 00:19:59,188][98560] Updated weights for policy 1, policy_version 87052 (0.0009) -[2023-10-11 00:19:59,556][98560] Updated weights for policy 1, policy_version 87062 (0.0009) -[2023-10-11 00:19:59,913][98560] Updated weights for policy 1, policy_version 87072 (0.0010) -[2023-10-11 00:20:00,556][97672] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 178913280. Throughput: 0: 1702.5, 1: 1709.1. Samples: 44733586. Policy #0 lag: (min: 29.0, avg: 32.6, max: 61.0) -[2023-10-11 00:20:00,556][97672] Avg episode reward: [(0, '-0.760'), (1, '22.360')] -[2023-10-11 00:20:01,944][98559] Updated weights for policy 0, policy_version 87650 (0.0010) -[2023-10-11 00:20:02,307][98559] Updated weights for policy 0, policy_version 87660 (0.0008) -[2023-10-11 00:20:02,675][98559] Updated weights for policy 0, policy_version 87670 (0.0008) -[2023-10-11 00:20:03,036][98559] Updated weights for policy 0, policy_version 87680 (0.0008) -[2023-10-11 00:20:03,977][98560] Updated weights for policy 1, policy_version 87082 (0.0007) -[2023-10-11 00:20:04,353][98560] Updated weights for policy 1, policy_version 87092 (0.0009) -[2023-10-11 00:20:04,719][98560] Updated weights for policy 1, policy_version 87102 (0.0008) -[2023-10-11 00:20:05,556][97672] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 178978816. Throughput: 0: 1718.4, 1: 1680.7. Samples: 44753458. Policy #0 lag: (min: 29.0, avg: 32.6, max: 61.0) -[2023-10-11 00:20:05,557][97672] Avg episode reward: [(0, '-0.720'), (1, '22.420')] -[2023-10-11 00:20:06,842][98559] Updated weights for policy 0, policy_version 87690 (0.0008) -[2023-10-11 00:20:07,207][98559] Updated weights for policy 0, policy_version 87700 (0.0007) -[2023-10-11 00:20:07,565][98559] Updated weights for policy 0, policy_version 87710 (0.0007) -[2023-10-11 00:20:08,822][98560] Updated weights for policy 1, policy_version 87112 (0.0009) -[2023-10-11 00:20:09,192][98560] Updated weights for policy 1, policy_version 87122 (0.0007) -[2023-10-11 00:20:09,562][98560] Updated weights for policy 1, policy_version 87132 (0.0007) -[2023-10-11 00:20:10,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 179044352. Throughput: 0: 1695.6, 1: 1706.8. Samples: 44763924. Policy #0 lag: (min: 29.0, avg: 32.6, max: 61.0) -[2023-10-11 00:20:10,557][97672] Avg episode reward: [(0, '-0.720'), (1, '22.400')] -[2023-10-11 00:20:11,609][98559] Updated weights for policy 0, policy_version 87720 (0.0008) -[2023-10-11 00:20:11,968][98559] Updated weights for policy 0, policy_version 87730 (0.0012) -[2023-10-11 00:20:12,339][98559] Updated weights for policy 0, policy_version 87740 (0.0009) -[2023-10-11 00:20:13,666][98560] Updated weights for policy 1, policy_version 87142 (0.0009) -[2023-10-11 00:20:14,033][98560] Updated weights for policy 1, policy_version 87152 (0.0008) -[2023-10-11 00:20:14,402][98560] Updated weights for policy 1, policy_version 87162 (0.0007) -[2023-10-11 00:20:15,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 179109888. Throughput: 0: 1715.6, 1: 1692.1. Samples: 44784424. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-11 00:20:15,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.480')] -[2023-10-11 00:20:16,352][98559] Updated weights for policy 0, policy_version 87750 (0.0009) -[2023-10-11 00:20:16,713][98559] Updated weights for policy 0, policy_version 87760 (0.0008) -[2023-10-11 00:20:17,076][98559] Updated weights for policy 0, policy_version 87770 (0.0009) -[2023-10-11 00:20:18,432][98560] Updated weights for policy 1, policy_version 87172 (0.0009) -[2023-10-11 00:20:18,796][98560] Updated weights for policy 1, policy_version 87182 (0.0008) -[2023-10-11 00:20:19,167][98560] Updated weights for policy 1, policy_version 87192 (0.0009) -[2023-10-11 00:20:20,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 179175424. Throughput: 0: 1718.5, 1: 1671.5. Samples: 44804426. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-11 00:20:20,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.540')] -[2023-10-11 00:20:21,343][98559] Updated weights for policy 0, policy_version 87780 (0.0009) -[2023-10-11 00:20:21,714][98559] Updated weights for policy 0, policy_version 87790 (0.0008) -[2023-10-11 00:20:22,074][98559] Updated weights for policy 0, policy_version 87800 (0.0007) -[2023-10-11 00:20:23,049][98560] Updated weights for policy 1, policy_version 87202 (0.0008) -[2023-10-11 00:20:23,462][98560] Updated weights for policy 1, policy_version 87212 (0.0011) -[2023-10-11 00:20:23,820][98560] Updated weights for policy 1, policy_version 87222 (0.0009) -[2023-10-11 00:20:24,194][98560] Updated weights for policy 1, policy_version 87232 (0.0010) -[2023-10-11 00:20:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 179240960. Throughput: 0: 1694.0, 1: 1709.5. Samples: 44815126. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-11 00:20:25,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.580')] -[2023-10-11 00:20:26,137][98559] Updated weights for policy 0, policy_version 87810 (0.0010) -[2023-10-11 00:20:26,512][98559] Updated weights for policy 0, policy_version 87820 (0.0010) -[2023-10-11 00:20:26,881][98559] Updated weights for policy 0, policy_version 87830 (0.0010) -[2023-10-11 00:20:27,240][98559] Updated weights for policy 0, policy_version 87840 (0.0011) -[2023-10-11 00:20:28,297][98560] Updated weights for policy 1, policy_version 87242 (0.0007) -[2023-10-11 00:20:28,659][98560] Updated weights for policy 1, policy_version 87252 (0.0009) -[2023-10-11 00:20:29,029][98560] Updated weights for policy 1, policy_version 87262 (0.0010) -[2023-10-11 00:20:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 179306496. Throughput: 0: 1715.0, 1: 1686.0. Samples: 44835158. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-11 00:20:30,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.600')] -[2023-10-11 00:20:31,150][98559] Updated weights for policy 0, policy_version 87850 (0.0008) -[2023-10-11 00:20:31,514][98559] Updated weights for policy 0, policy_version 87860 (0.0008) -[2023-10-11 00:20:31,876][98559] Updated weights for policy 0, policy_version 87870 (0.0008) -[2023-10-11 00:20:33,183][98560] Updated weights for policy 1, policy_version 87272 (0.0008) -[2023-10-11 00:20:33,547][98560] Updated weights for policy 1, policy_version 87282 (0.0007) -[2023-10-11 00:20:33,911][98560] Updated weights for policy 1, policy_version 87292 (0.0007) -[2023-10-11 00:20:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 179372032. Throughput: 0: 1715.9, 1: 1677.2. Samples: 44855362. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-11 00:20:35,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.680')] -[2023-10-11 00:20:35,566][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000087296_89391104.pth... -[2023-10-11 00:20:35,600][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000085696_87752704.pth -[2023-10-11 00:20:35,604][98439] Saving a milestone ./train_atari/atari_doubledunk_APPO/checkpoint_p1/milestones/checkpoint_000087296_89391104.pth -[2023-10-11 00:20:35,967][98559] Updated weights for policy 0, policy_version 87880 (0.0010) -[2023-10-11 00:20:36,336][98559] Updated weights for policy 0, policy_version 87890 (0.0008) -[2023-10-11 00:20:36,693][98559] Updated weights for policy 0, policy_version 87900 (0.0008) -[2023-10-11 00:20:36,834][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000087904_90013696.pth... -[2023-10-11 00:20:36,862][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000086272_88342528.pth -[2023-10-11 00:20:36,865][98385] Saving a milestone ./train_atari/atari_doubledunk_APPO/checkpoint_p0/milestones/checkpoint_000087904_90013696.pth -[2023-10-11 00:20:37,892][98560] Updated weights for policy 1, policy_version 87302 (0.0010) -[2023-10-11 00:20:38,256][98560] Updated weights for policy 1, policy_version 87312 (0.0007) -[2023-10-11 00:20:38,625][98560] Updated weights for policy 1, policy_version 87322 (0.0010) -[2023-10-11 00:20:40,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 179437568. Throughput: 0: 1703.3, 1: 1691.2. Samples: 44865654. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-11 00:20:40,556][97672] Avg episode reward: [(0, '-0.780'), (1, '22.660')] -[2023-10-11 00:20:40,807][98559] Updated weights for policy 0, policy_version 87910 (0.0009) -[2023-10-11 00:20:41,169][98559] Updated weights for policy 0, policy_version 87920 (0.0010) -[2023-10-11 00:20:41,540][98559] Updated weights for policy 0, policy_version 87930 (0.0012) -[2023-10-11 00:20:42,579][98560] Updated weights for policy 1, policy_version 87332 (0.0008) -[2023-10-11 00:20:42,943][98560] Updated weights for policy 1, policy_version 87342 (0.0009) -[2023-10-11 00:20:43,310][98560] Updated weights for policy 1, policy_version 87352 (0.0008) -[2023-10-11 00:20:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 179503104. Throughput: 0: 1707.7, 1: 1665.5. Samples: 44885380. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-11 00:20:45,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.640')] -[2023-10-11 00:20:45,565][98559] Updated weights for policy 0, policy_version 87940 (0.0009) -[2023-10-11 00:20:45,925][98559] Updated weights for policy 0, policy_version 87950 (0.0009) -[2023-10-11 00:20:46,281][98559] Updated weights for policy 0, policy_version 87960 (0.0008) -[2023-10-11 00:20:47,456][98560] Updated weights for policy 1, policy_version 87362 (0.0007) -[2023-10-11 00:20:47,818][98560] Updated weights for policy 1, policy_version 87372 (0.0009) -[2023-10-11 00:20:48,180][98560] Updated weights for policy 1, policy_version 87382 (0.0007) -[2023-10-11 00:20:48,550][98560] Updated weights for policy 1, policy_version 87392 (0.0007) -[2023-10-11 00:20:50,237][98559] Updated weights for policy 0, policy_version 87970 (0.0009) -[2023-10-11 00:20:50,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 179568640. Throughput: 0: 1704.3, 1: 1688.6. Samples: 44906136. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-11 00:20:50,556][97672] Avg episode reward: [(0, '-0.800'), (1, '22.580')] -[2023-10-11 00:20:50,598][98559] Updated weights for policy 0, policy_version 87980 (0.0010) -[2023-10-11 00:20:50,971][98559] Updated weights for policy 0, policy_version 87990 (0.0010) -[2023-10-11 00:20:51,333][98559] Updated weights for policy 0, policy_version 88000 (0.0011) -[2023-10-11 00:20:52,497][98560] Updated weights for policy 1, policy_version 87402 (0.0008) -[2023-10-11 00:20:52,874][98560] Updated weights for policy 1, policy_version 87412 (0.0008) -[2023-10-11 00:20:53,241][98560] Updated weights for policy 1, policy_version 87422 (0.0009) -[2023-10-11 00:20:55,178][98559] Updated weights for policy 0, policy_version 88010 (0.0011) -[2023-10-11 00:20:55,544][98559] Updated weights for policy 0, policy_version 88020 (0.0011) -[2023-10-11 00:20:55,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 179634176. Throughput: 0: 1709.9, 1: 1682.0. Samples: 44916560. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-11 00:20:55,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.580')] -[2023-10-11 00:20:55,910][98559] Updated weights for policy 0, policy_version 88030 (0.0009) -[2023-10-11 00:20:57,023][98560] Updated weights for policy 1, policy_version 87432 (0.0010) -[2023-10-11 00:20:57,379][98560] Updated weights for policy 1, policy_version 87442 (0.0009) -[2023-10-11 00:20:57,753][98560] Updated weights for policy 1, policy_version 87452 (0.0009) -[2023-10-11 00:21:00,027][98559] Updated weights for policy 0, policy_version 88040 (0.0007) -[2023-10-11 00:21:00,394][98559] Updated weights for policy 0, policy_version 88050 (0.0008) -[2023-10-11 00:21:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 179699712. Throughput: 0: 1710.0, 1: 1678.7. Samples: 44936912. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-11 00:21:00,556][97672] Avg episode reward: [(0, '-0.800'), (1, '22.540')] -[2023-10-11 00:21:00,759][98559] Updated weights for policy 0, policy_version 88060 (0.0009) -[2023-10-11 00:21:01,839][98560] Updated weights for policy 1, policy_version 87462 (0.0009) -[2023-10-11 00:21:02,199][98560] Updated weights for policy 1, policy_version 87472 (0.0007) -[2023-10-11 00:21:02,558][98560] Updated weights for policy 1, policy_version 87482 (0.0010) -[2023-10-11 00:21:04,614][98559] Updated weights for policy 0, policy_version 88070 (0.0009) -[2023-10-11 00:21:04,978][98559] Updated weights for policy 0, policy_version 88080 (0.0009) -[2023-10-11 00:21:05,346][98559] Updated weights for policy 0, policy_version 88090 (0.0009) -[2023-10-11 00:21:05,556][97672] Fps is (10 sec: 16384.5, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 179798016. Throughput: 0: 1690.2, 1: 1695.4. Samples: 44956778. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-11 00:21:05,556][97672] Avg episode reward: [(0, '-0.820'), (1, '22.540')] -[2023-10-11 00:21:06,721][98560] Updated weights for policy 1, policy_version 87492 (0.0008) -[2023-10-11 00:21:07,076][98560] Updated weights for policy 1, policy_version 87502 (0.0009) -[2023-10-11 00:21:07,446][98560] Updated weights for policy 1, policy_version 87512 (0.0009) -[2023-10-11 00:21:09,336][98559] Updated weights for policy 0, policy_version 88100 (0.0009) -[2023-10-11 00:21:09,707][98559] Updated weights for policy 0, policy_version 88110 (0.0009) -[2023-10-11 00:21:10,062][98559] Updated weights for policy 0, policy_version 88120 (0.0010) -[2023-10-11 00:21:10,556][97672] Fps is (10 sec: 16383.6, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 179863552. Throughput: 0: 1716.8, 1: 1664.4. Samples: 44967282. Policy #0 lag: (min: 24.0, avg: 48.1, max: 56.0) -[2023-10-11 00:21:10,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.540')] -[2023-10-11 00:21:11,389][98560] Updated weights for policy 1, policy_version 87522 (0.0009) -[2023-10-11 00:21:11,761][98560] Updated weights for policy 1, policy_version 87532 (0.0010) -[2023-10-11 00:21:12,131][98560] Updated weights for policy 1, policy_version 87542 (0.0009) -[2023-10-11 00:21:12,504][98560] Updated weights for policy 1, policy_version 87552 (0.0009) -[2023-10-11 00:21:14,045][98559] Updated weights for policy 0, policy_version 88130 (0.0009) -[2023-10-11 00:21:14,411][98559] Updated weights for policy 0, policy_version 88140 (0.0008) -[2023-10-11 00:21:14,773][98559] Updated weights for policy 0, policy_version 88150 (0.0008) -[2023-10-11 00:21:15,138][98559] Updated weights for policy 0, policy_version 88160 (0.0009) -[2023-10-11 00:21:15,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 179929088. Throughput: 0: 1708.2, 1: 1688.9. Samples: 44988028. Policy #0 lag: (min: 24.0, avg: 48.1, max: 56.0) -[2023-10-11 00:21:15,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.540')] -[2023-10-11 00:21:16,690][98560] Updated weights for policy 1, policy_version 87562 (0.0009) -[2023-10-11 00:21:17,061][98560] Updated weights for policy 1, policy_version 87572 (0.0007) -[2023-10-11 00:21:17,426][98560] Updated weights for policy 1, policy_version 87582 (0.0008) -[2023-10-11 00:21:19,136][98559] Updated weights for policy 0, policy_version 88170 (0.0009) -[2023-10-11 00:21:19,496][98559] Updated weights for policy 0, policy_version 88180 (0.0009) -[2023-10-11 00:21:19,869][98559] Updated weights for policy 0, policy_version 88190 (0.0007) -[2023-10-11 00:21:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 179994624. Throughput: 0: 1690.7, 1: 1699.6. Samples: 45007926. Policy #0 lag: (min: 24.0, avg: 48.1, max: 56.0) -[2023-10-11 00:21:20,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.480')] -[2023-10-11 00:21:21,517][98560] Updated weights for policy 1, policy_version 87592 (0.0010) -[2023-10-11 00:21:21,888][98560] Updated weights for policy 1, policy_version 87602 (0.0009) -[2023-10-11 00:21:22,250][98560] Updated weights for policy 1, policy_version 87612 (0.0009) -[2023-10-11 00:21:23,996][98559] Updated weights for policy 0, policy_version 88200 (0.0009) -[2023-10-11 00:21:24,360][98559] Updated weights for policy 0, policy_version 88210 (0.0010) -[2023-10-11 00:21:24,726][98559] Updated weights for policy 0, policy_version 88220 (0.0010) -[2023-10-11 00:21:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 180060160. Throughput: 0: 1722.7, 1: 1670.8. Samples: 45018360. Policy #0 lag: (min: 24.0, avg: 48.1, max: 56.0) -[2023-10-11 00:21:25,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.460')] -[2023-10-11 00:21:26,209][98560] Updated weights for policy 1, policy_version 87622 (0.0008) -[2023-10-11 00:21:26,579][98560] Updated weights for policy 1, policy_version 87632 (0.0008) -[2023-10-11 00:21:26,935][98560] Updated weights for policy 1, policy_version 87642 (0.0008) -[2023-10-11 00:21:28,746][98559] Updated weights for policy 0, policy_version 88230 (0.0008) -[2023-10-11 00:21:29,121][98559] Updated weights for policy 0, policy_version 88240 (0.0010) -[2023-10-11 00:21:29,487][98559] Updated weights for policy 0, policy_version 88250 (0.0009) -[2023-10-11 00:21:30,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 180125696. Throughput: 0: 1702.5, 1: 1698.9. Samples: 45038444. Policy #0 lag: (min: 24.0, avg: 48.1, max: 56.0) -[2023-10-11 00:21:30,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.440')] -[2023-10-11 00:21:30,998][98560] Updated weights for policy 1, policy_version 87652 (0.0008) -[2023-10-11 00:21:31,355][98560] Updated weights for policy 1, policy_version 87662 (0.0010) -[2023-10-11 00:21:31,726][98560] Updated weights for policy 1, policy_version 87672 (0.0011) -[2023-10-11 00:21:33,495][98559] Updated weights for policy 0, policy_version 88260 (0.0010) -[2023-10-11 00:21:33,856][98559] Updated weights for policy 0, policy_version 88270 (0.0010) -[2023-10-11 00:21:34,225][98559] Updated weights for policy 0, policy_version 88280 (0.0010) -[2023-10-11 00:21:35,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 180191232. Throughput: 0: 1695.7, 1: 1703.0. Samples: 45059078. Policy #0 lag: (min: 24.0, avg: 48.1, max: 56.0) -[2023-10-11 00:21:35,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.360')] -[2023-10-11 00:21:35,715][98560] Updated weights for policy 1, policy_version 87682 (0.0010) -[2023-10-11 00:21:36,089][98560] Updated weights for policy 1, policy_version 87692 (0.0007) -[2023-10-11 00:21:36,457][98560] Updated weights for policy 1, policy_version 87702 (0.0008) -[2023-10-11 00:21:36,815][98560] Updated weights for policy 1, policy_version 87712 (0.0011) -[2023-10-11 00:21:38,183][98559] Updated weights for policy 0, policy_version 88290 (0.0007) -[2023-10-11 00:21:38,551][98559] Updated weights for policy 0, policy_version 88300 (0.0007) -[2023-10-11 00:21:38,918][98559] Updated weights for policy 0, policy_version 88310 (0.0007) -[2023-10-11 00:21:39,276][98559] Updated weights for policy 0, policy_version 88320 (0.0009) -[2023-10-11 00:21:40,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 180256768. Throughput: 0: 1712.2, 1: 1681.9. Samples: 45069294. Policy #0 lag: (min: 24.0, avg: 48.1, max: 56.0) -[2023-10-11 00:21:40,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.380')] -[2023-10-11 00:21:40,940][98560] Updated weights for policy 1, policy_version 87722 (0.0009) -[2023-10-11 00:21:41,301][98560] Updated weights for policy 1, policy_version 87732 (0.0008) -[2023-10-11 00:21:41,667][98560] Updated weights for policy 1, policy_version 87742 (0.0009) -[2023-10-11 00:21:43,078][98559] Updated weights for policy 0, policy_version 88330 (0.0010) -[2023-10-11 00:21:43,445][98559] Updated weights for policy 0, policy_version 88340 (0.0009) -[2023-10-11 00:21:43,807][98559] Updated weights for policy 0, policy_version 88350 (0.0009) -[2023-10-11 00:21:45,533][98560] Updated weights for policy 1, policy_version 87752 (0.0009) -[2023-10-11 00:21:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 180322304. Throughput: 0: 1691.8, 1: 1697.2. Samples: 45089418. Policy #0 lag: (min: 24.0, avg: 48.1, max: 56.0) -[2023-10-11 00:21:45,556][97672] Avg episode reward: [(0, '-0.820'), (1, '22.400')] -[2023-10-11 00:21:45,898][98560] Updated weights for policy 1, policy_version 87762 (0.0008) -[2023-10-11 00:21:46,281][98560] Updated weights for policy 1, policy_version 87772 (0.0009) -[2023-10-11 00:21:47,801][98559] Updated weights for policy 0, policy_version 88360 (0.0009) -[2023-10-11 00:21:48,165][98559] Updated weights for policy 0, policy_version 88370 (0.0009) -[2023-10-11 00:21:48,542][98559] Updated weights for policy 0, policy_version 88380 (0.0009) -[2023-10-11 00:21:50,268][98560] Updated weights for policy 1, policy_version 87782 (0.0008) -[2023-10-11 00:21:50,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 180387840. Throughput: 0: 1712.9, 1: 1706.1. Samples: 45110634. Policy #0 lag: (min: 24.0, avg: 48.1, max: 56.0) -[2023-10-11 00:21:50,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.360')] -[2023-10-11 00:21:50,630][98560] Updated weights for policy 1, policy_version 87792 (0.0009) -[2023-10-11 00:21:51,005][98560] Updated weights for policy 1, policy_version 87802 (0.0009) -[2023-10-11 00:21:52,536][98559] Updated weights for policy 0, policy_version 88390 (0.0010) -[2023-10-11 00:21:52,898][98559] Updated weights for policy 0, policy_version 88400 (0.0009) -[2023-10-11 00:21:53,267][98559] Updated weights for policy 0, policy_version 88410 (0.0010) -[2023-10-11 00:21:55,020][98560] Updated weights for policy 1, policy_version 87812 (0.0009) -[2023-10-11 00:21:55,391][98560] Updated weights for policy 1, policy_version 87822 (0.0009) -[2023-10-11 00:21:55,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 180453376. Throughput: 0: 1692.1, 1: 1702.5. Samples: 45120038. Policy #0 lag: (min: 24.0, avg: 48.1, max: 56.0) -[2023-10-11 00:21:55,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.380')] -[2023-10-11 00:21:55,759][98560] Updated weights for policy 1, policy_version 87832 (0.0009) -[2023-10-11 00:21:57,198][98559] Updated weights for policy 0, policy_version 88420 (0.0007) -[2023-10-11 00:21:57,558][98559] Updated weights for policy 0, policy_version 88430 (0.0008) -[2023-10-11 00:21:57,925][98559] Updated weights for policy 0, policy_version 88440 (0.0010) -[2023-10-11 00:21:59,877][98560] Updated weights for policy 1, policy_version 87842 (0.0007) -[2023-10-11 00:22:00,245][98560] Updated weights for policy 1, policy_version 87852 (0.0010) -[2023-10-11 00:22:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 180518912. Throughput: 0: 1693.1, 1: 1704.3. Samples: 45140910. Policy #0 lag: (min: 24.0, avg: 48.1, max: 56.0) -[2023-10-11 00:22:00,556][97672] Avg episode reward: [(0, '-0.820'), (1, '22.420')] -[2023-10-11 00:22:00,606][98560] Updated weights for policy 1, policy_version 87862 (0.0007) -[2023-10-11 00:22:00,977][98560] Updated weights for policy 1, policy_version 87872 (0.0009) -[2023-10-11 00:22:01,992][98559] Updated weights for policy 0, policy_version 88450 (0.0009) -[2023-10-11 00:22:02,366][98559] Updated weights for policy 0, policy_version 88460 (0.0009) -[2023-10-11 00:22:02,722][98559] Updated weights for policy 0, policy_version 88470 (0.0011) -[2023-10-11 00:22:03,083][98559] Updated weights for policy 0, policy_version 88480 (0.0009) -[2023-10-11 00:22:05,063][98560] Updated weights for policy 1, policy_version 87882 (0.0007) -[2023-10-11 00:22:05,436][98560] Updated weights for policy 1, policy_version 87892 (0.0007) -[2023-10-11 00:22:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 180584448. Throughput: 0: 1715.9, 1: 1704.9. Samples: 45161860. Policy #0 lag: (min: 24.0, avg: 48.1, max: 56.0) -[2023-10-11 00:22:05,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.420')] -[2023-10-11 00:22:05,807][98560] Updated weights for policy 1, policy_version 87902 (0.0007) -[2023-10-11 00:22:07,084][98559] Updated weights for policy 0, policy_version 88490 (0.0007) -[2023-10-11 00:22:07,452][98559] Updated weights for policy 0, policy_version 88500 (0.0009) -[2023-10-11 00:22:07,821][98559] Updated weights for policy 0, policy_version 88510 (0.0010) -[2023-10-11 00:22:09,752][98560] Updated weights for policy 1, policy_version 87912 (0.0010) -[2023-10-11 00:22:10,113][98560] Updated weights for policy 1, policy_version 87922 (0.0009) -[2023-10-11 00:22:10,484][98560] Updated weights for policy 1, policy_version 87932 (0.0009) -[2023-10-11 00:22:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 180649984. Throughput: 0: 1684.0, 1: 1706.1. Samples: 45170916. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-11 00:22:10,556][97672] Avg episode reward: [(0, '-0.820'), (1, '22.400')] -[2023-10-11 00:22:11,909][98559] Updated weights for policy 0, policy_version 88520 (0.0007) -[2023-10-11 00:22:12,279][98559] Updated weights for policy 0, policy_version 88530 (0.0007) -[2023-10-11 00:22:12,643][98559] Updated weights for policy 0, policy_version 88540 (0.0007) -[2023-10-11 00:22:14,456][98560] Updated weights for policy 1, policy_version 87942 (0.0009) -[2023-10-11 00:22:14,829][98560] Updated weights for policy 1, policy_version 87952 (0.0009) -[2023-10-11 00:22:15,198][98560] Updated weights for policy 1, policy_version 87962 (0.0009) -[2023-10-11 00:22:15,556][97672] Fps is (10 sec: 16384.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 180748288. Throughput: 0: 1707.6, 1: 1709.9. Samples: 45192234. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-11 00:22:15,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.420')] -[2023-10-11 00:22:16,598][98559] Updated weights for policy 0, policy_version 88550 (0.0007) -[2023-10-11 00:22:16,995][98559] Updated weights for policy 0, policy_version 88560 (0.0009) -[2023-10-11 00:22:17,363][98559] Updated weights for policy 0, policy_version 88570 (0.0008) -[2023-10-11 00:22:19,196][98560] Updated weights for policy 1, policy_version 87972 (0.0009) -[2023-10-11 00:22:19,576][98560] Updated weights for policy 1, policy_version 87982 (0.0008) -[2023-10-11 00:22:19,936][98560] Updated weights for policy 1, policy_version 87992 (0.0010) -[2023-10-11 00:22:20,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 180813824. Throughput: 0: 1714.5, 1: 1695.0. Samples: 45212506. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-11 00:22:20,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.480')] -[2023-10-11 00:22:21,467][98559] Updated weights for policy 0, policy_version 88580 (0.0007) -[2023-10-11 00:22:21,834][98559] Updated weights for policy 0, policy_version 88590 (0.0008) -[2023-10-11 00:22:22,195][98559] Updated weights for policy 0, policy_version 88600 (0.0007) -[2023-10-11 00:22:23,813][98560] Updated weights for policy 1, policy_version 88002 (0.0008) -[2023-10-11 00:22:24,174][98560] Updated weights for policy 1, policy_version 88012 (0.0011) -[2023-10-11 00:22:24,540][98560] Updated weights for policy 1, policy_version 88022 (0.0011) -[2023-10-11 00:22:24,910][98560] Updated weights for policy 1, policy_version 88032 (0.0011) -[2023-10-11 00:22:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 180879360. Throughput: 0: 1689.9, 1: 1716.8. Samples: 45222594. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-11 00:22:25,556][97672] Avg episode reward: [(0, '-0.820'), (1, '22.480')] -[2023-10-11 00:22:25,970][98559] Updated weights for policy 0, policy_version 88610 (0.0011) -[2023-10-11 00:22:26,335][98559] Updated weights for policy 0, policy_version 88620 (0.0008) -[2023-10-11 00:22:26,705][98559] Updated weights for policy 0, policy_version 88630 (0.0010) -[2023-10-11 00:22:27,071][98559] Updated weights for policy 0, policy_version 88640 (0.0009) -[2023-10-11 00:22:28,938][98560] Updated weights for policy 1, policy_version 88042 (0.0007) -[2023-10-11 00:22:29,299][98560] Updated weights for policy 1, policy_version 88052 (0.0009) -[2023-10-11 00:22:29,670][98560] Updated weights for policy 1, policy_version 88062 (0.0011) -[2023-10-11 00:22:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 180944896. Throughput: 0: 1718.4, 1: 1711.4. Samples: 45243760. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-11 00:22:30,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.500')] -[2023-10-11 00:22:31,025][98559] Updated weights for policy 0, policy_version 88650 (0.0010) -[2023-10-11 00:22:31,389][98559] Updated weights for policy 0, policy_version 88660 (0.0011) -[2023-10-11 00:22:31,759][98559] Updated weights for policy 0, policy_version 88670 (0.0008) -[2023-10-11 00:22:33,856][98560] Updated weights for policy 1, policy_version 88072 (0.0009) -[2023-10-11 00:22:34,218][98560] Updated weights for policy 1, policy_version 88082 (0.0009) -[2023-10-11 00:22:34,584][98560] Updated weights for policy 1, policy_version 88092 (0.0008) -[2023-10-11 00:22:35,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 181010432. Throughput: 0: 1715.1, 1: 1682.7. Samples: 45263538. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-11 00:22:35,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.480')] -[2023-10-11 00:22:35,568][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000088096_90210304.pth... -[2023-10-11 00:22:35,608][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000086496_88571904.pth -[2023-10-11 00:22:35,722][98559] Updated weights for policy 0, policy_version 88680 (0.0007) -[2023-10-11 00:22:36,088][98559] Updated weights for policy 0, policy_version 88690 (0.0007) -[2023-10-11 00:22:36,462][98559] Updated weights for policy 0, policy_version 88700 (0.0008) -[2023-10-11 00:22:36,603][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000088704_90832896.pth... -[2023-10-11 00:22:36,640][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000087104_89194496.pth -[2023-10-11 00:22:38,639][98560] Updated weights for policy 1, policy_version 88102 (0.0009) -[2023-10-11 00:22:39,002][98560] Updated weights for policy 1, policy_version 88112 (0.0010) -[2023-10-11 00:22:39,367][98560] Updated weights for policy 1, policy_version 88122 (0.0010) -[2023-10-11 00:22:40,450][98559] Updated weights for policy 0, policy_version 88710 (0.0008) -[2023-10-11 00:22:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 181075968. Throughput: 0: 1711.0, 1: 1713.2. Samples: 45274126. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-11 00:22:40,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.500')] -[2023-10-11 00:22:40,817][98559] Updated weights for policy 0, policy_version 88720 (0.0008) -[2023-10-11 00:22:41,172][98559] Updated weights for policy 0, policy_version 88730 (0.0009) -[2023-10-11 00:22:43,416][98560] Updated weights for policy 1, policy_version 88132 (0.0008) -[2023-10-11 00:22:43,787][98560] Updated weights for policy 1, policy_version 88142 (0.0008) -[2023-10-11 00:22:44,155][98560] Updated weights for policy 1, policy_version 88152 (0.0009) -[2023-10-11 00:22:45,362][98559] Updated weights for policy 0, policy_version 88740 (0.0009) -[2023-10-11 00:22:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 181141504. Throughput: 0: 1721.4, 1: 1695.9. Samples: 45294692. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-11 00:22:45,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.440')] -[2023-10-11 00:22:45,739][98559] Updated weights for policy 0, policy_version 88750 (0.0008) -[2023-10-11 00:22:46,111][98559] Updated weights for policy 0, policy_version 88760 (0.0009) -[2023-10-11 00:22:48,108][98560] Updated weights for policy 1, policy_version 88162 (0.0008) -[2023-10-11 00:22:48,478][98560] Updated weights for policy 1, policy_version 88172 (0.0010) -[2023-10-11 00:22:48,845][98560] Updated weights for policy 1, policy_version 88182 (0.0007) -[2023-10-11 00:22:49,206][98560] Updated weights for policy 1, policy_version 88192 (0.0007) -[2023-10-11 00:22:50,287][98559] Updated weights for policy 0, policy_version 88770 (0.0011) -[2023-10-11 00:22:50,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 181207040. Throughput: 0: 1708.6, 1: 1682.6. Samples: 45314466. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-11 00:22:50,558][97672] Avg episode reward: [(0, '-0.840'), (1, '22.480')] -[2023-10-11 00:22:50,665][98559] Updated weights for policy 0, policy_version 88780 (0.0010) -[2023-10-11 00:22:51,023][98559] Updated weights for policy 0, policy_version 88790 (0.0009) -[2023-10-11 00:22:51,388][98559] Updated weights for policy 0, policy_version 88800 (0.0009) -[2023-10-11 00:22:53,597][98560] Updated weights for policy 1, policy_version 88202 (0.0009) -[2023-10-11 00:22:53,960][98560] Updated weights for policy 1, policy_version 88212 (0.0007) -[2023-10-11 00:22:54,321][98560] Updated weights for policy 1, policy_version 88222 (0.0007) -[2023-10-11 00:22:55,295][98559] Updated weights for policy 0, policy_version 88810 (0.0010) -[2023-10-11 00:22:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 181272576. Throughput: 0: 1713.1, 1: 1712.2. Samples: 45325056. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-11 00:22:55,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.480')] -[2023-10-11 00:22:55,658][98559] Updated weights for policy 0, policy_version 88820 (0.0007) -[2023-10-11 00:22:56,021][98559] Updated weights for policy 0, policy_version 88830 (0.0008) -[2023-10-11 00:22:58,270][98560] Updated weights for policy 1, policy_version 88232 (0.0007) -[2023-10-11 00:22:58,638][98560] Updated weights for policy 1, policy_version 88242 (0.0008) -[2023-10-11 00:22:59,002][98560] Updated weights for policy 1, policy_version 88252 (0.0010) -[2023-10-11 00:22:59,905][98559] Updated weights for policy 0, policy_version 88840 (0.0009) -[2023-10-11 00:23:00,281][98559] Updated weights for policy 0, policy_version 88850 (0.0010) -[2023-10-11 00:23:00,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 181338112. Throughput: 0: 1715.6, 1: 1684.2. Samples: 45345222. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-11 00:23:00,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.460')] -[2023-10-11 00:23:00,648][98559] Updated weights for policy 0, policy_version 88860 (0.0008) -[2023-10-11 00:23:02,911][98560] Updated weights for policy 1, policy_version 88262 (0.0008) -[2023-10-11 00:23:03,269][98560] Updated weights for policy 1, policy_version 88272 (0.0009) -[2023-10-11 00:23:03,628][98560] Updated weights for policy 1, policy_version 88282 (0.0009) -[2023-10-11 00:23:04,784][98559] Updated weights for policy 0, policy_version 88870 (0.0009) -[2023-10-11 00:23:05,170][98559] Updated weights for policy 0, policy_version 88880 (0.0009) -[2023-10-11 00:23:05,537][98559] Updated weights for policy 0, policy_version 88890 (0.0007) -[2023-10-11 00:23:05,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 181403648. Throughput: 0: 1698.1, 1: 1687.6. Samples: 45364864. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-11 00:23:05,556][97672] Avg episode reward: [(0, '-0.820'), (1, '22.460')] -[2023-10-11 00:23:07,729][98560] Updated weights for policy 1, policy_version 88292 (0.0009) -[2023-10-11 00:23:08,095][98560] Updated weights for policy 1, policy_version 88302 (0.0008) -[2023-10-11 00:23:08,461][98560] Updated weights for policy 1, policy_version 88312 (0.0010) -[2023-10-11 00:23:09,401][98559] Updated weights for policy 0, policy_version 88900 (0.0009) -[2023-10-11 00:23:09,769][98559] Updated weights for policy 0, policy_version 88910 (0.0008) -[2023-10-11 00:23:10,131][98559] Updated weights for policy 0, policy_version 88920 (0.0008) -[2023-10-11 00:23:10,556][97672] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 181501952. Throughput: 0: 1716.7, 1: 1693.5. Samples: 45376050. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-11 00:23:10,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.500')] -[2023-10-11 00:23:12,413][98560] Updated weights for policy 1, policy_version 88322 (0.0009) -[2023-10-11 00:23:12,773][98560] Updated weights for policy 1, policy_version 88332 (0.0008) -[2023-10-11 00:23:13,147][98560] Updated weights for policy 1, policy_version 88342 (0.0008) -[2023-10-11 00:23:13,511][98560] Updated weights for policy 1, policy_version 88352 (0.0009) -[2023-10-11 00:23:14,112][98559] Updated weights for policy 0, policy_version 88930 (0.0009) -[2023-10-11 00:23:14,476][98559] Updated weights for policy 0, policy_version 88940 (0.0009) -[2023-10-11 00:23:14,850][98559] Updated weights for policy 0, policy_version 88950 (0.0007) -[2023-10-11 00:23:15,217][98559] Updated weights for policy 0, policy_version 88960 (0.0011) -[2023-10-11 00:23:15,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 181567488. Throughput: 0: 1706.2, 1: 1671.9. Samples: 45395774. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-11 00:23:15,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.520')] -[2023-10-11 00:23:17,340][98560] Updated weights for policy 1, policy_version 88362 (0.0007) -[2023-10-11 00:23:17,711][98560] Updated weights for policy 1, policy_version 88372 (0.0009) -[2023-10-11 00:23:18,076][98560] Updated weights for policy 1, policy_version 88382 (0.0009) -[2023-10-11 00:23:19,355][98559] Updated weights for policy 0, policy_version 88970 (0.0011) -[2023-10-11 00:23:19,725][98559] Updated weights for policy 0, policy_version 88980 (0.0008) -[2023-10-11 00:23:20,095][98559] Updated weights for policy 0, policy_version 88990 (0.0009) -[2023-10-11 00:23:20,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 181633024. Throughput: 0: 1685.0, 1: 1700.8. Samples: 45415900. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-11 00:23:20,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.540')] -[2023-10-11 00:23:21,945][98560] Updated weights for policy 1, policy_version 88392 (0.0010) -[2023-10-11 00:23:22,313][98560] Updated weights for policy 1, policy_version 88402 (0.0008) -[2023-10-11 00:23:22,687][98560] Updated weights for policy 1, policy_version 88412 (0.0008) -[2023-10-11 00:23:24,032][98559] Updated weights for policy 0, policy_version 89000 (0.0009) -[2023-10-11 00:23:24,391][98559] Updated weights for policy 0, policy_version 89010 (0.0010) -[2023-10-11 00:23:24,767][98559] Updated weights for policy 0, policy_version 89020 (0.0008) -[2023-10-11 00:23:25,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 181698560. Throughput: 0: 1714.9, 1: 1679.1. Samples: 45426858. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-11 00:23:25,556][97672] Avg episode reward: [(0, '-0.820'), (1, '22.560')] -[2023-10-11 00:23:26,804][98560] Updated weights for policy 1, policy_version 88422 (0.0009) -[2023-10-11 00:23:27,176][98560] Updated weights for policy 1, policy_version 88432 (0.0010) -[2023-10-11 00:23:27,538][98560] Updated weights for policy 1, policy_version 88442 (0.0007) -[2023-10-11 00:23:28,702][98559] Updated weights for policy 0, policy_version 89030 (0.0009) -[2023-10-11 00:23:29,073][98559] Updated weights for policy 0, policy_version 89040 (0.0011) -[2023-10-11 00:23:29,434][98559] Updated weights for policy 0, policy_version 89050 (0.0010) -[2023-10-11 00:23:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 181764096. Throughput: 0: 1694.5, 1: 1684.4. Samples: 45446744. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-11 00:23:30,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.560')] -[2023-10-11 00:23:31,471][98560] Updated weights for policy 1, policy_version 88452 (0.0008) -[2023-10-11 00:23:31,836][98560] Updated weights for policy 1, policy_version 88462 (0.0007) -[2023-10-11 00:23:32,194][98560] Updated weights for policy 1, policy_version 88472 (0.0007) -[2023-10-11 00:23:33,400][98559] Updated weights for policy 0, policy_version 89060 (0.0009) -[2023-10-11 00:23:33,759][98559] Updated weights for policy 0, policy_version 89070 (0.0010) -[2023-10-11 00:23:34,132][98559] Updated weights for policy 0, policy_version 89080 (0.0010) -[2023-10-11 00:23:35,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 181829632. Throughput: 0: 1703.4, 1: 1700.8. Samples: 45467652. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-11 00:23:35,556][97672] Avg episode reward: [(0, '-0.820'), (1, '22.560')] -[2023-10-11 00:23:36,282][98560] Updated weights for policy 1, policy_version 88482 (0.0010) -[2023-10-11 00:23:36,642][98560] Updated weights for policy 1, policy_version 88492 (0.0007) -[2023-10-11 00:23:37,014][98560] Updated weights for policy 1, policy_version 88502 (0.0008) -[2023-10-11 00:23:37,378][98560] Updated weights for policy 1, policy_version 88512 (0.0008) -[2023-10-11 00:23:38,012][98559] Updated weights for policy 0, policy_version 89090 (0.0010) -[2023-10-11 00:23:38,385][98559] Updated weights for policy 0, policy_version 89100 (0.0007) -[2023-10-11 00:23:38,746][98559] Updated weights for policy 0, policy_version 89110 (0.0009) -[2023-10-11 00:23:39,112][98559] Updated weights for policy 0, policy_version 89120 (0.0008) -[2023-10-11 00:23:40,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 181895168. Throughput: 0: 1725.8, 1: 1671.4. Samples: 45477930. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-11 00:23:40,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.540')] -[2023-10-11 00:23:41,542][98560] Updated weights for policy 1, policy_version 88522 (0.0010) -[2023-10-11 00:23:41,916][98560] Updated weights for policy 1, policy_version 88532 (0.0011) -[2023-10-11 00:23:42,287][98560] Updated weights for policy 1, policy_version 88542 (0.0010) -[2023-10-11 00:23:43,095][98559] Updated weights for policy 0, policy_version 89130 (0.0009) -[2023-10-11 00:23:43,466][98559] Updated weights for policy 0, policy_version 89140 (0.0007) -[2023-10-11 00:23:43,825][98559] Updated weights for policy 0, policy_version 89150 (0.0007) -[2023-10-11 00:23:45,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 181960704. Throughput: 0: 1704.0, 1: 1690.9. Samples: 45497994. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-11 00:23:45,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.560')] -[2023-10-11 00:23:46,311][98560] Updated weights for policy 1, policy_version 88552 (0.0008) -[2023-10-11 00:23:46,690][98560] Updated weights for policy 1, policy_version 88562 (0.0008) -[2023-10-11 00:23:47,054][98560] Updated weights for policy 1, policy_version 88572 (0.0007) -[2023-10-11 00:23:47,767][98559] Updated weights for policy 0, policy_version 89160 (0.0010) -[2023-10-11 00:23:48,128][98559] Updated weights for policy 0, policy_version 89170 (0.0010) -[2023-10-11 00:23:48,499][98559] Updated weights for policy 0, policy_version 89180 (0.0008) -[2023-10-11 00:23:50,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 182026240. Throughput: 0: 1726.7, 1: 1702.4. Samples: 45519174. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-11 00:23:50,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.600')] -[2023-10-11 00:23:51,075][98560] Updated weights for policy 1, policy_version 88582 (0.0009) -[2023-10-11 00:23:51,438][98560] Updated weights for policy 1, policy_version 88592 (0.0010) -[2023-10-11 00:23:51,813][98560] Updated weights for policy 1, policy_version 88602 (0.0011) -[2023-10-11 00:23:52,348][98559] Updated weights for policy 0, policy_version 89190 (0.0008) -[2023-10-11 00:23:52,733][98559] Updated weights for policy 0, policy_version 89200 (0.0007) -[2023-10-11 00:23:53,109][98559] Updated weights for policy 0, policy_version 89210 (0.0010) -[2023-10-11 00:23:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 182091776. Throughput: 0: 1706.7, 1: 1676.5. Samples: 45528294. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-11 00:23:55,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.640')] -[2023-10-11 00:23:56,039][98560] Updated weights for policy 1, policy_version 88612 (0.0009) -[2023-10-11 00:23:56,405][98560] Updated weights for policy 1, policy_version 88622 (0.0007) -[2023-10-11 00:23:56,775][98560] Updated weights for policy 1, policy_version 88632 (0.0009) -[2023-10-11 00:23:57,102][98559] Updated weights for policy 0, policy_version 89220 (0.0010) -[2023-10-11 00:23:57,467][98559] Updated weights for policy 0, policy_version 89230 (0.0009) -[2023-10-11 00:23:57,824][98559] Updated weights for policy 0, policy_version 89240 (0.0008) -[2023-10-11 00:24:00,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 182157312. Throughput: 0: 1710.2, 1: 1701.6. Samples: 45549304. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-11 00:24:00,557][97672] Avg episode reward: [(0, '-0.840'), (1, '22.620')] -[2023-10-11 00:24:00,868][98560] Updated weights for policy 1, policy_version 88642 (0.0008) -[2023-10-11 00:24:01,230][98560] Updated weights for policy 1, policy_version 88652 (0.0008) -[2023-10-11 00:24:01,598][98560] Updated weights for policy 1, policy_version 88662 (0.0007) -[2023-10-11 00:24:01,701][98559] Updated weights for policy 0, policy_version 89250 (0.0008) -[2023-10-11 00:24:01,965][98560] Updated weights for policy 1, policy_version 88672 (0.0009) -[2023-10-11 00:24:02,065][98559] Updated weights for policy 0, policy_version 89260 (0.0007) -[2023-10-11 00:24:02,429][98559] Updated weights for policy 0, policy_version 89270 (0.0008) -[2023-10-11 00:24:02,807][98559] Updated weights for policy 0, policy_version 89280 (0.0008) -[2023-10-11 00:24:05,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 182222848. Throughput: 0: 1732.9, 1: 1694.0. Samples: 45570106. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-11 00:24:05,556][97672] Avg episode reward: [(0, '-0.840'), (1, '22.580')] -[2023-10-11 00:24:05,937][98560] Updated weights for policy 1, policy_version 88682 (0.0008) -[2023-10-11 00:24:06,305][98560] Updated weights for policy 1, policy_version 88692 (0.0010) -[2023-10-11 00:24:06,677][98560] Updated weights for policy 1, policy_version 88702 (0.0008) -[2023-10-11 00:24:06,749][98559] Updated weights for policy 0, policy_version 89290 (0.0008) -[2023-10-11 00:24:07,119][98559] Updated weights for policy 0, policy_version 89300 (0.0008) -[2023-10-11 00:24:07,487][98559] Updated weights for policy 0, policy_version 89310 (0.0009) -[2023-10-11 00:24:10,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 182288384. Throughput: 0: 1701.9, 1: 1687.2. Samples: 45579368. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-11 00:24:10,556][97672] Avg episode reward: [(0, '-0.840'), (1, '22.520')] -[2023-10-11 00:24:10,683][98560] Updated weights for policy 1, policy_version 88712 (0.0007) -[2023-10-11 00:24:11,060][98560] Updated weights for policy 1, policy_version 88722 (0.0008) -[2023-10-11 00:24:11,424][98560] Updated weights for policy 1, policy_version 88732 (0.0008) -[2023-10-11 00:24:11,641][98559] Updated weights for policy 0, policy_version 89320 (0.0008) -[2023-10-11 00:24:12,011][98559] Updated weights for policy 0, policy_version 89330 (0.0008) -[2023-10-11 00:24:12,382][98559] Updated weights for policy 0, policy_version 89340 (0.0007) -[2023-10-11 00:24:15,457][98560] Updated weights for policy 1, policy_version 88742 (0.0011) -[2023-10-11 00:24:15,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 182353920. Throughput: 0: 1715.1, 1: 1696.7. Samples: 45600272. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-11 00:24:15,557][97672] Avg episode reward: [(0, '-0.820'), (1, '22.560')] -[2023-10-11 00:24:15,829][98560] Updated weights for policy 1, policy_version 88752 (0.0008) -[2023-10-11 00:24:16,192][98560] Updated weights for policy 1, policy_version 88762 (0.0008) -[2023-10-11 00:24:16,437][98559] Updated weights for policy 0, policy_version 89350 (0.0007) -[2023-10-11 00:24:16,807][98559] Updated weights for policy 0, policy_version 89360 (0.0009) -[2023-10-11 00:24:17,172][98559] Updated weights for policy 0, policy_version 89370 (0.0010) -[2023-10-11 00:24:20,234][98560] Updated weights for policy 1, policy_version 88772 (0.0007) -[2023-10-11 00:24:20,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 182419456. Throughput: 0: 1718.2, 1: 1695.8. Samples: 45621282. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-11 00:24:20,557][97672] Avg episode reward: [(0, '-0.760'), (1, '22.540')] -[2023-10-11 00:24:20,604][98560] Updated weights for policy 1, policy_version 88782 (0.0008) -[2023-10-11 00:24:20,980][98560] Updated weights for policy 1, policy_version 88792 (0.0010) -[2023-10-11 00:24:21,145][98559] Updated weights for policy 0, policy_version 89380 (0.0007) -[2023-10-11 00:24:21,510][98559] Updated weights for policy 0, policy_version 89390 (0.0008) -[2023-10-11 00:24:21,883][98559] Updated weights for policy 0, policy_version 89400 (0.0008) -[2023-10-11 00:24:24,968][98560] Updated weights for policy 1, policy_version 88802 (0.0008) -[2023-10-11 00:24:25,344][98560] Updated weights for policy 1, policy_version 88812 (0.0007) -[2023-10-11 00:24:25,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 182484992. Throughput: 0: 1692.5, 1: 1699.0. Samples: 45630544. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-11 00:24:25,556][97672] Avg episode reward: [(0, '-0.760'), (1, '22.560')] -[2023-10-11 00:24:25,711][98560] Updated weights for policy 1, policy_version 88822 (0.0008) -[2023-10-11 00:24:25,919][98559] Updated weights for policy 0, policy_version 89410 (0.0008) -[2023-10-11 00:24:26,079][98560] Updated weights for policy 1, policy_version 88832 (0.0009) -[2023-10-11 00:24:26,284][98559] Updated weights for policy 0, policy_version 89420 (0.0009) -[2023-10-11 00:24:26,654][98559] Updated weights for policy 0, policy_version 89430 (0.0009) -[2023-10-11 00:24:27,015][98559] Updated weights for policy 0, policy_version 89440 (0.0008) -[2023-10-11 00:24:30,087][98560] Updated weights for policy 1, policy_version 88842 (0.0009) -[2023-10-11 00:24:30,451][98560] Updated weights for policy 1, policy_version 88852 (0.0008) -[2023-10-11 00:24:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 182550528. Throughput: 0: 1710.7, 1: 1702.9. Samples: 45651604. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-11 00:24:30,557][97672] Avg episode reward: [(0, '-0.760'), (1, '22.620')] -[2023-10-11 00:24:30,815][98560] Updated weights for policy 1, policy_version 88862 (0.0009) -[2023-10-11 00:24:31,054][98559] Updated weights for policy 0, policy_version 89450 (0.0008) -[2023-10-11 00:24:31,416][98559] Updated weights for policy 0, policy_version 89460 (0.0007) -[2023-10-11 00:24:31,789][98559] Updated weights for policy 0, policy_version 89470 (0.0008) -[2023-10-11 00:24:34,893][98560] Updated weights for policy 1, policy_version 88872 (0.0009) -[2023-10-11 00:24:35,256][98560] Updated weights for policy 1, policy_version 88882 (0.0011) -[2023-10-11 00:24:35,556][97672] Fps is (10 sec: 13106.7, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 182616064. Throughput: 0: 1707.6, 1: 1698.6. Samples: 45672454. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-11 00:24:35,557][97672] Avg episode reward: [(0, '-0.760'), (1, '22.640')] -[2023-10-11 00:24:35,628][98560] Updated weights for policy 1, policy_version 88892 (0.0008) -[2023-10-11 00:24:35,771][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000088896_91029504.pth... -[2023-10-11 00:24:35,799][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000087296_89391104.pth -[2023-10-11 00:24:35,902][98559] Updated weights for policy 0, policy_version 89480 (0.0008) -[2023-10-11 00:24:36,261][98559] Updated weights for policy 0, policy_version 89490 (0.0007) -[2023-10-11 00:24:36,632][98559] Updated weights for policy 0, policy_version 89500 (0.0008) -[2023-10-11 00:24:36,772][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000089504_91652096.pth... -[2023-10-11 00:24:36,801][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000087904_90013696.pth -[2023-10-11 00:24:39,572][98560] Updated weights for policy 1, policy_version 88902 (0.0007) -[2023-10-11 00:24:39,932][98560] Updated weights for policy 1, policy_version 88912 (0.0008) -[2023-10-11 00:24:40,306][98560] Updated weights for policy 1, policy_version 88922 (0.0008) -[2023-10-11 00:24:40,556][97672] Fps is (10 sec: 16384.4, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 182714368. Throughput: 0: 1707.4, 1: 1700.6. Samples: 45681656. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-11 00:24:40,556][97672] Avg episode reward: [(0, '-0.780'), (1, '22.660')] -[2023-10-11 00:24:40,594][98559] Updated weights for policy 0, policy_version 89510 (0.0008) -[2023-10-11 00:24:40,956][98559] Updated weights for policy 0, policy_version 89520 (0.0011) -[2023-10-11 00:24:41,328][98559] Updated weights for policy 0, policy_version 89530 (0.0008) -[2023-10-11 00:24:44,287][98560] Updated weights for policy 1, policy_version 88932 (0.0007) -[2023-10-11 00:24:44,653][98560] Updated weights for policy 1, policy_version 88942 (0.0010) -[2023-10-11 00:24:45,016][98560] Updated weights for policy 1, policy_version 88952 (0.0008) -[2023-10-11 00:24:45,057][98559] Updated weights for policy 0, policy_version 89540 (0.0008) -[2023-10-11 00:24:45,432][98559] Updated weights for policy 0, policy_version 89550 (0.0009) -[2023-10-11 00:24:45,556][97672] Fps is (10 sec: 16384.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 182779904. Throughput: 0: 1713.2, 1: 1702.5. Samples: 45703012. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-11 00:24:45,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.640')] -[2023-10-11 00:24:45,799][98559] Updated weights for policy 0, policy_version 89560 (0.0008) -[2023-10-11 00:24:48,955][98560] Updated weights for policy 1, policy_version 88962 (0.0009) -[2023-10-11 00:24:49,322][98560] Updated weights for policy 1, policy_version 88972 (0.0008) -[2023-10-11 00:24:49,682][98560] Updated weights for policy 1, policy_version 88982 (0.0008) -[2023-10-11 00:24:49,897][98559] Updated weights for policy 0, policy_version 89570 (0.0009) -[2023-10-11 00:24:50,051][98560] Updated weights for policy 1, policy_version 88992 (0.0010) -[2023-10-11 00:24:50,268][98559] Updated weights for policy 0, policy_version 89580 (0.0008) -[2023-10-11 00:24:50,556][97672] Fps is (10 sec: 13106.7, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 182845440. Throughput: 0: 1700.8, 1: 1691.2. Samples: 45722748. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-11 00:24:50,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.640')] -[2023-10-11 00:24:50,626][98559] Updated weights for policy 0, policy_version 89590 (0.0010) -[2023-10-11 00:24:50,982][98559] Updated weights for policy 0, policy_version 89600 (0.0010) -[2023-10-11 00:24:54,074][98560] Updated weights for policy 1, policy_version 89002 (0.0009) -[2023-10-11 00:24:54,433][98560] Updated weights for policy 1, policy_version 89012 (0.0009) -[2023-10-11 00:24:54,798][98560] Updated weights for policy 1, policy_version 89022 (0.0009) -[2023-10-11 00:24:55,140][98559] Updated weights for policy 0, policy_version 89610 (0.0010) -[2023-10-11 00:24:55,500][98559] Updated weights for policy 0, policy_version 89620 (0.0008) -[2023-10-11 00:24:55,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 182910976. Throughput: 0: 1710.2, 1: 1709.2. Samples: 45733242. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-11 00:24:55,558][97672] Avg episode reward: [(0, '-0.780'), (1, '22.700')] -[2023-10-11 00:24:55,861][98559] Updated weights for policy 0, policy_version 89630 (0.0007) -[2023-10-11 00:24:58,799][98560] Updated weights for policy 1, policy_version 89032 (0.0008) -[2023-10-11 00:24:59,165][98560] Updated weights for policy 1, policy_version 89042 (0.0007) -[2023-10-11 00:24:59,539][98560] Updated weights for policy 1, policy_version 89052 (0.0008) -[2023-10-11 00:24:59,877][98559] Updated weights for policy 0, policy_version 89640 (0.0009) -[2023-10-11 00:25:00,241][98559] Updated weights for policy 0, policy_version 89650 (0.0007) -[2023-10-11 00:25:00,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 182976512. Throughput: 0: 1715.1, 1: 1710.2. Samples: 45754410. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-11 00:25:00,556][97672] Avg episode reward: [(0, '-0.780'), (1, '22.720')] -[2023-10-11 00:25:00,599][98559] Updated weights for policy 0, policy_version 89660 (0.0010) -[2023-10-11 00:25:03,480][98560] Updated weights for policy 1, policy_version 89062 (0.0008) -[2023-10-11 00:25:03,846][98560] Updated weights for policy 1, policy_version 89072 (0.0007) -[2023-10-11 00:25:04,213][98560] Updated weights for policy 1, policy_version 89082 (0.0007) -[2023-10-11 00:25:04,550][98559] Updated weights for policy 0, policy_version 89670 (0.0009) -[2023-10-11 00:25:04,911][98559] Updated weights for policy 0, policy_version 89680 (0.0007) -[2023-10-11 00:25:05,280][98559] Updated weights for policy 0, policy_version 89690 (0.0008) -[2023-10-11 00:25:05,556][97672] Fps is (10 sec: 16384.6, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 183074816. Throughput: 0: 1692.9, 1: 1692.6. Samples: 45773628. Policy #0 lag: (min: 18.0, avg: 26.0, max: 50.0) -[2023-10-11 00:25:05,556][97672] Avg episode reward: [(0, '-0.780'), (1, '22.780')] -[2023-10-11 00:25:08,302][98560] Updated weights for policy 1, policy_version 89092 (0.0008) -[2023-10-11 00:25:08,667][98560] Updated weights for policy 1, policy_version 89102 (0.0007) -[2023-10-11 00:25:09,040][98560] Updated weights for policy 1, policy_version 89112 (0.0007) -[2023-10-11 00:25:09,173][98559] Updated weights for policy 0, policy_version 89700 (0.0007) -[2023-10-11 00:25:09,533][98559] Updated weights for policy 0, policy_version 89710 (0.0008) -[2023-10-11 00:25:09,902][98559] Updated weights for policy 0, policy_version 89720 (0.0009) -[2023-10-11 00:25:10,556][97672] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 183140352. Throughput: 0: 1721.0, 1: 1722.8. Samples: 45785514. Policy #0 lag: (min: 18.0, avg: 26.0, max: 50.0) -[2023-10-11 00:25:10,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.740')] -[2023-10-11 00:25:13,132][98560] Updated weights for policy 1, policy_version 89122 (0.0007) -[2023-10-11 00:25:13,500][98560] Updated weights for policy 1, policy_version 89132 (0.0007) -[2023-10-11 00:25:13,843][98559] Updated weights for policy 0, policy_version 89730 (0.0008) -[2023-10-11 00:25:13,860][98560] Updated weights for policy 1, policy_version 89142 (0.0007) -[2023-10-11 00:25:14,206][98559] Updated weights for policy 0, policy_version 89740 (0.0008) -[2023-10-11 00:25:14,219][98560] Updated weights for policy 1, policy_version 89152 (0.0007) -[2023-10-11 00:25:14,568][98559] Updated weights for policy 0, policy_version 89750 (0.0008) -[2023-10-11 00:25:14,940][98559] Updated weights for policy 0, policy_version 89760 (0.0007) -[2023-10-11 00:25:15,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 183205888. Throughput: 0: 1708.5, 1: 1698.8. Samples: 45804936. Policy #0 lag: (min: 18.0, avg: 26.0, max: 50.0) -[2023-10-11 00:25:15,557][97672] Avg episode reward: [(0, '-0.800'), (1, '22.680')] -[2023-10-11 00:25:18,340][98560] Updated weights for policy 1, policy_version 89162 (0.0008) -[2023-10-11 00:25:18,706][98560] Updated weights for policy 1, policy_version 89172 (0.0008) -[2023-10-11 00:25:18,908][98559] Updated weights for policy 0, policy_version 89770 (0.0009) -[2023-10-11 00:25:19,073][98560] Updated weights for policy 1, policy_version 89182 (0.0009) -[2023-10-11 00:25:19,275][98559] Updated weights for policy 0, policy_version 89780 (0.0009) -[2023-10-11 00:25:19,643][98559] Updated weights for policy 0, policy_version 89790 (0.0008) -[2023-10-11 00:25:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 183271424. Throughput: 0: 1693.8, 1: 1684.7. Samples: 45824488. Policy #0 lag: (min: 18.0, avg: 26.0, max: 50.0) -[2023-10-11 00:25:20,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.620')] -[2023-10-11 00:25:23,100][98560] Updated weights for policy 1, policy_version 89192 (0.0009) -[2023-10-11 00:25:23,471][98560] Updated weights for policy 1, policy_version 89202 (0.0008) -[2023-10-11 00:25:23,617][98559] Updated weights for policy 0, policy_version 89800 (0.0008) -[2023-10-11 00:25:23,832][98560] Updated weights for policy 1, policy_version 89212 (0.0010) -[2023-10-11 00:25:23,971][98559] Updated weights for policy 0, policy_version 89810 (0.0009) -[2023-10-11 00:25:24,330][98559] Updated weights for policy 0, policy_version 89820 (0.0009) -[2023-10-11 00:25:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 183336960. Throughput: 0: 1723.7, 1: 1717.5. Samples: 45836508. Policy #0 lag: (min: 18.0, avg: 26.0, max: 50.0) -[2023-10-11 00:25:25,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.560')] -[2023-10-11 00:25:27,798][98560] Updated weights for policy 1, policy_version 89222 (0.0009) -[2023-10-11 00:25:28,160][98560] Updated weights for policy 1, policy_version 89232 (0.0009) -[2023-10-11 00:25:28,476][98559] Updated weights for policy 0, policy_version 89830 (0.0009) -[2023-10-11 00:25:28,535][98560] Updated weights for policy 1, policy_version 89242 (0.0008) -[2023-10-11 00:25:28,849][98559] Updated weights for policy 0, policy_version 89840 (0.0007) -[2023-10-11 00:25:29,222][98559] Updated weights for policy 0, policy_version 89850 (0.0008) -[2023-10-11 00:25:30,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 183402496. Throughput: 0: 1689.6, 1: 1684.3. Samples: 45854838. Policy #0 lag: (min: 18.0, avg: 26.0, max: 50.0) -[2023-10-11 00:25:30,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.600')] -[2023-10-11 00:25:32,631][98560] Updated weights for policy 1, policy_version 89252 (0.0007) -[2023-10-11 00:25:32,994][98560] Updated weights for policy 1, policy_version 89262 (0.0008) -[2023-10-11 00:25:33,191][98559] Updated weights for policy 0, policy_version 89860 (0.0010) -[2023-10-11 00:25:33,367][98560] Updated weights for policy 1, policy_version 89272 (0.0007) -[2023-10-11 00:25:33,556][98559] Updated weights for policy 0, policy_version 89870 (0.0009) -[2023-10-11 00:25:33,925][98559] Updated weights for policy 0, policy_version 89880 (0.0007) -[2023-10-11 00:25:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 183468032. Throughput: 0: 1699.7, 1: 1695.1. Samples: 45875516. Policy #0 lag: (min: 18.0, avg: 26.0, max: 50.0) -[2023-10-11 00:25:35,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.620')] -[2023-10-11 00:25:37,205][98560] Updated weights for policy 1, policy_version 89282 (0.0007) -[2023-10-11 00:25:37,570][98560] Updated weights for policy 1, policy_version 89292 (0.0008) -[2023-10-11 00:25:37,902][98559] Updated weights for policy 0, policy_version 89890 (0.0007) -[2023-10-11 00:25:37,940][98560] Updated weights for policy 1, policy_version 89302 (0.0009) -[2023-10-11 00:25:38,266][98559] Updated weights for policy 0, policy_version 89900 (0.0008) -[2023-10-11 00:25:38,299][98560] Updated weights for policy 1, policy_version 89312 (0.0008) -[2023-10-11 00:25:38,628][98559] Updated weights for policy 0, policy_version 89910 (0.0007) -[2023-10-11 00:25:39,000][98559] Updated weights for policy 0, policy_version 89920 (0.0008) -[2023-10-11 00:25:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 183533568. Throughput: 0: 1709.2, 1: 1694.7. Samples: 45886414. Policy #0 lag: (min: 18.0, avg: 26.0, max: 50.0) -[2023-10-11 00:25:40,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.540')] -[2023-10-11 00:25:42,301][98560] Updated weights for policy 1, policy_version 89322 (0.0008) -[2023-10-11 00:25:42,664][98560] Updated weights for policy 1, policy_version 89332 (0.0007) -[2023-10-11 00:25:43,023][98559] Updated weights for policy 0, policy_version 89930 (0.0008) -[2023-10-11 00:25:43,032][98560] Updated weights for policy 1, policy_version 89342 (0.0010) -[2023-10-11 00:25:43,396][98559] Updated weights for policy 0, policy_version 89940 (0.0009) -[2023-10-11 00:25:43,757][98559] Updated weights for policy 0, policy_version 89950 (0.0008) -[2023-10-11 00:25:45,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 183599104. Throughput: 0: 1691.2, 1: 1680.1. Samples: 45906120. Policy #0 lag: (min: 18.0, avg: 26.0, max: 50.0) -[2023-10-11 00:25:45,557][97672] Avg episode reward: [(0, '-0.780'), (1, '22.500')] -[2023-10-11 00:25:47,043][98560] Updated weights for policy 1, policy_version 89352 (0.0010) -[2023-10-11 00:25:47,413][98560] Updated weights for policy 1, policy_version 89362 (0.0010) -[2023-10-11 00:25:47,785][98560] Updated weights for policy 1, policy_version 89372 (0.0007) -[2023-10-11 00:25:47,847][98559] Updated weights for policy 0, policy_version 89960 (0.0008) -[2023-10-11 00:25:48,213][98559] Updated weights for policy 0, policy_version 89970 (0.0008) -[2023-10-11 00:25:48,583][98559] Updated weights for policy 0, policy_version 89980 (0.0007) -[2023-10-11 00:25:50,556][97672] Fps is (10 sec: 13106.7, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 183664640. Throughput: 0: 1710.5, 1: 1703.3. Samples: 45927248. Policy #0 lag: (min: 18.0, avg: 26.0, max: 50.0) -[2023-10-11 00:25:50,558][97672] Avg episode reward: [(0, '-0.780'), (1, '22.480')] -[2023-10-11 00:25:51,685][98560] Updated weights for policy 1, policy_version 89382 (0.0010) -[2023-10-11 00:25:52,050][98560] Updated weights for policy 1, policy_version 89392 (0.0008) -[2023-10-11 00:25:52,414][98560] Updated weights for policy 1, policy_version 89402 (0.0008) -[2023-10-11 00:25:52,469][98559] Updated weights for policy 0, policy_version 89990 (0.0007) -[2023-10-11 00:25:52,831][98559] Updated weights for policy 0, policy_version 90000 (0.0009) -[2023-10-11 00:25:53,205][98559] Updated weights for policy 0, policy_version 90010 (0.0008) -[2023-10-11 00:25:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 183730176. Throughput: 0: 1687.3, 1: 1669.9. Samples: 45936588. Policy #0 lag: (min: 18.0, avg: 26.0, max: 50.0) -[2023-10-11 00:25:55,557][97672] Avg episode reward: [(0, '-0.760'), (1, '22.480')] -[2023-10-11 00:25:56,345][98560] Updated weights for policy 1, policy_version 89412 (0.0008) -[2023-10-11 00:25:56,707][98560] Updated weights for policy 1, policy_version 89422 (0.0009) -[2023-10-11 00:25:57,082][98560] Updated weights for policy 1, policy_version 89432 (0.0009) -[2023-10-11 00:25:57,183][98559] Updated weights for policy 0, policy_version 90020 (0.0009) -[2023-10-11 00:25:57,544][98559] Updated weights for policy 0, policy_version 90030 (0.0008) -[2023-10-11 00:25:57,908][98559] Updated weights for policy 0, policy_version 90040 (0.0010) -[2023-10-11 00:26:00,556][97672] Fps is (10 sec: 13107.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 183795712. Throughput: 0: 1697.4, 1: 1695.1. Samples: 45957598. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-10-11 00:26:00,556][97672] Avg episode reward: [(0, '-0.760'), (1, '22.480')] -[2023-10-11 00:26:01,010][98560] Updated weights for policy 1, policy_version 89442 (0.0008) -[2023-10-11 00:26:01,386][98560] Updated weights for policy 1, policy_version 89452 (0.0008) -[2023-10-11 00:26:01,751][98560] Updated weights for policy 1, policy_version 89462 (0.0009) -[2023-10-11 00:26:01,952][98559] Updated weights for policy 0, policy_version 90050 (0.0010) -[2023-10-11 00:26:02,117][98560] Updated weights for policy 1, policy_version 89472 (0.0008) -[2023-10-11 00:26:02,317][98559] Updated weights for policy 0, policy_version 90060 (0.0007) -[2023-10-11 00:26:02,691][98559] Updated weights for policy 0, policy_version 90070 (0.0007) -[2023-10-11 00:26:03,048][98559] Updated weights for policy 0, policy_version 90080 (0.0009) -[2023-10-11 00:26:05,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 183861248. Throughput: 0: 1716.9, 1: 1712.2. Samples: 45978800. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-10-11 00:26:05,557][97672] Avg episode reward: [(0, '-0.760'), (1, '22.500')] -[2023-10-11 00:26:06,218][98560] Updated weights for policy 1, policy_version 89482 (0.0009) -[2023-10-11 00:26:06,578][98560] Updated weights for policy 1, policy_version 89492 (0.0008) -[2023-10-11 00:26:06,857][98559] Updated weights for policy 0, policy_version 90090 (0.0008) -[2023-10-11 00:26:06,942][98560] Updated weights for policy 1, policy_version 89502 (0.0007) -[2023-10-11 00:26:07,223][98559] Updated weights for policy 0, policy_version 90100 (0.0009) -[2023-10-11 00:26:07,592][98559] Updated weights for policy 0, policy_version 90110 (0.0010) -[2023-10-11 00:26:10,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 183926784. Throughput: 0: 1691.7, 1: 1679.4. Samples: 45988206. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-10-11 00:26:10,557][97672] Avg episode reward: [(0, '-0.760'), (1, '22.500')] -[2023-10-11 00:26:10,957][98560] Updated weights for policy 1, policy_version 89512 (0.0009) -[2023-10-11 00:26:11,321][98560] Updated weights for policy 1, policy_version 89522 (0.0009) -[2023-10-11 00:26:11,684][98560] Updated weights for policy 1, policy_version 89532 (0.0010) -[2023-10-11 00:26:11,746][98559] Updated weights for policy 0, policy_version 90120 (0.0010) -[2023-10-11 00:26:12,113][98559] Updated weights for policy 0, policy_version 90130 (0.0009) -[2023-10-11 00:26:12,488][98559] Updated weights for policy 0, policy_version 90140 (0.0009) -[2023-10-11 00:26:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 183992320. Throughput: 0: 1715.4, 1: 1715.6. Samples: 46009236. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-10-11 00:26:15,556][97672] Avg episode reward: [(0, '-0.760'), (1, '22.440')] -[2023-10-11 00:26:15,708][98560] Updated weights for policy 1, policy_version 89542 (0.0010) -[2023-10-11 00:26:16,067][98560] Updated weights for policy 1, policy_version 89552 (0.0009) -[2023-10-11 00:26:16,356][98559] Updated weights for policy 0, policy_version 90150 (0.0007) -[2023-10-11 00:26:16,427][98560] Updated weights for policy 1, policy_version 89562 (0.0009) -[2023-10-11 00:26:16,731][98559] Updated weights for policy 0, policy_version 90160 (0.0008) -[2023-10-11 00:26:17,097][98559] Updated weights for policy 0, policy_version 90170 (0.0008) -[2023-10-11 00:26:20,304][98560] Updated weights for policy 1, policy_version 89572 (0.0008) -[2023-10-11 00:26:20,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 184057856. Throughput: 0: 1718.6, 1: 1724.9. Samples: 46030476. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-10-11 00:26:20,557][97672] Avg episode reward: [(0, '-0.760'), (1, '22.440')] -[2023-10-11 00:26:20,672][98560] Updated weights for policy 1, policy_version 89582 (0.0009) -[2023-10-11 00:26:20,995][98559] Updated weights for policy 0, policy_version 90180 (0.0009) -[2023-10-11 00:26:21,048][98560] Updated weights for policy 1, policy_version 89592 (0.0009) -[2023-10-11 00:26:21,366][98559] Updated weights for policy 0, policy_version 90190 (0.0008) -[2023-10-11 00:26:21,733][98559] Updated weights for policy 0, policy_version 90200 (0.0008) -[2023-10-11 00:26:25,029][98560] Updated weights for policy 1, policy_version 89602 (0.0008) -[2023-10-11 00:26:25,398][98560] Updated weights for policy 1, policy_version 89612 (0.0008) -[2023-10-11 00:26:25,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 184123392. Throughput: 0: 1704.9, 1: 1707.2. Samples: 46039956. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-10-11 00:26:25,556][97672] Avg episode reward: [(0, '-0.760'), (1, '22.460')] -[2023-10-11 00:26:25,759][98560] Updated weights for policy 1, policy_version 89622 (0.0007) -[2023-10-11 00:26:25,800][98559] Updated weights for policy 0, policy_version 90210 (0.0008) -[2023-10-11 00:26:26,129][98560] Updated weights for policy 1, policy_version 89632 (0.0008) -[2023-10-11 00:26:26,154][98559] Updated weights for policy 0, policy_version 90220 (0.0008) -[2023-10-11 00:26:26,515][98559] Updated weights for policy 0, policy_version 90230 (0.0008) -[2023-10-11 00:26:26,883][98559] Updated weights for policy 0, policy_version 90240 (0.0009) -[2023-10-11 00:26:30,020][98560] Updated weights for policy 1, policy_version 89642 (0.0009) -[2023-10-11 00:26:30,392][98560] Updated weights for policy 1, policy_version 89652 (0.0009) -[2023-10-11 00:26:30,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 184188928. Throughput: 0: 1726.3, 1: 1725.3. Samples: 46061442. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-10-11 00:26:30,557][97672] Avg episode reward: [(0, '-0.760'), (1, '22.480')] -[2023-10-11 00:26:30,741][98559] Updated weights for policy 0, policy_version 90250 (0.0009) -[2023-10-11 00:26:30,761][98560] Updated weights for policy 1, policy_version 89662 (0.0009) -[2023-10-11 00:26:31,111][98559] Updated weights for policy 0, policy_version 90260 (0.0010) -[2023-10-11 00:26:31,471][98559] Updated weights for policy 0, policy_version 90270 (0.0010) -[2023-10-11 00:26:34,770][98560] Updated weights for policy 1, policy_version 89672 (0.0011) -[2023-10-11 00:26:35,140][98560] Updated weights for policy 1, policy_version 89682 (0.0009) -[2023-10-11 00:26:35,499][98560] Updated weights for policy 1, policy_version 89692 (0.0010) -[2023-10-11 00:26:35,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 184254464. Throughput: 0: 1725.5, 1: 1714.5. Samples: 46082048. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-10-11 00:26:35,557][97672] Avg episode reward: [(0, '-0.760'), (1, '22.580')] -[2023-10-11 00:26:35,575][98559] Updated weights for policy 0, policy_version 90280 (0.0007) -[2023-10-11 00:26:35,650][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000089696_91848704.pth... -[2023-10-11 00:26:35,690][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000088096_90210304.pth -[2023-10-11 00:26:35,940][98559] Updated weights for policy 0, policy_version 90290 (0.0007) -[2023-10-11 00:26:36,308][98559] Updated weights for policy 0, policy_version 90300 (0.0007) -[2023-10-11 00:26:36,454][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000090304_92471296.pth... -[2023-10-11 00:26:36,492][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000088704_90832896.pth -[2023-10-11 00:26:39,594][98560] Updated weights for policy 1, policy_version 89702 (0.0008) -[2023-10-11 00:26:39,959][98560] Updated weights for policy 1, policy_version 89712 (0.0007) -[2023-10-11 00:26:40,223][98559] Updated weights for policy 0, policy_version 90310 (0.0007) -[2023-10-11 00:26:40,324][98560] Updated weights for policy 1, policy_version 89722 (0.0008) -[2023-10-11 00:26:40,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 184352768. Throughput: 0: 1726.7, 1: 1721.1. Samples: 46091738. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-10-11 00:26:40,556][97672] Avg episode reward: [(0, '-0.760'), (1, '22.480')] -[2023-10-11 00:26:40,595][98559] Updated weights for policy 0, policy_version 90320 (0.0007) -[2023-10-11 00:26:40,954][98559] Updated weights for policy 0, policy_version 90330 (0.0007) -[2023-10-11 00:26:44,400][98560] Updated weights for policy 1, policy_version 89732 (0.0008) -[2023-10-11 00:26:44,767][98560] Updated weights for policy 1, policy_version 89742 (0.0008) -[2023-10-11 00:26:45,033][98559] Updated weights for policy 0, policy_version 90340 (0.0007) -[2023-10-11 00:26:45,131][98560] Updated weights for policy 1, policy_version 89752 (0.0009) -[2023-10-11 00:26:45,393][98559] Updated weights for policy 0, policy_version 90350 (0.0007) -[2023-10-11 00:26:45,556][97672] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 184418304. Throughput: 0: 1734.7, 1: 1720.5. Samples: 46113082. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-10-11 00:26:45,557][97672] Avg episode reward: [(0, '-0.760'), (1, '22.520')] -[2023-10-11 00:26:45,772][98559] Updated weights for policy 0, policy_version 90360 (0.0009) -[2023-10-11 00:26:49,234][98560] Updated weights for policy 1, policy_version 89762 (0.0009) -[2023-10-11 00:26:49,605][98560] Updated weights for policy 1, policy_version 89772 (0.0009) -[2023-10-11 00:26:49,635][98559] Updated weights for policy 0, policy_version 90370 (0.0008) -[2023-10-11 00:26:49,970][98560] Updated weights for policy 1, policy_version 89782 (0.0009) -[2023-10-11 00:26:50,003][98559] Updated weights for policy 0, policy_version 90380 (0.0009) -[2023-10-11 00:26:50,331][98560] Updated weights for policy 1, policy_version 89792 (0.0009) -[2023-10-11 00:26:50,378][98559] Updated weights for policy 0, policy_version 90390 (0.0009) -[2023-10-11 00:26:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 184483840. Throughput: 0: 1716.9, 1: 1706.6. Samples: 46132858. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-10-11 00:26:50,556][97672] Avg episode reward: [(0, '-0.760'), (1, '22.500')] -[2023-10-11 00:26:50,735][98559] Updated weights for policy 0, policy_version 90400 (0.0009) -[2023-10-11 00:26:54,313][98560] Updated weights for policy 1, policy_version 89802 (0.0008) -[2023-10-11 00:26:54,675][98560] Updated weights for policy 1, policy_version 89812 (0.0008) -[2023-10-11 00:26:54,755][98559] Updated weights for policy 0, policy_version 90410 (0.0008) -[2023-10-11 00:26:55,037][98560] Updated weights for policy 1, policy_version 89822 (0.0008) -[2023-10-11 00:26:55,124][98559] Updated weights for policy 0, policy_version 90420 (0.0009) -[2023-10-11 00:26:55,474][98559] Updated weights for policy 0, policy_version 90430 (0.0011) -[2023-10-11 00:26:55,556][97672] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 184582144. Throughput: 0: 1729.9, 1: 1725.0. Samples: 46143676. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-11 00:26:55,556][97672] Avg episode reward: [(0, '-0.760'), (1, '22.500')] -[2023-10-11 00:26:59,064][98560] Updated weights for policy 1, policy_version 89832 (0.0007) -[2023-10-11 00:26:59,436][98560] Updated weights for policy 1, policy_version 89842 (0.0007) -[2023-10-11 00:26:59,601][98559] Updated weights for policy 0, policy_version 90440 (0.0010) -[2023-10-11 00:26:59,803][98560] Updated weights for policy 1, policy_version 89852 (0.0007) -[2023-10-11 00:26:59,965][98559] Updated weights for policy 0, policy_version 90450 (0.0009) -[2023-10-11 00:27:00,331][98559] Updated weights for policy 0, policy_version 90460 (0.0009) -[2023-10-11 00:27:00,556][97672] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 184647680. Throughput: 0: 1728.9, 1: 1721.4. Samples: 46164498. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-11 00:27:00,557][97672] Avg episode reward: [(0, '-0.760'), (1, '22.480')] -[2023-10-11 00:27:03,780][98560] Updated weights for policy 1, policy_version 89862 (0.0008) -[2023-10-11 00:27:04,143][98560] Updated weights for policy 1, policy_version 89872 (0.0009) -[2023-10-11 00:27:04,215][98559] Updated weights for policy 0, policy_version 90470 (0.0009) -[2023-10-11 00:27:04,506][98560] Updated weights for policy 1, policy_version 89882 (0.0009) -[2023-10-11 00:27:04,576][98559] Updated weights for policy 0, policy_version 90480 (0.0010) -[2023-10-11 00:27:04,951][98559] Updated weights for policy 0, policy_version 90490 (0.0008) -[2023-10-11 00:27:05,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 184713216. Throughput: 0: 1704.0, 1: 1688.3. Samples: 46183128. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-11 00:27:05,557][97672] Avg episode reward: [(0, '-0.760'), (1, '22.480')] -[2023-10-11 00:27:08,620][98560] Updated weights for policy 1, policy_version 89892 (0.0008) -[2023-10-11 00:27:08,987][98559] Updated weights for policy 0, policy_version 90500 (0.0008) -[2023-10-11 00:27:08,992][98560] Updated weights for policy 1, policy_version 89902 (0.0009) -[2023-10-11 00:27:09,350][98560] Updated weights for policy 1, policy_version 89912 (0.0007) -[2023-10-11 00:27:09,355][98559] Updated weights for policy 0, policy_version 90510 (0.0010) -[2023-10-11 00:27:09,712][98559] Updated weights for policy 0, policy_version 90520 (0.0009) -[2023-10-11 00:27:10,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 184778752. Throughput: 0: 1728.8, 1: 1714.3. Samples: 46194898. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-11 00:27:10,557][97672] Avg episode reward: [(0, '-0.760'), (1, '22.520')] -[2023-10-11 00:27:13,512][98560] Updated weights for policy 1, policy_version 89922 (0.0008) -[2023-10-11 00:27:13,745][98559] Updated weights for policy 0, policy_version 90530 (0.0008) -[2023-10-11 00:27:13,889][98560] Updated weights for policy 1, policy_version 89932 (0.0009) -[2023-10-11 00:27:14,104][98559] Updated weights for policy 0, policy_version 90540 (0.0010) -[2023-10-11 00:27:14,260][98560] Updated weights for policy 1, policy_version 89942 (0.0009) -[2023-10-11 00:27:14,473][98559] Updated weights for policy 0, policy_version 90550 (0.0008) -[2023-10-11 00:27:14,624][98560] Updated weights for policy 1, policy_version 89952 (0.0009) -[2023-10-11 00:27:14,830][98559] Updated weights for policy 0, policy_version 90560 (0.0009) -[2023-10-11 00:27:15,556][97672] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 184844288. Throughput: 0: 1704.6, 1: 1699.5. Samples: 46214626. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-11 00:27:15,557][97672] Avg episode reward: [(0, '-0.680'), (1, '22.480')] -[2023-10-11 00:27:18,531][98560] Updated weights for policy 1, policy_version 89962 (0.0007) -[2023-10-11 00:27:18,646][98559] Updated weights for policy 0, policy_version 90570 (0.0007) -[2023-10-11 00:27:18,901][98560] Updated weights for policy 1, policy_version 89972 (0.0007) -[2023-10-11 00:27:19,014][98559] Updated weights for policy 0, policy_version 90580 (0.0007) -[2023-10-11 00:27:19,265][98560] Updated weights for policy 1, policy_version 89982 (0.0008) -[2023-10-11 00:27:19,383][98559] Updated weights for policy 0, policy_version 90590 (0.0007) -[2023-10-11 00:27:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 184909824. Throughput: 0: 1695.7, 1: 1682.5. Samples: 46234066. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-11 00:27:20,556][97672] Avg episode reward: [(0, '-0.680'), (1, '22.400')] -[2023-10-11 00:27:23,327][98560] Updated weights for policy 1, policy_version 89992 (0.0008) -[2023-10-11 00:27:23,363][98559] Updated weights for policy 0, policy_version 90600 (0.0008) -[2023-10-11 00:27:23,704][98560] Updated weights for policy 1, policy_version 90002 (0.0007) -[2023-10-11 00:27:23,726][98559] Updated weights for policy 0, policy_version 90610 (0.0007) -[2023-10-11 00:27:24,076][98560] Updated weights for policy 1, policy_version 90012 (0.0011) -[2023-10-11 00:27:24,102][98559] Updated weights for policy 0, policy_version 90620 (0.0009) -[2023-10-11 00:27:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 184975360. Throughput: 0: 1713.3, 1: 1704.4. Samples: 46245534. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-11 00:27:25,557][97672] Avg episode reward: [(0, '-0.680'), (1, '22.480')] -[2023-10-11 00:27:27,960][98560] Updated weights for policy 1, policy_version 90022 (0.0009) -[2023-10-11 00:27:28,304][98559] Updated weights for policy 0, policy_version 90630 (0.0009) -[2023-10-11 00:27:28,326][98560] Updated weights for policy 1, policy_version 90032 (0.0008) -[2023-10-11 00:27:28,670][98559] Updated weights for policy 0, policy_version 90640 (0.0008) -[2023-10-11 00:27:28,697][98560] Updated weights for policy 1, policy_version 90042 (0.0008) -[2023-10-11 00:27:29,031][98559] Updated weights for policy 0, policy_version 90650 (0.0009) -[2023-10-11 00:27:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 185040896. Throughput: 0: 1679.1, 1: 1683.3. Samples: 46264392. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-11 00:27:30,557][97672] Avg episode reward: [(0, '-0.680'), (1, '22.520')] -[2023-10-11 00:27:32,894][98560] Updated weights for policy 1, policy_version 90052 (0.0009) -[2023-10-11 00:27:33,062][98559] Updated weights for policy 0, policy_version 90660 (0.0009) -[2023-10-11 00:27:33,260][98560] Updated weights for policy 1, policy_version 90062 (0.0008) -[2023-10-11 00:27:33,426][98559] Updated weights for policy 0, policy_version 90670 (0.0008) -[2023-10-11 00:27:33,627][98560] Updated weights for policy 1, policy_version 90072 (0.0008) -[2023-10-11 00:27:33,787][98559] Updated weights for policy 0, policy_version 90680 (0.0007) -[2023-10-11 00:27:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 185106432. Throughput: 0: 1693.5, 1: 1689.5. Samples: 46285090. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-11 00:27:35,557][97672] Avg episode reward: [(0, '-0.680'), (1, '22.560')] -[2023-10-11 00:27:37,610][98560] Updated weights for policy 1, policy_version 90082 (0.0008) -[2023-10-11 00:27:37,805][98559] Updated weights for policy 0, policy_version 90690 (0.0008) -[2023-10-11 00:27:37,985][98560] Updated weights for policy 1, policy_version 90092 (0.0009) -[2023-10-11 00:27:38,165][98559] Updated weights for policy 0, policy_version 90700 (0.0010) -[2023-10-11 00:27:38,352][98560] Updated weights for policy 1, policy_version 90102 (0.0009) -[2023-10-11 00:27:38,533][98559] Updated weights for policy 0, policy_version 90710 (0.0008) -[2023-10-11 00:27:38,707][98560] Updated weights for policy 1, policy_version 90112 (0.0007) -[2023-10-11 00:27:38,893][98559] Updated weights for policy 0, policy_version 90720 (0.0009) -[2023-10-11 00:27:40,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13653.2, 300 sec: 13662.6). Total num frames: 185171968. Throughput: 0: 1689.7, 1: 1694.6. Samples: 46295970. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-11 00:27:40,558][97672] Avg episode reward: [(0, '-0.680'), (1, '22.640')] -[2023-10-11 00:27:42,822][98560] Updated weights for policy 1, policy_version 90122 (0.0008) -[2023-10-11 00:27:43,035][98559] Updated weights for policy 0, policy_version 90730 (0.0010) -[2023-10-11 00:27:43,195][98560] Updated weights for policy 1, policy_version 90132 (0.0009) -[2023-10-11 00:27:43,413][98559] Updated weights for policy 0, policy_version 90740 (0.0009) -[2023-10-11 00:27:43,555][98560] Updated weights for policy 1, policy_version 90142 (0.0009) -[2023-10-11 00:27:43,771][98559] Updated weights for policy 0, policy_version 90750 (0.0008) -[2023-10-11 00:27:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 185237504. Throughput: 0: 1675.0, 1: 1667.0. Samples: 46314890. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-11 00:27:45,557][97672] Avg episode reward: [(0, '-0.680'), (1, '22.720')] -[2023-10-11 00:27:47,424][98560] Updated weights for policy 1, policy_version 90152 (0.0007) -[2023-10-11 00:27:47,793][98560] Updated weights for policy 1, policy_version 90162 (0.0009) -[2023-10-11 00:27:47,817][98559] Updated weights for policy 0, policy_version 90760 (0.0009) -[2023-10-11 00:27:48,168][98560] Updated weights for policy 1, policy_version 90172 (0.0009) -[2023-10-11 00:27:48,171][98559] Updated weights for policy 0, policy_version 90770 (0.0008) -[2023-10-11 00:27:48,539][98559] Updated weights for policy 0, policy_version 90780 (0.0009) -[2023-10-11 00:27:50,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 185303040. Throughput: 0: 1700.8, 1: 1694.6. Samples: 46335922. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-11 00:27:50,556][97672] Avg episode reward: [(0, '-0.680'), (1, '22.760')] -[2023-10-11 00:27:52,129][98560] Updated weights for policy 1, policy_version 90182 (0.0009) -[2023-10-11 00:27:52,495][98560] Updated weights for policy 1, policy_version 90192 (0.0008) -[2023-10-11 00:27:52,636][98559] Updated weights for policy 0, policy_version 90790 (0.0009) -[2023-10-11 00:27:52,864][98560] Updated weights for policy 1, policy_version 90202 (0.0007) -[2023-10-11 00:27:53,013][98559] Updated weights for policy 0, policy_version 90800 (0.0009) -[2023-10-11 00:27:53,369][98559] Updated weights for policy 0, policy_version 90810 (0.0008) -[2023-10-11 00:27:55,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 185368576. Throughput: 0: 1675.1, 1: 1680.0. Samples: 46345876. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:27:55,557][97672] Avg episode reward: [(0, '-0.680'), (1, '22.760')] -[2023-10-11 00:27:56,788][98560] Updated weights for policy 1, policy_version 90212 (0.0008) -[2023-10-11 00:27:57,157][98560] Updated weights for policy 1, policy_version 90222 (0.0009) -[2023-10-11 00:27:57,254][98559] Updated weights for policy 0, policy_version 90820 (0.0009) -[2023-10-11 00:27:57,526][98560] Updated weights for policy 1, policy_version 90232 (0.0007) -[2023-10-11 00:27:57,625][98559] Updated weights for policy 0, policy_version 90830 (0.0008) -[2023-10-11 00:27:57,986][98559] Updated weights for policy 0, policy_version 90840 (0.0010) -[2023-10-11 00:28:00,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 13662.6). Total num frames: 185434112. Throughput: 0: 1687.6, 1: 1683.5. Samples: 46366328. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:28:00,557][97672] Avg episode reward: [(0, '-0.680'), (1, '22.780')] -[2023-10-11 00:28:01,534][98560] Updated weights for policy 1, policy_version 90242 (0.0009) -[2023-10-11 00:28:01,895][98560] Updated weights for policy 1, policy_version 90252 (0.0009) -[2023-10-11 00:28:02,018][98559] Updated weights for policy 0, policy_version 90850 (0.0009) -[2023-10-11 00:28:02,260][98560] Updated weights for policy 1, policy_version 90262 (0.0009) -[2023-10-11 00:28:02,381][98559] Updated weights for policy 0, policy_version 90860 (0.0009) -[2023-10-11 00:28:02,626][98560] Updated weights for policy 1, policy_version 90272 (0.0009) -[2023-10-11 00:28:02,751][98559] Updated weights for policy 0, policy_version 90870 (0.0008) -[2023-10-11 00:28:03,119][98559] Updated weights for policy 0, policy_version 90880 (0.0008) -[2023-10-11 00:28:05,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 185499648. Throughput: 0: 1699.9, 1: 1709.2. Samples: 46387476. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:28:05,557][97672] Avg episode reward: [(0, '-0.680'), (1, '22.880')] -[2023-10-11 00:28:05,568][98439] Saving new best policy, reward=22.880! -[2023-10-11 00:28:06,709][98560] Updated weights for policy 1, policy_version 90282 (0.0009) -[2023-10-11 00:28:07,070][98560] Updated weights for policy 1, policy_version 90292 (0.0009) -[2023-10-11 00:28:07,102][98559] Updated weights for policy 0, policy_version 90890 (0.0008) -[2023-10-11 00:28:07,445][98560] Updated weights for policy 1, policy_version 90302 (0.0007) -[2023-10-11 00:28:07,456][98559] Updated weights for policy 0, policy_version 90900 (0.0007) -[2023-10-11 00:28:07,818][98559] Updated weights for policy 0, policy_version 90910 (0.0007) -[2023-10-11 00:28:10,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 185565184. Throughput: 0: 1679.3, 1: 1682.0. Samples: 46396792. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:28:10,557][97672] Avg episode reward: [(0, '-0.680'), (1, '22.820')] -[2023-10-11 00:28:11,436][98560] Updated weights for policy 1, policy_version 90312 (0.0007) -[2023-10-11 00:28:11,791][98560] Updated weights for policy 1, policy_version 90322 (0.0008) -[2023-10-11 00:28:11,795][98559] Updated weights for policy 0, policy_version 90920 (0.0009) -[2023-10-11 00:28:12,149][98559] Updated weights for policy 0, policy_version 90930 (0.0010) -[2023-10-11 00:28:12,152][98560] Updated weights for policy 1, policy_version 90332 (0.0007) -[2023-10-11 00:28:12,513][98559] Updated weights for policy 0, policy_version 90940 (0.0009) -[2023-10-11 00:28:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 185630720. Throughput: 0: 1715.1, 1: 1704.3. Samples: 46418264. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:28:15,557][97672] Avg episode reward: [(0, '-0.680'), (1, '22.780')] -[2023-10-11 00:28:16,179][98560] Updated weights for policy 1, policy_version 90342 (0.0008) -[2023-10-11 00:28:16,313][98559] Updated weights for policy 0, policy_version 90950 (0.0007) -[2023-10-11 00:28:16,549][98560] Updated weights for policy 1, policy_version 90352 (0.0008) -[2023-10-11 00:28:16,673][98559] Updated weights for policy 0, policy_version 90960 (0.0009) -[2023-10-11 00:28:16,911][98560] Updated weights for policy 1, policy_version 90362 (0.0009) -[2023-10-11 00:28:17,032][98559] Updated weights for policy 0, policy_version 90970 (0.0009) -[2023-10-11 00:28:20,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 185696256. Throughput: 0: 1721.7, 1: 1709.2. Samples: 46439476. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:28:20,557][97672] Avg episode reward: [(0, '-0.680'), (1, '22.740')] -[2023-10-11 00:28:20,838][98559] Updated weights for policy 0, policy_version 90980 (0.0008) -[2023-10-11 00:28:20,997][98560] Updated weights for policy 1, policy_version 90372 (0.0009) -[2023-10-11 00:28:21,192][98559] Updated weights for policy 0, policy_version 90990 (0.0009) -[2023-10-11 00:28:21,368][98560] Updated weights for policy 1, policy_version 90382 (0.0008) -[2023-10-11 00:28:21,552][98559] Updated weights for policy 0, policy_version 91000 (0.0009) -[2023-10-11 00:28:21,723][98560] Updated weights for policy 1, policy_version 90392 (0.0008) -[2023-10-11 00:28:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 185761792. Throughput: 0: 1710.4, 1: 1684.5. Samples: 46448740. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:28:25,557][97672] Avg episode reward: [(0, '-0.680'), (1, '22.660')] -[2023-10-11 00:28:25,594][98559] Updated weights for policy 0, policy_version 91010 (0.0009) -[2023-10-11 00:28:25,752][98560] Updated weights for policy 1, policy_version 90402 (0.0008) -[2023-10-11 00:28:25,959][98559] Updated weights for policy 0, policy_version 91020 (0.0007) -[2023-10-11 00:28:26,114][98560] Updated weights for policy 1, policy_version 90412 (0.0008) -[2023-10-11 00:28:26,329][98559] Updated weights for policy 0, policy_version 91030 (0.0008) -[2023-10-11 00:28:26,483][98560] Updated weights for policy 1, policy_version 90422 (0.0008) -[2023-10-11 00:28:26,695][98559] Updated weights for policy 0, policy_version 91040 (0.0009) -[2023-10-11 00:28:26,859][98560] Updated weights for policy 1, policy_version 90432 (0.0010) -[2023-10-11 00:28:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 185827328. Throughput: 0: 1728.2, 1: 1711.4. Samples: 46469672. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:28:30,557][97672] Avg episode reward: [(0, '-0.680'), (1, '22.540')] -[2023-10-11 00:28:30,775][98559] Updated weights for policy 0, policy_version 91050 (0.0010) -[2023-10-11 00:28:30,925][98560] Updated weights for policy 1, policy_version 90442 (0.0007) -[2023-10-11 00:28:31,137][98559] Updated weights for policy 0, policy_version 91060 (0.0009) -[2023-10-11 00:28:31,285][98560] Updated weights for policy 1, policy_version 90452 (0.0008) -[2023-10-11 00:28:31,502][98559] Updated weights for policy 0, policy_version 91070 (0.0007) -[2023-10-11 00:28:31,652][98560] Updated weights for policy 1, policy_version 90462 (0.0007) -[2023-10-11 00:28:35,453][98559] Updated weights for policy 0, policy_version 91080 (0.0007) -[2023-10-11 00:28:35,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 185892864. Throughput: 0: 1721.3, 1: 1715.1. Samples: 46490560. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:28:35,557][97672] Avg episode reward: [(0, '-0.660'), (1, '22.500')] -[2023-10-11 00:28:35,668][98560] Updated weights for policy 1, policy_version 90472 (0.0008) -[2023-10-11 00:28:35,809][98559] Updated weights for policy 0, policy_version 91090 (0.0009) -[2023-10-11 00:28:36,035][98560] Updated weights for policy 1, policy_version 90482 (0.0008) -[2023-10-11 00:28:36,172][98559] Updated weights for policy 0, policy_version 91100 (0.0008) -[2023-10-11 00:28:36,314][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000091104_93290496.pth... -[2023-10-11 00:28:36,352][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000089504_91652096.pth -[2023-10-11 00:28:36,417][98560] Updated weights for policy 1, policy_version 90492 (0.0010) -[2023-10-11 00:28:36,554][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000090496_92667904.pth... -[2023-10-11 00:28:36,595][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000088896_91029504.pth -[2023-10-11 00:28:40,342][98559] Updated weights for policy 0, policy_version 91110 (0.0009) -[2023-10-11 00:28:40,442][98560] Updated weights for policy 1, policy_version 90502 (0.0008) -[2023-10-11 00:28:40,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 185958400. Throughput: 0: 1720.0, 1: 1695.6. Samples: 46499580. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:28:40,557][97672] Avg episode reward: [(0, '-0.640'), (1, '22.520')] -[2023-10-11 00:28:40,713][98559] Updated weights for policy 0, policy_version 91120 (0.0008) -[2023-10-11 00:28:40,804][98560] Updated weights for policy 1, policy_version 90512 (0.0007) -[2023-10-11 00:28:41,084][98559] Updated weights for policy 0, policy_version 91130 (0.0008) -[2023-10-11 00:28:41,173][98560] Updated weights for policy 1, policy_version 90522 (0.0008) -[2023-10-11 00:28:45,013][98559] Updated weights for policy 0, policy_version 91140 (0.0008) -[2023-10-11 00:28:45,204][98560] Updated weights for policy 1, policy_version 90532 (0.0008) -[2023-10-11 00:28:45,376][98559] Updated weights for policy 0, policy_version 91150 (0.0007) -[2023-10-11 00:28:45,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 186023936. Throughput: 0: 1728.7, 1: 1703.3. Samples: 46520768. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:28:45,557][97672] Avg episode reward: [(0, '-0.640'), (1, '22.580')] -[2023-10-11 00:28:45,565][98560] Updated weights for policy 1, policy_version 90542 (0.0009) -[2023-10-11 00:28:45,743][98559] Updated weights for policy 0, policy_version 91160 (0.0007) -[2023-10-11 00:28:45,938][98560] Updated weights for policy 1, policy_version 90552 (0.0010) -[2023-10-11 00:28:49,877][98559] Updated weights for policy 0, policy_version 91170 (0.0007) -[2023-10-11 00:28:49,989][98560] Updated weights for policy 1, policy_version 90562 (0.0009) -[2023-10-11 00:28:50,244][98559] Updated weights for policy 0, policy_version 91180 (0.0008) -[2023-10-11 00:28:50,355][98560] Updated weights for policy 1, policy_version 90572 (0.0007) -[2023-10-11 00:28:50,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 186089472. Throughput: 0: 1715.4, 1: 1698.4. Samples: 46541094. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:28:50,557][97672] Avg episode reward: [(0, '-0.640'), (1, '22.540')] -[2023-10-11 00:28:50,612][98559] Updated weights for policy 0, policy_version 91190 (0.0009) -[2023-10-11 00:28:50,726][98560] Updated weights for policy 1, policy_version 90582 (0.0009) -[2023-10-11 00:28:50,966][98559] Updated weights for policy 0, policy_version 91200 (0.0008) -[2023-10-11 00:28:51,087][98560] Updated weights for policy 1, policy_version 90592 (0.0010) -[2023-10-11 00:28:55,080][98559] Updated weights for policy 0, policy_version 91210 (0.0008) -[2023-10-11 00:28:55,186][98560] Updated weights for policy 1, policy_version 90602 (0.0008) -[2023-10-11 00:28:55,437][98559] Updated weights for policy 0, policy_version 91220 (0.0008) -[2023-10-11 00:28:55,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 186155008. Throughput: 0: 1724.3, 1: 1694.8. Samples: 46550650. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-11 00:28:55,556][97672] Avg episode reward: [(0, '-0.600'), (1, '22.480')] -[2023-10-11 00:28:55,557][98560] Updated weights for policy 1, policy_version 90612 (0.0009) -[2023-10-11 00:28:55,806][98559] Updated weights for policy 0, policy_version 91230 (0.0007) -[2023-10-11 00:28:55,874][98385] Saving new best policy, reward=-0.600! -[2023-10-11 00:28:55,913][98560] Updated weights for policy 1, policy_version 90622 (0.0009) -[2023-10-11 00:28:59,766][98559] Updated weights for policy 0, policy_version 91240 (0.0009) -[2023-10-11 00:28:59,879][98560] Updated weights for policy 1, policy_version 90632 (0.0009) -[2023-10-11 00:29:00,137][98559] Updated weights for policy 0, policy_version 91250 (0.0008) -[2023-10-11 00:29:00,245][98560] Updated weights for policy 1, policy_version 90642 (0.0008) -[2023-10-11 00:29:00,502][98559] Updated weights for policy 0, policy_version 91260 (0.0009) -[2023-10-11 00:29:00,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 186220544. Throughput: 0: 1722.8, 1: 1693.6. Samples: 46572002. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-11 00:29:00,557][97672] Avg episode reward: [(0, '-0.600'), (1, '22.460')] -[2023-10-11 00:29:00,613][98560] Updated weights for policy 1, policy_version 90652 (0.0008) -[2023-10-11 00:29:04,455][98559] Updated weights for policy 0, policy_version 91270 (0.0009) -[2023-10-11 00:29:04,626][98560] Updated weights for policy 1, policy_version 90662 (0.0008) -[2023-10-11 00:29:04,816][98559] Updated weights for policy 0, policy_version 91280 (0.0010) -[2023-10-11 00:29:04,991][98560] Updated weights for policy 1, policy_version 90672 (0.0008) -[2023-10-11 00:29:05,176][98559] Updated weights for policy 0, policy_version 91290 (0.0009) -[2023-10-11 00:29:05,360][98560] Updated weights for policy 1, policy_version 90682 (0.0009) -[2023-10-11 00:29:05,556][97672] Fps is (10 sec: 16383.5, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 186318848. Throughput: 0: 1689.4, 1: 1693.9. Samples: 46591724. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-11 00:29:05,558][97672] Avg episode reward: [(0, '-0.600'), (1, '22.480')] -[2023-10-11 00:29:09,224][98559] Updated weights for policy 0, policy_version 91300 (0.0010) -[2023-10-11 00:29:09,412][98560] Updated weights for policy 1, policy_version 90692 (0.0009) -[2023-10-11 00:29:09,584][98559] Updated weights for policy 0, policy_version 91310 (0.0008) -[2023-10-11 00:29:09,777][98560] Updated weights for policy 1, policy_version 90702 (0.0008) -[2023-10-11 00:29:09,955][98559] Updated weights for policy 0, policy_version 91320 (0.0008) -[2023-10-11 00:29:10,138][98560] Updated weights for policy 1, policy_version 90712 (0.0008) -[2023-10-11 00:29:10,556][97672] Fps is (10 sec: 19661.0, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 186417152. Throughput: 0: 1709.7, 1: 1700.5. Samples: 46602198. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-11 00:29:10,556][97672] Avg episode reward: [(0, '-0.600'), (1, '22.420')] -[2023-10-11 00:29:14,034][98559] Updated weights for policy 0, policy_version 91330 (0.0009) -[2023-10-11 00:29:14,151][98560] Updated weights for policy 1, policy_version 90722 (0.0009) -[2023-10-11 00:29:14,398][98559] Updated weights for policy 0, policy_version 91340 (0.0009) -[2023-10-11 00:29:14,521][98560] Updated weights for policy 1, policy_version 90732 (0.0009) -[2023-10-11 00:29:14,773][98559] Updated weights for policy 0, policy_version 91350 (0.0009) -[2023-10-11 00:29:14,888][98560] Updated weights for policy 1, policy_version 90742 (0.0008) -[2023-10-11 00:29:15,133][98559] Updated weights for policy 0, policy_version 91360 (0.0010) -[2023-10-11 00:29:15,251][98560] Updated weights for policy 1, policy_version 90752 (0.0007) -[2023-10-11 00:29:15,556][97672] Fps is (10 sec: 16384.6, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 186482688. Throughput: 0: 1699.0, 1: 1700.5. Samples: 46622652. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-11 00:29:15,556][97672] Avg episode reward: [(0, '-0.600'), (1, '22.540')] -[2023-10-11 00:29:19,005][98559] Updated weights for policy 0, policy_version 91370 (0.0010) -[2023-10-11 00:29:19,367][98559] Updated weights for policy 0, policy_version 91380 (0.0007) -[2023-10-11 00:29:19,400][98560] Updated weights for policy 1, policy_version 90762 (0.0008) -[2023-10-11 00:29:19,726][98559] Updated weights for policy 0, policy_version 91390 (0.0007) -[2023-10-11 00:29:19,762][98560] Updated weights for policy 1, policy_version 90772 (0.0009) -[2023-10-11 00:29:20,118][98560] Updated weights for policy 1, policy_version 90782 (0.0009) -[2023-10-11 00:29:20,556][97672] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 186548224. Throughput: 0: 1690.2, 1: 1678.2. Samples: 46642138. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-11 00:29:20,557][97672] Avg episode reward: [(0, '-0.600'), (1, '22.500')] -[2023-10-11 00:29:23,686][98559] Updated weights for policy 0, policy_version 91400 (0.0008) -[2023-10-11 00:29:24,054][98559] Updated weights for policy 0, policy_version 91410 (0.0007) -[2023-10-11 00:29:24,216][98560] Updated weights for policy 1, policy_version 90792 (0.0008) -[2023-10-11 00:29:24,408][98559] Updated weights for policy 0, policy_version 91420 (0.0007) -[2023-10-11 00:29:24,595][98560] Updated weights for policy 1, policy_version 90802 (0.0010) -[2023-10-11 00:29:24,955][98560] Updated weights for policy 1, policy_version 90812 (0.0010) -[2023-10-11 00:29:25,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 186613760. Throughput: 0: 1719.7, 1: 1700.8. Samples: 46653502. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-11 00:29:25,556][97672] Avg episode reward: [(0, '-0.580'), (1, '22.520')] -[2023-10-11 00:29:25,557][98385] Saving new best policy, reward=-0.580! -[2023-10-11 00:29:28,408][98559] Updated weights for policy 0, policy_version 91430 (0.0008) -[2023-10-11 00:29:28,779][98559] Updated weights for policy 0, policy_version 91440 (0.0008) -[2023-10-11 00:29:29,034][98560] Updated weights for policy 1, policy_version 90822 (0.0009) -[2023-10-11 00:29:29,156][98559] Updated weights for policy 0, policy_version 91450 (0.0008) -[2023-10-11 00:29:29,411][98560] Updated weights for policy 1, policy_version 90832 (0.0008) -[2023-10-11 00:29:29,779][98560] Updated weights for policy 1, policy_version 90842 (0.0009) -[2023-10-11 00:29:30,556][97672] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 186679296. Throughput: 0: 1690.1, 1: 1698.4. Samples: 46673252. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-11 00:29:30,557][97672] Avg episode reward: [(0, '-0.580'), (1, '22.540')] -[2023-10-11 00:29:33,035][98559] Updated weights for policy 0, policy_version 91460 (0.0008) -[2023-10-11 00:29:33,400][98559] Updated weights for policy 0, policy_version 91470 (0.0009) -[2023-10-11 00:29:33,768][98559] Updated weights for policy 0, policy_version 91480 (0.0009) -[2023-10-11 00:29:33,867][98560] Updated weights for policy 1, policy_version 90852 (0.0008) -[2023-10-11 00:29:34,233][98560] Updated weights for policy 1, policy_version 90862 (0.0008) -[2023-10-11 00:29:34,601][98560] Updated weights for policy 1, policy_version 90872 (0.0010) -[2023-10-11 00:29:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 186744832. Throughput: 0: 1706.0, 1: 1675.8. Samples: 46693276. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-11 00:29:35,557][97672] Avg episode reward: [(0, '-0.580'), (1, '22.420')] -[2023-10-11 00:29:37,757][98559] Updated weights for policy 0, policy_version 91490 (0.0008) -[2023-10-11 00:29:38,122][98559] Updated weights for policy 0, policy_version 91500 (0.0009) -[2023-10-11 00:29:38,485][98559] Updated weights for policy 0, policy_version 91510 (0.0008) -[2023-10-11 00:29:38,510][98560] Updated weights for policy 1, policy_version 90882 (0.0007) -[2023-10-11 00:29:38,856][98559] Updated weights for policy 0, policy_version 91520 (0.0007) -[2023-10-11 00:29:38,872][98560] Updated weights for policy 1, policy_version 90892 (0.0007) -[2023-10-11 00:29:39,235][98560] Updated weights for policy 1, policy_version 90902 (0.0007) -[2023-10-11 00:29:39,606][98560] Updated weights for policy 1, policy_version 90912 (0.0010) -[2023-10-11 00:29:40,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 186810368. Throughput: 0: 1707.2, 1: 1698.7. Samples: 46703916. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-11 00:29:40,557][97672] Avg episode reward: [(0, '-0.500'), (1, '22.420')] -[2023-10-11 00:29:40,559][98385] Saving new best policy, reward=-0.500! -[2023-10-11 00:29:42,696][98559] Updated weights for policy 0, policy_version 91530 (0.0007) -[2023-10-11 00:29:43,052][98559] Updated weights for policy 0, policy_version 91540 (0.0007) -[2023-10-11 00:29:43,417][98559] Updated weights for policy 0, policy_version 91550 (0.0008) -[2023-10-11 00:29:43,806][98560] Updated weights for policy 1, policy_version 90922 (0.0008) -[2023-10-11 00:29:44,175][98560] Updated weights for policy 1, policy_version 90932 (0.0007) -[2023-10-11 00:29:44,538][98560] Updated weights for policy 1, policy_version 90942 (0.0011) -[2023-10-11 00:29:45,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 186875904. Throughput: 0: 1692.1, 1: 1688.9. Samples: 46724148. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-11 00:29:45,557][97672] Avg episode reward: [(0, '-0.500'), (1, '22.360')] -[2023-10-11 00:29:47,400][98559] Updated weights for policy 0, policy_version 91560 (0.0010) -[2023-10-11 00:29:47,753][98559] Updated weights for policy 0, policy_version 91570 (0.0009) -[2023-10-11 00:29:48,121][98559] Updated weights for policy 0, policy_version 91580 (0.0007) -[2023-10-11 00:29:48,546][98560] Updated weights for policy 1, policy_version 90952 (0.0008) -[2023-10-11 00:29:48,910][98560] Updated weights for policy 1, policy_version 90962 (0.0010) -[2023-10-11 00:29:49,273][98560] Updated weights for policy 1, policy_version 90972 (0.0009) -[2023-10-11 00:29:50,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 186941440. Throughput: 0: 1723.9, 1: 1668.6. Samples: 46744386. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:29:50,556][97672] Avg episode reward: [(0, '-0.500'), (1, '22.360')] -[2023-10-11 00:29:52,047][98559] Updated weights for policy 0, policy_version 91590 (0.0008) -[2023-10-11 00:29:52,422][98559] Updated weights for policy 0, policy_version 91600 (0.0009) -[2023-10-11 00:29:52,781][98559] Updated weights for policy 0, policy_version 91610 (0.0007) -[2023-10-11 00:29:53,412][98560] Updated weights for policy 1, policy_version 90982 (0.0009) -[2023-10-11 00:29:53,780][98560] Updated weights for policy 1, policy_version 90992 (0.0007) -[2023-10-11 00:29:54,136][98560] Updated weights for policy 1, policy_version 91002 (0.0008) -[2023-10-11 00:29:55,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 187006976. Throughput: 0: 1699.5, 1: 1690.6. Samples: 46754754. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:29:55,557][97672] Avg episode reward: [(0, '-0.480'), (1, '22.280')] -[2023-10-11 00:29:55,559][98385] Saving new best policy, reward=-0.480! -[2023-10-11 00:29:56,756][98559] Updated weights for policy 0, policy_version 91620 (0.0009) -[2023-10-11 00:29:57,122][98559] Updated weights for policy 0, policy_version 91630 (0.0009) -[2023-10-11 00:29:57,492][98559] Updated weights for policy 0, policy_version 91640 (0.0009) -[2023-10-11 00:29:58,024][98560] Updated weights for policy 1, policy_version 91012 (0.0009) -[2023-10-11 00:29:58,388][98560] Updated weights for policy 1, policy_version 91022 (0.0008) -[2023-10-11 00:29:58,758][98560] Updated weights for policy 1, policy_version 91032 (0.0008) -[2023-10-11 00:30:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 187072512. Throughput: 0: 1715.3, 1: 1672.3. Samples: 46775096. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:30:00,556][97672] Avg episode reward: [(0, '-0.480'), (1, '22.280')] -[2023-10-11 00:30:01,500][98559] Updated weights for policy 0, policy_version 91650 (0.0009) -[2023-10-11 00:30:01,866][98559] Updated weights for policy 0, policy_version 91660 (0.0010) -[2023-10-11 00:30:02,233][98559] Updated weights for policy 0, policy_version 91670 (0.0010) -[2023-10-11 00:30:02,603][98559] Updated weights for policy 0, policy_version 91680 (0.0008) -[2023-10-11 00:30:02,827][98560] Updated weights for policy 1, policy_version 91042 (0.0008) -[2023-10-11 00:30:03,189][98560] Updated weights for policy 1, policy_version 91052 (0.0009) -[2023-10-11 00:30:03,552][98560] Updated weights for policy 1, policy_version 91062 (0.0007) -[2023-10-11 00:30:03,928][98560] Updated weights for policy 1, policy_version 91072 (0.0008) -[2023-10-11 00:30:05,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 187138048. Throughput: 0: 1730.1, 1: 1683.5. Samples: 46795750. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:30:05,557][97672] Avg episode reward: [(0, '-0.480'), (1, '22.340')] -[2023-10-11 00:30:06,611][98559] Updated weights for policy 0, policy_version 91690 (0.0008) -[2023-10-11 00:30:06,979][98559] Updated weights for policy 0, policy_version 91700 (0.0010) -[2023-10-11 00:30:07,343][98559] Updated weights for policy 0, policy_version 91710 (0.0010) -[2023-10-11 00:30:07,847][98560] Updated weights for policy 1, policy_version 91082 (0.0008) -[2023-10-11 00:30:08,215][98560] Updated weights for policy 1, policy_version 91092 (0.0008) -[2023-10-11 00:30:08,584][98560] Updated weights for policy 1, policy_version 91102 (0.0009) -[2023-10-11 00:30:10,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 187203584. Throughput: 0: 1693.9, 1: 1695.3. Samples: 46806018. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:30:10,556][97672] Avg episode reward: [(0, '-0.480'), (1, '22.380')] -[2023-10-11 00:30:11,442][98559] Updated weights for policy 0, policy_version 91720 (0.0009) -[2023-10-11 00:30:11,795][98559] Updated weights for policy 0, policy_version 91730 (0.0011) -[2023-10-11 00:30:12,167][98559] Updated weights for policy 0, policy_version 91740 (0.0008) -[2023-10-11 00:30:12,594][98560] Updated weights for policy 1, policy_version 91112 (0.0008) -[2023-10-11 00:30:12,963][98560] Updated weights for policy 1, policy_version 91122 (0.0007) -[2023-10-11 00:30:13,325][98560] Updated weights for policy 1, policy_version 91132 (0.0007) -[2023-10-11 00:30:15,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 187269120. Throughput: 0: 1719.2, 1: 1675.0. Samples: 46825990. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:30:15,556][97672] Avg episode reward: [(0, '-0.480'), (1, '22.340')] -[2023-10-11 00:30:16,282][98559] Updated weights for policy 0, policy_version 91750 (0.0008) -[2023-10-11 00:30:16,662][98559] Updated weights for policy 0, policy_version 91760 (0.0007) -[2023-10-11 00:30:17,028][98559] Updated weights for policy 0, policy_version 91770 (0.0008) -[2023-10-11 00:30:17,315][98560] Updated weights for policy 1, policy_version 91142 (0.0008) -[2023-10-11 00:30:17,706][98560] Updated weights for policy 1, policy_version 91152 (0.0009) -[2023-10-11 00:30:18,064][98560] Updated weights for policy 1, policy_version 91162 (0.0011) -[2023-10-11 00:30:20,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 187334656. Throughput: 0: 1714.8, 1: 1695.5. Samples: 46846736. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:30:20,557][97672] Avg episode reward: [(0, '-0.480'), (1, '22.380')] -[2023-10-11 00:30:20,980][98559] Updated weights for policy 0, policy_version 91780 (0.0008) -[2023-10-11 00:30:21,345][98559] Updated weights for policy 0, policy_version 91790 (0.0008) -[2023-10-11 00:30:21,710][98559] Updated weights for policy 0, policy_version 91800 (0.0008) -[2023-10-11 00:30:22,030][98560] Updated weights for policy 1, policy_version 91172 (0.0011) -[2023-10-11 00:30:22,395][98560] Updated weights for policy 1, policy_version 91182 (0.0009) -[2023-10-11 00:30:22,762][98560] Updated weights for policy 1, policy_version 91192 (0.0009) -[2023-10-11 00:30:25,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 187400192. Throughput: 0: 1704.5, 1: 1684.3. Samples: 46856412. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:30:25,557][97672] Avg episode reward: [(0, '-0.480'), (1, '22.400')] -[2023-10-11 00:30:25,637][98559] Updated weights for policy 0, policy_version 91810 (0.0008) -[2023-10-11 00:30:26,017][98559] Updated weights for policy 0, policy_version 91820 (0.0009) -[2023-10-11 00:30:26,387][98559] Updated weights for policy 0, policy_version 91830 (0.0008) -[2023-10-11 00:30:26,750][98559] Updated weights for policy 0, policy_version 91840 (0.0008) -[2023-10-11 00:30:26,784][98560] Updated weights for policy 1, policy_version 91202 (0.0009) -[2023-10-11 00:30:27,158][98560] Updated weights for policy 1, policy_version 91212 (0.0010) -[2023-10-11 00:30:27,530][98560] Updated weights for policy 1, policy_version 91222 (0.0009) -[2023-10-11 00:30:27,899][98560] Updated weights for policy 1, policy_version 91232 (0.0008) -[2023-10-11 00:30:30,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 187465728. Throughput: 0: 1713.6, 1: 1683.7. Samples: 46877028. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:30:30,556][97672] Avg episode reward: [(0, '-0.480'), (1, '22.560')] -[2023-10-11 00:30:30,676][98559] Updated weights for policy 0, policy_version 91850 (0.0007) -[2023-10-11 00:30:31,042][98559] Updated weights for policy 0, policy_version 91860 (0.0008) -[2023-10-11 00:30:31,407][98559] Updated weights for policy 0, policy_version 91870 (0.0007) -[2023-10-11 00:30:31,918][98560] Updated weights for policy 1, policy_version 91242 (0.0007) -[2023-10-11 00:30:32,294][98560] Updated weights for policy 1, policy_version 91252 (0.0007) -[2023-10-11 00:30:32,663][98560] Updated weights for policy 1, policy_version 91262 (0.0007) -[2023-10-11 00:30:35,382][98559] Updated weights for policy 0, policy_version 91880 (0.0007) -[2023-10-11 00:30:35,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 187531264. Throughput: 0: 1704.7, 1: 1707.8. Samples: 46897950. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:30:35,557][97672] Avg episode reward: [(0, '-0.480'), (1, '22.600')] -[2023-10-11 00:30:35,564][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000091264_93454336.pth... -[2023-10-11 00:30:35,595][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000089696_91848704.pth -[2023-10-11 00:30:35,749][98559] Updated weights for policy 0, policy_version 91890 (0.0009) -[2023-10-11 00:30:36,109][98559] Updated weights for policy 0, policy_version 91900 (0.0010) -[2023-10-11 00:30:36,252][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000091904_94109696.pth... -[2023-10-11 00:30:36,294][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000090304_92471296.pth -[2023-10-11 00:30:36,628][98560] Updated weights for policy 1, policy_version 91272 (0.0008) -[2023-10-11 00:30:36,995][98560] Updated weights for policy 1, policy_version 91282 (0.0009) -[2023-10-11 00:30:37,365][98560] Updated weights for policy 1, policy_version 91292 (0.0010) -[2023-10-11 00:30:40,024][98559] Updated weights for policy 0, policy_version 91910 (0.0009) -[2023-10-11 00:30:40,394][98559] Updated weights for policy 0, policy_version 91920 (0.0007) -[2023-10-11 00:30:40,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 187596800. Throughput: 0: 1714.3, 1: 1681.3. Samples: 46907556. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:30:40,557][97672] Avg episode reward: [(0, '-0.480'), (1, '22.660')] -[2023-10-11 00:30:40,756][98559] Updated weights for policy 0, policy_version 91930 (0.0008) -[2023-10-11 00:30:41,479][98560] Updated weights for policy 1, policy_version 91302 (0.0009) -[2023-10-11 00:30:41,841][98560] Updated weights for policy 1, policy_version 91312 (0.0009) -[2023-10-11 00:30:42,212][98560] Updated weights for policy 1, policy_version 91322 (0.0008) -[2023-10-11 00:30:44,730][98559] Updated weights for policy 0, policy_version 91940 (0.0010) -[2023-10-11 00:30:45,093][98559] Updated weights for policy 0, policy_version 91950 (0.0011) -[2023-10-11 00:30:45,460][98559] Updated weights for policy 0, policy_version 91960 (0.0008) -[2023-10-11 00:30:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 187662336. Throughput: 0: 1716.4, 1: 1693.0. Samples: 46928522. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:30:45,557][97672] Avg episode reward: [(0, '-0.480'), (1, '22.640')] -[2023-10-11 00:30:46,282][98560] Updated weights for policy 1, policy_version 91332 (0.0010) -[2023-10-11 00:30:46,652][98560] Updated weights for policy 1, policy_version 91342 (0.0010) -[2023-10-11 00:30:47,025][98560] Updated weights for policy 1, policy_version 91352 (0.0009) -[2023-10-11 00:30:49,438][98559] Updated weights for policy 0, policy_version 91970 (0.0007) -[2023-10-11 00:30:49,811][98559] Updated weights for policy 0, policy_version 91980 (0.0009) -[2023-10-11 00:30:50,172][98559] Updated weights for policy 0, policy_version 91990 (0.0010) -[2023-10-11 00:30:50,544][98559] Updated weights for policy 0, policy_version 92000 (0.0012) -[2023-10-11 00:30:50,556][97672] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 187760640. Throughput: 0: 1695.7, 1: 1700.5. Samples: 46948580. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:30:50,557][97672] Avg episode reward: [(0, '-0.480'), (1, '22.660')] -[2023-10-11 00:30:50,971][98560] Updated weights for policy 1, policy_version 91362 (0.0007) -[2023-10-11 00:30:51,342][98560] Updated weights for policy 1, policy_version 91372 (0.0007) -[2023-10-11 00:30:51,694][98560] Updated weights for policy 1, policy_version 91382 (0.0009) -[2023-10-11 00:30:52,061][98560] Updated weights for policy 1, policy_version 91392 (0.0008) -[2023-10-11 00:30:54,614][98559] Updated weights for policy 0, policy_version 92010 (0.0008) -[2023-10-11 00:30:54,974][98559] Updated weights for policy 0, policy_version 92020 (0.0007) -[2023-10-11 00:30:55,341][98559] Updated weights for policy 0, policy_version 92030 (0.0008) -[2023-10-11 00:30:55,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 187826176. Throughput: 0: 1725.0, 1: 1677.1. Samples: 46959110. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:30:55,557][97672] Avg episode reward: [(0, '-0.480'), (1, '22.560')] -[2023-10-11 00:30:56,058][98560] Updated weights for policy 1, policy_version 91402 (0.0007) -[2023-10-11 00:30:56,433][98560] Updated weights for policy 1, policy_version 91412 (0.0007) -[2023-10-11 00:30:56,797][98560] Updated weights for policy 1, policy_version 91422 (0.0007) -[2023-10-11 00:30:59,289][98559] Updated weights for policy 0, policy_version 92040 (0.0007) -[2023-10-11 00:30:59,658][98559] Updated weights for policy 0, policy_version 92050 (0.0008) -[2023-10-11 00:31:00,023][98559] Updated weights for policy 0, policy_version 92060 (0.0011) -[2023-10-11 00:31:00,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 187891712. Throughput: 0: 1720.8, 1: 1700.8. Samples: 46979964. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:31:00,557][97672] Avg episode reward: [(0, '-0.460'), (1, '22.580')] -[2023-10-11 00:31:00,558][98385] Saving new best policy, reward=-0.460! -[2023-10-11 00:31:00,854][98560] Updated weights for policy 1, policy_version 91432 (0.0008) -[2023-10-11 00:31:01,231][98560] Updated weights for policy 1, policy_version 91442 (0.0010) -[2023-10-11 00:31:01,603][98560] Updated weights for policy 1, policy_version 91452 (0.0009) -[2023-10-11 00:31:04,156][98559] Updated weights for policy 0, policy_version 92070 (0.0010) -[2023-10-11 00:31:04,515][98559] Updated weights for policy 0, policy_version 92080 (0.0008) -[2023-10-11 00:31:04,887][98559] Updated weights for policy 0, policy_version 92090 (0.0009) -[2023-10-11 00:31:05,427][98560] Updated weights for policy 1, policy_version 91462 (0.0010) -[2023-10-11 00:31:05,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 187957248. Throughput: 0: 1698.0, 1: 1710.7. Samples: 47000126. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:31:05,556][97672] Avg episode reward: [(0, '-0.460'), (1, '22.580')] -[2023-10-11 00:31:05,806][98560] Updated weights for policy 1, policy_version 91472 (0.0010) -[2023-10-11 00:31:06,171][98560] Updated weights for policy 1, policy_version 91482 (0.0008) -[2023-10-11 00:31:08,773][98559] Updated weights for policy 0, policy_version 92100 (0.0009) -[2023-10-11 00:31:09,142][98559] Updated weights for policy 0, policy_version 92110 (0.0010) -[2023-10-11 00:31:09,512][98559] Updated weights for policy 0, policy_version 92120 (0.0010) -[2023-10-11 00:31:10,229][98560] Updated weights for policy 1, policy_version 91492 (0.0011) -[2023-10-11 00:31:10,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.2, 300 sec: 13662.6). Total num frames: 188022784. Throughput: 0: 1728.1, 1: 1699.3. Samples: 47010648. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:31:10,558][97672] Avg episode reward: [(0, '-0.480'), (1, '22.540')] -[2023-10-11 00:31:10,602][98560] Updated weights for policy 1, policy_version 91502 (0.0009) -[2023-10-11 00:31:10,973][98560] Updated weights for policy 1, policy_version 91512 (0.0010) -[2023-10-11 00:31:13,504][98559] Updated weights for policy 0, policy_version 92130 (0.0008) -[2023-10-11 00:31:13,869][98559] Updated weights for policy 0, policy_version 92140 (0.0008) -[2023-10-11 00:31:14,231][98559] Updated weights for policy 0, policy_version 92150 (0.0008) -[2023-10-11 00:31:14,595][98559] Updated weights for policy 0, policy_version 92160 (0.0009) -[2023-10-11 00:31:15,072][98560] Updated weights for policy 1, policy_version 91522 (0.0010) -[2023-10-11 00:31:15,440][98560] Updated weights for policy 1, policy_version 91532 (0.0009) -[2023-10-11 00:31:15,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 188088320. Throughput: 0: 1704.5, 1: 1709.3. Samples: 47030650. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:31:15,557][97672] Avg episode reward: [(0, '-0.480'), (1, '22.540')] -[2023-10-11 00:31:15,799][98560] Updated weights for policy 1, policy_version 91542 (0.0010) -[2023-10-11 00:31:16,161][98560] Updated weights for policy 1, policy_version 91552 (0.0008) -[2023-10-11 00:31:18,581][98559] Updated weights for policy 0, policy_version 92170 (0.0008) -[2023-10-11 00:31:18,940][98559] Updated weights for policy 0, policy_version 92180 (0.0007) -[2023-10-11 00:31:19,311][98559] Updated weights for policy 0, policy_version 92190 (0.0008) -[2023-10-11 00:31:20,183][98560] Updated weights for policy 1, policy_version 91562 (0.0008) -[2023-10-11 00:31:20,547][98560] Updated weights for policy 1, policy_version 91572 (0.0007) -[2023-10-11 00:31:20,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 188153856. Throughput: 0: 1706.0, 1: 1705.4. Samples: 47051460. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:31:20,557][97672] Avg episode reward: [(0, '-0.480'), (1, '22.540')] -[2023-10-11 00:31:20,907][98560] Updated weights for policy 1, policy_version 91582 (0.0009) -[2023-10-11 00:31:23,383][98559] Updated weights for policy 0, policy_version 92200 (0.0010) -[2023-10-11 00:31:23,742][98559] Updated weights for policy 0, policy_version 92210 (0.0007) -[2023-10-11 00:31:24,101][98559] Updated weights for policy 0, policy_version 92220 (0.0008) -[2023-10-11 00:31:24,773][98560] Updated weights for policy 1, policy_version 91592 (0.0010) -[2023-10-11 00:31:25,135][98560] Updated weights for policy 1, policy_version 91602 (0.0007) -[2023-10-11 00:31:25,512][98560] Updated weights for policy 1, policy_version 91612 (0.0007) -[2023-10-11 00:31:25,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 188219392. Throughput: 0: 1721.0, 1: 1705.0. Samples: 47061724. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:31:25,557][97672] Avg episode reward: [(0, '-0.480'), (1, '22.560')] -[2023-10-11 00:31:28,093][98559] Updated weights for policy 0, policy_version 92230 (0.0009) -[2023-10-11 00:31:28,463][98559] Updated weights for policy 0, policy_version 92240 (0.0009) -[2023-10-11 00:31:28,831][98559] Updated weights for policy 0, policy_version 92250 (0.0011) -[2023-10-11 00:31:29,702][98560] Updated weights for policy 1, policy_version 91622 (0.0009) -[2023-10-11 00:31:30,061][98560] Updated weights for policy 1, policy_version 91632 (0.0010) -[2023-10-11 00:31:30,428][98560] Updated weights for policy 1, policy_version 91642 (0.0009) -[2023-10-11 00:31:30,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 188284928. Throughput: 0: 1694.0, 1: 1715.7. Samples: 47081956. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:31:30,556][97672] Avg episode reward: [(0, '-0.420'), (1, '22.680')] -[2023-10-11 00:31:30,557][98385] Saving new best policy, reward=-0.420! -[2023-10-11 00:31:32,765][98559] Updated weights for policy 0, policy_version 92260 (0.0011) -[2023-10-11 00:31:33,131][98559] Updated weights for policy 0, policy_version 92270 (0.0011) -[2023-10-11 00:31:33,512][98559] Updated weights for policy 0, policy_version 92280 (0.0011) -[2023-10-11 00:31:34,545][98560] Updated weights for policy 1, policy_version 91652 (0.0009) -[2023-10-11 00:31:34,913][98560] Updated weights for policy 1, policy_version 91662 (0.0008) -[2023-10-11 00:31:35,277][98560] Updated weights for policy 1, policy_version 91672 (0.0008) -[2023-10-11 00:31:35,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 188350464. Throughput: 0: 1718.9, 1: 1708.5. Samples: 47102810. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:31:35,556][97672] Avg episode reward: [(0, '-0.400'), (1, '22.700')] -[2023-10-11 00:31:35,564][98385] Saving new best policy, reward=-0.400! -[2023-10-11 00:31:37,541][98559] Updated weights for policy 0, policy_version 92290 (0.0009) -[2023-10-11 00:31:37,910][98559] Updated weights for policy 0, policy_version 92300 (0.0007) -[2023-10-11 00:31:38,286][98559] Updated weights for policy 0, policy_version 92310 (0.0009) -[2023-10-11 00:31:38,645][98559] Updated weights for policy 0, policy_version 92320 (0.0008) -[2023-10-11 00:31:39,209][98560] Updated weights for policy 1, policy_version 91682 (0.0009) -[2023-10-11 00:31:39,586][98560] Updated weights for policy 1, policy_version 91692 (0.0011) -[2023-10-11 00:31:39,953][98560] Updated weights for policy 1, policy_version 91702 (0.0009) -[2023-10-11 00:31:40,314][98560] Updated weights for policy 1, policy_version 91712 (0.0009) -[2023-10-11 00:31:40,556][97672] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 188448768. Throughput: 0: 1700.3, 1: 1712.9. Samples: 47112706. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:31:40,557][97672] Avg episode reward: [(0, '-0.400'), (1, '22.660')] -[2023-10-11 00:31:42,576][98559] Updated weights for policy 0, policy_version 92330 (0.0007) -[2023-10-11 00:31:42,942][98559] Updated weights for policy 0, policy_version 92340 (0.0008) -[2023-10-11 00:31:43,301][98559] Updated weights for policy 0, policy_version 92350 (0.0010) -[2023-10-11 00:31:44,263][98560] Updated weights for policy 1, policy_version 91722 (0.0011) -[2023-10-11 00:31:44,615][98560] Updated weights for policy 1, policy_version 91732 (0.0010) -[2023-10-11 00:31:44,979][98560] Updated weights for policy 1, policy_version 91742 (0.0011) -[2023-10-11 00:31:45,556][97672] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 188514304. Throughput: 0: 1703.6, 1: 1713.5. Samples: 47133734. Policy #0 lag: (min: 10.0, avg: 12.8, max: 35.0) -[2023-10-11 00:31:45,557][97672] Avg episode reward: [(0, '-0.400'), (1, '22.680')] -[2023-10-11 00:31:47,104][98559] Updated weights for policy 0, policy_version 92360 (0.0009) -[2023-10-11 00:31:47,460][98559] Updated weights for policy 0, policy_version 92370 (0.0009) -[2023-10-11 00:31:47,826][98559] Updated weights for policy 0, policy_version 92380 (0.0007) -[2023-10-11 00:31:49,063][98560] Updated weights for policy 1, policy_version 91752 (0.0008) -[2023-10-11 00:31:49,419][98560] Updated weights for policy 1, policy_version 91762 (0.0007) -[2023-10-11 00:31:49,786][98560] Updated weights for policy 1, policy_version 91772 (0.0007) -[2023-10-11 00:31:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 188579840. Throughput: 0: 1734.3, 1: 1685.5. Samples: 47154018. Policy #0 lag: (min: 10.0, avg: 12.8, max: 35.0) -[2023-10-11 00:31:50,557][97672] Avg episode reward: [(0, '-0.480'), (1, '22.780')] -[2023-10-11 00:31:51,841][98559] Updated weights for policy 0, policy_version 92390 (0.0008) -[2023-10-11 00:31:52,224][98559] Updated weights for policy 0, policy_version 92400 (0.0009) -[2023-10-11 00:31:52,590][98559] Updated weights for policy 0, policy_version 92410 (0.0008) -[2023-10-11 00:31:53,730][98560] Updated weights for policy 1, policy_version 91782 (0.0009) -[2023-10-11 00:31:54,125][98560] Updated weights for policy 1, policy_version 91792 (0.0008) -[2023-10-11 00:31:54,492][98560] Updated weights for policy 1, policy_version 91802 (0.0009) -[2023-10-11 00:31:55,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 188645376. Throughput: 0: 1699.9, 1: 1712.6. Samples: 47164210. Policy #0 lag: (min: 10.0, avg: 12.8, max: 35.0) -[2023-10-11 00:31:55,557][97672] Avg episode reward: [(0, '-0.480'), (1, '22.820')] -[2023-10-11 00:31:56,570][98559] Updated weights for policy 0, policy_version 92420 (0.0008) -[2023-10-11 00:31:56,936][98559] Updated weights for policy 0, policy_version 92430 (0.0009) -[2023-10-11 00:31:57,309][98559] Updated weights for policy 0, policy_version 92440 (0.0007) -[2023-10-11 00:31:58,615][98560] Updated weights for policy 1, policy_version 91812 (0.0009) -[2023-10-11 00:31:58,972][98560] Updated weights for policy 1, policy_version 91822 (0.0010) -[2023-10-11 00:31:59,348][98560] Updated weights for policy 1, policy_version 91832 (0.0012) -[2023-10-11 00:32:00,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 188710912. Throughput: 0: 1724.6, 1: 1699.0. Samples: 47184710. Policy #0 lag: (min: 10.0, avg: 12.8, max: 35.0) -[2023-10-11 00:32:00,557][97672] Avg episode reward: [(0, '-0.480'), (1, '22.700')] -[2023-10-11 00:32:01,236][98559] Updated weights for policy 0, policy_version 92450 (0.0008) -[2023-10-11 00:32:01,611][98559] Updated weights for policy 0, policy_version 92460 (0.0009) -[2023-10-11 00:32:01,971][98559] Updated weights for policy 0, policy_version 92470 (0.0008) -[2023-10-11 00:32:02,343][98559] Updated weights for policy 0, policy_version 92480 (0.0007) -[2023-10-11 00:32:03,164][98560] Updated weights for policy 1, policy_version 91842 (0.0008) -[2023-10-11 00:32:03,537][98560] Updated weights for policy 1, policy_version 91852 (0.0009) -[2023-10-11 00:32:03,903][98560] Updated weights for policy 1, policy_version 91862 (0.0007) -[2023-10-11 00:32:04,268][98560] Updated weights for policy 1, policy_version 91872 (0.0009) -[2023-10-11 00:32:05,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 188776448. Throughput: 0: 1729.5, 1: 1682.8. Samples: 47205014. Policy #0 lag: (min: 10.0, avg: 12.8, max: 35.0) -[2023-10-11 00:32:05,557][97672] Avg episode reward: [(0, '-0.480'), (1, '22.740')] -[2023-10-11 00:32:06,361][98559] Updated weights for policy 0, policy_version 92490 (0.0010) -[2023-10-11 00:32:06,734][98559] Updated weights for policy 0, policy_version 92500 (0.0008) -[2023-10-11 00:32:07,094][98559] Updated weights for policy 0, policy_version 92510 (0.0008) -[2023-10-11 00:32:08,371][98560] Updated weights for policy 1, policy_version 91882 (0.0010) -[2023-10-11 00:32:08,738][98560] Updated weights for policy 1, policy_version 91892 (0.0007) -[2023-10-11 00:32:09,107][98560] Updated weights for policy 1, policy_version 91902 (0.0008) -[2023-10-11 00:32:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 188841984. Throughput: 0: 1705.5, 1: 1711.7. Samples: 47215498. Policy #0 lag: (min: 10.0, avg: 12.8, max: 35.0) -[2023-10-11 00:32:10,557][97672] Avg episode reward: [(0, '-0.480'), (1, '22.720')] -[2023-10-11 00:32:11,126][98559] Updated weights for policy 0, policy_version 92520 (0.0009) -[2023-10-11 00:32:11,500][98559] Updated weights for policy 0, policy_version 92530 (0.0010) -[2023-10-11 00:32:11,860][98559] Updated weights for policy 0, policy_version 92540 (0.0009) -[2023-10-11 00:32:13,055][98560] Updated weights for policy 1, policy_version 91912 (0.0008) -[2023-10-11 00:32:13,425][98560] Updated weights for policy 1, policy_version 91922 (0.0007) -[2023-10-11 00:32:13,793][98560] Updated weights for policy 1, policy_version 91932 (0.0007) -[2023-10-11 00:32:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 188907520. Throughput: 0: 1729.1, 1: 1687.0. Samples: 47235684. Policy #0 lag: (min: 10.0, avg: 12.8, max: 35.0) -[2023-10-11 00:32:15,557][97672] Avg episode reward: [(0, '-0.460'), (1, '22.640')] -[2023-10-11 00:32:15,794][98559] Updated weights for policy 0, policy_version 92550 (0.0009) -[2023-10-11 00:32:16,168][98559] Updated weights for policy 0, policy_version 92560 (0.0011) -[2023-10-11 00:32:16,541][98559] Updated weights for policy 0, policy_version 92570 (0.0009) -[2023-10-11 00:32:17,812][98560] Updated weights for policy 1, policy_version 91942 (0.0008) -[2023-10-11 00:32:18,169][98560] Updated weights for policy 1, policy_version 91952 (0.0008) -[2023-10-11 00:32:18,548][98560] Updated weights for policy 1, policy_version 91962 (0.0007) -[2023-10-11 00:32:20,498][98559] Updated weights for policy 0, policy_version 92580 (0.0009) -[2023-10-11 00:32:20,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 188973056. Throughput: 0: 1721.4, 1: 1694.4. Samples: 47256524. Policy #0 lag: (min: 10.0, avg: 12.8, max: 35.0) -[2023-10-11 00:32:20,556][97672] Avg episode reward: [(0, '-0.460'), (1, '22.540')] -[2023-10-11 00:32:20,857][98559] Updated weights for policy 0, policy_version 92590 (0.0009) -[2023-10-11 00:32:21,232][98559] Updated weights for policy 0, policy_version 92600 (0.0009) -[2023-10-11 00:32:22,412][98560] Updated weights for policy 1, policy_version 91972 (0.0009) -[2023-10-11 00:32:22,775][98560] Updated weights for policy 1, policy_version 91982 (0.0009) -[2023-10-11 00:32:23,143][98560] Updated weights for policy 1, policy_version 91992 (0.0010) -[2023-10-11 00:32:24,974][98559] Updated weights for policy 0, policy_version 92610 (0.0008) -[2023-10-11 00:32:25,340][98559] Updated weights for policy 0, policy_version 92620 (0.0008) -[2023-10-11 00:32:25,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 189038592. Throughput: 0: 1718.7, 1: 1705.3. Samples: 47266786. Policy #0 lag: (min: 10.0, avg: 12.8, max: 35.0) -[2023-10-11 00:32:25,556][97672] Avg episode reward: [(0, '-0.460'), (1, '22.560')] -[2023-10-11 00:32:25,701][98559] Updated weights for policy 0, policy_version 92630 (0.0010) -[2023-10-11 00:32:26,080][98559] Updated weights for policy 0, policy_version 92640 (0.0009) -[2023-10-11 00:32:27,206][98560] Updated weights for policy 1, policy_version 92002 (0.0008) -[2023-10-11 00:32:27,578][98560] Updated weights for policy 1, policy_version 92012 (0.0009) -[2023-10-11 00:32:27,946][98560] Updated weights for policy 1, policy_version 92022 (0.0007) -[2023-10-11 00:32:28,314][98560] Updated weights for policy 1, policy_version 92032 (0.0007) -[2023-10-11 00:32:29,977][98559] Updated weights for policy 0, policy_version 92650 (0.0008) -[2023-10-11 00:32:30,349][98559] Updated weights for policy 0, policy_version 92660 (0.0007) -[2023-10-11 00:32:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 189104128. Throughput: 0: 1726.9, 1: 1682.7. Samples: 47287166. Policy #0 lag: (min: 10.0, avg: 12.8, max: 35.0) -[2023-10-11 00:32:30,557][97672] Avg episode reward: [(0, '-0.460'), (1, '22.540')] -[2023-10-11 00:32:30,720][98559] Updated weights for policy 0, policy_version 92670 (0.0007) -[2023-10-11 00:32:32,270][98560] Updated weights for policy 1, policy_version 92042 (0.0010) -[2023-10-11 00:32:32,640][98560] Updated weights for policy 1, policy_version 92052 (0.0008) -[2023-10-11 00:32:32,999][98560] Updated weights for policy 1, policy_version 92062 (0.0011) -[2023-10-11 00:32:34,623][98559] Updated weights for policy 0, policy_version 92680 (0.0008) -[2023-10-11 00:32:34,987][98559] Updated weights for policy 0, policy_version 92690 (0.0008) -[2023-10-11 00:32:35,352][98559] Updated weights for policy 0, policy_version 92700 (0.0008) -[2023-10-11 00:32:35,556][97672] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 189202432. Throughput: 0: 1701.7, 1: 1705.3. Samples: 47307334. Policy #0 lag: (min: 10.0, avg: 12.8, max: 35.0) -[2023-10-11 00:32:35,557][97672] Avg episode reward: [(0, '-0.460'), (1, '22.440')] -[2023-10-11 00:32:35,569][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000092064_94273536.pth... -[2023-10-11 00:32:35,569][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000092704_94928896.pth... -[2023-10-11 00:32:35,608][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000091104_93290496.pth -[2023-10-11 00:32:35,611][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000090496_92667904.pth -[2023-10-11 00:32:36,978][98560] Updated weights for policy 1, policy_version 92072 (0.0008) -[2023-10-11 00:32:37,350][98560] Updated weights for policy 1, policy_version 92082 (0.0010) -[2023-10-11 00:32:37,715][98560] Updated weights for policy 1, policy_version 92092 (0.0010) -[2023-10-11 00:32:39,465][98559] Updated weights for policy 0, policy_version 92710 (0.0008) -[2023-10-11 00:32:39,831][98559] Updated weights for policy 0, policy_version 92720 (0.0009) -[2023-10-11 00:32:40,201][98559] Updated weights for policy 0, policy_version 92730 (0.0010) -[2023-10-11 00:32:40,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 189267968. Throughput: 0: 1730.6, 1: 1688.1. Samples: 47318054. Policy #0 lag: (min: 31.0, avg: 32.1, max: 54.0) -[2023-10-11 00:32:40,557][97672] Avg episode reward: [(0, '-0.480'), (1, '22.460')] -[2023-10-11 00:32:41,689][98560] Updated weights for policy 1, policy_version 92102 (0.0010) -[2023-10-11 00:32:42,053][98560] Updated weights for policy 1, policy_version 92112 (0.0009) -[2023-10-11 00:32:42,426][98560] Updated weights for policy 1, policy_version 92122 (0.0007) -[2023-10-11 00:32:44,120][98559] Updated weights for policy 0, policy_version 92740 (0.0008) -[2023-10-11 00:32:44,484][98559] Updated weights for policy 0, policy_version 92750 (0.0010) -[2023-10-11 00:32:44,853][98559] Updated weights for policy 0, policy_version 92760 (0.0010) -[2023-10-11 00:32:45,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 189333504. Throughput: 0: 1725.4, 1: 1697.4. Samples: 47338734. Policy #0 lag: (min: 31.0, avg: 32.1, max: 54.0) -[2023-10-11 00:32:45,557][97672] Avg episode reward: [(0, '-0.500'), (1, '22.480')] -[2023-10-11 00:32:46,678][98560] Updated weights for policy 1, policy_version 92132 (0.0007) -[2023-10-11 00:32:47,092][98560] Updated weights for policy 1, policy_version 92142 (0.0008) -[2023-10-11 00:32:47,451][98560] Updated weights for policy 1, policy_version 92152 (0.0007) -[2023-10-11 00:32:48,916][98559] Updated weights for policy 0, policy_version 92770 (0.0010) -[2023-10-11 00:32:49,278][98559] Updated weights for policy 0, policy_version 92780 (0.0009) -[2023-10-11 00:32:49,648][98559] Updated weights for policy 0, policy_version 92790 (0.0009) -[2023-10-11 00:32:50,013][98559] Updated weights for policy 0, policy_version 92800 (0.0008) -[2023-10-11 00:32:50,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 189399040. Throughput: 0: 1703.4, 1: 1712.1. Samples: 47358710. Policy #0 lag: (min: 31.0, avg: 32.1, max: 54.0) -[2023-10-11 00:32:50,557][97672] Avg episode reward: [(0, '-0.460'), (1, '22.480')] -[2023-10-11 00:32:51,508][98560] Updated weights for policy 1, policy_version 92162 (0.0009) -[2023-10-11 00:32:51,876][98560] Updated weights for policy 1, policy_version 92172 (0.0007) -[2023-10-11 00:32:52,250][98560] Updated weights for policy 1, policy_version 92182 (0.0008) -[2023-10-11 00:32:52,611][98560] Updated weights for policy 1, policy_version 92192 (0.0007) -[2023-10-11 00:32:54,138][98559] Updated weights for policy 0, policy_version 92810 (0.0008) -[2023-10-11 00:32:54,501][98559] Updated weights for policy 0, policy_version 92820 (0.0007) -[2023-10-11 00:32:54,871][98559] Updated weights for policy 0, policy_version 92830 (0.0008) -[2023-10-11 00:32:55,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 189464576. Throughput: 0: 1735.8, 1: 1680.6. Samples: 47369234. Policy #0 lag: (min: 31.0, avg: 32.1, max: 54.0) -[2023-10-11 00:32:55,556][97672] Avg episode reward: [(0, '-0.460'), (1, '22.460')] -[2023-10-11 00:32:56,582][98560] Updated weights for policy 1, policy_version 92202 (0.0011) -[2023-10-11 00:32:56,945][98560] Updated weights for policy 1, policy_version 92212 (0.0010) -[2023-10-11 00:32:57,315][98560] Updated weights for policy 1, policy_version 92222 (0.0008) -[2023-10-11 00:32:58,708][98559] Updated weights for policy 0, policy_version 92840 (0.0008) -[2023-10-11 00:32:59,079][98559] Updated weights for policy 0, policy_version 92850 (0.0009) -[2023-10-11 00:32:59,448][98559] Updated weights for policy 0, policy_version 92860 (0.0009) -[2023-10-11 00:33:00,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 189530112. Throughput: 0: 1715.6, 1: 1699.2. Samples: 47389350. Policy #0 lag: (min: 31.0, avg: 32.1, max: 54.0) -[2023-10-11 00:33:00,556][97672] Avg episode reward: [(0, '-0.460'), (1, '22.480')] -[2023-10-11 00:33:01,355][98560] Updated weights for policy 1, policy_version 92232 (0.0007) -[2023-10-11 00:33:01,727][98560] Updated weights for policy 1, policy_version 92242 (0.0007) -[2023-10-11 00:33:02,089][98560] Updated weights for policy 1, policy_version 92252 (0.0007) -[2023-10-11 00:33:03,436][98559] Updated weights for policy 0, policy_version 92870 (0.0010) -[2023-10-11 00:33:03,804][98559] Updated weights for policy 0, policy_version 92880 (0.0010) -[2023-10-11 00:33:04,170][98559] Updated weights for policy 0, policy_version 92890 (0.0007) -[2023-10-11 00:33:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 189595648. Throughput: 0: 1711.5, 1: 1705.2. Samples: 47410276. Policy #0 lag: (min: 31.0, avg: 32.1, max: 54.0) -[2023-10-11 00:33:05,556][97672] Avg episode reward: [(0, '-0.500'), (1, '22.520')] -[2023-10-11 00:33:06,010][98560] Updated weights for policy 1, policy_version 92262 (0.0009) -[2023-10-11 00:33:06,376][98560] Updated weights for policy 1, policy_version 92272 (0.0009) -[2023-10-11 00:33:06,741][98560] Updated weights for policy 1, policy_version 92282 (0.0009) -[2023-10-11 00:33:08,168][98559] Updated weights for policy 0, policy_version 92900 (0.0009) -[2023-10-11 00:33:08,540][98559] Updated weights for policy 0, policy_version 92910 (0.0008) -[2023-10-11 00:33:08,914][98559] Updated weights for policy 0, policy_version 92920 (0.0011) -[2023-10-11 00:33:10,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 189661184. Throughput: 0: 1730.3, 1: 1682.7. Samples: 47420368. Policy #0 lag: (min: 31.0, avg: 32.1, max: 54.0) -[2023-10-11 00:33:10,557][97672] Avg episode reward: [(0, '-0.500'), (1, '22.520')] -[2023-10-11 00:33:10,754][98560] Updated weights for policy 1, policy_version 92292 (0.0007) -[2023-10-11 00:33:11,132][98560] Updated weights for policy 1, policy_version 92302 (0.0007) -[2023-10-11 00:33:11,493][98560] Updated weights for policy 1, policy_version 92312 (0.0008) -[2023-10-11 00:33:12,955][98559] Updated weights for policy 0, policy_version 92930 (0.0007) -[2023-10-11 00:33:13,317][98559] Updated weights for policy 0, policy_version 92940 (0.0009) -[2023-10-11 00:33:13,696][98559] Updated weights for policy 0, policy_version 92950 (0.0008) -[2023-10-11 00:33:14,053][98559] Updated weights for policy 0, policy_version 92960 (0.0007) -[2023-10-11 00:33:15,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 189726720. Throughput: 0: 1701.8, 1: 1701.3. Samples: 47440306. Policy #0 lag: (min: 31.0, avg: 32.1, max: 54.0) -[2023-10-11 00:33:15,557][97672] Avg episode reward: [(0, '-0.500'), (1, '22.520')] -[2023-10-11 00:33:15,592][98560] Updated weights for policy 1, policy_version 92322 (0.0010) -[2023-10-11 00:33:15,961][98560] Updated weights for policy 1, policy_version 92332 (0.0008) -[2023-10-11 00:33:16,324][98560] Updated weights for policy 1, policy_version 92342 (0.0007) -[2023-10-11 00:33:16,683][98560] Updated weights for policy 1, policy_version 92352 (0.0008) -[2023-10-11 00:33:18,012][98559] Updated weights for policy 0, policy_version 92970 (0.0010) -[2023-10-11 00:33:18,381][98559] Updated weights for policy 0, policy_version 92980 (0.0007) -[2023-10-11 00:33:18,745][98559] Updated weights for policy 0, policy_version 92990 (0.0008) -[2023-10-11 00:33:20,484][98560] Updated weights for policy 1, policy_version 92362 (0.0009) -[2023-10-11 00:33:20,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 189792256. Throughput: 0: 1724.6, 1: 1703.6. Samples: 47461600. Policy #0 lag: (min: 31.0, avg: 32.1, max: 54.0) -[2023-10-11 00:33:20,557][97672] Avg episode reward: [(0, '-0.500'), (1, '22.580')] -[2023-10-11 00:33:20,861][98560] Updated weights for policy 1, policy_version 92372 (0.0008) -[2023-10-11 00:33:21,238][98560] Updated weights for policy 1, policy_version 92382 (0.0010) -[2023-10-11 00:33:22,600][98559] Updated weights for policy 0, policy_version 93000 (0.0007) -[2023-10-11 00:33:22,962][98559] Updated weights for policy 0, policy_version 93010 (0.0011) -[2023-10-11 00:33:23,326][98559] Updated weights for policy 0, policy_version 93020 (0.0008) -[2023-10-11 00:33:25,282][98560] Updated weights for policy 1, policy_version 92392 (0.0008) -[2023-10-11 00:33:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 189857792. Throughput: 0: 1707.0, 1: 1696.0. Samples: 47471190. Policy #0 lag: (min: 31.0, avg: 32.1, max: 54.0) -[2023-10-11 00:33:25,557][97672] Avg episode reward: [(0, '-0.500'), (1, '22.560')] -[2023-10-11 00:33:25,656][98560] Updated weights for policy 1, policy_version 92402 (0.0007) -[2023-10-11 00:33:26,019][98560] Updated weights for policy 1, policy_version 92412 (0.0007) -[2023-10-11 00:33:27,256][98559] Updated weights for policy 0, policy_version 93030 (0.0009) -[2023-10-11 00:33:27,637][98559] Updated weights for policy 0, policy_version 93040 (0.0008) -[2023-10-11 00:33:28,004][98559] Updated weights for policy 0, policy_version 93050 (0.0009) -[2023-10-11 00:33:29,859][98560] Updated weights for policy 1, policy_version 92422 (0.0007) -[2023-10-11 00:33:30,222][98560] Updated weights for policy 1, policy_version 92432 (0.0008) -[2023-10-11 00:33:30,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 189923328. Throughput: 0: 1706.1, 1: 1705.5. Samples: 47492258. Policy #0 lag: (min: 31.0, avg: 32.1, max: 54.0) -[2023-10-11 00:33:30,556][97672] Avg episode reward: [(0, '-0.500'), (1, '22.540')] -[2023-10-11 00:33:30,594][98560] Updated weights for policy 1, policy_version 92442 (0.0011) -[2023-10-11 00:33:31,906][98559] Updated weights for policy 0, policy_version 93060 (0.0008) -[2023-10-11 00:33:32,273][98559] Updated weights for policy 0, policy_version 93070 (0.0009) -[2023-10-11 00:33:32,634][98559] Updated weights for policy 0, policy_version 93080 (0.0011) -[2023-10-11 00:33:34,788][98560] Updated weights for policy 1, policy_version 92452 (0.0010) -[2023-10-11 00:33:35,191][98560] Updated weights for policy 1, policy_version 92462 (0.0008) -[2023-10-11 00:33:35,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 13662.6). Total num frames: 189988864. Throughput: 0: 1726.5, 1: 1706.6. Samples: 47513198. Policy #0 lag: (min: 31.0, avg: 32.1, max: 54.0) -[2023-10-11 00:33:35,556][97672] Avg episode reward: [(0, '-0.500'), (1, '22.560')] -[2023-10-11 00:33:35,561][98560] Updated weights for policy 1, policy_version 92472 (0.0008) -[2023-10-11 00:33:36,603][98559] Updated weights for policy 0, policy_version 93090 (0.0009) -[2023-10-11 00:33:36,964][98559] Updated weights for policy 0, policy_version 93100 (0.0011) -[2023-10-11 00:33:37,333][98559] Updated weights for policy 0, policy_version 93110 (0.0009) -[2023-10-11 00:33:37,709][98559] Updated weights for policy 0, policy_version 93120 (0.0007) -[2023-10-11 00:33:39,558][98560] Updated weights for policy 1, policy_version 92482 (0.0008) -[2023-10-11 00:33:39,934][98560] Updated weights for policy 1, policy_version 92492 (0.0008) -[2023-10-11 00:33:40,292][98560] Updated weights for policy 1, policy_version 92502 (0.0009) -[2023-10-11 00:33:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 190054400. Throughput: 0: 1695.7, 1: 1711.0. Samples: 47522536. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) -[2023-10-11 00:33:40,556][97672] Avg episode reward: [(0, '-0.520'), (1, '22.600')] -[2023-10-11 00:33:40,653][98560] Updated weights for policy 1, policy_version 92512 (0.0011) -[2023-10-11 00:33:41,573][98559] Updated weights for policy 0, policy_version 93130 (0.0008) -[2023-10-11 00:33:41,942][98559] Updated weights for policy 0, policy_version 93140 (0.0010) -[2023-10-11 00:33:42,307][98559] Updated weights for policy 0, policy_version 93150 (0.0009) -[2023-10-11 00:33:44,605][98560] Updated weights for policy 1, policy_version 92522 (0.0008) -[2023-10-11 00:33:44,978][98560] Updated weights for policy 1, policy_version 92532 (0.0008) -[2023-10-11 00:33:45,340][98560] Updated weights for policy 1, policy_version 92542 (0.0007) -[2023-10-11 00:33:45,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 190152704. Throughput: 0: 1719.1, 1: 1713.9. Samples: 47543832. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) -[2023-10-11 00:33:45,556][97672] Avg episode reward: [(0, '-0.520'), (1, '22.560')] -[2023-10-11 00:33:46,391][98559] Updated weights for policy 0, policy_version 93160 (0.0008) -[2023-10-11 00:33:46,752][98559] Updated weights for policy 0, policy_version 93170 (0.0009) -[2023-10-11 00:33:47,113][98559] Updated weights for policy 0, policy_version 93180 (0.0009) -[2023-10-11 00:33:49,380][98560] Updated weights for policy 1, policy_version 92552 (0.0009) -[2023-10-11 00:33:49,751][98560] Updated weights for policy 1, policy_version 92562 (0.0009) -[2023-10-11 00:33:50,126][98560] Updated weights for policy 1, policy_version 92572 (0.0009) -[2023-10-11 00:33:50,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 190218240. Throughput: 0: 1729.6, 1: 1693.2. Samples: 47564304. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) -[2023-10-11 00:33:50,556][97672] Avg episode reward: [(0, '-0.520'), (1, '22.580')] -[2023-10-11 00:33:51,010][98559] Updated weights for policy 0, policy_version 93190 (0.0007) -[2023-10-11 00:33:51,368][98559] Updated weights for policy 0, policy_version 93200 (0.0007) -[2023-10-11 00:33:51,728][98559] Updated weights for policy 0, policy_version 93210 (0.0010) -[2023-10-11 00:33:54,121][98560] Updated weights for policy 1, policy_version 92582 (0.0008) -[2023-10-11 00:33:54,486][98560] Updated weights for policy 1, policy_version 92592 (0.0009) -[2023-10-11 00:33:54,858][98560] Updated weights for policy 1, policy_version 92602 (0.0011) -[2023-10-11 00:33:55,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 190283776. Throughput: 0: 1708.2, 1: 1714.8. Samples: 47574402. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) -[2023-10-11 00:33:55,557][97672] Avg episode reward: [(0, '-0.520'), (1, '22.620')] -[2023-10-11 00:33:55,660][98559] Updated weights for policy 0, policy_version 93220 (0.0010) -[2023-10-11 00:33:56,024][98559] Updated weights for policy 0, policy_version 93230 (0.0007) -[2023-10-11 00:33:56,397][98559] Updated weights for policy 0, policy_version 93240 (0.0010) -[2023-10-11 00:33:58,907][98560] Updated weights for policy 1, policy_version 92612 (0.0008) -[2023-10-11 00:33:59,269][98560] Updated weights for policy 1, policy_version 92622 (0.0007) -[2023-10-11 00:33:59,636][98560] Updated weights for policy 1, policy_version 92632 (0.0008) -[2023-10-11 00:34:00,407][98559] Updated weights for policy 0, policy_version 93250 (0.0009) -[2023-10-11 00:34:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 190349312. Throughput: 0: 1734.9, 1: 1715.8. Samples: 47595588. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) -[2023-10-11 00:34:00,556][97672] Avg episode reward: [(0, '-0.520'), (1, '22.620')] -[2023-10-11 00:34:00,777][98559] Updated weights for policy 0, policy_version 93260 (0.0009) -[2023-10-11 00:34:01,138][98559] Updated weights for policy 0, policy_version 93270 (0.0008) -[2023-10-11 00:34:01,508][98559] Updated weights for policy 0, policy_version 93280 (0.0010) -[2023-10-11 00:34:03,641][98560] Updated weights for policy 1, policy_version 92642 (0.0008) -[2023-10-11 00:34:04,001][98560] Updated weights for policy 1, policy_version 92652 (0.0008) -[2023-10-11 00:34:04,364][98560] Updated weights for policy 1, policy_version 92662 (0.0007) -[2023-10-11 00:34:04,730][98560] Updated weights for policy 1, policy_version 92672 (0.0010) -[2023-10-11 00:34:05,352][98559] Updated weights for policy 0, policy_version 93290 (0.0009) -[2023-10-11 00:34:05,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 190414848. Throughput: 0: 1723.4, 1: 1688.0. Samples: 47615112. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) -[2023-10-11 00:34:05,557][97672] Avg episode reward: [(0, '-0.520'), (1, '22.580')] -[2023-10-11 00:34:05,730][98559] Updated weights for policy 0, policy_version 93300 (0.0009) -[2023-10-11 00:34:06,101][98559] Updated weights for policy 0, policy_version 93310 (0.0009) -[2023-10-11 00:34:08,797][98560] Updated weights for policy 1, policy_version 92682 (0.0008) -[2023-10-11 00:34:09,166][98560] Updated weights for policy 1, policy_version 92692 (0.0008) -[2023-10-11 00:34:09,535][98560] Updated weights for policy 1, policy_version 92702 (0.0007) -[2023-10-11 00:34:10,045][98559] Updated weights for policy 0, policy_version 93320 (0.0008) -[2023-10-11 00:34:10,408][98559] Updated weights for policy 0, policy_version 93330 (0.0009) -[2023-10-11 00:34:10,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 190480384. Throughput: 0: 1722.3, 1: 1714.4. Samples: 47625842. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) -[2023-10-11 00:34:10,557][97672] Avg episode reward: [(0, '-0.500'), (1, '22.500')] -[2023-10-11 00:34:10,778][98559] Updated weights for policy 0, policy_version 93340 (0.0010) -[2023-10-11 00:34:13,566][98560] Updated weights for policy 1, policy_version 92712 (0.0009) -[2023-10-11 00:34:13,936][98560] Updated weights for policy 1, policy_version 92722 (0.0008) -[2023-10-11 00:34:14,299][98560] Updated weights for policy 1, policy_version 92732 (0.0008) -[2023-10-11 00:34:14,764][98559] Updated weights for policy 0, policy_version 93350 (0.0010) -[2023-10-11 00:34:15,146][98559] Updated weights for policy 0, policy_version 93360 (0.0007) -[2023-10-11 00:34:15,509][98559] Updated weights for policy 0, policy_version 93370 (0.0008) -[2023-10-11 00:34:15,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 190545920. Throughput: 0: 1733.6, 1: 1699.2. Samples: 47646730. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) -[2023-10-11 00:34:15,557][97672] Avg episode reward: [(0, '-0.500'), (1, '22.480')] -[2023-10-11 00:34:18,273][98560] Updated weights for policy 1, policy_version 92742 (0.0008) -[2023-10-11 00:34:18,647][98560] Updated weights for policy 1, policy_version 92752 (0.0008) -[2023-10-11 00:34:19,008][98560] Updated weights for policy 1, policy_version 92762 (0.0009) -[2023-10-11 00:34:19,343][98559] Updated weights for policy 0, policy_version 93380 (0.0008) -[2023-10-11 00:34:19,714][98559] Updated weights for policy 0, policy_version 93390 (0.0007) -[2023-10-11 00:34:20,076][98559] Updated weights for policy 0, policy_version 93400 (0.0007) -[2023-10-11 00:34:20,556][97672] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 190644224. Throughput: 0: 1706.1, 1: 1685.8. Samples: 47665834. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) -[2023-10-11 00:34:20,557][97672] Avg episode reward: [(0, '-0.500'), (1, '22.400')] -[2023-10-11 00:34:23,142][98560] Updated weights for policy 1, policy_version 92772 (0.0007) -[2023-10-11 00:34:23,544][98560] Updated weights for policy 1, policy_version 92782 (0.0008) -[2023-10-11 00:34:23,914][98560] Updated weights for policy 1, policy_version 92792 (0.0008) -[2023-10-11 00:34:24,023][98559] Updated weights for policy 0, policy_version 93410 (0.0008) -[2023-10-11 00:34:24,397][98559] Updated weights for policy 0, policy_version 93420 (0.0009) -[2023-10-11 00:34:24,759][98559] Updated weights for policy 0, policy_version 93430 (0.0010) -[2023-10-11 00:34:25,128][98559] Updated weights for policy 0, policy_version 93440 (0.0008) -[2023-10-11 00:34:25,556][97672] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 190709760. Throughput: 0: 1733.4, 1: 1709.3. Samples: 47677458. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) -[2023-10-11 00:34:25,557][97672] Avg episode reward: [(0, '-0.500'), (1, '22.340')] -[2023-10-11 00:34:27,938][98560] Updated weights for policy 1, policy_version 92802 (0.0009) -[2023-10-11 00:34:28,302][98560] Updated weights for policy 1, policy_version 92812 (0.0009) -[2023-10-11 00:34:28,680][98560] Updated weights for policy 1, policy_version 92822 (0.0008) -[2023-10-11 00:34:29,049][98560] Updated weights for policy 1, policy_version 92832 (0.0009) -[2023-10-11 00:34:29,268][98559] Updated weights for policy 0, policy_version 93450 (0.0008) -[2023-10-11 00:34:29,642][98559] Updated weights for policy 0, policy_version 93460 (0.0011) -[2023-10-11 00:34:30,001][98559] Updated weights for policy 0, policy_version 93470 (0.0009) -[2023-10-11 00:34:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 190775296. Throughput: 0: 1717.7, 1: 1683.3. Samples: 47696880. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) -[2023-10-11 00:34:30,558][97672] Avg episode reward: [(0, '-0.500'), (1, '22.340')] -[2023-10-11 00:34:33,291][98560] Updated weights for policy 1, policy_version 92842 (0.0009) -[2023-10-11 00:34:33,664][98560] Updated weights for policy 1, policy_version 92852 (0.0008) -[2023-10-11 00:34:34,022][98560] Updated weights for policy 1, policy_version 92862 (0.0007) -[2023-10-11 00:34:34,045][98559] Updated weights for policy 0, policy_version 93480 (0.0007) -[2023-10-11 00:34:34,417][98559] Updated weights for policy 0, policy_version 93490 (0.0008) -[2023-10-11 00:34:34,789][98559] Updated weights for policy 0, policy_version 93500 (0.0009) -[2023-10-11 00:34:35,556][97672] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 190840832. Throughput: 0: 1697.6, 1: 1685.1. Samples: 47716522. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) -[2023-10-11 00:34:35,556][97672] Avg episode reward: [(0, '-0.500'), (1, '22.420')] -[2023-10-11 00:34:35,566][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000092864_95092736.pth... -[2023-10-11 00:34:35,567][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000093504_95748096.pth... -[2023-10-11 00:34:35,602][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000091904_94109696.pth -[2023-10-11 00:34:35,606][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000091264_93454336.pth -[2023-10-11 00:34:37,931][98560] Updated weights for policy 1, policy_version 92872 (0.0008) -[2023-10-11 00:34:38,302][98560] Updated weights for policy 1, policy_version 92882 (0.0010) -[2023-10-11 00:34:38,666][98560] Updated weights for policy 1, policy_version 92892 (0.0009) -[2023-10-11 00:34:38,745][98559] Updated weights for policy 0, policy_version 93510 (0.0008) -[2023-10-11 00:34:39,118][98559] Updated weights for policy 0, policy_version 93520 (0.0009) -[2023-10-11 00:34:39,485][98559] Updated weights for policy 0, policy_version 93530 (0.0011) -[2023-10-11 00:34:40,556][97672] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 190906368. Throughput: 0: 1727.8, 1: 1694.8. Samples: 47728418. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-11 00:34:40,557][97672] Avg episode reward: [(0, '-0.480'), (1, '22.400')] -[2023-10-11 00:34:42,745][98560] Updated weights for policy 1, policy_version 92902 (0.0008) -[2023-10-11 00:34:43,111][98560] Updated weights for policy 1, policy_version 92912 (0.0007) -[2023-10-11 00:34:43,484][98560] Updated weights for policy 1, policy_version 92922 (0.0007) -[2023-10-11 00:34:43,575][98559] Updated weights for policy 0, policy_version 93540 (0.0009) -[2023-10-11 00:34:43,939][98559] Updated weights for policy 0, policy_version 93550 (0.0008) -[2023-10-11 00:34:44,311][98559] Updated weights for policy 0, policy_version 93560 (0.0009) -[2023-10-11 00:34:45,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 190971904. Throughput: 0: 1698.9, 1: 1669.2. Samples: 47747152. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-11 00:34:45,556][97672] Avg episode reward: [(0, '-0.480'), (1, '22.440')] -[2023-10-11 00:34:47,636][98560] Updated weights for policy 1, policy_version 92932 (0.0008) -[2023-10-11 00:34:47,999][98560] Updated weights for policy 1, policy_version 92942 (0.0010) -[2023-10-11 00:34:48,326][98559] Updated weights for policy 0, policy_version 93570 (0.0010) -[2023-10-11 00:34:48,364][98560] Updated weights for policy 1, policy_version 92952 (0.0009) -[2023-10-11 00:34:48,697][98559] Updated weights for policy 0, policy_version 93580 (0.0010) -[2023-10-11 00:34:49,061][98559] Updated weights for policy 0, policy_version 93590 (0.0009) -[2023-10-11 00:34:49,428][98559] Updated weights for policy 0, policy_version 93600 (0.0008) -[2023-10-11 00:34:50,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 191037440. Throughput: 0: 1698.6, 1: 1694.8. Samples: 47767816. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-11 00:34:50,557][97672] Avg episode reward: [(0, '-0.480'), (1, '22.440')] -[2023-10-11 00:34:52,276][98560] Updated weights for policy 1, policy_version 92962 (0.0007) -[2023-10-11 00:34:52,650][98560] Updated weights for policy 1, policy_version 92972 (0.0008) -[2023-10-11 00:34:53,010][98560] Updated weights for policy 1, policy_version 92982 (0.0008) -[2023-10-11 00:34:53,379][98560] Updated weights for policy 1, policy_version 92992 (0.0008) -[2023-10-11 00:34:53,459][98559] Updated weights for policy 0, policy_version 93610 (0.0009) -[2023-10-11 00:34:53,836][98559] Updated weights for policy 0, policy_version 93620 (0.0008) -[2023-10-11 00:34:54,200][98559] Updated weights for policy 0, policy_version 93630 (0.0007) -[2023-10-11 00:34:55,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 191102976. Throughput: 0: 1712.3, 1: 1686.3. Samples: 47778782. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-11 00:34:55,557][97672] Avg episode reward: [(0, '-0.480'), (1, '22.540')] -[2023-10-11 00:34:57,372][98560] Updated weights for policy 1, policy_version 93002 (0.0009) -[2023-10-11 00:34:57,738][98560] Updated weights for policy 1, policy_version 93012 (0.0007) -[2023-10-11 00:34:58,088][98559] Updated weights for policy 0, policy_version 93640 (0.0008) -[2023-10-11 00:34:58,097][98560] Updated weights for policy 1, policy_version 93022 (0.0009) -[2023-10-11 00:34:58,445][98559] Updated weights for policy 0, policy_version 93650 (0.0008) -[2023-10-11 00:34:58,807][98559] Updated weights for policy 0, policy_version 93660 (0.0007) -[2023-10-11 00:35:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 191168512. Throughput: 0: 1688.3, 1: 1678.6. Samples: 47798242. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-11 00:35:00,556][97672] Avg episode reward: [(0, '-0.480'), (1, '22.520')] -[2023-10-11 00:35:02,014][98560] Updated weights for policy 1, policy_version 93032 (0.0007) -[2023-10-11 00:35:02,380][98560] Updated weights for policy 1, policy_version 93042 (0.0008) -[2023-10-11 00:35:02,750][98560] Updated weights for policy 1, policy_version 93052 (0.0007) -[2023-10-11 00:35:02,787][98559] Updated weights for policy 0, policy_version 93670 (0.0008) -[2023-10-11 00:35:03,153][98559] Updated weights for policy 0, policy_version 93680 (0.0007) -[2023-10-11 00:35:03,518][98559] Updated weights for policy 0, policy_version 93690 (0.0009) -[2023-10-11 00:35:05,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 191234048. Throughput: 0: 1715.0, 1: 1696.5. Samples: 47819350. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-11 00:35:05,557][97672] Avg episode reward: [(0, '-0.480'), (1, '22.580')] -[2023-10-11 00:35:06,852][98560] Updated weights for policy 1, policy_version 93062 (0.0009) -[2023-10-11 00:35:07,221][98560] Updated weights for policy 1, policy_version 93072 (0.0011) -[2023-10-11 00:35:07,442][98559] Updated weights for policy 0, policy_version 93700 (0.0011) -[2023-10-11 00:35:07,590][98560] Updated weights for policy 1, policy_version 93082 (0.0009) -[2023-10-11 00:35:07,807][98559] Updated weights for policy 0, policy_version 93710 (0.0008) -[2023-10-11 00:35:08,179][98559] Updated weights for policy 0, policy_version 93720 (0.0009) -[2023-10-11 00:35:10,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 191299584. Throughput: 0: 1694.8, 1: 1670.3. Samples: 47828888. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-11 00:35:10,557][97672] Avg episode reward: [(0, '-0.440'), (1, '22.680')] -[2023-10-11 00:35:11,588][98560] Updated weights for policy 1, policy_version 93092 (0.0008) -[2023-10-11 00:35:11,949][98560] Updated weights for policy 1, policy_version 93102 (0.0008) -[2023-10-11 00:35:12,151][98559] Updated weights for policy 0, policy_version 93730 (0.0010) -[2023-10-11 00:35:12,314][98560] Updated weights for policy 1, policy_version 93112 (0.0009) -[2023-10-11 00:35:12,507][98559] Updated weights for policy 0, policy_version 93740 (0.0009) -[2023-10-11 00:35:12,874][98559] Updated weights for policy 0, policy_version 93750 (0.0008) -[2023-10-11 00:35:13,236][98559] Updated weights for policy 0, policy_version 93760 (0.0009) -[2023-10-11 00:35:15,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 191365120. Throughput: 0: 1702.9, 1: 1689.1. Samples: 47849522. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-11 00:35:15,557][97672] Avg episode reward: [(0, '-0.440'), (1, '22.680')] -[2023-10-11 00:35:16,456][98560] Updated weights for policy 1, policy_version 93122 (0.0009) -[2023-10-11 00:35:16,872][98560] Updated weights for policy 1, policy_version 93132 (0.0009) -[2023-10-11 00:35:17,248][98560] Updated weights for policy 1, policy_version 93142 (0.0007) -[2023-10-11 00:35:17,283][98559] Updated weights for policy 0, policy_version 93770 (0.0007) -[2023-10-11 00:35:17,608][98560] Updated weights for policy 1, policy_version 93152 (0.0008) -[2023-10-11 00:35:17,652][98559] Updated weights for policy 0, policy_version 93780 (0.0007) -[2023-10-11 00:35:18,007][98559] Updated weights for policy 0, policy_version 93790 (0.0008) -[2023-10-11 00:35:20,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 191430656. Throughput: 0: 1720.3, 1: 1695.9. Samples: 47870252. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-11 00:35:20,557][97672] Avg episode reward: [(0, '-0.460'), (1, '22.540')] -[2023-10-11 00:35:21,815][98560] Updated weights for policy 1, policy_version 93162 (0.0007) -[2023-10-11 00:35:21,923][98559] Updated weights for policy 0, policy_version 93800 (0.0008) -[2023-10-11 00:35:22,183][98560] Updated weights for policy 1, policy_version 93172 (0.0007) -[2023-10-11 00:35:22,299][98559] Updated weights for policy 0, policy_version 93810 (0.0009) -[2023-10-11 00:35:22,549][98560] Updated weights for policy 1, policy_version 93182 (0.0008) -[2023-10-11 00:35:22,666][98559] Updated weights for policy 0, policy_version 93820 (0.0008) -[2023-10-11 00:35:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13662.6). Total num frames: 191496192. Throughput: 0: 1691.3, 1: 1666.5. Samples: 47879520. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-11 00:35:25,557][97672] Avg episode reward: [(0, '-0.480'), (1, '22.460')] -[2023-10-11 00:35:26,360][98560] Updated weights for policy 1, policy_version 93192 (0.0009) -[2023-10-11 00:35:26,459][98559] Updated weights for policy 0, policy_version 93830 (0.0009) -[2023-10-11 00:35:26,738][98560] Updated weights for policy 1, policy_version 93202 (0.0008) -[2023-10-11 00:35:26,815][98559] Updated weights for policy 0, policy_version 93840 (0.0008) -[2023-10-11 00:35:27,105][98560] Updated weights for policy 1, policy_version 93212 (0.0008) -[2023-10-11 00:35:27,175][98559] Updated weights for policy 0, policy_version 93850 (0.0009) -[2023-10-11 00:35:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 191561728. Throughput: 0: 1720.5, 1: 1689.3. Samples: 47900592. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-11 00:35:30,557][97672] Avg episode reward: [(0, '-0.480'), (1, '22.400')] -[2023-10-11 00:35:31,234][98559] Updated weights for policy 0, policy_version 93860 (0.0007) -[2023-10-11 00:35:31,370][98560] Updated weights for policy 1, policy_version 93222 (0.0008) -[2023-10-11 00:35:31,605][98559] Updated weights for policy 0, policy_version 93870 (0.0007) -[2023-10-11 00:35:31,728][98560] Updated weights for policy 1, policy_version 93232 (0.0009) -[2023-10-11 00:35:31,970][98559] Updated weights for policy 0, policy_version 93880 (0.0007) -[2023-10-11 00:35:32,097][98560] Updated weights for policy 1, policy_version 93242 (0.0007) -[2023-10-11 00:35:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.1, 300 sec: 13662.6). Total num frames: 191627264. Throughput: 0: 1730.6, 1: 1689.8. Samples: 47921732. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-11 00:35:35,557][97672] Avg episode reward: [(0, '-0.480'), (1, '22.400')] -[2023-10-11 00:35:35,933][98559] Updated weights for policy 0, policy_version 93890 (0.0007) -[2023-10-11 00:35:36,006][98560] Updated weights for policy 1, policy_version 93252 (0.0007) -[2023-10-11 00:35:36,301][98559] Updated weights for policy 0, policy_version 93900 (0.0007) -[2023-10-11 00:35:36,368][98560] Updated weights for policy 1, policy_version 93262 (0.0009) -[2023-10-11 00:35:36,670][98559] Updated weights for policy 0, policy_version 93910 (0.0007) -[2023-10-11 00:35:36,733][98560] Updated weights for policy 1, policy_version 93272 (0.0008) -[2023-10-11 00:35:37,031][98559] Updated weights for policy 0, policy_version 93920 (0.0009) -[2023-10-11 00:35:40,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 191692800. Throughput: 0: 1708.0, 1: 1671.3. Samples: 47930846. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-11 00:35:40,556][97672] Avg episode reward: [(0, '-0.480'), (1, '22.420')] -[2023-10-11 00:35:40,699][98560] Updated weights for policy 1, policy_version 93282 (0.0010) -[2023-10-11 00:35:41,049][98559] Updated weights for policy 0, policy_version 93930 (0.0008) -[2023-10-11 00:35:41,072][98560] Updated weights for policy 1, policy_version 93292 (0.0008) -[2023-10-11 00:35:41,411][98559] Updated weights for policy 0, policy_version 93940 (0.0007) -[2023-10-11 00:35:41,448][98560] Updated weights for policy 1, policy_version 93302 (0.0008) -[2023-10-11 00:35:41,782][98559] Updated weights for policy 0, policy_version 93950 (0.0008) -[2023-10-11 00:35:41,821][98560] Updated weights for policy 1, policy_version 93312 (0.0008) -[2023-10-11 00:35:45,556][97672] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 191758336. Throughput: 0: 1723.2, 1: 1690.4. Samples: 47951854. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-11 00:35:45,556][97672] Avg episode reward: [(0, '-0.480'), (1, '22.460')] -[2023-10-11 00:35:45,817][98560] Updated weights for policy 1, policy_version 93322 (0.0011) -[2023-10-11 00:35:45,858][98559] Updated weights for policy 0, policy_version 93960 (0.0008) -[2023-10-11 00:35:46,188][98560] Updated weights for policy 1, policy_version 93332 (0.0007) -[2023-10-11 00:35:46,211][98559] Updated weights for policy 0, policy_version 93970 (0.0007) -[2023-10-11 00:35:46,550][98560] Updated weights for policy 1, policy_version 93342 (0.0008) -[2023-10-11 00:35:46,580][98559] Updated weights for policy 0, policy_version 93980 (0.0007) -[2023-10-11 00:35:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 191823872. Throughput: 0: 1723.3, 1: 1679.4. Samples: 47972474. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-11 00:35:50,557][97672] Avg episode reward: [(0, '-0.460'), (1, '22.440')] -[2023-10-11 00:35:50,577][98559] Updated weights for policy 0, policy_version 93990 (0.0007) -[2023-10-11 00:35:50,797][98560] Updated weights for policy 1, policy_version 93352 (0.0008) -[2023-10-11 00:35:50,964][98559] Updated weights for policy 0, policy_version 94000 (0.0009) -[2023-10-11 00:35:51,158][98560] Updated weights for policy 1, policy_version 93362 (0.0009) -[2023-10-11 00:35:51,321][98559] Updated weights for policy 0, policy_version 94010 (0.0010) -[2023-10-11 00:35:51,525][98560] Updated weights for policy 1, policy_version 93372 (0.0007) -[2023-10-11 00:35:55,299][98559] Updated weights for policy 0, policy_version 94020 (0.0009) -[2023-10-11 00:35:55,540][98560] Updated weights for policy 1, policy_version 93382 (0.0008) -[2023-10-11 00:35:55,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 191889408. Throughput: 0: 1715.8, 1: 1679.2. Samples: 47981662. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-11 00:35:55,557][97672] Avg episode reward: [(0, '-0.460'), (1, '22.360')] -[2023-10-11 00:35:55,660][98559] Updated weights for policy 0, policy_version 94030 (0.0007) -[2023-10-11 00:35:55,902][98560] Updated weights for policy 1, policy_version 93392 (0.0007) -[2023-10-11 00:35:56,022][98559] Updated weights for policy 0, policy_version 94040 (0.0007) -[2023-10-11 00:35:56,266][98560] Updated weights for policy 1, policy_version 93402 (0.0008) -[2023-10-11 00:35:59,996][98559] Updated weights for policy 0, policy_version 94050 (0.0007) -[2023-10-11 00:36:00,095][98560] Updated weights for policy 1, policy_version 93412 (0.0009) -[2023-10-11 00:36:00,358][98559] Updated weights for policy 0, policy_version 94060 (0.0009) -[2023-10-11 00:36:00,458][98560] Updated weights for policy 1, policy_version 93422 (0.0008) -[2023-10-11 00:36:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 191954944. Throughput: 0: 1721.4, 1: 1687.2. Samples: 48002910. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-11 00:36:00,556][97672] Avg episode reward: [(0, '-0.460'), (1, '22.400')] -[2023-10-11 00:36:00,717][98559] Updated weights for policy 0, policy_version 94070 (0.0007) -[2023-10-11 00:36:00,824][98560] Updated weights for policy 1, policy_version 93432 (0.0007) -[2023-10-11 00:36:01,085][98559] Updated weights for policy 0, policy_version 94080 (0.0007) -[2023-10-11 00:36:05,070][98560] Updated weights for policy 1, policy_version 93442 (0.0008) -[2023-10-11 00:36:05,148][98559] Updated weights for policy 0, policy_version 94090 (0.0008) -[2023-10-11 00:36:05,466][98560] Updated weights for policy 1, policy_version 93452 (0.0007) -[2023-10-11 00:36:05,509][98559] Updated weights for policy 0, policy_version 94100 (0.0008) -[2023-10-11 00:36:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 192020480. Throughput: 0: 1704.9, 1: 1691.1. Samples: 48023072. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-11 00:36:05,556][97672] Avg episode reward: [(0, '-0.460'), (1, '22.420')] -[2023-10-11 00:36:05,827][98560] Updated weights for policy 1, policy_version 93462 (0.0007) -[2023-10-11 00:36:05,879][98559] Updated weights for policy 0, policy_version 94110 (0.0008) -[2023-10-11 00:36:06,194][98560] Updated weights for policy 1, policy_version 93472 (0.0008) -[2023-10-11 00:36:09,948][98559] Updated weights for policy 0, policy_version 94120 (0.0008) -[2023-10-11 00:36:10,182][98560] Updated weights for policy 1, policy_version 93482 (0.0007) -[2023-10-11 00:36:10,311][98559] Updated weights for policy 0, policy_version 94130 (0.0007) -[2023-10-11 00:36:10,546][98560] Updated weights for policy 1, policy_version 93492 (0.0007) -[2023-10-11 00:36:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 192086016. Throughput: 0: 1713.7, 1: 1690.5. Samples: 48032712. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-11 00:36:10,557][97672] Avg episode reward: [(0, '-0.460'), (1, '22.440')] -[2023-10-11 00:36:10,664][98559] Updated weights for policy 0, policy_version 94140 (0.0007) -[2023-10-11 00:36:10,915][98560] Updated weights for policy 1, policy_version 93502 (0.0008) -[2023-10-11 00:36:14,832][98559] Updated weights for policy 0, policy_version 94150 (0.0008) -[2023-10-11 00:36:15,072][98560] Updated weights for policy 1, policy_version 93512 (0.0008) -[2023-10-11 00:36:15,189][98559] Updated weights for policy 0, policy_version 94160 (0.0008) -[2023-10-11 00:36:15,436][98560] Updated weights for policy 1, policy_version 93522 (0.0008) -[2023-10-11 00:36:15,555][98559] Updated weights for policy 0, policy_version 94170 (0.0009) -[2023-10-11 00:36:15,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 192151552. Throughput: 0: 1705.7, 1: 1689.8. Samples: 48053388. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-11 00:36:15,556][97672] Avg episode reward: [(0, '-0.460'), (1, '22.380')] -[2023-10-11 00:36:15,807][98560] Updated weights for policy 1, policy_version 93532 (0.0009) -[2023-10-11 00:36:19,708][98559] Updated weights for policy 0, policy_version 94180 (0.0008) -[2023-10-11 00:36:20,046][98560] Updated weights for policy 1, policy_version 93542 (0.0009) -[2023-10-11 00:36:20,066][98559] Updated weights for policy 0, policy_version 94190 (0.0007) -[2023-10-11 00:36:20,406][98560] Updated weights for policy 1, policy_version 93552 (0.0008) -[2023-10-11 00:36:20,449][98559] Updated weights for policy 0, policy_version 94200 (0.0009) -[2023-10-11 00:36:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 192217088. Throughput: 0: 1677.6, 1: 1687.6. Samples: 48073164. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-11 00:36:20,556][97672] Avg episode reward: [(0, '-0.460'), (1, '22.320')] -[2023-10-11 00:36:20,775][98560] Updated weights for policy 1, policy_version 93562 (0.0008) -[2023-10-11 00:36:24,431][98559] Updated weights for policy 0, policy_version 94210 (0.0009) -[2023-10-11 00:36:24,801][98559] Updated weights for policy 0, policy_version 94220 (0.0009) -[2023-10-11 00:36:24,871][98560] Updated weights for policy 1, policy_version 93572 (0.0007) -[2023-10-11 00:36:25,162][98559] Updated weights for policy 0, policy_version 94230 (0.0008) -[2023-10-11 00:36:25,235][98560] Updated weights for policy 1, policy_version 93582 (0.0009) -[2023-10-11 00:36:25,527][98559] Updated weights for policy 0, policy_version 94240 (0.0008) -[2023-10-11 00:36:25,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 192315392. Throughput: 0: 1697.9, 1: 1688.4. Samples: 48083228. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-11 00:36:25,556][97672] Avg episode reward: [(0, '-0.420'), (1, '22.360')] -[2023-10-11 00:36:25,597][98560] Updated weights for policy 1, policy_version 93592 (0.0008) -[2023-10-11 00:36:29,531][98559] Updated weights for policy 0, policy_version 94250 (0.0008) -[2023-10-11 00:36:29,531][98560] Updated weights for policy 1, policy_version 93602 (0.0008) -[2023-10-11 00:36:29,895][98559] Updated weights for policy 0, policy_version 94260 (0.0008) -[2023-10-11 00:36:29,900][98560] Updated weights for policy 1, policy_version 93612 (0.0008) -[2023-10-11 00:36:30,256][98559] Updated weights for policy 0, policy_version 94270 (0.0008) -[2023-10-11 00:36:30,261][98560] Updated weights for policy 1, policy_version 93622 (0.0008) -[2023-10-11 00:36:30,556][97672] Fps is (10 sec: 16383.8, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 192380928. Throughput: 0: 1698.5, 1: 1688.2. Samples: 48104258. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-11 00:36:30,557][97672] Avg episode reward: [(0, '-0.420'), (1, '22.320')] -[2023-10-11 00:36:30,635][98560] Updated weights for policy 1, policy_version 93632 (0.0009) -[2023-10-11 00:36:34,253][98559] Updated weights for policy 0, policy_version 94280 (0.0007) -[2023-10-11 00:36:34,609][98559] Updated weights for policy 0, policy_version 94290 (0.0007) -[2023-10-11 00:36:34,815][98560] Updated weights for policy 1, policy_version 93642 (0.0008) -[2023-10-11 00:36:34,984][98559] Updated weights for policy 0, policy_version 94300 (0.0009) -[2023-10-11 00:36:35,192][98560] Updated weights for policy 1, policy_version 93652 (0.0007) -[2023-10-11 00:36:35,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 192446464. Throughput: 0: 1676.9, 1: 1690.0. Samples: 48123988. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-11 00:36:35,557][97672] Avg episode reward: [(0, '-0.420'), (1, '22.340')] -[2023-10-11 00:36:35,566][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000094304_96567296.pth... -[2023-10-11 00:36:35,569][98560] Updated weights for policy 1, policy_version 93662 (0.0008) -[2023-10-11 00:36:35,601][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000092704_94928896.pth -[2023-10-11 00:36:35,633][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000093664_95911936.pth... -[2023-10-11 00:36:35,668][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000092064_94273536.pth -[2023-10-11 00:36:39,028][98559] Updated weights for policy 0, policy_version 94310 (0.0010) -[2023-10-11 00:36:39,407][98559] Updated weights for policy 0, policy_version 94320 (0.0009) -[2023-10-11 00:36:39,561][98560] Updated weights for policy 1, policy_version 93672 (0.0008) -[2023-10-11 00:36:39,764][98559] Updated weights for policy 0, policy_version 94330 (0.0009) -[2023-10-11 00:36:39,921][98560] Updated weights for policy 1, policy_version 93682 (0.0009) -[2023-10-11 00:36:40,286][98560] Updated weights for policy 1, policy_version 93692 (0.0009) -[2023-10-11 00:36:40,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 192544768. Throughput: 0: 1708.4, 1: 1694.3. Samples: 48134780. Policy #0 lag: (min: 17.0, avg: 31.0, max: 49.0) -[2023-10-11 00:36:40,557][97672] Avg episode reward: [(0, '-0.420'), (1, '22.300')] -[2023-10-11 00:36:43,578][98559] Updated weights for policy 0, policy_version 94340 (0.0008) -[2023-10-11 00:36:43,947][98559] Updated weights for policy 0, policy_version 94350 (0.0008) -[2023-10-11 00:36:44,156][98560] Updated weights for policy 1, policy_version 93702 (0.0009) -[2023-10-11 00:36:44,304][98559] Updated weights for policy 0, policy_version 94360 (0.0009) -[2023-10-11 00:36:44,526][98560] Updated weights for policy 1, policy_version 93712 (0.0009) -[2023-10-11 00:36:44,887][98560] Updated weights for policy 1, policy_version 93722 (0.0009) -[2023-10-11 00:36:45,556][97672] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 192610304. Throughput: 0: 1690.0, 1: 1693.0. Samples: 48155148. Policy #0 lag: (min: 17.0, avg: 31.0, max: 49.0) -[2023-10-11 00:36:45,557][97672] Avg episode reward: [(0, '-0.420'), (1, '22.300')] -[2023-10-11 00:36:48,105][98559] Updated weights for policy 0, policy_version 94370 (0.0009) -[2023-10-11 00:36:48,470][98559] Updated weights for policy 0, policy_version 94380 (0.0009) -[2023-10-11 00:36:48,834][98559] Updated weights for policy 0, policy_version 94390 (0.0011) -[2023-10-11 00:36:48,877][98560] Updated weights for policy 1, policy_version 93732 (0.0008) -[2023-10-11 00:36:49,201][98559] Updated weights for policy 0, policy_version 94400 (0.0008) -[2023-10-11 00:36:49,244][98560] Updated weights for policy 1, policy_version 93742 (0.0009) -[2023-10-11 00:36:49,610][98560] Updated weights for policy 1, policy_version 93752 (0.0008) -[2023-10-11 00:36:50,556][97672] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 192675840. Throughput: 0: 1702.6, 1: 1672.8. Samples: 48174964. Policy #0 lag: (min: 17.0, avg: 31.0, max: 49.0) -[2023-10-11 00:36:50,557][97672] Avg episode reward: [(0, '-0.420'), (1, '22.280')] -[2023-10-11 00:36:53,220][98559] Updated weights for policy 0, policy_version 94410 (0.0007) -[2023-10-11 00:36:53,581][98559] Updated weights for policy 0, policy_version 94420 (0.0007) -[2023-10-11 00:36:53,773][98560] Updated weights for policy 1, policy_version 93762 (0.0011) -[2023-10-11 00:36:53,949][98559] Updated weights for policy 0, policy_version 94430 (0.0007) -[2023-10-11 00:36:54,188][98560] Updated weights for policy 1, policy_version 93772 (0.0009) -[2023-10-11 00:36:54,548][98560] Updated weights for policy 1, policy_version 93782 (0.0010) -[2023-10-11 00:36:54,916][98560] Updated weights for policy 1, policy_version 93792 (0.0008) -[2023-10-11 00:36:55,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 192741376. Throughput: 0: 1708.3, 1: 1696.7. Samples: 48185936. Policy #0 lag: (min: 17.0, avg: 31.0, max: 49.0) -[2023-10-11 00:36:55,557][97672] Avg episode reward: [(0, '-0.420'), (1, '22.340')] -[2023-10-11 00:36:57,800][98559] Updated weights for policy 0, policy_version 94440 (0.0008) -[2023-10-11 00:36:58,171][98559] Updated weights for policy 0, policy_version 94450 (0.0010) -[2023-10-11 00:36:58,526][98559] Updated weights for policy 0, policy_version 94460 (0.0009) -[2023-10-11 00:36:58,862][98560] Updated weights for policy 1, policy_version 93802 (0.0008) -[2023-10-11 00:36:59,230][98560] Updated weights for policy 1, policy_version 93812 (0.0010) -[2023-10-11 00:36:59,603][98560] Updated weights for policy 1, policy_version 93822 (0.0009) -[2023-10-11 00:37:00,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 192806912. Throughput: 0: 1696.1, 1: 1692.9. Samples: 48205894. Policy #0 lag: (min: 17.0, avg: 31.0, max: 49.0) -[2023-10-11 00:37:00,556][97672] Avg episode reward: [(0, '-0.400'), (1, '22.480')] -[2023-10-11 00:37:02,318][98559] Updated weights for policy 0, policy_version 94470 (0.0009) -[2023-10-11 00:37:02,681][98559] Updated weights for policy 0, policy_version 94480 (0.0008) -[2023-10-11 00:37:03,051][98559] Updated weights for policy 0, policy_version 94490 (0.0008) -[2023-10-11 00:37:03,798][98560] Updated weights for policy 1, policy_version 93832 (0.0007) -[2023-10-11 00:37:04,165][98560] Updated weights for policy 1, policy_version 93842 (0.0007) -[2023-10-11 00:37:04,541][98560] Updated weights for policy 1, policy_version 93852 (0.0009) -[2023-10-11 00:37:05,556][97672] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 192872448. Throughput: 0: 1724.3, 1: 1670.0. Samples: 48225908. Policy #0 lag: (min: 17.0, avg: 31.0, max: 49.0) -[2023-10-11 00:37:05,558][97672] Avg episode reward: [(0, '-0.400'), (1, '22.500')] -[2023-10-11 00:37:07,117][98559] Updated weights for policy 0, policy_version 94500 (0.0010) -[2023-10-11 00:37:07,488][98559] Updated weights for policy 0, policy_version 94510 (0.0010) -[2023-10-11 00:37:07,856][98559] Updated weights for policy 0, policy_version 94520 (0.0008) -[2023-10-11 00:37:08,581][98560] Updated weights for policy 1, policy_version 93862 (0.0010) -[2023-10-11 00:37:08,944][98560] Updated weights for policy 1, policy_version 93872 (0.0007) -[2023-10-11 00:37:09,313][98560] Updated weights for policy 1, policy_version 93882 (0.0009) -[2023-10-11 00:37:10,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 192937984. Throughput: 0: 1706.0, 1: 1698.8. Samples: 48236444. Policy #0 lag: (min: 17.0, avg: 31.0, max: 49.0) -[2023-10-11 00:37:10,557][97672] Avg episode reward: [(0, '-0.400'), (1, '22.580')] -[2023-10-11 00:37:11,851][98559] Updated weights for policy 0, policy_version 94530 (0.0007) -[2023-10-11 00:37:12,216][98559] Updated weights for policy 0, policy_version 94540 (0.0010) -[2023-10-11 00:37:12,582][98559] Updated weights for policy 0, policy_version 94550 (0.0010) -[2023-10-11 00:37:12,948][98559] Updated weights for policy 0, policy_version 94560 (0.0010) -[2023-10-11 00:37:13,414][98560] Updated weights for policy 1, policy_version 93892 (0.0008) -[2023-10-11 00:37:13,784][98560] Updated weights for policy 1, policy_version 93902 (0.0008) -[2023-10-11 00:37:14,151][98560] Updated weights for policy 1, policy_version 93912 (0.0007) -[2023-10-11 00:37:15,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 193003520. Throughput: 0: 1707.7, 1: 1687.3. Samples: 48257032. Policy #0 lag: (min: 17.0, avg: 31.0, max: 49.0) -[2023-10-11 00:37:15,557][97672] Avg episode reward: [(0, '-0.420'), (1, '22.540')] -[2023-10-11 00:37:17,032][98559] Updated weights for policy 0, policy_version 94570 (0.0011) -[2023-10-11 00:37:17,402][98559] Updated weights for policy 0, policy_version 94580 (0.0009) -[2023-10-11 00:37:17,763][98559] Updated weights for policy 0, policy_version 94590 (0.0010) -[2023-10-11 00:37:18,137][98560] Updated weights for policy 1, policy_version 93922 (0.0008) -[2023-10-11 00:37:18,502][98560] Updated weights for policy 1, policy_version 93932 (0.0007) -[2023-10-11 00:37:18,872][98560] Updated weights for policy 1, policy_version 93942 (0.0008) -[2023-10-11 00:37:19,244][98560] Updated weights for policy 1, policy_version 93952 (0.0009) -[2023-10-11 00:37:20,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 193069056. Throughput: 0: 1730.5, 1: 1675.7. Samples: 48277270. Policy #0 lag: (min: 17.0, avg: 31.0, max: 49.0) -[2023-10-11 00:37:20,556][97672] Avg episode reward: [(0, '-0.420'), (1, '22.560')] -[2023-10-11 00:37:21,718][98559] Updated weights for policy 0, policy_version 94600 (0.0011) -[2023-10-11 00:37:22,095][98559] Updated weights for policy 0, policy_version 94610 (0.0009) -[2023-10-11 00:37:22,454][98559] Updated weights for policy 0, policy_version 94620 (0.0010) -[2023-10-11 00:37:23,252][98560] Updated weights for policy 1, policy_version 93962 (0.0008) -[2023-10-11 00:37:23,615][98560] Updated weights for policy 1, policy_version 93972 (0.0007) -[2023-10-11 00:37:23,985][98560] Updated weights for policy 1, policy_version 93982 (0.0009) -[2023-10-11 00:37:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 193134592. Throughput: 0: 1700.4, 1: 1702.6. Samples: 48287914. Policy #0 lag: (min: 17.0, avg: 31.0, max: 49.0) -[2023-10-11 00:37:25,557][97672] Avg episode reward: [(0, '-0.420'), (1, '22.560')] -[2023-10-11 00:37:26,556][98559] Updated weights for policy 0, policy_version 94630 (0.0009) -[2023-10-11 00:37:26,933][98559] Updated weights for policy 0, policy_version 94640 (0.0010) -[2023-10-11 00:37:27,295][98559] Updated weights for policy 0, policy_version 94650 (0.0009) -[2023-10-11 00:37:28,044][98560] Updated weights for policy 1, policy_version 93992 (0.0008) -[2023-10-11 00:37:28,421][98560] Updated weights for policy 1, policy_version 94002 (0.0008) -[2023-10-11 00:37:28,786][98560] Updated weights for policy 1, policy_version 94012 (0.0009) -[2023-10-11 00:37:30,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 193200128. Throughput: 0: 1719.7, 1: 1679.4. Samples: 48308106. Policy #0 lag: (min: 17.0, avg: 31.0, max: 49.0) -[2023-10-11 00:37:30,557][97672] Avg episode reward: [(0, '-0.420'), (1, '22.600')] -[2023-10-11 00:37:31,288][98559] Updated weights for policy 0, policy_version 94660 (0.0008) -[2023-10-11 00:37:31,660][98559] Updated weights for policy 0, policy_version 94670 (0.0008) -[2023-10-11 00:37:32,021][98559] Updated weights for policy 0, policy_version 94680 (0.0008) -[2023-10-11 00:37:32,798][98560] Updated weights for policy 1, policy_version 94022 (0.0010) -[2023-10-11 00:37:33,156][98560] Updated weights for policy 1, policy_version 94032 (0.0010) -[2023-10-11 00:37:33,523][98560] Updated weights for policy 1, policy_version 94042 (0.0008) -[2023-10-11 00:37:35,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 193265664. Throughput: 0: 1719.2, 1: 1695.2. Samples: 48328614. Policy #0 lag: (min: 17.0, avg: 31.0, max: 49.0) -[2023-10-11 00:37:35,557][97672] Avg episode reward: [(0, '-0.420'), (1, '22.580')] -[2023-10-11 00:37:36,073][98559] Updated weights for policy 0, policy_version 94690 (0.0008) -[2023-10-11 00:37:36,436][98559] Updated weights for policy 0, policy_version 94700 (0.0009) -[2023-10-11 00:37:36,809][98559] Updated weights for policy 0, policy_version 94710 (0.0008) -[2023-10-11 00:37:37,165][98559] Updated weights for policy 0, policy_version 94720 (0.0009) -[2023-10-11 00:37:37,501][98560] Updated weights for policy 1, policy_version 94052 (0.0010) -[2023-10-11 00:37:37,865][98560] Updated weights for policy 1, policy_version 94062 (0.0010) -[2023-10-11 00:37:38,231][98560] Updated weights for policy 1, policy_version 94072 (0.0010) -[2023-10-11 00:37:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 193331200. Throughput: 0: 1701.4, 1: 1694.2. Samples: 48338736. Policy #0 lag: (min: 17.0, avg: 31.0, max: 49.0) -[2023-10-11 00:37:40,557][97672] Avg episode reward: [(0, '-0.420'), (1, '22.540')] -[2023-10-11 00:37:41,171][98559] Updated weights for policy 0, policy_version 94730 (0.0007) -[2023-10-11 00:37:41,526][98559] Updated weights for policy 0, policy_version 94740 (0.0008) -[2023-10-11 00:37:41,897][98559] Updated weights for policy 0, policy_version 94750 (0.0008) -[2023-10-11 00:37:41,921][98560] Updated weights for policy 1, policy_version 94082 (0.0010) -[2023-10-11 00:37:42,293][98560] Updated weights for policy 1, policy_version 94092 (0.0009) -[2023-10-11 00:37:42,667][98560] Updated weights for policy 1, policy_version 94102 (0.0010) -[2023-10-11 00:37:43,038][98560] Updated weights for policy 1, policy_version 94112 (0.0008) -[2023-10-11 00:37:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 193396736. Throughput: 0: 1722.4, 1: 1679.8. Samples: 48358996. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-11 00:37:45,557][97672] Avg episode reward: [(0, '-0.420'), (1, '22.540')] -[2023-10-11 00:37:45,880][98559] Updated weights for policy 0, policy_version 94760 (0.0008) -[2023-10-11 00:37:46,253][98559] Updated weights for policy 0, policy_version 94770 (0.0007) -[2023-10-11 00:37:46,614][98559] Updated weights for policy 0, policy_version 94780 (0.0007) -[2023-10-11 00:37:47,129][98560] Updated weights for policy 1, policy_version 94122 (0.0007) -[2023-10-11 00:37:47,495][98560] Updated weights for policy 1, policy_version 94132 (0.0007) -[2023-10-11 00:37:47,860][98560] Updated weights for policy 1, policy_version 94142 (0.0008) -[2023-10-11 00:37:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 193462272. Throughput: 0: 1721.7, 1: 1706.1. Samples: 48380156. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-11 00:37:50,557][98559] Updated weights for policy 0, policy_version 94790 (0.0008) -[2023-10-11 00:37:50,557][97672] Avg episode reward: [(0, '-0.420'), (1, '22.480')] -[2023-10-11 00:37:50,922][98559] Updated weights for policy 0, policy_version 94800 (0.0009) -[2023-10-11 00:37:51,300][98559] Updated weights for policy 0, policy_version 94810 (0.0008) -[2023-10-11 00:37:51,922][98560] Updated weights for policy 1, policy_version 94152 (0.0009) -[2023-10-11 00:37:52,294][98560] Updated weights for policy 1, policy_version 94162 (0.0008) -[2023-10-11 00:37:52,654][98560] Updated weights for policy 1, policy_version 94172 (0.0007) -[2023-10-11 00:37:55,235][98559] Updated weights for policy 0, policy_version 94820 (0.0010) -[2023-10-11 00:37:55,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 193527808. Throughput: 0: 1722.7, 1: 1680.1. Samples: 48389568. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-11 00:37:55,556][97672] Avg episode reward: [(0, '-0.360'), (1, '22.500')] -[2023-10-11 00:37:55,599][98559] Updated weights for policy 0, policy_version 94830 (0.0008) -[2023-10-11 00:37:55,971][98559] Updated weights for policy 0, policy_version 94840 (0.0008) -[2023-10-11 00:37:56,256][98385] Saving new best policy, reward=-0.360! -[2023-10-11 00:37:56,692][98560] Updated weights for policy 1, policy_version 94182 (0.0011) -[2023-10-11 00:37:57,059][98560] Updated weights for policy 1, policy_version 94192 (0.0010) -[2023-10-11 00:37:57,440][98560] Updated weights for policy 1, policy_version 94202 (0.0010) -[2023-10-11 00:38:00,078][98559] Updated weights for policy 0, policy_version 94850 (0.0009) -[2023-10-11 00:38:00,439][98559] Updated weights for policy 0, policy_version 94860 (0.0011) -[2023-10-11 00:38:00,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 193593344. Throughput: 0: 1719.6, 1: 1684.9. Samples: 48410236. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-11 00:38:00,556][97672] Avg episode reward: [(0, '-0.360'), (1, '22.540')] -[2023-10-11 00:38:00,801][98559] Updated weights for policy 0, policy_version 94870 (0.0012) -[2023-10-11 00:38:01,172][98559] Updated weights for policy 0, policy_version 94880 (0.0009) -[2023-10-11 00:38:01,474][98560] Updated weights for policy 1, policy_version 94212 (0.0010) -[2023-10-11 00:38:01,851][98560] Updated weights for policy 1, policy_version 94222 (0.0008) -[2023-10-11 00:38:02,216][98560] Updated weights for policy 1, policy_version 94232 (0.0009) -[2023-10-11 00:38:05,042][98559] Updated weights for policy 0, policy_version 94890 (0.0008) -[2023-10-11 00:38:05,414][98559] Updated weights for policy 0, policy_version 94900 (0.0009) -[2023-10-11 00:38:05,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 193658880. Throughput: 0: 1705.4, 1: 1701.6. Samples: 48430584. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-11 00:38:05,556][97672] Avg episode reward: [(0, '-0.360'), (1, '22.540')] -[2023-10-11 00:38:05,778][98559] Updated weights for policy 0, policy_version 94910 (0.0009) -[2023-10-11 00:38:06,300][98560] Updated weights for policy 1, policy_version 94242 (0.0008) -[2023-10-11 00:38:06,669][98560] Updated weights for policy 1, policy_version 94252 (0.0010) -[2023-10-11 00:38:07,039][98560] Updated weights for policy 1, policy_version 94262 (0.0010) -[2023-10-11 00:38:07,406][98560] Updated weights for policy 1, policy_version 94272 (0.0009) -[2023-10-11 00:38:09,890][98559] Updated weights for policy 0, policy_version 94920 (0.0010) -[2023-10-11 00:38:10,254][98559] Updated weights for policy 0, policy_version 94930 (0.0009) -[2023-10-11 00:38:10,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 193724416. Throughput: 0: 1721.1, 1: 1672.4. Samples: 48440622. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-11 00:38:10,557][97672] Avg episode reward: [(0, '-0.360'), (1, '22.600')] -[2023-10-11 00:38:10,624][98559] Updated weights for policy 0, policy_version 94940 (0.0008) -[2023-10-11 00:38:11,420][98560] Updated weights for policy 1, policy_version 94282 (0.0009) -[2023-10-11 00:38:11,785][98560] Updated weights for policy 1, policy_version 94292 (0.0007) -[2023-10-11 00:38:12,152][98560] Updated weights for policy 1, policy_version 94302 (0.0007) -[2023-10-11 00:38:14,586][98559] Updated weights for policy 0, policy_version 94950 (0.0007) -[2023-10-11 00:38:14,953][98559] Updated weights for policy 0, policy_version 94960 (0.0007) -[2023-10-11 00:38:15,318][98559] Updated weights for policy 0, policy_version 94970 (0.0007) -[2023-10-11 00:38:15,556][97672] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 193822720. Throughput: 0: 1722.2, 1: 1695.9. Samples: 48461918. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-11 00:38:15,557][97672] Avg episode reward: [(0, '-0.360'), (1, '22.580')] -[2023-10-11 00:38:16,413][98560] Updated weights for policy 1, policy_version 94312 (0.0007) -[2023-10-11 00:38:16,782][98560] Updated weights for policy 1, policy_version 94322 (0.0007) -[2023-10-11 00:38:17,156][98560] Updated weights for policy 1, policy_version 94332 (0.0007) -[2023-10-11 00:38:19,150][98559] Updated weights for policy 0, policy_version 94980 (0.0007) -[2023-10-11 00:38:19,518][98559] Updated weights for policy 0, policy_version 94990 (0.0007) -[2023-10-11 00:38:19,882][98559] Updated weights for policy 0, policy_version 95000 (0.0008) -[2023-10-11 00:38:20,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 193888256. Throughput: 0: 1698.6, 1: 1700.3. Samples: 48481566. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-11 00:38:20,557][97672] Avg episode reward: [(0, '-0.360'), (1, '22.580')] -[2023-10-11 00:38:20,930][98560] Updated weights for policy 1, policy_version 94342 (0.0008) -[2023-10-11 00:38:21,292][98560] Updated weights for policy 1, policy_version 94352 (0.0008) -[2023-10-11 00:38:21,662][98560] Updated weights for policy 1, policy_version 94362 (0.0008) -[2023-10-11 00:38:23,781][98559] Updated weights for policy 0, policy_version 95010 (0.0008) -[2023-10-11 00:38:24,146][98559] Updated weights for policy 0, policy_version 95020 (0.0010) -[2023-10-11 00:38:24,516][98559] Updated weights for policy 0, policy_version 95030 (0.0008) -[2023-10-11 00:38:24,874][98559] Updated weights for policy 0, policy_version 95040 (0.0011) -[2023-10-11 00:38:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 193953792. Throughput: 0: 1729.8, 1: 1680.6. Samples: 48492204. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-11 00:38:25,557][97672] Avg episode reward: [(0, '-0.380'), (1, '22.640')] -[2023-10-11 00:38:25,597][98560] Updated weights for policy 1, policy_version 94372 (0.0008) -[2023-10-11 00:38:25,968][98560] Updated weights for policy 1, policy_version 94382 (0.0008) -[2023-10-11 00:38:26,329][98560] Updated weights for policy 1, policy_version 94392 (0.0010) -[2023-10-11 00:38:28,873][98559] Updated weights for policy 0, policy_version 95050 (0.0007) -[2023-10-11 00:38:29,233][98559] Updated weights for policy 0, policy_version 95060 (0.0008) -[2023-10-11 00:38:29,587][98559] Updated weights for policy 0, policy_version 95070 (0.0009) -[2023-10-11 00:38:30,178][98560] Updated weights for policy 1, policy_version 94402 (0.0009) -[2023-10-11 00:38:30,553][98560] Updated weights for policy 1, policy_version 94412 (0.0007) -[2023-10-11 00:38:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 194019328. Throughput: 0: 1707.3, 1: 1706.4. Samples: 48512616. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-11 00:38:30,557][97672] Avg episode reward: [(0, '-0.400'), (1, '22.600')] -[2023-10-11 00:38:30,919][98560] Updated weights for policy 1, policy_version 94422 (0.0010) -[2023-10-11 00:38:31,287][98560] Updated weights for policy 1, policy_version 94432 (0.0009) -[2023-10-11 00:38:33,570][98559] Updated weights for policy 0, policy_version 95080 (0.0009) -[2023-10-11 00:38:33,933][98559] Updated weights for policy 0, policy_version 95090 (0.0008) -[2023-10-11 00:38:34,305][98559] Updated weights for policy 0, policy_version 95100 (0.0009) -[2023-10-11 00:38:35,455][98560] Updated weights for policy 1, policy_version 94442 (0.0008) -[2023-10-11 00:38:35,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 194084864. Throughput: 0: 1701.3, 1: 1706.0. Samples: 48533488. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-11 00:38:35,557][97672] Avg episode reward: [(0, '-0.400'), (1, '22.640')] -[2023-10-11 00:38:35,568][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000095104_97386496.pth... -[2023-10-11 00:38:35,602][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000093504_95748096.pth -[2023-10-11 00:38:35,817][98560] Updated weights for policy 1, policy_version 94452 (0.0009) -[2023-10-11 00:38:36,182][98560] Updated weights for policy 1, policy_version 94462 (0.0010) -[2023-10-11 00:38:36,250][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000094464_96731136.pth... -[2023-10-11 00:38:36,288][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000092864_95092736.pth -[2023-10-11 00:38:38,408][98559] Updated weights for policy 0, policy_version 95110 (0.0009) -[2023-10-11 00:38:38,759][98559] Updated weights for policy 0, policy_version 95120 (0.0010) -[2023-10-11 00:38:39,122][98559] Updated weights for policy 0, policy_version 95130 (0.0011) -[2023-10-11 00:38:40,316][98560] Updated weights for policy 1, policy_version 94472 (0.0009) -[2023-10-11 00:38:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 194150400. Throughput: 0: 1723.8, 1: 1697.9. Samples: 48543546. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-11 00:38:40,556][97672] Avg episode reward: [(0, '-0.400'), (1, '22.640')] -[2023-10-11 00:38:40,677][98560] Updated weights for policy 1, policy_version 94482 (0.0009) -[2023-10-11 00:38:41,044][98560] Updated weights for policy 1, policy_version 94492 (0.0009) -[2023-10-11 00:38:43,184][98559] Updated weights for policy 0, policy_version 95140 (0.0010) -[2023-10-11 00:38:43,550][98559] Updated weights for policy 0, policy_version 95150 (0.0008) -[2023-10-11 00:38:43,908][98559] Updated weights for policy 0, policy_version 95160 (0.0007) -[2023-10-11 00:38:45,241][98560] Updated weights for policy 1, policy_version 94502 (0.0009) -[2023-10-11 00:38:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 194215936. Throughput: 0: 1703.2, 1: 1703.1. Samples: 48563518. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-11 00:38:45,557][97672] Avg episode reward: [(0, '-0.400'), (1, '22.620')] -[2023-10-11 00:38:45,610][98560] Updated weights for policy 1, policy_version 94512 (0.0009) -[2023-10-11 00:38:45,967][98560] Updated weights for policy 1, policy_version 94522 (0.0009) -[2023-10-11 00:38:47,840][98559] Updated weights for policy 0, policy_version 95170 (0.0010) -[2023-10-11 00:38:48,207][98559] Updated weights for policy 0, policy_version 95180 (0.0007) -[2023-10-11 00:38:48,567][98559] Updated weights for policy 0, policy_version 95190 (0.0007) -[2023-10-11 00:38:48,927][98559] Updated weights for policy 0, policy_version 95200 (0.0008) -[2023-10-11 00:38:50,012][98560] Updated weights for policy 1, policy_version 94532 (0.0008) -[2023-10-11 00:38:50,386][98560] Updated weights for policy 1, policy_version 94542 (0.0007) -[2023-10-11 00:38:50,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 194281472. Throughput: 0: 1721.1, 1: 1703.9. Samples: 48584710. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-11 00:38:50,557][97672] Avg episode reward: [(0, '-0.440'), (1, '22.540')] -[2023-10-11 00:38:50,759][98560] Updated weights for policy 1, policy_version 94552 (0.0010) -[2023-10-11 00:38:52,786][98559] Updated weights for policy 0, policy_version 95210 (0.0007) -[2023-10-11 00:38:53,152][98559] Updated weights for policy 0, policy_version 95220 (0.0010) -[2023-10-11 00:38:53,520][98559] Updated weights for policy 0, policy_version 95230 (0.0007) -[2023-10-11 00:38:54,669][98560] Updated weights for policy 1, policy_version 94562 (0.0008) -[2023-10-11 00:38:55,049][98560] Updated weights for policy 1, policy_version 94572 (0.0008) -[2023-10-11 00:38:55,413][98560] Updated weights for policy 1, policy_version 94582 (0.0010) -[2023-10-11 00:38:55,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 194347008. Throughput: 0: 1709.6, 1: 1703.2. Samples: 48594198. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-11 00:38:55,556][97672] Avg episode reward: [(0, '-0.440'), (1, '22.540')] -[2023-10-11 00:38:55,774][98560] Updated weights for policy 1, policy_version 94592 (0.0010) -[2023-10-11 00:38:57,494][98559] Updated weights for policy 0, policy_version 95240 (0.0009) -[2023-10-11 00:38:57,866][98559] Updated weights for policy 0, policy_version 95250 (0.0007) -[2023-10-11 00:38:58,221][98559] Updated weights for policy 0, policy_version 95260 (0.0007) -[2023-10-11 00:38:59,933][98560] Updated weights for policy 1, policy_version 94602 (0.0010) -[2023-10-11 00:39:00,301][98560] Updated weights for policy 1, policy_version 94612 (0.0008) -[2023-10-11 00:39:00,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 194412544. Throughput: 0: 1701.2, 1: 1704.3. Samples: 48615164. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-11 00:39:00,556][97672] Avg episode reward: [(0, '-0.440'), (1, '22.540')] -[2023-10-11 00:39:00,657][98560] Updated weights for policy 1, policy_version 94622 (0.0008) -[2023-10-11 00:39:02,239][98559] Updated weights for policy 0, policy_version 95270 (0.0008) -[2023-10-11 00:39:02,597][98559] Updated weights for policy 0, policy_version 95280 (0.0009) -[2023-10-11 00:39:02,964][98559] Updated weights for policy 0, policy_version 95290 (0.0009) -[2023-10-11 00:39:04,644][98560] Updated weights for policy 1, policy_version 94632 (0.0010) -[2023-10-11 00:39:05,011][98560] Updated weights for policy 1, policy_version 94642 (0.0010) -[2023-10-11 00:39:05,372][98560] Updated weights for policy 1, policy_version 94652 (0.0008) -[2023-10-11 00:39:05,556][97672] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 194510848. Throughput: 0: 1730.2, 1: 1698.2. Samples: 48635844. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-11 00:39:05,556][97672] Avg episode reward: [(0, '-0.440'), (1, '22.580')] -[2023-10-11 00:39:06,939][98559] Updated weights for policy 0, policy_version 95300 (0.0008) -[2023-10-11 00:39:07,302][98559] Updated weights for policy 0, policy_version 95310 (0.0011) -[2023-10-11 00:39:07,667][98559] Updated weights for policy 0, policy_version 95320 (0.0008) -[2023-10-11 00:39:09,475][98560] Updated weights for policy 1, policy_version 94662 (0.0009) -[2023-10-11 00:39:09,841][98560] Updated weights for policy 1, policy_version 94672 (0.0011) -[2023-10-11 00:39:10,209][98560] Updated weights for policy 1, policy_version 94682 (0.0012) -[2023-10-11 00:39:10,556][97672] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 194576384. Throughput: 0: 1698.7, 1: 1704.9. Samples: 48645368. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-11 00:39:10,557][97672] Avg episode reward: [(0, '-0.440'), (1, '22.460')] -[2023-10-11 00:39:11,665][98559] Updated weights for policy 0, policy_version 95330 (0.0009) -[2023-10-11 00:39:12,039][98559] Updated weights for policy 0, policy_version 95340 (0.0008) -[2023-10-11 00:39:12,413][98559] Updated weights for policy 0, policy_version 95350 (0.0008) -[2023-10-11 00:39:12,773][98559] Updated weights for policy 0, policy_version 95360 (0.0009) -[2023-10-11 00:39:14,290][98560] Updated weights for policy 1, policy_version 94692 (0.0009) -[2023-10-11 00:39:14,657][98560] Updated weights for policy 1, policy_version 94702 (0.0009) -[2023-10-11 00:39:15,017][98560] Updated weights for policy 1, policy_version 94712 (0.0007) -[2023-10-11 00:39:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 194641920. Throughput: 0: 1712.8, 1: 1698.3. Samples: 48666114. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-11 00:39:15,556][97672] Avg episode reward: [(0, '-0.440'), (1, '22.380')] -[2023-10-11 00:39:16,817][98559] Updated weights for policy 0, policy_version 95370 (0.0010) -[2023-10-11 00:39:17,187][98559] Updated weights for policy 0, policy_version 95380 (0.0008) -[2023-10-11 00:39:17,562][98559] Updated weights for policy 0, policy_version 95390 (0.0008) -[2023-10-11 00:39:18,982][98560] Updated weights for policy 1, policy_version 94722 (0.0009) -[2023-10-11 00:39:19,341][98560] Updated weights for policy 1, policy_version 94732 (0.0009) -[2023-10-11 00:39:19,712][98560] Updated weights for policy 1, policy_version 94742 (0.0008) -[2023-10-11 00:39:20,076][98560] Updated weights for policy 1, policy_version 94752 (0.0007) -[2023-10-11 00:39:20,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 194707456. Throughput: 0: 1719.4, 1: 1679.5. Samples: 48686436. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-11 00:39:20,557][97672] Avg episode reward: [(0, '-0.440'), (1, '22.380')] -[2023-10-11 00:39:21,485][98559] Updated weights for policy 0, policy_version 95400 (0.0009) -[2023-10-11 00:39:21,848][98559] Updated weights for policy 0, policy_version 95410 (0.0010) -[2023-10-11 00:39:22,215][98559] Updated weights for policy 0, policy_version 95420 (0.0008) -[2023-10-11 00:39:24,210][98560] Updated weights for policy 1, policy_version 94762 (0.0008) -[2023-10-11 00:39:24,583][98560] Updated weights for policy 1, policy_version 94772 (0.0008) -[2023-10-11 00:39:24,947][98560] Updated weights for policy 1, policy_version 94782 (0.0008) -[2023-10-11 00:39:25,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 194772992. Throughput: 0: 1695.1, 1: 1703.3. Samples: 48696474. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-11 00:39:25,557][97672] Avg episode reward: [(0, '-0.440'), (1, '22.400')] -[2023-10-11 00:39:26,191][98559] Updated weights for policy 0, policy_version 95430 (0.0007) -[2023-10-11 00:39:26,564][98559] Updated weights for policy 0, policy_version 95440 (0.0009) -[2023-10-11 00:39:26,933][98559] Updated weights for policy 0, policy_version 95450 (0.0009) -[2023-10-11 00:39:28,931][98560] Updated weights for policy 1, policy_version 94792 (0.0007) -[2023-10-11 00:39:29,291][98560] Updated weights for policy 1, policy_version 94802 (0.0007) -[2023-10-11 00:39:29,667][98560] Updated weights for policy 1, policy_version 94812 (0.0008) -[2023-10-11 00:39:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 194838528. Throughput: 0: 1719.6, 1: 1699.1. Samples: 48717356. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-11 00:39:30,556][97672] Avg episode reward: [(0, '-0.440'), (1, '22.360')] -[2023-10-11 00:39:30,918][98559] Updated weights for policy 0, policy_version 95460 (0.0009) -[2023-10-11 00:39:31,273][98559] Updated weights for policy 0, policy_version 95470 (0.0008) -[2023-10-11 00:39:31,652][98559] Updated weights for policy 0, policy_version 95480 (0.0007) -[2023-10-11 00:39:33,651][98560] Updated weights for policy 1, policy_version 94822 (0.0010) -[2023-10-11 00:39:34,028][98560] Updated weights for policy 1, policy_version 94832 (0.0008) -[2023-10-11 00:39:34,385][98560] Updated weights for policy 1, policy_version 94842 (0.0009) -[2023-10-11 00:39:35,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 194904064. Throughput: 0: 1716.9, 1: 1671.4. Samples: 48737184. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-11 00:39:35,556][97672] Avg episode reward: [(0, '-0.540'), (1, '22.400')] -[2023-10-11 00:39:35,564][98559] Updated weights for policy 0, policy_version 95490 (0.0007) -[2023-10-11 00:39:35,933][98559] Updated weights for policy 0, policy_version 95500 (0.0008) -[2023-10-11 00:39:36,291][98559] Updated weights for policy 0, policy_version 95510 (0.0008) -[2023-10-11 00:39:36,656][98559] Updated weights for policy 0, policy_version 95520 (0.0008) -[2023-10-11 00:39:38,300][98560] Updated weights for policy 1, policy_version 94852 (0.0009) -[2023-10-11 00:39:38,673][98560] Updated weights for policy 1, policy_version 94862 (0.0007) -[2023-10-11 00:39:39,030][98560] Updated weights for policy 1, policy_version 94872 (0.0010) -[2023-10-11 00:39:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 194969600. Throughput: 0: 1712.6, 1: 1702.2. Samples: 48747864. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-11 00:39:40,557][97672] Avg episode reward: [(0, '-0.540'), (1, '22.380')] -[2023-10-11 00:39:40,722][98559] Updated weights for policy 0, policy_version 95530 (0.0008) -[2023-10-11 00:39:41,090][98559] Updated weights for policy 0, policy_version 95540 (0.0007) -[2023-10-11 00:39:41,448][98559] Updated weights for policy 0, policy_version 95550 (0.0008) -[2023-10-11 00:39:43,138][98560] Updated weights for policy 1, policy_version 94882 (0.0009) -[2023-10-11 00:39:43,507][98560] Updated weights for policy 1, policy_version 94892 (0.0009) -[2023-10-11 00:39:43,878][98560] Updated weights for policy 1, policy_version 94902 (0.0007) -[2023-10-11 00:39:44,243][98560] Updated weights for policy 1, policy_version 94912 (0.0008) -[2023-10-11 00:39:45,262][98559] Updated weights for policy 0, policy_version 95560 (0.0008) -[2023-10-11 00:39:45,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 195035136. Throughput: 0: 1719.1, 1: 1685.4. Samples: 48768368. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-11 00:39:45,557][97672] Avg episode reward: [(0, '-0.540'), (1, '22.380')] -[2023-10-11 00:39:45,632][98559] Updated weights for policy 0, policy_version 95570 (0.0009) -[2023-10-11 00:39:46,001][98559] Updated weights for policy 0, policy_version 95580 (0.0008) -[2023-10-11 00:39:48,334][98560] Updated weights for policy 1, policy_version 94922 (0.0009) -[2023-10-11 00:39:48,703][98560] Updated weights for policy 1, policy_version 94932 (0.0009) -[2023-10-11 00:39:49,059][98560] Updated weights for policy 1, policy_version 94942 (0.0010) -[2023-10-11 00:39:50,037][98559] Updated weights for policy 0, policy_version 95590 (0.0008) -[2023-10-11 00:39:50,401][98559] Updated weights for policy 0, policy_version 95600 (0.0009) -[2023-10-11 00:39:50,556][97672] Fps is (10 sec: 13106.7, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 195100672. Throughput: 0: 1706.4, 1: 1676.6. Samples: 48788080. Policy #0 lag: (min: 2.0, avg: 7.9, max: 34.0) -[2023-10-11 00:39:50,557][97672] Avg episode reward: [(0, '-0.540'), (1, '22.340')] -[2023-10-11 00:39:50,759][98559] Updated weights for policy 0, policy_version 95610 (0.0008) -[2023-10-11 00:39:52,851][98560] Updated weights for policy 1, policy_version 94952 (0.0008) -[2023-10-11 00:39:53,215][98560] Updated weights for policy 1, policy_version 94962 (0.0009) -[2023-10-11 00:39:53,583][98560] Updated weights for policy 1, policy_version 94972 (0.0007) -[2023-10-11 00:39:54,736][98559] Updated weights for policy 0, policy_version 95620 (0.0007) -[2023-10-11 00:39:55,111][98559] Updated weights for policy 0, policy_version 95630 (0.0009) -[2023-10-11 00:39:55,489][98559] Updated weights for policy 0, policy_version 95640 (0.0009) -[2023-10-11 00:39:55,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 195166208. Throughput: 0: 1720.2, 1: 1698.6. Samples: 48799214. Policy #0 lag: (min: 2.0, avg: 7.9, max: 34.0) -[2023-10-11 00:39:55,557][97672] Avg episode reward: [(0, '-0.460'), (1, '22.460')] -[2023-10-11 00:39:57,627][98560] Updated weights for policy 1, policy_version 94982 (0.0007) -[2023-10-11 00:39:57,993][98560] Updated weights for policy 1, policy_version 94992 (0.0009) -[2023-10-11 00:39:58,364][98560] Updated weights for policy 1, policy_version 95002 (0.0010) -[2023-10-11 00:39:59,413][98559] Updated weights for policy 0, policy_version 95650 (0.0010) -[2023-10-11 00:39:59,772][98559] Updated weights for policy 0, policy_version 95660 (0.0009) -[2023-10-11 00:40:00,138][98559] Updated weights for policy 0, policy_version 95670 (0.0008) -[2023-10-11 00:40:00,505][98559] Updated weights for policy 0, policy_version 95680 (0.0010) -[2023-10-11 00:40:00,556][97672] Fps is (10 sec: 16384.7, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 195264512. Throughput: 0: 1723.8, 1: 1672.7. Samples: 48818956. Policy #0 lag: (min: 2.0, avg: 7.9, max: 34.0) -[2023-10-11 00:40:00,557][97672] Avg episode reward: [(0, '-0.460'), (1, '22.520')] -[2023-10-11 00:40:02,284][98560] Updated weights for policy 1, policy_version 95012 (0.0009) -[2023-10-11 00:40:02,650][98560] Updated weights for policy 1, policy_version 95022 (0.0007) -[2023-10-11 00:40:03,023][98560] Updated weights for policy 1, policy_version 95032 (0.0009) -[2023-10-11 00:40:04,520][98559] Updated weights for policy 0, policy_version 95690 (0.0010) -[2023-10-11 00:40:04,891][98559] Updated weights for policy 0, policy_version 95700 (0.0010) -[2023-10-11 00:40:05,258][98559] Updated weights for policy 0, policy_version 95710 (0.0011) -[2023-10-11 00:40:05,556][97672] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 195330048. Throughput: 0: 1692.7, 1: 1691.2. Samples: 48838714. Policy #0 lag: (min: 2.0, avg: 7.9, max: 34.0) -[2023-10-11 00:40:05,557][97672] Avg episode reward: [(0, '-0.480'), (1, '22.560')] -[2023-10-11 00:40:06,942][98560] Updated weights for policy 1, policy_version 95042 (0.0010) -[2023-10-11 00:40:07,309][98560] Updated weights for policy 1, policy_version 95052 (0.0009) -[2023-10-11 00:40:07,678][98560] Updated weights for policy 1, policy_version 95062 (0.0007) -[2023-10-11 00:40:08,046][98560] Updated weights for policy 1, policy_version 95072 (0.0007) -[2023-10-11 00:40:09,367][98559] Updated weights for policy 0, policy_version 95720 (0.0011) -[2023-10-11 00:40:09,721][98559] Updated weights for policy 0, policy_version 95730 (0.0011) -[2023-10-11 00:40:10,081][98559] Updated weights for policy 0, policy_version 95740 (0.0009) -[2023-10-11 00:40:10,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 195395584. Throughput: 0: 1718.5, 1: 1686.2. Samples: 48849686. Policy #0 lag: (min: 2.0, avg: 7.9, max: 34.0) -[2023-10-11 00:40:10,557][97672] Avg episode reward: [(0, '-0.500'), (1, '22.540')] -[2023-10-11 00:40:12,160][98560] Updated weights for policy 1, policy_version 95082 (0.0009) -[2023-10-11 00:40:12,530][98560] Updated weights for policy 1, policy_version 95092 (0.0008) -[2023-10-11 00:40:12,895][98560] Updated weights for policy 1, policy_version 95102 (0.0010) -[2023-10-11 00:40:14,133][98559] Updated weights for policy 0, policy_version 95750 (0.0008) -[2023-10-11 00:40:14,494][98559] Updated weights for policy 0, policy_version 95760 (0.0008) -[2023-10-11 00:40:14,860][98559] Updated weights for policy 0, policy_version 95770 (0.0008) -[2023-10-11 00:40:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 195461120. Throughput: 0: 1706.6, 1: 1678.6. Samples: 48869690. Policy #0 lag: (min: 2.0, avg: 7.9, max: 34.0) -[2023-10-11 00:40:15,557][97672] Avg episode reward: [(0, '-0.500'), (1, '22.580')] -[2023-10-11 00:40:17,096][98560] Updated weights for policy 1, policy_version 95112 (0.0010) -[2023-10-11 00:40:17,459][98560] Updated weights for policy 1, policy_version 95122 (0.0010) -[2023-10-11 00:40:17,831][98560] Updated weights for policy 1, policy_version 95132 (0.0009) -[2023-10-11 00:40:18,724][98559] Updated weights for policy 0, policy_version 95780 (0.0007) -[2023-10-11 00:40:19,090][98559] Updated weights for policy 0, policy_version 95790 (0.0009) -[2023-10-11 00:40:19,448][98559] Updated weights for policy 0, policy_version 95800 (0.0007) -[2023-10-11 00:40:20,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 195526656. Throughput: 0: 1695.5, 1: 1708.4. Samples: 48890358. Policy #0 lag: (min: 2.0, avg: 7.9, max: 34.0) -[2023-10-11 00:40:20,557][97672] Avg episode reward: [(0, '-0.500'), (1, '22.620')] -[2023-10-11 00:40:21,710][98560] Updated weights for policy 1, policy_version 95142 (0.0009) -[2023-10-11 00:40:22,083][98560] Updated weights for policy 1, policy_version 95152 (0.0012) -[2023-10-11 00:40:22,451][98560] Updated weights for policy 1, policy_version 95162 (0.0009) -[2023-10-11 00:40:23,442][98559] Updated weights for policy 0, policy_version 95810 (0.0008) -[2023-10-11 00:40:23,813][98559] Updated weights for policy 0, policy_version 95820 (0.0009) -[2023-10-11 00:40:24,171][98559] Updated weights for policy 0, policy_version 95830 (0.0008) -[2023-10-11 00:40:24,535][98559] Updated weights for policy 0, policy_version 95840 (0.0009) -[2023-10-11 00:40:25,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 195592192. Throughput: 0: 1725.7, 1: 1678.4. Samples: 48901050. Policy #0 lag: (min: 2.0, avg: 7.9, max: 34.0) -[2023-10-11 00:40:25,557][97672] Avg episode reward: [(0, '-0.500'), (1, '22.580')] -[2023-10-11 00:40:26,548][98560] Updated weights for policy 1, policy_version 95172 (0.0009) -[2023-10-11 00:40:26,924][98560] Updated weights for policy 1, policy_version 95182 (0.0009) -[2023-10-11 00:40:27,287][98560] Updated weights for policy 1, policy_version 95192 (0.0007) -[2023-10-11 00:40:28,617][98559] Updated weights for policy 0, policy_version 95850 (0.0008) -[2023-10-11 00:40:28,977][98559] Updated weights for policy 0, policy_version 95860 (0.0010) -[2023-10-11 00:40:29,343][98559] Updated weights for policy 0, policy_version 95870 (0.0008) -[2023-10-11 00:40:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 195657728. Throughput: 0: 1699.1, 1: 1692.4. Samples: 48920984. Policy #0 lag: (min: 2.0, avg: 7.9, max: 34.0) -[2023-10-11 00:40:30,557][97672] Avg episode reward: [(0, '-0.500'), (1, '22.620')] -[2023-10-11 00:40:31,242][98560] Updated weights for policy 1, policy_version 95202 (0.0008) -[2023-10-11 00:40:31,610][98560] Updated weights for policy 1, policy_version 95212 (0.0011) -[2023-10-11 00:40:31,982][98560] Updated weights for policy 1, policy_version 95222 (0.0009) -[2023-10-11 00:40:32,344][98560] Updated weights for policy 1, policy_version 95232 (0.0008) -[2023-10-11 00:40:33,392][98559] Updated weights for policy 0, policy_version 95880 (0.0008) -[2023-10-11 00:40:33,753][98559] Updated weights for policy 0, policy_version 95890 (0.0009) -[2023-10-11 00:40:34,126][98559] Updated weights for policy 0, policy_version 95900 (0.0007) -[2023-10-11 00:40:35,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 195723264. Throughput: 0: 1702.5, 1: 1715.4. Samples: 48941886. Policy #0 lag: (min: 2.0, avg: 7.9, max: 34.0) -[2023-10-11 00:40:35,557][97672] Avg episode reward: [(0, '-0.500'), (1, '22.600')] -[2023-10-11 00:40:35,570][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000095904_98205696.pth... -[2023-10-11 00:40:35,570][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000095232_97517568.pth... -[2023-10-11 00:40:35,602][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000093664_95911936.pth -[2023-10-11 00:40:35,605][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000094304_96567296.pth -[2023-10-11 00:40:35,606][98439] Saving a milestone ./train_atari/atari_doubledunk_APPO/checkpoint_p1/milestones/checkpoint_000095232_97517568.pth -[2023-10-11 00:40:35,609][98385] Saving a milestone ./train_atari/atari_doubledunk_APPO/checkpoint_p0/milestones/checkpoint_000095904_98205696.pth -[2023-10-11 00:40:36,393][98560] Updated weights for policy 1, policy_version 95242 (0.0008) -[2023-10-11 00:40:36,753][98560] Updated weights for policy 1, policy_version 95252 (0.0008) -[2023-10-11 00:40:37,124][98560] Updated weights for policy 1, policy_version 95262 (0.0008) -[2023-10-11 00:40:38,209][98559] Updated weights for policy 0, policy_version 95910 (0.0009) -[2023-10-11 00:40:38,594][98559] Updated weights for policy 0, policy_version 95920 (0.0009) -[2023-10-11 00:40:38,960][98559] Updated weights for policy 0, policy_version 95930 (0.0009) -[2023-10-11 00:40:40,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 195788800. Throughput: 0: 1709.8, 1: 1684.0. Samples: 48951932. Policy #0 lag: (min: 2.0, avg: 7.9, max: 34.0) -[2023-10-11 00:40:40,557][97672] Avg episode reward: [(0, '-0.500'), (1, '22.540')] -[2023-10-11 00:40:41,250][98560] Updated weights for policy 1, policy_version 95272 (0.0009) -[2023-10-11 00:40:41,618][98560] Updated weights for policy 1, policy_version 95282 (0.0009) -[2023-10-11 00:40:41,985][98560] Updated weights for policy 1, policy_version 95292 (0.0008) -[2023-10-11 00:40:43,003][98559] Updated weights for policy 0, policy_version 95940 (0.0008) -[2023-10-11 00:40:43,362][98559] Updated weights for policy 0, policy_version 95950 (0.0009) -[2023-10-11 00:40:43,724][98559] Updated weights for policy 0, policy_version 95960 (0.0007) -[2023-10-11 00:40:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 195854336. Throughput: 0: 1689.7, 1: 1709.5. Samples: 48971924. Policy #0 lag: (min: 8.0, avg: 31.5, max: 40.0) -[2023-10-11 00:40:45,557][97672] Avg episode reward: [(0, '-0.500'), (1, '22.560')] -[2023-10-11 00:40:45,996][98560] Updated weights for policy 1, policy_version 95302 (0.0011) -[2023-10-11 00:40:46,377][98560] Updated weights for policy 1, policy_version 95312 (0.0009) -[2023-10-11 00:40:46,749][98560] Updated weights for policy 1, policy_version 95322 (0.0007) -[2023-10-11 00:40:47,614][98559] Updated weights for policy 0, policy_version 95970 (0.0009) -[2023-10-11 00:40:47,977][98559] Updated weights for policy 0, policy_version 95980 (0.0008) -[2023-10-11 00:40:48,356][98559] Updated weights for policy 0, policy_version 95990 (0.0008) -[2023-10-11 00:40:48,719][98559] Updated weights for policy 0, policy_version 96000 (0.0009) -[2023-10-11 00:40:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 195919872. Throughput: 0: 1716.6, 1: 1704.0. Samples: 48992642. Policy #0 lag: (min: 8.0, avg: 31.5, max: 40.0) -[2023-10-11 00:40:50,557][97672] Avg episode reward: [(0, '-0.500'), (1, '22.500')] -[2023-10-11 00:40:50,886][98560] Updated weights for policy 1, policy_version 95332 (0.0008) -[2023-10-11 00:40:51,253][98560] Updated weights for policy 1, policy_version 95342 (0.0008) -[2023-10-11 00:40:51,634][98560] Updated weights for policy 1, policy_version 95352 (0.0009) -[2023-10-11 00:40:52,774][98559] Updated weights for policy 0, policy_version 96010 (0.0008) -[2023-10-11 00:40:53,136][98559] Updated weights for policy 0, policy_version 96020 (0.0007) -[2023-10-11 00:40:53,508][98559] Updated weights for policy 0, policy_version 96030 (0.0008) -[2023-10-11 00:40:55,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 195985408. Throughput: 0: 1698.1, 1: 1689.1. Samples: 49002112. Policy #0 lag: (min: 8.0, avg: 31.5, max: 40.0) -[2023-10-11 00:40:55,557][97672] Avg episode reward: [(0, '-0.520'), (1, '22.520')] -[2023-10-11 00:40:55,643][98560] Updated weights for policy 1, policy_version 95362 (0.0008) -[2023-10-11 00:40:56,010][98560] Updated weights for policy 1, policy_version 95372 (0.0010) -[2023-10-11 00:40:56,380][98560] Updated weights for policy 1, policy_version 95382 (0.0008) -[2023-10-11 00:40:56,736][98560] Updated weights for policy 1, policy_version 95392 (0.0009) -[2023-10-11 00:40:57,508][98559] Updated weights for policy 0, policy_version 96040 (0.0009) -[2023-10-11 00:40:57,863][98559] Updated weights for policy 0, policy_version 96050 (0.0007) -[2023-10-11 00:40:58,237][98559] Updated weights for policy 0, policy_version 96060 (0.0008) -[2023-10-11 00:41:00,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 196050944. Throughput: 0: 1705.9, 1: 1701.2. Samples: 49023012. Policy #0 lag: (min: 8.0, avg: 31.5, max: 40.0) -[2023-10-11 00:41:00,557][97672] Avg episode reward: [(0, '-0.520'), (1, '22.540')] -[2023-10-11 00:41:00,774][98560] Updated weights for policy 1, policy_version 95402 (0.0008) -[2023-10-11 00:41:01,133][98560] Updated weights for policy 1, policy_version 95412 (0.0009) -[2023-10-11 00:41:01,509][98560] Updated weights for policy 1, policy_version 95422 (0.0009) -[2023-10-11 00:41:02,051][98559] Updated weights for policy 0, policy_version 96070 (0.0008) -[2023-10-11 00:41:02,420][98559] Updated weights for policy 0, policy_version 96080 (0.0008) -[2023-10-11 00:41:02,779][98559] Updated weights for policy 0, policy_version 96090 (0.0008) -[2023-10-11 00:41:05,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 196116480. Throughput: 0: 1718.4, 1: 1696.8. Samples: 49044044. Policy #0 lag: (min: 8.0, avg: 31.5, max: 40.0) -[2023-10-11 00:41:05,557][97672] Avg episode reward: [(0, '-0.520'), (1, '22.520')] -[2023-10-11 00:41:05,637][98560] Updated weights for policy 1, policy_version 95432 (0.0008) -[2023-10-11 00:41:06,010][98560] Updated weights for policy 1, policy_version 95442 (0.0009) -[2023-10-11 00:41:06,385][98560] Updated weights for policy 1, policy_version 95452 (0.0007) -[2023-10-11 00:41:06,666][98559] Updated weights for policy 0, policy_version 96100 (0.0009) -[2023-10-11 00:41:07,040][98559] Updated weights for policy 0, policy_version 96110 (0.0009) -[2023-10-11 00:41:07,393][98559] Updated weights for policy 0, policy_version 96120 (0.0010) -[2023-10-11 00:41:10,515][98560] Updated weights for policy 1, policy_version 95462 (0.0009) -[2023-10-11 00:41:10,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 196182016. Throughput: 0: 1690.6, 1: 1690.2. Samples: 49053186. Policy #0 lag: (min: 8.0, avg: 31.5, max: 40.0) -[2023-10-11 00:41:10,557][97672] Avg episode reward: [(0, '-0.520'), (1, '22.500')] -[2023-10-11 00:41:10,878][98560] Updated weights for policy 1, policy_version 95472 (0.0011) -[2023-10-11 00:41:11,245][98560] Updated weights for policy 1, policy_version 95482 (0.0009) -[2023-10-11 00:41:11,458][98559] Updated weights for policy 0, policy_version 96130 (0.0008) -[2023-10-11 00:41:11,825][98559] Updated weights for policy 0, policy_version 96140 (0.0011) -[2023-10-11 00:41:12,189][98559] Updated weights for policy 0, policy_version 96150 (0.0007) -[2023-10-11 00:41:12,556][98559] Updated weights for policy 0, policy_version 96160 (0.0008) -[2023-10-11 00:41:15,274][98560] Updated weights for policy 1, policy_version 95492 (0.0008) -[2023-10-11 00:41:15,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 196247552. Throughput: 0: 1720.3, 1: 1688.2. Samples: 49074364. Policy #0 lag: (min: 8.0, avg: 31.5, max: 40.0) -[2023-10-11 00:41:15,556][97672] Avg episode reward: [(0, '-0.500'), (1, '22.500')] -[2023-10-11 00:41:15,639][98560] Updated weights for policy 1, policy_version 95502 (0.0010) -[2023-10-11 00:41:16,009][98560] Updated weights for policy 1, policy_version 95512 (0.0008) -[2023-10-11 00:41:16,552][98559] Updated weights for policy 0, policy_version 96170 (0.0009) -[2023-10-11 00:41:16,920][98559] Updated weights for policy 0, policy_version 96180 (0.0010) -[2023-10-11 00:41:17,290][98559] Updated weights for policy 0, policy_version 96190 (0.0008) -[2023-10-11 00:41:19,849][98560] Updated weights for policy 1, policy_version 95522 (0.0009) -[2023-10-11 00:41:20,209][98560] Updated weights for policy 1, policy_version 95532 (0.0008) -[2023-10-11 00:41:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 196313088. Throughput: 0: 1733.6, 1: 1686.8. Samples: 49095802. Policy #0 lag: (min: 8.0, avg: 31.5, max: 40.0) -[2023-10-11 00:41:20,556][97672] Avg episode reward: [(0, '-0.500'), (1, '22.480')] -[2023-10-11 00:41:20,575][98560] Updated weights for policy 1, policy_version 95542 (0.0009) -[2023-10-11 00:41:20,939][98560] Updated weights for policy 1, policy_version 95552 (0.0007) -[2023-10-11 00:41:21,081][98559] Updated weights for policy 0, policy_version 96200 (0.0008) -[2023-10-11 00:41:21,439][98559] Updated weights for policy 0, policy_version 96210 (0.0008) -[2023-10-11 00:41:21,810][98559] Updated weights for policy 0, policy_version 96220 (0.0009) -[2023-10-11 00:41:24,997][98560] Updated weights for policy 1, policy_version 95562 (0.0008) -[2023-10-11 00:41:25,361][98560] Updated weights for policy 1, policy_version 95572 (0.0007) -[2023-10-11 00:41:25,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 196378624. Throughput: 0: 1713.5, 1: 1687.5. Samples: 49104978. Policy #0 lag: (min: 8.0, avg: 31.5, max: 40.0) -[2023-10-11 00:41:25,557][97672] Avg episode reward: [(0, '-0.520'), (1, '22.540')] -[2023-10-11 00:41:25,730][98560] Updated weights for policy 1, policy_version 95582 (0.0008) -[2023-10-11 00:41:25,798][98559] Updated weights for policy 0, policy_version 96230 (0.0009) -[2023-10-11 00:41:26,161][98559] Updated weights for policy 0, policy_version 96240 (0.0009) -[2023-10-11 00:41:26,534][98559] Updated weights for policy 0, policy_version 96250 (0.0009) -[2023-10-11 00:41:29,748][98560] Updated weights for policy 1, policy_version 95592 (0.0009) -[2023-10-11 00:41:30,110][98560] Updated weights for policy 1, policy_version 95602 (0.0011) -[2023-10-11 00:41:30,474][98560] Updated weights for policy 1, policy_version 95612 (0.0010) -[2023-10-11 00:41:30,499][98559] Updated weights for policy 0, policy_version 96260 (0.0008) -[2023-10-11 00:41:30,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 196444160. Throughput: 0: 1731.4, 1: 1692.6. Samples: 49126002. Policy #0 lag: (min: 8.0, avg: 31.5, max: 40.0) -[2023-10-11 00:41:30,557][97672] Avg episode reward: [(0, '-0.520'), (1, '22.580')] -[2023-10-11 00:41:30,859][98559] Updated weights for policy 0, policy_version 96270 (0.0009) -[2023-10-11 00:41:31,222][98559] Updated weights for policy 0, policy_version 96280 (0.0011) -[2023-10-11 00:41:34,659][98560] Updated weights for policy 1, policy_version 95622 (0.0008) -[2023-10-11 00:41:35,035][98560] Updated weights for policy 1, policy_version 95632 (0.0008) -[2023-10-11 00:41:35,195][98559] Updated weights for policy 0, policy_version 96290 (0.0010) -[2023-10-11 00:41:35,406][98560] Updated weights for policy 1, policy_version 95642 (0.0008) -[2023-10-11 00:41:35,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13440.4). Total num frames: 196509696. Throughput: 0: 1731.5, 1: 1687.5. Samples: 49146496. Policy #0 lag: (min: 8.0, avg: 31.5, max: 40.0) -[2023-10-11 00:41:35,557][97672] Avg episode reward: [(0, '-0.520'), (1, '22.540')] -[2023-10-11 00:41:35,563][98559] Updated weights for policy 0, policy_version 96300 (0.0007) -[2023-10-11 00:41:35,928][98559] Updated weights for policy 0, policy_version 96310 (0.0009) -[2023-10-11 00:41:36,290][98559] Updated weights for policy 0, policy_version 96320 (0.0009) -[2023-10-11 00:41:39,477][98560] Updated weights for policy 1, policy_version 95652 (0.0008) -[2023-10-11 00:41:39,834][98560] Updated weights for policy 1, policy_version 95662 (0.0008) -[2023-10-11 00:41:40,198][98560] Updated weights for policy 1, policy_version 95672 (0.0009) -[2023-10-11 00:41:40,274][98559] Updated weights for policy 0, policy_version 96330 (0.0008) -[2023-10-11 00:41:40,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 196608000. Throughput: 0: 1733.8, 1: 1694.3. Samples: 49156374. Policy #0 lag: (min: 8.0, avg: 31.5, max: 40.0) -[2023-10-11 00:41:40,556][97672] Avg episode reward: [(0, '-0.520'), (1, '22.580')] -[2023-10-11 00:41:40,645][98559] Updated weights for policy 0, policy_version 96340 (0.0008) -[2023-10-11 00:41:41,005][98559] Updated weights for policy 0, policy_version 96350 (0.0011) -[2023-10-11 00:41:44,192][98560] Updated weights for policy 1, policy_version 95682 (0.0009) -[2023-10-11 00:41:44,561][98560] Updated weights for policy 1, policy_version 95692 (0.0009) -[2023-10-11 00:41:44,924][98560] Updated weights for policy 1, policy_version 95702 (0.0009) -[2023-10-11 00:41:44,941][98559] Updated weights for policy 0, policy_version 96360 (0.0008) -[2023-10-11 00:41:45,282][98560] Updated weights for policy 1, policy_version 95712 (0.0010) -[2023-10-11 00:41:45,315][98559] Updated weights for policy 0, policy_version 96370 (0.0008) -[2023-10-11 00:41:45,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 196673536. Throughput: 0: 1733.7, 1: 1690.2. Samples: 49177086. Policy #0 lag: (min: 8.0, avg: 31.5, max: 40.0) -[2023-10-11 00:41:45,557][97672] Avg episode reward: [(0, '-0.520'), (1, '22.580')] -[2023-10-11 00:41:45,678][98559] Updated weights for policy 0, policy_version 96380 (0.0008) -[2023-10-11 00:41:49,378][98560] Updated weights for policy 1, policy_version 95722 (0.0010) -[2023-10-11 00:41:49,732][98559] Updated weights for policy 0, policy_version 96390 (0.0007) -[2023-10-11 00:41:49,752][98560] Updated weights for policy 1, policy_version 95732 (0.0009) -[2023-10-11 00:41:50,108][98559] Updated weights for policy 0, policy_version 96400 (0.0007) -[2023-10-11 00:41:50,110][98560] Updated weights for policy 1, policy_version 95742 (0.0009) -[2023-10-11 00:41:50,482][98559] Updated weights for policy 0, policy_version 96410 (0.0008) -[2023-10-11 00:41:50,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 196739072. Throughput: 0: 1707.6, 1: 1676.6. Samples: 49196332. Policy #0 lag: (min: 0.0, avg: 29.2, max: 32.0) -[2023-10-11 00:41:50,557][97672] Avg episode reward: [(0, '-0.520'), (1, '22.560')] -[2023-10-11 00:41:54,226][98560] Updated weights for policy 1, policy_version 95752 (0.0008) -[2023-10-11 00:41:54,409][98559] Updated weights for policy 0, policy_version 96420 (0.0008) -[2023-10-11 00:41:54,591][98560] Updated weights for policy 1, policy_version 95762 (0.0009) -[2023-10-11 00:41:54,766][98559] Updated weights for policy 0, policy_version 96430 (0.0009) -[2023-10-11 00:41:54,944][98560] Updated weights for policy 1, policy_version 95772 (0.0011) -[2023-10-11 00:41:55,137][98559] Updated weights for policy 0, policy_version 96440 (0.0009) -[2023-10-11 00:41:55,556][97672] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 196837376. Throughput: 0: 1725.9, 1: 1698.5. Samples: 49207284. Policy #0 lag: (min: 0.0, avg: 29.2, max: 32.0) -[2023-10-11 00:41:55,558][97672] Avg episode reward: [(0, '-0.520'), (1, '22.540')] -[2023-10-11 00:41:59,049][98560] Updated weights for policy 1, policy_version 95782 (0.0009) -[2023-10-11 00:41:59,082][98559] Updated weights for policy 0, policy_version 96450 (0.0011) -[2023-10-11 00:41:59,410][98560] Updated weights for policy 1, policy_version 95792 (0.0009) -[2023-10-11 00:41:59,445][98559] Updated weights for policy 0, policy_version 96460 (0.0008) -[2023-10-11 00:41:59,770][98560] Updated weights for policy 1, policy_version 95802 (0.0009) -[2023-10-11 00:41:59,820][98559] Updated weights for policy 0, policy_version 96470 (0.0011) -[2023-10-11 00:42:00,174][98559] Updated weights for policy 0, policy_version 96480 (0.0010) -[2023-10-11 00:42:00,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 196902912. Throughput: 0: 1716.2, 1: 1692.1. Samples: 49227736. Policy #0 lag: (min: 0.0, avg: 29.2, max: 32.0) -[2023-10-11 00:42:00,557][97672] Avg episode reward: [(0, '-0.520'), (1, '22.560')] -[2023-10-11 00:42:03,648][98560] Updated weights for policy 1, policy_version 95812 (0.0008) -[2023-10-11 00:42:04,023][98560] Updated weights for policy 1, policy_version 95822 (0.0009) -[2023-10-11 00:42:04,173][98559] Updated weights for policy 0, policy_version 96490 (0.0007) -[2023-10-11 00:42:04,389][98560] Updated weights for policy 1, policy_version 95832 (0.0008) -[2023-10-11 00:42:04,541][98559] Updated weights for policy 0, policy_version 96500 (0.0007) -[2023-10-11 00:42:04,903][98559] Updated weights for policy 0, policy_version 96510 (0.0008) -[2023-10-11 00:42:05,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 196968448. Throughput: 0: 1691.7, 1: 1667.1. Samples: 49246948. Policy #0 lag: (min: 0.0, avg: 29.2, max: 32.0) -[2023-10-11 00:42:05,557][97672] Avg episode reward: [(0, '-0.520'), (1, '22.500')] -[2023-10-11 00:42:08,226][98560] Updated weights for policy 1, policy_version 95842 (0.0007) -[2023-10-11 00:42:08,596][98560] Updated weights for policy 1, policy_version 95852 (0.0008) -[2023-10-11 00:42:08,886][98559] Updated weights for policy 0, policy_version 96520 (0.0007) -[2023-10-11 00:42:08,962][98560] Updated weights for policy 1, policy_version 95862 (0.0009) -[2023-10-11 00:42:09,250][98559] Updated weights for policy 0, policy_version 96530 (0.0010) -[2023-10-11 00:42:09,334][98560] Updated weights for policy 1, policy_version 95872 (0.0007) -[2023-10-11 00:42:09,614][98559] Updated weights for policy 0, policy_version 96540 (0.0009) -[2023-10-11 00:42:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 197033984. Throughput: 0: 1722.3, 1: 1700.6. Samples: 49259006. Policy #0 lag: (min: 0.0, avg: 29.2, max: 32.0) -[2023-10-11 00:42:10,557][97672] Avg episode reward: [(0, '-0.540'), (1, '22.480')] -[2023-10-11 00:42:13,458][98560] Updated weights for policy 1, policy_version 95882 (0.0007) -[2023-10-11 00:42:13,630][98559] Updated weights for policy 0, policy_version 96550 (0.0008) -[2023-10-11 00:42:13,825][98560] Updated weights for policy 1, policy_version 95892 (0.0009) -[2023-10-11 00:42:14,013][98559] Updated weights for policy 0, policy_version 96560 (0.0009) -[2023-10-11 00:42:14,195][98560] Updated weights for policy 1, policy_version 95902 (0.0009) -[2023-10-11 00:42:14,372][98559] Updated weights for policy 0, policy_version 96570 (0.0008) -[2023-10-11 00:42:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 197099520. Throughput: 0: 1702.5, 1: 1685.1. Samples: 49278442. Policy #0 lag: (min: 0.0, avg: 29.2, max: 32.0) -[2023-10-11 00:42:15,557][97672] Avg episode reward: [(0, '-0.540'), (1, '22.520')] -[2023-10-11 00:42:18,026][98560] Updated weights for policy 1, policy_version 95912 (0.0009) -[2023-10-11 00:42:18,405][98560] Updated weights for policy 1, policy_version 95922 (0.0008) -[2023-10-11 00:42:18,457][98559] Updated weights for policy 0, policy_version 96580 (0.0010) -[2023-10-11 00:42:18,778][98560] Updated weights for policy 1, policy_version 95932 (0.0008) -[2023-10-11 00:42:18,817][98559] Updated weights for policy 0, policy_version 96590 (0.0009) -[2023-10-11 00:42:19,187][98559] Updated weights for policy 0, policy_version 96600 (0.0010) -[2023-10-11 00:42:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 197165056. Throughput: 0: 1695.3, 1: 1686.2. Samples: 49298666. Policy #0 lag: (min: 0.0, avg: 29.2, max: 32.0) -[2023-10-11 00:42:20,557][97672] Avg episode reward: [(0, '-0.540'), (1, '22.560')] -[2023-10-11 00:42:22,673][98560] Updated weights for policy 1, policy_version 95942 (0.0008) -[2023-10-11 00:42:23,035][98560] Updated weights for policy 1, policy_version 95952 (0.0010) -[2023-10-11 00:42:23,302][98559] Updated weights for policy 0, policy_version 96610 (0.0008) -[2023-10-11 00:42:23,402][98560] Updated weights for policy 1, policy_version 95962 (0.0008) -[2023-10-11 00:42:23,669][98559] Updated weights for policy 0, policy_version 96620 (0.0008) -[2023-10-11 00:42:24,047][98559] Updated weights for policy 0, policy_version 96630 (0.0008) -[2023-10-11 00:42:24,410][98559] Updated weights for policy 0, policy_version 96640 (0.0009) -[2023-10-11 00:42:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 197230592. Throughput: 0: 1710.5, 1: 1707.8. Samples: 49310198. Policy #0 lag: (min: 0.0, avg: 29.2, max: 32.0) -[2023-10-11 00:42:25,557][97672] Avg episode reward: [(0, '-0.560'), (1, '22.560')] -[2023-10-11 00:42:27,562][98560] Updated weights for policy 1, policy_version 95972 (0.0008) -[2023-10-11 00:42:27,938][98560] Updated weights for policy 1, policy_version 95982 (0.0008) -[2023-10-11 00:42:28,293][98560] Updated weights for policy 1, policy_version 95992 (0.0008) -[2023-10-11 00:42:28,297][98559] Updated weights for policy 0, policy_version 96650 (0.0008) -[2023-10-11 00:42:28,665][98559] Updated weights for policy 0, policy_version 96660 (0.0007) -[2023-10-11 00:42:29,026][98559] Updated weights for policy 0, policy_version 96670 (0.0008) -[2023-10-11 00:42:30,556][97672] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 197296128. Throughput: 0: 1693.6, 1: 1687.6. Samples: 49329240. Policy #0 lag: (min: 0.0, avg: 29.2, max: 32.0) -[2023-10-11 00:42:30,556][97672] Avg episode reward: [(0, '-0.560'), (1, '22.520')] -[2023-10-11 00:42:32,240][98560] Updated weights for policy 1, policy_version 96002 (0.0008) -[2023-10-11 00:42:32,602][98560] Updated weights for policy 1, policy_version 96012 (0.0009) -[2023-10-11 00:42:32,973][98560] Updated weights for policy 1, policy_version 96022 (0.0009) -[2023-10-11 00:42:33,107][98559] Updated weights for policy 0, policy_version 96680 (0.0008) -[2023-10-11 00:42:33,336][98560] Updated weights for policy 1, policy_version 96032 (0.0009) -[2023-10-11 00:42:33,486][98559] Updated weights for policy 0, policy_version 96690 (0.0009) -[2023-10-11 00:42:33,837][98559] Updated weights for policy 0, policy_version 96700 (0.0007) -[2023-10-11 00:42:35,556][97672] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 197361664. Throughput: 0: 1715.6, 1: 1706.6. Samples: 49350330. Policy #0 lag: (min: 0.0, avg: 29.2, max: 32.0) -[2023-10-11 00:42:35,556][97672] Avg episode reward: [(0, '-0.560'), (1, '22.520')] -[2023-10-11 00:42:35,566][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000096704_99024896.pth... -[2023-10-11 00:42:35,566][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000096032_98336768.pth... -[2023-10-11 00:42:35,604][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000095104_97386496.pth -[2023-10-11 00:42:35,607][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000094464_96731136.pth -[2023-10-11 00:42:37,518][98560] Updated weights for policy 1, policy_version 96042 (0.0008) -[2023-10-11 00:42:37,845][98559] Updated weights for policy 0, policy_version 96710 (0.0008) -[2023-10-11 00:42:37,887][98560] Updated weights for policy 1, policy_version 96052 (0.0007) -[2023-10-11 00:42:38,211][98559] Updated weights for policy 0, policy_version 96720 (0.0007) -[2023-10-11 00:42:38,256][98560] Updated weights for policy 1, policy_version 96062 (0.0008) -[2023-10-11 00:42:38,569][98559] Updated weights for policy 0, policy_version 96730 (0.0007) -[2023-10-11 00:42:40,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 197427200. Throughput: 0: 1707.1, 1: 1702.9. Samples: 49360736. Policy #0 lag: (min: 0.0, avg: 29.2, max: 32.0) -[2023-10-11 00:42:40,556][97672] Avg episode reward: [(0, '-0.560'), (1, '22.560')] -[2023-10-11 00:42:42,323][98560] Updated weights for policy 1, policy_version 96072 (0.0009) -[2023-10-11 00:42:42,481][98559] Updated weights for policy 0, policy_version 96740 (0.0007) -[2023-10-11 00:42:42,692][98560] Updated weights for policy 1, policy_version 96082 (0.0009) -[2023-10-11 00:42:42,844][98559] Updated weights for policy 0, policy_version 96750 (0.0008) -[2023-10-11 00:42:43,061][98560] Updated weights for policy 1, policy_version 96092 (0.0008) -[2023-10-11 00:42:43,206][98559] Updated weights for policy 0, policy_version 96760 (0.0009) -[2023-10-11 00:42:45,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 197492736. Throughput: 0: 1699.6, 1: 1694.7. Samples: 49380478. Policy #0 lag: (min: 0.0, avg: 29.2, max: 32.0) -[2023-10-11 00:42:45,557][97672] Avg episode reward: [(0, '-0.560'), (1, '22.620')] -[2023-10-11 00:42:47,000][98559] Updated weights for policy 0, policy_version 96770 (0.0008) -[2023-10-11 00:42:47,059][98560] Updated weights for policy 1, policy_version 96102 (0.0009) -[2023-10-11 00:42:47,359][98559] Updated weights for policy 0, policy_version 96780 (0.0009) -[2023-10-11 00:42:47,435][98560] Updated weights for policy 1, policy_version 96112 (0.0008) -[2023-10-11 00:42:47,721][98559] Updated weights for policy 0, policy_version 96790 (0.0009) -[2023-10-11 00:42:47,804][98560] Updated weights for policy 1, policy_version 96122 (0.0008) -[2023-10-11 00:42:48,090][98559] Updated weights for policy 0, policy_version 96800 (0.0008) -[2023-10-11 00:42:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 197558272. Throughput: 0: 1718.0, 1: 1719.1. Samples: 49401614. Policy #0 lag: (min: 1.0, avg: 2.0, max: 16.0) -[2023-10-11 00:42:50,556][97672] Avg episode reward: [(0, '-0.560'), (1, '22.580')] -[2023-10-11 00:42:51,746][98560] Updated weights for policy 1, policy_version 96132 (0.0009) -[2023-10-11 00:42:52,077][98559] Updated weights for policy 0, policy_version 96810 (0.0009) -[2023-10-11 00:42:52,118][98560] Updated weights for policy 1, policy_version 96142 (0.0008) -[2023-10-11 00:42:52,439][98559] Updated weights for policy 0, policy_version 96820 (0.0009) -[2023-10-11 00:42:52,497][98560] Updated weights for policy 1, policy_version 96152 (0.0008) -[2023-10-11 00:42:52,803][98559] Updated weights for policy 0, policy_version 96830 (0.0009) -[2023-10-11 00:42:55,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13662.6). Total num frames: 197623808. Throughput: 0: 1687.4, 1: 1689.3. Samples: 49410960. Policy #0 lag: (min: 1.0, avg: 2.0, max: 16.0) -[2023-10-11 00:42:55,556][97672] Avg episode reward: [(0, '-0.560'), (1, '22.600')] -[2023-10-11 00:42:56,575][98560] Updated weights for policy 1, policy_version 96162 (0.0009) -[2023-10-11 00:42:56,769][98559] Updated weights for policy 0, policy_version 96840 (0.0008) -[2023-10-11 00:42:56,936][98560] Updated weights for policy 1, policy_version 96172 (0.0007) -[2023-10-11 00:42:57,135][98559] Updated weights for policy 0, policy_version 96850 (0.0008) -[2023-10-11 00:42:57,310][98560] Updated weights for policy 1, policy_version 96182 (0.0009) -[2023-10-11 00:42:57,494][98559] Updated weights for policy 0, policy_version 96860 (0.0007) -[2023-10-11 00:42:57,667][98560] Updated weights for policy 1, policy_version 96192 (0.0007) -[2023-10-11 00:43:00,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 197689344. Throughput: 0: 1712.7, 1: 1695.7. Samples: 49431816. Policy #0 lag: (min: 1.0, avg: 2.0, max: 16.0) -[2023-10-11 00:43:00,556][97672] Avg episode reward: [(0, '-0.560'), (1, '22.620')] -[2023-10-11 00:43:01,710][98560] Updated weights for policy 1, policy_version 96202 (0.0009) -[2023-10-11 00:43:01,720][98559] Updated weights for policy 0, policy_version 96870 (0.0009) -[2023-10-11 00:43:02,077][98560] Updated weights for policy 1, policy_version 96212 (0.0008) -[2023-10-11 00:43:02,093][98559] Updated weights for policy 0, policy_version 96880 (0.0010) -[2023-10-11 00:43:02,454][98560] Updated weights for policy 1, policy_version 96222 (0.0010) -[2023-10-11 00:43:02,469][98559] Updated weights for policy 0, policy_version 96890 (0.0008) -[2023-10-11 00:43:05,556][97672] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 197754880. Throughput: 0: 1714.8, 1: 1704.4. Samples: 49452526. Policy #0 lag: (min: 1.0, avg: 2.0, max: 16.0) -[2023-10-11 00:43:05,557][97672] Avg episode reward: [(0, '-0.560'), (1, '22.600')] -[2023-10-11 00:43:06,528][98560] Updated weights for policy 1, policy_version 96232 (0.0008) -[2023-10-11 00:43:06,573][98559] Updated weights for policy 0, policy_version 96900 (0.0008) -[2023-10-11 00:43:06,895][98560] Updated weights for policy 1, policy_version 96242 (0.0007) -[2023-10-11 00:43:06,933][98559] Updated weights for policy 0, policy_version 96910 (0.0008) -[2023-10-11 00:43:07,267][98560] Updated weights for policy 1, policy_version 96252 (0.0009) -[2023-10-11 00:43:07,300][98559] Updated weights for policy 0, policy_version 96920 (0.0009) -[2023-10-11 00:43:10,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 197820416. Throughput: 0: 1691.6, 1: 1677.9. Samples: 49461824. Policy #0 lag: (min: 1.0, avg: 2.0, max: 16.0) -[2023-10-11 00:43:10,557][97672] Avg episode reward: [(0, '-0.560'), (1, '22.620')] -[2023-10-11 00:43:11,177][98559] Updated weights for policy 0, policy_version 96930 (0.0009) -[2023-10-11 00:43:11,430][98560] Updated weights for policy 1, policy_version 96262 (0.0009) -[2023-10-11 00:43:11,538][98559] Updated weights for policy 0, policy_version 96940 (0.0008) -[2023-10-11 00:43:11,794][98560] Updated weights for policy 1, policy_version 96272 (0.0008) -[2023-10-11 00:43:11,911][98559] Updated weights for policy 0, policy_version 96950 (0.0008) -[2023-10-11 00:43:12,158][98560] Updated weights for policy 1, policy_version 96282 (0.0007) -[2023-10-11 00:43:12,279][98559] Updated weights for policy 0, policy_version 96960 (0.0007) -[2023-10-11 00:43:15,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 197885952. Throughput: 0: 1711.5, 1: 1696.8. Samples: 49482612. Policy #0 lag: (min: 1.0, avg: 2.0, max: 16.0) -[2023-10-11 00:43:15,557][97672] Avg episode reward: [(0, '-0.560'), (1, '22.620')] -[2023-10-11 00:43:16,157][98560] Updated weights for policy 1, policy_version 96292 (0.0007) -[2023-10-11 00:43:16,266][98559] Updated weights for policy 0, policy_version 96970 (0.0007) -[2023-10-11 00:43:16,521][98560] Updated weights for policy 1, policy_version 96302 (0.0007) -[2023-10-11 00:43:16,632][98559] Updated weights for policy 0, policy_version 96980 (0.0009) -[2023-10-11 00:43:16,895][98560] Updated weights for policy 1, policy_version 96312 (0.0007) -[2023-10-11 00:43:16,995][98559] Updated weights for policy 0, policy_version 96990 (0.0010) -[2023-10-11 00:43:20,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 197951488. Throughput: 0: 1713.8, 1: 1697.8. Samples: 49503852. Policy #0 lag: (min: 1.0, avg: 2.0, max: 16.0) -[2023-10-11 00:43:20,558][97672] Avg episode reward: [(0, '-0.560'), (1, '22.680')] -[2023-10-11 00:43:20,913][98560] Updated weights for policy 1, policy_version 96322 (0.0008) -[2023-10-11 00:43:20,960][98559] Updated weights for policy 0, policy_version 97000 (0.0009) -[2023-10-11 00:43:21,273][98560] Updated weights for policy 1, policy_version 96332 (0.0007) -[2023-10-11 00:43:21,324][98559] Updated weights for policy 0, policy_version 97010 (0.0008) -[2023-10-11 00:43:21,641][98560] Updated weights for policy 1, policy_version 96342 (0.0007) -[2023-10-11 00:43:21,683][98559] Updated weights for policy 0, policy_version 97020 (0.0008) -[2023-10-11 00:43:22,008][98560] Updated weights for policy 1, policy_version 96352 (0.0007) -[2023-10-11 00:43:25,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 198017024. Throughput: 0: 1698.9, 1: 1685.5. Samples: 49513038. Policy #0 lag: (min: 1.0, avg: 2.0, max: 16.0) -[2023-10-11 00:43:25,558][97672] Avg episode reward: [(0, '-0.560'), (1, '22.680')] -[2023-10-11 00:43:25,747][98559] Updated weights for policy 0, policy_version 97030 (0.0008) -[2023-10-11 00:43:26,028][98560] Updated weights for policy 1, policy_version 96362 (0.0007) -[2023-10-11 00:43:26,113][98559] Updated weights for policy 0, policy_version 97040 (0.0007) -[2023-10-11 00:43:26,393][98560] Updated weights for policy 1, policy_version 96372 (0.0008) -[2023-10-11 00:43:26,475][98559] Updated weights for policy 0, policy_version 97050 (0.0008) -[2023-10-11 00:43:26,757][98560] Updated weights for policy 1, policy_version 96382 (0.0010) -[2023-10-11 00:43:30,556][97672] Fps is (10 sec: 13107.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 198082560. Throughput: 0: 1708.4, 1: 1703.4. Samples: 49534006. Policy #0 lag: (min: 1.0, avg: 2.0, max: 16.0) -[2023-10-11 00:43:30,556][97672] Avg episode reward: [(0, '-0.620'), (1, '22.680')] -[2023-10-11 00:43:30,608][98559] Updated weights for policy 0, policy_version 97060 (0.0007) -[2023-10-11 00:43:30,798][98560] Updated weights for policy 1, policy_version 96392 (0.0008) -[2023-10-11 00:43:30,971][98559] Updated weights for policy 0, policy_version 97070 (0.0007) -[2023-10-11 00:43:31,172][98560] Updated weights for policy 1, policy_version 96402 (0.0010) -[2023-10-11 00:43:31,345][98559] Updated weights for policy 0, policy_version 97080 (0.0007) -[2023-10-11 00:43:31,534][98560] Updated weights for policy 1, policy_version 96412 (0.0009) -[2023-10-11 00:43:35,425][98559] Updated weights for policy 0, policy_version 97090 (0.0007) -[2023-10-11 00:43:35,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 198148096. Throughput: 0: 1702.6, 1: 1695.4. Samples: 49554526. Policy #0 lag: (min: 1.0, avg: 2.0, max: 16.0) -[2023-10-11 00:43:35,557][97672] Avg episode reward: [(0, '-0.620'), (1, '22.720')] -[2023-10-11 00:43:35,605][98560] Updated weights for policy 1, policy_version 96422 (0.0009) -[2023-10-11 00:43:35,795][98559] Updated weights for policy 0, policy_version 97100 (0.0009) -[2023-10-11 00:43:35,980][98560] Updated weights for policy 1, policy_version 96432 (0.0009) -[2023-10-11 00:43:36,157][98559] Updated weights for policy 0, policy_version 97110 (0.0009) -[2023-10-11 00:43:36,337][98560] Updated weights for policy 1, policy_version 96442 (0.0009) -[2023-10-11 00:43:36,518][98559] Updated weights for policy 0, policy_version 97120 (0.0008) -[2023-10-11 00:43:40,450][98560] Updated weights for policy 1, policy_version 96452 (0.0009) -[2023-10-11 00:43:40,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 198213632. Throughput: 0: 1702.5, 1: 1688.8. Samples: 49563570. Policy #0 lag: (min: 1.0, avg: 2.0, max: 16.0) -[2023-10-11 00:43:40,556][97672] Avg episode reward: [(0, '-0.620'), (1, '22.740')] -[2023-10-11 00:43:40,594][98559] Updated weights for policy 0, policy_version 97130 (0.0008) -[2023-10-11 00:43:40,802][98560] Updated weights for policy 1, policy_version 96462 (0.0008) -[2023-10-11 00:43:40,954][98559] Updated weights for policy 0, policy_version 97140 (0.0008) -[2023-10-11 00:43:41,178][98560] Updated weights for policy 1, policy_version 96472 (0.0009) -[2023-10-11 00:43:41,321][98559] Updated weights for policy 0, policy_version 97150 (0.0008) -[2023-10-11 00:43:45,228][98560] Updated weights for policy 1, policy_version 96482 (0.0008) -[2023-10-11 00:43:45,259][98559] Updated weights for policy 0, policy_version 97160 (0.0009) -[2023-10-11 00:43:45,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 198279168. Throughput: 0: 1705.6, 1: 1691.8. Samples: 49584698. Policy #0 lag: (min: 1.0, avg: 2.0, max: 16.0) -[2023-10-11 00:43:45,557][97672] Avg episode reward: [(0, '-0.500'), (1, '22.680')] -[2023-10-11 00:43:45,594][98560] Updated weights for policy 1, policy_version 96492 (0.0008) -[2023-10-11 00:43:45,626][98559] Updated weights for policy 0, policy_version 97170 (0.0008) -[2023-10-11 00:43:45,975][98560] Updated weights for policy 1, policy_version 96502 (0.0009) -[2023-10-11 00:43:45,995][98559] Updated weights for policy 0, policy_version 97180 (0.0008) -[2023-10-11 00:43:46,328][98560] Updated weights for policy 1, policy_version 96512 (0.0007) -[2023-10-11 00:43:50,129][98559] Updated weights for policy 0, policy_version 97190 (0.0007) -[2023-10-11 00:43:50,378][98560] Updated weights for policy 1, policy_version 96522 (0.0007) -[2023-10-11 00:43:50,511][98559] Updated weights for policy 0, policy_version 97200 (0.0007) -[2023-10-11 00:43:50,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 198344704. Throughput: 0: 1698.4, 1: 1688.0. Samples: 49604918. Policy #0 lag: (min: 1.0, avg: 2.0, max: 16.0) -[2023-10-11 00:43:50,557][97672] Avg episode reward: [(0, '-0.500'), (1, '22.720')] -[2023-10-11 00:43:50,743][98560] Updated weights for policy 1, policy_version 96532 (0.0007) -[2023-10-11 00:43:50,871][98559] Updated weights for policy 0, policy_version 97210 (0.0008) -[2023-10-11 00:43:51,109][98560] Updated weights for policy 1, policy_version 96542 (0.0007) -[2023-10-11 00:43:54,859][98559] Updated weights for policy 0, policy_version 97220 (0.0009) -[2023-10-11 00:43:55,174][98560] Updated weights for policy 1, policy_version 96552 (0.0008) -[2023-10-11 00:43:55,223][98559] Updated weights for policy 0, policy_version 97230 (0.0009) -[2023-10-11 00:43:55,540][98560] Updated weights for policy 1, policy_version 96562 (0.0007) -[2023-10-11 00:43:55,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 198410240. Throughput: 0: 1709.2, 1: 1688.9. Samples: 49614738. Policy #0 lag: (min: 28.0, avg: 35.5, max: 60.0) -[2023-10-11 00:43:55,557][97672] Avg episode reward: [(0, '-0.500'), (1, '22.560')] -[2023-10-11 00:43:55,594][98559] Updated weights for policy 0, policy_version 97240 (0.0007) -[2023-10-11 00:43:55,896][98560] Updated weights for policy 1, policy_version 96572 (0.0007) -[2023-10-11 00:43:59,634][98559] Updated weights for policy 0, policy_version 97250 (0.0008) -[2023-10-11 00:43:59,941][98560] Updated weights for policy 1, policy_version 96582 (0.0010) -[2023-10-11 00:43:59,998][98559] Updated weights for policy 0, policy_version 97260 (0.0008) -[2023-10-11 00:44:00,310][98560] Updated weights for policy 1, policy_version 96592 (0.0008) -[2023-10-11 00:44:00,369][98559] Updated weights for policy 0, policy_version 97270 (0.0007) -[2023-10-11 00:44:00,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 198475776. Throughput: 0: 1710.3, 1: 1686.2. Samples: 49635452. Policy #0 lag: (min: 28.0, avg: 35.5, max: 60.0) -[2023-10-11 00:44:00,557][97672] Avg episode reward: [(0, '-0.500'), (1, '22.600')] -[2023-10-11 00:44:00,665][98560] Updated weights for policy 1, policy_version 96602 (0.0007) -[2023-10-11 00:44:00,731][98559] Updated weights for policy 0, policy_version 97280 (0.0009) -[2023-10-11 00:44:04,491][98559] Updated weights for policy 0, policy_version 97290 (0.0010) -[2023-10-11 00:44:04,792][98560] Updated weights for policy 1, policy_version 96612 (0.0009) -[2023-10-11 00:44:04,852][98559] Updated weights for policy 0, policy_version 97300 (0.0010) -[2023-10-11 00:44:05,155][98560] Updated weights for policy 1, policy_version 96622 (0.0008) -[2023-10-11 00:44:05,222][98559] Updated weights for policy 0, policy_version 97310 (0.0009) -[2023-10-11 00:44:05,525][98560] Updated weights for policy 1, policy_version 96632 (0.0008) -[2023-10-11 00:44:05,556][97672] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 198574080. Throughput: 0: 1681.8, 1: 1675.5. Samples: 49654928. Policy #0 lag: (min: 28.0, avg: 35.5, max: 60.0) -[2023-10-11 00:44:05,557][97672] Avg episode reward: [(0, '-0.500'), (1, '22.600')] -[2023-10-11 00:44:09,230][98559] Updated weights for policy 0, policy_version 97320 (0.0010) -[2023-10-11 00:44:09,412][98560] Updated weights for policy 1, policy_version 96642 (0.0009) -[2023-10-11 00:44:09,590][98559] Updated weights for policy 0, policy_version 97330 (0.0009) -[2023-10-11 00:44:09,770][98560] Updated weights for policy 1, policy_version 96652 (0.0008) -[2023-10-11 00:44:09,963][98559] Updated weights for policy 0, policy_version 97340 (0.0008) -[2023-10-11 00:44:10,141][98560] Updated weights for policy 1, policy_version 96662 (0.0008) -[2023-10-11 00:44:10,499][98560] Updated weights for policy 1, policy_version 96672 (0.0009) -[2023-10-11 00:44:10,556][97672] Fps is (10 sec: 19660.5, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 198672384. Throughput: 0: 1712.7, 1: 1675.3. Samples: 49665496. Policy #0 lag: (min: 28.0, avg: 35.5, max: 60.0) -[2023-10-11 00:44:10,557][97672] Avg episode reward: [(0, '-0.520'), (1, '22.540')] -[2023-10-11 00:44:14,015][98559] Updated weights for policy 0, policy_version 97350 (0.0008) -[2023-10-11 00:44:14,377][98559] Updated weights for policy 0, policy_version 97360 (0.0010) -[2023-10-11 00:44:14,696][98560] Updated weights for policy 1, policy_version 96682 (0.0009) -[2023-10-11 00:44:14,743][98559] Updated weights for policy 0, policy_version 97370 (0.0008) -[2023-10-11 00:44:15,058][98560] Updated weights for policy 1, policy_version 96692 (0.0008) -[2023-10-11 00:44:15,420][98560] Updated weights for policy 1, policy_version 96702 (0.0010) -[2023-10-11 00:44:15,556][97672] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 198737920. Throughput: 0: 1698.2, 1: 1674.7. Samples: 49685786. Policy #0 lag: (min: 28.0, avg: 35.5, max: 60.0) -[2023-10-11 00:44:15,557][97672] Avg episode reward: [(0, '-0.520'), (1, '22.540')] -[2023-10-11 00:44:18,639][98559] Updated weights for policy 0, policy_version 97380 (0.0009) -[2023-10-11 00:44:19,011][98559] Updated weights for policy 0, policy_version 97390 (0.0008) -[2023-10-11 00:44:19,377][98559] Updated weights for policy 0, policy_version 97400 (0.0008) -[2023-10-11 00:44:19,383][98560] Updated weights for policy 1, policy_version 96712 (0.0007) -[2023-10-11 00:44:19,745][98560] Updated weights for policy 1, policy_version 96722 (0.0007) -[2023-10-11 00:44:20,116][98560] Updated weights for policy 1, policy_version 96732 (0.0009) -[2023-10-11 00:44:20,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 198803456. Throughput: 0: 1693.9, 1: 1667.4. Samples: 49705782. Policy #0 lag: (min: 28.0, avg: 35.5, max: 60.0) -[2023-10-11 00:44:20,557][97672] Avg episode reward: [(0, '-0.500'), (1, '22.600')] -[2023-10-11 00:44:23,171][98559] Updated weights for policy 0, policy_version 97410 (0.0009) -[2023-10-11 00:44:23,532][98559] Updated weights for policy 0, policy_version 97420 (0.0009) -[2023-10-11 00:44:23,892][98559] Updated weights for policy 0, policy_version 97430 (0.0009) -[2023-10-11 00:44:24,078][98560] Updated weights for policy 1, policy_version 96742 (0.0010) -[2023-10-11 00:44:24,265][98559] Updated weights for policy 0, policy_version 97440 (0.0009) -[2023-10-11 00:44:24,462][98560] Updated weights for policy 1, policy_version 96752 (0.0009) -[2023-10-11 00:44:24,830][98560] Updated weights for policy 1, policy_version 96762 (0.0010) -[2023-10-11 00:44:25,556][97672] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 198868992. Throughput: 0: 1720.1, 1: 1688.0. Samples: 49716936. Policy #0 lag: (min: 28.0, avg: 35.5, max: 60.0) -[2023-10-11 00:44:25,557][97672] Avg episode reward: [(0, '-0.500'), (1, '22.640')] -[2023-10-11 00:44:28,306][98559] Updated weights for policy 0, policy_version 97450 (0.0010) -[2023-10-11 00:44:28,686][98559] Updated weights for policy 0, policy_version 97460 (0.0007) -[2023-10-11 00:44:28,862][98560] Updated weights for policy 1, policy_version 96772 (0.0009) -[2023-10-11 00:44:29,046][98559] Updated weights for policy 0, policy_version 97470 (0.0007) -[2023-10-11 00:44:29,233][98560] Updated weights for policy 1, policy_version 96782 (0.0008) -[2023-10-11 00:44:29,595][98560] Updated weights for policy 1, policy_version 96792 (0.0009) -[2023-10-11 00:44:30,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 198934528. Throughput: 0: 1690.0, 1: 1689.3. Samples: 49736768. Policy #0 lag: (min: 28.0, avg: 35.5, max: 60.0) -[2023-10-11 00:44:30,557][97672] Avg episode reward: [(0, '-0.500'), (1, '22.580')] -[2023-10-11 00:44:33,120][98559] Updated weights for policy 0, policy_version 97480 (0.0009) -[2023-10-11 00:44:33,490][98559] Updated weights for policy 0, policy_version 97490 (0.0010) -[2023-10-11 00:44:33,644][98560] Updated weights for policy 1, policy_version 96802 (0.0009) -[2023-10-11 00:44:33,850][98559] Updated weights for policy 0, policy_version 97500 (0.0008) -[2023-10-11 00:44:34,015][98560] Updated weights for policy 1, policy_version 96812 (0.0007) -[2023-10-11 00:44:34,386][98560] Updated weights for policy 1, policy_version 96822 (0.0010) -[2023-10-11 00:44:34,748][98560] Updated weights for policy 1, policy_version 96832 (0.0009) -[2023-10-11 00:44:35,556][97672] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 199000064. Throughput: 0: 1700.9, 1: 1666.1. Samples: 49756434. Policy #0 lag: (min: 28.0, avg: 35.5, max: 60.0) -[2023-10-11 00:44:35,558][97672] Avg episode reward: [(0, '-0.500'), (1, '22.520')] -[2023-10-11 00:44:35,570][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000096832_99155968.pth... -[2023-10-11 00:44:35,570][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000097504_99844096.pth... -[2023-10-11 00:44:35,607][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000095904_98205696.pth -[2023-10-11 00:44:35,608][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000095232_97517568.pth -[2023-10-11 00:44:37,961][98559] Updated weights for policy 0, policy_version 97510 (0.0009) -[2023-10-11 00:44:38,345][98559] Updated weights for policy 0, policy_version 97520 (0.0008) -[2023-10-11 00:44:38,707][98559] Updated weights for policy 0, policy_version 97530 (0.0007) -[2023-10-11 00:44:38,883][98560] Updated weights for policy 1, policy_version 96842 (0.0009) -[2023-10-11 00:44:39,245][98560] Updated weights for policy 1, policy_version 96852 (0.0007) -[2023-10-11 00:44:39,600][98560] Updated weights for policy 1, policy_version 96862 (0.0008) -[2023-10-11 00:44:40,556][97672] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 199065600. Throughput: 0: 1702.4, 1: 1689.4. Samples: 49767372. Policy #0 lag: (min: 28.0, avg: 35.5, max: 60.0) -[2023-10-11 00:44:40,557][97672] Avg episode reward: [(0, '-0.500'), (1, '22.560')] -[2023-10-11 00:44:42,665][98559] Updated weights for policy 0, policy_version 97540 (0.0007) -[2023-10-11 00:44:43,034][98559] Updated weights for policy 0, policy_version 97550 (0.0008) -[2023-10-11 00:44:43,401][98559] Updated weights for policy 0, policy_version 97560 (0.0009) -[2023-10-11 00:44:43,615][98560] Updated weights for policy 1, policy_version 96872 (0.0008) -[2023-10-11 00:44:43,987][98560] Updated weights for policy 1, policy_version 96882 (0.0009) -[2023-10-11 00:44:44,362][98560] Updated weights for policy 1, policy_version 96892 (0.0009) -[2023-10-11 00:44:45,556][97672] Fps is (10 sec: 13108.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 199131136. Throughput: 0: 1687.8, 1: 1688.5. Samples: 49787386. Policy #0 lag: (min: 28.0, avg: 35.5, max: 60.0) -[2023-10-11 00:44:45,556][97672] Avg episode reward: [(0, '-0.520'), (1, '22.520')] -[2023-10-11 00:44:47,319][98559] Updated weights for policy 0, policy_version 97570 (0.0009) -[2023-10-11 00:44:47,677][98559] Updated weights for policy 0, policy_version 97580 (0.0010) -[2023-10-11 00:44:48,044][98559] Updated weights for policy 0, policy_version 97590 (0.0009) -[2023-10-11 00:44:48,403][98559] Updated weights for policy 0, policy_version 97600 (0.0008) -[2023-10-11 00:44:48,458][98560] Updated weights for policy 1, policy_version 96902 (0.0009) -[2023-10-11 00:44:48,829][98560] Updated weights for policy 1, policy_version 96912 (0.0008) -[2023-10-11 00:44:49,193][98560] Updated weights for policy 1, policy_version 96922 (0.0008) -[2023-10-11 00:44:50,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 199196672. Throughput: 0: 1715.9, 1: 1680.2. Samples: 49807752. Policy #0 lag: (min: 28.0, avg: 35.5, max: 60.0) -[2023-10-11 00:44:50,556][97672] Avg episode reward: [(0, '-0.520'), (1, '22.480')] -[2023-10-11 00:44:52,473][98559] Updated weights for policy 0, policy_version 97610 (0.0008) -[2023-10-11 00:44:52,835][98559] Updated weights for policy 0, policy_version 97620 (0.0007) -[2023-10-11 00:44:53,203][98559] Updated weights for policy 0, policy_version 97630 (0.0008) -[2023-10-11 00:44:53,217][98560] Updated weights for policy 1, policy_version 96932 (0.0009) -[2023-10-11 00:44:53,581][98560] Updated weights for policy 1, policy_version 96942 (0.0007) -[2023-10-11 00:44:53,954][98560] Updated weights for policy 1, policy_version 96952 (0.0008) -[2023-10-11 00:44:55,556][97672] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 199262208. Throughput: 0: 1688.1, 1: 1707.4. Samples: 49818290. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:44:55,556][97672] Avg episode reward: [(0, '-0.520'), (1, '22.480')] -[2023-10-11 00:44:57,018][98559] Updated weights for policy 0, policy_version 97640 (0.0008) -[2023-10-11 00:44:57,385][98559] Updated weights for policy 0, policy_version 97650 (0.0009) -[2023-10-11 00:44:57,746][98559] Updated weights for policy 0, policy_version 97660 (0.0008) -[2023-10-11 00:44:57,873][98560] Updated weights for policy 1, policy_version 96962 (0.0009) -[2023-10-11 00:44:58,247][98560] Updated weights for policy 1, policy_version 96972 (0.0010) -[2023-10-11 00:44:58,606][98560] Updated weights for policy 1, policy_version 96982 (0.0010) -[2023-10-11 00:44:58,974][98560] Updated weights for policy 1, policy_version 96992 (0.0009) -[2023-10-11 00:45:00,556][97672] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 199327744. Throughput: 0: 1712.0, 1: 1687.5. Samples: 49838760. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:45:00,557][97672] Avg episode reward: [(0, '-0.520'), (1, '22.460')] -[2023-10-11 00:45:01,763][98559] Updated weights for policy 0, policy_version 97670 (0.0008) -[2023-10-11 00:45:02,130][98559] Updated weights for policy 0, policy_version 97680 (0.0009) -[2023-10-11 00:45:02,490][98559] Updated weights for policy 0, policy_version 97690 (0.0008) -[2023-10-11 00:45:03,106][98560] Updated weights for policy 1, policy_version 97002 (0.0009) -[2023-10-11 00:45:03,472][98560] Updated weights for policy 1, policy_version 97012 (0.0007) -[2023-10-11 00:45:03,833][98560] Updated weights for policy 1, policy_version 97022 (0.0009) -[2023-10-11 00:45:05,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 199393280. Throughput: 0: 1719.9, 1: 1693.1. Samples: 49859366. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:45:05,557][97672] Avg episode reward: [(0, '-0.520'), (1, '22.400')] -[2023-10-11 00:45:06,599][98559] Updated weights for policy 0, policy_version 97700 (0.0008) -[2023-10-11 00:45:06,966][98559] Updated weights for policy 0, policy_version 97710 (0.0011) -[2023-10-11 00:45:07,332][98559] Updated weights for policy 0, policy_version 97720 (0.0009) -[2023-10-11 00:45:07,879][98560] Updated weights for policy 1, policy_version 97032 (0.0007) -[2023-10-11 00:45:08,250][98560] Updated weights for policy 1, policy_version 97042 (0.0007) -[2023-10-11 00:45:08,607][98560] Updated weights for policy 1, policy_version 97052 (0.0009) -[2023-10-11 00:45:10,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 199458816. Throughput: 0: 1691.8, 1: 1705.0. Samples: 49869792. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:45:10,557][97672] Avg episode reward: [(0, '-0.520'), (1, '22.340')] -[2023-10-11 00:45:11,369][98559] Updated weights for policy 0, policy_version 97730 (0.0009) -[2023-10-11 00:45:11,730][98559] Updated weights for policy 0, policy_version 97740 (0.0007) -[2023-10-11 00:45:12,097][98559] Updated weights for policy 0, policy_version 97750 (0.0008) -[2023-10-11 00:45:12,462][98559] Updated weights for policy 0, policy_version 97760 (0.0010) -[2023-10-11 00:45:12,656][98560] Updated weights for policy 1, policy_version 97062 (0.0010) -[2023-10-11 00:45:13,036][98560] Updated weights for policy 1, policy_version 97072 (0.0010) -[2023-10-11 00:45:13,397][98560] Updated weights for policy 1, policy_version 97082 (0.0007) -[2023-10-11 00:45:15,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 199524352. Throughput: 0: 1715.3, 1: 1680.6. Samples: 49889584. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:45:15,557][97672] Avg episode reward: [(0, '-0.520'), (1, '22.320')] -[2023-10-11 00:45:16,454][98559] Updated weights for policy 0, policy_version 97770 (0.0011) -[2023-10-11 00:45:16,815][98559] Updated weights for policy 0, policy_version 97780 (0.0009) -[2023-10-11 00:45:17,177][98559] Updated weights for policy 0, policy_version 97790 (0.0009) -[2023-10-11 00:45:17,536][98560] Updated weights for policy 1, policy_version 97092 (0.0008) -[2023-10-11 00:45:17,943][98560] Updated weights for policy 1, policy_version 97102 (0.0008) -[2023-10-11 00:45:18,307][98560] Updated weights for policy 1, policy_version 97112 (0.0007) -[2023-10-11 00:45:20,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 199589888. Throughput: 0: 1720.1, 1: 1703.0. Samples: 49910470. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:45:20,557][97672] Avg episode reward: [(0, '-0.520'), (1, '22.320')] -[2023-10-11 00:45:21,246][98559] Updated weights for policy 0, policy_version 97800 (0.0011) -[2023-10-11 00:45:21,605][98559] Updated weights for policy 0, policy_version 97810 (0.0009) -[2023-10-11 00:45:21,973][98559] Updated weights for policy 0, policy_version 97820 (0.0008) -[2023-10-11 00:45:22,320][98560] Updated weights for policy 1, policy_version 97122 (0.0008) -[2023-10-11 00:45:22,690][98560] Updated weights for policy 1, policy_version 97132 (0.0008) -[2023-10-11 00:45:23,054][98560] Updated weights for policy 1, policy_version 97142 (0.0007) -[2023-10-11 00:45:23,417][98560] Updated weights for policy 1, policy_version 97152 (0.0007) -[2023-10-11 00:45:25,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 199655424. Throughput: 0: 1702.4, 1: 1698.8. Samples: 49920428. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:45:25,557][97672] Avg episode reward: [(0, '-0.540'), (1, '22.420')] -[2023-10-11 00:45:26,035][98559] Updated weights for policy 0, policy_version 97830 (0.0008) -[2023-10-11 00:45:26,401][98559] Updated weights for policy 0, policy_version 97840 (0.0007) -[2023-10-11 00:45:26,766][98559] Updated weights for policy 0, policy_version 97850 (0.0007) -[2023-10-11 00:45:27,273][98560] Updated weights for policy 1, policy_version 97162 (0.0007) -[2023-10-11 00:45:27,642][98560] Updated weights for policy 1, policy_version 97172 (0.0009) -[2023-10-11 00:45:28,013][98560] Updated weights for policy 1, policy_version 97182 (0.0008) -[2023-10-11 00:45:30,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 199720960. Throughput: 0: 1717.0, 1: 1693.0. Samples: 49940836. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:45:30,556][97672] Avg episode reward: [(0, '-0.500'), (1, '22.520')] -[2023-10-11 00:45:30,710][98559] Updated weights for policy 0, policy_version 97860 (0.0009) -[2023-10-11 00:45:31,076][98559] Updated weights for policy 0, policy_version 97870 (0.0010) -[2023-10-11 00:45:31,446][98559] Updated weights for policy 0, policy_version 97880 (0.0009) -[2023-10-11 00:45:32,032][98560] Updated weights for policy 1, policy_version 97192 (0.0007) -[2023-10-11 00:45:32,395][98560] Updated weights for policy 1, policy_version 97202 (0.0007) -[2023-10-11 00:45:32,757][98560] Updated weights for policy 1, policy_version 97212 (0.0009) -[2023-10-11 00:45:35,311][98559] Updated weights for policy 0, policy_version 97890 (0.0009) -[2023-10-11 00:45:35,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 199786496. Throughput: 0: 1717.8, 1: 1708.0. Samples: 49961914. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:45:35,557][97672] Avg episode reward: [(0, '-0.500'), (1, '22.540')] -[2023-10-11 00:45:35,679][98559] Updated weights for policy 0, policy_version 97900 (0.0009) -[2023-10-11 00:45:36,053][98559] Updated weights for policy 0, policy_version 97910 (0.0008) -[2023-10-11 00:45:36,414][98559] Updated weights for policy 0, policy_version 97920 (0.0009) -[2023-10-11 00:45:36,750][98560] Updated weights for policy 1, policy_version 97222 (0.0008) -[2023-10-11 00:45:37,115][98560] Updated weights for policy 1, policy_version 97232 (0.0010) -[2023-10-11 00:45:37,483][98560] Updated weights for policy 1, policy_version 97242 (0.0008) -[2023-10-11 00:45:40,450][98559] Updated weights for policy 0, policy_version 97930 (0.0011) -[2023-10-11 00:45:40,556][97672] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 199852032. Throughput: 0: 1719.3, 1: 1682.1. Samples: 49971354. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:45:40,556][97672] Avg episode reward: [(0, '-0.480'), (1, '22.520')] -[2023-10-11 00:45:40,815][98559] Updated weights for policy 0, policy_version 97940 (0.0010) -[2023-10-11 00:45:41,183][98559] Updated weights for policy 0, policy_version 97950 (0.0011) -[2023-10-11 00:45:41,517][98560] Updated weights for policy 1, policy_version 97252 (0.0010) -[2023-10-11 00:45:41,889][98560] Updated weights for policy 1, policy_version 97262 (0.0007) -[2023-10-11 00:45:42,250][98560] Updated weights for policy 1, policy_version 97272 (0.0009) -[2023-10-11 00:45:45,029][98559] Updated weights for policy 0, policy_version 97960 (0.0009) -[2023-10-11 00:45:45,398][98559] Updated weights for policy 0, policy_version 97970 (0.0007) -[2023-10-11 00:45:45,556][97672] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 199917568. Throughput: 0: 1713.6, 1: 1699.7. Samples: 49992360. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:45:45,557][97672] Avg episode reward: [(0, '-0.480'), (1, '22.500')] -[2023-10-11 00:45:45,757][98559] Updated weights for policy 0, policy_version 97980 (0.0008) -[2023-10-11 00:45:46,157][98560] Updated weights for policy 1, policy_version 97282 (0.0008) -[2023-10-11 00:45:46,530][98560] Updated weights for policy 1, policy_version 97292 (0.0009) -[2023-10-11 00:45:46,897][98560] Updated weights for policy 1, policy_version 97302 (0.0009) -[2023-10-11 00:45:47,257][98560] Updated weights for policy 1, policy_version 97312 (0.0008) -[2023-10-11 00:45:49,774][98559] Updated weights for policy 0, policy_version 97990 (0.0008) -[2023-10-11 00:45:50,141][98559] Updated weights for policy 0, policy_version 98000 (0.0008) -[2023-10-11 00:45:50,508][98559] Updated weights for policy 0, policy_version 98010 (0.0007) -[2023-10-11 00:45:50,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 199983104. Throughput: 0: 1699.4, 1: 1708.0. Samples: 50012698. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-11 00:45:50,556][97672] Avg episode reward: [(0, '-0.480'), (1, '22.500')] -[2023-10-11 00:45:51,267][98560] Updated weights for policy 1, policy_version 97322 (0.0007) -[2023-10-11 00:45:51,638][98560] Updated weights for policy 1, policy_version 97332 (0.0008) -[2023-10-11 00:45:52,001][98560] Updated weights for policy 1, policy_version 97342 (0.0008) -[2023-10-11 00:45:54,395][98559] Updated weights for policy 0, policy_version 98020 (0.0008) -[2023-10-11 00:45:54,765][98559] Updated weights for policy 0, policy_version 98030 (0.0010) -[2023-10-11 00:45:55,128][98559] Updated weights for policy 0, policy_version 98040 (0.0008) -[2023-10-11 00:45:55,556][97672] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 200081408. Throughput: 0: 1726.2, 1: 1678.3. Samples: 50022996. Policy #0 lag: (min: 31.0, avg: 31.2, max: 40.0) -[2023-10-11 00:45:55,557][97672] Avg episode reward: [(0, '-0.480'), (1, '22.500')] -[2023-10-11 00:45:55,973][98560] Updated weights for policy 1, policy_version 97352 (0.0009) -[2023-10-11 00:45:56,338][98560] Updated weights for policy 1, policy_version 97362 (0.0010) -[2023-10-11 00:45:56,698][98560] Updated weights for policy 1, policy_version 97372 (0.0007) -[2023-10-11 00:45:59,147][98559] Updated weights for policy 0, policy_version 98050 (0.0007) -[2023-10-11 00:45:59,510][98559] Updated weights for policy 0, policy_version 98060 (0.0010) -[2023-10-11 00:45:59,873][98559] Updated weights for policy 0, policy_version 98070 (0.0009) -[2023-10-11 00:46:00,234][98559] Updated weights for policy 0, policy_version 98080 (0.0008) -[2023-10-11 00:46:00,507][98560] Updated weights for policy 1, policy_version 97382 (0.0007) -[2023-10-11 00:46:00,556][97672] Fps is (10 sec: 16383.8, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 200146944. Throughput: 0: 1722.3, 1: 1708.7. Samples: 50043980. Policy #0 lag: (min: 31.0, avg: 31.2, max: 40.0) -[2023-10-11 00:46:00,557][97672] Avg episode reward: [(0, '-0.480'), (1, '22.580')] -[2023-10-11 00:46:00,872][98560] Updated weights for policy 1, policy_version 97392 (0.0008) -[2023-10-11 00:46:01,233][98560] Updated weights for policy 1, policy_version 97402 (0.0009) -[2023-10-11 00:46:04,234][98559] Updated weights for policy 0, policy_version 98090 (0.0007) -[2023-10-11 00:46:04,590][98559] Updated weights for policy 0, policy_version 98100 (0.0010) -[2023-10-11 00:46:04,951][98559] Updated weights for policy 0, policy_version 98110 (0.0009) -[2023-10-11 00:46:05,321][98560] Updated weights for policy 1, policy_version 97412 (0.0007) -[2023-10-11 00:46:05,556][97672] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 200212480. Throughput: 0: 1700.0, 1: 1716.0. Samples: 50064190. Policy #0 lag: (min: 31.0, avg: 31.2, max: 40.0) -[2023-10-11 00:46:05,557][97672] Avg episode reward: [(0, '-0.480'), (1, '22.640')] -[2023-10-11 00:46:05,696][98560] Updated weights for policy 1, policy_version 97422 (0.0008) -[2023-10-11 00:46:06,070][98560] Updated weights for policy 1, policy_version 97432 (0.0010) -[2023-10-11 00:46:08,792][98559] Updated weights for policy 0, policy_version 98120 (0.0007) -[2023-10-11 00:46:09,154][98559] Updated weights for policy 0, policy_version 98130 (0.0009) -[2023-10-11 00:46:09,517][98559] Updated weights for policy 0, policy_version 98140 (0.0011) -[2023-10-11 00:46:10,090][98560] Updated weights for policy 1, policy_version 97442 (0.0010) -[2023-10-11 00:46:10,457][98560] Updated weights for policy 1, policy_version 97452 (0.0009) -[2023-10-11 00:46:10,556][97672] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 200278016. Throughput: 0: 1736.9, 1: 1692.8. Samples: 50074762. Policy #0 lag: (min: 31.0, avg: 31.2, max: 40.0) -[2023-10-11 00:46:10,557][97672] Avg episode reward: [(0, '-0.480'), (1, '22.620')] -[2023-10-11 00:46:10,823][98560] Updated weights for policy 1, policy_version 97462 (0.0008) -[2023-10-11 00:46:11,181][98560] Updated weights for policy 1, policy_version 97472 (0.0009) -[2023-10-11 00:46:13,364][98559] Updated weights for policy 0, policy_version 98150 (0.0008) -[2023-10-11 00:46:13,732][98559] Updated weights for policy 0, policy_version 98160 (0.0007) -[2023-10-11 00:46:14,098][98559] Updated weights for policy 0, policy_version 98170 (0.0009) -[2023-10-11 00:46:15,297][98560] Updated weights for policy 1, policy_version 97482 (0.0008) -[2023-10-11 00:46:15,556][97672] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 200343552. Throughput: 0: 1712.2, 1: 1708.1. Samples: 50094750. Policy #0 lag: (min: 31.0, avg: 31.2, max: 40.0) -[2023-10-11 00:46:15,556][97672] Avg episode reward: [(0, '-0.480'), (1, '22.560')] -[2023-10-11 00:46:15,656][98560] Updated weights for policy 1, policy_version 97492 (0.0008) -[2023-10-11 00:46:16,025][98560] Updated weights for policy 1, policy_version 97502 (0.0009) -[2023-10-11 00:46:17,975][98559] Updated weights for policy 0, policy_version 98180 (0.0007) -[2023-10-11 00:46:18,340][98559] Updated weights for policy 0, policy_version 98190 (0.0007) -[2023-10-11 00:46:18,709][98559] Updated weights for policy 0, policy_version 98200 (0.0007) -[2023-10-11 00:46:20,088][98560] Updated weights for policy 1, policy_version 97512 (0.0010) -[2023-10-11 00:46:20,449][98560] Updated weights for policy 1, policy_version 97522 (0.0009) -[2023-10-11 00:46:20,556][97672] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 200409088. Throughput: 0: 1711.8, 1: 1707.8. Samples: 50115798. Policy #0 lag: (min: 31.0, avg: 31.2, max: 40.0) -[2023-10-11 00:46:20,557][97672] Avg episode reward: [(0, '-0.480'), (1, '22.640')] -[2023-10-11 00:46:20,808][98560] Updated weights for policy 1, policy_version 97532 (0.0007) -[2023-10-11 00:46:22,716][98559] Updated weights for policy 0, policy_version 98210 (0.0010) -[2023-10-11 00:46:23,072][98559] Updated weights for policy 0, policy_version 98220 (0.0008) -[2023-10-11 00:46:23,440][98559] Updated weights for policy 0, policy_version 98230 (0.0009) -[2023-10-11 00:46:23,801][98559] Updated weights for policy 0, policy_version 98240 (0.0008) -[2023-10-11 00:46:24,681][98560] Updated weights for policy 1, policy_version 97542 (0.0010) -[2023-10-11 00:46:25,037][98560] Updated weights for policy 1, policy_version 97552 (0.0008) -[2023-10-11 00:46:25,406][98560] Updated weights for policy 1, policy_version 97562 (0.0009) -[2023-10-11 00:46:25,556][97672] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 200474624. Throughput: 0: 1724.4, 1: 1705.8. Samples: 50125714. Policy #0 lag: (min: 31.0, avg: 31.2, max: 40.0) -[2023-10-11 00:46:25,556][97672] Avg episode reward: [(0, '-0.480'), (1, '22.680')] -[2023-10-11 00:46:27,837][98559] Updated weights for policy 0, policy_version 98250 (0.0009) -[2023-10-11 00:46:28,200][98559] Updated weights for policy 0, policy_version 98260 (0.0011) -[2023-10-11 00:46:28,566][98559] Updated weights for policy 0, policy_version 98270 (0.0008) -[2023-10-11 00:46:29,379][98560] Updated weights for policy 1, policy_version 97572 (0.0008) -[2023-10-11 00:46:29,754][98560] Updated weights for policy 1, policy_version 97582 (0.0011) -[2023-10-11 00:46:30,116][98560] Updated weights for policy 1, policy_version 97592 (0.0010) -[2023-10-11 00:46:30,556][97672] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 200572928. Throughput: 0: 1709.3, 1: 1713.2. Samples: 50146374. Policy #0 lag: (min: 31.0, avg: 31.2, max: 40.0) -[2023-10-11 00:46:30,557][97672] Avg episode reward: [(0, '-0.520'), (1, '22.680')] -[2023-10-11 00:46:32,449][98559] Updated weights for policy 0, policy_version 98280 (0.0008) -[2023-10-11 00:46:32,818][98559] Updated weights for policy 0, policy_version 98290 (0.0008) -[2023-10-11 00:46:33,176][98559] Updated weights for policy 0, policy_version 98300 (0.0009) -[2023-10-11 00:46:34,158][98560] Updated weights for policy 1, policy_version 97602 (0.0007) -[2023-10-11 00:46:34,525][98560] Updated weights for policy 1, policy_version 97612 (0.0009) -[2023-10-11 00:46:34,890][98560] Updated weights for policy 1, policy_version 97622 (0.0012) -[2023-10-11 00:46:35,265][98560] Updated weights for policy 1, policy_version 97632 (0.0009) -[2023-10-11 00:46:35,556][97672] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 200638464. Throughput: 0: 1728.2, 1: 1698.5. Samples: 50166900. Policy #0 lag: (min: 31.0, avg: 31.2, max: 40.0) -[2023-10-11 00:46:35,557][97672] Avg episode reward: [(0, '-0.520'), (1, '22.760')] -[2023-10-11 00:46:35,565][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000097632_99975168.pth... -[2023-10-11 00:46:35,565][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000098304_100663296.pth... -[2023-10-11 00:46:35,595][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000096704_99024896.pth -[2023-10-11 00:46:35,605][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000096032_98336768.pth -[2023-10-11 00:46:37,203][98559] Updated weights for policy 0, policy_version 98310 (0.0009) -[2023-10-11 00:46:37,566][98559] Updated weights for policy 0, policy_version 98320 (0.0008) -[2023-10-11 00:46:37,932][98559] Updated weights for policy 0, policy_version 98330 (0.0008) -[2023-10-11 00:46:39,202][98560] Updated weights for policy 1, policy_version 97642 (0.0009) -[2023-10-11 00:46:39,567][98560] Updated weights for policy 1, policy_version 97652 (0.0009) -[2023-10-11 00:46:39,939][98560] Updated weights for policy 1, policy_version 97662 (0.0007) -[2023-10-11 00:46:40,556][97672] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 200704000. Throughput: 0: 1705.6, 1: 1716.8. Samples: 50177004. Policy #0 lag: (min: 31.0, avg: 31.2, max: 40.0) -[2023-10-11 00:46:40,558][97672] Avg episode reward: [(0, '-0.560'), (1, '22.760')] -[2023-10-11 00:46:41,904][98559] Updated weights for policy 0, policy_version 98340 (0.0010) -[2023-10-11 00:46:42,265][98559] Updated weights for policy 0, policy_version 98350 (0.0009) -[2023-10-11 00:46:42,641][98559] Updated weights for policy 0, policy_version 98360 (0.0009) -[2023-10-11 00:46:42,936][98597] Stopping RolloutWorker_w3... -[2023-10-11 00:46:42,936][98596] Stopping RolloutWorker_w1... -[2023-10-11 00:46:42,936][98601] Stopping RolloutWorker_w7... -[2023-10-11 00:46:42,936][98597] Loop rollout_proc3_evt_loop terminating... -[2023-10-11 00:46:42,936][98596] Loop rollout_proc1_evt_loop terminating... -[2023-10-11 00:46:42,936][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000098368_100728832.pth... -[2023-10-11 00:46:42,937][98601] Loop rollout_proc7_evt_loop terminating... -[2023-10-11 00:46:42,936][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000097664_100007936.pth... -[2023-10-11 00:46:42,936][97672] Component RolloutWorker_w3 stopped! -[2023-10-11 00:46:42,937][99352] Stopping RolloutWorker_w15... -[2023-10-11 00:46:42,937][97672] Component RolloutWorker_w1 stopped! -[2023-10-11 00:46:42,937][99352] Loop rollout_proc15_evt_loop terminating... -[2023-10-11 00:46:42,938][97672] Component Batcher_0 stopped! -[2023-10-11 00:46:42,938][98607] Stopping RolloutWorker_w13... -[2023-10-11 00:46:42,938][97672] Component RolloutWorker_w7 stopped! -[2023-10-11 00:46:42,939][98607] Loop rollout_proc13_evt_loop terminating... -[2023-10-11 00:46:42,939][97672] Component RolloutWorker_w15 stopped! -[2023-10-11 00:46:42,939][98606] Stopping RolloutWorker_w12... -[2023-10-11 00:46:42,939][97672] Component Batcher_1 stopped! -[2023-10-11 00:46:42,940][98606] Loop rollout_proc12_evt_loop terminating... -[2023-10-11 00:46:42,940][98595] Stopping RolloutWorker_w2... -[2023-10-11 00:46:42,940][98598] Stopping RolloutWorker_w4... -[2023-10-11 00:46:42,940][97672] Component RolloutWorker_w13 stopped! -[2023-10-11 00:46:42,940][98598] Loop rollout_proc4_evt_loop terminating... -[2023-10-11 00:46:42,940][98604] Stopping RolloutWorker_w10... -[2023-10-11 00:46:42,940][98595] Loop rollout_proc2_evt_loop terminating... -[2023-10-11 00:46:42,940][98604] Loop rollout_proc10_evt_loop terminating... -[2023-10-11 00:46:42,940][97672] Component RolloutWorker_w12 stopped! -[2023-10-11 00:46:42,941][97672] Component RolloutWorker_w2 stopped! -[2023-10-11 00:46:42,941][98605] Stopping RolloutWorker_w11... -[2023-10-11 00:46:42,941][97672] Component RolloutWorker_w4 stopped! -[2023-10-11 00:46:42,941][98603] Stopping RolloutWorker_w8... -[2023-10-11 00:46:42,941][98600] Stopping RolloutWorker_w6... -[2023-10-11 00:46:42,941][99320] Stopping RolloutWorker_w14... -[2023-10-11 00:46:42,942][98605] Loop rollout_proc11_evt_loop terminating... -[2023-10-11 00:46:42,942][98592] Stopping RolloutWorker_w0... -[2023-10-11 00:46:42,942][97672] Component RolloutWorker_w10 stopped! -[2023-10-11 00:46:42,942][98599] Stopping RolloutWorker_w5... -[2023-10-11 00:46:42,942][98603] Loop rollout_proc8_evt_loop terminating... -[2023-10-11 00:46:42,942][98600] Loop rollout_proc6_evt_loop terminating... -[2023-10-11 00:46:42,942][99320] Loop rollout_proc14_evt_loop terminating... -[2023-10-11 00:46:42,936][98385] Stopping Batcher_0... -[2023-10-11 00:46:42,942][98592] Loop rollout_proc0_evt_loop terminating... -[2023-10-11 00:46:42,937][98439] Stopping Batcher_1... -[2023-10-11 00:46:42,942][98599] Loop rollout_proc5_evt_loop terminating... -[2023-10-11 00:46:42,942][97672] Component RolloutWorker_w11 stopped! -[2023-10-11 00:46:42,942][98602] Stopping RolloutWorker_w9... -[2023-10-11 00:46:42,942][97672] Component RolloutWorker_w8 stopped! -[2023-10-11 00:46:42,943][97672] Component RolloutWorker_w6 stopped! -[2023-10-11 00:46:42,943][98602] Loop rollout_proc9_evt_loop terminating... -[2023-10-11 00:46:42,943][97672] Component RolloutWorker_w14 stopped! -[2023-10-11 00:46:42,943][97672] Component RolloutWorker_w0 stopped! -[2023-10-11 00:46:42,944][97672] Component RolloutWorker_w5 stopped! -[2023-10-11 00:46:42,944][97672] Component RolloutWorker_w9 stopped! -[2023-10-11 00:46:42,949][98439] Loop batcher_evt_loop terminating... -[2023-10-11 00:46:42,949][98385] Loop batcher_evt_loop terminating... -[2023-10-11 00:46:42,962][98560] Weights refcount: 2 0 -[2023-10-11 00:46:42,964][98560] Stopping InferenceWorker_p1-w0... -[2023-10-11 00:46:42,965][98560] Loop inference_proc1-0_evt_loop terminating... -[2023-10-11 00:46:42,964][97672] Component InferenceWorker_p1-w0 stopped! -[2023-10-11 00:46:42,971][98559] Weights refcount: 2 0 -[2023-10-11 00:46:42,973][98559] Stopping InferenceWorker_p0-w0... -[2023-10-11 00:46:42,974][98559] Loop inference_proc0-0_evt_loop terminating... -[2023-10-11 00:46:42,974][97672] Component InferenceWorker_p0-w0 stopped! -[2023-10-11 00:46:42,983][98439] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000096832_99155968.pth -[2023-10-11 00:46:42,988][98439] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p1/checkpoint_000097664_100007936.pth... -[2023-10-11 00:46:42,989][98385] Removing ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000097504_99844096.pth -[2023-10-11 00:46:42,995][98385] Saving ./train_atari/atari_doubledunk_APPO/checkpoint_p0/checkpoint_000098368_100728832.pth... -[2023-10-11 00:46:43,026][98439] Stopping LearnerWorker_p1... -[2023-10-11 00:46:43,026][98439] Loop learner_proc1_evt_loop terminating... -[2023-10-11 00:46:43,026][97672] Component LearnerWorker_p1 stopped! -[2023-10-11 00:46:43,057][98385] Stopping LearnerWorker_p0... -[2023-10-11 00:46:43,058][98385] Loop learner_proc0_evt_loop terminating... -[2023-10-11 00:46:43,058][97672] Component LearnerWorker_p0 stopped! -[2023-10-11 00:46:43,059][97672] Waiting for process learner_proc0 to stop... -[2023-10-11 00:46:43,916][97672] Waiting for process learner_proc1 to stop... -[2023-10-11 00:46:43,917][97672] Waiting for process inference_proc0-0 to join... -[2023-10-11 00:46:43,918][97672] Waiting for process inference_proc1-0 to join... -[2023-10-11 00:46:43,919][97672] Waiting for process rollout_proc0 to join... -[2023-10-11 00:46:43,919][97672] Waiting for process rollout_proc1 to join... -[2023-10-11 00:46:43,920][97672] Waiting for process rollout_proc2 to join... -[2023-10-11 00:46:43,921][97672] Waiting for process rollout_proc3 to join... -[2023-10-11 00:46:43,922][97672] Waiting for process rollout_proc4 to join... -[2023-10-11 00:46:43,922][97672] Waiting for process rollout_proc5 to join... -[2023-10-11 00:46:43,923][97672] Waiting for process rollout_proc6 to join... -[2023-10-11 00:46:43,923][97672] Waiting for process rollout_proc7 to join... -[2023-10-11 00:46:43,924][97672] Waiting for process rollout_proc8 to join... -[2023-10-11 00:46:43,924][97672] Waiting for process rollout_proc9 to join... -[2023-10-11 00:46:43,925][97672] Waiting for process rollout_proc10 to join... -[2023-10-11 00:46:43,925][97672] Waiting for process rollout_proc11 to join... -[2023-10-11 00:46:43,926][97672] Waiting for process rollout_proc12 to join... -[2023-10-11 00:46:43,926][97672] Waiting for process rollout_proc13 to join... -[2023-10-11 00:46:43,927][97672] Waiting for process rollout_proc14 to join... -[2023-10-11 00:46:43,927][97672] Waiting for process rollout_proc15 to join... -[2023-10-11 00:46:43,928][97672] Batcher 0 profile tree view: -batching: 171.3496, releasing_batches: 0.0909 -[2023-10-11 00:46:43,928][97672] Batcher 1 profile tree view: -batching: 170.3977, releasing_batches: 0.0896 -[2023-10-11 00:46:43,929][97672] InferenceWorker_p0-w0 profile tree view: -wait_policy: 0.0001 - wait_policy_total: 2404.3737 -update_model: 203.0991 - weight_update: 0.0010 -one_step: 0.0034 - handle_policy_step: 11448.1524 - deserialize: 64.7881, stack: 195.5139, obs_to_device_normalize: 2562.4610, forward: 5202.3040, prepare_outputs: 2467.2059, send_messages: 456.9198 -[2023-10-11 00:46:43,929][97672] InferenceWorker_p1-w0 profile tree view: -wait_policy: 0.0001 - wait_policy_total: 2526.4663 -update_model: 206.2169 - weight_update: 0.0007 -one_step: 0.0022 - handle_policy_step: 11320.5451 - deserialize: 63.1474, stack: 192.7384, obs_to_device_normalize: 2517.1150, forward: 5145.8617, prepare_outputs: 2431.4400, send_messages: 474.0728 -[2023-10-11 00:46:43,930][97672] Learner 0 profile tree view: -misc: 0.0178, prepare_batch: 270.1984 -train: 3633.8656 - epoch_init: 0.1901, minibatch_init: 13.2290, losses_postprocess: 892.1548, kl_divergence: 31.8660, update: 385.2854, after_optimizer: 2123.3303 - calculate_losses: 171.2563 - losses_init: 0.3856, forward_head: 59.9047, bptt_initial: 1.4520, bptt: 2.1274, tail: 38.2799, advantages_returns: 11.2418, losses: 44.0072 -[2023-10-11 00:46:43,930][97672] Learner 1 profile tree view: -misc: 0.0180, prepare_batch: 269.4637 -train: 3608.7675 - epoch_init: 0.1865, minibatch_init: 13.0764, losses_postprocess: 889.3266, kl_divergence: 31.8295, update: 380.0315, after_optimizer: 2111.1114 - calculate_losses: 166.6800 - losses_init: 0.3779, forward_head: 55.7942, bptt_initial: 1.4493, bptt: 1.8479, tail: 38.1939, advantages_returns: 11.3197, losses: 43.8728 -[2023-10-11 00:46:43,931][97672] RolloutWorker_w0 profile tree view: -wait_for_trajectories: 1.2287, enqueue_policy_requests: 408.9698, process_policy_outputs: 191.4541, env_step: 7518.5149, finalize_trajectories: 3.4544, complete_rollouts: 2.8837 -post_env_step: 377.3804 - process_env_step: 84.5467 -[2023-10-11 00:46:43,931][97672] RolloutWorker_w15 profile tree view: -wait_for_trajectories: 1.2528, enqueue_policy_requests: 409.6121, process_policy_outputs: 191.2917, env_step: 7531.3089, finalize_trajectories: 3.4786, complete_rollouts: 2.9354 -post_env_step: 374.4521 - process_env_step: 84.6543 -[2023-10-11 00:46:43,931][97672] Loop Runner_EvtLoop terminating... -[2023-10-11 00:46:43,932][97672] Runner profile tree view: -main_loop: 14763.8358 -[2023-10-11 00:46:43,932][97672] Collected {0: 100728832, 1: 100007936}, FPS: 13596.5 +version https://git-lfs.github.com/spec/v1 +oid sha256:d4c28346bb0c7a4a602646ff8de9f87acffc54dbc53fd59b4c5e0c6b5d7b7d1a +size 48941281