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.1698653362.rhmmedcatt-proliant-ml350-gen10 b/.summary/0/events.out.tfevents.1698653362.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..89d6932bb84b4d2b6e9c78bfdd4eb4346ad9b17c --- /dev/null +++ b/.summary/0/events.out.tfevents.1698653362.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b8ed7f6fd5862e56ad7c41807bd2888ad4bebe41e3819af3fc62200b82cd453 +size 49290166 diff --git a/.summary/0/events.out.tfevents.1698760576.rhmmedcatt-proliant-ml350-gen10 b/.summary/0/events.out.tfevents.1698760576.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..117a6ea116a5e9747f9657801952b9aed519d64f --- /dev/null +++ b/.summary/0/events.out.tfevents.1698760576.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f881fcc2c6a758a26d99629d9fbf808494e9b47304510551acc8b7e9daa44820 +size 30416159 diff --git a/.summary/1/events.out.tfevents.1698653362.rhmmedcatt-proliant-ml350-gen10 b/.summary/1/events.out.tfevents.1698653362.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..28ae77c3a5dbb28a25f02e2da56e999187deb9f1 --- /dev/null +++ b/.summary/1/events.out.tfevents.1698653362.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32644dc5beb2bf6874817ae4ac4cc0be2568a085496219b51514159cbaee2981 +size 26079604 diff --git a/.summary/1/events.out.tfevents.1698760576.rhmmedcatt-proliant-ml350-gen10 b/.summary/1/events.out.tfevents.1698760576.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..497e124b63aed152483737e78d2828b4824815f1 --- /dev/null +++ b/.summary/1/events.out.tfevents.1698760576.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73ae0722d4c0e370d67f191460f91e76b7ef3d4c69b367f6939c48681db79168 +size 15755067 diff --git a/README.md b/README.md index 9841aece3ad85f3dfde50e09afa3ee4d91ed34fd..dfd3018ab461161a2964042eeeaf8c4753ce8ccc 100644 --- a/README.md +++ b/README.md @@ -15,35 +15,39 @@ model-index: type: atari_defender metrics: - type: mean_reward - value: 59120.00 +/- 11022.48 + value: 302420.00 +/- 89166.87 name: mean_reward verified: false --- -A(n) **APPO** model trained on the **atari_defender** 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_defender -``` +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_defender** 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_defender +``` + + ## Using the model To run the model after download, use the `enjoy` script corresponding to this environment: diff --git a/checkpoint_p0/best_001199552_307085312_reward_133.300.pth b/checkpoint_p0/best_001199552_307085312_reward_133.300.pth new file mode 100644 index 0000000000000000000000000000000000000000..65bff3b5b6fdc9c3dfcb0422028ad1537c8b8d14 --- /dev/null +++ b/checkpoint_p0/best_001199552_307085312_reward_133.300.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d00656292f99ffa433dda9da279a4f17b2f039944c3ee3fdbf2592bd5783495 +size 20795955 diff --git a/checkpoint_p0/checkpoint_001952192_499761152.pth b/checkpoint_p0/checkpoint_001952192_499761152.pth new file mode 100644 index 0000000000000000000000000000000000000000..0269665eda858afdfe5195fb7549892b0daf9a93 --- /dev/null +++ b/checkpoint_p0/checkpoint_001952192_499761152.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b48983e20b1a58f131d52a27f4c81dcfb51f926c26fce6676329397b119c4f74 +size 20796291 diff --git a/checkpoint_p0/checkpoint_001953184_500015104.pth b/checkpoint_p0/checkpoint_001953184_500015104.pth new file mode 100644 index 0000000000000000000000000000000000000000..d8a731e8a8db7d313488d5cefb5539449ca033c7 --- /dev/null +++ b/checkpoint_p0/checkpoint_001953184_500015104.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c374beee5d8282dc847caecb9d95d3e4fd90de607947f4b5e88c2a5118096663 +size 20796291 diff --git a/checkpoint_p0/milestones/checkpoint_000013440_3440640.pth b/checkpoint_p0/milestones/checkpoint_000013440_3440640.pth new file mode 100644 index 0000000000000000000000000000000000000000..017c6bb16ae44636977069cce3cc0db07cd4b17c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000013440_3440640.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:171779875487b0744ee29ffdc011e1857e1e306c1b2360dc2b63e2a5b83d03da +size 20796955 diff --git a/checkpoint_p0/milestones/checkpoint_000027776_7110656.pth b/checkpoint_p0/milestones/checkpoint_000027776_7110656.pth new file mode 100644 index 0000000000000000000000000000000000000000..464453f42d815e8a7db7e97bc7cdbc82bbfe3429 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000027776_7110656.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afcdac1cde6080b0344a6074a2f9ad0d6f3822b7d829c15a2d05f2c5bf2507fe +size 20796955 diff --git a/checkpoint_p0/milestones/checkpoint_000042240_10813440.pth b/checkpoint_p0/milestones/checkpoint_000042240_10813440.pth new file mode 100644 index 0000000000000000000000000000000000000000..ae18b905f6e525184946c9f0d54db98a0ee979ab --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000042240_10813440.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74494ba968c48b1e469f33caffac89b83d3d8da3a5dd7d2548b7e4e6db27d3b4 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000056640_14499840.pth b/checkpoint_p0/milestones/checkpoint_000056640_14499840.pth new file mode 100644 index 0000000000000000000000000000000000000000..92242a25a786fa72bbc0d05e73a0840e182e0691 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000056640_14499840.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbf91b393385c5b856ece8a9a9f8c524193b3e6e0d41fcf6500da2d02450beaf +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000071200_18227200.pth b/checkpoint_p0/milestones/checkpoint_000071200_18227200.pth new file mode 100644 index 0000000000000000000000000000000000000000..ebeef07d9707c7f73e0af67981aa3d0842346c22 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000071200_18227200.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76146d4a91c174f8d99de057730a79cf67dd47493b42aea30cf5f8186ef48e8e +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000085568_21905408.pth b/checkpoint_p0/milestones/checkpoint_000085568_21905408.pth new file mode 100644 index 0000000000000000000000000000000000000000..d0bb681af71837823b229ffea1f7a186b131c1a5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000085568_21905408.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:487ce530b9bf572c0ae46c5a6c07c366c6355c28ac8319cfd33ce96b27ff7dcf +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000100032_25608192.pth b/checkpoint_p0/milestones/checkpoint_000100032_25608192.pth new file mode 100644 index 0000000000000000000000000000000000000000..b415919e2a9d23d95f72821f55c3e049c97c46a8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000100032_25608192.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c33d0cfef08c25a95554c3e913498f9c61f50bd5c4154cc831853ae4b1bfd21a +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000114560_29327360.pth b/checkpoint_p0/milestones/checkpoint_000114560_29327360.pth new file mode 100644 index 0000000000000000000000000000000000000000..11aa59a50d7e4a552d6766e3c2496ef06948cbd1 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000114560_29327360.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eebeae7e81b1622aef570a1a6e87d42df78360e0fcf0a0c96ecf1d4ab5742c70 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000128928_33005568.pth b/checkpoint_p0/milestones/checkpoint_000128928_33005568.pth new file mode 100644 index 0000000000000000000000000000000000000000..ee0b497c8b6584e3cd74d747c7a57473c11d38c2 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000128928_33005568.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a2064826869f5202dadab94a30e5326a4a49e91e13b495221370987b1f8276b +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000143392_36708352.pth b/checkpoint_p0/milestones/checkpoint_000143392_36708352.pth new file mode 100644 index 0000000000000000000000000000000000000000..9164e7729cdbb293640d0eedcffb6270bf793872 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000143392_36708352.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f35cddbcdfd23d51f56cf042d389af9de238c4353672c0f35d2a41ca04956c64 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000157856_40411136.pth b/checkpoint_p0/milestones/checkpoint_000157856_40411136.pth new file mode 100644 index 0000000000000000000000000000000000000000..0da75166ae92825386ed419906935dc2a86cfd4b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000157856_40411136.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:546a6e83ce911c4864340f8c0b4cd452f4cfa5c35f5ab28546e41ab7b1a59496 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000172320_44113920.pth b/checkpoint_p0/milestones/checkpoint_000172320_44113920.pth new file mode 100644 index 0000000000000000000000000000000000000000..4a33000a347ce0278dbdd08dfc9a6335cfd872bf --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000172320_44113920.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3a6f399201371a8e927991411bd7097aa786b53e7651f7d165f827d9f7f21e0 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000186816_47824896.pth b/checkpoint_p0/milestones/checkpoint_000186816_47824896.pth new file mode 100644 index 0000000000000000000000000000000000000000..e2a4ced87ddf1ba67d0e860534748d4a5ee819ec --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000186816_47824896.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43947330c34e5d138f772d67f12c080c9e66781a33d7bccdaced71a23696279a +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000201152_51494912.pth b/checkpoint_p0/milestones/checkpoint_000201152_51494912.pth new file mode 100644 index 0000000000000000000000000000000000000000..98f1544dd780107876228af727aebe288c61c0be --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000201152_51494912.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfaa706efc98bb500a5add6c8ddc31964b98ae014bfd6ae7d7dfbd6e8c7e8601 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000215488_55164928.pth b/checkpoint_p0/milestones/checkpoint_000215488_55164928.pth new file mode 100644 index 0000000000000000000000000000000000000000..33077f4f70fbcef893c662299c325b8d797f371f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000215488_55164928.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0672a1d4bedc37866316f2919abbe72fb4b353639e3f7a017cd863877a550754 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000229952_58867712.pth b/checkpoint_p0/milestones/checkpoint_000229952_58867712.pth new file mode 100644 index 0000000000000000000000000000000000000000..5c552f9aadb10083b424066014fa6bdd03ecda7a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000229952_58867712.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb20114c49a6bed9f6129b1681af65b3ee70f3b8e5927ba4529f202bca6dee6e +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000244544_62603264.pth b/checkpoint_p0/milestones/checkpoint_000244544_62603264.pth new file mode 100644 index 0000000000000000000000000000000000000000..972c9ce1aab31e3ec760661ff7aedf90a4265fc0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000244544_62603264.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24d160dc235cc994e8ee2edaff5b0b6a9e6a4f5b37af03e2a0badafa5d445667 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000259008_66306048.pth b/checkpoint_p0/milestones/checkpoint_000259008_66306048.pth new file mode 100644 index 0000000000000000000000000000000000000000..ea305dda32fea0a32a65f1f5f899399d83eb6f52 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000259008_66306048.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbaefee8382e9dadce5d6026b8a3684fae44df1ef0014c72366fde2d53d0f157 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000273536_70025216.pth b/checkpoint_p0/milestones/checkpoint_000273536_70025216.pth new file mode 100644 index 0000000000000000000000000000000000000000..d0e4acf3e167b1188f581e9c47e0322b6ffc2931 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000273536_70025216.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55621c51819b997c8abd305125b9e8a1d9234e28958a675f3cd62f6d36bdad18 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000287968_73719808.pth b/checkpoint_p0/milestones/checkpoint_000287968_73719808.pth new file mode 100644 index 0000000000000000000000000000000000000000..6160105cff33fddb1164cfcf0280c7f6f2e18e99 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000287968_73719808.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f46bd619f1cf1f6085a9665ad9e0f35c549ce308ad8a5d3b668a0e80facd0b7 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000302304_77389824.pth b/checkpoint_p0/milestones/checkpoint_000302304_77389824.pth new file mode 100644 index 0000000000000000000000000000000000000000..b79b9f17517c856519cc846fb3aa0a2bdcb3b721 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000302304_77389824.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a67f3d95bb741ac2c361f663ea7b7320be28c1d93ff1fb96732c3d44c3ef8151 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000316576_81043456.pth b/checkpoint_p0/milestones/checkpoint_000316576_81043456.pth new file mode 100644 index 0000000000000000000000000000000000000000..3241fcc36cc63150fdbc9e4f0bcc7518458dad5c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000316576_81043456.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd4f0d438f6733ca2beb3c739417c60122dfac0d1b280420d9aaf1dc37a8fb70 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000330816_84688896.pth b/checkpoint_p0/milestones/checkpoint_000330816_84688896.pth new file mode 100644 index 0000000000000000000000000000000000000000..37be115e96e1adfaff2c55ce0d2af94d3667a5ed --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000330816_84688896.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acc7ff89e0887087bfe0000dcce5571b542e2e76a6fc5f7bd21c4ee30b1fa3bb +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000345024_88326144.pth b/checkpoint_p0/milestones/checkpoint_000345024_88326144.pth new file mode 100644 index 0000000000000000000000000000000000000000..13db3404ac5821b065016de9ab92ee1ea7a7e2f5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000345024_88326144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:184346ddfe7fa34d6f66970127b5e95b1bbe235cccf9ab028a08ebb8c0f3eac5 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000359328_91987968.pth b/checkpoint_p0/milestones/checkpoint_000359328_91987968.pth new file mode 100644 index 0000000000000000000000000000000000000000..e28533facb38d03de601c3453ca2642093fb04ac --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000359328_91987968.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:284f1a2aa91a51e976a4ec2e43c628e1a7196ea7a4efac45dce5100a00b1a028 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000373632_95649792.pth b/checkpoint_p0/milestones/checkpoint_000373632_95649792.pth new file mode 100644 index 0000000000000000000000000000000000000000..43a62812d5cd2f890fa339c32e441d4f58c7f0db --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000373632_95649792.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00704e0aacb7f4e459942189bff9df6c23f7a9b940ede4e9af17179a4524e865 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000387968_99319808.pth b/checkpoint_p0/milestones/checkpoint_000387968_99319808.pth new file mode 100644 index 0000000000000000000000000000000000000000..a95eb242ce0d1335177be778a2fdf3c887fbebcf --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000387968_99319808.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec936c2a9d639958eb96a6c022196402b5bcee427fc390ab796ffdd87db8b522 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000402240_102973440.pth b/checkpoint_p0/milestones/checkpoint_000402240_102973440.pth new file mode 100644 index 0000000000000000000000000000000000000000..6ecf5183ee787b81523307c5e5910566840e9371 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000402240_102973440.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d76536852a9f7f4b7608214d3a7cec4a873f7320ebb56af6a1b30c449c51f46 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000416352_106586112.pth b/checkpoint_p0/milestones/checkpoint_000416352_106586112.pth new file mode 100644 index 0000000000000000000000000000000000000000..5e11aa0f33962002382d8f122a996fa977e89ae0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000416352_106586112.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c2d92b070ddabc18d22662494c6bdf912a044a9686761e6b14716f20f14b8d7 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000430592_110231552.pth b/checkpoint_p0/milestones/checkpoint_000430592_110231552.pth new file mode 100644 index 0000000000000000000000000000000000000000..1b26282a4b4625f87969e0d131000779fc5e15e7 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000430592_110231552.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b82af7b90d74780a30bcbe24c0bac19d29dc8ea8e0cfef0b51069022c7519787 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000444832_113876992.pth b/checkpoint_p0/milestones/checkpoint_000444832_113876992.pth new file mode 100644 index 0000000000000000000000000000000000000000..138e8d2176be37d8b027ff8e76fa0246d0535192 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000444832_113876992.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2b53ed34dca6dc3c1c8437fc505eafe7f3fae17fde4da3686b10a0eacdd426e +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000459104_117530624.pth b/checkpoint_p0/milestones/checkpoint_000459104_117530624.pth new file mode 100644 index 0000000000000000000000000000000000000000..2793a7d793f9eb082aa9ccc3ec159744fbe5c15f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000459104_117530624.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a5774f1bda58155b7c9f6f43facb7b5247f0298e29329111b7f50fe773e0752 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000473376_121184256.pth b/checkpoint_p0/milestones/checkpoint_000473376_121184256.pth new file mode 100644 index 0000000000000000000000000000000000000000..8a7e14990e48acde573c707314343e5e5f300fc5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000473376_121184256.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7118f5307c6fb3e0bbf22d08c5a3dd0e47d29a0ace98c364e6ecc16dae8c57a9 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000487680_124846080.pth b/checkpoint_p0/milestones/checkpoint_000487680_124846080.pth new file mode 100644 index 0000000000000000000000000000000000000000..466beb2c21eae26933335cda02f33faa438de2e0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000487680_124846080.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f5ddf4559c1f8887d53f389ad5da6a1a612d01ebf9be1d152c8ed98f82cd4b3 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000501984_128507904.pth b/checkpoint_p0/milestones/checkpoint_000501984_128507904.pth new file mode 100644 index 0000000000000000000000000000000000000000..0832eec5f89aff9df76288932b8a1ae1af86c91b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000501984_128507904.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8b71644f9c4b997bd4efad0a65ca2cb77ae9195753ae10757bd863019b36149 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000516256_132161536.pth b/checkpoint_p0/milestones/checkpoint_000516256_132161536.pth new file mode 100644 index 0000000000000000000000000000000000000000..2fce8bbbcad1a03a8b7ad7d0e59908c26d3d4d79 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000516256_132161536.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:410449b25e86ae5220374bf428310bc74c439c351be9f7423847c501cc5e6f78 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000530528_135815168.pth b/checkpoint_p0/milestones/checkpoint_000530528_135815168.pth new file mode 100644 index 0000000000000000000000000000000000000000..9584bd23f22734346ff9add2aaa597523d28cd5d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000530528_135815168.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21e35bdf64aa7cdd0fdcaa9df205f1a7b8c0546e7953b529f11e1a68d66d65aa +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000544864_139485184.pth b/checkpoint_p0/milestones/checkpoint_000544864_139485184.pth new file mode 100644 index 0000000000000000000000000000000000000000..d9803775f0b6daf275c3fed2ce904e6179be109e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000544864_139485184.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7631a4a3132b177e30d7a112687875eba8281cb35e55a5bedc048887638698ac +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000559136_143138816.pth b/checkpoint_p0/milestones/checkpoint_000559136_143138816.pth new file mode 100644 index 0000000000000000000000000000000000000000..ddb5a39132ae0b4d42a1859530214d1af9e2f385 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000559136_143138816.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07a61cc3d3b166b9fed03544b3b0111230268a275a65e6c265d5a7819d249195 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000573472_146808832.pth b/checkpoint_p0/milestones/checkpoint_000573472_146808832.pth new file mode 100644 index 0000000000000000000000000000000000000000..15426ce836f0dd60bdabb81cb40cd280536009e2 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000573472_146808832.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc719db7dcda6850808925c5797ac74b251b877ad16390987a5c2de1a8c3a07b +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000587808_150478848.pth b/checkpoint_p0/milestones/checkpoint_000587808_150478848.pth new file mode 100644 index 0000000000000000000000000000000000000000..769c62aae5cec4c0f5da420b7eb4450eb6b0613e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000587808_150478848.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7c70189fac5b625c3dcf5e8e60a1c831af04587c3e369204871d35ab9c53a5b +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000602080_154132480.pth b/checkpoint_p0/milestones/checkpoint_000602080_154132480.pth new file mode 100644 index 0000000000000000000000000000000000000000..c9043a77befb717450d0a86b889dca57c2c95444 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000602080_154132480.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb7bc77ab86a5e804892acbac765e262ad41225074274e9bd7d32729f064656c +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000616416_157802496.pth b/checkpoint_p0/milestones/checkpoint_000616416_157802496.pth new file mode 100644 index 0000000000000000000000000000000000000000..2b43e49b5836b92a10191312d0b6357e17a0f5ae --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000616416_157802496.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6493953afd28350d59d503fd66a7e91558c8ddc831c5d82678e2d5fad98bde60 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000630688_161456128.pth b/checkpoint_p0/milestones/checkpoint_000630688_161456128.pth new file mode 100644 index 0000000000000000000000000000000000000000..c7c61a8c0442350d6e84762767d9b8831f121eb8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000630688_161456128.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72d841a3094c6882652ee7fda3f4a30739903d667ae195db5ef56081d1c1d403 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000645024_165126144.pth b/checkpoint_p0/milestones/checkpoint_000645024_165126144.pth new file mode 100644 index 0000000000000000000000000000000000000000..969fdf5459fcb0c584d5d22edd7d59d7f1527597 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000645024_165126144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94339807aceb1def6e3d4e11684178a07c7a2750b0306f321af90d460ec72cdd +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000659360_168796160.pth b/checkpoint_p0/milestones/checkpoint_000659360_168796160.pth new file mode 100644 index 0000000000000000000000000000000000000000..5ce86dc505f338f23c72530d86d2163dbd4db646 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000659360_168796160.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:881d1de82b256ba77d9edb1d2796c5f83dc688a17b530ca3132b262961674f99 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000673664_172457984.pth b/checkpoint_p0/milestones/checkpoint_000673664_172457984.pth new file mode 100644 index 0000000000000000000000000000000000000000..2efbc2fc79ea4232a8fdecef3eb97cf01760b644 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000673664_172457984.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d221a83a84f0b7617ce51c81380e48efd339d0de044f81fa53098b36c57a7ec +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000687968_176119808.pth b/checkpoint_p0/milestones/checkpoint_000687968_176119808.pth new file mode 100644 index 0000000000000000000000000000000000000000..ed0f8bcc2aefb8d0e5e93ab63f6a352667a0eef4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000687968_176119808.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaad62e71c84c38133fee1300fe8c9c980de07b5ed02b60e27d92ebe78a3d7e8 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000702304_179789824.pth b/checkpoint_p0/milestones/checkpoint_000702304_179789824.pth new file mode 100644 index 0000000000000000000000000000000000000000..03fe3256405451121d978b2c58ce0c43d710536b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000702304_179789824.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:820a5b85764cf4ddd48a5562053ae6be6624fb9f8a30f33d388e014db54004b8 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000716672_183468032.pth b/checkpoint_p0/milestones/checkpoint_000716672_183468032.pth new file mode 100644 index 0000000000000000000000000000000000000000..3cce232e24b3a8a13fe7a6373a2eb0e7fd9fa1d5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000716672_183468032.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6d24c480f56c47ff15fc1d78c07da19ecdf861b875086f5a265ced7ccfdb656 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000731040_187146240.pth b/checkpoint_p0/milestones/checkpoint_000731040_187146240.pth new file mode 100644 index 0000000000000000000000000000000000000000..b123436ddbc7ac9303b2fa6df47f4f90e5de9a4c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000731040_187146240.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f774d49491e43cae4a41b36a0ce91b52c86aae480fc623bf455ba7c0321f4db8 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000745376_190816256.pth b/checkpoint_p0/milestones/checkpoint_000745376_190816256.pth new file mode 100644 index 0000000000000000000000000000000000000000..5c560b78366da3db4fa76f69fcf9316e2d363396 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000745376_190816256.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c63d689bf32b314c2faf13ab6ef0f2ddbf5dec32dc2e17e6871e484bbeb8e6c5 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000759776_194502656.pth b/checkpoint_p0/milestones/checkpoint_000759776_194502656.pth new file mode 100644 index 0000000000000000000000000000000000000000..ba5976636ceeffb42fe0fb8f75583fd34baa1e38 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000759776_194502656.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b84abbbdcdea52e8f7a2bca5f511c0d23e02bb0ae3e3c2183af3222134368cbe +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000774176_198189056.pth b/checkpoint_p0/milestones/checkpoint_000774176_198189056.pth new file mode 100644 index 0000000000000000000000000000000000000000..f088fca99b066284ecbb8b88a266360312585d8f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000774176_198189056.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef096f229a3fce93be0047116608a3e6b82b617a6ed1abec1243fae3e742636b +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000788480_201850880.pth b/checkpoint_p0/milestones/checkpoint_000788480_201850880.pth new file mode 100644 index 0000000000000000000000000000000000000000..7508e82b440530281f6d88403f0a0707015270fd --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000788480_201850880.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4494561cc31745aff62cb4dbf5ddcb6398596330ffee02b250b0e1d04b5303d8 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000802848_205529088.pth b/checkpoint_p0/milestones/checkpoint_000802848_205529088.pth new file mode 100644 index 0000000000000000000000000000000000000000..521ade3d99406e903a2a5eda5382556a5843ac63 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000802848_205529088.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0572d062fe63c8820e642a64a13dd23955ac00f0f78d201e620dade6b92185a6 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000817312_209231872.pth b/checkpoint_p0/milestones/checkpoint_000817312_209231872.pth new file mode 100644 index 0000000000000000000000000000000000000000..29ed52486e57f475ff71323973053e7a17d1df70 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000817312_209231872.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:720a7642f3f182ac82f1a609520f09894722f1ce28eac3f88beaacf66fc85ad5 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000831616_212893696.pth b/checkpoint_p0/milestones/checkpoint_000831616_212893696.pth new file mode 100644 index 0000000000000000000000000000000000000000..3796cf9cd47cc899225233f051e3276bf2846f82 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000831616_212893696.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88b182c829903c5daccfb89177c69f160f9500fc67120afaf890e23c43234139 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000845920_216555520.pth b/checkpoint_p0/milestones/checkpoint_000845920_216555520.pth new file mode 100644 index 0000000000000000000000000000000000000000..ae7ee850e042e9672d32e0eefbe798a0d2d580f2 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000845920_216555520.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:083f9feef6180729c0e3be65b27a133597652815592af0da830ec6b9c82c64f7 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000860288_220233728.pth b/checkpoint_p0/milestones/checkpoint_000860288_220233728.pth new file mode 100644 index 0000000000000000000000000000000000000000..6f8c10107d167cdd71e71eb9cad70e2aa5c2e032 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000860288_220233728.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2b166ae95ca95ea0fac98f13eb268c47b81bcee84a1a88b8fdc4a4ec5343616 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000874688_223920128.pth b/checkpoint_p0/milestones/checkpoint_000874688_223920128.pth new file mode 100644 index 0000000000000000000000000000000000000000..08ef3bc9065b158dd5a94a5fa776fd66428d9142 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000874688_223920128.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69c4c1b681230c8b3ae9f9d97bfa4befabef53b76637a4e86486fe0158d1b7bc +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000889120_227614720.pth b/checkpoint_p0/milestones/checkpoint_000889120_227614720.pth new file mode 100644 index 0000000000000000000000000000000000000000..746ce356e982f59539379642a1f3a6023270adff --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000889120_227614720.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7be6a0489563e526b5a99f6f558698963a445849e698fe7a5cd0d5db04b0d9ce +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000903424_231276544.pth b/checkpoint_p0/milestones/checkpoint_000903424_231276544.pth new file mode 100644 index 0000000000000000000000000000000000000000..48f14d6ccd1065f2d97c45eb021b25688e20fed7 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000903424_231276544.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c74c705efd7c988d5ffc303180914256a1734a4d56d0ca27b2b7dd1dc9a69a3c +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000917760_234946560.pth b/checkpoint_p0/milestones/checkpoint_000917760_234946560.pth new file mode 100644 index 0000000000000000000000000000000000000000..ec26774d19f375dfc1cb47f523c62a15a1f06b37 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000917760_234946560.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82a3b8ec68eece61ee1830688cf928e36269a51d4c745f4e74e68291aa65fcfe +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000932128_238624768.pth b/checkpoint_p0/milestones/checkpoint_000932128_238624768.pth new file mode 100644 index 0000000000000000000000000000000000000000..a376dacf05dd12c961437cda3f01c9c4a396e654 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000932128_238624768.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57320ba109f421e6ccff752fff6a4633e05c1bf0214e8e1c241440f8696c46cc +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000946368_242270208.pth b/checkpoint_p0/milestones/checkpoint_000946368_242270208.pth new file mode 100644 index 0000000000000000000000000000000000000000..0c63448d07ced98e7422917dbfa17eaa58003aa8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000946368_242270208.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73be667635252129cba8f0e7804f38843f87f974b0c3e160a8c737930a90b09f +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000960736_245948416.pth b/checkpoint_p0/milestones/checkpoint_000960736_245948416.pth new file mode 100644 index 0000000000000000000000000000000000000000..827c829badd3cb984e6e858ca58bfba9c12407a2 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000960736_245948416.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a3012a4cc3013565d156256fa4d3799212a8389eff47515a061cb2023760f3d +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000975008_249602048.pth b/checkpoint_p0/milestones/checkpoint_000975008_249602048.pth new file mode 100644 index 0000000000000000000000000000000000000000..9b8014ed78516224a2066acf6fbc6d1439b97cf4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000975008_249602048.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f75b1d063435c81499d04015b94cac8bb805360ea73e01a7f4eb50201d6fb5d +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000989376_253280256.pth b/checkpoint_p0/milestones/checkpoint_000989376_253280256.pth new file mode 100644 index 0000000000000000000000000000000000000000..a5d7843e0e31a7c96909f5706c5e3be0935e48dd --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000989376_253280256.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0320a5615f6db3f6c493313621bb5734708b39a56bc8359de6ad4931a10e90fa +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001003680_256942080.pth b/checkpoint_p0/milestones/checkpoint_001003680_256942080.pth new file mode 100644 index 0000000000000000000000000000000000000000..da8daa2b5766040e6546cab5cfb6b940c30eb35f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001003680_256942080.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f82ffc59ae14a46c2868d7a3cdb549b64ca9d23c8daf3d6f548dcaea93903352 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001017952_260595712.pth b/checkpoint_p0/milestones/checkpoint_001017952_260595712.pth new file mode 100644 index 0000000000000000000000000000000000000000..7502378185f613d1abe9ba021ddb09798c04a5fc --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001017952_260595712.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a2235fd361f402c5a341091889d9f6cf8855932197d2d88f55fbd96e8529181 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001032224_264249344.pth b/checkpoint_p0/milestones/checkpoint_001032224_264249344.pth new file mode 100644 index 0000000000000000000000000000000000000000..c31d8ddca0374de5bf23b3bbd55692545ae0cfd5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001032224_264249344.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:725ffc93fa08d9b8da4c91de0c5af66528dc1ebf53b8a747be9cc9d7e25da15f +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001046592_267927552.pth b/checkpoint_p0/milestones/checkpoint_001046592_267927552.pth new file mode 100644 index 0000000000000000000000000000000000000000..2dd09a228c591045515f459b7d48b8ea6c391947 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001046592_267927552.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb38d7905ea70e4ae4f5349fe65275437492a6285775fc021c903eca0e001c09 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001060960_271605760.pth b/checkpoint_p0/milestones/checkpoint_001060960_271605760.pth new file mode 100644 index 0000000000000000000000000000000000000000..508ac1b221fdff176f253ee421842feefc3eb3f3 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001060960_271605760.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df8653d7497636904ce32b5f97a8b23f071955b741bfa00990e4fe138d6239d7 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001075264_275267584.pth b/checkpoint_p0/milestones/checkpoint_001075264_275267584.pth new file mode 100644 index 0000000000000000000000000000000000000000..496dc1612411fc0ef4a54dc932ce20d2e7f22de4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001075264_275267584.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa2ef6d19da3985409166fe29d1d955c89248ad551eb5aafe0aa624770fe13dd +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001089632_278945792.pth b/checkpoint_p0/milestones/checkpoint_001089632_278945792.pth new file mode 100644 index 0000000000000000000000000000000000000000..6f44dca4877b4c81bbc379fb1b9b5aa8222985e3 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001089632_278945792.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09d64c3239f78417dd81bf6f7987605729f037d58253dfe164f09fb24628175f +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001103936_282607616.pth b/checkpoint_p0/milestones/checkpoint_001103936_282607616.pth new file mode 100644 index 0000000000000000000000000000000000000000..6c41d45ed1b91d5699a005889aca37a61b8142fb --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001103936_282607616.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7364a6d29c86b6c962f2f5e6daa4a44c3ab223ed7c9c02bab7df44241e1e262a +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001118272_286277632.pth b/checkpoint_p0/milestones/checkpoint_001118272_286277632.pth new file mode 100644 index 0000000000000000000000000000000000000000..56bd40aec9d13c88b5b960e4e5e4b31eba22514e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001118272_286277632.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f71d3cf2f6036f269d0d2a5dda2ae166deebe1c9cea3a442d5a4baf378fac87a +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001132672_289964032.pth b/checkpoint_p0/milestones/checkpoint_001132672_289964032.pth new file mode 100644 index 0000000000000000000000000000000000000000..3ad9a1fed1c2bece9c5d16138f2da7bf68168ff6 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001132672_289964032.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6f4a96b050cba8c45eb9550b139196811e9f27d1a8d7609a2c70647f2338cfe +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001147104_293658624.pth b/checkpoint_p0/milestones/checkpoint_001147104_293658624.pth new file mode 100644 index 0000000000000000000000000000000000000000..3587d8d40f819359de6a182c24f24e49d35c8066 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001147104_293658624.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6f500b590fe5ecef90bfbf41bb3f6029e0a7f182c9c38a47f1fc3dffb029cc7 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001161408_297320448.pth b/checkpoint_p0/milestones/checkpoint_001161408_297320448.pth new file mode 100644 index 0000000000000000000000000000000000000000..cb3d6b4ad050bb0049368d8b73ca4db9503914cf --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001161408_297320448.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5320f9ba06d0086cf2d6494e11be646a06dfc8a162f859c263b69e3f3346bac9 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001175744_300990464.pth b/checkpoint_p0/milestones/checkpoint_001175744_300990464.pth new file mode 100644 index 0000000000000000000000000000000000000000..3d489f7772ef9c47f657be2317560b9b980731b9 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001175744_300990464.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebcce837f21b35913aaa6c5bb0393d446ad5f85ff4c745600f9e5e971521c9b4 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001190112_304668672.pth b/checkpoint_p0/milestones/checkpoint_001190112_304668672.pth new file mode 100644 index 0000000000000000000000000000000000000000..91f5673b8e0a7eb9b83ed84e5fee3d46ddbe85c0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001190112_304668672.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0f44ebce9787a6232b7aeb2d2a58568944110d50b760ca3f84b388ea68d85da +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001212864_310493184.pth b/checkpoint_p0/milestones/checkpoint_001212864_310493184.pth new file mode 100644 index 0000000000000000000000000000000000000000..ffab52adf9ba5b607c8eef54c0f91ca702086be4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001212864_310493184.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc33a7f5940f936627e8999499385f8368f7a15ec04d5c81307a2b647975d18d +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001227424_314220544.pth b/checkpoint_p0/milestones/checkpoint_001227424_314220544.pth new file mode 100644 index 0000000000000000000000000000000000000000..c798ef23c8fbdbdea586e7724408044a5542e817 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001227424_314220544.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4cdc33ae45b1ba0106c865a8b23e8c3008010ee13e345a93b91924e56dd121a +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001241920_317931520.pth b/checkpoint_p0/milestones/checkpoint_001241920_317931520.pth new file mode 100644 index 0000000000000000000000000000000000000000..1baf897db9da14a9f9bcaae64ffe1041c3048d90 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001241920_317931520.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1467fe90c85aa07e91dfe8b15d1fae65900d16ae12055cd89df091f0126a56bc +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001256480_321658880.pth b/checkpoint_p0/milestones/checkpoint_001256480_321658880.pth new file mode 100644 index 0000000000000000000000000000000000000000..25e2fd69d9203d0bfac37a8015030754297a3b91 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001256480_321658880.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:715368b0674fa748e4fe2966ed5532de3d44f714bbf77daf19c4c504cfffe8c6 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001270976_325369856.pth b/checkpoint_p0/milestones/checkpoint_001270976_325369856.pth new file mode 100644 index 0000000000000000000000000000000000000000..53e2ceb4ff08488fcc5d1057556d7e596d916272 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001270976_325369856.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92c55a190759c6326bcd2637a813a50c7a0e14b7e03047c94ea061cc6cdfc2d6 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001285504_329089024.pth b/checkpoint_p0/milestones/checkpoint_001285504_329089024.pth new file mode 100644 index 0000000000000000000000000000000000000000..a4185592ffd4e1f3eb3ab0967c43c56223720ce8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001285504_329089024.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b93c0b840f7fe3922943c91fbb018038ec43ba1bc16e52e546512dc1de5d0a22 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001300000_332800000.pth b/checkpoint_p0/milestones/checkpoint_001300000_332800000.pth new file mode 100644 index 0000000000000000000000000000000000000000..9b45f49a42a3d12293b248a1f17b2d1629006c90 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001300000_332800000.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c4a3b43fad769bf15d2bbcf96a2c03ec3ffce78672d13dbac0145b0321df62f +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001314464_336502784.pth b/checkpoint_p0/milestones/checkpoint_001314464_336502784.pth new file mode 100644 index 0000000000000000000000000000000000000000..b0dcbd150c01dde2d76d228c14f72169122eba13 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001314464_336502784.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cee9804c858460249394fac59720621dbec8dde43164eb4cddab4542702e6bbc +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001328960_340213760.pth b/checkpoint_p0/milestones/checkpoint_001328960_340213760.pth new file mode 100644 index 0000000000000000000000000000000000000000..de602090620b0ab73dbf8cea50476bdb43d23681 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001328960_340213760.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b18ec10dd34a225552923262f9a718df10f5800c06605994fcd3e263a7e98317 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001343488_343932928.pth b/checkpoint_p0/milestones/checkpoint_001343488_343932928.pth new file mode 100644 index 0000000000000000000000000000000000000000..10d6e7b1c364e6646ac2039dbd870e3e03e64b80 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001343488_343932928.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a81946dbb085d60ae6408edffe41959f1fd7ccb1054a13b56550546d71310070 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001358016_347652096.pth b/checkpoint_p0/milestones/checkpoint_001358016_347652096.pth new file mode 100644 index 0000000000000000000000000000000000000000..77df901df0315a5c6a7ff1a63afd6da45a1b0854 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001358016_347652096.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d723c3613f085352a52b36bdaa0501570dfe83f8e8d054b6dd3fb603a80f5b10 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001372544_351371264.pth b/checkpoint_p0/milestones/checkpoint_001372544_351371264.pth new file mode 100644 index 0000000000000000000000000000000000000000..8c62b68ab3d74f4694ae1978f5d337bfd5b29d47 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001372544_351371264.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a78b87951f3f77cd330376ced42dfff2024ee849f5e0dcabea03421d40970f3 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001387008_355074048.pth b/checkpoint_p0/milestones/checkpoint_001387008_355074048.pth new file mode 100644 index 0000000000000000000000000000000000000000..9152acaad835a601adf69b0d4c2723c0caf6ce59 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001387008_355074048.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a469e4bb9928ed17d0bc45e6ec6294f1db39f134978268056b0262cdfd88e016 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001401536_358793216.pth b/checkpoint_p0/milestones/checkpoint_001401536_358793216.pth new file mode 100644 index 0000000000000000000000000000000000000000..7db1f6c2bb44658dab1be00dde82e3a13ab1d224 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001401536_358793216.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98485cb5460d886839ea1b8f466788b18d05e3f860b180fba2bbe3b716c7b3b4 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001416096_362520576.pth b/checkpoint_p0/milestones/checkpoint_001416096_362520576.pth new file mode 100644 index 0000000000000000000000000000000000000000..171c53f6e4556626603bfa52a53ad21d4367309a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001416096_362520576.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc83da5ade893e7319628695cc8538aae7521a26a25a636bc9e593f23afb3b38 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001430624_366239744.pth b/checkpoint_p0/milestones/checkpoint_001430624_366239744.pth new file mode 100644 index 0000000000000000000000000000000000000000..139bddf3741b557e8d6dd36b0d8772d132fcd0dd --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001430624_366239744.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05867aeaa216d76d6e576b251f6ccd6b7c1b30c4653f32a2c3da018119c37926 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001445120_369950720.pth b/checkpoint_p0/milestones/checkpoint_001445120_369950720.pth new file mode 100644 index 0000000000000000000000000000000000000000..a0dac3cae4fdc6cd63ba8a9c25b591eafb7cf31f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001445120_369950720.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffd0b7de8c32d7be96c65155a57d9a2f14515297554df761d5a78b4dd2309eae +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001459264_373571584.pth b/checkpoint_p0/milestones/checkpoint_001459264_373571584.pth new file mode 100644 index 0000000000000000000000000000000000000000..23d5a6777b9a19958de077f7afb27cab89e7b8fd --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001459264_373571584.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ce387cb9232c2ae11206510e41202e53c96fb6198bb6d40b457361f25940fa5 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001473664_377257984.pth b/checkpoint_p0/milestones/checkpoint_001473664_377257984.pth new file mode 100644 index 0000000000000000000000000000000000000000..7a7cca8c56d7740d97f07c9279d8046daf153352 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001473664_377257984.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ea486cd895943071f428295c44d31766d794e476b481eaf0e5e63f235d5f41d +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001488128_380960768.pth b/checkpoint_p0/milestones/checkpoint_001488128_380960768.pth new file mode 100644 index 0000000000000000000000000000000000000000..99f3ad8d8044719a9e82d1a62839593691c7b3c9 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001488128_380960768.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56282e9850ac8ab836ad452918da4007aea45736369c8ae8126bae1b2495aa17 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001502560_384655360.pth b/checkpoint_p0/milestones/checkpoint_001502560_384655360.pth new file mode 100644 index 0000000000000000000000000000000000000000..3e0dbca8e358762b270531f469709c0e6d4940df --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001502560_384655360.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52fa96ff9d6f3f1b145956edd1459abf9316b772f3b9e1d641221ec7e5c84615 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001517024_388358144.pth b/checkpoint_p0/milestones/checkpoint_001517024_388358144.pth new file mode 100644 index 0000000000000000000000000000000000000000..8f1aaf8042682e08392ff9f52ae111cdd1779f2b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001517024_388358144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e081f6158467d8f8a4194f76af8efd33d911cee72be02ff6066aa7d86f7b9983 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001531488_392060928.pth b/checkpoint_p0/milestones/checkpoint_001531488_392060928.pth new file mode 100644 index 0000000000000000000000000000000000000000..673608bab7b8839500343c9aeffc2171e62d1679 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001531488_392060928.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c85c5d9bcd7ed5cdf411fa3b1ad8834f8dabee1263df2c3a17f921e74df5800 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001545920_395755520.pth b/checkpoint_p0/milestones/checkpoint_001545920_395755520.pth new file mode 100644 index 0000000000000000000000000000000000000000..6d297d7d2967777445942e855a54a98776b6be86 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001545920_395755520.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ffc28896b73f00e932deccc92d2f01339c1cb4b6f4b2f95510612d3a32dcb69 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001560384_399458304.pth b/checkpoint_p0/milestones/checkpoint_001560384_399458304.pth new file mode 100644 index 0000000000000000000000000000000000000000..b885a3836b90a382ad91bda0e47aee8d2c279d8d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001560384_399458304.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edc48b8185f4f584ab858bd233ec8fbd0692f1d12f3d516a81109543b61321eb +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001574848_403161088.pth b/checkpoint_p0/milestones/checkpoint_001574848_403161088.pth new file mode 100644 index 0000000000000000000000000000000000000000..ce2ac6713e11e618f5caca0bf821386515bf90db --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001574848_403161088.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0d54dd1db89ab9f2b843cb4e7fa7537baa54127ba487709217f1f9e0ea5c7fe +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001589344_406872064.pth b/checkpoint_p0/milestones/checkpoint_001589344_406872064.pth new file mode 100644 index 0000000000000000000000000000000000000000..6ea807481f836703a296023098b690421f9599e5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001589344_406872064.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78c12630f5aec8bacb2d66a29d73b05bb30d8eb1c95aa03481676e2608ac6e56 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001603872_410591232.pth b/checkpoint_p0/milestones/checkpoint_001603872_410591232.pth new file mode 100644 index 0000000000000000000000000000000000000000..181d8c76f8d2ad9cb15e2fceff3e6d034c3cbfce --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001603872_410591232.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3bd2640e06cd41b029f89c7912a1434fa55fdfdd7ba0132ed28493f7cc613c1 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001618432_414318592.pth b/checkpoint_p0/milestones/checkpoint_001618432_414318592.pth new file mode 100644 index 0000000000000000000000000000000000000000..c14c91d4fd3524cf8027ff99c48cdab8e03be933 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001618432_414318592.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c02a49a494efaa14a4770d1bbb6b51c16cdf3202c5e2fcd45bac86e52c681cb5 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001632896_418021376.pth b/checkpoint_p0/milestones/checkpoint_001632896_418021376.pth new file mode 100644 index 0000000000000000000000000000000000000000..a53ffa6e0775d3e15e8c45a52e18b8b07ac77b4c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001632896_418021376.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65eee87e927bad784d4b3ce37e0f22e390c4ca6a4ee7fa3ad3e82c349f220c3d +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001647424_421740544.pth b/checkpoint_p0/milestones/checkpoint_001647424_421740544.pth new file mode 100644 index 0000000000000000000000000000000000000000..6f384a8f1b8ba3b7dd8a591299c1021852da3220 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001647424_421740544.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:154ab43f95c5de90045b4287cc8fb37b86b7216bd8c4d5657623fab38fac6f82 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001661888_425443328.pth b/checkpoint_p0/milestones/checkpoint_001661888_425443328.pth new file mode 100644 index 0000000000000000000000000000000000000000..1db6311bf1231bc8cc0fc5895864a4dc2b439d9b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001661888_425443328.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:003ed97f8fe41b3934dd6bb9dda0487da45b6b9bb13816c149e481ed3dd7ed6d +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001676416_429162496.pth b/checkpoint_p0/milestones/checkpoint_001676416_429162496.pth new file mode 100644 index 0000000000000000000000000000000000000000..fa9b8eff9f5aba3f18f31d07c0712f2772616a8a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001676416_429162496.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54e1b06608ecb91f5ff8ecccdcac8756e2fca846aad7e6d0c5b522ea0bea790b +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001690976_432889856.pth b/checkpoint_p0/milestones/checkpoint_001690976_432889856.pth new file mode 100644 index 0000000000000000000000000000000000000000..ae2c915cdafa50ce5cad851d8886d2a177915cde --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001690976_432889856.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a06454c60cdd302083e0481a62b91ab6e1bfe9a54ef5145136ef33871bd0edc +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001705536_436617216.pth b/checkpoint_p0/milestones/checkpoint_001705536_436617216.pth new file mode 100644 index 0000000000000000000000000000000000000000..ba0a33a26a231c44a30d268730d230339251dd4a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001705536_436617216.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d31e4d584d3163bcd30e2865fc81c71a2abb5808b6c045def0de2f44c3558920 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001720096_440344576.pth b/checkpoint_p0/milestones/checkpoint_001720096_440344576.pth new file mode 100644 index 0000000000000000000000000000000000000000..89ed3773e461806e378e3ae6505b66e7464a6b32 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001720096_440344576.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e56c9085902d53dd60e17131cbf829d06144ffc59ab7adf4f1d6d3f6cd6704fe +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001734592_444055552.pth b/checkpoint_p0/milestones/checkpoint_001734592_444055552.pth new file mode 100644 index 0000000000000000000000000000000000000000..a9b61c729e2727804e30adabe99bb51048fc2808 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001734592_444055552.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5aef3af7696debed47e426683c0fccebe06414cc22ad9478eec06039781853c +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001749120_447774720.pth b/checkpoint_p0/milestones/checkpoint_001749120_447774720.pth new file mode 100644 index 0000000000000000000000000000000000000000..98889b02d013b4b693219e70765a0d7c91f429b1 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001749120_447774720.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd73be95ec9528191413ca39d642178f631ff7a1f56f5b1942822f117be19d59 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001763712_451510272.pth b/checkpoint_p0/milestones/checkpoint_001763712_451510272.pth new file mode 100644 index 0000000000000000000000000000000000000000..ff5dddead504abc42dacad33122c283c505e9907 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001763712_451510272.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef6ff80b3107c7efbaf29b03c3389cbce31d96f383691bf73513d3385231daa2 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001778272_455237632.pth b/checkpoint_p0/milestones/checkpoint_001778272_455237632.pth new file mode 100644 index 0000000000000000000000000000000000000000..20cfe5631e9d9544fe360004210ff5a28eab53d6 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001778272_455237632.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1a9922096183e0377fa7f44a3878f56d32df3aaba9aa635336ab884d951e40b +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001792800_458956800.pth b/checkpoint_p0/milestones/checkpoint_001792800_458956800.pth new file mode 100644 index 0000000000000000000000000000000000000000..bc324dad1b4914cdf10f4fa8c89cf28e3e11fc7b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001792800_458956800.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94d15a8339156e83018d6268a0de75f25f2f1749ed905d2bd31969d91c7a1192 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001807328_462675968.pth b/checkpoint_p0/milestones/checkpoint_001807328_462675968.pth new file mode 100644 index 0000000000000000000000000000000000000000..80655c1ef6b383186e44e24a6f608f919efef450 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001807328_462675968.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaa148b3dc9311e64a0a7f3b74bab6d2179634647e124565ba1dbf3b9287b33a +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001821792_466378752.pth b/checkpoint_p0/milestones/checkpoint_001821792_466378752.pth new file mode 100644 index 0000000000000000000000000000000000000000..6538dcc955c7df727fd6fcce335fd5417a790ca0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001821792_466378752.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50663e1ded46d51db5155cdc6005c24e6168068982670e71dc1eacf83fe0be38 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001836352_470106112.pth b/checkpoint_p0/milestones/checkpoint_001836352_470106112.pth new file mode 100644 index 0000000000000000000000000000000000000000..618824de5ee651074e97418c1563c0946bf540a2 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001836352_470106112.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a6db695956bbcc9488ed10c2a4dcc5d164bbe733149bb7d6d1e93078383b9df +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001850816_473808896.pth b/checkpoint_p0/milestones/checkpoint_001850816_473808896.pth new file mode 100644 index 0000000000000000000000000000000000000000..9c00d75000b58226191f9526ce73cb2f12ac87e4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001850816_473808896.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2652a7cf64627f36b67d95620a65e6f2804e46fae58048f355022e34bdf47bd7 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001865344_477528064.pth b/checkpoint_p0/milestones/checkpoint_001865344_477528064.pth new file mode 100644 index 0000000000000000000000000000000000000000..9db16269d70421759891193d42bd79ced35faa49 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001865344_477528064.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:414c844507876fda1f9f9f4d1c146571a4b74279bd64457d15c8e81e79a4f494 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001879840_481239040.pth b/checkpoint_p0/milestones/checkpoint_001879840_481239040.pth new file mode 100644 index 0000000000000000000000000000000000000000..e3be2416ac20c60d73d8614a1292cce190af0492 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001879840_481239040.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dcb3cfeb75fc7f630d2844348b1767103cb291f1485226057bfec14633d5750 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001894368_484958208.pth b/checkpoint_p0/milestones/checkpoint_001894368_484958208.pth new file mode 100644 index 0000000000000000000000000000000000000000..736f77302bdcc87acff748bde8854b4fd11f99c6 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001894368_484958208.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b82382cd6d9d5d8e082dbc18fc5f8d863adf1760a5fea2e5ff7dd466d0ea636 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001908704_488628224.pth b/checkpoint_p0/milestones/checkpoint_001908704_488628224.pth new file mode 100644 index 0000000000000000000000000000000000000000..b96bfe3274bb27cc604b41fdef87aae45c7b8ff6 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001908704_488628224.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5bf8520064e962c434fb1ce05a1951801f17de85c515558f76468842f4edfc9 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001923200_492339200.pth b/checkpoint_p0/milestones/checkpoint_001923200_492339200.pth new file mode 100644 index 0000000000000000000000000000000000000000..319359e91cce40c0aea48007a283265c235c27e6 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001923200_492339200.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac0ac22fe8cab38ac4df788f22b4454ef6ebf13650541e99b00aa67b092cdbe4 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001937664_496041984.pth b/checkpoint_p0/milestones/checkpoint_001937664_496041984.pth new file mode 100644 index 0000000000000000000000000000000000000000..7bcd1f5bada25480dc3d7f800c21da9c2e454b1e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001937664_496041984.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f13a3843b480ce5d88878f72e9507ff3022ad96c1c3c03063e4970df23af060 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001952192_499761152.pth b/checkpoint_p0/milestones/checkpoint_001952192_499761152.pth new file mode 100644 index 0000000000000000000000000000000000000000..b7aaed20eae65e75e3d7c068832e44112b29ac1b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001952192_499761152.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f334358b5d7d856223632def08be5997292898bb57aae7d2a70aa2378efeaae8 +size 20797195 diff --git a/checkpoint_p1/best_001132576_289939456_reward_154.830.pth b/checkpoint_p1/best_001132576_289939456_reward_154.830.pth new file mode 100644 index 0000000000000000000000000000000000000000..08d84d1f087ae56370b7cd701d1470748d8d3c4a --- /dev/null +++ b/checkpoint_p1/best_001132576_289939456_reward_154.830.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:367c24b460c305f6ae5e752b337c75cf4baafe060e4764917fc63343ba47bb3f +size 20795763 diff --git a/checkpoint_p1/checkpoint_001965152_503078912.pth b/checkpoint_p1/checkpoint_001965152_503078912.pth new file mode 100644 index 0000000000000000000000000000000000000000..660129ca0ff1e5cc9bb4b990d2d377ce10548cf5 --- /dev/null +++ b/checkpoint_p1/checkpoint_001965152_503078912.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6656dbf935024c837b6da6bb0662bc12947f00d19a6ca68e75895f9ddcc6868 +size 20796291 diff --git a/checkpoint_p1/checkpoint_001966144_503332864.pth b/checkpoint_p1/checkpoint_001966144_503332864.pth new file mode 100644 index 0000000000000000000000000000000000000000..61bc15a4f7697de60bfb6dd45a9a072bdee10b66 --- /dev/null +++ b/checkpoint_p1/checkpoint_001966144_503332864.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc83a5a942c6002bf6d2dde4c9f1679032bbdb7197082d75b31d234959de0af0 +size 20796291 diff --git a/checkpoint_p1/milestones/checkpoint_000013600_3481600.pth b/checkpoint_p1/milestones/checkpoint_000013600_3481600.pth new file mode 100644 index 0000000000000000000000000000000000000000..e433e1a552846a84586f3db08610e5bb99ff9e62 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000013600_3481600.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ada183a4bbc0dce2c7aeb5a2622cfaa1b12998dff3c17bfcaec4df81a5dfd14 +size 20796955 diff --git a/checkpoint_p1/milestones/checkpoint_000028192_7217152.pth b/checkpoint_p1/milestones/checkpoint_000028192_7217152.pth new file mode 100644 index 0000000000000000000000000000000000000000..e14d392f70f902b0deacd20e9c426ac711757590 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000028192_7217152.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c545e2be847c875dca107cb0a5aeb3f7be4e2a3f9b0afce9a1ca1c360f12a6ae +size 20796955 diff --git a/checkpoint_p1/milestones/checkpoint_000042816_10960896.pth b/checkpoint_p1/milestones/checkpoint_000042816_10960896.pth new file mode 100644 index 0000000000000000000000000000000000000000..5b814cba784541881ede9b4c65a9c748a0e67884 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000042816_10960896.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8111a9e9176dc3be32a9c60772b75d696c30913829da5efa511edaf4ec96980f +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000057344_14680064.pth b/checkpoint_p1/milestones/checkpoint_000057344_14680064.pth new file mode 100644 index 0000000000000000000000000000000000000000..a2047021808a246f25c749079f8469307de874da --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000057344_14680064.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a31343aff66e3741b05e643f36838d786dbcaddd930b5c56d644c7a309a9e466 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000072064_18448384.pth b/checkpoint_p1/milestones/checkpoint_000072064_18448384.pth new file mode 100644 index 0000000000000000000000000000000000000000..77d3f72c7d0bfbad6423aa67c431da68d9701d7e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000072064_18448384.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a5e5c71ac03be7c8eb1266bd93bbc3c688154c36ab479dbece871c3704003fe +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000086688_22192128.pth b/checkpoint_p1/milestones/checkpoint_000086688_22192128.pth new file mode 100644 index 0000000000000000000000000000000000000000..94cb40fdc1c8399d94877ebc9167165536ab284d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000086688_22192128.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dc775aad8f779f4dbb9c8e35316e79a46d88ca64beea3f73f84420f66116803 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000101312_25935872.pth b/checkpoint_p1/milestones/checkpoint_000101312_25935872.pth new file mode 100644 index 0000000000000000000000000000000000000000..a44849d7d88cd3dc833e155ba849078ed5416a35 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000101312_25935872.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a40e684d498e547de12720300212e4d046aa53c8116e0b13512199edc44375f0 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000116000_29696000.pth b/checkpoint_p1/milestones/checkpoint_000116000_29696000.pth new file mode 100644 index 0000000000000000000000000000000000000000..90f2e2fa83103fee7b1ff645bb58b0b548bd98b3 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000116000_29696000.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e994434b896b3720237e947bb77d056d39cb47b2a53d8cd9fb090e822f70977 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000130496_33406976.pth b/checkpoint_p1/milestones/checkpoint_000130496_33406976.pth new file mode 100644 index 0000000000000000000000000000000000000000..6249c4c8fcb7872c5f5f7d7e7cb990266fabc2af --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000130496_33406976.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:923ee063fca5d4cb88d1b047b09ad98e34b3f2bdab26039dfa5707692506c2ac +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000145152_37158912.pth b/checkpoint_p1/milestones/checkpoint_000145152_37158912.pth new file mode 100644 index 0000000000000000000000000000000000000000..b5c407d7206c21f8f8cfbb06f2a942a8735cd199 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000145152_37158912.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e230468157e239ea026f6342706bb93cea4a819382069b708b5e01c15f8347c +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000159776_40902656.pth b/checkpoint_p1/milestones/checkpoint_000159776_40902656.pth new file mode 100644 index 0000000000000000000000000000000000000000..783f9b756baf4130641ee27515a92f3c4aceedef --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000159776_40902656.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36c4c718278d83b35da0a282ede6695afdc6f4701be3fdb895869d65c70c9c02 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000174400_44646400.pth b/checkpoint_p1/milestones/checkpoint_000174400_44646400.pth new file mode 100644 index 0000000000000000000000000000000000000000..93f8c59e107f9bd330325cfd4f1d922e5b50b3e1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000174400_44646400.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b241c02623e488c1dc81bac03103fc8ed8758fd9f641da3050d76adab7b21c24 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000189056_48398336.pth b/checkpoint_p1/milestones/checkpoint_000189056_48398336.pth new file mode 100644 index 0000000000000000000000000000000000000000..80925a2b7a020f21c4f7fa6ed960a87c4d1dac32 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000189056_48398336.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2036784341b152c2ff3caa20dae83662e9ada3207a1c1aae16eeac0c998e23e6 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000203488_52092928.pth b/checkpoint_p1/milestones/checkpoint_000203488_52092928.pth new file mode 100644 index 0000000000000000000000000000000000000000..a9e033738ee2a57c1d42e3832046264152d64191 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000203488_52092928.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebbee4862368415a4cc232aa7f4a8a826b9c912d80ec67bac6a2883d70f07872 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000217984_55803904.pth b/checkpoint_p1/milestones/checkpoint_000217984_55803904.pth new file mode 100644 index 0000000000000000000000000000000000000000..e7aa9db834e79281d94d80a38a0b4b2f1c0aa0b3 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000217984_55803904.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82612deeb5d03337a5d38202120073a5d9ea5aafdce8b16e2c4b3c258b5f1e75 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000232672_59564032.pth b/checkpoint_p1/milestones/checkpoint_000232672_59564032.pth new file mode 100644 index 0000000000000000000000000000000000000000..292963c9c0283a002a894285cfba93c77ce41706 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000232672_59564032.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2079ac818561ec82aa8e0d039758d9ea5f15b57720993769673e6131b23e4bfa +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000247296_63307776.pth b/checkpoint_p1/milestones/checkpoint_000247296_63307776.pth new file mode 100644 index 0000000000000000000000000000000000000000..be6b9938a1b7a791db9864e912e3eeb0657c4a8a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000247296_63307776.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:514ef6cf4eff54689b8cb0c6c6541fad3f933d7a50453b9a11cd6cde0a7dced7 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000261856_67035136.pth b/checkpoint_p1/milestones/checkpoint_000261856_67035136.pth new file mode 100644 index 0000000000000000000000000000000000000000..21cd8ba3f76da5e0f8acb836b1ae35ad951bee1f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000261856_67035136.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18602d2250a2da12c6441506343b32aa3103d36bb7884c834f6b7e71811fd67a +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000276448_70770688.pth b/checkpoint_p1/milestones/checkpoint_000276448_70770688.pth new file mode 100644 index 0000000000000000000000000000000000000000..cdc4de50a1f7ce81c4692a82c99ef6f1b165caee --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000276448_70770688.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3cb7efa98d719228f51cf5f005fa2c21ba2fb0661bba2fe81ceba7382969b45 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000291040_74506240.pth b/checkpoint_p1/milestones/checkpoint_000291040_74506240.pth new file mode 100644 index 0000000000000000000000000000000000000000..5121d6a253ce7efecc6e9433a62bc3ee3f6f38a5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000291040_74506240.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffa708e98cedebcc5bee38854b081cc1a11ebdeed6841e75d09c467e0141925e +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000305536_78217216.pth b/checkpoint_p1/milestones/checkpoint_000305536_78217216.pth new file mode 100644 index 0000000000000000000000000000000000000000..64aafb26a238c3276757f8b8fe710e032494a080 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000305536_78217216.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4acacd18c11fae871b365722a00d86d1235d905ebb6934488c4ca753fc6a583b +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000319968_81911808.pth b/checkpoint_p1/milestones/checkpoint_000319968_81911808.pth new file mode 100644 index 0000000000000000000000000000000000000000..f742f04dc1a989edba2cdf49e67d86f8ed12ab64 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000319968_81911808.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:632bdc393f17ec3190d74725952f1f330724a25a3745ec6f1d4620da83a4922b +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000334368_85598208.pth b/checkpoint_p1/milestones/checkpoint_000334368_85598208.pth new file mode 100644 index 0000000000000000000000000000000000000000..a804115f011e480dcf04be9239b912bd2431d5dc --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000334368_85598208.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac3535b6e2a29dbe4edbba79834369a1ce4bcfa092db854950d51226c0b57d43 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000348800_89292800.pth b/checkpoint_p1/milestones/checkpoint_000348800_89292800.pth new file mode 100644 index 0000000000000000000000000000000000000000..48fbc7c069b0bacf5f4e3e08277ed86ff4b341a9 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000348800_89292800.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17eabe42d4d1514adeb60d479fde5cd60a6079c0216e013afb1eb27fecaf4823 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000363200_92979200.pth b/checkpoint_p1/milestones/checkpoint_000363200_92979200.pth new file mode 100644 index 0000000000000000000000000000000000000000..df9ce3bd414b100cacdb4f3966e6c133cd3174b7 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000363200_92979200.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b0729d53302c0a10e9a433865594ba5863096b7977c99a286d3ed30f6b92e02 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000377632_96673792.pth b/checkpoint_p1/milestones/checkpoint_000377632_96673792.pth new file mode 100644 index 0000000000000000000000000000000000000000..f49bbe1207c88411a98be417be0fe5855e8c340a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000377632_96673792.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80b7e1c3adc973baab33e260be098f249cefa9f58c7455974d1bccefdbfe900f +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000392064_100368384.pth b/checkpoint_p1/milestones/checkpoint_000392064_100368384.pth new file mode 100644 index 0000000000000000000000000000000000000000..6a2aede8da1b1491eedf87d47701898a5946d69d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000392064_100368384.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6df6895e0bb4733d4513f34595c51ef629ec727b612418ced475060312bd4977 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000406496_104062976.pth b/checkpoint_p1/milestones/checkpoint_000406496_104062976.pth new file mode 100644 index 0000000000000000000000000000000000000000..ea07c31346403c654a01e7c07ae71c19c09a82a8 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000406496_104062976.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f286c21819cb5d308a9592d25146c61663136e44e9989ab41d24a9a77da42802 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000420864_107741184.pth b/checkpoint_p1/milestones/checkpoint_000420864_107741184.pth new file mode 100644 index 0000000000000000000000000000000000000000..b3dbdc614402e1c47254ed22eb5509fbbdfdf1b2 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000420864_107741184.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d20d0ae8d74c0102ac1799dba2363a2890128a367e992df6df0f573565a47d53 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000435264_111427584.pth b/checkpoint_p1/milestones/checkpoint_000435264_111427584.pth new file mode 100644 index 0000000000000000000000000000000000000000..408059bc832aa0c20a1af07a1afa487091f09abf --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000435264_111427584.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46af9d4ff08f202dc1db29a8c59d75b75f7855f6be7fecb99aa431aa0b27d745 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000449664_115113984.pth b/checkpoint_p1/milestones/checkpoint_000449664_115113984.pth new file mode 100644 index 0000000000000000000000000000000000000000..b5fd0856604c9f4bcb52b84ba09a6df9b1c172e7 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000449664_115113984.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8dcbf8bac6c21895ffed3fd7e51816833ecf1063218362dea72ca851e12b246 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000464096_118808576.pth b/checkpoint_p1/milestones/checkpoint_000464096_118808576.pth new file mode 100644 index 0000000000000000000000000000000000000000..6e9f590f600e19bf607cd90b9970631cf160ac96 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000464096_118808576.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d3aab710390d7f9eadc2abe199c9ff425d7a0e41c2fa2346604c0dbc2c527ce +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000478528_122503168.pth b/checkpoint_p1/milestones/checkpoint_000478528_122503168.pth new file mode 100644 index 0000000000000000000000000000000000000000..ea04cd5e283c9c9580b3d9a5cc92d1d067e3dae2 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000478528_122503168.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f153b376f2a55442284040cbe7be9d4ef0388beacd6e89f1f6b1446723fb41e0 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000492928_126189568.pth b/checkpoint_p1/milestones/checkpoint_000492928_126189568.pth new file mode 100644 index 0000000000000000000000000000000000000000..aaf616fb3ecbb2e13cf5aa837440001b9274e03c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000492928_126189568.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24737d9f4e37ebae7af71302955ca477d83e90c6b9a48619605bbe90ea8086ea +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000507360_129884160.pth b/checkpoint_p1/milestones/checkpoint_000507360_129884160.pth new file mode 100644 index 0000000000000000000000000000000000000000..a26628247924932a5348e041656ff19f7b5a07b2 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000507360_129884160.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a972ba0214339b238f51c90d4fff456bae6470dec53f2d822ed017b6b8aab18e +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000521792_133578752.pth b/checkpoint_p1/milestones/checkpoint_000521792_133578752.pth new file mode 100644 index 0000000000000000000000000000000000000000..e30d86a890684b9954f3757af7988b43d5a9754f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000521792_133578752.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7835f63e2b0ddfb0f9403c7c74be19ef6ad3ceed8c0244fb7aff226213e410cc +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000536256_137281536.pth b/checkpoint_p1/milestones/checkpoint_000536256_137281536.pth new file mode 100644 index 0000000000000000000000000000000000000000..77e9c42ef72e96edfb0fe0b5553cd6f07a5ddf2f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000536256_137281536.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47a8941b5ff1d47f8b8f396d4b171c389cc316352a504c2331585d08b7be4def +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000550816_141008896.pth b/checkpoint_p1/milestones/checkpoint_000550816_141008896.pth new file mode 100644 index 0000000000000000000000000000000000000000..68b6bff61513dcfcd0981e7e7cf37203fcfe04a1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000550816_141008896.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87a0a72d65dfe472849789acc2844f83348602e17830cbf23cd05aa08df972b4 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000565280_144711680.pth b/checkpoint_p1/milestones/checkpoint_000565280_144711680.pth new file mode 100644 index 0000000000000000000000000000000000000000..e83b1180561203cec3669344d8b827a8e3ae3be1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000565280_144711680.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f05b7e436efa30bad0d7c1d0a04d3ca838c3f3262bf250bad1242244f00f268 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000579712_148406272.pth b/checkpoint_p1/milestones/checkpoint_000579712_148406272.pth new file mode 100644 index 0000000000000000000000000000000000000000..74d6c4a55de5b36b9283b07dd1515bb0dc9daca1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000579712_148406272.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4086e32f399171782c6b08ae7734e75668df98c5e6ccbef9b5ef0410e8531343 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000594176_152109056.pth b/checkpoint_p1/milestones/checkpoint_000594176_152109056.pth new file mode 100644 index 0000000000000000000000000000000000000000..b92ae5a7dc94fc236858cd467bfb786fea60caeb --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000594176_152109056.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb3ef188f9b5dadcafa11213f09d65c5b990a7f379d250382b70edd3d74cd1f2 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000608640_155811840.pth b/checkpoint_p1/milestones/checkpoint_000608640_155811840.pth new file mode 100644 index 0000000000000000000000000000000000000000..7e54322ce30bc8321a392aa3c94ebaec40fb7f25 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000608640_155811840.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:284abf1e947fe223ad2434aa5aaa78ae83f9884f2d76e61891172d02c07021dd +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000623168_159531008.pth b/checkpoint_p1/milestones/checkpoint_000623168_159531008.pth new file mode 100644 index 0000000000000000000000000000000000000000..39401953fc47e6a03fe0f93e1c05282fae4fe2b2 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000623168_159531008.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:987889bff31bacb36042755cb723c3be8bfce98bcc6c8262eefd9aa481e115a3 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000637632_163233792.pth b/checkpoint_p1/milestones/checkpoint_000637632_163233792.pth new file mode 100644 index 0000000000000000000000000000000000000000..8e836cb7a6c21211fd3ebf8648e9c3ba7c0e999a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000637632_163233792.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d158ca0fc0c2b2cd6cd9555c318acf629e6f57085cd05bd2380d27be25b001e +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000652224_166969344.pth b/checkpoint_p1/milestones/checkpoint_000652224_166969344.pth new file mode 100644 index 0000000000000000000000000000000000000000..64ec9d3626d990d91fbe28f1d439fe653924dbbe --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000652224_166969344.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1af770a782cb1fb737c019d8090fc5ea547774a8413b59b8585e336cfe4ddfec +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000666752_170688512.pth b/checkpoint_p1/milestones/checkpoint_000666752_170688512.pth new file mode 100644 index 0000000000000000000000000000000000000000..9ebf7f43a5062693967f24db5d2b2acdb9c0afc8 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000666752_170688512.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f226ff428f42af211b634cb50b9ba9c94d47e015e190ee4e5495bba9f2ef314 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000681248_174399488.pth b/checkpoint_p1/milestones/checkpoint_000681248_174399488.pth new file mode 100644 index 0000000000000000000000000000000000000000..c6d7b415fcb4b0b48838524ff0cf661b716d1194 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000681248_174399488.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9fddec083193c75cea0a7ab89e85918d4b7a7cc6ce721a5cb0f0cb986f134d7 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000695744_178110464.pth b/checkpoint_p1/milestones/checkpoint_000695744_178110464.pth new file mode 100644 index 0000000000000000000000000000000000000000..01f6c8c986440dffffcb25cb31732426a4d8a41e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000695744_178110464.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:029e3a2428b0b6f6dba36b40d591790d6b369329a011ffef17f3abd880ba1599 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000710272_181829632.pth b/checkpoint_p1/milestones/checkpoint_000710272_181829632.pth new file mode 100644 index 0000000000000000000000000000000000000000..cb5e98cca9b7a3b44b581a38d85a247841dec707 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000710272_181829632.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98651d20615d766594cbd8046a448b641f34c846595e755c05f1dce6da32f6c0 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000724704_185524224.pth b/checkpoint_p1/milestones/checkpoint_000724704_185524224.pth new file mode 100644 index 0000000000000000000000000000000000000000..88059811354def3a03c8e03cabead2b2545a6c74 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000724704_185524224.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad3c9b172d5973944e542b55ecf3d36dfd76cf0d96315138c79b825f497f7242 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000739232_189243392.pth b/checkpoint_p1/milestones/checkpoint_000739232_189243392.pth new file mode 100644 index 0000000000000000000000000000000000000000..efd0ea2cf85778c0f8862697297e5955cb1ff66a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000739232_189243392.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a24ee8be825d792b1030d72ad55081563c049b0b3adcfab88409e5902209c2f +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000753696_192946176.pth b/checkpoint_p1/milestones/checkpoint_000753696_192946176.pth new file mode 100644 index 0000000000000000000000000000000000000000..9cb13bfabca40bb0949a69ff3efc0d41b0b73f96 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000753696_192946176.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74c6d400553d5bdb7068b043bfe41c699980c1affcdea753b5a865b924b15acb +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000768256_196673536.pth b/checkpoint_p1/milestones/checkpoint_000768256_196673536.pth new file mode 100644 index 0000000000000000000000000000000000000000..c01d7e5ed7ee52718930a331928206116acd98b3 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000768256_196673536.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35710e53d02a97f20e04f9791abcb75c1bd506213814bd237775d6fe5f2a42bf +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000782720_200376320.pth b/checkpoint_p1/milestones/checkpoint_000782720_200376320.pth new file mode 100644 index 0000000000000000000000000000000000000000..88874c6902f143f4cca53a492c39c5c26f1e3792 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000782720_200376320.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c80978b36032373e9ff12ad7a02bd084bb668b405914b39fa31faed86951556 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000797216_204087296.pth b/checkpoint_p1/milestones/checkpoint_000797216_204087296.pth new file mode 100644 index 0000000000000000000000000000000000000000..76c32ace12f75fd1e626daeb6f4c42bdba1df56e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000797216_204087296.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:331718f591365fda385cca717d1b0169c45ba1cbbbf3ea94f9f9c3ced45462d3 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000811712_207798272.pth b/checkpoint_p1/milestones/checkpoint_000811712_207798272.pth new file mode 100644 index 0000000000000000000000000000000000000000..5fc2a2544913e75f6d2f849e69c1528f8826e983 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000811712_207798272.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cc83e059aac4e4d9d43dc3dbfa61fcf8707d4653c948698268ccd2a01df3281 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000826208_211509248.pth b/checkpoint_p1/milestones/checkpoint_000826208_211509248.pth new file mode 100644 index 0000000000000000000000000000000000000000..764f2000bb6754016f05791ff94b9e094d4c4567 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000826208_211509248.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f85f6b10de73a8e64e65a0aa4838b04aa333146a35a3a7f25aabd4a7f1807b03 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000840736_215228416.pth b/checkpoint_p1/milestones/checkpoint_000840736_215228416.pth new file mode 100644 index 0000000000000000000000000000000000000000..a7d120fc669035e9b4148cfb2c1f6b8ef8258016 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000840736_215228416.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e33c0645706e956e9efb7e5229a1282eb6ebaf1b3b1b3276208c11809ec56da +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000855264_218947584.pth b/checkpoint_p1/milestones/checkpoint_000855264_218947584.pth new file mode 100644 index 0000000000000000000000000000000000000000..f16dbd66e9af5a859ed63b1572ebc1e4408d1460 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000855264_218947584.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3fab7622b830d85c333b5009f10880006efd64c93427870dc46cc311e8eed07 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000869728_222650368.pth b/checkpoint_p1/milestones/checkpoint_000869728_222650368.pth new file mode 100644 index 0000000000000000000000000000000000000000..6e25055d7ca2caacbb18788018ef50535be2d3f9 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000869728_222650368.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d2bce7558fe8acef709e7a4a9e52e520010430e9715ff7f687d0654a822f259 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000884256_226369536.pth b/checkpoint_p1/milestones/checkpoint_000884256_226369536.pth new file mode 100644 index 0000000000000000000000000000000000000000..539cd3fc01b261a39a5f91999a55dacb23a3d5bc --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000884256_226369536.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce8544ce517bb7138332705f9dd0e31a0e10c693bbbfd9011017a816cff2bd0a +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000898784_230088704.pth b/checkpoint_p1/milestones/checkpoint_000898784_230088704.pth new file mode 100644 index 0000000000000000000000000000000000000000..0ec15f304842e8e1a244a4166b3bff5ed10409c6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000898784_230088704.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34ff4260ec0208ab3947c95191c29e81578c6fbea782c10e3a8d75e19a301671 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000913312_233807872.pth b/checkpoint_p1/milestones/checkpoint_000913312_233807872.pth new file mode 100644 index 0000000000000000000000000000000000000000..9bc76bfc4c21a3a3a25e27e30e6b5cfca1aee672 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000913312_233807872.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a923b3627f3c45c45eb4b762758b283a0a0d4f903e14572e2595fb1269e2ed2 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000927744_237502464.pth b/checkpoint_p1/milestones/checkpoint_000927744_237502464.pth new file mode 100644 index 0000000000000000000000000000000000000000..cf670a7115c475e62f2305f86f399265fa7929dd --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000927744_237502464.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7147eacf3cbbf31e10861ad1f081947130392437203ec4a9a0f8fb8e29fcc54 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000942144_241188864.pth b/checkpoint_p1/milestones/checkpoint_000942144_241188864.pth new file mode 100644 index 0000000000000000000000000000000000000000..e54af9a762ab161d5829eff51291c7a8d4b2196e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000942144_241188864.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eedab46312d687f0c9384bdf21c03998614f315329a13f715a2cc5c8289ccc5f +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000956672_244908032.pth b/checkpoint_p1/milestones/checkpoint_000956672_244908032.pth new file mode 100644 index 0000000000000000000000000000000000000000..1138f397ec79886f39ddb0053963831f2b432f2f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000956672_244908032.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e964f18979932529015d1592832e17cc86e2c9362f176384464518b0d82b8e1f +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000971200_248627200.pth b/checkpoint_p1/milestones/checkpoint_000971200_248627200.pth new file mode 100644 index 0000000000000000000000000000000000000000..1b9a0fca9508b83f2f60f672dd64552319e1166e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000971200_248627200.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81facd8fe1dd41cb56f6ea00bacb9ce778c49282b77ef8f0788643bba4b04d5d +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000985728_252346368.pth b/checkpoint_p1/milestones/checkpoint_000985728_252346368.pth new file mode 100644 index 0000000000000000000000000000000000000000..5628480851fab9808a9475278c6b58ee64ae8724 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000985728_252346368.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f8f5b67d5b698ee845fadbaec4d834c6ee3897ee836982cb85a42f1eccac1cb +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001000256_256065536.pth b/checkpoint_p1/milestones/checkpoint_001000256_256065536.pth new file mode 100644 index 0000000000000000000000000000000000000000..6b00fd01fda06c2246a23a057bffbb20bf1da314 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001000256_256065536.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:006774d26d84c69f93a839fc59f2c958c57d627b88c8d5879a15b2732b35a265 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001014656_259751936.pth b/checkpoint_p1/milestones/checkpoint_001014656_259751936.pth new file mode 100644 index 0000000000000000000000000000000000000000..ea48cc6fc2ceb3ca45136cad2b26e04f50a5ea9f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001014656_259751936.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f83ce626b574c12eebe520438a821e929d23b01531ef4a1119e71913fb9e9f4 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001029120_263454720.pth b/checkpoint_p1/milestones/checkpoint_001029120_263454720.pth new file mode 100644 index 0000000000000000000000000000000000000000..46d282ac31f8b6aacd74d9fee72211338910805e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001029120_263454720.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a7d5fc04451a4fe4d0330c5f9017bfe4e5363bd8e4de614fa070e0b1eac7ab9 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001043552_267149312.pth b/checkpoint_p1/milestones/checkpoint_001043552_267149312.pth new file mode 100644 index 0000000000000000000000000000000000000000..7f0452b288c578b6fea065232c101128d8876a6c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001043552_267149312.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5db23324078a14e93e76f1649dbb0a49dbfd6306cac009bfa1b2f4e4a2ed91c9 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001058016_270852096.pth b/checkpoint_p1/milestones/checkpoint_001058016_270852096.pth new file mode 100644 index 0000000000000000000000000000000000000000..c2757265f1cd05133f0a76b0b07a3f5815b3d013 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001058016_270852096.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed927e35c03777e65fd19d78740b2235b660d39579437ec620192dd552229ebf +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001072512_274563072.pth b/checkpoint_p1/milestones/checkpoint_001072512_274563072.pth new file mode 100644 index 0000000000000000000000000000000000000000..191bbd4453502cf2b5a22d3c21f7de39825fca2a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001072512_274563072.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fa3dcb31dbfd9d77efe24109baea3c78e2e7678f1422c6df2e7b7d794c3a2ea +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001087008_278274048.pth b/checkpoint_p1/milestones/checkpoint_001087008_278274048.pth new file mode 100644 index 0000000000000000000000000000000000000000..a48c9cb839f358b5516e8c1cae221fa3c8b2e9a5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001087008_278274048.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:187795219bd050b42642d8071374f91623d739bc06292a06c3fc349a279e4d3a +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001101504_281985024.pth b/checkpoint_p1/milestones/checkpoint_001101504_281985024.pth new file mode 100644 index 0000000000000000000000000000000000000000..c08252038373af842cdf0034a1d626f3e02d077e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001101504_281985024.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb12a4771f0fd37f804856bb2a8a3c01335454b44ddef0f5e0af9c5b3cd38eb9 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001116064_285712384.pth b/checkpoint_p1/milestones/checkpoint_001116064_285712384.pth new file mode 100644 index 0000000000000000000000000000000000000000..619006f7ce621ae5a15ba314d1449b272c8d9ab6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001116064_285712384.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15ad4dbb30f3c9b00b3f11af5b0eb25775e6afdcafcbe5e06af792dd3afa8104 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001130656_289447936.pth b/checkpoint_p1/milestones/checkpoint_001130656_289447936.pth new file mode 100644 index 0000000000000000000000000000000000000000..ab7f75096371f7a497c7b97f4f9bfc92b39d1201 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001130656_289447936.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:738be3f96b50f40b42308fb05b12ccd197e1998682667a3b66def0a061ca2284 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001145152_293158912.pth b/checkpoint_p1/milestones/checkpoint_001145152_293158912.pth new file mode 100644 index 0000000000000000000000000000000000000000..3b6ab6b847a880188565c8d282ab3a1c31b76358 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001145152_293158912.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:405720f4a58db6d9cdc76968b0e03ca541252dee0c66083eb8d9fe39b00e470a +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001159648_296869888.pth b/checkpoint_p1/milestones/checkpoint_001159648_296869888.pth new file mode 100644 index 0000000000000000000000000000000000000000..c3a447fc84cd5a0bf3d5fa20eb4e37a67d313561 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001159648_296869888.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a60be1c4e0aed08c3e07c4fce10f8368e47c4e91dd7426b7811d90c8ee3ea1e8 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001174112_300572672.pth b/checkpoint_p1/milestones/checkpoint_001174112_300572672.pth new file mode 100644 index 0000000000000000000000000000000000000000..bf73140a85fa223f8997048be01fdba72a47bff5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001174112_300572672.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c542377d36a86d0f9e1fbbf937c31924688c4c5e961b184c04d08913a08dfa64 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001188640_304291840.pth b/checkpoint_p1/milestones/checkpoint_001188640_304291840.pth new file mode 100644 index 0000000000000000000000000000000000000000..2ab0a574c08d5719c1dccf5a8f02e7ef03525ec5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001188640_304291840.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0719ac94702ccfef8b68d12a3c2a1660a0333d791b11f0e1daf2adb2f5426d5 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001203200_308019200.pth b/checkpoint_p1/milestones/checkpoint_001203200_308019200.pth new file mode 100644 index 0000000000000000000000000000000000000000..ecba019b7ad058f37d03505965018e47fbecd74c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001203200_308019200.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d38eba9bdaeedbc282881a14fc4acf90ac33af8df9013ac6cbd600aaf578ffa +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001225920_313835520.pth b/checkpoint_p1/milestones/checkpoint_001225920_313835520.pth new file mode 100644 index 0000000000000000000000000000000000000000..a519cd89a31e48da1e3975ec307a57790c1a252e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001225920_313835520.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7d6db1e84db3c2ea4e91b701074e36cc39ee0b567505028307bab7f88b4435c +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001240416_317546496.pth b/checkpoint_p1/milestones/checkpoint_001240416_317546496.pth new file mode 100644 index 0000000000000000000000000000000000000000..711e35b5d75d724e4fd9f88f4b515aac01de6caa --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001240416_317546496.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8614aa682acac8e344776eecd7b4a5a0fe9ba6b4b76f8a49154387e4daa74e9 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001254880_321249280.pth b/checkpoint_p1/milestones/checkpoint_001254880_321249280.pth new file mode 100644 index 0000000000000000000000000000000000000000..9057233a4e048d3ac24d9ef32e752efee67aa7e0 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001254880_321249280.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87b85116bdf99389b3cb0b9d3516754aadde02cc7cfde52090593aafa9a0f279 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001269376_324960256.pth b/checkpoint_p1/milestones/checkpoint_001269376_324960256.pth new file mode 100644 index 0000000000000000000000000000000000000000..4700f7b2e06196ea213cdde5f76ce4d30fc6470c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001269376_324960256.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9d47544521da7c98cf83aef460849494253493d6abff13a99e6b07e7d934af8 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001283872_328671232.pth b/checkpoint_p1/milestones/checkpoint_001283872_328671232.pth new file mode 100644 index 0000000000000000000000000000000000000000..78a28483cc144f8a69ea48a5885a19915eebc8d3 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001283872_328671232.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:322b236d5a6900ececd1f4abec0372823862b40b90bf4246263753392a47101c +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001298432_332398592.pth b/checkpoint_p1/milestones/checkpoint_001298432_332398592.pth new file mode 100644 index 0000000000000000000000000000000000000000..ae46a86642f3a47952f4180f92f089a2522b52d9 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001298432_332398592.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c62b283c9368bd9914fe5f1ad73de95387396cb6cd9e0afe61d8c481f0187171 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001312928_336109568.pth b/checkpoint_p1/milestones/checkpoint_001312928_336109568.pth new file mode 100644 index 0000000000000000000000000000000000000000..5c37e974975506984ffd3989909f2df508a2448d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001312928_336109568.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee4edf993979919d5e297f8bafd86db3759c07e387694965361255a26c2a5a0a +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001327328_339795968.pth b/checkpoint_p1/milestones/checkpoint_001327328_339795968.pth new file mode 100644 index 0000000000000000000000000000000000000000..155321c508aa2ffdb7e9de02ed0f49894c0b4d22 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001327328_339795968.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d02dea62dc8154041675ab5000bdf25d3e722f44fa989cfbac28deaa599e4be +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001341824_343506944.pth b/checkpoint_p1/milestones/checkpoint_001341824_343506944.pth new file mode 100644 index 0000000000000000000000000000000000000000..604217b458e49031b0fc20efe4713a2685c8a692 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001341824_343506944.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb5d76fa795c8740e561d32e711d25db4584a30eaa889a5c4db5612fddd1c0fc +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001356352_347226112.pth b/checkpoint_p1/milestones/checkpoint_001356352_347226112.pth new file mode 100644 index 0000000000000000000000000000000000000000..559a63836cb987817fd491d468ecc7181901da6b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001356352_347226112.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c4a1d2d8184eb9c2d4cc941f710a4ecffc9dcf24984bb52650bb8493c594872 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001370912_350953472.pth b/checkpoint_p1/milestones/checkpoint_001370912_350953472.pth new file mode 100644 index 0000000000000000000000000000000000000000..888fc61650575c3504e69e74f662374a8ae1ef71 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001370912_350953472.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46fc8ae6f6e7050bdb6e566f166cb560fa007364d98886556067214fff800e7a +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001385536_354697216.pth b/checkpoint_p1/milestones/checkpoint_001385536_354697216.pth new file mode 100644 index 0000000000000000000000000000000000000000..9307739523ea4adc8b955f8933f829680f750550 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001385536_354697216.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:827fc07b3f8dc7ba2674191441dea7f61b431413e7f35cc1c63ea8e2f125b47f +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001400064_358416384.pth b/checkpoint_p1/milestones/checkpoint_001400064_358416384.pth new file mode 100644 index 0000000000000000000000000000000000000000..566485d44b2a17890cc33f8496c110da0929b021 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001400064_358416384.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6825b4eb084ad97b76a623a5154be8933fa861b02daaf7fb71de98a14b786dd2 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001414560_362127360.pth b/checkpoint_p1/milestones/checkpoint_001414560_362127360.pth new file mode 100644 index 0000000000000000000000000000000000000000..81d8fbf2dc5ed5cec176c316538ff2e7912e1ae3 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001414560_362127360.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3e4db3fc4e56bdc1477e865ab41d4cb60b50604b073c9b8a852967c17701bb0 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001429056_365838336.pth b/checkpoint_p1/milestones/checkpoint_001429056_365838336.pth new file mode 100644 index 0000000000000000000000000000000000000000..38f030256b72e5d469f7f9cfd05fc3786a362d0b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001429056_365838336.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a958f56e57a78c33dda69ed9ce05054f7d8012b95c9bcad76f939024c7727e2 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001443616_369565696.pth b/checkpoint_p1/milestones/checkpoint_001443616_369565696.pth new file mode 100644 index 0000000000000000000000000000000000000000..c2c47285ba2a8d0e4765b083b6e30336cb3bad82 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001443616_369565696.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58dbdc2a17801a8abc60e4f4f471415b86d9d87461c7fb801c2768830b5b34fa +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001458080_373268480.pth b/checkpoint_p1/milestones/checkpoint_001458080_373268480.pth new file mode 100644 index 0000000000000000000000000000000000000000..8e355faf91c26da67598de16e0ad1bf63eee5f06 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001458080_373268480.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b74ec60392da1ac797be1f18a7bf097b7480bfd8af926eef6f90b85db945ecba +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001472192_376881152.pth b/checkpoint_p1/milestones/checkpoint_001472192_376881152.pth new file mode 100644 index 0000000000000000000000000000000000000000..45b3f89b02ab1aee9e09bc23972e83d75560e3b2 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001472192_376881152.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a27f380fb68bee5238d3ab1625f90e1745c121f424c77a2279a64c5c54165b55 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001486624_380575744.pth b/checkpoint_p1/milestones/checkpoint_001486624_380575744.pth new file mode 100644 index 0000000000000000000000000000000000000000..fe17b1019f7ce6bd737b7969481765304cb1f884 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001486624_380575744.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:675332f7b86d54d240ba52fa96210587f984f22427522501066d09ccc5cc609b +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001501024_384262144.pth b/checkpoint_p1/milestones/checkpoint_001501024_384262144.pth new file mode 100644 index 0000000000000000000000000000000000000000..b9d9f905e8a14e17195bb81f4a1c6d252f32f653 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001501024_384262144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fbdb4a46d077608a1076ed367f1b668b5486a41db46fa30880f0b3e0d19ac01 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001515392_387940352.pth b/checkpoint_p1/milestones/checkpoint_001515392_387940352.pth new file mode 100644 index 0000000000000000000000000000000000000000..424a51ba6baafc724aa61b4e0752a46c67f05e26 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001515392_387940352.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b7ea3ea5783aef99d9510d251c7473a14340451f0b14d4232622e4b03f1a5f5 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001529856_391643136.pth b/checkpoint_p1/milestones/checkpoint_001529856_391643136.pth new file mode 100644 index 0000000000000000000000000000000000000000..d6c82d2911b273fb5e34b15fd30e64572e6caff1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001529856_391643136.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8261510126382835bba5bb0a9d11a220f27237216dd9fd4dafe1107c93db6f24 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001544320_395345920.pth b/checkpoint_p1/milestones/checkpoint_001544320_395345920.pth new file mode 100644 index 0000000000000000000000000000000000000000..ecf039605b81a6ea7e312d88fce31a4f372baa99 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001544320_395345920.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61feaaeaf26ae07cc17d6eb55a4deca50e24d9b295749d5647818ad9d7595da7 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001558720_399032320.pth b/checkpoint_p1/milestones/checkpoint_001558720_399032320.pth new file mode 100644 index 0000000000000000000000000000000000000000..fadfa426eda52915711a9ea7b8bbb275232400ff --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001558720_399032320.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:162a749930649c64abaef786a37856f244242fbd296ff52149e54203ea8f3f10 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001573152_402726912.pth b/checkpoint_p1/milestones/checkpoint_001573152_402726912.pth new file mode 100644 index 0000000000000000000000000000000000000000..208d4c3b6e5087a0e591547fe33c7e04317e1202 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001573152_402726912.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c871d74d479a61e2c2710a4153aae6675342b2a264c4aae6f8f7d55e50c8d37 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001587712_406454272.pth b/checkpoint_p1/milestones/checkpoint_001587712_406454272.pth new file mode 100644 index 0000000000000000000000000000000000000000..260d900e21891b400b5a7d3e35f423921d6c2c60 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001587712_406454272.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ea73e26f0ad67ffca3572ea67dab44fe4e46c63b332088833d4e6e8e539d938 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001602240_410173440.pth b/checkpoint_p1/milestones/checkpoint_001602240_410173440.pth new file mode 100644 index 0000000000000000000000000000000000000000..94b6466bf0b3031e487ba4e786263b83c4e61c60 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001602240_410173440.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cdf83a9609848e9cdc210fa353b0e0af1dce5a24184962dfade162386d3cd57 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001616736_413884416.pth b/checkpoint_p1/milestones/checkpoint_001616736_413884416.pth new file mode 100644 index 0000000000000000000000000000000000000000..149a34c1ed79a008abbb0ff07dc89558c55a6734 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001616736_413884416.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb0e565361c06af4d2c158f6efbaf677d997a20f6a2cebf29bf94acdbb472fef +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001631232_417595392.pth b/checkpoint_p1/milestones/checkpoint_001631232_417595392.pth new file mode 100644 index 0000000000000000000000000000000000000000..96c0e09f9636ce5f0bf25158e353a0680b1f662a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001631232_417595392.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efca4829cadeb0f49578ece348e472e92f11e5d4fc6e6a1703dd322a29b1f1b8 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001645728_421306368.pth b/checkpoint_p1/milestones/checkpoint_001645728_421306368.pth new file mode 100644 index 0000000000000000000000000000000000000000..7c6c8f8e021c115cc05d1c2f659a96efc4e9cc50 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001645728_421306368.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f0d08951680b5270a64233148ad9dae247d2601d7eb3938d9e5787b435f1a38 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001660224_425017344.pth b/checkpoint_p1/milestones/checkpoint_001660224_425017344.pth new file mode 100644 index 0000000000000000000000000000000000000000..e7ad805f0046edf66c47f7bd07cf25571316db93 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001660224_425017344.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9a0ae3958618492da7b33bb59e4fb058819935443659f4f3d31dfe8d7b9c5e0 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001674720_428728320.pth b/checkpoint_p1/milestones/checkpoint_001674720_428728320.pth new file mode 100644 index 0000000000000000000000000000000000000000..15e416708cdc58aee50eb7bc4abb3be36bfd8caa --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001674720_428728320.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bb5e5e8a2772ba2d8edfb29db573acaff6e12dd4682efd2e6bfa7aec041c224 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001689280_432455680.pth b/checkpoint_p1/milestones/checkpoint_001689280_432455680.pth new file mode 100644 index 0000000000000000000000000000000000000000..3d1c8a4ace6b79c8a9b4a8127700fd18cc99f8ea --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001689280_432455680.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e85fde18c1b2f33bc53270f0187dcf191f7259b8c3d2c5f619a47592295078c +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001703776_436166656.pth b/checkpoint_p1/milestones/checkpoint_001703776_436166656.pth new file mode 100644 index 0000000000000000000000000000000000000000..76519923d6cb1f28a495c33386391c25a2af73a5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001703776_436166656.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:016ee73e9dc186a0000008cae8866c07efca9f54ff9d5ff8de3bc7b09e23b027 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001718304_439885824.pth b/checkpoint_p1/milestones/checkpoint_001718304_439885824.pth new file mode 100644 index 0000000000000000000000000000000000000000..b1ab09000e963e59855341f7118a1c86512fea2f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001718304_439885824.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:206d69cda4fa50bc5d4990affbc868401abd5d50e78782d0f6e2d98704150205 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001732800_443596800.pth b/checkpoint_p1/milestones/checkpoint_001732800_443596800.pth new file mode 100644 index 0000000000000000000000000000000000000000..8f60ee6d4879765f4de0ca9a0fce0b1bcdb1cd9a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001732800_443596800.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2312ca36b6577de65e7aedfc67de0208e004b91a1866019ff20fdd580ca51220 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001747328_447315968.pth b/checkpoint_p1/milestones/checkpoint_001747328_447315968.pth new file mode 100644 index 0000000000000000000000000000000000000000..27dc9cd78c18e707eb8a989446bc96e0f93d1aaa --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001747328_447315968.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d3184fd29d208ca56c8e72349dc056fc40b4ca38f393da3a258e245a3217ff1 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001761888_451043328.pth b/checkpoint_p1/milestones/checkpoint_001761888_451043328.pth new file mode 100644 index 0000000000000000000000000000000000000000..d2ea337fc2de864c47381a1de5bc631f1258d739 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001761888_451043328.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f503f556b545f9f738df9e62a3b35a68cc14434ba9c2fd99f75135eb1eb688f2 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001776448_454770688.pth b/checkpoint_p1/milestones/checkpoint_001776448_454770688.pth new file mode 100644 index 0000000000000000000000000000000000000000..5c2196b5792be881b68da93577de1fd94feb78ae --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001776448_454770688.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:367f490d25eb69c923268d9fcd40aaa4a4a4e89f26a7694d676b5c2a2e958b86 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001790976_458489856.pth b/checkpoint_p1/milestones/checkpoint_001790976_458489856.pth new file mode 100644 index 0000000000000000000000000000000000000000..5607db1c81d644ca875d001d42886af72f550921 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001790976_458489856.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb0f13470ff2e120ad6e1a1fb6fc4cc24f4941eb24fe0d441f1f1a3f6701bb76 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001805568_462225408.pth b/checkpoint_p1/milestones/checkpoint_001805568_462225408.pth new file mode 100644 index 0000000000000000000000000000000000000000..b15d06af45b1fa85f03f04ec8c61878e8775b829 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001805568_462225408.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34b4050f2c9802b30f7f64b02dec7de0f3c149847750c4e360d00172c1cfcec7 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001820064_465936384.pth b/checkpoint_p1/milestones/checkpoint_001820064_465936384.pth new file mode 100644 index 0000000000000000000000000000000000000000..2907e1d30e549274b9fd94c1b159e439d1535b83 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001820064_465936384.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:216e93dc983238eb899f04d19977bdc2c6d5b417db278483333fe2727983eb00 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001834560_469647360.pth b/checkpoint_p1/milestones/checkpoint_001834560_469647360.pth new file mode 100644 index 0000000000000000000000000000000000000000..99d226eb65b07504583df0d9a77b744b3f7f297a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001834560_469647360.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:533d82bfd5c3035120e4539eccd80a20aaab1176de61700badcb920ed3d87499 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001849120_473374720.pth b/checkpoint_p1/milestones/checkpoint_001849120_473374720.pth new file mode 100644 index 0000000000000000000000000000000000000000..bd415acdba3a3d1ff6c6bc47c0e0d329d7329883 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001849120_473374720.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:611db5b6aa9270b0573611876c649dca092732f2e1e48d9e20533b3d753b6b66 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001863648_477093888.pth b/checkpoint_p1/milestones/checkpoint_001863648_477093888.pth new file mode 100644 index 0000000000000000000000000000000000000000..fc3360e83818721f71d11f158c37bc1e269f4f32 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001863648_477093888.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:780b42a88250ff926d7881d230f29d62d8f083cb93ee03afad7709e6823c816d +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001878176_480813056.pth b/checkpoint_p1/milestones/checkpoint_001878176_480813056.pth new file mode 100644 index 0000000000000000000000000000000000000000..24b02c0d4061993f7d4af714618b35a8068658d1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001878176_480813056.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:032d84175f5fc638a6ef83a3994e1e5386472c047f52c8ad2303342ce0c94525 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001892736_484540416.pth b/checkpoint_p1/milestones/checkpoint_001892736_484540416.pth new file mode 100644 index 0000000000000000000000000000000000000000..9cccbd2613d7c84882042e90d0ef335f54247b6a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001892736_484540416.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fb21a02887cd0444ad13f3a1dd5a15091c982f2036137055ca357f84557b032 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001907264_488259584.pth b/checkpoint_p1/milestones/checkpoint_001907264_488259584.pth new file mode 100644 index 0000000000000000000000000000000000000000..e0b63ec240cd8e44c673f3f25acfc1775b46a80d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001907264_488259584.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21ff17a51a112302aed420d62e97d26f97863573f939e9d4332858083fdabce6 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001921568_491921408.pth b/checkpoint_p1/milestones/checkpoint_001921568_491921408.pth new file mode 100644 index 0000000000000000000000000000000000000000..452a9f5e8571e56564718741a25536e760ab85b2 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001921568_491921408.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd75810b6ba52244c39bff70483904d7a1a25ecf04b650cbafd7825b1059b754 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001936128_495648768.pth b/checkpoint_p1/milestones/checkpoint_001936128_495648768.pth new file mode 100644 index 0000000000000000000000000000000000000000..8f56d4fa769069173570f4e4cb7f52b833853cf2 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001936128_495648768.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:874c647ece18a824c3ad40948747f2ae89cb32df1dca2385befa06b48cb20eff +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001950656_499367936.pth b/checkpoint_p1/milestones/checkpoint_001950656_499367936.pth new file mode 100644 index 0000000000000000000000000000000000000000..054932184424e5b2918ca2d1de737034667b14e2 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001950656_499367936.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdf9be14b2907e7bd2a1cf892494bcc893fb269163271aeb8bd690bd0cc8d49c +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001965152_503078912.pth b/checkpoint_p1/milestones/checkpoint_001965152_503078912.pth new file mode 100644 index 0000000000000000000000000000000000000000..e398753a6bdb40c979d82f8a4637cb27af4edf28 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001965152_503078912.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f2547dee265e94809a21f32cef5b7d6ed016e81eb0ff3c9bb8c9417cd130106 +size 20797195 diff --git a/config.json b/config.json index 74ccfb7d7c73734729e7fed9df0a6b5ad8528e9d..f38d3eb8f45a2e1256360127d5b7489d368347b4 100644 --- a/config.json +++ b/config.json @@ -4,7 +4,7 @@ "env": "atari_defender", "experiment": "atari_defender_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_defender --experiment=atari_defender_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_defender --wandb_job_type=SF --wandb_tags=atari", + "command_line": "--algo=APPO --env=atari_defender --experiment=atari_defender_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_defender --wandb_job_type=SF --wandb_tags=atari", "cli_args": { "algo": "APPO", "env": "atari_defender", "experiment": "atari_defender_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_defender_APPO_20231010_124028_375230" + "wandb_unique_id": "atari_defender_APPO_20231030_080919_282132" } \ 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 c9742deb8245b3076b4928420e357cff11570262..9b5a825a31f033faf7f897241e47494065653ce0 100644 --- a/replay.mp4 +++ b/replay.mp4 @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:6a41cce53440aafd1a1dba87af7ed9c53e5b7e688d1deaa3cf3f8378c70d912f -size 10526907 +oid sha256:2118031a8b6e5b506be71a67e3dc42f91373404e8a3613af00e5945572c2d18d +size 45575597 diff --git a/sf_log.txt b/sf_log.txt index 3cd6d6e41af6b784e76d1ad5711043f1858765ea..29d052b1b31bdd73d22aafc13c8d93f97e83864c 100644 --- a/sf_log.txt +++ b/sf_log.txt @@ -1,26090 +1,3 @@ -[2023-10-10 12:40:34,991][75634] Saving configuration to ./train_atari/atari_defender_APPO/config.json... -[2023-10-10 12:40:35,308][75634] Rollout worker 0 uses device cpu -[2023-10-10 12:40:35,309][75634] Rollout worker 1 uses device cpu -[2023-10-10 12:40:35,309][75634] Rollout worker 2 uses device cpu -[2023-10-10 12:40:35,310][75634] Rollout worker 3 uses device cpu -[2023-10-10 12:40:35,310][75634] Rollout worker 4 uses device cpu -[2023-10-10 12:40:35,311][75634] Rollout worker 5 uses device cpu -[2023-10-10 12:40:35,311][75634] Rollout worker 6 uses device cpu -[2023-10-10 12:40:35,312][75634] Rollout worker 7 uses device cpu -[2023-10-10 12:40:35,312][75634] Rollout worker 8 uses device cpu -[2023-10-10 12:40:35,312][75634] Rollout worker 9 uses device cpu -[2023-10-10 12:40:35,313][75634] Rollout worker 10 uses device cpu -[2023-10-10 12:40:35,313][75634] Rollout worker 11 uses device cpu -[2023-10-10 12:40:35,314][75634] Rollout worker 12 uses device cpu -[2023-10-10 12:40:35,314][75634] Rollout worker 13 uses device cpu -[2023-10-10 12:40:35,314][75634] Rollout worker 14 uses device cpu -[2023-10-10 12:40:35,315][75634] Rollout worker 15 uses device cpu -[2023-10-10 12:40:35,607][75634] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-10 12:40:35,607][75634] InferenceWorker_p0-w0: min num requests: 2 -[2023-10-10 12:40:35,610][75634] Using GPUs [1] for process 1 (actually maps to GPUs [1]) -[2023-10-10 12:40:35,610][75634] InferenceWorker_p1-w0: min num requests: 2 -[2023-10-10 12:40:35,655][75634] Starting all processes... -[2023-10-10 12:40:35,656][75634] Starting process learner_proc0 -[2023-10-10 12:40:37,328][75634] Starting process learner_proc1 -[2023-10-10 12:40:37,333][76362] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-10 12:40:37,333][76362] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 -[2023-10-10 12:40:37,351][76362] Num visible devices: 1 -[2023-10-10 12:40:37,370][76362] Setting fixed seed 1234 -[2023-10-10 12:40:37,371][76362] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-10 12:40:37,371][76362] Initializing actor-critic model on device cuda:0 -[2023-10-10 12:40:37,372][76362] RunningMeanStd input shape: (4, 84, 84) -[2023-10-10 12:40:37,372][76362] RunningMeanStd input shape: (1,) -[2023-10-10 12:40:37,383][76362] ConvEncoder: input_channels=4 -[2023-10-10 12:40:37,563][76362] Conv encoder output size: 512 -[2023-10-10 12:40:37,565][76362] Created Actor Critic model with architecture: -[2023-10-10 12:40:37,565][76362] 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 12:40:38,156][76362] Using optimizer -[2023-10-10 12:40:38,157][76362] No checkpoints found -[2023-10-10 12:40:38,157][76362] Did not load from checkpoint, starting from scratch! -[2023-10-10 12:40:38,157][76362] Initialized policy 0 weights for model version 0 -[2023-10-10 12:40:38,159][76362] LearnerWorker_p0 finished initialization! -[2023-10-10 12:40:38,159][76362] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-10 12:40:39,071][75634] Starting all processes... -[2023-10-10 12:40:39,076][76421] Using GPUs [1] for process 1 (actually maps to GPUs [1]) -[2023-10-10 12:40:39,076][76421] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [1]) for learning process 1 -[2023-10-10 12:40:39,078][75634] Starting process inference_proc0-0 -[2023-10-10 12:40:39,078][75634] Starting process inference_proc1-0 -[2023-10-10 12:40:39,078][75634] Starting process rollout_proc0 -[2023-10-10 12:40:39,079][75634] Starting process rollout_proc1 -[2023-10-10 12:40:39,079][75634] Starting process rollout_proc2 -[2023-10-10 12:40:39,096][76421] Num visible devices: 1 -[2023-10-10 12:40:39,079][75634] Starting process rollout_proc3 -[2023-10-10 12:40:39,111][76421] Setting fixed seed 1234 -[2023-10-10 12:40:39,112][76421] Using GPUs [0] for process 1 (actually maps to GPUs [1]) -[2023-10-10 12:40:39,112][76421] Initializing actor-critic model on device cuda:0 -[2023-10-10 12:40:39,085][75634] Starting process rollout_proc4 -[2023-10-10 12:40:39,113][76421] RunningMeanStd input shape: (4, 84, 84) -[2023-10-10 12:40:39,114][76421] RunningMeanStd input shape: (1,) -[2023-10-10 12:40:39,088][75634] Starting process rollout_proc5 -[2023-10-10 12:40:39,089][75634] Starting process rollout_proc6 -[2023-10-10 12:40:39,090][75634] Starting process rollout_proc7 -[2023-10-10 12:40:39,090][75634] Starting process rollout_proc8 -[2023-10-10 12:40:39,094][75634] Starting process rollout_proc9 -[2023-10-10 12:40:39,126][76421] ConvEncoder: input_channels=4 -[2023-10-10 12:40:39,094][75634] Starting process rollout_proc10 -[2023-10-10 12:40:39,094][75634] Starting process rollout_proc11 -[2023-10-10 12:40:39,098][75634] Starting process rollout_proc12 -[2023-10-10 12:40:39,098][75634] Starting process rollout_proc13 -[2023-10-10 12:40:39,610][76421] Conv encoder output size: 512 -[2023-10-10 12:40:39,613][76421] Created Actor Critic model with architecture: -[2023-10-10 12:40:39,613][76421] 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 12:40:40,422][76421] Using optimizer -[2023-10-10 12:40:40,423][76421] No checkpoints found -[2023-10-10 12:40:40,423][76421] Did not load from checkpoint, starting from scratch! -[2023-10-10 12:40:40,423][76421] Initialized policy 1 weights for model version 0 -[2023-10-10 12:40:40,425][76421] LearnerWorker_p1 finished initialization! -[2023-10-10 12:40:40,425][76421] Using GPUs [0] for process 1 (actually maps to GPUs [1]) -[2023-10-10 12:40:41,276][75634] Starting process rollout_proc14 -[2023-10-10 12:40:41,281][76543] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-10 12:40:41,282][76543] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 -[2023-10-10 12:40:41,300][76543] Num visible devices: 1 -[2023-10-10 12:40:41,384][75634] Starting process rollout_proc15 -[2023-10-10 12:40:41,393][76592] Worker 12 uses CPU cores [24, 25] -[2023-10-10 12:40:41,482][76584] Worker 6 uses CPU cores [12, 13] -[2023-10-10 12:40:41,569][76582] Worker 4 uses CPU cores [8, 9] -[2023-10-10 12:40:41,586][76581] Worker 2 uses CPU cores [4, 5] -[2023-10-10 12:40:41,600][76579] Worker 1 uses CPU cores [2, 3] -[2023-10-10 12:40:41,650][76588] Worker 9 uses CPU cores [18, 19] -[2023-10-10 12:40:41,706][76586] Worker 8 uses CPU cores [16, 17] -[2023-10-10 12:40:41,745][76587] Worker 10 uses CPU cores [20, 21] -[2023-10-10 12:40:41,806][76580] Worker 3 uses CPU cores [6, 7] -[2023-10-10 12:40:41,846][76590] Worker 13 uses CPU cores [26, 27] -[2023-10-10 12:40:41,898][76583] Worker 5 uses CPU cores [10, 11] -[2023-10-10 12:40:41,902][76542] Using GPUs [1] for process 1 (actually maps to GPUs [1]) -[2023-10-10 12:40:41,903][76542] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [1]) for inference process 1 -[2023-10-10 12:40:41,916][76585] Worker 7 uses CPU cores [14, 15] -[2023-10-10 12:40:41,922][76542] Num visible devices: 1 -[2023-10-10 12:40:41,934][76589] Worker 11 uses CPU cores [22, 23] -[2023-10-10 12:40:41,968][76577] Worker 0 uses CPU cores [0, 1] -[2023-10-10 12:40:42,053][76543] RunningMeanStd input shape: (4, 84, 84) -[2023-10-10 12:40:42,054][76543] RunningMeanStd input shape: (1,) -[2023-10-10 12:40:42,065][76543] ConvEncoder: input_channels=4 -[2023-10-10 12:40:42,167][76543] Conv encoder output size: 512 -[2023-10-10 12:40:42,520][76542] RunningMeanStd input shape: (4, 84, 84) -[2023-10-10 12:40:42,520][76542] RunningMeanStd input shape: (1,) -[2023-10-10 12:40:42,531][76542] ConvEncoder: input_channels=4 -[2023-10-10 12:40:42,631][76542] Conv encoder output size: 512 -[2023-10-10 12:40:43,305][77297] Worker 14 uses CPU cores [28, 29] -[2023-10-10 12:40:43,395][75634] Inference worker 0-0 is ready! -[2023-10-10 12:40:43,396][75634] Inference worker 1-0 is ready! -[2023-10-10 12:40:43,396][75634] All inference workers are ready! Signal rollout workers to start! -[2023-10-10 12:40:43,397][76584] EnvRunner 6-0 uses policy 0 -[2023-10-10 12:40:43,397][75634] 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 12:40:43,397][76580] EnvRunner 3-0 uses policy 1 -[2023-10-10 12:40:43,398][76589] EnvRunner 11-0 uses policy 1 -[2023-10-10 12:40:43,397][76590] EnvRunner 13-0 uses policy 1 -[2023-10-10 12:40:43,397][76583] EnvRunner 5-0 uses policy 1 -[2023-10-10 12:40:43,397][76582] EnvRunner 4-0 uses policy 0 -[2023-10-10 12:40:43,398][76585] EnvRunner 7-0 uses policy 1 -[2023-10-10 12:40:43,398][76587] EnvRunner 10-0 uses policy 0 -[2023-10-10 12:40:43,398][76581] EnvRunner 2-0 uses policy 0 -[2023-10-10 12:40:43,398][76579] EnvRunner 1-0 uses policy 1 -[2023-10-10 12:40:43,398][76586] EnvRunner 8-0 uses policy 0 -[2023-10-10 12:40:43,398][76577] EnvRunner 0-0 uses policy 0 -[2023-10-10 12:40:43,398][76592] EnvRunner 12-0 uses policy 0 -[2023-10-10 12:40:43,398][76588] EnvRunner 9-0 uses policy 1 -[2023-10-10 12:40:43,398][77362] Worker 15 uses CPU cores [30, 31] -[2023-10-10 12:40:43,491][77297] EnvRunner 14-0 uses policy 0 -[2023-10-10 12:40:43,583][77362] EnvRunner 15-0 uses policy 1 -[2023-10-10 12:40:45,595][75634] Heartbeat connected on Batcher_0 -[2023-10-10 12:40:45,597][75634] Heartbeat connected on LearnerWorker_p0 -[2023-10-10 12:40:45,600][75634] Heartbeat connected on Batcher_1 -[2023-10-10 12:40:45,603][75634] Heartbeat connected on LearnerWorker_p1 -[2023-10-10 12:40:45,610][75634] Heartbeat connected on InferenceWorker_p0-w0 -[2023-10-10 12:40:45,612][75634] Heartbeat connected on InferenceWorker_p1-w0 -[2023-10-10 12:40:45,616][75634] Heartbeat connected on RolloutWorker_w1 -[2023-10-10 12:40:45,617][75634] Heartbeat connected on RolloutWorker_w0 -[2023-10-10 12:40:45,622][75634] Heartbeat connected on RolloutWorker_w2 -[2023-10-10 12:40:45,623][75634] Heartbeat connected on RolloutWorker_w3 -[2023-10-10 12:40:45,624][75634] Heartbeat connected on RolloutWorker_w4 -[2023-10-10 12:40:45,628][75634] Heartbeat connected on RolloutWorker_w5 -[2023-10-10 12:40:45,631][75634] Heartbeat connected on RolloutWorker_w6 -[2023-10-10 12:40:45,636][75634] Heartbeat connected on RolloutWorker_w8 -[2023-10-10 12:40:45,637][75634] Heartbeat connected on RolloutWorker_w7 -[2023-10-10 12:40:45,638][75634] Heartbeat connected on RolloutWorker_w9 -[2023-10-10 12:40:45,643][75634] Heartbeat connected on RolloutWorker_w11 -[2023-10-10 12:40:45,644][75634] Heartbeat connected on RolloutWorker_w10 -[2023-10-10 12:40:45,646][75634] Heartbeat connected on RolloutWorker_w12 -[2023-10-10 12:40:45,652][75634] Heartbeat connected on RolloutWorker_w14 -[2023-10-10 12:40:45,653][75634] Heartbeat connected on RolloutWorker_w13 -[2023-10-10 12:40:45,658][75634] Heartbeat connected on RolloutWorker_w15 -[2023-10-10 12:40:46,076][75634] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 207.6, 1: 640.7. Samples: 2272. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-10-10 12:40:46,076][75634] Avg episode reward: [(0, '3.000')] -[2023-10-10 12:40:51,076][75634] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 896.5, 1: 1043.2. Samples: 14894. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-10-10 12:40:51,077][75634] Avg episode reward: [(0, '4.000'), (1, '3.000')] -[2023-10-10 12:40:52,837][76542] Updated weights for policy 1, policy_version 10 (0.0008) -[2023-10-10 12:40:52,922][76543] Updated weights for policy 0, policy_version 10 (0.0008) -[2023-10-10 12:40:53,217][76542] Updated weights for policy 1, policy_version 20 (0.0009) -[2023-10-10 12:40:53,290][76543] Updated weights for policy 0, policy_version 20 (0.0008) -[2023-10-10 12:40:53,570][76542] Updated weights for policy 1, policy_version 30 (0.0007) -[2023-10-10 12:40:53,657][76543] Updated weights for policy 0, policy_version 30 (0.0008) -[2023-10-10 12:40:55,900][76542] Updated weights for policy 1, policy_version 40 (0.0008) -[2023-10-10 12:40:56,025][76543] Updated weights for policy 0, policy_version 40 (0.0008) -[2023-10-10 12:40:56,076][75634] Fps is (10 sec: 6553.6, 60 sec: 5169.1, 300 sec: 5169.1). Total num frames: 65536. Throughput: 0: 1238.3, 1: 1323.7. Samples: 32482. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-10 12:40:56,076][75634] Avg episode reward: [(0, '5.667'), (1, '4.886')] -[2023-10-10 12:40:56,262][76542] Updated weights for policy 1, policy_version 50 (0.0008) -[2023-10-10 12:40:56,399][76543] Updated weights for policy 0, policy_version 50 (0.0009) -[2023-10-10 12:40:56,632][76542] Updated weights for policy 1, policy_version 60 (0.0008) -[2023-10-10 12:40:56,782][76543] Updated weights for policy 0, policy_version 60 (0.0009) -[2023-10-10 12:40:59,889][76542] Updated weights for policy 1, policy_version 70 (0.0010) -[2023-10-10 12:41:00,078][76543] Updated weights for policy 0, policy_version 70 (0.0008) -[2023-10-10 12:41:00,247][76542] Updated weights for policy 1, policy_version 80 (0.0008) -[2023-10-10 12:41:00,443][76543] Updated weights for policy 0, policy_version 80 (0.0008) -[2023-10-10 12:41:00,620][76542] Updated weights for policy 1, policy_version 90 (0.0008) -[2023-10-10 12:41:00,812][76543] Updated weights for policy 0, policy_version 90 (0.0008) -[2023-10-10 12:41:01,076][75634] Fps is (10 sec: 19661.1, 60 sec: 11121.3, 300 sec: 11121.3). Total num frames: 196608. Throughput: 0: 1499.0, 1: 1507.3. Samples: 53146. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:41:01,076][75634] Avg episode reward: [(0, '5.209'), (1, '4.304')] -[2023-10-10 12:41:04,089][76543] Updated weights for policy 0, policy_version 100 (0.0009) -[2023-10-10 12:41:04,177][76542] Updated weights for policy 1, policy_version 100 (0.0009) -[2023-10-10 12:41:04,448][76543] Updated weights for policy 0, policy_version 110 (0.0007) -[2023-10-10 12:41:04,538][76542] Updated weights for policy 1, policy_version 110 (0.0010) -[2023-10-10 12:41:04,823][76543] Updated weights for policy 0, policy_version 120 (0.0008) -[2023-10-10 12:41:04,904][76542] Updated weights for policy 1, policy_version 120 (0.0008) -[2023-10-10 12:41:06,076][75634] Fps is (10 sec: 19660.2, 60 sec: 11559.1, 300 sec: 11559.1). Total num frames: 262144. Throughput: 0: 1395.3, 1: 1448.9. Samples: 64504. Policy #0 lag: (min: 22.0, avg: 24.7, max: 54.0) -[2023-10-10 12:41:06,077][75634] Avg episode reward: [(0, '4.852'), (1, '4.877')] -[2023-10-10 12:41:06,078][76362] Saving new best policy, reward=4.852! -[2023-10-10 12:41:06,078][76421] Saving new best policy, reward=4.877! -[2023-10-10 12:41:08,555][76543] Updated weights for policy 0, policy_version 130 (0.0008) -[2023-10-10 12:41:08,655][76542] Updated weights for policy 1, policy_version 130 (0.0009) -[2023-10-10 12:41:08,914][76543] Updated weights for policy 0, policy_version 140 (0.0007) -[2023-10-10 12:41:09,019][76542] Updated weights for policy 1, policy_version 140 (0.0007) -[2023-10-10 12:41:09,287][76543] Updated weights for policy 0, policy_version 150 (0.0008) -[2023-10-10 12:41:09,385][76542] Updated weights for policy 1, policy_version 150 (0.0009) -[2023-10-10 12:41:09,650][76543] Updated weights for policy 0, policy_version 160 (0.0009) -[2023-10-10 12:41:09,751][76542] Updated weights for policy 1, policy_version 160 (0.0007) -[2023-10-10 12:41:11,076][75634] Fps is (10 sec: 13107.0, 60 sec: 11838.8, 300 sec: 11838.8). Total num frames: 327680. Throughput: 0: 1525.4, 1: 1549.3. Samples: 85102. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-10 12:41:11,077][75634] Avg episode reward: [(0, '4.649'), (1, '4.942')] -[2023-10-10 12:41:11,079][76421] Saving new best policy, reward=4.942! -[2023-10-10 12:41:13,380][76543] Updated weights for policy 0, policy_version 170 (0.0007) -[2023-10-10 12:41:13,462][76542] Updated weights for policy 1, policy_version 170 (0.0007) -[2023-10-10 12:41:13,756][76543] Updated weights for policy 0, policy_version 180 (0.0007) -[2023-10-10 12:41:13,820][76542] Updated weights for policy 1, policy_version 180 (0.0008) -[2023-10-10 12:41:14,125][76543] Updated weights for policy 0, policy_version 190 (0.0008) -[2023-10-10 12:41:14,190][76542] Updated weights for policy 1, policy_version 190 (0.0008) -[2023-10-10 12:41:16,076][75634] Fps is (10 sec: 13107.5, 60 sec: 12032.9, 300 sec: 12032.9). Total num frames: 393216. Throughput: 0: 1629.2, 1: 1659.3. Samples: 107462. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:41:16,076][75634] Avg episode reward: [(0, '4.747'), (1, '4.851')] -[2023-10-10 12:41:17,912][76542] Updated weights for policy 1, policy_version 200 (0.0009) -[2023-10-10 12:41:17,964][76543] Updated weights for policy 0, policy_version 200 (0.0009) -[2023-10-10 12:41:18,274][76542] Updated weights for policy 1, policy_version 210 (0.0008) -[2023-10-10 12:41:18,321][76543] Updated weights for policy 0, policy_version 210 (0.0008) -[2023-10-10 12:41:18,643][76542] Updated weights for policy 1, policy_version 220 (0.0007) -[2023-10-10 12:41:18,690][76543] Updated weights for policy 0, policy_version 220 (0.0009) -[2023-10-10 12:41:21,076][75634] Fps is (10 sec: 13107.5, 60 sec: 12175.5, 300 sec: 12175.5). Total num frames: 458752. Throughput: 0: 1563.6, 1: 1576.0. Samples: 118294. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:41:21,076][75634] Avg episode reward: [(0, '5.090'), (1, '5.010')] -[2023-10-10 12:41:21,077][76421] Saving new best policy, reward=5.010! -[2023-10-10 12:41:21,077][76362] Saving new best policy, reward=5.090! -[2023-10-10 12:41:22,340][76542] Updated weights for policy 1, policy_version 230 (0.0009) -[2023-10-10 12:41:22,404][76543] Updated weights for policy 0, policy_version 230 (0.0009) -[2023-10-10 12:41:22,697][76542] Updated weights for policy 1, policy_version 240 (0.0009) -[2023-10-10 12:41:22,765][76543] Updated weights for policy 0, policy_version 240 (0.0008) -[2023-10-10 12:41:23,058][76542] Updated weights for policy 1, policy_version 250 (0.0008) -[2023-10-10 12:41:23,135][76543] Updated weights for policy 0, policy_version 250 (0.0007) -[2023-10-10 12:41:26,076][75634] Fps is (10 sec: 13107.3, 60 sec: 12284.6, 300 sec: 12284.6). Total num frames: 524288. Throughput: 0: 1628.6, 1: 1652.9. Samples: 140048. Policy #0 lag: (min: 4.0, avg: 6.2, max: 36.0) -[2023-10-10 12:41:26,076][75634] Avg episode reward: [(0, '5.150'), (1, '5.080')] -[2023-10-10 12:41:26,077][76421] Saving new best policy, reward=5.080! -[2023-10-10 12:41:26,077][76362] Saving new best policy, reward=5.150! -[2023-10-10 12:41:26,795][76542] Updated weights for policy 1, policy_version 260 (0.0008) -[2023-10-10 12:41:26,930][76543] Updated weights for policy 0, policy_version 260 (0.0008) -[2023-10-10 12:41:27,161][76542] Updated weights for policy 1, policy_version 270 (0.0007) -[2023-10-10 12:41:27,296][76543] Updated weights for policy 0, policy_version 270 (0.0009) -[2023-10-10 12:41:27,528][76542] Updated weights for policy 1, policy_version 280 (0.0009) -[2023-10-10 12:41:27,664][76543] Updated weights for policy 0, policy_version 280 (0.0007) -[2023-10-10 12:41:31,076][75634] Fps is (10 sec: 13107.2, 60 sec: 12370.9, 300 sec: 12370.9). Total num frames: 589824. Throughput: 0: 1779.8, 1: 1781.4. Samples: 162526. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 12:41:31,076][75634] Avg episode reward: [(0, '4.890'), (1, '4.890')] -[2023-10-10 12:41:31,338][76542] Updated weights for policy 1, policy_version 290 (0.0008) -[2023-10-10 12:41:31,398][76543] Updated weights for policy 0, policy_version 290 (0.0009) -[2023-10-10 12:41:31,705][76542] Updated weights for policy 1, policy_version 300 (0.0007) -[2023-10-10 12:41:31,774][76543] Updated weights for policy 0, policy_version 300 (0.0009) -[2023-10-10 12:41:32,060][76542] Updated weights for policy 1, policy_version 310 (0.0007) -[2023-10-10 12:41:32,141][76543] Updated weights for policy 0, policy_version 310 (0.0009) -[2023-10-10 12:41:32,428][76542] Updated weights for policy 1, policy_version 320 (0.0008) -[2023-10-10 12:41:32,515][76543] Updated weights for policy 0, policy_version 320 (0.0007) -[2023-10-10 12:41:36,076][75634] Fps is (10 sec: 13107.1, 60 sec: 12440.8, 300 sec: 12440.8). Total num frames: 655360. Throughput: 0: 1749.4, 1: 1754.5. Samples: 172570. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:41:36,076][75634] Avg episode reward: [(0, '5.300'), (1, '5.270')] -[2023-10-10 12:41:36,212][76542] Updated weights for policy 1, policy_version 330 (0.0010) -[2023-10-10 12:41:36,385][76543] Updated weights for policy 0, policy_version 330 (0.0008) -[2023-10-10 12:41:36,565][76542] Updated weights for policy 1, policy_version 340 (0.0009) -[2023-10-10 12:41:36,747][76543] Updated weights for policy 0, policy_version 340 (0.0007) -[2023-10-10 12:41:36,941][76542] Updated weights for policy 1, policy_version 350 (0.0007) -[2023-10-10 12:41:37,007][76421] Saving new best policy, reward=5.270! -[2023-10-10 12:41:37,113][76543] Updated weights for policy 0, policy_version 350 (0.0008) -[2023-10-10 12:41:37,186][76362] Saving new best policy, reward=5.300! -[2023-10-10 12:41:40,540][76542] Updated weights for policy 1, policy_version 360 (0.0007) -[2023-10-10 12:41:40,827][76543] Updated weights for policy 0, policy_version 360 (0.0008) -[2023-10-10 12:41:40,904][76542] Updated weights for policy 1, policy_version 370 (0.0008) -[2023-10-10 12:41:41,076][75634] Fps is (10 sec: 13107.2, 60 sec: 12498.6, 300 sec: 12498.6). Total num frames: 720896. Throughput: 0: 1804.5, 1: 1808.4. Samples: 195064. Policy #0 lag: (min: 26.0, avg: 26.1, max: 33.0) -[2023-10-10 12:41:41,076][75634] Avg episode reward: [(0, '5.550'), (1, '5.190')] -[2023-10-10 12:41:41,199][76543] Updated weights for policy 0, policy_version 370 (0.0008) -[2023-10-10 12:41:41,270][76542] Updated weights for policy 1, policy_version 380 (0.0008) -[2023-10-10 12:41:41,559][76543] Updated weights for policy 0, policy_version 380 (0.0008) -[2023-10-10 12:41:41,704][76362] Saving new best policy, reward=5.550! -[2023-10-10 12:41:44,959][76542] Updated weights for policy 1, policy_version 390 (0.0009) -[2023-10-10 12:41:45,156][76543] Updated weights for policy 0, policy_version 390 (0.0008) -[2023-10-10 12:41:45,324][76542] Updated weights for policy 1, policy_version 400 (0.0009) -[2023-10-10 12:41:45,518][76543] Updated weights for policy 0, policy_version 400 (0.0008) -[2023-10-10 12:41:45,691][76542] Updated weights for policy 1, policy_version 410 (0.0008) -[2023-10-10 12:41:45,891][76543] Updated weights for policy 0, policy_version 410 (0.0008) -[2023-10-10 12:41:46,076][75634] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13069.9). Total num frames: 819200. Throughput: 0: 1813.0, 1: 1814.7. Samples: 216390. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:41:46,076][75634] Avg episode reward: [(0, '5.310'), (1, '5.930')] -[2023-10-10 12:41:46,082][76421] Saving new best policy, reward=5.930! -[2023-10-10 12:41:49,338][76542] Updated weights for policy 1, policy_version 420 (0.0008) -[2023-10-10 12:41:49,541][76543] Updated weights for policy 0, policy_version 420 (0.0009) -[2023-10-10 12:41:49,704][76542] Updated weights for policy 1, policy_version 430 (0.0008) -[2023-10-10 12:41:49,906][76543] Updated weights for policy 0, policy_version 430 (0.0010) -[2023-10-10 12:41:50,073][76542] Updated weights for policy 1, policy_version 440 (0.0007) -[2023-10-10 12:41:50,278][76543] Updated weights for policy 0, policy_version 440 (0.0009) -[2023-10-10 12:41:51,076][75634] Fps is (10 sec: 19660.8, 60 sec: 15291.8, 300 sec: 13556.8). Total num frames: 917504. Throughput: 0: 1818.1, 1: 1813.3. Samples: 227914. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:41:51,076][75634] Avg episode reward: [(0, '5.010'), (1, '6.340')] -[2023-10-10 12:41:51,077][76421] Saving new best policy, reward=6.340! -[2023-10-10 12:41:53,881][76542] Updated weights for policy 1, policy_version 450 (0.0007) -[2023-10-10 12:41:53,954][76543] Updated weights for policy 0, policy_version 450 (0.0007) -[2023-10-10 12:41:54,249][76542] Updated weights for policy 1, policy_version 460 (0.0010) -[2023-10-10 12:41:54,321][76543] Updated weights for policy 0, policy_version 460 (0.0007) -[2023-10-10 12:41:54,615][76542] Updated weights for policy 1, policy_version 470 (0.0009) -[2023-10-10 12:41:54,684][76543] Updated weights for policy 0, policy_version 470 (0.0009) -[2023-10-10 12:41:54,979][76542] Updated weights for policy 1, policy_version 480 (0.0007) -[2023-10-10 12:41:55,051][76543] Updated weights for policy 0, policy_version 480 (0.0009) -[2023-10-10 12:41:56,076][75634] Fps is (10 sec: 16383.7, 60 sec: 15291.7, 300 sec: 13525.9). Total num frames: 983040. Throughput: 0: 1825.3, 1: 1815.5. Samples: 248940. Policy #0 lag: (min: 1.0, avg: 4.8, max: 33.0) -[2023-10-10 12:41:56,077][75634] Avg episode reward: [(0, '5.180'), (1, '6.560')] -[2023-10-10 12:41:56,079][76421] Saving new best policy, reward=6.560! -[2023-10-10 12:41:58,707][76543] Updated weights for policy 0, policy_version 490 (0.0009) -[2023-10-10 12:41:58,897][76542] Updated weights for policy 1, policy_version 490 (0.0007) -[2023-10-10 12:41:59,073][76543] Updated weights for policy 0, policy_version 500 (0.0007) -[2023-10-10 12:41:59,261][76542] Updated weights for policy 1, policy_version 500 (0.0007) -[2023-10-10 12:41:59,446][76543] Updated weights for policy 0, policy_version 510 (0.0008) -[2023-10-10 12:41:59,619][76542] Updated weights for policy 1, policy_version 510 (0.0009) -[2023-10-10 12:42:01,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13498.9). Total num frames: 1048576. Throughput: 0: 1805.8, 1: 1805.2. Samples: 269956. Policy #0 lag: (min: 26.0, avg: 31.8, max: 58.0) -[2023-10-10 12:42:01,077][75634] Avg episode reward: [(0, '5.160'), (1, '6.600')] -[2023-10-10 12:42:01,083][76421] Saving new best policy, reward=6.600! -[2023-10-10 12:42:03,205][76542] Updated weights for policy 1, policy_version 520 (0.0008) -[2023-10-10 12:42:03,272][76543] Updated weights for policy 0, policy_version 520 (0.0008) -[2023-10-10 12:42:03,586][76542] Updated weights for policy 1, policy_version 530 (0.0008) -[2023-10-10 12:42:03,645][76543] Updated weights for policy 0, policy_version 530 (0.0008) -[2023-10-10 12:42:03,946][76542] Updated weights for policy 1, policy_version 540 (0.0009) -[2023-10-10 12:42:04,013][76543] Updated weights for policy 0, policy_version 540 (0.0008) -[2023-10-10 12:42:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13475.2). Total num frames: 1114112. Throughput: 0: 1811.3, 1: 1813.9. Samples: 281430. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:42:06,077][75634] Avg episode reward: [(0, '5.240'), (1, '6.290')] -[2023-10-10 12:42:07,526][76542] Updated weights for policy 1, policy_version 550 (0.0009) -[2023-10-10 12:42:07,820][76543] Updated weights for policy 0, policy_version 550 (0.0008) -[2023-10-10 12:42:07,901][76542] Updated weights for policy 1, policy_version 560 (0.0009) -[2023-10-10 12:42:08,196][76543] Updated weights for policy 0, policy_version 560 (0.0009) -[2023-10-10 12:42:08,252][76542] Updated weights for policy 1, policy_version 570 (0.0008) -[2023-10-10 12:42:08,559][76543] Updated weights for policy 0, policy_version 570 (0.0008) -[2023-10-10 12:42:11,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13454.3). Total num frames: 1179648. Throughput: 0: 1797.6, 1: 1807.1. Samples: 302256. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-10 12:42:11,076][75634] Avg episode reward: [(0, '5.320'), (1, '6.860')] -[2023-10-10 12:42:11,077][76421] Saving new best policy, reward=6.860! -[2023-10-10 12:42:11,859][76542] Updated weights for policy 1, policy_version 580 (0.0007) -[2023-10-10 12:42:12,223][76542] Updated weights for policy 1, policy_version 590 (0.0010) -[2023-10-10 12:42:12,329][76543] Updated weights for policy 0, policy_version 580 (0.0007) -[2023-10-10 12:42:12,595][76542] Updated weights for policy 1, policy_version 600 (0.0008) -[2023-10-10 12:42:12,703][76543] Updated weights for policy 0, policy_version 590 (0.0007) -[2023-10-10 12:42:13,068][76543] Updated weights for policy 0, policy_version 600 (0.0010) -[2023-10-10 12:42:16,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13435.5). Total num frames: 1245184. Throughput: 0: 1807.8, 1: 1812.1. Samples: 325422. Policy #0 lag: (min: 17.0, avg: 20.3, max: 49.0) -[2023-10-10 12:42:16,076][75634] Avg episode reward: [(0, '5.400'), (1, '6.260')] -[2023-10-10 12:42:16,223][76542] Updated weights for policy 1, policy_version 610 (0.0009) -[2023-10-10 12:42:16,587][76542] Updated weights for policy 1, policy_version 620 (0.0010) -[2023-10-10 12:42:16,680][76543] Updated weights for policy 0, policy_version 610 (0.0008) -[2023-10-10 12:42:16,958][76542] Updated weights for policy 1, policy_version 630 (0.0007) -[2023-10-10 12:42:17,042][76543] Updated weights for policy 0, policy_version 620 (0.0009) -[2023-10-10 12:42:17,322][76542] Updated weights for policy 1, policy_version 640 (0.0009) -[2023-10-10 12:42:17,420][76543] Updated weights for policy 0, policy_version 630 (0.0007) -[2023-10-10 12:42:17,790][76543] Updated weights for policy 0, policy_version 640 (0.0008) -[2023-10-10 12:42:21,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13418.7). Total num frames: 1310720. Throughput: 0: 1807.1, 1: 1808.8. Samples: 335290. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-10 12:42:21,077][75634] Avg episode reward: [(0, '5.670'), (1, '5.590')] -[2023-10-10 12:42:21,078][76362] Saving new best policy, reward=5.670! -[2023-10-10 12:42:21,189][76542] Updated weights for policy 1, policy_version 650 (0.0009) -[2023-10-10 12:42:21,555][76542] Updated weights for policy 1, policy_version 660 (0.0008) -[2023-10-10 12:42:21,682][76543] Updated weights for policy 0, policy_version 650 (0.0008) -[2023-10-10 12:42:21,923][76542] Updated weights for policy 1, policy_version 670 (0.0009) -[2023-10-10 12:42:22,061][76543] Updated weights for policy 0, policy_version 660 (0.0007) -[2023-10-10 12:42:22,432][76543] Updated weights for policy 0, policy_version 670 (0.0008) -[2023-10-10 12:42:25,527][76542] Updated weights for policy 1, policy_version 680 (0.0008) -[2023-10-10 12:42:25,907][76542] Updated weights for policy 1, policy_version 690 (0.0008) -[2023-10-10 12:42:26,060][76543] Updated weights for policy 0, policy_version 680 (0.0007) -[2023-10-10 12:42:26,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13403.6). Total num frames: 1376256. Throughput: 0: 1804.5, 1: 1814.4. Samples: 357916. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-10-10 12:42:26,076][75634] Avg episode reward: [(0, '5.890'), (1, '5.670')] -[2023-10-10 12:42:26,266][76542] Updated weights for policy 1, policy_version 700 (0.0007) -[2023-10-10 12:42:26,432][76543] Updated weights for policy 0, policy_version 690 (0.0008) -[2023-10-10 12:42:26,807][76543] Updated weights for policy 0, policy_version 700 (0.0007) -[2023-10-10 12:42:26,955][76362] Saving new best policy, reward=5.890! -[2023-10-10 12:42:30,070][76542] Updated weights for policy 1, policy_version 710 (0.0008) -[2023-10-10 12:42:30,421][76543] Updated weights for policy 0, policy_version 710 (0.0008) -[2023-10-10 12:42:30,433][76542] Updated weights for policy 1, policy_version 720 (0.0007) -[2023-10-10 12:42:30,793][76542] Updated weights for policy 1, policy_version 730 (0.0008) -[2023-10-10 12:42:30,797][76543] Updated weights for policy 0, policy_version 720 (0.0008) -[2023-10-10 12:42:31,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 13694.1). Total num frames: 1474560. Throughput: 0: 1809.2, 1: 1819.1. Samples: 379664. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-10 12:42:31,076][75634] Avg episode reward: [(0, '5.840'), (1, '5.560')] -[2023-10-10 12:42:31,084][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000000736_753664.pth... -[2023-10-10 12:42:31,162][76543] Updated weights for policy 0, policy_version 730 (0.0008) -[2023-10-10 12:42:31,378][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000000736_753664.pth... -[2023-10-10 12:42:34,540][76542] Updated weights for policy 1, policy_version 740 (0.0008) -[2023-10-10 12:42:34,905][76543] Updated weights for policy 0, policy_version 740 (0.0009) -[2023-10-10 12:42:34,913][76542] Updated weights for policy 1, policy_version 750 (0.0008) -[2023-10-10 12:42:35,267][76543] Updated weights for policy 0, policy_version 750 (0.0008) -[2023-10-10 12:42:35,271][76542] Updated weights for policy 1, policy_version 760 (0.0008) -[2023-10-10 12:42:35,637][76543] Updated weights for policy 0, policy_version 760 (0.0008) -[2023-10-10 12:42:36,076][75634] Fps is (10 sec: 19660.6, 60 sec: 15291.7, 300 sec: 13958.9). Total num frames: 1572864. Throughput: 0: 1800.9, 1: 1813.0. Samples: 390540. Policy #0 lag: (min: 31.0, avg: 32.3, max: 56.0) -[2023-10-10 12:42:36,076][75634] Avg episode reward: [(0, '5.610'), (1, '5.710')] -[2023-10-10 12:42:39,117][76542] Updated weights for policy 1, policy_version 770 (0.0008) -[2023-10-10 12:42:39,484][76542] Updated weights for policy 1, policy_version 780 (0.0008) -[2023-10-10 12:42:39,499][76543] Updated weights for policy 0, policy_version 770 (0.0007) -[2023-10-10 12:42:39,850][76542] Updated weights for policy 1, policy_version 790 (0.0008) -[2023-10-10 12:42:39,856][76543] Updated weights for policy 0, policy_version 780 (0.0010) -[2023-10-10 12:42:40,208][76542] Updated weights for policy 1, policy_version 800 (0.0009) -[2023-10-10 12:42:40,227][76543] Updated weights for policy 0, policy_version 790 (0.0008) -[2023-10-10 12:42:40,589][76543] Updated weights for policy 0, policy_version 800 (0.0007) -[2023-10-10 12:42:41,076][75634] Fps is (10 sec: 16383.9, 60 sec: 15291.7, 300 sec: 13922.7). Total num frames: 1638400. Throughput: 0: 1805.7, 1: 1821.8. Samples: 412178. Policy #0 lag: (min: 15.0, avg: 16.6, max: 43.0) -[2023-10-10 12:42:41,077][75634] Avg episode reward: [(0, '5.480'), (1, '5.430')] -[2023-10-10 12:42:43,974][76542] Updated weights for policy 1, policy_version 810 (0.0007) -[2023-10-10 12:42:44,346][76542] Updated weights for policy 1, policy_version 820 (0.0007) -[2023-10-10 12:42:44,409][76543] Updated weights for policy 0, policy_version 810 (0.0008) -[2023-10-10 12:42:44,712][76542] Updated weights for policy 1, policy_version 830 (0.0010) -[2023-10-10 12:42:44,780][76543] Updated weights for policy 0, policy_version 820 (0.0008) -[2023-10-10 12:42:45,143][76543] Updated weights for policy 0, policy_version 830 (0.0009) -[2023-10-10 12:42:46,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 13889.5). Total num frames: 1703936. Throughput: 0: 1797.7, 1: 1815.4. Samples: 432544. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-10 12:42:46,076][75634] Avg episode reward: [(0, '5.870'), (1, '5.690')] -[2023-10-10 12:42:48,356][76542] Updated weights for policy 1, policy_version 840 (0.0008) -[2023-10-10 12:42:48,643][76543] Updated weights for policy 0, policy_version 840 (0.0008) -[2023-10-10 12:42:48,727][76542] Updated weights for policy 1, policy_version 850 (0.0008) -[2023-10-10 12:42:49,020][76543] Updated weights for policy 0, policy_version 850 (0.0008) -[2023-10-10 12:42:49,095][76542] Updated weights for policy 1, policy_version 860 (0.0008) -[2023-10-10 12:42:49,386][76543] Updated weights for policy 0, policy_version 860 (0.0008) -[2023-10-10 12:42:51,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13858.8). Total num frames: 1769472. Throughput: 0: 1813.6, 1: 1816.4. Samples: 444778. Policy #0 lag: (min: 8.0, avg: 29.0, max: 40.0) -[2023-10-10 12:42:51,076][75634] Avg episode reward: [(0, '5.850'), (1, '5.890')] -[2023-10-10 12:42:52,865][76542] Updated weights for policy 1, policy_version 870 (0.0009) -[2023-10-10 12:42:53,163][76543] Updated weights for policy 0, policy_version 870 (0.0007) -[2023-10-10 12:42:53,234][76542] Updated weights for policy 1, policy_version 880 (0.0008) -[2023-10-10 12:42:53,535][76543] Updated weights for policy 0, policy_version 880 (0.0008) -[2023-10-10 12:42:53,598][76542] Updated weights for policy 1, policy_version 890 (0.0007) -[2023-10-10 12:42:53,904][76543] Updated weights for policy 0, policy_version 890 (0.0009) -[2023-10-10 12:42:56,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13830.5). Total num frames: 1835008. Throughput: 0: 1809.2, 1: 1813.1. Samples: 465258. Policy #0 lag: (min: 22.0, avg: 44.9, max: 48.0) -[2023-10-10 12:42:56,077][75634] Avg episode reward: [(0, '5.750'), (1, '6.060')] -[2023-10-10 12:42:57,263][76542] Updated weights for policy 1, policy_version 900 (0.0008) -[2023-10-10 12:42:57,618][76543] Updated weights for policy 0, policy_version 900 (0.0009) -[2023-10-10 12:42:57,639][76542] Updated weights for policy 1, policy_version 910 (0.0007) -[2023-10-10 12:42:57,985][76543] Updated weights for policy 0, policy_version 910 (0.0009) -[2023-10-10 12:42:57,996][76542] Updated weights for policy 1, policy_version 920 (0.0009) -[2023-10-10 12:42:58,347][76543] Updated weights for policy 0, policy_version 920 (0.0007) -[2023-10-10 12:43:01,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13804.2). Total num frames: 1900544. Throughput: 0: 1808.2, 1: 1812.8. Samples: 488366. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:43:01,076][75634] Avg episode reward: [(0, '6.370'), (1, '6.120')] -[2023-10-10 12:43:01,086][76362] Saving new best policy, reward=6.370! -[2023-10-10 12:43:01,680][76542] Updated weights for policy 1, policy_version 930 (0.0008) -[2023-10-10 12:43:01,945][76543] Updated weights for policy 0, policy_version 930 (0.0007) -[2023-10-10 12:43:02,040][76542] Updated weights for policy 1, policy_version 940 (0.0009) -[2023-10-10 12:43:02,321][76543] Updated weights for policy 0, policy_version 940 (0.0008) -[2023-10-10 12:43:02,411][76542] Updated weights for policy 1, policy_version 950 (0.0009) -[2023-10-10 12:43:02,701][76543] Updated weights for policy 0, policy_version 950 (0.0008) -[2023-10-10 12:43:02,781][76542] Updated weights for policy 1, policy_version 960 (0.0008) -[2023-10-10 12:43:03,064][76543] Updated weights for policy 0, policy_version 960 (0.0010) -[2023-10-10 12:43:06,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13779.8). Total num frames: 1966080. Throughput: 0: 1808.4, 1: 1809.3. Samples: 498090. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 12:43:06,076][75634] Avg episode reward: [(0, '6.530'), (1, '5.740')] -[2023-10-10 12:43:06,077][76362] Saving new best policy, reward=6.530! -[2023-10-10 12:43:06,571][76542] Updated weights for policy 1, policy_version 970 (0.0009) -[2023-10-10 12:43:06,727][76543] Updated weights for policy 0, policy_version 970 (0.0008) -[2023-10-10 12:43:06,942][76542] Updated weights for policy 1, policy_version 980 (0.0007) -[2023-10-10 12:43:07,085][76543] Updated weights for policy 0, policy_version 980 (0.0008) -[2023-10-10 12:43:07,309][76542] Updated weights for policy 1, policy_version 990 (0.0007) -[2023-10-10 12:43:07,461][76543] Updated weights for policy 0, policy_version 990 (0.0008) -[2023-10-10 12:43:10,955][76542] Updated weights for policy 1, policy_version 1000 (0.0007) -[2023-10-10 12:43:11,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13757.0). Total num frames: 2031616. Throughput: 0: 1812.5, 1: 1805.0. Samples: 520702. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-10 12:43:11,076][75634] Avg episode reward: [(0, '6.250'), (1, '5.800')] -[2023-10-10 12:43:11,283][76543] Updated weights for policy 0, policy_version 1000 (0.0008) -[2023-10-10 12:43:11,326][76542] Updated weights for policy 1, policy_version 1010 (0.0008) -[2023-10-10 12:43:11,658][76543] Updated weights for policy 0, policy_version 1010 (0.0009) -[2023-10-10 12:43:11,692][76542] Updated weights for policy 1, policy_version 1020 (0.0007) -[2023-10-10 12:43:12,027][76543] Updated weights for policy 0, policy_version 1020 (0.0007) -[2023-10-10 12:43:15,257][76542] Updated weights for policy 1, policy_version 1030 (0.0009) -[2023-10-10 12:43:15,619][76542] Updated weights for policy 1, policy_version 1040 (0.0008) -[2023-10-10 12:43:15,650][76543] Updated weights for policy 0, policy_version 1030 (0.0009) -[2023-10-10 12:43:15,988][76542] Updated weights for policy 1, policy_version 1050 (0.0007) -[2023-10-10 12:43:16,016][76543] Updated weights for policy 0, policy_version 1040 (0.0008) -[2023-10-10 12:43:16,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13735.7). Total num frames: 2097152. Throughput: 0: 1809.3, 1: 1815.0. Samples: 542756. Policy #0 lag: (min: 13.0, avg: 13.9, max: 34.0) -[2023-10-10 12:43:16,077][75634] Avg episode reward: [(0, '6.640'), (1, '5.430')] -[2023-10-10 12:43:16,378][76543] Updated weights for policy 0, policy_version 1050 (0.0007) -[2023-10-10 12:43:16,595][76362] Saving new best policy, reward=6.640! -[2023-10-10 12:43:19,726][76542] Updated weights for policy 1, policy_version 1060 (0.0008) -[2023-10-10 12:43:20,067][76543] Updated weights for policy 0, policy_version 1060 (0.0008) -[2023-10-10 12:43:20,094][76542] Updated weights for policy 1, policy_version 1070 (0.0008) -[2023-10-10 12:43:20,439][76543] Updated weights for policy 0, policy_version 1070 (0.0007) -[2023-10-10 12:43:20,452][76542] Updated weights for policy 1, policy_version 1080 (0.0009) -[2023-10-10 12:43:20,822][76543] Updated weights for policy 0, policy_version 1080 (0.0008) -[2023-10-10 12:43:21,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 13923.6). Total num frames: 2195456. Throughput: 0: 1807.9, 1: 1812.7. Samples: 553464. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-10 12:43:21,076][75634] Avg episode reward: [(0, '6.550'), (1, '5.580')] -[2023-10-10 12:43:24,255][76542] Updated weights for policy 1, policy_version 1090 (0.0009) -[2023-10-10 12:43:24,609][76543] Updated weights for policy 0, policy_version 1090 (0.0009) -[2023-10-10 12:43:24,622][76542] Updated weights for policy 1, policy_version 1100 (0.0009) -[2023-10-10 12:43:24,982][76543] Updated weights for policy 0, policy_version 1100 (0.0008) -[2023-10-10 12:43:24,993][76542] Updated weights for policy 1, policy_version 1110 (0.0008) -[2023-10-10 12:43:25,352][76543] Updated weights for policy 0, policy_version 1110 (0.0009) -[2023-10-10 12:43:25,354][76542] Updated weights for policy 1, policy_version 1120 (0.0007) -[2023-10-10 12:43:25,732][76543] Updated weights for policy 0, policy_version 1120 (0.0008) -[2023-10-10 12:43:26,076][75634] Fps is (10 sec: 19660.7, 60 sec: 15291.7, 300 sec: 14100.0). Total num frames: 2293760. Throughput: 0: 1810.0, 1: 1812.0. Samples: 575170. Policy #0 lag: (min: 6.0, avg: 9.1, max: 38.0) -[2023-10-10 12:43:26,077][75634] Avg episode reward: [(0, '6.240'), (1, '5.670')] -[2023-10-10 12:43:29,091][76542] Updated weights for policy 1, policy_version 1130 (0.0007) -[2023-10-10 12:43:29,376][76543] Updated weights for policy 0, policy_version 1130 (0.0009) -[2023-10-10 12:43:29,454][76542] Updated weights for policy 1, policy_version 1140 (0.0007) -[2023-10-10 12:43:29,742][76543] Updated weights for policy 0, policy_version 1140 (0.0008) -[2023-10-10 12:43:29,821][76542] Updated weights for policy 1, policy_version 1150 (0.0007) -[2023-10-10 12:43:30,115][76543] Updated weights for policy 0, policy_version 1150 (0.0008) -[2023-10-10 12:43:31,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14070.4). Total num frames: 2359296. Throughput: 0: 1816.5, 1: 1810.4. Samples: 595758. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:43:31,076][75634] Avg episode reward: [(0, '6.210'), (1, '5.750')] -[2023-10-10 12:43:33,617][76542] Updated weights for policy 1, policy_version 1160 (0.0010) -[2023-10-10 12:43:33,826][76543] Updated weights for policy 0, policy_version 1160 (0.0010) -[2023-10-10 12:43:33,988][76542] Updated weights for policy 1, policy_version 1170 (0.0010) -[2023-10-10 12:43:34,190][76543] Updated weights for policy 0, policy_version 1170 (0.0009) -[2023-10-10 12:43:34,361][76542] Updated weights for policy 1, policy_version 1180 (0.0007) -[2023-10-10 12:43:34,568][76543] Updated weights for policy 0, policy_version 1180 (0.0008) -[2023-10-10 12:43:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14042.5). Total num frames: 2424832. Throughput: 0: 1815.5, 1: 1816.7. Samples: 608232. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-10 12:43:36,077][75634] Avg episode reward: [(0, '6.370'), (1, '5.430')] -[2023-10-10 12:43:38,179][76542] Updated weights for policy 1, policy_version 1190 (0.0009) -[2023-10-10 12:43:38,260][76543] Updated weights for policy 0, policy_version 1190 (0.0010) -[2023-10-10 12:43:38,543][76542] Updated weights for policy 1, policy_version 1200 (0.0007) -[2023-10-10 12:43:38,638][76543] Updated weights for policy 0, policy_version 1200 (0.0008) -[2023-10-10 12:43:38,923][76542] Updated weights for policy 1, policy_version 1210 (0.0007) -[2023-10-10 12:43:39,012][76543] Updated weights for policy 0, policy_version 1210 (0.0008) -[2023-10-10 12:43:41,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14016.2). Total num frames: 2490368. Throughput: 0: 1814.8, 1: 1809.3. Samples: 628342. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-10-10 12:43:41,077][75634] Avg episode reward: [(0, '5.980'), (1, '5.550')] -[2023-10-10 12:43:42,698][76542] Updated weights for policy 1, policy_version 1220 (0.0009) -[2023-10-10 12:43:42,754][76543] Updated weights for policy 0, policy_version 1220 (0.0009) -[2023-10-10 12:43:43,067][76542] Updated weights for policy 1, policy_version 1230 (0.0008) -[2023-10-10 12:43:43,128][76543] Updated weights for policy 0, policy_version 1230 (0.0008) -[2023-10-10 12:43:43,441][76542] Updated weights for policy 1, policy_version 1240 (0.0009) -[2023-10-10 12:43:43,507][76543] Updated weights for policy 0, policy_version 1240 (0.0009) -[2023-10-10 12:43:46,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13991.3). Total num frames: 2555904. Throughput: 0: 1802.7, 1: 1804.3. Samples: 650682. Policy #0 lag: (min: 31.0, avg: 31.2, max: 40.0) -[2023-10-10 12:43:46,076][75634] Avg episode reward: [(0, '6.480'), (1, '5.380')] -[2023-10-10 12:43:47,164][76542] Updated weights for policy 1, policy_version 1250 (0.0007) -[2023-10-10 12:43:47,239][76543] Updated weights for policy 0, policy_version 1250 (0.0008) -[2023-10-10 12:43:47,534][76542] Updated weights for policy 1, policy_version 1260 (0.0009) -[2023-10-10 12:43:47,612][76543] Updated weights for policy 0, policy_version 1260 (0.0008) -[2023-10-10 12:43:47,903][76542] Updated weights for policy 1, policy_version 1270 (0.0009) -[2023-10-10 12:43:47,987][76543] Updated weights for policy 0, policy_version 1270 (0.0010) -[2023-10-10 12:43:48,265][76542] Updated weights for policy 1, policy_version 1280 (0.0007) -[2023-10-10 12:43:48,352][76543] Updated weights for policy 0, policy_version 1280 (0.0007) -[2023-10-10 12:43:51,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13967.7). Total num frames: 2621440. Throughput: 0: 1804.7, 1: 1808.8. Samples: 660694. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:43:51,077][75634] Avg episode reward: [(0, '6.000'), (1, '5.480')] -[2023-10-10 12:43:52,000][76542] Updated weights for policy 1, policy_version 1290 (0.0007) -[2023-10-10 12:43:52,192][76543] Updated weights for policy 0, policy_version 1290 (0.0008) -[2023-10-10 12:43:52,372][76542] Updated weights for policy 1, policy_version 1300 (0.0008) -[2023-10-10 12:43:52,554][76543] Updated weights for policy 0, policy_version 1300 (0.0007) -[2023-10-10 12:43:52,746][76542] Updated weights for policy 1, policy_version 1310 (0.0007) -[2023-10-10 12:43:52,926][76543] Updated weights for policy 0, policy_version 1310 (0.0008) -[2023-10-10 12:43:56,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13945.4). Total num frames: 2686976. Throughput: 0: 1796.2, 1: 1806.2. Samples: 682808. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-10 12:43:56,077][75634] Avg episode reward: [(0, '6.120'), (1, '5.740')] -[2023-10-10 12:43:56,465][76542] Updated weights for policy 1, policy_version 1320 (0.0010) -[2023-10-10 12:43:56,743][76543] Updated weights for policy 0, policy_version 1320 (0.0008) -[2023-10-10 12:43:56,842][76542] Updated weights for policy 1, policy_version 1330 (0.0008) -[2023-10-10 12:43:57,116][76543] Updated weights for policy 0, policy_version 1330 (0.0007) -[2023-10-10 12:43:57,212][76542] Updated weights for policy 1, policy_version 1340 (0.0009) -[2023-10-10 12:43:57,496][76543] Updated weights for policy 0, policy_version 1340 (0.0007) -[2023-10-10 12:44:00,819][76542] Updated weights for policy 1, policy_version 1350 (0.0009) -[2023-10-10 12:44:01,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13924.2). Total num frames: 2752512. Throughput: 0: 1796.6, 1: 1815.9. Samples: 705316. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-10 12:44:01,076][75634] Avg episode reward: [(0, '6.280'), (1, '5.710')] -[2023-10-10 12:44:01,088][76543] Updated weights for policy 0, policy_version 1350 (0.0007) -[2023-10-10 12:44:01,186][76542] Updated weights for policy 1, policy_version 1360 (0.0007) -[2023-10-10 12:44:01,456][76543] Updated weights for policy 0, policy_version 1360 (0.0007) -[2023-10-10 12:44:01,551][76542] Updated weights for policy 1, policy_version 1370 (0.0008) -[2023-10-10 12:44:01,830][76543] Updated weights for policy 0, policy_version 1370 (0.0007) -[2023-10-10 12:44:05,309][76542] Updated weights for policy 1, policy_version 1380 (0.0008) -[2023-10-10 12:44:05,601][76543] Updated weights for policy 0, policy_version 1380 (0.0009) -[2023-10-10 12:44:05,672][76542] Updated weights for policy 1, policy_version 1390 (0.0008) -[2023-10-10 12:44:05,984][76543] Updated weights for policy 0, policy_version 1390 (0.0007) -[2023-10-10 12:44:06,042][76542] Updated weights for policy 1, policy_version 1400 (0.0007) -[2023-10-10 12:44:06,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13904.0). Total num frames: 2818048. Throughput: 0: 1795.0, 1: 1802.5. Samples: 715350. Policy #0 lag: (min: 10.0, avg: 12.9, max: 42.0) -[2023-10-10 12:44:06,076][75634] Avg episode reward: [(0, '6.140'), (1, '5.770')] -[2023-10-10 12:44:06,352][76543] Updated weights for policy 0, policy_version 1400 (0.0009) -[2023-10-10 12:44:09,703][76542] Updated weights for policy 1, policy_version 1410 (0.0007) -[2023-10-10 12:44:10,060][76543] Updated weights for policy 0, policy_version 1410 (0.0008) -[2023-10-10 12:44:10,081][76542] Updated weights for policy 1, policy_version 1420 (0.0008) -[2023-10-10 12:44:10,425][76543] Updated weights for policy 0, policy_version 1420 (0.0007) -[2023-10-10 12:44:10,446][76542] Updated weights for policy 1, policy_version 1430 (0.0009) -[2023-10-10 12:44:10,793][76543] Updated weights for policy 0, policy_version 1430 (0.0007) -[2023-10-10 12:44:10,812][76542] Updated weights for policy 1, policy_version 1440 (0.0010) -[2023-10-10 12:44:11,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14042.6). Total num frames: 2916352. Throughput: 0: 1799.4, 1: 1820.2. Samples: 738054. Policy #0 lag: (min: 10.0, avg: 18.0, max: 42.0) -[2023-10-10 12:44:11,076][75634] Avg episode reward: [(0, '6.480'), (1, '6.320')] -[2023-10-10 12:44:11,167][76543] Updated weights for policy 0, policy_version 1440 (0.0009) -[2023-10-10 12:44:14,409][76542] Updated weights for policy 1, policy_version 1450 (0.0008) -[2023-10-10 12:44:14,778][76542] Updated weights for policy 1, policy_version 1460 (0.0007) -[2023-10-10 12:44:14,847][76543] Updated weights for policy 0, policy_version 1450 (0.0009) -[2023-10-10 12:44:15,144][76542] Updated weights for policy 1, policy_version 1470 (0.0008) -[2023-10-10 12:44:15,224][76543] Updated weights for policy 0, policy_version 1460 (0.0008) -[2023-10-10 12:44:15,609][76543] Updated weights for policy 0, policy_version 1470 (0.0008) -[2023-10-10 12:44:16,076][75634] Fps is (10 sec: 19659.8, 60 sec: 15291.7, 300 sec: 14174.7). Total num frames: 3014656. Throughput: 0: 1808.3, 1: 1808.6. Samples: 758522. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 12:44:16,077][75634] Avg episode reward: [(0, '6.810'), (1, '5.990')] -[2023-10-10 12:44:16,090][76362] Saving new best policy, reward=6.810! -[2023-10-10 12:44:18,885][76542] Updated weights for policy 1, policy_version 1480 (0.0009) -[2023-10-10 12:44:19,248][76542] Updated weights for policy 1, policy_version 1490 (0.0010) -[2023-10-10 12:44:19,269][76543] Updated weights for policy 0, policy_version 1480 (0.0010) -[2023-10-10 12:44:19,615][76542] Updated weights for policy 1, policy_version 1500 (0.0008) -[2023-10-10 12:44:19,630][76543] Updated weights for policy 0, policy_version 1490 (0.0007) -[2023-10-10 12:44:20,011][76543] Updated weights for policy 0, policy_version 1500 (0.0008) -[2023-10-10 12:44:21,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14150.2). Total num frames: 3080192. Throughput: 0: 1791.7, 1: 1817.2. Samples: 770632. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 12:44:21,076][75634] Avg episode reward: [(0, '7.330'), (1, '6.880')] -[2023-10-10 12:44:21,077][76362] Saving new best policy, reward=7.330! -[2023-10-10 12:44:21,077][76421] Saving new best policy, reward=6.880! -[2023-10-10 12:44:23,331][76542] Updated weights for policy 1, policy_version 1510 (0.0008) -[2023-10-10 12:44:23,655][76543] Updated weights for policy 0, policy_version 1510 (0.0008) -[2023-10-10 12:44:23,695][76542] Updated weights for policy 1, policy_version 1520 (0.0007) -[2023-10-10 12:44:24,021][76543] Updated weights for policy 0, policy_version 1520 (0.0008) -[2023-10-10 12:44:24,064][76542] Updated weights for policy 1, policy_version 1530 (0.0007) -[2023-10-10 12:44:24,385][76543] Updated weights for policy 0, policy_version 1530 (0.0007) -[2023-10-10 12:44:26,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14126.8). Total num frames: 3145728. Throughput: 0: 1806.3, 1: 1806.0. Samples: 790898. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 12:44:26,077][75634] Avg episode reward: [(0, '6.720'), (1, '6.910')] -[2023-10-10 12:44:26,078][76421] Saving new best policy, reward=6.910! -[2023-10-10 12:44:27,632][76542] Updated weights for policy 1, policy_version 1540 (0.0007) -[2023-10-10 12:44:27,999][76542] Updated weights for policy 1, policy_version 1550 (0.0009) -[2023-10-10 12:44:28,116][76543] Updated weights for policy 0, policy_version 1540 (0.0008) -[2023-10-10 12:44:28,371][76542] Updated weights for policy 1, policy_version 1560 (0.0008) -[2023-10-10 12:44:28,484][76543] Updated weights for policy 0, policy_version 1550 (0.0007) -[2023-10-10 12:44:28,854][76543] Updated weights for policy 0, policy_version 1560 (0.0007) -[2023-10-10 12:44:31,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14104.4). Total num frames: 3211264. Throughput: 0: 1799.3, 1: 1813.2. Samples: 813246. Policy #0 lag: (min: 17.0, avg: 22.5, max: 49.0) -[2023-10-10 12:44:31,077][75634] Avg episode reward: [(0, '7.320'), (1, '6.100')] -[2023-10-10 12:44:31,092][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000001568_1605632.pth... -[2023-10-10 12:44:31,092][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000001568_1605632.pth... -[2023-10-10 12:44:32,010][76542] Updated weights for policy 1, policy_version 1570 (0.0008) -[2023-10-10 12:44:32,377][76542] Updated weights for policy 1, policy_version 1580 (0.0009) -[2023-10-10 12:44:32,524][76543] Updated weights for policy 0, policy_version 1570 (0.0009) -[2023-10-10 12:44:32,751][76542] Updated weights for policy 1, policy_version 1590 (0.0010) -[2023-10-10 12:44:32,903][76543] Updated weights for policy 0, policy_version 1580 (0.0008) -[2023-10-10 12:44:33,122][76542] Updated weights for policy 1, policy_version 1600 (0.0008) -[2023-10-10 12:44:33,280][76543] Updated weights for policy 0, policy_version 1590 (0.0008) -[2023-10-10 12:44:33,651][76543] Updated weights for policy 0, policy_version 1600 (0.0007) -[2023-10-10 12:44:36,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14083.0). Total num frames: 3276800. Throughput: 0: 1808.4, 1: 1812.4. Samples: 823632. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-10 12:44:36,077][75634] Avg episode reward: [(0, '6.700'), (1, '6.140')] -[2023-10-10 12:44:36,886][76542] Updated weights for policy 1, policy_version 1610 (0.0009) -[2023-10-10 12:44:37,262][76542] Updated weights for policy 1, policy_version 1620 (0.0010) -[2023-10-10 12:44:37,298][76543] Updated weights for policy 0, policy_version 1610 (0.0008) -[2023-10-10 12:44:37,637][76542] Updated weights for policy 1, policy_version 1630 (0.0007) -[2023-10-10 12:44:37,672][76543] Updated weights for policy 0, policy_version 1620 (0.0009) -[2023-10-10 12:44:38,044][76543] Updated weights for policy 0, policy_version 1630 (0.0008) -[2023-10-10 12:44:41,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14062.4). Total num frames: 3342336. Throughput: 0: 1804.9, 1: 1817.6. Samples: 845820. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-10 12:44:41,076][75634] Avg episode reward: [(0, '6.790'), (1, '5.490')] -[2023-10-10 12:44:41,394][76542] Updated weights for policy 1, policy_version 1640 (0.0008) -[2023-10-10 12:44:41,778][76542] Updated weights for policy 1, policy_version 1650 (0.0008) -[2023-10-10 12:44:41,908][76543] Updated weights for policy 0, policy_version 1640 (0.0009) -[2023-10-10 12:44:42,145][76542] Updated weights for policy 1, policy_version 1660 (0.0007) -[2023-10-10 12:44:42,282][76543] Updated weights for policy 0, policy_version 1650 (0.0008) -[2023-10-10 12:44:42,653][76543] Updated weights for policy 0, policy_version 1660 (0.0008) -[2023-10-10 12:44:45,881][76542] Updated weights for policy 1, policy_version 1670 (0.0008) -[2023-10-10 12:44:46,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14042.7). Total num frames: 3407872. Throughput: 0: 1804.8, 1: 1813.7. Samples: 868148. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-10 12:44:46,076][75634] Avg episode reward: [(0, '6.880'), (1, '5.580')] -[2023-10-10 12:44:46,245][76542] Updated weights for policy 1, policy_version 1680 (0.0007) -[2023-10-10 12:44:46,406][76543] Updated weights for policy 0, policy_version 1670 (0.0009) -[2023-10-10 12:44:46,617][76542] Updated weights for policy 1, policy_version 1690 (0.0009) -[2023-10-10 12:44:46,786][76543] Updated weights for policy 0, policy_version 1680 (0.0009) -[2023-10-10 12:44:47,161][76543] Updated weights for policy 0, policy_version 1690 (0.0010) -[2023-10-10 12:44:50,476][76542] Updated weights for policy 1, policy_version 1700 (0.0007) -[2023-10-10 12:44:50,843][76542] Updated weights for policy 1, policy_version 1710 (0.0009) -[2023-10-10 12:44:51,043][76543] Updated weights for policy 0, policy_version 1700 (0.0010) -[2023-10-10 12:44:51,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14023.9). Total num frames: 3473408. Throughput: 0: 1803.4, 1: 1807.6. Samples: 877842. Policy #0 lag: (min: 31.0, avg: 32.9, max: 60.0) -[2023-10-10 12:44:51,076][75634] Avg episode reward: [(0, '7.100'), (1, '5.550')] -[2023-10-10 12:44:51,205][76542] Updated weights for policy 1, policy_version 1720 (0.0009) -[2023-10-10 12:44:51,416][76543] Updated weights for policy 0, policy_version 1710 (0.0008) -[2023-10-10 12:44:51,796][76543] Updated weights for policy 0, policy_version 1720 (0.0009) -[2023-10-10 12:44:54,974][76542] Updated weights for policy 1, policy_version 1730 (0.0008) -[2023-10-10 12:44:55,332][76542] Updated weights for policy 1, policy_version 1740 (0.0010) -[2023-10-10 12:44:55,687][76543] Updated weights for policy 0, policy_version 1730 (0.0010) -[2023-10-10 12:44:55,698][76542] Updated weights for policy 1, policy_version 1750 (0.0009) -[2023-10-10 12:44:56,056][76543] Updated weights for policy 0, policy_version 1740 (0.0010) -[2023-10-10 12:44:56,072][76542] Updated weights for policy 1, policy_version 1760 (0.0008) -[2023-10-10 12:44:56,077][75634] Fps is (10 sec: 16381.9, 60 sec: 14745.3, 300 sec: 14135.3). Total num frames: 3571712. Throughput: 0: 1800.5, 1: 1804.7. Samples: 900290. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:44:56,079][75634] Avg episode reward: [(0, '6.890'), (1, '5.900')] -[2023-10-10 12:44:56,417][76543] Updated weights for policy 0, policy_version 1750 (0.0007) -[2023-10-10 12:44:56,808][76543] Updated weights for policy 0, policy_version 1760 (0.0008) -[2023-10-10 12:44:59,796][76542] Updated weights for policy 1, policy_version 1770 (0.0010) -[2023-10-10 12:45:00,167][76542] Updated weights for policy 1, policy_version 1780 (0.0010) -[2023-10-10 12:45:00,505][76543] Updated weights for policy 0, policy_version 1770 (0.0008) -[2023-10-10 12:45:00,534][76542] Updated weights for policy 1, policy_version 1790 (0.0011) -[2023-10-10 12:45:00,883][76543] Updated weights for policy 0, policy_version 1780 (0.0009) -[2023-10-10 12:45:01,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14115.5). Total num frames: 3637248. Throughput: 0: 1814.2, 1: 1801.6. Samples: 921234. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:45:01,076][75634] Avg episode reward: [(0, '7.620'), (1, '6.260')] -[2023-10-10 12:45:01,243][76543] Updated weights for policy 0, policy_version 1790 (0.0009) -[2023-10-10 12:45:01,319][76362] Saving new best policy, reward=7.620! -[2023-10-10 12:45:04,216][76542] Updated weights for policy 1, policy_version 1800 (0.0008) -[2023-10-10 12:45:04,574][76542] Updated weights for policy 1, policy_version 1810 (0.0011) -[2023-10-10 12:45:04,942][76542] Updated weights for policy 1, policy_version 1820 (0.0007) -[2023-10-10 12:45:05,031][76543] Updated weights for policy 0, policy_version 1800 (0.0010) -[2023-10-10 12:45:05,401][76543] Updated weights for policy 0, policy_version 1810 (0.0010) -[2023-10-10 12:45:05,774][76543] Updated weights for policy 0, policy_version 1820 (0.0012) -[2023-10-10 12:45:06,076][75634] Fps is (10 sec: 16385.8, 60 sec: 15291.7, 300 sec: 14221.0). Total num frames: 3735552. Throughput: 0: 1795.8, 1: 1806.6. Samples: 932740. Policy #0 lag: (min: 31.0, avg: 47.2, max: 63.0) -[2023-10-10 12:45:06,077][75634] Avg episode reward: [(0, '7.220'), (1, '6.720')] -[2023-10-10 12:45:08,576][76542] Updated weights for policy 1, policy_version 1830 (0.0008) -[2023-10-10 12:45:08,944][76542] Updated weights for policy 1, policy_version 1840 (0.0010) -[2023-10-10 12:45:09,307][76542] Updated weights for policy 1, policy_version 1850 (0.0007) -[2023-10-10 12:45:09,354][76543] Updated weights for policy 0, policy_version 1830 (0.0009) -[2023-10-10 12:45:09,719][76543] Updated weights for policy 0, policy_version 1840 (0.0008) -[2023-10-10 12:45:10,092][76543] Updated weights for policy 0, policy_version 1850 (0.0008) -[2023-10-10 12:45:11,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14200.2). Total num frames: 3801088. Throughput: 0: 1815.4, 1: 1808.9. Samples: 953992. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:45:11,076][75634] Avg episode reward: [(0, '7.230'), (1, '6.990')] -[2023-10-10 12:45:11,077][76421] Saving new best policy, reward=6.990! -[2023-10-10 12:45:12,856][76542] Updated weights for policy 1, policy_version 1860 (0.0008) -[2023-10-10 12:45:13,228][76542] Updated weights for policy 1, policy_version 1870 (0.0009) -[2023-10-10 12:45:13,593][76542] Updated weights for policy 1, policy_version 1880 (0.0009) -[2023-10-10 12:45:13,630][76543] Updated weights for policy 0, policy_version 1860 (0.0009) -[2023-10-10 12:45:14,018][76543] Updated weights for policy 0, policy_version 1870 (0.0010) -[2023-10-10 12:45:14,391][76543] Updated weights for policy 0, policy_version 1880 (0.0008) -[2023-10-10 12:45:16,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.6, 300 sec: 14180.2). Total num frames: 3866624. Throughput: 0: 1801.9, 1: 1807.3. Samples: 975656. Policy #0 lag: (min: 26.0, avg: 34.4, max: 58.0) -[2023-10-10 12:45:16,076][75634] Avg episode reward: [(0, '7.780'), (1, '6.960')] -[2023-10-10 12:45:16,087][76362] Saving new best policy, reward=7.780! -[2023-10-10 12:45:17,397][76542] Updated weights for policy 1, policy_version 1890 (0.0009) -[2023-10-10 12:45:17,756][76542] Updated weights for policy 1, policy_version 1900 (0.0010) -[2023-10-10 12:45:18,107][76543] Updated weights for policy 0, policy_version 1890 (0.0007) -[2023-10-10 12:45:18,124][76542] Updated weights for policy 1, policy_version 1910 (0.0007) -[2023-10-10 12:45:18,482][76543] Updated weights for policy 0, policy_version 1900 (0.0008) -[2023-10-10 12:45:18,490][76542] Updated weights for policy 1, policy_version 1920 (0.0007) -[2023-10-10 12:45:18,864][76543] Updated weights for policy 0, policy_version 1910 (0.0009) -[2023-10-10 12:45:19,234][76543] Updated weights for policy 0, policy_version 1920 (0.0008) -[2023-10-10 12:45:21,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14160.8). Total num frames: 3932160. Throughput: 0: 1818.8, 1: 1806.6. Samples: 986772. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-10 12:45:21,076][75634] Avg episode reward: [(0, '7.440'), (1, '7.340')] -[2023-10-10 12:45:21,077][76421] Saving new best policy, reward=7.340! -[2023-10-10 12:45:22,193][76542] Updated weights for policy 1, policy_version 1930 (0.0008) -[2023-10-10 12:45:22,554][76542] Updated weights for policy 1, policy_version 1940 (0.0008) -[2023-10-10 12:45:22,913][76543] Updated weights for policy 0, policy_version 1930 (0.0008) -[2023-10-10 12:45:22,925][76542] Updated weights for policy 1, policy_version 1950 (0.0008) -[2023-10-10 12:45:23,295][76543] Updated weights for policy 0, policy_version 1940 (0.0009) -[2023-10-10 12:45:23,677][76543] Updated weights for policy 0, policy_version 1950 (0.0009) -[2023-10-10 12:45:26,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14142.2). Total num frames: 3997696. Throughput: 0: 1798.0, 1: 1804.8. Samples: 1007946. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:45:26,076][75634] Avg episode reward: [(0, '7.310'), (1, '6.670')] -[2023-10-10 12:45:26,671][76542] Updated weights for policy 1, policy_version 1960 (0.0008) -[2023-10-10 12:45:27,047][76542] Updated weights for policy 1, policy_version 1970 (0.0008) -[2023-10-10 12:45:27,409][76543] Updated weights for policy 0, policy_version 1960 (0.0008) -[2023-10-10 12:45:27,410][76542] Updated weights for policy 1, policy_version 1980 (0.0007) -[2023-10-10 12:45:27,785][76543] Updated weights for policy 0, policy_version 1970 (0.0009) -[2023-10-10 12:45:28,155][76543] Updated weights for policy 0, policy_version 1980 (0.0009) -[2023-10-10 12:45:31,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14124.2). Total num frames: 4063232. Throughput: 0: 1791.5, 1: 1805.0. Samples: 1029990. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-10 12:45:31,076][75634] Avg episode reward: [(0, '7.540'), (1, '6.240')] -[2023-10-10 12:45:31,118][76542] Updated weights for policy 1, policy_version 1990 (0.0007) -[2023-10-10 12:45:31,486][76542] Updated weights for policy 1, policy_version 2000 (0.0008) -[2023-10-10 12:45:31,850][76542] Updated weights for policy 1, policy_version 2010 (0.0008) -[2023-10-10 12:45:31,973][76543] Updated weights for policy 0, policy_version 1990 (0.0008) -[2023-10-10 12:45:32,419][76543] Updated weights for policy 0, policy_version 2002 (0.0007) -[2023-10-10 12:45:32,796][76543] Updated weights for policy 0, policy_version 2012 (0.0010) -[2023-10-10 12:45:35,642][76542] Updated weights for policy 1, policy_version 2020 (0.0007) -[2023-10-10 12:45:36,008][76542] Updated weights for policy 1, policy_version 2030 (0.0008) -[2023-10-10 12:45:36,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.8). Total num frames: 4128768. Throughput: 0: 1790.3, 1: 1807.7. Samples: 1039752. Policy #0 lag: (min: 1.0, avg: 2.7, max: 29.0) -[2023-10-10 12:45:36,077][75634] Avg episode reward: [(0, '7.210'), (1, '6.980')] -[2023-10-10 12:45:36,379][76542] Updated weights for policy 1, policy_version 2040 (0.0009) -[2023-10-10 12:45:36,576][76543] Updated weights for policy 0, policy_version 2022 (0.0009) -[2023-10-10 12:45:36,957][76543] Updated weights for policy 0, policy_version 2032 (0.0009) -[2023-10-10 12:45:37,326][76543] Updated weights for policy 0, policy_version 2042 (0.0008) -[2023-10-10 12:45:40,079][76542] Updated weights for policy 1, policy_version 2050 (0.0008) -[2023-10-10 12:45:40,444][76542] Updated weights for policy 1, policy_version 2060 (0.0007) -[2023-10-10 12:45:40,824][76542] Updated weights for policy 1, policy_version 2070 (0.0008) -[2023-10-10 12:45:41,026][76543] Updated weights for policy 0, policy_version 2052 (0.0007) -[2023-10-10 12:45:41,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 4194304. Throughput: 0: 1791.7, 1: 1815.4. Samples: 1062608. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:45:41,077][75634] Avg episode reward: [(0, '6.730'), (1, '7.360')] -[2023-10-10 12:45:41,194][76421] Saving new best policy, reward=7.360! -[2023-10-10 12:45:41,194][76542] Updated weights for policy 1, policy_version 2080 (0.0008) -[2023-10-10 12:45:41,400][76543] Updated weights for policy 0, policy_version 2062 (0.0007) -[2023-10-10 12:45:41,764][76543] Updated weights for policy 0, policy_version 2072 (0.0007) -[2023-10-10 12:45:44,975][76542] Updated weights for policy 1, policy_version 2090 (0.0009) -[2023-10-10 12:45:45,344][76542] Updated weights for policy 1, policy_version 2100 (0.0009) -[2023-10-10 12:45:45,419][76543] Updated weights for policy 0, policy_version 2082 (0.0007) -[2023-10-10 12:45:45,712][76542] Updated weights for policy 1, policy_version 2110 (0.0009) -[2023-10-10 12:45:45,793][76543] Updated weights for policy 0, policy_version 2092 (0.0007) -[2023-10-10 12:45:46,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 4292608. Throughput: 0: 1801.2, 1: 1816.3. Samples: 1084018. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 12:45:46,076][75634] Avg episode reward: [(0, '7.090'), (1, '7.200')] -[2023-10-10 12:45:46,170][76543] Updated weights for policy 0, policy_version 2102 (0.0007) -[2023-10-10 12:45:46,538][76543] Updated weights for policy 0, policy_version 2112 (0.0009) -[2023-10-10 12:45:49,448][76542] Updated weights for policy 1, policy_version 2120 (0.0010) -[2023-10-10 12:45:49,820][76542] Updated weights for policy 1, policy_version 2130 (0.0011) -[2023-10-10 12:45:50,185][76542] Updated weights for policy 1, policy_version 2140 (0.0008) -[2023-10-10 12:45:50,361][76543] Updated weights for policy 0, policy_version 2122 (0.0008) -[2023-10-10 12:45:50,734][76543] Updated weights for policy 0, policy_version 2132 (0.0008) -[2023-10-10 12:45:51,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 4358144. Throughput: 0: 1795.2, 1: 1811.8. Samples: 1095052. Policy #0 lag: (min: 26.0, avg: 34.1, max: 58.0) -[2023-10-10 12:45:51,076][75634] Avg episode reward: [(0, '7.050'), (1, '8.030')] -[2023-10-10 12:45:51,077][76421] Saving new best policy, reward=8.030! -[2023-10-10 12:45:51,104][76543] Updated weights for policy 0, policy_version 2142 (0.0009) -[2023-10-10 12:45:54,024][76542] Updated weights for policy 1, policy_version 2150 (0.0009) -[2023-10-10 12:45:54,403][76542] Updated weights for policy 1, policy_version 2160 (0.0009) -[2023-10-10 12:45:54,763][76542] Updated weights for policy 1, policy_version 2170 (0.0008) -[2023-10-10 12:45:54,789][76543] Updated weights for policy 0, policy_version 2152 (0.0007) -[2023-10-10 12:45:55,168][76543] Updated weights for policy 0, policy_version 2162 (0.0007) -[2023-10-10 12:45:55,548][76543] Updated weights for policy 0, policy_version 2172 (0.0010) -[2023-10-10 12:45:56,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.9, 300 sec: 14440.1). Total num frames: 4456448. Throughput: 0: 1797.8, 1: 1812.2. Samples: 1116442. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-10 12:45:56,077][75634] Avg episode reward: [(0, '7.420'), (1, '8.010')] -[2023-10-10 12:45:58,383][76542] Updated weights for policy 1, policy_version 2180 (0.0007) -[2023-10-10 12:45:58,744][76542] Updated weights for policy 1, policy_version 2190 (0.0008) -[2023-10-10 12:45:59,111][76542] Updated weights for policy 1, policy_version 2200 (0.0010) -[2023-10-10 12:45:59,345][76543] Updated weights for policy 0, policy_version 2182 (0.0009) -[2023-10-10 12:45:59,724][76543] Updated weights for policy 0, policy_version 2192 (0.0009) -[2023-10-10 12:46:00,086][76543] Updated weights for policy 0, policy_version 2202 (0.0008) -[2023-10-10 12:46:01,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 4521984. Throughput: 0: 1796.6, 1: 1802.3. Samples: 1137608. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:46:01,077][75634] Avg episode reward: [(0, '6.820'), (1, '8.310')] -[2023-10-10 12:46:01,086][76421] Saving new best policy, reward=8.310! -[2023-10-10 12:46:02,830][76542] Updated weights for policy 1, policy_version 2210 (0.0009) -[2023-10-10 12:46:03,198][76542] Updated weights for policy 1, policy_version 2220 (0.0007) -[2023-10-10 12:46:03,570][76542] Updated weights for policy 1, policy_version 2230 (0.0009) -[2023-10-10 12:46:03,674][76543] Updated weights for policy 0, policy_version 2212 (0.0008) -[2023-10-10 12:46:03,929][76542] Updated weights for policy 1, policy_version 2240 (0.0008) -[2023-10-10 12:46:04,048][76543] Updated weights for policy 0, policy_version 2222 (0.0007) -[2023-10-10 12:46:04,417][76543] Updated weights for policy 0, policy_version 2232 (0.0007) -[2023-10-10 12:46:06,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 4587520. Throughput: 0: 1803.2, 1: 1807.3. Samples: 1149244. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:46:06,077][75634] Avg episode reward: [(0, '6.290'), (1, '7.800')] -[2023-10-10 12:46:07,662][76542] Updated weights for policy 1, policy_version 2250 (0.0008) -[2023-10-10 12:46:07,879][76543] Updated weights for policy 0, policy_version 2242 (0.0007) -[2023-10-10 12:46:08,023][76542] Updated weights for policy 1, policy_version 2260 (0.0009) -[2023-10-10 12:46:08,253][76543] Updated weights for policy 0, policy_version 2252 (0.0007) -[2023-10-10 12:46:08,395][76542] Updated weights for policy 1, policy_version 2270 (0.0009) -[2023-10-10 12:46:08,614][76543] Updated weights for policy 0, policy_version 2262 (0.0007) -[2023-10-10 12:46:08,992][76543] Updated weights for policy 0, policy_version 2272 (0.0008) -[2023-10-10 12:46:11,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 4653056. Throughput: 0: 1808.0, 1: 1796.0. Samples: 1170122. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:46:11,077][75634] Avg episode reward: [(0, '6.350'), (1, '7.760')] -[2023-10-10 12:46:12,315][76542] Updated weights for policy 1, policy_version 2280 (0.0009) -[2023-10-10 12:46:12,690][76542] Updated weights for policy 1, policy_version 2290 (0.0007) -[2023-10-10 12:46:12,724][76543] Updated weights for policy 0, policy_version 2282 (0.0007) -[2023-10-10 12:46:13,062][76542] Updated weights for policy 1, policy_version 2300 (0.0007) -[2023-10-10 12:46:13,107][76543] Updated weights for policy 0, policy_version 2292 (0.0008) -[2023-10-10 12:46:13,478][76543] Updated weights for policy 0, policy_version 2302 (0.0010) -[2023-10-10 12:46:16,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 4718592. Throughput: 0: 1809.8, 1: 1796.2. Samples: 1192262. Policy #0 lag: (min: 9.0, avg: 18.2, max: 41.0) -[2023-10-10 12:46:16,077][75634] Avg episode reward: [(0, '7.040'), (1, '8.020')] -[2023-10-10 12:46:16,864][76542] Updated weights for policy 1, policy_version 2310 (0.0009) -[2023-10-10 12:46:17,126][76543] Updated weights for policy 0, policy_version 2312 (0.0008) -[2023-10-10 12:46:17,239][76542] Updated weights for policy 1, policy_version 2320 (0.0008) -[2023-10-10 12:46:17,508][76543] Updated weights for policy 0, policy_version 2322 (0.0007) -[2023-10-10 12:46:17,600][76542] Updated weights for policy 1, policy_version 2330 (0.0007) -[2023-10-10 12:46:17,873][76543] Updated weights for policy 0, policy_version 2332 (0.0008) -[2023-10-10 12:46:21,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 4784128. Throughput: 0: 1816.0, 1: 1795.0. Samples: 1202246. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:46:21,077][75634] Avg episode reward: [(0, '7.370'), (1, '8.470')] -[2023-10-10 12:46:21,192][76542] Updated weights for policy 1, policy_version 2340 (0.0008) -[2023-10-10 12:46:21,553][76543] Updated weights for policy 0, policy_version 2342 (0.0011) -[2023-10-10 12:46:21,561][76542] Updated weights for policy 1, policy_version 2350 (0.0008) -[2023-10-10 12:46:21,915][76543] Updated weights for policy 0, policy_version 2352 (0.0009) -[2023-10-10 12:46:21,928][76542] Updated weights for policy 1, policy_version 2360 (0.0008) -[2023-10-10 12:46:22,217][76421] Saving new best policy, reward=8.470! -[2023-10-10 12:46:22,297][76543] Updated weights for policy 0, policy_version 2362 (0.0009) -[2023-10-10 12:46:25,587][76542] Updated weights for policy 1, policy_version 2370 (0.0007) -[2023-10-10 12:46:25,963][76542] Updated weights for policy 1, policy_version 2380 (0.0007) -[2023-10-10 12:46:26,049][76543] Updated weights for policy 0, policy_version 2372 (0.0007) -[2023-10-10 12:46:26,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 4849664. Throughput: 0: 1814.4, 1: 1797.0. Samples: 1225118. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:46:26,076][75634] Avg episode reward: [(0, '7.650'), (1, '7.790')] -[2023-10-10 12:46:26,334][76542] Updated weights for policy 1, policy_version 2390 (0.0007) -[2023-10-10 12:46:26,410][76543] Updated weights for policy 0, policy_version 2382 (0.0007) -[2023-10-10 12:46:26,699][76542] Updated weights for policy 1, policy_version 2400 (0.0009) -[2023-10-10 12:46:26,790][76543] Updated weights for policy 0, policy_version 2392 (0.0008) -[2023-10-10 12:46:30,424][76542] Updated weights for policy 1, policy_version 2410 (0.0007) -[2023-10-10 12:46:30,486][76543] Updated weights for policy 0, policy_version 2402 (0.0007) -[2023-10-10 12:46:30,785][76542] Updated weights for policy 1, policy_version 2420 (0.0007) -[2023-10-10 12:46:30,857][76543] Updated weights for policy 0, policy_version 2412 (0.0008) -[2023-10-10 12:46:31,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 4915200. Throughput: 0: 1815.8, 1: 1810.4. Samples: 1247198. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:46:31,077][75634] Avg episode reward: [(0, '7.290'), (1, '7.460')] -[2023-10-10 12:46:31,151][76542] Updated weights for policy 1, policy_version 2430 (0.0009) -[2023-10-10 12:46:31,222][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000002432_2490368.pth... -[2023-10-10 12:46:31,228][76543] Updated weights for policy 0, policy_version 2422 (0.0007) -[2023-10-10 12:46:31,251][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000000736_753664.pth -[2023-10-10 12:46:31,598][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000002432_2490368.pth... -[2023-10-10 12:46:31,599][76543] Updated weights for policy 0, policy_version 2432 (0.0009) -[2023-10-10 12:46:31,627][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000000736_753664.pth -[2023-10-10 12:46:34,684][76542] Updated weights for policy 1, policy_version 2440 (0.0007) -[2023-10-10 12:46:35,051][76542] Updated weights for policy 1, policy_version 2450 (0.0008) -[2023-10-10 12:46:35,301][76543] Updated weights for policy 0, policy_version 2442 (0.0007) -[2023-10-10 12:46:35,421][76542] Updated weights for policy 1, policy_version 2460 (0.0007) -[2023-10-10 12:46:35,681][76543] Updated weights for policy 0, policy_version 2452 (0.0009) -[2023-10-10 12:46:36,055][76543] Updated weights for policy 0, policy_version 2462 (0.0009) -[2023-10-10 12:46:36,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 5013504. Throughput: 0: 1819.6, 1: 1802.4. Samples: 1258042. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:46:36,077][75634] Avg episode reward: [(0, '6.350'), (1, '7.950')] -[2023-10-10 12:46:39,048][76542] Updated weights for policy 1, policy_version 2470 (0.0008) -[2023-10-10 12:46:39,406][76542] Updated weights for policy 1, policy_version 2480 (0.0009) -[2023-10-10 12:46:39,779][76542] Updated weights for policy 1, policy_version 2490 (0.0010) -[2023-10-10 12:46:39,799][76543] Updated weights for policy 0, policy_version 2472 (0.0009) -[2023-10-10 12:46:40,178][76543] Updated weights for policy 0, policy_version 2482 (0.0010) -[2023-10-10 12:46:40,550][76543] Updated weights for policy 0, policy_version 2492 (0.0009) -[2023-10-10 12:46:41,076][75634] Fps is (10 sec: 19661.1, 60 sec: 15291.7, 300 sec: 14551.2). Total num frames: 5111808. Throughput: 0: 1817.8, 1: 1812.8. Samples: 1279822. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:46:41,076][75634] Avg episode reward: [(0, '6.360'), (1, '7.680')] -[2023-10-10 12:46:43,431][76542] Updated weights for policy 1, policy_version 2500 (0.0009) -[2023-10-10 12:46:43,790][76542] Updated weights for policy 1, policy_version 2510 (0.0008) -[2023-10-10 12:46:44,163][76542] Updated weights for policy 1, policy_version 2520 (0.0007) -[2023-10-10 12:46:44,326][76543] Updated weights for policy 0, policy_version 2502 (0.0010) -[2023-10-10 12:46:44,696][76543] Updated weights for policy 0, policy_version 2512 (0.0010) -[2023-10-10 12:46:45,072][76543] Updated weights for policy 0, policy_version 2522 (0.0007) -[2023-10-10 12:46:46,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 5177344. Throughput: 0: 1818.6, 1: 1811.5. Samples: 1300960. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-10 12:46:46,077][75634] Avg episode reward: [(0, '6.340'), (1, '7.410')] -[2023-10-10 12:46:47,917][76542] Updated weights for policy 1, policy_version 2530 (0.0009) -[2023-10-10 12:46:48,283][76542] Updated weights for policy 1, policy_version 2540 (0.0007) -[2023-10-10 12:46:48,653][76542] Updated weights for policy 1, policy_version 2550 (0.0008) -[2023-10-10 12:46:48,909][76543] Updated weights for policy 0, policy_version 2532 (0.0008) -[2023-10-10 12:46:49,023][76542] Updated weights for policy 1, policy_version 2560 (0.0008) -[2023-10-10 12:46:49,282][76543] Updated weights for policy 0, policy_version 2542 (0.0009) -[2023-10-10 12:46:49,650][76543] Updated weights for policy 0, policy_version 2552 (0.0008) -[2023-10-10 12:46:51,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 5242880. Throughput: 0: 1813.0, 1: 1815.9. Samples: 1312546. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:46:51,077][75634] Avg episode reward: [(0, '6.440'), (1, '7.400')] -[2023-10-10 12:46:52,710][76542] Updated weights for policy 1, policy_version 2570 (0.0007) -[2023-10-10 12:46:53,081][76542] Updated weights for policy 1, policy_version 2580 (0.0010) -[2023-10-10 12:46:53,305][76543] Updated weights for policy 0, policy_version 2562 (0.0007) -[2023-10-10 12:46:53,443][76542] Updated weights for policy 1, policy_version 2590 (0.0008) -[2023-10-10 12:46:53,685][76543] Updated weights for policy 0, policy_version 2572 (0.0007) -[2023-10-10 12:46:54,056][76543] Updated weights for policy 0, policy_version 2582 (0.0009) -[2023-10-10 12:46:54,430][76543] Updated weights for policy 0, policy_version 2592 (0.0011) -[2023-10-10 12:46:56,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 5308416. Throughput: 0: 1814.3, 1: 1817.6. Samples: 1333556. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:46:56,077][75634] Avg episode reward: [(0, '6.460'), (1, '7.920')] -[2023-10-10 12:46:57,149][76542] Updated weights for policy 1, policy_version 2600 (0.0008) -[2023-10-10 12:46:57,521][76542] Updated weights for policy 1, policy_version 2610 (0.0008) -[2023-10-10 12:46:57,893][76542] Updated weights for policy 1, policy_version 2620 (0.0008) -[2023-10-10 12:46:58,114][76543] Updated weights for policy 0, policy_version 2602 (0.0008) -[2023-10-10 12:46:58,490][76543] Updated weights for policy 0, policy_version 2612 (0.0008) -[2023-10-10 12:46:58,868][76543] Updated weights for policy 0, policy_version 2622 (0.0007) -[2023-10-10 12:47:01,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 5373952. Throughput: 0: 1811.0, 1: 1821.7. Samples: 1355734. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-10-10 12:47:01,077][75634] Avg episode reward: [(0, '7.020'), (1, '7.870')] -[2023-10-10 12:47:01,728][76542] Updated weights for policy 1, policy_version 2630 (0.0010) -[2023-10-10 12:47:02,092][76542] Updated weights for policy 1, policy_version 2640 (0.0010) -[2023-10-10 12:47:02,461][76542] Updated weights for policy 1, policy_version 2650 (0.0009) -[2023-10-10 12:47:02,496][76543] Updated weights for policy 0, policy_version 2632 (0.0009) -[2023-10-10 12:47:02,872][76543] Updated weights for policy 0, policy_version 2642 (0.0009) -[2023-10-10 12:47:03,248][76543] Updated weights for policy 0, policy_version 2652 (0.0008) -[2023-10-10 12:47:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 5439488. Throughput: 0: 1816.2, 1: 1822.0. Samples: 1365968. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-10-10 12:47:06,077][75634] Avg episode reward: [(0, '7.860'), (1, '8.540')] -[2023-10-10 12:47:06,078][76362] Saving new best policy, reward=7.860! -[2023-10-10 12:47:06,172][76542] Updated weights for policy 1, policy_version 2660 (0.0009) -[2023-10-10 12:47:06,548][76542] Updated weights for policy 1, policy_version 2670 (0.0008) -[2023-10-10 12:47:06,918][76542] Updated weights for policy 1, policy_version 2680 (0.0009) -[2023-10-10 12:47:06,946][76543] Updated weights for policy 0, policy_version 2662 (0.0008) -[2023-10-10 12:47:07,212][76421] Saving new best policy, reward=8.540! -[2023-10-10 12:47:07,317][76543] Updated weights for policy 0, policy_version 2672 (0.0011) -[2023-10-10 12:47:07,698][76543] Updated weights for policy 0, policy_version 2682 (0.0008) -[2023-10-10 12:47:10,728][76542] Updated weights for policy 1, policy_version 2690 (0.0009) -[2023-10-10 12:47:11,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 5505024. Throughput: 0: 1811.4, 1: 1819.0. Samples: 1388484. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-10 12:47:11,076][75634] Avg episode reward: [(0, '8.430'), (1, '8.690')] -[2023-10-10 12:47:11,077][76362] Saving new best policy, reward=8.430! -[2023-10-10 12:47:11,104][76542] Updated weights for policy 1, policy_version 2700 (0.0008) -[2023-10-10 12:47:11,471][76542] Updated weights for policy 1, policy_version 2710 (0.0008) -[2023-10-10 12:47:11,545][76543] Updated weights for policy 0, policy_version 2692 (0.0010) -[2023-10-10 12:47:11,837][76421] Saving new best policy, reward=8.690! -[2023-10-10 12:47:11,841][76542] Updated weights for policy 1, policy_version 2720 (0.0007) -[2023-10-10 12:47:11,929][76543] Updated weights for policy 0, policy_version 2702 (0.0009) -[2023-10-10 12:47:12,293][76543] Updated weights for policy 0, policy_version 2712 (0.0008) -[2023-10-10 12:47:15,513][76542] Updated weights for policy 1, policy_version 2730 (0.0009) -[2023-10-10 12:47:15,880][76542] Updated weights for policy 1, policy_version 2740 (0.0009) -[2023-10-10 12:47:15,910][76543] Updated weights for policy 0, policy_version 2722 (0.0009) -[2023-10-10 12:47:16,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 5570560. Throughput: 0: 1804.8, 1: 1826.6. Samples: 1410612. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-10 12:47:16,076][75634] Avg episode reward: [(0, '8.670'), (1, '9.070')] -[2023-10-10 12:47:16,254][76542] Updated weights for policy 1, policy_version 2750 (0.0009) -[2023-10-10 12:47:16,290][76543] Updated weights for policy 0, policy_version 2732 (0.0007) -[2023-10-10 12:47:16,320][76421] Saving new best policy, reward=9.070! -[2023-10-10 12:47:16,667][76543] Updated weights for policy 0, policy_version 2742 (0.0008) -[2023-10-10 12:47:17,035][76362] Saving new best policy, reward=8.670! -[2023-10-10 12:47:17,036][76543] Updated weights for policy 0, policy_version 2752 (0.0007) -[2023-10-10 12:47:20,003][76542] Updated weights for policy 1, policy_version 2760 (0.0010) -[2023-10-10 12:47:20,371][76542] Updated weights for policy 1, policy_version 2770 (0.0010) -[2023-10-10 12:47:20,736][76542] Updated weights for policy 1, policy_version 2780 (0.0008) -[2023-10-10 12:47:20,745][76543] Updated weights for policy 0, policy_version 2762 (0.0008) -[2023-10-10 12:47:21,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 5668864. Throughput: 0: 1805.8, 1: 1820.3. Samples: 1421214. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-10 12:47:21,077][75634] Avg episode reward: [(0, '8.820'), (1, '8.740')] -[2023-10-10 12:47:21,130][76543] Updated weights for policy 0, policy_version 2772 (0.0009) -[2023-10-10 12:47:21,502][76543] Updated weights for policy 0, policy_version 2782 (0.0009) -[2023-10-10 12:47:21,577][76362] Saving new best policy, reward=8.820! -[2023-10-10 12:47:24,479][76542] Updated weights for policy 1, policy_version 2790 (0.0008) -[2023-10-10 12:47:24,858][76542] Updated weights for policy 1, policy_version 2800 (0.0010) -[2023-10-10 12:47:25,169][76543] Updated weights for policy 0, policy_version 2792 (0.0009) -[2023-10-10 12:47:25,220][76542] Updated weights for policy 1, policy_version 2810 (0.0008) -[2023-10-10 12:47:25,538][76543] Updated weights for policy 0, policy_version 2802 (0.0008) -[2023-10-10 12:47:25,910][76543] Updated weights for policy 0, policy_version 2812 (0.0009) -[2023-10-10 12:47:26,076][75634] Fps is (10 sec: 19660.9, 60 sec: 15291.7, 300 sec: 14551.2). Total num frames: 5767168. Throughput: 0: 1807.0, 1: 1819.5. Samples: 1443016. Policy #0 lag: (min: 25.0, avg: 31.4, max: 57.0) -[2023-10-10 12:47:26,076][75634] Avg episode reward: [(0, '8.620'), (1, '8.620')] -[2023-10-10 12:47:28,956][76542] Updated weights for policy 1, policy_version 2820 (0.0009) -[2023-10-10 12:47:29,330][76542] Updated weights for policy 1, policy_version 2830 (0.0010) -[2023-10-10 12:47:29,664][76543] Updated weights for policy 0, policy_version 2822 (0.0008) -[2023-10-10 12:47:29,690][76542] Updated weights for policy 1, policy_version 2840 (0.0009) -[2023-10-10 12:47:30,027][76543] Updated weights for policy 0, policy_version 2832 (0.0008) -[2023-10-10 12:47:30,408][76543] Updated weights for policy 0, policy_version 2842 (0.0007) -[2023-10-10 12:47:31,076][75634] Fps is (10 sec: 16384.0, 60 sec: 15291.7, 300 sec: 14440.1). Total num frames: 5832704. Throughput: 0: 1813.7, 1: 1807.4. Samples: 1463910. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) -[2023-10-10 12:47:31,077][75634] Avg episode reward: [(0, '8.390'), (1, '8.400')] -[2023-10-10 12:47:33,396][76542] Updated weights for policy 1, policy_version 2850 (0.0008) -[2023-10-10 12:47:33,763][76542] Updated weights for policy 1, policy_version 2860 (0.0007) -[2023-10-10 12:47:34,125][76542] Updated weights for policy 1, policy_version 2870 (0.0007) -[2023-10-10 12:47:34,207][76543] Updated weights for policy 0, policy_version 2852 (0.0009) -[2023-10-10 12:47:34,494][76542] Updated weights for policy 1, policy_version 2880 (0.0010) -[2023-10-10 12:47:34,570][76543] Updated weights for policy 0, policy_version 2862 (0.0009) -[2023-10-10 12:47:34,947][76543] Updated weights for policy 0, policy_version 2872 (0.0008) -[2023-10-10 12:47:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 5898240. Throughput: 0: 1802.0, 1: 1820.0. Samples: 1475540. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) -[2023-10-10 12:47:36,076][75634] Avg episode reward: [(0, '8.480'), (1, '8.790')] -[2023-10-10 12:47:38,024][76542] Updated weights for policy 1, policy_version 2890 (0.0007) -[2023-10-10 12:47:38,387][76542] Updated weights for policy 1, policy_version 2900 (0.0008) -[2023-10-10 12:47:38,547][76543] Updated weights for policy 0, policy_version 2882 (0.0007) -[2023-10-10 12:47:38,766][76542] Updated weights for policy 1, policy_version 2910 (0.0007) -[2023-10-10 12:47:38,934][76543] Updated weights for policy 0, policy_version 2892 (0.0009) -[2023-10-10 12:47:39,313][76543] Updated weights for policy 0, policy_version 2902 (0.0011) -[2023-10-10 12:47:39,687][76543] Updated weights for policy 0, policy_version 2912 (0.0009) -[2023-10-10 12:47:41,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 5963776. Throughput: 0: 1806.2, 1: 1812.5. Samples: 1496396. Policy #0 lag: (min: 15.0, avg: 18.6, max: 47.0) -[2023-10-10 12:47:41,077][75634] Avg episode reward: [(0, '8.520'), (1, '8.810')] -[2023-10-10 12:47:42,434][76542] Updated weights for policy 1, policy_version 2920 (0.0009) -[2023-10-10 12:47:42,801][76542] Updated weights for policy 1, policy_version 2930 (0.0008) -[2023-10-10 12:47:43,172][76542] Updated weights for policy 1, policy_version 2940 (0.0008) -[2023-10-10 12:47:43,328][76543] Updated weights for policy 0, policy_version 2922 (0.0009) -[2023-10-10 12:47:43,713][76543] Updated weights for policy 0, policy_version 2932 (0.0008) -[2023-10-10 12:47:44,100][76543] Updated weights for policy 0, policy_version 2942 (0.0010) -[2023-10-10 12:47:46,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 6029312. Throughput: 0: 1800.6, 1: 1817.9. Samples: 1518566. Policy #0 lag: (min: 3.0, avg: 10.4, max: 35.0) -[2023-10-10 12:47:46,076][75634] Avg episode reward: [(0, '9.030'), (1, '8.900')] -[2023-10-10 12:47:46,088][76362] Saving new best policy, reward=9.030! -[2023-10-10 12:47:46,795][76542] Updated weights for policy 1, policy_version 2950 (0.0008) -[2023-10-10 12:47:47,167][76542] Updated weights for policy 1, policy_version 2960 (0.0009) -[2023-10-10 12:47:47,541][76542] Updated weights for policy 1, policy_version 2970 (0.0008) -[2023-10-10 12:47:47,854][76543] Updated weights for policy 0, policy_version 2952 (0.0010) -[2023-10-10 12:47:48,219][76543] Updated weights for policy 0, policy_version 2962 (0.0008) -[2023-10-10 12:47:48,592][76543] Updated weights for policy 0, policy_version 2972 (0.0008) -[2023-10-10 12:47:51,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 6094848. Throughput: 0: 1809.3, 1: 1819.8. Samples: 1529278. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-10-10 12:47:51,077][75634] Avg episode reward: [(0, '9.110'), (1, '8.530')] -[2023-10-10 12:47:51,078][76362] Saving new best policy, reward=9.110! -[2023-10-10 12:47:51,278][76542] Updated weights for policy 1, policy_version 2980 (0.0008) -[2023-10-10 12:47:51,647][76542] Updated weights for policy 1, policy_version 2990 (0.0010) -[2023-10-10 12:47:52,025][76542] Updated weights for policy 1, policy_version 3000 (0.0009) -[2023-10-10 12:47:52,499][76543] Updated weights for policy 0, policy_version 2982 (0.0009) -[2023-10-10 12:47:52,871][76543] Updated weights for policy 0, policy_version 2992 (0.0010) -[2023-10-10 12:47:53,237][76543] Updated weights for policy 0, policy_version 3002 (0.0010) -[2023-10-10 12:47:55,833][76542] Updated weights for policy 1, policy_version 3010 (0.0009) -[2023-10-10 12:47:56,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 6160384. Throughput: 0: 1800.4, 1: 1816.3. Samples: 1551232. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-10-10 12:47:56,076][75634] Avg episode reward: [(0, '8.780'), (1, '7.920')] -[2023-10-10 12:47:56,202][76542] Updated weights for policy 1, policy_version 3020 (0.0012) -[2023-10-10 12:47:56,570][76542] Updated weights for policy 1, policy_version 3030 (0.0011) -[2023-10-10 12:47:56,943][76542] Updated weights for policy 1, policy_version 3040 (0.0008) -[2023-10-10 12:47:56,979][76543] Updated weights for policy 0, policy_version 3012 (0.0010) -[2023-10-10 12:47:57,358][76543] Updated weights for policy 0, policy_version 3022 (0.0008) -[2023-10-10 12:47:57,728][76543] Updated weights for policy 0, policy_version 3032 (0.0007) -[2023-10-10 12:48:00,667][76542] Updated weights for policy 1, policy_version 3050 (0.0011) -[2023-10-10 12:48:01,029][76542] Updated weights for policy 1, policy_version 3060 (0.0011) -[2023-10-10 12:48:01,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 6225920. Throughput: 0: 1804.6, 1: 1815.4. Samples: 1573514. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:48:01,076][75634] Avg episode reward: [(0, '8.290'), (1, '8.210')] -[2023-10-10 12:48:01,357][76543] Updated weights for policy 0, policy_version 3042 (0.0007) -[2023-10-10 12:48:01,397][76542] Updated weights for policy 1, policy_version 3070 (0.0008) -[2023-10-10 12:48:01,734][76543] Updated weights for policy 0, policy_version 3052 (0.0010) -[2023-10-10 12:48:02,097][76543] Updated weights for policy 0, policy_version 3062 (0.0009) -[2023-10-10 12:48:02,469][76543] Updated weights for policy 0, policy_version 3072 (0.0011) -[2023-10-10 12:48:05,027][76542] Updated weights for policy 1, policy_version 3080 (0.0008) -[2023-10-10 12:48:05,389][76542] Updated weights for policy 1, policy_version 3090 (0.0009) -[2023-10-10 12:48:05,766][76542] Updated weights for policy 1, policy_version 3100 (0.0009) -[2023-10-10 12:48:06,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 6324224. Throughput: 0: 1802.5, 1: 1815.4. Samples: 1584016. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:48:06,076][75634] Avg episode reward: [(0, '7.310'), (1, '8.380')] -[2023-10-10 12:48:06,423][76543] Updated weights for policy 0, policy_version 3082 (0.0008) -[2023-10-10 12:48:06,786][76543] Updated weights for policy 0, policy_version 3092 (0.0007) -[2023-10-10 12:48:07,162][76543] Updated weights for policy 0, policy_version 3102 (0.0007) -[2023-10-10 12:48:09,422][76542] Updated weights for policy 1, policy_version 3110 (0.0008) -[2023-10-10 12:48:09,784][76542] Updated weights for policy 1, policy_version 3120 (0.0008) -[2023-10-10 12:48:10,155][76542] Updated weights for policy 1, policy_version 3130 (0.0010) -[2023-10-10 12:48:10,644][76543] Updated weights for policy 0, policy_version 3112 (0.0008) -[2023-10-10 12:48:11,016][76543] Updated weights for policy 0, policy_version 3122 (0.0008) -[2023-10-10 12:48:11,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 6389760. Throughput: 0: 1799.7, 1: 1826.8. Samples: 1606206. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-10 12:48:11,076][75634] Avg episode reward: [(0, '7.290'), (1, '8.410')] -[2023-10-10 12:48:11,386][76543] Updated weights for policy 0, policy_version 3132 (0.0007) -[2023-10-10 12:48:13,885][76542] Updated weights for policy 1, policy_version 3140 (0.0009) -[2023-10-10 12:48:14,254][76542] Updated weights for policy 1, policy_version 3150 (0.0007) -[2023-10-10 12:48:14,623][76542] Updated weights for policy 1, policy_version 3160 (0.0009) -[2023-10-10 12:48:14,953][76543] Updated weights for policy 0, policy_version 3142 (0.0007) -[2023-10-10 12:48:15,330][76543] Updated weights for policy 0, policy_version 3152 (0.0008) -[2023-10-10 12:48:15,696][76543] Updated weights for policy 0, policy_version 3162 (0.0009) -[2023-10-10 12:48:16,076][75634] Fps is (10 sec: 16383.9, 60 sec: 15291.7, 300 sec: 14551.2). Total num frames: 6488064. Throughput: 0: 1816.7, 1: 1826.2. Samples: 1627840. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-10 12:48:16,076][75634] Avg episode reward: [(0, '7.350'), (1, '8.770')] -[2023-10-10 12:48:18,305][76542] Updated weights for policy 1, policy_version 3170 (0.0008) -[2023-10-10 12:48:18,674][76542] Updated weights for policy 1, policy_version 3180 (0.0009) -[2023-10-10 12:48:19,033][76542] Updated weights for policy 1, policy_version 3190 (0.0009) -[2023-10-10 12:48:19,403][76542] Updated weights for policy 1, policy_version 3200 (0.0008) -[2023-10-10 12:48:19,467][76543] Updated weights for policy 0, policy_version 3172 (0.0008) -[2023-10-10 12:48:19,848][76543] Updated weights for policy 0, policy_version 3182 (0.0007) -[2023-10-10 12:48:20,220][76543] Updated weights for policy 0, policy_version 3192 (0.0007) -[2023-10-10 12:48:21,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 6553600. Throughput: 0: 1811.7, 1: 1822.0. Samples: 1639060. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 12:48:21,077][75634] Avg episode reward: [(0, '8.170'), (1, '8.590')] -[2023-10-10 12:48:23,304][76542] Updated weights for policy 1, policy_version 3210 (0.0007) -[2023-10-10 12:48:23,676][76542] Updated weights for policy 1, policy_version 3220 (0.0008) -[2023-10-10 12:48:23,735][76543] Updated weights for policy 0, policy_version 3202 (0.0007) -[2023-10-10 12:48:24,039][76542] Updated weights for policy 1, policy_version 3230 (0.0008) -[2023-10-10 12:48:24,121][76543] Updated weights for policy 0, policy_version 3212 (0.0009) -[2023-10-10 12:48:24,491][76543] Updated weights for policy 0, policy_version 3222 (0.0012) -[2023-10-10 12:48:24,860][76543] Updated weights for policy 0, policy_version 3232 (0.0009) -[2023-10-10 12:48:26,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 6619136. Throughput: 0: 1824.3, 1: 1815.0. Samples: 1660164. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 12:48:26,077][75634] Avg episode reward: [(0, '8.720'), (1, '8.920')] -[2023-10-10 12:48:27,667][76542] Updated weights for policy 1, policy_version 3240 (0.0007) -[2023-10-10 12:48:28,040][76542] Updated weights for policy 1, policy_version 3250 (0.0008) -[2023-10-10 12:48:28,412][76542] Updated weights for policy 1, policy_version 3260 (0.0008) -[2023-10-10 12:48:28,690][76543] Updated weights for policy 0, policy_version 3242 (0.0008) -[2023-10-10 12:48:29,071][76543] Updated weights for policy 0, policy_version 3252 (0.0008) -[2023-10-10 12:48:29,438][76543] Updated weights for policy 0, policy_version 3262 (0.0011) -[2023-10-10 12:48:31,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 6684672. Throughput: 0: 1816.7, 1: 1811.8. Samples: 1681848. Policy #0 lag: (min: 19.0, avg: 20.7, max: 46.0) -[2023-10-10 12:48:31,077][75634] Avg episode reward: [(0, '9.040'), (1, '9.040')] -[2023-10-10 12:48:31,089][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000003264_3342336.pth... -[2023-10-10 12:48:31,089][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000003264_3342336.pth... -[2023-10-10 12:48:31,119][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000001568_1605632.pth -[2023-10-10 12:48:31,127][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000001568_1605632.pth -[2023-10-10 12:48:32,148][76542] Updated weights for policy 1, policy_version 3270 (0.0010) -[2023-10-10 12:48:32,515][76542] Updated weights for policy 1, policy_version 3280 (0.0008) -[2023-10-10 12:48:32,884][76542] Updated weights for policy 1, policy_version 3290 (0.0009) -[2023-10-10 12:48:33,158][76543] Updated weights for policy 0, policy_version 3272 (0.0007) -[2023-10-10 12:48:33,535][76543] Updated weights for policy 0, policy_version 3282 (0.0010) -[2023-10-10 12:48:33,913][76543] Updated weights for policy 0, policy_version 3292 (0.0008) -[2023-10-10 12:48:36,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 6750208. Throughput: 0: 1822.8, 1: 1809.9. Samples: 1692748. Policy #0 lag: (min: 19.0, avg: 20.7, max: 46.0) -[2023-10-10 12:48:36,076][75634] Avg episode reward: [(0, '9.610'), (1, '9.640')] -[2023-10-10 12:48:36,077][76362] Saving new best policy, reward=9.610! -[2023-10-10 12:48:36,077][76421] Saving new best policy, reward=9.640! -[2023-10-10 12:48:36,424][76542] Updated weights for policy 1, policy_version 3300 (0.0007) -[2023-10-10 12:48:36,792][76542] Updated weights for policy 1, policy_version 3310 (0.0010) -[2023-10-10 12:48:37,165][76542] Updated weights for policy 1, policy_version 3320 (0.0008) -[2023-10-10 12:48:37,498][76543] Updated weights for policy 0, policy_version 3302 (0.0007) -[2023-10-10 12:48:37,868][76543] Updated weights for policy 0, policy_version 3312 (0.0008) -[2023-10-10 12:48:38,252][76543] Updated weights for policy 0, policy_version 3322 (0.0007) -[2023-10-10 12:48:40,734][76542] Updated weights for policy 1, policy_version 3330 (0.0009) -[2023-10-10 12:48:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 6815744. Throughput: 0: 1818.3, 1: 1817.7. Samples: 1714850. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-10 12:48:41,077][75634] Avg episode reward: [(0, '9.240'), (1, '9.690')] -[2023-10-10 12:48:41,104][76542] Updated weights for policy 1, policy_version 3340 (0.0009) -[2023-10-10 12:48:41,477][76542] Updated weights for policy 1, policy_version 3350 (0.0009) -[2023-10-10 12:48:41,846][76421] Saving new best policy, reward=9.690! -[2023-10-10 12:48:41,846][76542] Updated weights for policy 1, policy_version 3360 (0.0008) -[2023-10-10 12:48:41,975][76543] Updated weights for policy 0, policy_version 3332 (0.0008) -[2023-10-10 12:48:42,345][76543] Updated weights for policy 0, policy_version 3342 (0.0009) -[2023-10-10 12:48:42,713][76543] Updated weights for policy 0, policy_version 3352 (0.0008) -[2023-10-10 12:48:45,591][76542] Updated weights for policy 1, policy_version 3370 (0.0010) -[2023-10-10 12:48:45,961][76542] Updated weights for policy 1, policy_version 3380 (0.0008) -[2023-10-10 12:48:46,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 6881280. Throughput: 0: 1819.7, 1: 1817.5. Samples: 1737190. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-10 12:48:46,077][75634] Avg episode reward: [(0, '8.440'), (1, '10.040')] -[2023-10-10 12:48:46,275][76543] Updated weights for policy 0, policy_version 3362 (0.0009) -[2023-10-10 12:48:46,328][76542] Updated weights for policy 1, policy_version 3390 (0.0007) -[2023-10-10 12:48:46,402][76421] Saving new best policy, reward=10.040! -[2023-10-10 12:48:46,651][76543] Updated weights for policy 0, policy_version 3372 (0.0008) -[2023-10-10 12:48:47,023][76543] Updated weights for policy 0, policy_version 3382 (0.0008) -[2023-10-10 12:48:47,392][76543] Updated weights for policy 0, policy_version 3392 (0.0009) -[2023-10-10 12:48:50,029][76542] Updated weights for policy 1, policy_version 3400 (0.0011) -[2023-10-10 12:48:50,396][76542] Updated weights for policy 1, policy_version 3410 (0.0008) -[2023-10-10 12:48:50,773][76542] Updated weights for policy 1, policy_version 3420 (0.0007) -[2023-10-10 12:48:51,063][76543] Updated weights for policy 0, policy_version 3402 (0.0010) -[2023-10-10 12:48:51,076][75634] Fps is (10 sec: 16384.5, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 6979584. Throughput: 0: 1820.3, 1: 1817.2. Samples: 1747704. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:48:51,076][75634] Avg episode reward: [(0, '8.530'), (1, '10.220')] -[2023-10-10 12:48:51,077][76421] Saving new best policy, reward=10.220! -[2023-10-10 12:48:51,443][76543] Updated weights for policy 0, policy_version 3412 (0.0007) -[2023-10-10 12:48:51,817][76543] Updated weights for policy 0, policy_version 3422 (0.0007) -[2023-10-10 12:48:54,461][76542] Updated weights for policy 1, policy_version 3430 (0.0008) -[2023-10-10 12:48:54,829][76542] Updated weights for policy 1, policy_version 3440 (0.0007) -[2023-10-10 12:48:55,209][76542] Updated weights for policy 1, policy_version 3450 (0.0008) -[2023-10-10 12:48:55,552][76543] Updated weights for policy 0, policy_version 3432 (0.0007) -[2023-10-10 12:48:55,928][76543] Updated weights for policy 0, policy_version 3442 (0.0008) -[2023-10-10 12:48:56,076][75634] Fps is (10 sec: 16384.6, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 7045120. Throughput: 0: 1822.6, 1: 1813.3. Samples: 1769822. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:48:56,076][75634] Avg episode reward: [(0, '8.190'), (1, '9.050')] -[2023-10-10 12:48:56,304][76543] Updated weights for policy 0, policy_version 3452 (0.0008) -[2023-10-10 12:48:58,718][76542] Updated weights for policy 1, policy_version 3460 (0.0007) -[2023-10-10 12:48:59,090][76542] Updated weights for policy 1, policy_version 3470 (0.0009) -[2023-10-10 12:48:59,458][76542] Updated weights for policy 1, policy_version 3480 (0.0010) -[2023-10-10 12:48:59,920][76543] Updated weights for policy 0, policy_version 3462 (0.0008) -[2023-10-10 12:49:00,298][76543] Updated weights for policy 0, policy_version 3472 (0.0009) -[2023-10-10 12:49:00,673][76543] Updated weights for policy 0, policy_version 3482 (0.0008) -[2023-10-10 12:49:01,076][75634] Fps is (10 sec: 16383.8, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 7143424. Throughput: 0: 1816.3, 1: 1814.2. Samples: 1791212. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:49:01,077][75634] Avg episode reward: [(0, '8.900'), (1, '9.410')] -[2023-10-10 12:49:03,194][76542] Updated weights for policy 1, policy_version 3490 (0.0010) -[2023-10-10 12:49:03,563][76542] Updated weights for policy 1, policy_version 3500 (0.0009) -[2023-10-10 12:49:03,925][76542] Updated weights for policy 1, policy_version 3510 (0.0009) -[2023-10-10 12:49:04,292][76542] Updated weights for policy 1, policy_version 3520 (0.0009) -[2023-10-10 12:49:04,338][76543] Updated weights for policy 0, policy_version 3492 (0.0009) -[2023-10-10 12:49:04,709][76543] Updated weights for policy 0, policy_version 3502 (0.0010) -[2023-10-10 12:49:05,083][76543] Updated weights for policy 0, policy_version 3512 (0.0010) -[2023-10-10 12:49:06,076][75634] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 7208960. Throughput: 0: 1816.6, 1: 1818.4. Samples: 1802636. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-10 12:49:06,077][75634] Avg episode reward: [(0, '8.450'), (1, '9.620')] -[2023-10-10 12:49:08,074][76542] Updated weights for policy 1, policy_version 3530 (0.0009) -[2023-10-10 12:49:08,445][76542] Updated weights for policy 1, policy_version 3540 (0.0008) -[2023-10-10 12:49:08,808][76542] Updated weights for policy 1, policy_version 3550 (0.0008) -[2023-10-10 12:49:08,970][76543] Updated weights for policy 0, policy_version 3522 (0.0008) -[2023-10-10 12:49:09,338][76543] Updated weights for policy 0, policy_version 3532 (0.0009) -[2023-10-10 12:49:09,713][76543] Updated weights for policy 0, policy_version 3542 (0.0009) -[2023-10-10 12:49:10,083][76543] Updated weights for policy 0, policy_version 3552 (0.0011) -[2023-10-10 12:49:11,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 7274496. Throughput: 0: 1815.6, 1: 1826.1. Samples: 1824040. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-10 12:49:11,077][75634] Avg episode reward: [(0, '8.810'), (1, '8.920')] -[2023-10-10 12:49:12,655][76542] Updated weights for policy 1, policy_version 3560 (0.0009) -[2023-10-10 12:49:13,036][76542] Updated weights for policy 1, policy_version 3570 (0.0010) -[2023-10-10 12:49:13,405][76542] Updated weights for policy 1, policy_version 3580 (0.0007) -[2023-10-10 12:49:13,879][76543] Updated weights for policy 0, policy_version 3562 (0.0009) -[2023-10-10 12:49:14,262][76543] Updated weights for policy 0, policy_version 3572 (0.0011) -[2023-10-10 12:49:14,628][76543] Updated weights for policy 0, policy_version 3582 (0.0012) -[2023-10-10 12:49:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 7340032. Throughput: 0: 1811.5, 1: 1819.3. Samples: 1845236. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-10-10 12:49:16,077][75634] Avg episode reward: [(0, '9.710'), (1, '9.540')] -[2023-10-10 12:49:16,087][76362] Saving new best policy, reward=9.710! -[2023-10-10 12:49:17,098][76542] Updated weights for policy 1, policy_version 3590 (0.0008) -[2023-10-10 12:49:17,471][76542] Updated weights for policy 1, policy_version 3600 (0.0008) -[2023-10-10 12:49:17,842][76542] Updated weights for policy 1, policy_version 3610 (0.0008) -[2023-10-10 12:49:18,246][76543] Updated weights for policy 0, policy_version 3592 (0.0009) -[2023-10-10 12:49:18,632][76543] Updated weights for policy 0, policy_version 3602 (0.0009) -[2023-10-10 12:49:18,997][76543] Updated weights for policy 0, policy_version 3612 (0.0008) -[2023-10-10 12:49:21,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 7405568. Throughput: 0: 1818.8, 1: 1816.9. Samples: 1856354. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-10-10 12:49:21,076][75634] Avg episode reward: [(0, '9.180'), (1, '9.040')] -[2023-10-10 12:49:21,445][76542] Updated weights for policy 1, policy_version 3620 (0.0008) -[2023-10-10 12:49:21,810][76542] Updated weights for policy 1, policy_version 3630 (0.0009) -[2023-10-10 12:49:22,179][76542] Updated weights for policy 1, policy_version 3640 (0.0009) -[2023-10-10 12:49:22,638][76543] Updated weights for policy 0, policy_version 3622 (0.0010) -[2023-10-10 12:49:23,004][76543] Updated weights for policy 0, policy_version 3632 (0.0008) -[2023-10-10 12:49:23,374][76543] Updated weights for policy 0, policy_version 3642 (0.0007) -[2023-10-10 12:49:25,930][76542] Updated weights for policy 1, policy_version 3650 (0.0009) -[2023-10-10 12:49:26,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.2). Total num frames: 7471104. Throughput: 0: 1812.3, 1: 1811.0. Samples: 1877896. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 12:49:26,076][75634] Avg episode reward: [(0, '8.560'), (1, '8.320')] -[2023-10-10 12:49:26,293][76542] Updated weights for policy 1, policy_version 3660 (0.0010) -[2023-10-10 12:49:26,665][76542] Updated weights for policy 1, policy_version 3670 (0.0009) -[2023-10-10 12:49:27,024][76542] Updated weights for policy 1, policy_version 3680 (0.0008) -[2023-10-10 12:49:27,124][76543] Updated weights for policy 0, policy_version 3652 (0.0008) -[2023-10-10 12:49:27,490][76543] Updated weights for policy 0, policy_version 3662 (0.0009) -[2023-10-10 12:49:27,874][76543] Updated weights for policy 0, policy_version 3672 (0.0008) -[2023-10-10 12:49:30,604][76542] Updated weights for policy 1, policy_version 3690 (0.0008) -[2023-10-10 12:49:30,978][76542] Updated weights for policy 1, policy_version 3700 (0.0011) -[2023-10-10 12:49:31,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 7536640. Throughput: 0: 1809.5, 1: 1816.8. Samples: 1900374. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 12:49:31,077][75634] Avg episode reward: [(0, '8.310'), (1, '8.820')] -[2023-10-10 12:49:31,348][76542] Updated weights for policy 1, policy_version 3710 (0.0008) -[2023-10-10 12:49:31,391][76543] Updated weights for policy 0, policy_version 3682 (0.0010) -[2023-10-10 12:49:31,760][76543] Updated weights for policy 0, policy_version 3692 (0.0007) -[2023-10-10 12:49:32,139][76543] Updated weights for policy 0, policy_version 3702 (0.0010) -[2023-10-10 12:49:32,510][76543] Updated weights for policy 0, policy_version 3712 (0.0010) -[2023-10-10 12:49:35,132][76542] Updated weights for policy 1, policy_version 3720 (0.0009) -[2023-10-10 12:49:35,498][76542] Updated weights for policy 1, policy_version 3730 (0.0010) -[2023-10-10 12:49:35,869][76542] Updated weights for policy 1, policy_version 3740 (0.0008) -[2023-10-10 12:49:36,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 7634944. Throughput: 0: 1810.6, 1: 1811.4. Samples: 1910692. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-10 12:49:36,076][75634] Avg episode reward: [(0, '7.920'), (1, '7.960')] -[2023-10-10 12:49:36,275][76543] Updated weights for policy 0, policy_version 3722 (0.0008) -[2023-10-10 12:49:36,657][76543] Updated weights for policy 0, policy_version 3732 (0.0007) -[2023-10-10 12:49:37,023][76543] Updated weights for policy 0, policy_version 3742 (0.0008) -[2023-10-10 12:49:39,511][76542] Updated weights for policy 1, policy_version 3750 (0.0009) -[2023-10-10 12:49:39,879][76542] Updated weights for policy 1, policy_version 3760 (0.0012) -[2023-10-10 12:49:40,251][76542] Updated weights for policy 1, policy_version 3770 (0.0011) -[2023-10-10 12:49:40,593][76543] Updated weights for policy 0, policy_version 3752 (0.0008) -[2023-10-10 12:49:40,976][76543] Updated weights for policy 0, policy_version 3762 (0.0010) -[2023-10-10 12:49:41,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 7700480. Throughput: 0: 1813.7, 1: 1813.6. Samples: 1933050. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-10 12:49:41,076][75634] Avg episode reward: [(0, '8.490'), (1, '8.830')] -[2023-10-10 12:49:41,344][76543] Updated weights for policy 0, policy_version 3772 (0.0008) -[2023-10-10 12:49:44,042][76542] Updated weights for policy 1, policy_version 3780 (0.0008) -[2023-10-10 12:49:44,407][76542] Updated weights for policy 1, policy_version 3790 (0.0008) -[2023-10-10 12:49:44,777][76542] Updated weights for policy 1, policy_version 3800 (0.0008) -[2023-10-10 12:49:44,972][76543] Updated weights for policy 0, policy_version 3782 (0.0008) -[2023-10-10 12:49:45,350][76543] Updated weights for policy 0, policy_version 3792 (0.0007) -[2023-10-10 12:49:45,732][76543] Updated weights for policy 0, policy_version 3802 (0.0007) -[2023-10-10 12:49:46,076][75634] Fps is (10 sec: 16383.9, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 7798784. Throughput: 0: 1814.7, 1: 1806.2. Samples: 1954152. Policy #0 lag: (min: 16.0, avg: 35.9, max: 48.0) -[2023-10-10 12:49:46,076][75634] Avg episode reward: [(0, '9.300'), (1, '9.310')] -[2023-10-10 12:49:48,583][76542] Updated weights for policy 1, policy_version 3810 (0.0008) -[2023-10-10 12:49:48,958][76542] Updated weights for policy 1, policy_version 3820 (0.0007) -[2023-10-10 12:49:49,317][76542] Updated weights for policy 1, policy_version 3830 (0.0007) -[2023-10-10 12:49:49,441][76543] Updated weights for policy 0, policy_version 3812 (0.0009) -[2023-10-10 12:49:49,684][76542] Updated weights for policy 1, policy_version 3840 (0.0008) -[2023-10-10 12:49:49,805][76543] Updated weights for policy 0, policy_version 3822 (0.0010) -[2023-10-10 12:49:50,181][76543] Updated weights for policy 0, policy_version 3832 (0.0010) -[2023-10-10 12:49:51,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.3). Total num frames: 7864320. Throughput: 0: 1810.3, 1: 1810.8. Samples: 1965588. Policy #0 lag: (min: 29.0, avg: 36.0, max: 61.0) -[2023-10-10 12:49:51,077][75634] Avg episode reward: [(0, '9.240'), (1, '9.660')] -[2023-10-10 12:49:53,224][76542] Updated weights for policy 1, policy_version 3850 (0.0011) -[2023-10-10 12:49:53,591][76542] Updated weights for policy 1, policy_version 3860 (0.0011) -[2023-10-10 12:49:53,922][76543] Updated weights for policy 0, policy_version 3842 (0.0009) -[2023-10-10 12:49:53,947][76542] Updated weights for policy 1, policy_version 3870 (0.0010) -[2023-10-10 12:49:54,284][76543] Updated weights for policy 0, policy_version 3852 (0.0008) -[2023-10-10 12:49:54,663][76543] Updated weights for policy 0, policy_version 3862 (0.0010) -[2023-10-10 12:49:55,027][76543] Updated weights for policy 0, policy_version 3872 (0.0010) -[2023-10-10 12:49:56,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 7929856. Throughput: 0: 1810.8, 1: 1809.2. Samples: 1986940. Policy #0 lag: (min: 29.0, avg: 36.0, max: 61.0) -[2023-10-10 12:49:56,077][75634] Avg episode reward: [(0, '9.800'), (1, '10.280')] -[2023-10-10 12:49:56,079][76362] Saving new best policy, reward=9.800! -[2023-10-10 12:49:56,079][76421] Saving new best policy, reward=10.280! -[2023-10-10 12:49:57,693][76542] Updated weights for policy 1, policy_version 3880 (0.0008) -[2023-10-10 12:49:58,053][76542] Updated weights for policy 1, policy_version 3890 (0.0008) -[2023-10-10 12:49:58,431][76542] Updated weights for policy 1, policy_version 3900 (0.0008) -[2023-10-10 12:49:58,750][76543] Updated weights for policy 0, policy_version 3882 (0.0009) -[2023-10-10 12:49:59,122][76543] Updated weights for policy 0, policy_version 3892 (0.0007) -[2023-10-10 12:49:59,506][76543] Updated weights for policy 0, policy_version 3902 (0.0007) -[2023-10-10 12:50:01,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 7995392. Throughput: 0: 1816.5, 1: 1818.9. Samples: 2008830. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-10 12:50:01,077][75634] Avg episode reward: [(0, '9.990'), (1, '10.220')] -[2023-10-10 12:50:01,086][76362] Saving new best policy, reward=9.990! -[2023-10-10 12:50:02,166][76542] Updated weights for policy 1, policy_version 3910 (0.0011) -[2023-10-10 12:50:02,548][76542] Updated weights for policy 1, policy_version 3920 (0.0008) -[2023-10-10 12:50:02,915][76542] Updated weights for policy 1, policy_version 3930 (0.0008) -[2023-10-10 12:50:03,079][76543] Updated weights for policy 0, policy_version 3912 (0.0009) -[2023-10-10 12:50:03,444][76543] Updated weights for policy 0, policy_version 3922 (0.0009) -[2023-10-10 12:50:03,815][76543] Updated weights for policy 0, policy_version 3932 (0.0008) -[2023-10-10 12:50:06,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 8060928. Throughput: 0: 1810.5, 1: 1822.3. Samples: 2019832. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-10 12:50:06,076][75634] Avg episode reward: [(0, '10.570'), (1, '10.700')] -[2023-10-10 12:50:06,077][76362] Saving new best policy, reward=10.570! -[2023-10-10 12:50:06,077][76421] Saving new best policy, reward=10.700! -[2023-10-10 12:50:06,526][76542] Updated weights for policy 1, policy_version 3940 (0.0007) -[2023-10-10 12:50:06,893][76542] Updated weights for policy 1, policy_version 3950 (0.0007) -[2023-10-10 12:50:07,267][76542] Updated weights for policy 1, policy_version 3960 (0.0010) -[2023-10-10 12:50:07,721][76543] Updated weights for policy 0, policy_version 3942 (0.0009) -[2023-10-10 12:50:08,084][76543] Updated weights for policy 0, policy_version 3952 (0.0009) -[2023-10-10 12:50:08,458][76543] Updated weights for policy 0, policy_version 3962 (0.0009) -[2023-10-10 12:50:11,009][76542] Updated weights for policy 1, policy_version 3970 (0.0007) -[2023-10-10 12:50:11,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 8126464. Throughput: 0: 1813.8, 1: 1821.3. Samples: 2041478. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:50:11,077][75634] Avg episode reward: [(0, '11.170'), (1, '10.970')] -[2023-10-10 12:50:11,078][76362] Saving new best policy, reward=11.170! -[2023-10-10 12:50:11,368][76542] Updated weights for policy 1, policy_version 3980 (0.0008) -[2023-10-10 12:50:11,734][76542] Updated weights for policy 1, policy_version 3990 (0.0007) -[2023-10-10 12:50:12,101][76421] Saving new best policy, reward=10.970! -[2023-10-10 12:50:12,104][76542] Updated weights for policy 1, policy_version 4000 (0.0008) -[2023-10-10 12:50:12,147][76543] Updated weights for policy 0, policy_version 3972 (0.0008) -[2023-10-10 12:50:12,525][76543] Updated weights for policy 0, policy_version 3982 (0.0008) -[2023-10-10 12:50:12,901][76543] Updated weights for policy 0, policy_version 3992 (0.0010) -[2023-10-10 12:50:15,725][76542] Updated weights for policy 1, policy_version 4010 (0.0007) -[2023-10-10 12:50:16,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 8192000. Throughput: 0: 1813.6, 1: 1821.8. Samples: 2063968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:50:16,077][75634] Avg episode reward: [(0, '10.940'), (1, '10.400')] -[2023-10-10 12:50:16,098][76542] Updated weights for policy 1, policy_version 4020 (0.0008) -[2023-10-10 12:50:16,460][76542] Updated weights for policy 1, policy_version 4030 (0.0009) -[2023-10-10 12:50:16,682][76543] Updated weights for policy 0, policy_version 4002 (0.0008) -[2023-10-10 12:50:17,050][76543] Updated weights for policy 0, policy_version 4012 (0.0011) -[2023-10-10 12:50:17,421][76543] Updated weights for policy 0, policy_version 4022 (0.0010) -[2023-10-10 12:50:17,802][76543] Updated weights for policy 0, policy_version 4032 (0.0012) -[2023-10-10 12:50:20,082][76542] Updated weights for policy 1, policy_version 4040 (0.0009) -[2023-10-10 12:50:20,449][76542] Updated weights for policy 1, policy_version 4050 (0.0009) -[2023-10-10 12:50:20,824][76542] Updated weights for policy 1, policy_version 4060 (0.0010) -[2023-10-10 12:50:21,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 8290304. Throughput: 0: 1813.3, 1: 1824.9. Samples: 2074412. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:50:21,077][75634] Avg episode reward: [(0, '10.170'), (1, '10.230')] -[2023-10-10 12:50:21,378][76543] Updated weights for policy 0, policy_version 4042 (0.0008) -[2023-10-10 12:50:21,758][76543] Updated weights for policy 0, policy_version 4052 (0.0009) -[2023-10-10 12:50:22,131][76543] Updated weights for policy 0, policy_version 4062 (0.0007) -[2023-10-10 12:50:24,390][76542] Updated weights for policy 1, policy_version 4070 (0.0010) -[2023-10-10 12:50:24,755][76542] Updated weights for policy 1, policy_version 4080 (0.0010) -[2023-10-10 12:50:25,118][76542] Updated weights for policy 1, policy_version 4090 (0.0007) -[2023-10-10 12:50:25,929][76543] Updated weights for policy 0, policy_version 4072 (0.0007) -[2023-10-10 12:50:26,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 8355840. Throughput: 0: 1811.7, 1: 1823.3. Samples: 2096628. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:50:26,076][75634] Avg episode reward: [(0, '8.980'), (1, '10.760')] -[2023-10-10 12:50:26,308][76543] Updated weights for policy 0, policy_version 4082 (0.0007) -[2023-10-10 12:50:26,679][76543] Updated weights for policy 0, policy_version 4092 (0.0007) -[2023-10-10 12:50:28,775][76542] Updated weights for policy 1, policy_version 4100 (0.0007) -[2023-10-10 12:50:29,143][76542] Updated weights for policy 1, policy_version 4110 (0.0008) -[2023-10-10 12:50:29,509][76542] Updated weights for policy 1, policy_version 4120 (0.0007) -[2023-10-10 12:50:30,262][76543] Updated weights for policy 0, policy_version 4102 (0.0008) -[2023-10-10 12:50:30,640][76543] Updated weights for policy 0, policy_version 4112 (0.0009) -[2023-10-10 12:50:31,015][76543] Updated weights for policy 0, policy_version 4122 (0.0007) -[2023-10-10 12:50:31,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 8421376. Throughput: 0: 1819.3, 1: 1831.1. Samples: 2118424. Policy #0 lag: (min: 2.0, avg: 8.9, max: 34.0) -[2023-10-10 12:50:31,077][75634] Avg episode reward: [(0, '8.890'), (1, '10.040')] -[2023-10-10 12:50:31,089][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000004128_4227072.pth... -[2023-10-10 12:50:31,121][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000002432_2490368.pth -[2023-10-10 12:50:31,230][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000004128_4227072.pth... -[2023-10-10 12:50:31,269][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000002432_2490368.pth -[2023-10-10 12:50:33,235][76542] Updated weights for policy 1, policy_version 4130 (0.0008) -[2023-10-10 12:50:33,612][76542] Updated weights for policy 1, policy_version 4140 (0.0010) -[2023-10-10 12:50:33,989][76542] Updated weights for policy 1, policy_version 4150 (0.0008) -[2023-10-10 12:50:34,360][76542] Updated weights for policy 1, policy_version 4160 (0.0009) -[2023-10-10 12:50:34,773][76543] Updated weights for policy 0, policy_version 4132 (0.0008) -[2023-10-10 12:50:35,153][76543] Updated weights for policy 0, policy_version 4142 (0.0008) -[2023-10-10 12:50:35,534][76543] Updated weights for policy 0, policy_version 4152 (0.0008) -[2023-10-10 12:50:36,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 8519680. Throughput: 0: 1819.0, 1: 1824.2. Samples: 2129532. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:50:36,077][75634] Avg episode reward: [(0, '9.160'), (1, '9.820')] -[2023-10-10 12:50:38,215][76542] Updated weights for policy 1, policy_version 4170 (0.0007) -[2023-10-10 12:50:38,590][76542] Updated weights for policy 1, policy_version 4180 (0.0008) -[2023-10-10 12:50:38,947][76542] Updated weights for policy 1, policy_version 4190 (0.0009) -[2023-10-10 12:50:39,181][76543] Updated weights for policy 0, policy_version 4162 (0.0009) -[2023-10-10 12:50:39,558][76543] Updated weights for policy 0, policy_version 4172 (0.0007) -[2023-10-10 12:50:39,931][76543] Updated weights for policy 0, policy_version 4182 (0.0010) -[2023-10-10 12:50:40,305][76543] Updated weights for policy 0, policy_version 4192 (0.0008) -[2023-10-10 12:50:41,076][75634] Fps is (10 sec: 16384.6, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 8585216. Throughput: 0: 1824.4, 1: 1822.3. Samples: 2151040. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:50:41,076][75634] Avg episode reward: [(0, '9.220'), (1, '9.250')] -[2023-10-10 12:50:42,945][76542] Updated weights for policy 1, policy_version 4200 (0.0010) -[2023-10-10 12:50:43,325][76542] Updated weights for policy 1, policy_version 4210 (0.0009) -[2023-10-10 12:50:43,686][76542] Updated weights for policy 1, policy_version 4220 (0.0008) -[2023-10-10 12:50:43,956][76543] Updated weights for policy 0, policy_version 4202 (0.0008) -[2023-10-10 12:50:44,324][76543] Updated weights for policy 0, policy_version 4212 (0.0010) -[2023-10-10 12:50:44,703][76543] Updated weights for policy 0, policy_version 4222 (0.0009) -[2023-10-10 12:50:46,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 8650752. Throughput: 0: 1815.7, 1: 1813.8. Samples: 2172160. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) -[2023-10-10 12:50:46,077][75634] Avg episode reward: [(0, '9.980'), (1, '9.630')] -[2023-10-10 12:50:47,253][76542] Updated weights for policy 1, policy_version 4230 (0.0007) -[2023-10-10 12:50:47,627][76542] Updated weights for policy 1, policy_version 4240 (0.0009) -[2023-10-10 12:50:48,002][76542] Updated weights for policy 1, policy_version 4250 (0.0010) -[2023-10-10 12:50:48,331][76543] Updated weights for policy 0, policy_version 4232 (0.0008) -[2023-10-10 12:50:48,710][76543] Updated weights for policy 0, policy_version 4242 (0.0008) -[2023-10-10 12:50:49,073][76543] Updated weights for policy 0, policy_version 4252 (0.0009) -[2023-10-10 12:50:51,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 8716288. Throughput: 0: 1823.3, 1: 1810.8. Samples: 2183366. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) -[2023-10-10 12:50:51,076][75634] Avg episode reward: [(0, '9.670'), (1, '9.090')] -[2023-10-10 12:50:51,860][76542] Updated weights for policy 1, policy_version 4260 (0.0009) -[2023-10-10 12:50:52,228][76542] Updated weights for policy 1, policy_version 4270 (0.0009) -[2023-10-10 12:50:52,598][76542] Updated weights for policy 1, policy_version 4280 (0.0008) -[2023-10-10 12:50:52,957][76543] Updated weights for policy 0, policy_version 4262 (0.0008) -[2023-10-10 12:50:53,325][76543] Updated weights for policy 0, policy_version 4272 (0.0009) -[2023-10-10 12:50:53,689][76543] Updated weights for policy 0, policy_version 4282 (0.0007) -[2023-10-10 12:50:56,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 8781824. Throughput: 0: 1818.3, 1: 1811.6. Samples: 2204824. Policy #0 lag: (min: 31.0, avg: 43.9, max: 63.0) -[2023-10-10 12:50:56,076][75634] Avg episode reward: [(0, '9.710'), (1, '9.250')] -[2023-10-10 12:50:56,152][76542] Updated weights for policy 1, policy_version 4290 (0.0008) -[2023-10-10 12:50:56,525][76542] Updated weights for policy 1, policy_version 4300 (0.0008) -[2023-10-10 12:50:56,900][76542] Updated weights for policy 1, policy_version 4310 (0.0008) -[2023-10-10 12:50:57,246][76543] Updated weights for policy 0, policy_version 4292 (0.0008) -[2023-10-10 12:50:57,272][76542] Updated weights for policy 1, policy_version 4320 (0.0009) -[2023-10-10 12:50:57,611][76543] Updated weights for policy 0, policy_version 4302 (0.0010) -[2023-10-10 12:50:57,988][76543] Updated weights for policy 0, policy_version 4312 (0.0009) -[2023-10-10 12:51:00,940][76542] Updated weights for policy 1, policy_version 4330 (0.0009) -[2023-10-10 12:51:01,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 8847360. Throughput: 0: 1815.2, 1: 1817.2. Samples: 2227424. Policy #0 lag: (min: 31.0, avg: 43.9, max: 63.0) -[2023-10-10 12:51:01,076][75634] Avg episode reward: [(0, '10.360'), (1, '9.400')] -[2023-10-10 12:51:01,310][76542] Updated weights for policy 1, policy_version 4340 (0.0008) -[2023-10-10 12:51:01,684][76542] Updated weights for policy 1, policy_version 4350 (0.0009) -[2023-10-10 12:51:01,788][76543] Updated weights for policy 0, policy_version 4322 (0.0009) -[2023-10-10 12:51:02,164][76543] Updated weights for policy 0, policy_version 4332 (0.0011) -[2023-10-10 12:51:02,531][76543] Updated weights for policy 0, policy_version 4342 (0.0010) -[2023-10-10 12:51:02,914][76543] Updated weights for policy 0, policy_version 4352 (0.0011) -[2023-10-10 12:51:05,421][76542] Updated weights for policy 1, policy_version 4360 (0.0009) -[2023-10-10 12:51:05,796][76542] Updated weights for policy 1, policy_version 4370 (0.0009) -[2023-10-10 12:51:06,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 8912896. Throughput: 0: 1812.8, 1: 1808.1. Samples: 2237356. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:51:06,077][75634] Avg episode reward: [(0, '10.110'), (1, '8.900')] -[2023-10-10 12:51:06,160][76542] Updated weights for policy 1, policy_version 4380 (0.0009) -[2023-10-10 12:51:06,600][76543] Updated weights for policy 0, policy_version 4362 (0.0008) -[2023-10-10 12:51:06,977][76543] Updated weights for policy 0, policy_version 4372 (0.0008) -[2023-10-10 12:51:07,350][76543] Updated weights for policy 0, policy_version 4382 (0.0009) -[2023-10-10 12:51:09,837][76542] Updated weights for policy 1, policy_version 4390 (0.0008) -[2023-10-10 12:51:10,205][76542] Updated weights for policy 1, policy_version 4400 (0.0008) -[2023-10-10 12:51:10,589][76542] Updated weights for policy 1, policy_version 4410 (0.0008) -[2023-10-10 12:51:11,049][76543] Updated weights for policy 0, policy_version 4392 (0.0010) -[2023-10-10 12:51:11,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 9011200. Throughput: 0: 1811.9, 1: 1817.4. Samples: 2259946. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:51:11,076][75634] Avg episode reward: [(0, '10.460'), (1, '9.190')] -[2023-10-10 12:51:11,430][76543] Updated weights for policy 0, policy_version 4402 (0.0009) -[2023-10-10 12:51:11,809][76543] Updated weights for policy 0, policy_version 4412 (0.0010) -[2023-10-10 12:51:14,080][76542] Updated weights for policy 1, policy_version 4420 (0.0008) -[2023-10-10 12:51:14,446][76542] Updated weights for policy 1, policy_version 4430 (0.0007) -[2023-10-10 12:51:14,815][76542] Updated weights for policy 1, policy_version 4440 (0.0008) -[2023-10-10 12:51:15,541][76543] Updated weights for policy 0, policy_version 4422 (0.0008) -[2023-10-10 12:51:15,910][76543] Updated weights for policy 0, policy_version 4432 (0.0009) -[2023-10-10 12:51:16,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 9076736. Throughput: 0: 1817.5, 1: 1807.1. Samples: 2281530. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-10 12:51:16,076][75634] Avg episode reward: [(0, '10.410'), (1, '9.310')] -[2023-10-10 12:51:16,281][76543] Updated weights for policy 0, policy_version 4442 (0.0007) -[2023-10-10 12:51:18,401][76542] Updated weights for policy 1, policy_version 4450 (0.0008) -[2023-10-10 12:51:18,768][76542] Updated weights for policy 1, policy_version 4460 (0.0007) -[2023-10-10 12:51:19,124][76542] Updated weights for policy 1, policy_version 4470 (0.0008) -[2023-10-10 12:51:19,493][76542] Updated weights for policy 1, policy_version 4480 (0.0008) -[2023-10-10 12:51:19,880][76543] Updated weights for policy 0, policy_version 4452 (0.0007) -[2023-10-10 12:51:20,252][76543] Updated weights for policy 0, policy_version 4462 (0.0008) -[2023-10-10 12:51:20,618][76543] Updated weights for policy 0, policy_version 4472 (0.0009) -[2023-10-10 12:51:21,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 9175040. Throughput: 0: 1807.7, 1: 1816.1. Samples: 2292604. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-10-10 12:51:21,077][75634] Avg episode reward: [(0, '9.980'), (1, '9.780')] -[2023-10-10 12:51:23,137][76542] Updated weights for policy 1, policy_version 4490 (0.0009) -[2023-10-10 12:51:23,496][76542] Updated weights for policy 1, policy_version 4500 (0.0011) -[2023-10-10 12:51:23,872][76542] Updated weights for policy 1, policy_version 4510 (0.0010) -[2023-10-10 12:51:24,368][76543] Updated weights for policy 0, policy_version 4482 (0.0010) -[2023-10-10 12:51:24,743][76543] Updated weights for policy 0, policy_version 4492 (0.0009) -[2023-10-10 12:51:25,111][76543] Updated weights for policy 0, policy_version 4502 (0.0011) -[2023-10-10 12:51:25,482][76543] Updated weights for policy 0, policy_version 4512 (0.0008) -[2023-10-10 12:51:26,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 9240576. Throughput: 0: 1817.6, 1: 1817.3. Samples: 2314610. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-10-10 12:51:26,076][75634] Avg episode reward: [(0, '11.330'), (1, '10.230')] -[2023-10-10 12:51:26,077][76362] Saving new best policy, reward=11.330! -[2023-10-10 12:51:27,885][76542] Updated weights for policy 1, policy_version 4520 (0.0008) -[2023-10-10 12:51:28,270][76542] Updated weights for policy 1, policy_version 4530 (0.0007) -[2023-10-10 12:51:28,635][76542] Updated weights for policy 1, policy_version 4540 (0.0007) -[2023-10-10 12:51:29,188][76543] Updated weights for policy 0, policy_version 4522 (0.0010) -[2023-10-10 12:51:29,558][76543] Updated weights for policy 0, policy_version 4532 (0.0009) -[2023-10-10 12:51:29,930][76543] Updated weights for policy 0, policy_version 4542 (0.0008) -[2023-10-10 12:51:31,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 9306112. Throughput: 0: 1813.9, 1: 1818.5. Samples: 2335616. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:51:31,077][75634] Avg episode reward: [(0, '12.060'), (1, '10.790')] -[2023-10-10 12:51:31,087][76362] Saving new best policy, reward=12.060! -[2023-10-10 12:51:32,132][76542] Updated weights for policy 1, policy_version 4550 (0.0007) -[2023-10-10 12:51:32,498][76542] Updated weights for policy 1, policy_version 4560 (0.0007) -[2023-10-10 12:51:32,865][76542] Updated weights for policy 1, policy_version 4570 (0.0009) -[2023-10-10 12:51:33,528][76543] Updated weights for policy 0, policy_version 4552 (0.0010) -[2023-10-10 12:51:33,907][76543] Updated weights for policy 0, policy_version 4562 (0.0007) -[2023-10-10 12:51:34,278][76543] Updated weights for policy 0, policy_version 4572 (0.0009) -[2023-10-10 12:51:36,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 9371648. Throughput: 0: 1821.4, 1: 1820.8. Samples: 2347262. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:51:36,077][75634] Avg episode reward: [(0, '11.940'), (1, '11.390')] -[2023-10-10 12:51:36,078][76421] Saving new best policy, reward=11.390! -[2023-10-10 12:51:36,538][76542] Updated weights for policy 1, policy_version 4580 (0.0009) -[2023-10-10 12:51:36,917][76542] Updated weights for policy 1, policy_version 4590 (0.0008) -[2023-10-10 12:51:37,280][76542] Updated weights for policy 1, policy_version 4600 (0.0007) -[2023-10-10 12:51:37,869][76543] Updated weights for policy 0, policy_version 4582 (0.0011) -[2023-10-10 12:51:38,246][76543] Updated weights for policy 0, policy_version 4592 (0.0009) -[2023-10-10 12:51:38,615][76543] Updated weights for policy 0, policy_version 4602 (0.0007) -[2023-10-10 12:51:41,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 9437184. Throughput: 0: 1818.7, 1: 1820.0. Samples: 2368570. Policy #0 lag: (min: 10.0, avg: 26.9, max: 42.0) -[2023-10-10 12:51:41,077][75634] Avg episode reward: [(0, '12.570'), (1, '10.740')] -[2023-10-10 12:51:41,078][76362] Saving new best policy, reward=12.570! -[2023-10-10 12:51:41,122][76542] Updated weights for policy 1, policy_version 4610 (0.0009) -[2023-10-10 12:51:41,492][76542] Updated weights for policy 1, policy_version 4620 (0.0009) -[2023-10-10 12:51:41,858][76542] Updated weights for policy 1, policy_version 4630 (0.0008) -[2023-10-10 12:51:42,228][76542] Updated weights for policy 1, policy_version 4640 (0.0008) -[2023-10-10 12:51:42,304][76543] Updated weights for policy 0, policy_version 4612 (0.0009) -[2023-10-10 12:51:42,687][76543] Updated weights for policy 0, policy_version 4622 (0.0008) -[2023-10-10 12:51:43,057][76543] Updated weights for policy 0, policy_version 4632 (0.0007) -[2023-10-10 12:51:46,052][76542] Updated weights for policy 1, policy_version 4650 (0.0009) -[2023-10-10 12:51:46,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 9502720. Throughput: 0: 1828.3, 1: 1814.6. Samples: 2391354. Policy #0 lag: (min: 10.0, avg: 26.9, max: 42.0) -[2023-10-10 12:51:46,076][75634] Avg episode reward: [(0, '11.260'), (1, '10.550')] -[2023-10-10 12:51:46,417][76542] Updated weights for policy 1, policy_version 4660 (0.0009) -[2023-10-10 12:51:46,754][76543] Updated weights for policy 0, policy_version 4642 (0.0009) -[2023-10-10 12:51:46,783][76542] Updated weights for policy 1, policy_version 4670 (0.0010) -[2023-10-10 12:51:47,128][76543] Updated weights for policy 0, policy_version 4652 (0.0010) -[2023-10-10 12:51:47,509][76543] Updated weights for policy 0, policy_version 4662 (0.0009) -[2023-10-10 12:51:47,876][76543] Updated weights for policy 0, policy_version 4672 (0.0008) -[2023-10-10 12:51:50,594][76542] Updated weights for policy 1, policy_version 4680 (0.0008) -[2023-10-10 12:51:50,959][76542] Updated weights for policy 1, policy_version 4690 (0.0010) -[2023-10-10 12:51:51,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 9568256. Throughput: 0: 1828.9, 1: 1809.6. Samples: 2401090. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:51:51,076][75634] Avg episode reward: [(0, '11.300'), (1, '10.330')] -[2023-10-10 12:51:51,332][76542] Updated weights for policy 1, policy_version 4700 (0.0009) -[2023-10-10 12:51:51,599][76543] Updated weights for policy 0, policy_version 4682 (0.0008) -[2023-10-10 12:51:51,967][76543] Updated weights for policy 0, policy_version 4692 (0.0011) -[2023-10-10 12:51:52,347][76543] Updated weights for policy 0, policy_version 4702 (0.0010) -[2023-10-10 12:51:54,957][76542] Updated weights for policy 1, policy_version 4710 (0.0008) -[2023-10-10 12:51:55,328][76542] Updated weights for policy 1, policy_version 4720 (0.0007) -[2023-10-10 12:51:55,695][76542] Updated weights for policy 1, policy_version 4730 (0.0007) -[2023-10-10 12:51:56,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 9666560. Throughput: 0: 1828.3, 1: 1815.2. Samples: 2423904. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:51:56,077][75634] Avg episode reward: [(0, '10.930'), (1, '10.060')] -[2023-10-10 12:51:56,139][76543] Updated weights for policy 0, policy_version 4712 (0.0009) -[2023-10-10 12:51:56,516][76543] Updated weights for policy 0, policy_version 4722 (0.0009) -[2023-10-10 12:51:56,899][76543] Updated weights for policy 0, policy_version 4732 (0.0007) -[2023-10-10 12:51:59,229][76542] Updated weights for policy 1, policy_version 4740 (0.0008) -[2023-10-10 12:51:59,594][76542] Updated weights for policy 1, policy_version 4750 (0.0008) -[2023-10-10 12:51:59,958][76542] Updated weights for policy 1, policy_version 4760 (0.0007) -[2023-10-10 12:52:00,589][76543] Updated weights for policy 0, policy_version 4742 (0.0009) -[2023-10-10 12:52:00,961][76543] Updated weights for policy 0, policy_version 4752 (0.0008) -[2023-10-10 12:52:01,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 9732096. Throughput: 0: 1826.0, 1: 1812.1. Samples: 2445246. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:52:01,076][75634] Avg episode reward: [(0, '11.680'), (1, '9.400')] -[2023-10-10 12:52:01,329][76543] Updated weights for policy 0, policy_version 4762 (0.0007) -[2023-10-10 12:52:03,740][76542] Updated weights for policy 1, policy_version 4770 (0.0009) -[2023-10-10 12:52:04,110][76542] Updated weights for policy 1, policy_version 4780 (0.0011) -[2023-10-10 12:52:04,468][76542] Updated weights for policy 1, policy_version 4790 (0.0008) -[2023-10-10 12:52:04,840][76542] Updated weights for policy 1, policy_version 4800 (0.0009) -[2023-10-10 12:52:04,936][76543] Updated weights for policy 0, policy_version 4772 (0.0007) -[2023-10-10 12:52:05,322][76543] Updated weights for policy 0, policy_version 4782 (0.0008) -[2023-10-10 12:52:05,688][76543] Updated weights for policy 0, policy_version 4792 (0.0009) -[2023-10-10 12:52:06,076][75634] Fps is (10 sec: 16384.0, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 9830400. Throughput: 0: 1829.6, 1: 1813.1. Samples: 2456526. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 12:52:06,077][75634] Avg episode reward: [(0, '11.540'), (1, '10.230')] -[2023-10-10 12:52:08,469][76542] Updated weights for policy 1, policy_version 4810 (0.0008) -[2023-10-10 12:52:08,846][76542] Updated weights for policy 1, policy_version 4820 (0.0007) -[2023-10-10 12:52:09,165][76543] Updated weights for policy 0, policy_version 4802 (0.0010) -[2023-10-10 12:52:09,209][76542] Updated weights for policy 1, policy_version 4830 (0.0007) -[2023-10-10 12:52:09,544][76543] Updated weights for policy 0, policy_version 4812 (0.0008) -[2023-10-10 12:52:09,916][76543] Updated weights for policy 0, policy_version 4822 (0.0010) -[2023-10-10 12:52:10,284][76543] Updated weights for policy 0, policy_version 4832 (0.0009) -[2023-10-10 12:52:11,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 9895936. Throughput: 0: 1820.9, 1: 1807.2. Samples: 2477876. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 12:52:11,076][75634] Avg episode reward: [(0, '10.910'), (1, '10.860')] -[2023-10-10 12:52:12,976][76542] Updated weights for policy 1, policy_version 4840 (0.0009) -[2023-10-10 12:52:13,354][76542] Updated weights for policy 1, policy_version 4850 (0.0009) -[2023-10-10 12:52:13,726][76542] Updated weights for policy 1, policy_version 4860 (0.0008) -[2023-10-10 12:52:13,982][76543] Updated weights for policy 0, policy_version 4842 (0.0008) -[2023-10-10 12:52:14,364][76543] Updated weights for policy 0, policy_version 4852 (0.0010) -[2023-10-10 12:52:14,736][76543] Updated weights for policy 0, policy_version 4862 (0.0008) -[2023-10-10 12:52:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 9961472. Throughput: 0: 1828.5, 1: 1810.9. Samples: 2499390. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-10 12:52:16,077][75634] Avg episode reward: [(0, '11.140'), (1, '10.920')] -[2023-10-10 12:52:17,406][76542] Updated weights for policy 1, policy_version 4870 (0.0010) -[2023-10-10 12:52:17,775][76542] Updated weights for policy 1, policy_version 4880 (0.0008) -[2023-10-10 12:52:18,150][76542] Updated weights for policy 1, policy_version 4890 (0.0009) -[2023-10-10 12:52:18,307][76543] Updated weights for policy 0, policy_version 4872 (0.0008) -[2023-10-10 12:52:18,686][76543] Updated weights for policy 0, policy_version 4882 (0.0008) -[2023-10-10 12:52:19,054][76543] Updated weights for policy 0, policy_version 4892 (0.0007) -[2023-10-10 12:52:21,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 10027008. Throughput: 0: 1819.6, 1: 1810.4. Samples: 2510612. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-10 12:52:21,077][75634] Avg episode reward: [(0, '10.230'), (1, '11.230')] -[2023-10-10 12:52:21,968][76542] Updated weights for policy 1, policy_version 4900 (0.0008) -[2023-10-10 12:52:22,344][76542] Updated weights for policy 1, policy_version 4910 (0.0007) -[2023-10-10 12:52:22,718][76542] Updated weights for policy 1, policy_version 4920 (0.0008) -[2023-10-10 12:52:22,910][76543] Updated weights for policy 0, policy_version 4902 (0.0009) -[2023-10-10 12:52:23,288][76543] Updated weights for policy 0, policy_version 4912 (0.0009) -[2023-10-10 12:52:23,649][76543] Updated weights for policy 0, policy_version 4922 (0.0009) -[2023-10-10 12:52:26,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 10092544. Throughput: 0: 1819.9, 1: 1806.4. Samples: 2531754. Policy #0 lag: (min: 31.0, avg: 32.2, max: 54.0) -[2023-10-10 12:52:26,077][75634] Avg episode reward: [(0, '11.370'), (1, '11.500')] -[2023-10-10 12:52:26,079][76421] Saving new best policy, reward=11.500! -[2023-10-10 12:52:26,385][76542] Updated weights for policy 1, policy_version 4930 (0.0009) -[2023-10-10 12:52:26,759][76542] Updated weights for policy 1, policy_version 4940 (0.0007) -[2023-10-10 12:52:27,127][76542] Updated weights for policy 1, policy_version 4950 (0.0008) -[2023-10-10 12:52:27,459][76543] Updated weights for policy 0, policy_version 4932 (0.0008) -[2023-10-10 12:52:27,507][76542] Updated weights for policy 1, policy_version 4960 (0.0007) -[2023-10-10 12:52:27,823][76543] Updated weights for policy 0, policy_version 4942 (0.0008) -[2023-10-10 12:52:28,206][76543] Updated weights for policy 0, policy_version 4952 (0.0008) -[2023-10-10 12:52:31,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 10158080. Throughput: 0: 1811.5, 1: 1815.5. Samples: 2554568. Policy #0 lag: (min: 31.0, avg: 32.2, max: 54.0) -[2023-10-10 12:52:31,077][75634] Avg episode reward: [(0, '11.900'), (1, '11.410')] -[2023-10-10 12:52:31,084][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000004960_5079040.pth... -[2023-10-10 12:52:31,122][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000003264_3342336.pth -[2023-10-10 12:52:31,159][76542] Updated weights for policy 1, policy_version 4970 (0.0009) -[2023-10-10 12:52:31,519][76542] Updated weights for policy 1, policy_version 4980 (0.0009) -[2023-10-10 12:52:31,895][76542] Updated weights for policy 1, policy_version 4990 (0.0009) -[2023-10-10 12:52:31,959][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000004992_5111808.pth... -[2023-10-10 12:52:31,969][76543] Updated weights for policy 0, policy_version 4962 (0.0009) -[2023-10-10 12:52:31,988][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000003264_3342336.pth -[2023-10-10 12:52:32,340][76543] Updated weights for policy 0, policy_version 4972 (0.0009) -[2023-10-10 12:52:32,720][76543] Updated weights for policy 0, policy_version 4982 (0.0010) -[2023-10-10 12:52:33,088][76543] Updated weights for policy 0, policy_version 4992 (0.0007) -[2023-10-10 12:52:35,522][76542] Updated weights for policy 1, policy_version 5000 (0.0007) -[2023-10-10 12:52:35,883][76542] Updated weights for policy 1, policy_version 5010 (0.0010) -[2023-10-10 12:52:36,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 10223616. Throughput: 0: 1813.5, 1: 1816.6. Samples: 2564444. Policy #0 lag: (min: 14.0, avg: 37.1, max: 40.0) -[2023-10-10 12:52:36,077][75634] Avg episode reward: [(0, '11.800'), (1, '10.910')] -[2023-10-10 12:52:36,249][76542] Updated weights for policy 1, policy_version 5020 (0.0009) -[2023-10-10 12:52:36,605][76543] Updated weights for policy 0, policy_version 5002 (0.0010) -[2023-10-10 12:52:36,989][76543] Updated weights for policy 0, policy_version 5012 (0.0009) -[2023-10-10 12:52:37,359][76543] Updated weights for policy 0, policy_version 5022 (0.0008) -[2023-10-10 12:52:40,007][76542] Updated weights for policy 1, policy_version 5030 (0.0009) -[2023-10-10 12:52:40,376][76542] Updated weights for policy 1, policy_version 5040 (0.0009) -[2023-10-10 12:52:40,733][76542] Updated weights for policy 1, policy_version 5050 (0.0008) -[2023-10-10 12:52:41,072][76543] Updated weights for policy 0, policy_version 5032 (0.0011) -[2023-10-10 12:52:41,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 10321920. Throughput: 0: 1813.1, 1: 1818.1. Samples: 2587308. Policy #0 lag: (min: 14.0, avg: 37.1, max: 40.0) -[2023-10-10 12:52:41,076][75634] Avg episode reward: [(0, '12.060'), (1, '10.650')] -[2023-10-10 12:52:41,444][76543] Updated weights for policy 0, policy_version 5042 (0.0010) -[2023-10-10 12:52:41,829][76543] Updated weights for policy 0, policy_version 5052 (0.0008) -[2023-10-10 12:52:44,411][76542] Updated weights for policy 1, policy_version 5060 (0.0007) -[2023-10-10 12:52:44,773][76542] Updated weights for policy 1, policy_version 5070 (0.0008) -[2023-10-10 12:52:45,141][76542] Updated weights for policy 1, policy_version 5080 (0.0009) -[2023-10-10 12:52:45,421][76543] Updated weights for policy 0, policy_version 5062 (0.0007) -[2023-10-10 12:52:45,798][76543] Updated weights for policy 0, policy_version 5072 (0.0007) -[2023-10-10 12:52:46,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 10387456. Throughput: 0: 1812.4, 1: 1815.4. Samples: 2608496. Policy #0 lag: (min: 27.0, avg: 41.4, max: 59.0) -[2023-10-10 12:52:46,077][75634] Avg episode reward: [(0, '11.800'), (1, '10.640')] -[2023-10-10 12:52:46,165][76543] Updated weights for policy 0, policy_version 5082 (0.0010) -[2023-10-10 12:52:48,923][76542] Updated weights for policy 1, policy_version 5090 (0.0008) -[2023-10-10 12:52:49,293][76542] Updated weights for policy 1, policy_version 5100 (0.0008) -[2023-10-10 12:52:49,658][76542] Updated weights for policy 1, policy_version 5110 (0.0008) -[2023-10-10 12:52:49,674][76543] Updated weights for policy 0, policy_version 5092 (0.0008) -[2023-10-10 12:52:50,024][76542] Updated weights for policy 1, policy_version 5120 (0.0007) -[2023-10-10 12:52:50,048][76543] Updated weights for policy 0, policy_version 5102 (0.0009) -[2023-10-10 12:52:50,423][76543] Updated weights for policy 0, policy_version 5112 (0.0009) -[2023-10-10 12:52:51,076][75634] Fps is (10 sec: 16383.6, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 10485760. Throughput: 0: 1814.2, 1: 1816.5. Samples: 2619908. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-10 12:52:51,077][75634] Avg episode reward: [(0, '12.040'), (1, '11.570')] -[2023-10-10 12:52:51,079][76421] Saving new best policy, reward=11.570! -[2023-10-10 12:52:53,622][76542] Updated weights for policy 1, policy_version 5130 (0.0007) -[2023-10-10 12:52:53,999][76542] Updated weights for policy 1, policy_version 5140 (0.0009) -[2023-10-10 12:52:54,155][76543] Updated weights for policy 0, policy_version 5122 (0.0009) -[2023-10-10 12:52:54,354][76542] Updated weights for policy 1, policy_version 5150 (0.0007) -[2023-10-10 12:52:54,526][76543] Updated weights for policy 0, policy_version 5132 (0.0009) -[2023-10-10 12:52:54,899][76543] Updated weights for policy 0, policy_version 5142 (0.0008) -[2023-10-10 12:52:55,284][76543] Updated weights for policy 0, policy_version 5152 (0.0007) -[2023-10-10 12:52:56,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 10551296. Throughput: 0: 1815.0, 1: 1809.8. Samples: 2640992. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-10 12:52:56,077][75634] Avg episode reward: [(0, '12.110'), (1, '10.400')] -[2023-10-10 12:52:58,062][76542] Updated weights for policy 1, policy_version 5160 (0.0007) -[2023-10-10 12:52:58,436][76542] Updated weights for policy 1, policy_version 5170 (0.0008) -[2023-10-10 12:52:58,806][76542] Updated weights for policy 1, policy_version 5180 (0.0007) -[2023-10-10 12:52:59,226][76543] Updated weights for policy 0, policy_version 5162 (0.0009) -[2023-10-10 12:52:59,599][76543] Updated weights for policy 0, policy_version 5172 (0.0011) -[2023-10-10 12:52:59,981][76543] Updated weights for policy 0, policy_version 5182 (0.0011) -[2023-10-10 12:53:01,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 10616832. Throughput: 0: 1806.1, 1: 1811.2. Samples: 2662168. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-10 12:53:01,077][75634] Avg episode reward: [(0, '12.480'), (1, '10.830')] -[2023-10-10 12:53:02,612][76542] Updated weights for policy 1, policy_version 5190 (0.0008) -[2023-10-10 12:53:02,975][76542] Updated weights for policy 1, policy_version 5200 (0.0010) -[2023-10-10 12:53:03,350][76542] Updated weights for policy 1, policy_version 5210 (0.0008) -[2023-10-10 12:53:03,841][76543] Updated weights for policy 0, policy_version 5192 (0.0009) -[2023-10-10 12:53:04,221][76543] Updated weights for policy 0, policy_version 5202 (0.0007) -[2023-10-10 12:53:04,583][76543] Updated weights for policy 0, policy_version 5212 (0.0010) -[2023-10-10 12:53:06,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 10682368. Throughput: 0: 1808.1, 1: 1809.3. Samples: 2673394. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-10 12:53:06,076][75634] Avg episode reward: [(0, '12.830'), (1, '10.650')] -[2023-10-10 12:53:06,077][76362] Saving new best policy, reward=12.830! -[2023-10-10 12:53:06,975][76542] Updated weights for policy 1, policy_version 5220 (0.0007) -[2023-10-10 12:53:07,346][76542] Updated weights for policy 1, policy_version 5230 (0.0007) -[2023-10-10 12:53:07,720][76542] Updated weights for policy 1, policy_version 5240 (0.0008) -[2023-10-10 12:53:08,298][76543] Updated weights for policy 0, policy_version 5222 (0.0009) -[2023-10-10 12:53:08,672][76543] Updated weights for policy 0, policy_version 5232 (0.0009) -[2023-10-10 12:53:09,051][76543] Updated weights for policy 0, policy_version 5242 (0.0007) -[2023-10-10 12:53:11,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 10747904. Throughput: 0: 1806.1, 1: 1819.4. Samples: 2694900. Policy #0 lag: (min: 1.0, avg: 8.3, max: 33.0) -[2023-10-10 12:53:11,076][75634] Avg episode reward: [(0, '12.740'), (1, '10.540')] -[2023-10-10 12:53:11,484][76542] Updated weights for policy 1, policy_version 5250 (0.0009) -[2023-10-10 12:53:11,860][76542] Updated weights for policy 1, policy_version 5260 (0.0007) -[2023-10-10 12:53:12,237][76542] Updated weights for policy 1, policy_version 5270 (0.0008) -[2023-10-10 12:53:12,606][76542] Updated weights for policy 1, policy_version 5280 (0.0008) -[2023-10-10 12:53:12,765][76543] Updated weights for policy 0, policy_version 5252 (0.0010) -[2023-10-10 12:53:13,141][76543] Updated weights for policy 0, policy_version 5262 (0.0011) -[2023-10-10 12:53:13,506][76543] Updated weights for policy 0, policy_version 5272 (0.0009) -[2023-10-10 12:53:16,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 10813440. Throughput: 0: 1801.4, 1: 1814.0. Samples: 2717264. Policy #0 lag: (min: 1.0, avg: 8.3, max: 33.0) -[2023-10-10 12:53:16,077][75634] Avg episode reward: [(0, '12.970'), (1, '11.100')] -[2023-10-10 12:53:16,087][76362] Saving new best policy, reward=12.970! -[2023-10-10 12:53:16,425][76542] Updated weights for policy 1, policy_version 5290 (0.0008) -[2023-10-10 12:53:16,802][76542] Updated weights for policy 1, policy_version 5300 (0.0009) -[2023-10-10 12:53:17,163][76542] Updated weights for policy 1, policy_version 5310 (0.0010) -[2023-10-10 12:53:17,282][76543] Updated weights for policy 0, policy_version 5282 (0.0009) -[2023-10-10 12:53:17,658][76543] Updated weights for policy 0, policy_version 5292 (0.0009) -[2023-10-10 12:53:18,031][76543] Updated weights for policy 0, policy_version 5302 (0.0008) -[2023-10-10 12:53:18,407][76543] Updated weights for policy 0, policy_version 5312 (0.0008) -[2023-10-10 12:53:20,855][76542] Updated weights for policy 1, policy_version 5320 (0.0010) -[2023-10-10 12:53:21,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 10878976. Throughput: 0: 1806.0, 1: 1814.8. Samples: 2727376. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-10 12:53:21,077][75634] Avg episode reward: [(0, '12.420'), (1, '10.540')] -[2023-10-10 12:53:21,232][76542] Updated weights for policy 1, policy_version 5330 (0.0009) -[2023-10-10 12:53:21,592][76542] Updated weights for policy 1, policy_version 5340 (0.0007) -[2023-10-10 12:53:22,265][76543] Updated weights for policy 0, policy_version 5322 (0.0007) -[2023-10-10 12:53:22,640][76543] Updated weights for policy 0, policy_version 5332 (0.0008) -[2023-10-10 12:53:23,018][76543] Updated weights for policy 0, policy_version 5342 (0.0009) -[2023-10-10 12:53:25,179][76542] Updated weights for policy 1, policy_version 5350 (0.0008) -[2023-10-10 12:53:25,548][76542] Updated weights for policy 1, policy_version 5360 (0.0007) -[2023-10-10 12:53:25,915][76542] Updated weights for policy 1, policy_version 5370 (0.0011) -[2023-10-10 12:53:26,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 10944512. Throughput: 0: 1798.4, 1: 1808.1. Samples: 2749604. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-10 12:53:26,077][75634] Avg episode reward: [(0, '10.770'), (1, '10.150')] -[2023-10-10 12:53:26,821][76543] Updated weights for policy 0, policy_version 5352 (0.0009) -[2023-10-10 12:53:27,186][76543] Updated weights for policy 0, policy_version 5362 (0.0009) -[2023-10-10 12:53:27,558][76543] Updated weights for policy 0, policy_version 5372 (0.0008) -[2023-10-10 12:53:29,566][76542] Updated weights for policy 1, policy_version 5380 (0.0011) -[2023-10-10 12:53:29,932][76542] Updated weights for policy 1, policy_version 5390 (0.0009) -[2023-10-10 12:53:30,312][76542] Updated weights for policy 1, policy_version 5400 (0.0007) -[2023-10-10 12:53:31,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 11042816. Throughput: 0: 1800.5, 1: 1810.9. Samples: 2771006. Policy #0 lag: (min: 4.0, avg: 10.9, max: 36.0) -[2023-10-10 12:53:31,076][75634] Avg episode reward: [(0, '11.680'), (1, '10.280')] -[2023-10-10 12:53:31,201][76543] Updated weights for policy 0, policy_version 5382 (0.0008) -[2023-10-10 12:53:31,573][76543] Updated weights for policy 0, policy_version 5392 (0.0007) -[2023-10-10 12:53:31,955][76543] Updated weights for policy 0, policy_version 5402 (0.0010) -[2023-10-10 12:53:33,903][76542] Updated weights for policy 1, policy_version 5410 (0.0008) -[2023-10-10 12:53:34,273][76542] Updated weights for policy 1, policy_version 5420 (0.0007) -[2023-10-10 12:53:34,652][76542] Updated weights for policy 1, policy_version 5430 (0.0011) -[2023-10-10 12:53:35,011][76542] Updated weights for policy 1, policy_version 5440 (0.0010) -[2023-10-10 12:53:35,555][76543] Updated weights for policy 0, policy_version 5412 (0.0011) -[2023-10-10 12:53:35,933][76543] Updated weights for policy 0, policy_version 5422 (0.0007) -[2023-10-10 12:53:36,076][75634] Fps is (10 sec: 16384.5, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 11108352. Throughput: 0: 1794.2, 1: 1820.6. Samples: 2782576. Policy #0 lag: (min: 4.0, avg: 10.9, max: 36.0) -[2023-10-10 12:53:36,076][75634] Avg episode reward: [(0, '11.870'), (1, '9.870')] -[2023-10-10 12:53:36,303][76543] Updated weights for policy 0, policy_version 5432 (0.0009) -[2023-10-10 12:53:38,647][76542] Updated weights for policy 1, policy_version 5450 (0.0009) -[2023-10-10 12:53:39,013][76542] Updated weights for policy 1, policy_version 5460 (0.0008) -[2023-10-10 12:53:39,376][76542] Updated weights for policy 1, policy_version 5470 (0.0009) -[2023-10-10 12:53:39,849][76543] Updated weights for policy 0, policy_version 5442 (0.0008) -[2023-10-10 12:53:40,217][76543] Updated weights for policy 0, policy_version 5452 (0.0009) -[2023-10-10 12:53:40,595][76543] Updated weights for policy 0, policy_version 5462 (0.0011) -[2023-10-10 12:53:40,970][76543] Updated weights for policy 0, policy_version 5472 (0.0010) -[2023-10-10 12:53:41,076][75634] Fps is (10 sec: 16383.5, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 11206656. Throughput: 0: 1803.7, 1: 1819.8. Samples: 2804052. Policy #0 lag: (min: 2.0, avg: 10.5, max: 34.0) -[2023-10-10 12:53:41,078][75634] Avg episode reward: [(0, '11.610'), (1, '10.480')] -[2023-10-10 12:53:43,342][76542] Updated weights for policy 1, policy_version 5480 (0.0007) -[2023-10-10 12:53:43,727][76542] Updated weights for policy 1, policy_version 5490 (0.0008) -[2023-10-10 12:53:44,104][76542] Updated weights for policy 1, policy_version 5500 (0.0007) -[2023-10-10 12:53:44,613][76543] Updated weights for policy 0, policy_version 5482 (0.0009) -[2023-10-10 12:53:44,993][76543] Updated weights for policy 0, policy_version 5492 (0.0010) -[2023-10-10 12:53:45,366][76543] Updated weights for policy 0, policy_version 5502 (0.0008) -[2023-10-10 12:53:46,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 11272192. Throughput: 0: 1810.3, 1: 1816.6. Samples: 2825378. Policy #0 lag: (min: 17.0, avg: 21.6, max: 46.0) -[2023-10-10 12:53:46,077][75634] Avg episode reward: [(0, '11.660'), (1, '10.990')] -[2023-10-10 12:53:47,597][76542] Updated weights for policy 1, policy_version 5510 (0.0008) -[2023-10-10 12:53:47,959][76542] Updated weights for policy 1, policy_version 5520 (0.0010) -[2023-10-10 12:53:48,322][76542] Updated weights for policy 1, policy_version 5530 (0.0009) -[2023-10-10 12:53:49,021][76543] Updated weights for policy 0, policy_version 5512 (0.0007) -[2023-10-10 12:53:49,392][76543] Updated weights for policy 0, policy_version 5522 (0.0007) -[2023-10-10 12:53:49,760][76543] Updated weights for policy 0, policy_version 5532 (0.0009) -[2023-10-10 12:53:51,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 11337728. Throughput: 0: 1806.0, 1: 1816.7. Samples: 2836414. Policy #0 lag: (min: 17.0, avg: 21.6, max: 46.0) -[2023-10-10 12:53:51,077][75634] Avg episode reward: [(0, '11.860'), (1, '12.060')] -[2023-10-10 12:53:51,079][76421] Saving new best policy, reward=12.060! -[2023-10-10 12:53:52,214][76542] Updated weights for policy 1, policy_version 5540 (0.0009) -[2023-10-10 12:53:52,580][76542] Updated weights for policy 1, policy_version 5550 (0.0009) -[2023-10-10 12:53:52,952][76542] Updated weights for policy 1, policy_version 5560 (0.0009) -[2023-10-10 12:53:53,602][76543] Updated weights for policy 0, policy_version 5542 (0.0010) -[2023-10-10 12:53:53,974][76543] Updated weights for policy 0, policy_version 5552 (0.0007) -[2023-10-10 12:53:54,345][76543] Updated weights for policy 0, policy_version 5562 (0.0011) -[2023-10-10 12:53:56,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 11403264. Throughput: 0: 1814.0, 1: 1811.1. Samples: 2858032. Policy #0 lag: (min: 17.0, avg: 28.7, max: 49.0) -[2023-10-10 12:53:56,076][75634] Avg episode reward: [(0, '12.600'), (1, '12.310')] -[2023-10-10 12:53:56,077][76421] Saving new best policy, reward=12.310! -[2023-10-10 12:53:56,676][76542] Updated weights for policy 1, policy_version 5570 (0.0009) -[2023-10-10 12:53:57,050][76542] Updated weights for policy 1, policy_version 5580 (0.0008) -[2023-10-10 12:53:57,422][76542] Updated weights for policy 1, policy_version 5590 (0.0008) -[2023-10-10 12:53:57,790][76542] Updated weights for policy 1, policy_version 5600 (0.0009) -[2023-10-10 12:53:57,894][76543] Updated weights for policy 0, policy_version 5572 (0.0009) -[2023-10-10 12:53:58,266][76543] Updated weights for policy 0, policy_version 5582 (0.0008) -[2023-10-10 12:53:58,643][76543] Updated weights for policy 0, policy_version 5592 (0.0007) -[2023-10-10 12:54:01,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 11468800. Throughput: 0: 1807.4, 1: 1808.5. Samples: 2879982. Policy #0 lag: (min: 17.0, avg: 28.7, max: 49.0) -[2023-10-10 12:54:01,076][75634] Avg episode reward: [(0, '12.030'), (1, '12.080')] -[2023-10-10 12:54:01,714][76542] Updated weights for policy 1, policy_version 5610 (0.0010) -[2023-10-10 12:54:02,078][76542] Updated weights for policy 1, policy_version 5620 (0.0009) -[2023-10-10 12:54:02,267][76543] Updated weights for policy 0, policy_version 5602 (0.0009) -[2023-10-10 12:54:02,454][76542] Updated weights for policy 1, policy_version 5630 (0.0008) -[2023-10-10 12:54:02,647][76543] Updated weights for policy 0, policy_version 5612 (0.0008) -[2023-10-10 12:54:03,014][76543] Updated weights for policy 0, policy_version 5622 (0.0007) -[2023-10-10 12:54:03,398][76543] Updated weights for policy 0, policy_version 5632 (0.0009) -[2023-10-10 12:54:06,042][76542] Updated weights for policy 1, policy_version 5640 (0.0010) -[2023-10-10 12:54:06,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 11534336. Throughput: 0: 1809.9, 1: 1810.5. Samples: 2890296. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:54:06,077][75634] Avg episode reward: [(0, '14.040'), (1, '12.100')] -[2023-10-10 12:54:06,078][76362] Saving new best policy, reward=14.040! -[2023-10-10 12:54:06,411][76542] Updated weights for policy 1, policy_version 5650 (0.0007) -[2023-10-10 12:54:06,776][76542] Updated weights for policy 1, policy_version 5660 (0.0008) -[2023-10-10 12:54:07,211][76543] Updated weights for policy 0, policy_version 5642 (0.0010) -[2023-10-10 12:54:07,582][76543] Updated weights for policy 0, policy_version 5652 (0.0008) -[2023-10-10 12:54:07,964][76543] Updated weights for policy 0, policy_version 5662 (0.0008) -[2023-10-10 12:54:10,478][76542] Updated weights for policy 1, policy_version 5670 (0.0010) -[2023-10-10 12:54:10,848][76542] Updated weights for policy 1, policy_version 5680 (0.0011) -[2023-10-10 12:54:11,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 11599872. Throughput: 0: 1811.1, 1: 1813.7. Samples: 2912720. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:54:11,077][75634] Avg episode reward: [(0, '14.220'), (1, '12.400')] -[2023-10-10 12:54:11,078][76362] Saving new best policy, reward=14.220! -[2023-10-10 12:54:11,226][76542] Updated weights for policy 1, policy_version 5690 (0.0010) -[2023-10-10 12:54:11,443][76421] Saving new best policy, reward=12.400! -[2023-10-10 12:54:11,722][76543] Updated weights for policy 0, policy_version 5672 (0.0010) -[2023-10-10 12:54:12,091][76543] Updated weights for policy 0, policy_version 5682 (0.0010) -[2023-10-10 12:54:12,478][76543] Updated weights for policy 0, policy_version 5692 (0.0008) -[2023-10-10 12:54:14,820][76542] Updated weights for policy 1, policy_version 5700 (0.0007) -[2023-10-10 12:54:15,194][76542] Updated weights for policy 1, policy_version 5710 (0.0011) -[2023-10-10 12:54:15,559][76542] Updated weights for policy 1, policy_version 5720 (0.0010) -[2023-10-10 12:54:16,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 11698176. Throughput: 0: 1806.6, 1: 1814.3. Samples: 2933944. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:54:16,076][75634] Avg episode reward: [(0, '14.010'), (1, '11.800')] -[2023-10-10 12:54:16,139][76543] Updated weights for policy 0, policy_version 5702 (0.0008) -[2023-10-10 12:54:16,513][76543] Updated weights for policy 0, policy_version 5712 (0.0010) -[2023-10-10 12:54:16,884][76543] Updated weights for policy 0, policy_version 5722 (0.0010) -[2023-10-10 12:54:19,242][76542] Updated weights for policy 1, policy_version 5730 (0.0011) -[2023-10-10 12:54:19,604][76542] Updated weights for policy 1, policy_version 5740 (0.0008) -[2023-10-10 12:54:19,979][76542] Updated weights for policy 1, policy_version 5750 (0.0009) -[2023-10-10 12:54:20,343][76542] Updated weights for policy 1, policy_version 5760 (0.0008) -[2023-10-10 12:54:20,526][76543] Updated weights for policy 0, policy_version 5732 (0.0009) -[2023-10-10 12:54:20,910][76543] Updated weights for policy 0, policy_version 5742 (0.0007) -[2023-10-10 12:54:21,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 11763712. Throughput: 0: 1809.3, 1: 1804.3. Samples: 2945188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:54:21,076][75634] Avg episode reward: [(0, '14.280'), (1, '11.780')] -[2023-10-10 12:54:21,276][76543] Updated weights for policy 0, policy_version 5752 (0.0009) -[2023-10-10 12:54:21,575][76362] Saving new best policy, reward=14.280! -[2023-10-10 12:54:23,986][76542] Updated weights for policy 1, policy_version 5770 (0.0007) -[2023-10-10 12:54:24,361][76542] Updated weights for policy 1, policy_version 5780 (0.0008) -[2023-10-10 12:54:24,724][76542] Updated weights for policy 1, policy_version 5790 (0.0008) -[2023-10-10 12:54:24,892][76543] Updated weights for policy 0, policy_version 5762 (0.0007) -[2023-10-10 12:54:25,269][76543] Updated weights for policy 0, policy_version 5772 (0.0007) -[2023-10-10 12:54:25,643][76543] Updated weights for policy 0, policy_version 5782 (0.0009) -[2023-10-10 12:54:26,007][76543] Updated weights for policy 0, policy_version 5792 (0.0008) -[2023-10-10 12:54:26,076][75634] Fps is (10 sec: 16383.6, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 11862016. Throughput: 0: 1812.2, 1: 1813.1. Samples: 2967192. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-10 12:54:26,077][75634] Avg episode reward: [(0, '14.640'), (1, '12.590')] -[2023-10-10 12:54:26,078][76362] Saving new best policy, reward=14.640! -[2023-10-10 12:54:26,079][76421] Saving new best policy, reward=12.590! -[2023-10-10 12:54:28,298][76542] Updated weights for policy 1, policy_version 5800 (0.0007) -[2023-10-10 12:54:28,679][76542] Updated weights for policy 1, policy_version 5810 (0.0009) -[2023-10-10 12:54:29,057][76542] Updated weights for policy 1, policy_version 5820 (0.0008) -[2023-10-10 12:54:29,861][76543] Updated weights for policy 0, policy_version 5802 (0.0009) -[2023-10-10 12:54:30,226][76543] Updated weights for policy 0, policy_version 5812 (0.0008) -[2023-10-10 12:54:30,608][76543] Updated weights for policy 0, policy_version 5822 (0.0007) -[2023-10-10 12:54:31,076][75634] Fps is (10 sec: 16383.4, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 11927552. Throughput: 0: 1815.6, 1: 1816.2. Samples: 2988812. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-10 12:54:31,077][75634] Avg episode reward: [(0, '14.400'), (1, '13.040')] -[2023-10-10 12:54:31,089][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000005824_5963776.pth... -[2023-10-10 12:54:31,090][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000005824_5963776.pth... -[2023-10-10 12:54:31,124][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000004128_4227072.pth -[2023-10-10 12:54:31,129][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000004128_4227072.pth -[2023-10-10 12:54:31,133][76421] Saving new best policy, reward=13.040! -[2023-10-10 12:54:32,713][76542] Updated weights for policy 1, policy_version 5830 (0.0009) -[2023-10-10 12:54:33,080][76542] Updated weights for policy 1, policy_version 5840 (0.0009) -[2023-10-10 12:54:33,444][76542] Updated weights for policy 1, policy_version 5850 (0.0010) -[2023-10-10 12:54:34,161][76543] Updated weights for policy 0, policy_version 5832 (0.0009) -[2023-10-10 12:54:34,544][76543] Updated weights for policy 0, policy_version 5842 (0.0011) -[2023-10-10 12:54:34,904][76543] Updated weights for policy 0, policy_version 5852 (0.0010) -[2023-10-10 12:54:36,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 11993088. Throughput: 0: 1811.1, 1: 1817.4. Samples: 2999694. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-10 12:54:36,077][75634] Avg episode reward: [(0, '13.320'), (1, '12.830')] -[2023-10-10 12:54:37,170][76542] Updated weights for policy 1, policy_version 5860 (0.0009) -[2023-10-10 12:54:37,538][76542] Updated weights for policy 1, policy_version 5870 (0.0007) -[2023-10-10 12:54:37,910][76542] Updated weights for policy 1, policy_version 5880 (0.0009) -[2023-10-10 12:54:38,496][76543] Updated weights for policy 0, policy_version 5862 (0.0008) -[2023-10-10 12:54:38,870][76543] Updated weights for policy 0, policy_version 5872 (0.0007) -[2023-10-10 12:54:39,248][76543] Updated weights for policy 0, policy_version 5882 (0.0008) -[2023-10-10 12:54:41,076][75634] Fps is (10 sec: 13107.7, 60 sec: 14199.6, 300 sec: 14440.1). Total num frames: 12058624. Throughput: 0: 1812.8, 1: 1822.4. Samples: 3021614. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-10 12:54:41,076][75634] Avg episode reward: [(0, '13.230'), (1, '12.180')] -[2023-10-10 12:54:41,443][76542] Updated weights for policy 1, policy_version 5890 (0.0009) -[2023-10-10 12:54:41,816][76542] Updated weights for policy 1, policy_version 5900 (0.0009) -[2023-10-10 12:54:42,177][76542] Updated weights for policy 1, policy_version 5910 (0.0008) -[2023-10-10 12:54:42,544][76542] Updated weights for policy 1, policy_version 5920 (0.0009) -[2023-10-10 12:54:42,827][76543] Updated weights for policy 0, policy_version 5892 (0.0008) -[2023-10-10 12:54:43,191][76543] Updated weights for policy 0, policy_version 5902 (0.0009) -[2023-10-10 12:54:43,569][76543] Updated weights for policy 0, policy_version 5912 (0.0008) -[2023-10-10 12:54:46,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 12124160. Throughput: 0: 1824.5, 1: 1828.4. Samples: 3044362. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-10 12:54:46,076][75634] Avg episode reward: [(0, '12.420'), (1, '12.350')] -[2023-10-10 12:54:46,286][76542] Updated weights for policy 1, policy_version 5930 (0.0007) -[2023-10-10 12:54:46,659][76542] Updated weights for policy 1, policy_version 5940 (0.0008) -[2023-10-10 12:54:47,031][76542] Updated weights for policy 1, policy_version 5950 (0.0008) -[2023-10-10 12:54:47,339][76543] Updated weights for policy 0, policy_version 5922 (0.0009) -[2023-10-10 12:54:47,719][76543] Updated weights for policy 0, policy_version 5932 (0.0007) -[2023-10-10 12:54:48,084][76543] Updated weights for policy 0, policy_version 5942 (0.0008) -[2023-10-10 12:54:48,465][76543] Updated weights for policy 0, policy_version 5952 (0.0007) -[2023-10-10 12:54:50,837][76542] Updated weights for policy 1, policy_version 5960 (0.0009) -[2023-10-10 12:54:51,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 12189696. Throughput: 0: 1826.4, 1: 1823.6. Samples: 3054544. Policy #0 lag: (min: 17.0, avg: 21.9, max: 49.0) -[2023-10-10 12:54:51,076][75634] Avg episode reward: [(0, '12.380'), (1, '13.520')] -[2023-10-10 12:54:51,209][76542] Updated weights for policy 1, policy_version 5970 (0.0009) -[2023-10-10 12:54:51,582][76542] Updated weights for policy 1, policy_version 5980 (0.0009) -[2023-10-10 12:54:51,728][76421] Saving new best policy, reward=13.520! -[2023-10-10 12:54:52,113][76543] Updated weights for policy 0, policy_version 5962 (0.0010) -[2023-10-10 12:54:52,480][76543] Updated weights for policy 0, policy_version 5972 (0.0010) -[2023-10-10 12:54:52,864][76543] Updated weights for policy 0, policy_version 5982 (0.0011) -[2023-10-10 12:54:55,199][76542] Updated weights for policy 1, policy_version 5990 (0.0008) -[2023-10-10 12:54:55,575][76542] Updated weights for policy 1, policy_version 6000 (0.0007) -[2023-10-10 12:54:55,942][76542] Updated weights for policy 1, policy_version 6010 (0.0008) -[2023-10-10 12:54:56,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 12255232. Throughput: 0: 1826.7, 1: 1826.0. Samples: 3077090. Policy #0 lag: (min: 17.0, avg: 21.9, max: 49.0) -[2023-10-10 12:54:56,077][75634] Avg episode reward: [(0, '11.960'), (1, '12.700')] -[2023-10-10 12:54:56,647][76543] Updated weights for policy 0, policy_version 5992 (0.0007) -[2023-10-10 12:54:57,015][76543] Updated weights for policy 0, policy_version 6002 (0.0008) -[2023-10-10 12:54:57,399][76543] Updated weights for policy 0, policy_version 6012 (0.0008) -[2023-10-10 12:54:59,716][76542] Updated weights for policy 1, policy_version 6020 (0.0007) -[2023-10-10 12:55:00,085][76542] Updated weights for policy 1, policy_version 6030 (0.0007) -[2023-10-10 12:55:00,455][76542] Updated weights for policy 1, policy_version 6040 (0.0009) -[2023-10-10 12:55:01,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 12353536. Throughput: 0: 1826.3, 1: 1823.6. Samples: 3098186. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:55:01,076][75634] Avg episode reward: [(0, '12.450'), (1, '12.300')] -[2023-10-10 12:55:01,163][76543] Updated weights for policy 0, policy_version 6022 (0.0009) -[2023-10-10 12:55:01,527][76543] Updated weights for policy 0, policy_version 6032 (0.0007) -[2023-10-10 12:55:01,910][76543] Updated weights for policy 0, policy_version 6042 (0.0007) -[2023-10-10 12:55:04,075][76542] Updated weights for policy 1, policy_version 6050 (0.0010) -[2023-10-10 12:55:04,449][76542] Updated weights for policy 1, policy_version 6060 (0.0008) -[2023-10-10 12:55:04,816][76542] Updated weights for policy 1, policy_version 6070 (0.0010) -[2023-10-10 12:55:05,187][76542] Updated weights for policy 1, policy_version 6080 (0.0010) -[2023-10-10 12:55:05,492][76543] Updated weights for policy 0, policy_version 6052 (0.0008) -[2023-10-10 12:55:05,867][76543] Updated weights for policy 0, policy_version 6062 (0.0009) -[2023-10-10 12:55:06,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 12419072. Throughput: 0: 1827.6, 1: 1827.6. Samples: 3109676. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:55:06,077][75634] Avg episode reward: [(0, '13.540'), (1, '12.320')] -[2023-10-10 12:55:06,242][76543] Updated weights for policy 0, policy_version 6072 (0.0008) -[2023-10-10 12:55:08,856][76542] Updated weights for policy 1, policy_version 6090 (0.0008) -[2023-10-10 12:55:09,230][76542] Updated weights for policy 1, policy_version 6100 (0.0009) -[2023-10-10 12:55:09,604][76542] Updated weights for policy 1, policy_version 6110 (0.0008) -[2023-10-10 12:55:09,951][76543] Updated weights for policy 0, policy_version 6082 (0.0007) -[2023-10-10 12:55:10,327][76543] Updated weights for policy 0, policy_version 6092 (0.0007) -[2023-10-10 12:55:10,699][76543] Updated weights for policy 0, policy_version 6102 (0.0009) -[2023-10-10 12:55:11,076][75634] Fps is (10 sec: 16383.6, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 12517376. Throughput: 0: 1819.5, 1: 1822.4. Samples: 3131080. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-10-10 12:55:11,077][75634] Avg episode reward: [(0, '14.390'), (1, '12.900')] -[2023-10-10 12:55:11,078][76543] Updated weights for policy 0, policy_version 6112 (0.0010) -[2023-10-10 12:55:13,258][76542] Updated weights for policy 1, policy_version 6120 (0.0008) -[2023-10-10 12:55:13,638][76542] Updated weights for policy 1, policy_version 6130 (0.0011) -[2023-10-10 12:55:14,011][76542] Updated weights for policy 1, policy_version 6140 (0.0011) -[2023-10-10 12:55:14,748][76543] Updated weights for policy 0, policy_version 6122 (0.0011) -[2023-10-10 12:55:15,126][76543] Updated weights for policy 0, policy_version 6132 (0.0007) -[2023-10-10 12:55:15,501][76543] Updated weights for policy 0, policy_version 6142 (0.0009) -[2023-10-10 12:55:16,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 12582912. Throughput: 0: 1820.0, 1: 1823.9. Samples: 3152786. Policy #0 lag: (min: 10.0, avg: 10.3, max: 21.0) -[2023-10-10 12:55:16,077][75634] Avg episode reward: [(0, '14.790'), (1, '13.550')] -[2023-10-10 12:55:16,088][76362] Saving new best policy, reward=14.790! -[2023-10-10 12:55:16,089][76421] Saving new best policy, reward=13.550! -[2023-10-10 12:55:17,627][76542] Updated weights for policy 1, policy_version 6150 (0.0008) -[2023-10-10 12:55:18,010][76542] Updated weights for policy 1, policy_version 6160 (0.0009) -[2023-10-10 12:55:18,388][76542] Updated weights for policy 1, policy_version 6170 (0.0007) -[2023-10-10 12:55:19,230][76543] Updated weights for policy 0, policy_version 6152 (0.0008) -[2023-10-10 12:55:19,602][76543] Updated weights for policy 0, policy_version 6162 (0.0009) -[2023-10-10 12:55:19,968][76543] Updated weights for policy 0, policy_version 6172 (0.0008) -[2023-10-10 12:55:21,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 12648448. Throughput: 0: 1818.7, 1: 1825.9. Samples: 3163702. Policy #0 lag: (min: 10.0, avg: 10.3, max: 21.0) -[2023-10-10 12:55:21,076][75634] Avg episode reward: [(0, '14.540'), (1, '13.320')] -[2023-10-10 12:55:22,055][76542] Updated weights for policy 1, policy_version 6180 (0.0007) -[2023-10-10 12:55:22,427][76542] Updated weights for policy 1, policy_version 6190 (0.0007) -[2023-10-10 12:55:22,798][76542] Updated weights for policy 1, policy_version 6200 (0.0008) -[2023-10-10 12:55:23,641][76543] Updated weights for policy 0, policy_version 6182 (0.0010) -[2023-10-10 12:55:24,011][76543] Updated weights for policy 0, policy_version 6192 (0.0010) -[2023-10-10 12:55:24,386][76543] Updated weights for policy 0, policy_version 6202 (0.0009) -[2023-10-10 12:55:26,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 12713984. Throughput: 0: 1820.1, 1: 1820.2. Samples: 3185428. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-10 12:55:26,077][75634] Avg episode reward: [(0, '14.540'), (1, '14.160')] -[2023-10-10 12:55:26,078][76421] Saving new best policy, reward=14.160! -[2023-10-10 12:55:26,564][76542] Updated weights for policy 1, policy_version 6210 (0.0008) -[2023-10-10 12:55:26,935][76542] Updated weights for policy 1, policy_version 6220 (0.0008) -[2023-10-10 12:55:27,305][76542] Updated weights for policy 1, policy_version 6230 (0.0009) -[2023-10-10 12:55:27,666][76542] Updated weights for policy 1, policy_version 6240 (0.0009) -[2023-10-10 12:55:28,108][76543] Updated weights for policy 0, policy_version 6212 (0.0009) -[2023-10-10 12:55:28,478][76543] Updated weights for policy 0, policy_version 6222 (0.0010) -[2023-10-10 12:55:28,853][76543] Updated weights for policy 0, policy_version 6232 (0.0007) -[2023-10-10 12:55:31,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 12779520. Throughput: 0: 1810.2, 1: 1816.2. Samples: 3207548. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-10 12:55:31,076][75634] Avg episode reward: [(0, '13.700'), (1, '14.470')] -[2023-10-10 12:55:31,447][76542] Updated weights for policy 1, policy_version 6250 (0.0008) -[2023-10-10 12:55:31,812][76542] Updated weights for policy 1, policy_version 6260 (0.0009) -[2023-10-10 12:55:32,186][76542] Updated weights for policy 1, policy_version 6270 (0.0007) -[2023-10-10 12:55:32,265][76421] Saving new best policy, reward=14.470! -[2023-10-10 12:55:32,617][76543] Updated weights for policy 0, policy_version 6242 (0.0007) -[2023-10-10 12:55:32,996][76543] Updated weights for policy 0, policy_version 6252 (0.0008) -[2023-10-10 12:55:33,365][76543] Updated weights for policy 0, policy_version 6262 (0.0009) -[2023-10-10 12:55:33,741][76543] Updated weights for policy 0, policy_version 6272 (0.0007) -[2023-10-10 12:55:35,890][76542] Updated weights for policy 1, policy_version 6280 (0.0008) -[2023-10-10 12:55:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 12845056. Throughput: 0: 1818.3, 1: 1817.9. Samples: 3218170. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:55:36,077][75634] Avg episode reward: [(0, '13.420'), (1, '14.050')] -[2023-10-10 12:55:36,263][76542] Updated weights for policy 1, policy_version 6290 (0.0009) -[2023-10-10 12:55:36,636][76542] Updated weights for policy 1, policy_version 6300 (0.0009) -[2023-10-10 12:55:37,398][76543] Updated weights for policy 0, policy_version 6282 (0.0010) -[2023-10-10 12:55:37,760][76543] Updated weights for policy 0, policy_version 6292 (0.0010) -[2023-10-10 12:55:38,143][76543] Updated weights for policy 0, policy_version 6302 (0.0010) -[2023-10-10 12:55:40,261][76542] Updated weights for policy 1, policy_version 6310 (0.0009) -[2023-10-10 12:55:40,628][76542] Updated weights for policy 1, policy_version 6320 (0.0008) -[2023-10-10 12:55:41,005][76542] Updated weights for policy 1, policy_version 6330 (0.0010) -[2023-10-10 12:55:41,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 12910592. Throughput: 0: 1812.1, 1: 1817.4. Samples: 3240416. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:55:41,077][75634] Avg episode reward: [(0, '13.780'), (1, '11.930')] -[2023-10-10 12:55:41,814][76543] Updated weights for policy 0, policy_version 6312 (0.0007) -[2023-10-10 12:55:42,185][76543] Updated weights for policy 0, policy_version 6322 (0.0007) -[2023-10-10 12:55:42,565][76543] Updated weights for policy 0, policy_version 6332 (0.0009) -[2023-10-10 12:55:44,808][76542] Updated weights for policy 1, policy_version 6340 (0.0008) -[2023-10-10 12:55:45,190][76542] Updated weights for policy 1, policy_version 6350 (0.0007) -[2023-10-10 12:55:45,566][76542] Updated weights for policy 1, policy_version 6360 (0.0009) -[2023-10-10 12:55:46,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 13008896. Throughput: 0: 1815.5, 1: 1817.9. Samples: 3261686. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:55:46,077][75634] Avg episode reward: [(0, '13.580'), (1, '12.980')] -[2023-10-10 12:55:46,164][76543] Updated weights for policy 0, policy_version 6342 (0.0008) -[2023-10-10 12:55:46,538][76543] Updated weights for policy 0, policy_version 6352 (0.0008) -[2023-10-10 12:55:46,911][76543] Updated weights for policy 0, policy_version 6362 (0.0008) -[2023-10-10 12:55:49,282][76542] Updated weights for policy 1, policy_version 6370 (0.0008) -[2023-10-10 12:55:49,653][76542] Updated weights for policy 1, policy_version 6380 (0.0008) -[2023-10-10 12:55:50,017][76542] Updated weights for policy 1, policy_version 6390 (0.0007) -[2023-10-10 12:55:50,391][76542] Updated weights for policy 1, policy_version 6400 (0.0009) -[2023-10-10 12:55:50,741][76543] Updated weights for policy 0, policy_version 6372 (0.0007) -[2023-10-10 12:55:51,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 13074432. Throughput: 0: 1815.8, 1: 1809.6. Samples: 3272820. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:55:51,076][75634] Avg episode reward: [(0, '14.790'), (1, '12.960')] -[2023-10-10 12:55:51,114][76543] Updated weights for policy 0, policy_version 6382 (0.0007) -[2023-10-10 12:55:51,491][76543] Updated weights for policy 0, policy_version 6392 (0.0007) -[2023-10-10 12:55:54,028][76542] Updated weights for policy 1, policy_version 6410 (0.0007) -[2023-10-10 12:55:54,396][76542] Updated weights for policy 1, policy_version 6420 (0.0009) -[2023-10-10 12:55:54,766][76542] Updated weights for policy 1, policy_version 6430 (0.0010) -[2023-10-10 12:55:55,043][76543] Updated weights for policy 0, policy_version 6402 (0.0009) -[2023-10-10 12:55:55,421][76543] Updated weights for policy 0, policy_version 6412 (0.0010) -[2023-10-10 12:55:55,793][76543] Updated weights for policy 0, policy_version 6422 (0.0010) -[2023-10-10 12:55:56,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 13139968. Throughput: 0: 1822.2, 1: 1814.9. Samples: 3294750. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:55:56,077][75634] Avg episode reward: [(0, '15.000'), (1, '12.610')] -[2023-10-10 12:55:56,169][76362] Saving new best policy, reward=15.000! -[2023-10-10 12:55:56,171][76543] Updated weights for policy 0, policy_version 6432 (0.0011) -[2023-10-10 12:55:58,600][76542] Updated weights for policy 1, policy_version 6440 (0.0008) -[2023-10-10 12:55:58,973][76542] Updated weights for policy 1, policy_version 6450 (0.0007) -[2023-10-10 12:55:59,352][76542] Updated weights for policy 1, policy_version 6460 (0.0009) -[2023-10-10 12:55:59,848][76543] Updated weights for policy 0, policy_version 6442 (0.0008) -[2023-10-10 12:56:00,223][76543] Updated weights for policy 0, policy_version 6452 (0.0007) -[2023-10-10 12:56:00,599][76543] Updated weights for policy 0, policy_version 6462 (0.0009) -[2023-10-10 12:56:01,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 13238272. Throughput: 0: 1824.8, 1: 1800.4. Samples: 3315918. Policy #0 lag: (min: 31.0, avg: 32.6, max: 59.0) -[2023-10-10 12:56:01,077][75634] Avg episode reward: [(0, '15.330'), (1, '12.410')] -[2023-10-10 12:56:01,087][76362] Saving new best policy, reward=15.330! -[2023-10-10 12:56:03,213][76542] Updated weights for policy 1, policy_version 6470 (0.0010) -[2023-10-10 12:56:03,584][76542] Updated weights for policy 1, policy_version 6480 (0.0008) -[2023-10-10 12:56:03,960][76542] Updated weights for policy 1, policy_version 6490 (0.0008) -[2023-10-10 12:56:04,294][76543] Updated weights for policy 0, policy_version 6472 (0.0008) -[2023-10-10 12:56:04,670][76543] Updated weights for policy 0, policy_version 6482 (0.0010) -[2023-10-10 12:56:05,061][76543] Updated weights for policy 0, policy_version 6492 (0.0009) -[2023-10-10 12:56:06,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 13303808. Throughput: 0: 1823.6, 1: 1809.6. Samples: 3327196. Policy #0 lag: (min: 31.0, avg: 32.6, max: 59.0) -[2023-10-10 12:56:06,077][75634] Avg episode reward: [(0, '16.100'), (1, '12.670')] -[2023-10-10 12:56:06,078][76362] Saving new best policy, reward=16.100! -[2023-10-10 12:56:07,671][76542] Updated weights for policy 1, policy_version 6500 (0.0008) -[2023-10-10 12:56:08,038][76542] Updated weights for policy 1, policy_version 6510 (0.0010) -[2023-10-10 12:56:08,406][76542] Updated weights for policy 1, policy_version 6520 (0.0009) -[2023-10-10 12:56:08,646][76543] Updated weights for policy 0, policy_version 6502 (0.0009) -[2023-10-10 12:56:09,016][76543] Updated weights for policy 0, policy_version 6512 (0.0008) -[2023-10-10 12:56:09,405][76543] Updated weights for policy 0, policy_version 6522 (0.0009) -[2023-10-10 12:56:11,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 13369344. Throughput: 0: 1822.9, 1: 1797.3. Samples: 3348332. Policy #0 lag: (min: 0.0, avg: 24.8, max: 32.0) -[2023-10-10 12:56:11,076][75634] Avg episode reward: [(0, '16.410'), (1, '11.820')] -[2023-10-10 12:56:11,077][76362] Saving new best policy, reward=16.410! -[2023-10-10 12:56:12,114][76542] Updated weights for policy 1, policy_version 6530 (0.0008) -[2023-10-10 12:56:12,475][76542] Updated weights for policy 1, policy_version 6540 (0.0007) -[2023-10-10 12:56:12,846][76542] Updated weights for policy 1, policy_version 6550 (0.0008) -[2023-10-10 12:56:13,155][76543] Updated weights for policy 0, policy_version 6532 (0.0010) -[2023-10-10 12:56:13,206][76542] Updated weights for policy 1, policy_version 6560 (0.0008) -[2023-10-10 12:56:13,529][76543] Updated weights for policy 0, policy_version 6542 (0.0009) -[2023-10-10 12:56:13,894][76543] Updated weights for policy 0, policy_version 6552 (0.0007) -[2023-10-10 12:56:16,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 13434880. Throughput: 0: 1818.9, 1: 1797.0. Samples: 3370266. Policy #0 lag: (min: 0.0, avg: 24.8, max: 32.0) -[2023-10-10 12:56:16,077][75634] Avg episode reward: [(0, '16.990'), (1, '11.910')] -[2023-10-10 12:56:16,089][76362] Saving new best policy, reward=16.990! -[2023-10-10 12:56:17,018][76542] Updated weights for policy 1, policy_version 6570 (0.0010) -[2023-10-10 12:56:17,384][76542] Updated weights for policy 1, policy_version 6580 (0.0009) -[2023-10-10 12:56:17,598][76543] Updated weights for policy 0, policy_version 6562 (0.0009) -[2023-10-10 12:56:17,755][76542] Updated weights for policy 1, policy_version 6590 (0.0010) -[2023-10-10 12:56:17,972][76543] Updated weights for policy 0, policy_version 6572 (0.0008) -[2023-10-10 12:56:18,348][76543] Updated weights for policy 0, policy_version 6582 (0.0007) -[2023-10-10 12:56:18,728][76543] Updated weights for policy 0, policy_version 6592 (0.0007) -[2023-10-10 12:56:21,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 13500416. Throughput: 0: 1820.6, 1: 1795.6. Samples: 3380898. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:56:21,076][75634] Avg episode reward: [(0, '17.050'), (1, '12.230')] -[2023-10-10 12:56:21,077][76362] Saving new best policy, reward=17.050! -[2023-10-10 12:56:21,497][76542] Updated weights for policy 1, policy_version 6600 (0.0009) -[2023-10-10 12:56:21,869][76542] Updated weights for policy 1, policy_version 6610 (0.0008) -[2023-10-10 12:56:22,246][76542] Updated weights for policy 1, policy_version 6620 (0.0008) -[2023-10-10 12:56:22,360][76543] Updated weights for policy 0, policy_version 6602 (0.0007) -[2023-10-10 12:56:22,723][76543] Updated weights for policy 0, policy_version 6612 (0.0008) -[2023-10-10 12:56:23,100][76543] Updated weights for policy 0, policy_version 6622 (0.0009) -[2023-10-10 12:56:25,973][76542] Updated weights for policy 1, policy_version 6630 (0.0008) -[2023-10-10 12:56:26,076][75634] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 13565952. Throughput: 0: 1820.2, 1: 1796.4. Samples: 3403162. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:56:26,076][75634] Avg episode reward: [(0, '18.620'), (1, '13.170')] -[2023-10-10 12:56:26,077][76362] Saving new best policy, reward=18.620! -[2023-10-10 12:56:26,347][76542] Updated weights for policy 1, policy_version 6640 (0.0010) -[2023-10-10 12:56:26,727][76542] Updated weights for policy 1, policy_version 6650 (0.0007) -[2023-10-10 12:56:26,756][76543] Updated weights for policy 0, policy_version 6632 (0.0010) -[2023-10-10 12:56:27,130][76543] Updated weights for policy 0, policy_version 6642 (0.0010) -[2023-10-10 12:56:27,495][76543] Updated weights for policy 0, policy_version 6652 (0.0010) -[2023-10-10 12:56:30,375][76542] Updated weights for policy 1, policy_version 6660 (0.0009) -[2023-10-10 12:56:30,746][76542] Updated weights for policy 1, policy_version 6670 (0.0010) -[2023-10-10 12:56:31,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 13631488. Throughput: 0: 1824.1, 1: 1816.8. Samples: 3425528. Policy #0 lag: (min: 31.0, avg: 32.5, max: 57.0) -[2023-10-10 12:56:31,076][75634] Avg episode reward: [(0, '16.260'), (1, '13.270')] -[2023-10-10 12:56:31,118][76542] Updated weights for policy 1, policy_version 6680 (0.0008) -[2023-10-10 12:56:31,237][76543] Updated weights for policy 0, policy_version 6662 (0.0007) -[2023-10-10 12:56:31,412][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000006688_6848512.pth... -[2023-10-10 12:56:31,453][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000004992_5111808.pth -[2023-10-10 12:56:31,616][76543] Updated weights for policy 0, policy_version 6672 (0.0009) -[2023-10-10 12:56:31,992][76543] Updated weights for policy 0, policy_version 6682 (0.0008) -[2023-10-10 12:56:32,210][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000006688_6848512.pth... -[2023-10-10 12:56:32,248][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000004960_5079040.pth -[2023-10-10 12:56:34,719][76542] Updated weights for policy 1, policy_version 6690 (0.0007) -[2023-10-10 12:56:35,082][76542] Updated weights for policy 1, policy_version 6700 (0.0010) -[2023-10-10 12:56:35,447][76542] Updated weights for policy 1, policy_version 6710 (0.0009) -[2023-10-10 12:56:35,538][76543] Updated weights for policy 0, policy_version 6692 (0.0007) -[2023-10-10 12:56:35,822][76542] Updated weights for policy 1, policy_version 6720 (0.0009) -[2023-10-10 12:56:35,919][76543] Updated weights for policy 0, policy_version 6702 (0.0008) -[2023-10-10 12:56:36,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 13729792. Throughput: 0: 1824.6, 1: 1803.4. Samples: 3436082. Policy #0 lag: (min: 31.0, avg: 32.5, max: 57.0) -[2023-10-10 12:56:36,077][75634] Avg episode reward: [(0, '16.840'), (1, '13.880')] -[2023-10-10 12:56:36,287][76543] Updated weights for policy 0, policy_version 6712 (0.0007) -[2023-10-10 12:56:39,619][76542] Updated weights for policy 1, policy_version 6730 (0.0011) -[2023-10-10 12:56:39,925][76543] Updated weights for policy 0, policy_version 6722 (0.0008) -[2023-10-10 12:56:39,989][76542] Updated weights for policy 1, policy_version 6740 (0.0009) -[2023-10-10 12:56:40,297][76543] Updated weights for policy 0, policy_version 6732 (0.0009) -[2023-10-10 12:56:40,353][76542] Updated weights for policy 1, policy_version 6750 (0.0008) -[2023-10-10 12:56:40,673][76543] Updated weights for policy 0, policy_version 6742 (0.0009) -[2023-10-10 12:56:41,051][76543] Updated weights for policy 0, policy_version 6752 (0.0007) -[2023-10-10 12:56:41,076][75634] Fps is (10 sec: 19660.7, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 13828096. Throughput: 0: 1821.2, 1: 1812.1. Samples: 3458250. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 12:56:41,077][75634] Avg episode reward: [(0, '16.190'), (1, '13.690')] -[2023-10-10 12:56:44,054][76542] Updated weights for policy 1, policy_version 6760 (0.0009) -[2023-10-10 12:56:44,423][76542] Updated weights for policy 1, policy_version 6770 (0.0008) -[2023-10-10 12:56:44,734][76543] Updated weights for policy 0, policy_version 6762 (0.0008) -[2023-10-10 12:56:44,785][76542] Updated weights for policy 1, policy_version 6780 (0.0007) -[2023-10-10 12:56:45,108][76543] Updated weights for policy 0, policy_version 6772 (0.0007) -[2023-10-10 12:56:45,481][76543] Updated weights for policy 0, policy_version 6782 (0.0008) -[2023-10-10 12:56:46,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 13893632. Throughput: 0: 1825.9, 1: 1809.8. Samples: 3479526. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-10 12:56:46,076][75634] Avg episode reward: [(0, '15.640'), (1, '13.790')] -[2023-10-10 12:56:48,599][76542] Updated weights for policy 1, policy_version 6790 (0.0008) -[2023-10-10 12:56:48,991][76542] Updated weights for policy 1, policy_version 6800 (0.0009) -[2023-10-10 12:56:49,172][76543] Updated weights for policy 0, policy_version 6792 (0.0007) -[2023-10-10 12:56:49,355][76542] Updated weights for policy 1, policy_version 6810 (0.0008) -[2023-10-10 12:56:49,551][76543] Updated weights for policy 0, policy_version 6802 (0.0009) -[2023-10-10 12:56:49,933][76543] Updated weights for policy 0, policy_version 6812 (0.0009) -[2023-10-10 12:56:51,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 13959168. Throughput: 0: 1827.7, 1: 1814.5. Samples: 3491098. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-10 12:56:51,076][75634] Avg episode reward: [(0, '15.870'), (1, '13.230')] -[2023-10-10 12:56:52,996][76542] Updated weights for policy 1, policy_version 6820 (0.0007) -[2023-10-10 12:56:53,376][76542] Updated weights for policy 1, policy_version 6830 (0.0010) -[2023-10-10 12:56:53,485][76543] Updated weights for policy 0, policy_version 6822 (0.0007) -[2023-10-10 12:56:53,750][76542] Updated weights for policy 1, policy_version 6840 (0.0008) -[2023-10-10 12:56:53,860][76543] Updated weights for policy 0, policy_version 6832 (0.0007) -[2023-10-10 12:56:54,234][76543] Updated weights for policy 0, policy_version 6842 (0.0010) -[2023-10-10 12:56:56,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 14024704. Throughput: 0: 1828.5, 1: 1802.9. Samples: 3511748. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 12:56:56,077][75634] Avg episode reward: [(0, '16.980'), (1, '12.880')] -[2023-10-10 12:56:57,452][76542] Updated weights for policy 1, policy_version 6850 (0.0008) -[2023-10-10 12:56:57,826][76542] Updated weights for policy 1, policy_version 6860 (0.0008) -[2023-10-10 12:56:57,936][76543] Updated weights for policy 0, policy_version 6852 (0.0008) -[2023-10-10 12:56:58,193][76542] Updated weights for policy 1, policy_version 6870 (0.0009) -[2023-10-10 12:56:58,301][76543] Updated weights for policy 0, policy_version 6862 (0.0008) -[2023-10-10 12:56:58,567][76542] Updated weights for policy 1, policy_version 6880 (0.0008) -[2023-10-10 12:56:58,679][76543] Updated weights for policy 0, policy_version 6872 (0.0007) -[2023-10-10 12:57:01,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 14090240. Throughput: 0: 1833.7, 1: 1805.3. Samples: 3534016. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 12:57:01,076][75634] Avg episode reward: [(0, '17.390'), (1, '13.380')] -[2023-10-10 12:57:02,244][76543] Updated weights for policy 0, policy_version 6882 (0.0008) -[2023-10-10 12:57:02,342][76542] Updated weights for policy 1, policy_version 6890 (0.0007) -[2023-10-10 12:57:02,615][76543] Updated weights for policy 0, policy_version 6892 (0.0007) -[2023-10-10 12:57:02,710][76542] Updated weights for policy 1, policy_version 6900 (0.0007) -[2023-10-10 12:57:02,978][76543] Updated weights for policy 0, policy_version 6902 (0.0009) -[2023-10-10 12:57:03,087][76542] Updated weights for policy 1, policy_version 6910 (0.0008) -[2023-10-10 12:57:03,354][76543] Updated weights for policy 0, policy_version 6912 (0.0010) -[2023-10-10 12:57:06,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 14155776. Throughput: 0: 1820.6, 1: 1807.1. Samples: 3544144. Policy #0 lag: (min: 24.0, avg: 49.4, max: 56.0) -[2023-10-10 12:57:06,077][75634] Avg episode reward: [(0, '17.260'), (1, '13.750')] -[2023-10-10 12:57:06,701][76542] Updated weights for policy 1, policy_version 6920 (0.0009) -[2023-10-10 12:57:07,068][76542] Updated weights for policy 1, policy_version 6930 (0.0009) -[2023-10-10 12:57:07,075][76543] Updated weights for policy 0, policy_version 6922 (0.0009) -[2023-10-10 12:57:07,427][76542] Updated weights for policy 1, policy_version 6940 (0.0008) -[2023-10-10 12:57:07,441][76543] Updated weights for policy 0, policy_version 6932 (0.0007) -[2023-10-10 12:57:07,818][76543] Updated weights for policy 0, policy_version 6942 (0.0008) -[2023-10-10 12:57:10,986][76542] Updated weights for policy 1, policy_version 6950 (0.0008) -[2023-10-10 12:57:11,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 14221312. Throughput: 0: 1828.2, 1: 1809.1. Samples: 3566840. Policy #0 lag: (min: 24.0, avg: 49.4, max: 56.0) -[2023-10-10 12:57:11,076][75634] Avg episode reward: [(0, '17.230'), (1, '13.440')] -[2023-10-10 12:57:11,346][76542] Updated weights for policy 1, policy_version 6960 (0.0009) -[2023-10-10 12:57:11,545][76543] Updated weights for policy 0, policy_version 6952 (0.0007) -[2023-10-10 12:57:11,713][76542] Updated weights for policy 1, policy_version 6970 (0.0007) -[2023-10-10 12:57:11,926][76543] Updated weights for policy 0, policy_version 6962 (0.0007) -[2023-10-10 12:57:12,300][76543] Updated weights for policy 0, policy_version 6972 (0.0009) -[2023-10-10 12:57:15,364][76542] Updated weights for policy 1, policy_version 6980 (0.0008) -[2023-10-10 12:57:15,735][76542] Updated weights for policy 1, policy_version 6990 (0.0010) -[2023-10-10 12:57:16,066][76543] Updated weights for policy 0, policy_version 6982 (0.0009) -[2023-10-10 12:57:16,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 14286848. Throughput: 0: 1819.3, 1: 1811.4. Samples: 3588908. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:57:16,077][75634] Avg episode reward: [(0, '16.760'), (1, '13.460')] -[2023-10-10 12:57:16,101][76542] Updated weights for policy 1, policy_version 7000 (0.0010) -[2023-10-10 12:57:16,430][76543] Updated weights for policy 0, policy_version 6992 (0.0008) -[2023-10-10 12:57:16,807][76543] Updated weights for policy 0, policy_version 7002 (0.0009) -[2023-10-10 12:57:19,922][76542] Updated weights for policy 1, policy_version 7010 (0.0010) -[2023-10-10 12:57:20,287][76542] Updated weights for policy 1, policy_version 7020 (0.0008) -[2023-10-10 12:57:20,629][76543] Updated weights for policy 0, policy_version 7012 (0.0010) -[2023-10-10 12:57:20,658][76542] Updated weights for policy 1, policy_version 7030 (0.0008) -[2023-10-10 12:57:21,010][76543] Updated weights for policy 0, policy_version 7022 (0.0008) -[2023-10-10 12:57:21,026][76542] Updated weights for policy 1, policy_version 7040 (0.0007) -[2023-10-10 12:57:21,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 14385152. Throughput: 0: 1814.1, 1: 1808.9. Samples: 3599114. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:57:21,076][75634] Avg episode reward: [(0, '16.680'), (1, '13.740')] -[2023-10-10 12:57:21,384][76543] Updated weights for policy 0, policy_version 7032 (0.0010) -[2023-10-10 12:57:24,713][76542] Updated weights for policy 1, policy_version 7050 (0.0010) -[2023-10-10 12:57:25,029][76543] Updated weights for policy 0, policy_version 7042 (0.0009) -[2023-10-10 12:57:25,080][76542] Updated weights for policy 1, policy_version 7060 (0.0009) -[2023-10-10 12:57:25,403][76543] Updated weights for policy 0, policy_version 7052 (0.0010) -[2023-10-10 12:57:25,439][76542] Updated weights for policy 1, policy_version 7070 (0.0007) -[2023-10-10 12:57:25,775][76543] Updated weights for policy 0, policy_version 7062 (0.0008) -[2023-10-10 12:57:26,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 14450688. Throughput: 0: 1809.4, 1: 1812.9. Samples: 3621252. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:57:26,076][75634] Avg episode reward: [(0, '17.980'), (1, '13.180')] -[2023-10-10 12:57:26,137][76543] Updated weights for policy 0, policy_version 7072 (0.0007) -[2023-10-10 12:57:29,373][76542] Updated weights for policy 1, policy_version 7080 (0.0009) -[2023-10-10 12:57:29,748][76542] Updated weights for policy 1, policy_version 7090 (0.0008) -[2023-10-10 12:57:29,944][76543] Updated weights for policy 0, policy_version 7082 (0.0008) -[2023-10-10 12:57:30,114][76542] Updated weights for policy 1, policy_version 7100 (0.0007) -[2023-10-10 12:57:30,328][76543] Updated weights for policy 0, policy_version 7092 (0.0007) -[2023-10-10 12:57:30,696][76543] Updated weights for policy 0, policy_version 7102 (0.0009) -[2023-10-10 12:57:31,076][75634] Fps is (10 sec: 16383.6, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 14548992. Throughput: 0: 1805.2, 1: 1799.4. Samples: 3641732. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-10 12:57:31,077][75634] Avg episode reward: [(0, '18.130'), (1, '13.710')] -[2023-10-10 12:57:33,887][76542] Updated weights for policy 1, policy_version 7110 (0.0009) -[2023-10-10 12:57:34,270][76542] Updated weights for policy 1, policy_version 7120 (0.0009) -[2023-10-10 12:57:34,408][76543] Updated weights for policy 0, policy_version 7112 (0.0007) -[2023-10-10 12:57:34,634][76542] Updated weights for policy 1, policy_version 7130 (0.0009) -[2023-10-10 12:57:34,781][76543] Updated weights for policy 0, policy_version 7122 (0.0007) -[2023-10-10 12:57:35,147][76543] Updated weights for policy 0, policy_version 7132 (0.0007) -[2023-10-10 12:57:36,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 14614528. Throughput: 0: 1802.5, 1: 1812.1. Samples: 3653754. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-10 12:57:36,076][75634] Avg episode reward: [(0, '17.550'), (1, '15.170')] -[2023-10-10 12:57:36,077][76421] Saving new best policy, reward=15.170! -[2023-10-10 12:57:38,457][76542] Updated weights for policy 1, policy_version 7140 (0.0008) -[2023-10-10 12:57:38,823][76542] Updated weights for policy 1, policy_version 7150 (0.0007) -[2023-10-10 12:57:38,891][76543] Updated weights for policy 0, policy_version 7142 (0.0008) -[2023-10-10 12:57:39,199][76542] Updated weights for policy 1, policy_version 7160 (0.0009) -[2023-10-10 12:57:39,265][76543] Updated weights for policy 0, policy_version 7152 (0.0009) -[2023-10-10 12:57:39,639][76543] Updated weights for policy 0, policy_version 7162 (0.0007) -[2023-10-10 12:57:41,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 14680064. Throughput: 0: 1807.3, 1: 1800.5. Samples: 3674098. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) -[2023-10-10 12:57:41,077][75634] Avg episode reward: [(0, '18.250'), (1, '15.300')] -[2023-10-10 12:57:41,078][76421] Saving new best policy, reward=15.300! -[2023-10-10 12:57:42,811][76542] Updated weights for policy 1, policy_version 7170 (0.0008) -[2023-10-10 12:57:43,184][76542] Updated weights for policy 1, policy_version 7180 (0.0007) -[2023-10-10 12:57:43,310][76543] Updated weights for policy 0, policy_version 7172 (0.0007) -[2023-10-10 12:57:43,557][76542] Updated weights for policy 1, policy_version 7190 (0.0007) -[2023-10-10 12:57:43,678][76543] Updated weights for policy 0, policy_version 7182 (0.0007) -[2023-10-10 12:57:43,925][76542] Updated weights for policy 1, policy_version 7200 (0.0007) -[2023-10-10 12:57:44,055][76543] Updated weights for policy 0, policy_version 7192 (0.0008) -[2023-10-10 12:57:46,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 14745600. Throughput: 0: 1800.2, 1: 1804.3. Samples: 3696218. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) -[2023-10-10 12:57:46,077][75634] Avg episode reward: [(0, '20.160'), (1, '15.770')] -[2023-10-10 12:57:46,088][76362] Saving new best policy, reward=20.160! -[2023-10-10 12:57:46,089][76421] Saving new best policy, reward=15.770! -[2023-10-10 12:57:47,634][76542] Updated weights for policy 1, policy_version 7210 (0.0008) -[2023-10-10 12:57:47,938][76543] Updated weights for policy 0, policy_version 7202 (0.0009) -[2023-10-10 12:57:48,008][76542] Updated weights for policy 1, policy_version 7220 (0.0010) -[2023-10-10 12:57:48,308][76543] Updated weights for policy 0, policy_version 7212 (0.0007) -[2023-10-10 12:57:48,383][76542] Updated weights for policy 1, policy_version 7230 (0.0007) -[2023-10-10 12:57:48,685][76543] Updated weights for policy 0, policy_version 7222 (0.0007) -[2023-10-10 12:57:49,058][76543] Updated weights for policy 0, policy_version 7232 (0.0008) -[2023-10-10 12:57:51,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 14811136. Throughput: 0: 1813.7, 1: 1803.3. Samples: 3706908. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 12:57:51,077][75634] Avg episode reward: [(0, '20.160'), (1, '15.100')] -[2023-10-10 12:57:51,960][76542] Updated weights for policy 1, policy_version 7240 (0.0007) -[2023-10-10 12:57:52,334][76542] Updated weights for policy 1, policy_version 7250 (0.0010) -[2023-10-10 12:57:52,705][76542] Updated weights for policy 1, policy_version 7260 (0.0008) -[2023-10-10 12:57:52,726][76543] Updated weights for policy 0, policy_version 7242 (0.0007) -[2023-10-10 12:57:53,103][76543] Updated weights for policy 0, policy_version 7252 (0.0008) -[2023-10-10 12:57:53,469][76543] Updated weights for policy 0, policy_version 7262 (0.0008) -[2023-10-10 12:57:56,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 14876672. Throughput: 0: 1794.4, 1: 1800.9. Samples: 3728628. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 12:57:56,076][75634] Avg episode reward: [(0, '19.620'), (1, '14.950')] -[2023-10-10 12:57:56,333][76542] Updated weights for policy 1, policy_version 7270 (0.0009) -[2023-10-10 12:57:56,696][76542] Updated weights for policy 1, policy_version 7280 (0.0011) -[2023-10-10 12:57:57,062][76542] Updated weights for policy 1, policy_version 7290 (0.0009) -[2023-10-10 12:57:57,315][76543] Updated weights for policy 0, policy_version 7272 (0.0008) -[2023-10-10 12:57:57,680][76543] Updated weights for policy 0, policy_version 7282 (0.0009) -[2023-10-10 12:57:58,057][76543] Updated weights for policy 0, policy_version 7292 (0.0007) -[2023-10-10 12:58:00,762][76542] Updated weights for policy 1, policy_version 7300 (0.0009) -[2023-10-10 12:58:01,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 14942208. Throughput: 0: 1801.3, 1: 1817.8. Samples: 3751770. Policy #0 lag: (min: 1.0, avg: 3.5, max: 33.0) -[2023-10-10 12:58:01,076][75634] Avg episode reward: [(0, '19.990'), (1, '14.250')] -[2023-10-10 12:58:01,138][76542] Updated weights for policy 1, policy_version 7310 (0.0009) -[2023-10-10 12:58:01,514][76542] Updated weights for policy 1, policy_version 7320 (0.0007) -[2023-10-10 12:58:01,679][76543] Updated weights for policy 0, policy_version 7302 (0.0007) -[2023-10-10 12:58:02,059][76543] Updated weights for policy 0, policy_version 7312 (0.0007) -[2023-10-10 12:58:02,430][76543] Updated weights for policy 0, policy_version 7322 (0.0007) -[2023-10-10 12:58:05,198][76542] Updated weights for policy 1, policy_version 7330 (0.0008) -[2023-10-10 12:58:05,566][76542] Updated weights for policy 1, policy_version 7340 (0.0010) -[2023-10-10 12:58:05,932][76542] Updated weights for policy 1, policy_version 7350 (0.0007) -[2023-10-10 12:58:05,993][76543] Updated weights for policy 0, policy_version 7332 (0.0008) -[2023-10-10 12:58:06,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 15007744. Throughput: 0: 1802.6, 1: 1812.0. Samples: 3761772. Policy #0 lag: (min: 1.0, avg: 3.5, max: 33.0) -[2023-10-10 12:58:06,076][75634] Avg episode reward: [(0, '19.210'), (1, '14.810')] -[2023-10-10 12:58:06,301][76542] Updated weights for policy 1, policy_version 7360 (0.0007) -[2023-10-10 12:58:06,371][76543] Updated weights for policy 0, policy_version 7342 (0.0007) -[2023-10-10 12:58:06,744][76543] Updated weights for policy 0, policy_version 7352 (0.0010) -[2023-10-10 12:58:09,949][76542] Updated weights for policy 1, policy_version 7370 (0.0008) -[2023-10-10 12:58:10,317][76542] Updated weights for policy 1, policy_version 7380 (0.0007) -[2023-10-10 12:58:10,403][76543] Updated weights for policy 0, policy_version 7362 (0.0008) -[2023-10-10 12:58:10,689][76542] Updated weights for policy 1, policy_version 7390 (0.0008) -[2023-10-10 12:58:10,776][76543] Updated weights for policy 0, policy_version 7372 (0.0008) -[2023-10-10 12:58:11,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 15106048. Throughput: 0: 1811.2, 1: 1819.2. Samples: 3784624. Policy #0 lag: (min: 13.0, avg: 17.4, max: 45.0) -[2023-10-10 12:58:11,076][75634] Avg episode reward: [(0, '16.670'), (1, '14.700')] -[2023-10-10 12:58:11,151][76543] Updated weights for policy 0, policy_version 7382 (0.0008) -[2023-10-10 12:58:11,518][76543] Updated weights for policy 0, policy_version 7392 (0.0007) -[2023-10-10 12:58:14,374][76542] Updated weights for policy 1, policy_version 7400 (0.0007) -[2023-10-10 12:58:14,750][76542] Updated weights for policy 1, policy_version 7410 (0.0007) -[2023-10-10 12:58:15,114][76542] Updated weights for policy 1, policy_version 7420 (0.0008) -[2023-10-10 12:58:15,219][76543] Updated weights for policy 0, policy_version 7402 (0.0009) -[2023-10-10 12:58:15,605][76543] Updated weights for policy 0, policy_version 7412 (0.0009) -[2023-10-10 12:58:15,981][76543] Updated weights for policy 0, policy_version 7422 (0.0008) -[2023-10-10 12:58:16,076][75634] Fps is (10 sec: 19660.9, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 15204352. Throughput: 0: 1826.3, 1: 1818.1. Samples: 3805728. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-10 12:58:16,076][75634] Avg episode reward: [(0, '16.460'), (1, '15.780')] -[2023-10-10 12:58:16,084][76421] Saving new best policy, reward=15.780! -[2023-10-10 12:58:18,870][76542] Updated weights for policy 1, policy_version 7430 (0.0008) -[2023-10-10 12:58:19,259][76542] Updated weights for policy 1, policy_version 7440 (0.0009) -[2023-10-10 12:58:19,370][76543] Updated weights for policy 0, policy_version 7432 (0.0009) -[2023-10-10 12:58:19,625][76542] Updated weights for policy 1, policy_version 7450 (0.0011) -[2023-10-10 12:58:19,742][76543] Updated weights for policy 0, policy_version 7442 (0.0008) -[2023-10-10 12:58:20,124][76543] Updated weights for policy 0, policy_version 7452 (0.0008) -[2023-10-10 12:58:21,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 15269888. Throughput: 0: 1817.9, 1: 1816.7. Samples: 3817316. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-10 12:58:21,077][75634] Avg episode reward: [(0, '16.940'), (1, '17.050')] -[2023-10-10 12:58:21,079][76421] Saving new best policy, reward=17.050! -[2023-10-10 12:58:23,286][76542] Updated weights for policy 1, policy_version 7460 (0.0007) -[2023-10-10 12:58:23,644][76542] Updated weights for policy 1, policy_version 7470 (0.0007) -[2023-10-10 12:58:23,755][76543] Updated weights for policy 0, policy_version 7462 (0.0008) -[2023-10-10 12:58:24,013][76542] Updated weights for policy 1, policy_version 7480 (0.0009) -[2023-10-10 12:58:24,124][76543] Updated weights for policy 0, policy_version 7472 (0.0008) -[2023-10-10 12:58:24,501][76543] Updated weights for policy 0, policy_version 7482 (0.0008) -[2023-10-10 12:58:26,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 15335424. Throughput: 0: 1819.3, 1: 1823.9. Samples: 3838038. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:58:26,076][75634] Avg episode reward: [(0, '17.800'), (1, '16.370')] -[2023-10-10 12:58:27,754][76542] Updated weights for policy 1, policy_version 7490 (0.0008) -[2023-10-10 12:58:28,125][76542] Updated weights for policy 1, policy_version 7500 (0.0011) -[2023-10-10 12:58:28,228][76543] Updated weights for policy 0, policy_version 7492 (0.0007) -[2023-10-10 12:58:28,497][76542] Updated weights for policy 1, policy_version 7510 (0.0007) -[2023-10-10 12:58:28,605][76543] Updated weights for policy 0, policy_version 7502 (0.0009) -[2023-10-10 12:58:28,865][76542] Updated weights for policy 1, policy_version 7520 (0.0007) -[2023-10-10 12:58:28,977][76543] Updated weights for policy 0, policy_version 7512 (0.0009) -[2023-10-10 12:58:31,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 15400960. Throughput: 0: 1817.4, 1: 1821.2. Samples: 3859956. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:58:31,077][75634] Avg episode reward: [(0, '17.840'), (1, '16.580')] -[2023-10-10 12:58:31,089][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000007520_7700480.pth... -[2023-10-10 12:58:31,089][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000007520_7700480.pth... -[2023-10-10 12:58:31,119][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000005824_5963776.pth -[2023-10-10 12:58:31,125][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000005824_5963776.pth -[2023-10-10 12:58:32,578][76542] Updated weights for policy 1, policy_version 7530 (0.0008) -[2023-10-10 12:58:32,804][76543] Updated weights for policy 0, policy_version 7522 (0.0008) -[2023-10-10 12:58:32,946][76542] Updated weights for policy 1, policy_version 7540 (0.0008) -[2023-10-10 12:58:33,184][76543] Updated weights for policy 0, policy_version 7532 (0.0009) -[2023-10-10 12:58:33,314][76542] Updated weights for policy 1, policy_version 7550 (0.0007) -[2023-10-10 12:58:33,546][76543] Updated weights for policy 0, policy_version 7542 (0.0007) -[2023-10-10 12:58:33,924][76543] Updated weights for policy 0, policy_version 7552 (0.0008) -[2023-10-10 12:58:36,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 15466496. Throughput: 0: 1817.5, 1: 1822.2. Samples: 3870698. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:58:36,077][75634] Avg episode reward: [(0, '18.840'), (1, '16.870')] -[2023-10-10 12:58:36,941][76542] Updated weights for policy 1, policy_version 7560 (0.0007) -[2023-10-10 12:58:37,308][76542] Updated weights for policy 1, policy_version 7570 (0.0008) -[2023-10-10 12:58:37,665][76543] Updated weights for policy 0, policy_version 7562 (0.0007) -[2023-10-10 12:58:37,681][76542] Updated weights for policy 1, policy_version 7580 (0.0007) -[2023-10-10 12:58:38,043][76543] Updated weights for policy 0, policy_version 7572 (0.0010) -[2023-10-10 12:58:38,424][76543] Updated weights for policy 0, policy_version 7582 (0.0008) -[2023-10-10 12:58:41,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 15532032. Throughput: 0: 1819.6, 1: 1818.2. Samples: 3892332. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:58:41,077][75634] Avg episode reward: [(0, '20.430'), (1, '16.400')] -[2023-10-10 12:58:41,078][76362] Saving new best policy, reward=20.430! -[2023-10-10 12:58:41,484][76542] Updated weights for policy 1, policy_version 7590 (0.0008) -[2023-10-10 12:58:41,845][76542] Updated weights for policy 1, policy_version 7600 (0.0008) -[2023-10-10 12:58:42,217][76542] Updated weights for policy 1, policy_version 7610 (0.0007) -[2023-10-10 12:58:42,290][76543] Updated weights for policy 0, policy_version 7592 (0.0007) -[2023-10-10 12:58:42,671][76543] Updated weights for policy 0, policy_version 7602 (0.0009) -[2023-10-10 12:58:43,046][76543] Updated weights for policy 0, policy_version 7612 (0.0008) -[2023-10-10 12:58:45,821][76542] Updated weights for policy 1, policy_version 7620 (0.0007) -[2023-10-10 12:58:46,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 15597568. Throughput: 0: 1811.7, 1: 1808.7. Samples: 3914688. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-10 12:58:46,077][75634] Avg episode reward: [(0, '20.480'), (1, '16.620')] -[2023-10-10 12:58:46,087][76362] Saving new best policy, reward=20.480! -[2023-10-10 12:58:46,186][76542] Updated weights for policy 1, policy_version 7630 (0.0007) -[2023-10-10 12:58:46,565][76542] Updated weights for policy 1, policy_version 7640 (0.0007) -[2023-10-10 12:58:46,712][76543] Updated weights for policy 0, policy_version 7622 (0.0007) -[2023-10-10 12:58:47,082][76543] Updated weights for policy 0, policy_version 7632 (0.0008) -[2023-10-10 12:58:47,458][76543] Updated weights for policy 0, policy_version 7642 (0.0008) -[2023-10-10 12:58:50,354][76542] Updated weights for policy 1, policy_version 7650 (0.0010) -[2023-10-10 12:58:50,724][76542] Updated weights for policy 1, policy_version 7660 (0.0008) -[2023-10-10 12:58:51,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 15663104. Throughput: 0: 1813.2, 1: 1802.1. Samples: 3924462. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-10 12:58:51,077][75634] Avg episode reward: [(0, '21.010'), (1, '15.840')] -[2023-10-10 12:58:51,095][76542] Updated weights for policy 1, policy_version 7670 (0.0008) -[2023-10-10 12:58:51,136][76543] Updated weights for policy 0, policy_version 7652 (0.0007) -[2023-10-10 12:58:51,461][76542] Updated weights for policy 1, policy_version 7680 (0.0007) -[2023-10-10 12:58:51,511][76543] Updated weights for policy 0, policy_version 7662 (0.0007) -[2023-10-10 12:58:51,889][76543] Updated weights for policy 0, policy_version 7672 (0.0008) -[2023-10-10 12:58:52,189][76362] Saving new best policy, reward=21.010! -[2023-10-10 12:58:55,039][76542] Updated weights for policy 1, policy_version 7690 (0.0009) -[2023-10-10 12:58:55,418][76542] Updated weights for policy 1, policy_version 7700 (0.0009) -[2023-10-10 12:58:55,528][76543] Updated weights for policy 0, policy_version 7682 (0.0010) -[2023-10-10 12:58:55,785][76542] Updated weights for policy 1, policy_version 7710 (0.0008) -[2023-10-10 12:58:55,897][76543] Updated weights for policy 0, policy_version 7692 (0.0008) -[2023-10-10 12:58:56,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 15761408. Throughput: 0: 1810.3, 1: 1808.5. Samples: 3947468. Policy #0 lag: (min: 25.0, avg: 28.2, max: 53.0) -[2023-10-10 12:58:56,077][75634] Avg episode reward: [(0, '20.790'), (1, '15.900')] -[2023-10-10 12:58:56,277][76543] Updated weights for policy 0, policy_version 7702 (0.0009) -[2023-10-10 12:58:56,659][76543] Updated weights for policy 0, policy_version 7712 (0.0007) -[2023-10-10 12:58:59,444][76542] Updated weights for policy 1, policy_version 7720 (0.0008) -[2023-10-10 12:58:59,803][76542] Updated weights for policy 1, policy_version 7730 (0.0012) -[2023-10-10 12:59:00,171][76542] Updated weights for policy 1, policy_version 7740 (0.0011) -[2023-10-10 12:59:00,578][76543] Updated weights for policy 0, policy_version 7722 (0.0008) -[2023-10-10 12:59:00,954][76543] Updated weights for policy 0, policy_version 7732 (0.0010) -[2023-10-10 12:59:01,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 15826944. Throughput: 0: 1811.6, 1: 1810.1. Samples: 3968704. Policy #0 lag: (min: 25.0, avg: 28.2, max: 53.0) -[2023-10-10 12:59:01,076][75634] Avg episode reward: [(0, '21.500'), (1, '16.160')] -[2023-10-10 12:59:01,334][76543] Updated weights for policy 0, policy_version 7742 (0.0008) -[2023-10-10 12:59:01,404][76362] Saving new best policy, reward=21.500! -[2023-10-10 12:59:03,957][76542] Updated weights for policy 1, policy_version 7750 (0.0011) -[2023-10-10 12:59:04,331][76542] Updated weights for policy 1, policy_version 7760 (0.0010) -[2023-10-10 12:59:04,696][76542] Updated weights for policy 1, policy_version 7770 (0.0008) -[2023-10-10 12:59:04,756][76543] Updated weights for policy 0, policy_version 7752 (0.0009) -[2023-10-10 12:59:05,137][76543] Updated weights for policy 0, policy_version 7762 (0.0009) -[2023-10-10 12:59:05,511][76543] Updated weights for policy 0, policy_version 7772 (0.0008) -[2023-10-10 12:59:06,076][75634] Fps is (10 sec: 16384.2, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 15925248. Throughput: 0: 1804.0, 1: 1818.8. Samples: 3980338. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:59:06,076][75634] Avg episode reward: [(0, '21.880'), (1, '16.160')] -[2023-10-10 12:59:06,077][76362] Saving new best policy, reward=21.880! -[2023-10-10 12:59:08,313][76542] Updated weights for policy 1, policy_version 7780 (0.0008) -[2023-10-10 12:59:08,682][76542] Updated weights for policy 1, policy_version 7790 (0.0008) -[2023-10-10 12:59:09,057][76542] Updated weights for policy 1, policy_version 7800 (0.0009) -[2023-10-10 12:59:09,091][76543] Updated weights for policy 0, policy_version 7782 (0.0007) -[2023-10-10 12:59:09,466][76543] Updated weights for policy 0, policy_version 7792 (0.0009) -[2023-10-10 12:59:09,841][76543] Updated weights for policy 0, policy_version 7802 (0.0010) -[2023-10-10 12:59:11,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 15990784. Throughput: 0: 1813.2, 1: 1816.4. Samples: 4001368. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-10-10 12:59:11,077][75634] Avg episode reward: [(0, '21.980'), (1, '15.890')] -[2023-10-10 12:59:11,077][76362] Saving new best policy, reward=21.980! -[2023-10-10 12:59:12,740][76542] Updated weights for policy 1, policy_version 7810 (0.0008) -[2023-10-10 12:59:13,106][76542] Updated weights for policy 1, policy_version 7820 (0.0007) -[2023-10-10 12:59:13,477][76542] Updated weights for policy 1, policy_version 7830 (0.0007) -[2023-10-10 12:59:13,557][76543] Updated weights for policy 0, policy_version 7812 (0.0008) -[2023-10-10 12:59:13,838][76542] Updated weights for policy 1, policy_version 7840 (0.0008) -[2023-10-10 12:59:13,936][76543] Updated weights for policy 0, policy_version 7822 (0.0009) -[2023-10-10 12:59:14,301][76543] Updated weights for policy 0, policy_version 7832 (0.0010) -[2023-10-10 12:59:16,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 16056320. Throughput: 0: 1807.7, 1: 1826.3. Samples: 4023486. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-10-10 12:59:16,077][75634] Avg episode reward: [(0, '21.940'), (1, '15.610')] -[2023-10-10 12:59:17,427][76542] Updated weights for policy 1, policy_version 7850 (0.0010) -[2023-10-10 12:59:17,798][76542] Updated weights for policy 1, policy_version 7860 (0.0010) -[2023-10-10 12:59:18,120][76543] Updated weights for policy 0, policy_version 7842 (0.0009) -[2023-10-10 12:59:18,172][76542] Updated weights for policy 1, policy_version 7870 (0.0007) -[2023-10-10 12:59:18,489][76543] Updated weights for policy 0, policy_version 7852 (0.0009) -[2023-10-10 12:59:18,863][76543] Updated weights for policy 0, policy_version 7862 (0.0007) -[2023-10-10 12:59:19,233][76543] Updated weights for policy 0, policy_version 7872 (0.0010) -[2023-10-10 12:59:21,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 16121856. Throughput: 0: 1816.4, 1: 1831.1. Samples: 4034834. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-10 12:59:21,077][75634] Avg episode reward: [(0, '22.280'), (1, '15.030')] -[2023-10-10 12:59:21,078][76362] Saving new best policy, reward=22.280! -[2023-10-10 12:59:21,870][76542] Updated weights for policy 1, policy_version 7880 (0.0007) -[2023-10-10 12:59:22,236][76542] Updated weights for policy 1, policy_version 7890 (0.0007) -[2023-10-10 12:59:22,602][76542] Updated weights for policy 1, policy_version 7900 (0.0008) -[2023-10-10 12:59:22,771][76543] Updated weights for policy 0, policy_version 7882 (0.0010) -[2023-10-10 12:59:23,139][76543] Updated weights for policy 0, policy_version 7892 (0.0010) -[2023-10-10 12:59:23,515][76543] Updated weights for policy 0, policy_version 7902 (0.0009) -[2023-10-10 12:59:26,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14440.2). Total num frames: 16187392. Throughput: 0: 1815.0, 1: 1836.2. Samples: 4056636. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-10 12:59:26,076][75634] Avg episode reward: [(0, '22.200'), (1, '14.740')] -[2023-10-10 12:59:26,290][76542] Updated weights for policy 1, policy_version 7910 (0.0008) -[2023-10-10 12:59:26,660][76542] Updated weights for policy 1, policy_version 7920 (0.0011) -[2023-10-10 12:59:27,024][76542] Updated weights for policy 1, policy_version 7930 (0.0007) -[2023-10-10 12:59:27,208][76543] Updated weights for policy 0, policy_version 7912 (0.0008) -[2023-10-10 12:59:27,582][76543] Updated weights for policy 0, policy_version 7922 (0.0009) -[2023-10-10 12:59:27,954][76543] Updated weights for policy 0, policy_version 7932 (0.0008) -[2023-10-10 12:59:30,784][76542] Updated weights for policy 1, policy_version 7940 (0.0008) -[2023-10-10 12:59:31,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 16252928. Throughput: 0: 1819.9, 1: 1831.9. Samples: 4079020. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:59:31,077][75634] Avg episode reward: [(0, '21.070'), (1, '13.990')] -[2023-10-10 12:59:31,155][76542] Updated weights for policy 1, policy_version 7950 (0.0007) -[2023-10-10 12:59:31,536][76542] Updated weights for policy 1, policy_version 7960 (0.0007) -[2023-10-10 12:59:31,600][76543] Updated weights for policy 0, policy_version 7942 (0.0010) -[2023-10-10 12:59:31,965][76543] Updated weights for policy 0, policy_version 7952 (0.0009) -[2023-10-10 12:59:32,338][76543] Updated weights for policy 0, policy_version 7962 (0.0008) -[2023-10-10 12:59:35,025][76542] Updated weights for policy 1, policy_version 7970 (0.0007) -[2023-10-10 12:59:35,391][76542] Updated weights for policy 1, policy_version 7980 (0.0007) -[2023-10-10 12:59:35,758][76542] Updated weights for policy 1, policy_version 7990 (0.0007) -[2023-10-10 12:59:36,007][76543] Updated weights for policy 0, policy_version 7972 (0.0009) -[2023-10-10 12:59:36,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 16318464. Throughput: 0: 1822.2, 1: 1842.6. Samples: 4089378. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 12:59:36,077][75634] Avg episode reward: [(0, '20.750'), (1, '14.120')] -[2023-10-10 12:59:36,132][76542] Updated weights for policy 1, policy_version 8000 (0.0008) -[2023-10-10 12:59:36,379][76543] Updated weights for policy 0, policy_version 7982 (0.0008) -[2023-10-10 12:59:36,743][76543] Updated weights for policy 0, policy_version 7992 (0.0007) -[2023-10-10 12:59:39,737][76542] Updated weights for policy 1, policy_version 8010 (0.0007) -[2023-10-10 12:59:40,116][76542] Updated weights for policy 1, policy_version 8020 (0.0009) -[2023-10-10 12:59:40,367][76543] Updated weights for policy 0, policy_version 8002 (0.0009) -[2023-10-10 12:59:40,492][76542] Updated weights for policy 1, policy_version 8030 (0.0007) -[2023-10-10 12:59:40,738][76543] Updated weights for policy 0, policy_version 8012 (0.0008) -[2023-10-10 12:59:41,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 16416768. Throughput: 0: 1821.5, 1: 1835.1. Samples: 4112018. Policy #0 lag: (min: 1.0, avg: 8.6, max: 33.0) -[2023-10-10 12:59:41,077][75634] Avg episode reward: [(0, '20.780'), (1, '13.720')] -[2023-10-10 12:59:41,110][76543] Updated weights for policy 0, policy_version 8022 (0.0009) -[2023-10-10 12:59:41,479][76543] Updated weights for policy 0, policy_version 8032 (0.0009) -[2023-10-10 12:59:44,138][76542] Updated weights for policy 1, policy_version 8040 (0.0007) -[2023-10-10 12:59:44,507][76542] Updated weights for policy 1, policy_version 8050 (0.0008) -[2023-10-10 12:59:44,868][76542] Updated weights for policy 1, policy_version 8060 (0.0008) -[2023-10-10 12:59:45,422][76543] Updated weights for policy 0, policy_version 8042 (0.0009) -[2023-10-10 12:59:45,784][76543] Updated weights for policy 0, policy_version 8052 (0.0007) -[2023-10-10 12:59:46,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 16482304. Throughput: 0: 1818.6, 1: 1844.4. Samples: 4133542. Policy #0 lag: (min: 1.0, avg: 8.6, max: 33.0) -[2023-10-10 12:59:46,077][75634] Avg episode reward: [(0, '19.950'), (1, '15.890')] -[2023-10-10 12:59:46,166][76543] Updated weights for policy 0, policy_version 8062 (0.0007) -[2023-10-10 12:59:48,648][76542] Updated weights for policy 1, policy_version 8070 (0.0008) -[2023-10-10 12:59:49,013][76542] Updated weights for policy 1, policy_version 8080 (0.0007) -[2023-10-10 12:59:49,386][76542] Updated weights for policy 1, policy_version 8090 (0.0010) -[2023-10-10 12:59:49,896][76543] Updated weights for policy 0, policy_version 8072 (0.0010) -[2023-10-10 12:59:50,267][76543] Updated weights for policy 0, policy_version 8082 (0.0008) -[2023-10-10 12:59:50,639][76543] Updated weights for policy 0, policy_version 8092 (0.0010) -[2023-10-10 12:59:51,076][75634] Fps is (10 sec: 16384.4, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 16580608. Throughput: 0: 1817.7, 1: 1833.5. Samples: 4144642. Policy #0 lag: (min: 21.0, avg: 24.1, max: 53.0) -[2023-10-10 12:59:51,076][75634] Avg episode reward: [(0, '20.050'), (1, '16.160')] -[2023-10-10 12:59:53,076][76542] Updated weights for policy 1, policy_version 8100 (0.0008) -[2023-10-10 12:59:53,447][76542] Updated weights for policy 1, policy_version 8110 (0.0009) -[2023-10-10 12:59:53,821][76542] Updated weights for policy 1, policy_version 8120 (0.0008) -[2023-10-10 12:59:54,309][76543] Updated weights for policy 0, policy_version 8102 (0.0009) -[2023-10-10 12:59:54,688][76543] Updated weights for policy 0, policy_version 8112 (0.0008) -[2023-10-10 12:59:55,063][76543] Updated weights for policy 0, policy_version 8122 (0.0009) -[2023-10-10 12:59:56,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 16646144. Throughput: 0: 1826.1, 1: 1839.7. Samples: 4166330. Policy #0 lag: (min: 2.0, avg: 10.0, max: 34.0) -[2023-10-10 12:59:56,077][75634] Avg episode reward: [(0, '20.880'), (1, '15.730')] -[2023-10-10 12:59:57,492][76542] Updated weights for policy 1, policy_version 8130 (0.0008) -[2023-10-10 12:59:57,860][76542] Updated weights for policy 1, policy_version 8140 (0.0007) -[2023-10-10 12:59:58,228][76542] Updated weights for policy 1, policy_version 8150 (0.0007) -[2023-10-10 12:59:58,594][76542] Updated weights for policy 1, policy_version 8160 (0.0010) -[2023-10-10 12:59:58,888][76543] Updated weights for policy 0, policy_version 8132 (0.0010) -[2023-10-10 12:59:59,264][76543] Updated weights for policy 0, policy_version 8142 (0.0009) -[2023-10-10 12:59:59,644][76543] Updated weights for policy 0, policy_version 8152 (0.0011) -[2023-10-10 13:00:01,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 16711680. Throughput: 0: 1818.5, 1: 1828.1. Samples: 4187584. Policy #0 lag: (min: 2.0, avg: 10.0, max: 34.0) -[2023-10-10 13:00:01,077][75634] Avg episode reward: [(0, '20.420'), (1, '15.840')] -[2023-10-10 13:00:02,385][76542] Updated weights for policy 1, policy_version 8170 (0.0011) -[2023-10-10 13:00:02,760][76542] Updated weights for policy 1, policy_version 8180 (0.0009) -[2023-10-10 13:00:03,122][76542] Updated weights for policy 1, policy_version 8190 (0.0007) -[2023-10-10 13:00:03,330][76543] Updated weights for policy 0, policy_version 8162 (0.0008) -[2023-10-10 13:00:03,704][76543] Updated weights for policy 0, policy_version 8172 (0.0008) -[2023-10-10 13:00:04,081][76543] Updated weights for policy 0, policy_version 8182 (0.0008) -[2023-10-10 13:00:04,455][76543] Updated weights for policy 0, policy_version 8192 (0.0009) -[2023-10-10 13:00:06,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 16777216. Throughput: 0: 1829.3, 1: 1825.2. Samples: 4199288. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-10 13:00:06,076][75634] Avg episode reward: [(0, '21.020'), (1, '16.160')] -[2023-10-10 13:00:06,798][76542] Updated weights for policy 1, policy_version 8200 (0.0009) -[2023-10-10 13:00:07,165][76542] Updated weights for policy 1, policy_version 8210 (0.0008) -[2023-10-10 13:00:07,538][76542] Updated weights for policy 1, policy_version 8220 (0.0007) -[2023-10-10 13:00:08,172][76543] Updated weights for policy 0, policy_version 8202 (0.0008) -[2023-10-10 13:00:08,532][76543] Updated weights for policy 0, policy_version 8212 (0.0009) -[2023-10-10 13:00:08,907][76543] Updated weights for policy 0, policy_version 8222 (0.0010) -[2023-10-10 13:00:11,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 16842752. Throughput: 0: 1818.8, 1: 1824.9. Samples: 4220602. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-10 13:00:11,076][75634] Avg episode reward: [(0, '21.100'), (1, '15.690')] -[2023-10-10 13:00:11,158][76542] Updated weights for policy 1, policy_version 8230 (0.0008) -[2023-10-10 13:00:11,536][76542] Updated weights for policy 1, policy_version 8240 (0.0009) -[2023-10-10 13:00:11,909][76542] Updated weights for policy 1, policy_version 8250 (0.0009) -[2023-10-10 13:00:12,515][76543] Updated weights for policy 0, policy_version 8232 (0.0009) -[2023-10-10 13:00:12,880][76543] Updated weights for policy 0, policy_version 8242 (0.0009) -[2023-10-10 13:00:13,253][76543] Updated weights for policy 0, policy_version 8252 (0.0009) -[2023-10-10 13:00:15,527][76542] Updated weights for policy 1, policy_version 8260 (0.0009) -[2023-10-10 13:00:15,894][76542] Updated weights for policy 1, policy_version 8270 (0.0008) -[2023-10-10 13:00:16,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 16908288. Throughput: 0: 1822.4, 1: 1823.5. Samples: 4243084. Policy #0 lag: (min: 30.0, avg: 38.7, max: 62.0) -[2023-10-10 13:00:16,076][75634] Avg episode reward: [(0, '21.200'), (1, '14.350')] -[2023-10-10 13:00:16,262][76542] Updated weights for policy 1, policy_version 8280 (0.0009) -[2023-10-10 13:00:16,820][76543] Updated weights for policy 0, policy_version 8262 (0.0009) -[2023-10-10 13:00:17,201][76543] Updated weights for policy 0, policy_version 8272 (0.0009) -[2023-10-10 13:00:17,576][76543] Updated weights for policy 0, policy_version 8282 (0.0011) -[2023-10-10 13:00:19,978][76542] Updated weights for policy 1, policy_version 8290 (0.0007) -[2023-10-10 13:00:20,340][76542] Updated weights for policy 1, policy_version 8300 (0.0008) -[2023-10-10 13:00:20,712][76542] Updated weights for policy 1, policy_version 8310 (0.0009) -[2023-10-10 13:00:21,073][76542] Updated weights for policy 1, policy_version 8320 (0.0008) -[2023-10-10 13:00:21,080][75634] Fps is (10 sec: 16377.6, 60 sec: 14744.7, 300 sec: 14551.0). Total num frames: 17006592. Throughput: 0: 1823.9, 1: 1825.0. Samples: 4253590. Policy #0 lag: (min: 30.0, avg: 38.7, max: 62.0) -[2023-10-10 13:00:21,081][75634] Avg episode reward: [(0, '20.960'), (1, '14.480')] -[2023-10-10 13:00:21,220][76543] Updated weights for policy 0, policy_version 8292 (0.0009) -[2023-10-10 13:00:21,593][76543] Updated weights for policy 0, policy_version 8302 (0.0007) -[2023-10-10 13:00:21,966][76543] Updated weights for policy 0, policy_version 8312 (0.0008) -[2023-10-10 13:00:24,783][76542] Updated weights for policy 1, policy_version 8330 (0.0008) -[2023-10-10 13:00:25,153][76542] Updated weights for policy 1, policy_version 8340 (0.0008) -[2023-10-10 13:00:25,512][76542] Updated weights for policy 1, policy_version 8350 (0.0008) -[2023-10-10 13:00:25,745][76543] Updated weights for policy 0, policy_version 8322 (0.0009) -[2023-10-10 13:00:26,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 17072128. Throughput: 0: 1818.4, 1: 1823.3. Samples: 4275892. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-10 13:00:26,076][75634] Avg episode reward: [(0, '22.790'), (1, '14.310')] -[2023-10-10 13:00:26,125][76543] Updated weights for policy 0, policy_version 8332 (0.0008) -[2023-10-10 13:00:26,492][76543] Updated weights for policy 0, policy_version 8342 (0.0007) -[2023-10-10 13:00:26,858][76362] Saving new best policy, reward=22.790! -[2023-10-10 13:00:26,859][76543] Updated weights for policy 0, policy_version 8352 (0.0010) -[2023-10-10 13:00:29,215][76542] Updated weights for policy 1, policy_version 8360 (0.0010) -[2023-10-10 13:00:29,574][76542] Updated weights for policy 1, policy_version 8370 (0.0009) -[2023-10-10 13:00:29,942][76542] Updated weights for policy 1, policy_version 8380 (0.0007) -[2023-10-10 13:00:30,581][76543] Updated weights for policy 0, policy_version 8362 (0.0008) -[2023-10-10 13:00:30,945][76543] Updated weights for policy 0, policy_version 8372 (0.0009) -[2023-10-10 13:00:31,076][75634] Fps is (10 sec: 13112.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 17137664. Throughput: 0: 1827.2, 1: 1816.8. Samples: 4297524. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-10 13:00:31,077][75634] Avg episode reward: [(0, '23.260'), (1, '14.570')] -[2023-10-10 13:00:31,085][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000008384_8585216.pth... -[2023-10-10 13:00:31,121][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000006688_6848512.pth -[2023-10-10 13:00:31,125][76421] Saving a milestone ./train_atari/atari_defender_APPO/checkpoint_p1/milestones/checkpoint_000008384_8585216.pth -[2023-10-10 13:00:31,328][76543] Updated weights for policy 0, policy_version 8382 (0.0012) -[2023-10-10 13:00:31,398][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000008384_8585216.pth... -[2023-10-10 13:00:31,428][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000006688_6848512.pth -[2023-10-10 13:00:31,431][76362] Saving new best policy, reward=23.260! -[2023-10-10 13:00:31,464][76362] Saving a milestone ./train_atari/atari_defender_APPO/checkpoint_p0/milestones/checkpoint_000008384_8585216.pth -[2023-10-10 13:00:33,641][76542] Updated weights for policy 1, policy_version 8390 (0.0007) -[2023-10-10 13:00:34,038][76542] Updated weights for policy 1, policy_version 8400 (0.0008) -[2023-10-10 13:00:34,401][76542] Updated weights for policy 1, policy_version 8410 (0.0007) -[2023-10-10 13:00:34,882][76543] Updated weights for policy 0, policy_version 8392 (0.0009) -[2023-10-10 13:00:35,257][76543] Updated weights for policy 0, policy_version 8402 (0.0007) -[2023-10-10 13:00:35,638][76543] Updated weights for policy 0, policy_version 8412 (0.0009) -[2023-10-10 13:00:36,076][75634] Fps is (10 sec: 16383.9, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 17235968. Throughput: 0: 1825.3, 1: 1817.5. Samples: 4308568. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-10 13:00:36,076][75634] Avg episode reward: [(0, '23.370'), (1, '15.420')] -[2023-10-10 13:00:36,077][76362] Saving new best policy, reward=23.370! -[2023-10-10 13:00:38,241][76542] Updated weights for policy 1, policy_version 8420 (0.0010) -[2023-10-10 13:00:38,611][76542] Updated weights for policy 1, policy_version 8430 (0.0010) -[2023-10-10 13:00:38,975][76542] Updated weights for policy 1, policy_version 8440 (0.0008) -[2023-10-10 13:00:39,271][76543] Updated weights for policy 0, policy_version 8422 (0.0009) -[2023-10-10 13:00:39,651][76543] Updated weights for policy 0, policy_version 8432 (0.0010) -[2023-10-10 13:00:40,022][76543] Updated weights for policy 0, policy_version 8442 (0.0010) -[2023-10-10 13:00:41,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 17301504. Throughput: 0: 1819.5, 1: 1806.8. Samples: 4329516. Policy #0 lag: (min: 21.0, avg: 23.9, max: 53.0) -[2023-10-10 13:00:41,077][75634] Avg episode reward: [(0, '21.920'), (1, '16.140')] -[2023-10-10 13:00:42,660][76542] Updated weights for policy 1, policy_version 8450 (0.0008) -[2023-10-10 13:00:43,026][76542] Updated weights for policy 1, policy_version 8460 (0.0008) -[2023-10-10 13:00:43,401][76542] Updated weights for policy 1, policy_version 8470 (0.0008) -[2023-10-10 13:00:43,631][76543] Updated weights for policy 0, policy_version 8452 (0.0011) -[2023-10-10 13:00:43,775][76542] Updated weights for policy 1, policy_version 8480 (0.0009) -[2023-10-10 13:00:44,006][76543] Updated weights for policy 0, policy_version 8462 (0.0007) -[2023-10-10 13:00:44,374][76543] Updated weights for policy 0, policy_version 8472 (0.0008) -[2023-10-10 13:00:46,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 17367040. Throughput: 0: 1826.4, 1: 1811.5. Samples: 4351288. Policy #0 lag: (min: 21.0, avg: 23.9, max: 53.0) -[2023-10-10 13:00:46,077][75634] Avg episode reward: [(0, '21.130'), (1, '16.020')] -[2023-10-10 13:00:47,467][76542] Updated weights for policy 1, policy_version 8490 (0.0009) -[2023-10-10 13:00:47,829][76542] Updated weights for policy 1, policy_version 8500 (0.0009) -[2023-10-10 13:00:47,871][76543] Updated weights for policy 0, policy_version 8482 (0.0009) -[2023-10-10 13:00:48,194][76542] Updated weights for policy 1, policy_version 8510 (0.0008) -[2023-10-10 13:00:48,255][76543] Updated weights for policy 0, policy_version 8492 (0.0008) -[2023-10-10 13:00:48,634][76543] Updated weights for policy 0, policy_version 8502 (0.0007) -[2023-10-10 13:00:49,011][76543] Updated weights for policy 0, policy_version 8512 (0.0007) -[2023-10-10 13:00:51,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 17432576. Throughput: 0: 1815.6, 1: 1813.0. Samples: 4362576. Policy #0 lag: (min: 26.0, avg: 26.5, max: 41.0) -[2023-10-10 13:00:51,076][75634] Avg episode reward: [(0, '20.620'), (1, '16.830')] -[2023-10-10 13:00:51,876][76542] Updated weights for policy 1, policy_version 8520 (0.0008) -[2023-10-10 13:00:52,241][76542] Updated weights for policy 1, policy_version 8530 (0.0007) -[2023-10-10 13:00:52,609][76542] Updated weights for policy 1, policy_version 8540 (0.0007) -[2023-10-10 13:00:52,668][76543] Updated weights for policy 0, policy_version 8522 (0.0007) -[2023-10-10 13:00:53,041][76543] Updated weights for policy 0, policy_version 8532 (0.0007) -[2023-10-10 13:00:53,407][76543] Updated weights for policy 0, policy_version 8542 (0.0007) -[2023-10-10 13:00:56,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 17498112. Throughput: 0: 1834.0, 1: 1810.1. Samples: 4384586. Policy #0 lag: (min: 26.0, avg: 26.5, max: 41.0) -[2023-10-10 13:00:56,076][75634] Avg episode reward: [(0, '20.730'), (1, '17.790')] -[2023-10-10 13:00:56,223][76542] Updated weights for policy 1, policy_version 8550 (0.0007) -[2023-10-10 13:00:56,594][76542] Updated weights for policy 1, policy_version 8560 (0.0010) -[2023-10-10 13:00:56,962][76542] Updated weights for policy 1, policy_version 8570 (0.0008) -[2023-10-10 13:00:57,059][76543] Updated weights for policy 0, policy_version 8552 (0.0007) -[2023-10-10 13:00:57,185][76421] Saving new best policy, reward=17.790! -[2023-10-10 13:00:57,432][76543] Updated weights for policy 0, policy_version 8562 (0.0010) -[2023-10-10 13:00:57,814][76543] Updated weights for policy 0, policy_version 8572 (0.0008) -[2023-10-10 13:01:00,690][76542] Updated weights for policy 1, policy_version 8580 (0.0009) -[2023-10-10 13:01:01,064][76542] Updated weights for policy 1, policy_version 8590 (0.0012) -[2023-10-10 13:01:01,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 17563648. Throughput: 0: 1826.4, 1: 1815.7. Samples: 4406982. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-10 13:01:01,076][75634] Avg episode reward: [(0, '20.990'), (1, '17.180')] -[2023-10-10 13:01:01,439][76542] Updated weights for policy 1, policy_version 8600 (0.0009) -[2023-10-10 13:01:01,670][76543] Updated weights for policy 0, policy_version 8582 (0.0008) -[2023-10-10 13:01:02,046][76543] Updated weights for policy 0, policy_version 8592 (0.0008) -[2023-10-10 13:01:02,417][76543] Updated weights for policy 0, policy_version 8602 (0.0008) -[2023-10-10 13:01:05,074][76542] Updated weights for policy 1, policy_version 8610 (0.0007) -[2023-10-10 13:01:05,442][76542] Updated weights for policy 1, policy_version 8620 (0.0009) -[2023-10-10 13:01:05,822][76542] Updated weights for policy 1, policy_version 8630 (0.0008) -[2023-10-10 13:01:06,076][75634] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 17629184. Throughput: 0: 1820.5, 1: 1817.7. Samples: 4417296. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-10 13:01:06,077][75634] Avg episode reward: [(0, '20.800'), (1, '16.090')] -[2023-10-10 13:01:06,141][76543] Updated weights for policy 0, policy_version 8612 (0.0008) -[2023-10-10 13:01:06,187][76542] Updated weights for policy 1, policy_version 8640 (0.0008) -[2023-10-10 13:01:06,518][76543] Updated weights for policy 0, policy_version 8622 (0.0007) -[2023-10-10 13:01:06,892][76543] Updated weights for policy 0, policy_version 8632 (0.0010) -[2023-10-10 13:01:09,791][76542] Updated weights for policy 1, policy_version 8650 (0.0009) -[2023-10-10 13:01:10,156][76542] Updated weights for policy 1, policy_version 8660 (0.0008) -[2023-10-10 13:01:10,530][76542] Updated weights for policy 1, policy_version 8670 (0.0008) -[2023-10-10 13:01:10,631][76543] Updated weights for policy 0, policy_version 8642 (0.0009) -[2023-10-10 13:01:10,995][76543] Updated weights for policy 0, policy_version 8652 (0.0007) -[2023-10-10 13:01:11,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 17727488. Throughput: 0: 1819.0, 1: 1817.4. Samples: 4439530. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 13:01:11,076][75634] Avg episode reward: [(0, '21.960'), (1, '15.810')] -[2023-10-10 13:01:11,365][76543] Updated weights for policy 0, policy_version 8662 (0.0007) -[2023-10-10 13:01:11,743][76543] Updated weights for policy 0, policy_version 8672 (0.0009) -[2023-10-10 13:01:14,317][76542] Updated weights for policy 1, policy_version 8680 (0.0008) -[2023-10-10 13:01:14,686][76542] Updated weights for policy 1, policy_version 8690 (0.0008) -[2023-10-10 13:01:15,052][76542] Updated weights for policy 1, policy_version 8700 (0.0009) -[2023-10-10 13:01:15,343][76543] Updated weights for policy 0, policy_version 8682 (0.0008) -[2023-10-10 13:01:15,719][76543] Updated weights for policy 0, policy_version 8692 (0.0010) -[2023-10-10 13:01:16,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 17793024. Throughput: 0: 1817.5, 1: 1812.4. Samples: 4460872. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 13:01:16,077][75634] Avg episode reward: [(0, '22.180'), (1, '15.550')] -[2023-10-10 13:01:16,098][76543] Updated weights for policy 0, policy_version 8702 (0.0010) -[2023-10-10 13:01:18,906][76542] Updated weights for policy 1, policy_version 8710 (0.0008) -[2023-10-10 13:01:19,291][76542] Updated weights for policy 1, policy_version 8720 (0.0007) -[2023-10-10 13:01:19,668][76542] Updated weights for policy 1, policy_version 8730 (0.0008) -[2023-10-10 13:01:19,689][76543] Updated weights for policy 0, policy_version 8712 (0.0008) -[2023-10-10 13:01:20,063][76543] Updated weights for policy 0, policy_version 8722 (0.0010) -[2023-10-10 13:01:20,441][76543] Updated weights for policy 0, policy_version 8732 (0.0008) -[2023-10-10 13:01:21,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14746.6, 300 sec: 14662.3). Total num frames: 17891328. Throughput: 0: 1822.7, 1: 1814.5. Samples: 4472242. Policy #0 lag: (min: 15.0, avg: 21.3, max: 47.0) -[2023-10-10 13:01:21,077][75634] Avg episode reward: [(0, '20.620'), (1, '17.050')] -[2023-10-10 13:01:23,335][76542] Updated weights for policy 1, policy_version 8740 (0.0007) -[2023-10-10 13:01:23,708][76542] Updated weights for policy 1, policy_version 8750 (0.0007) -[2023-10-10 13:01:23,952][76543] Updated weights for policy 0, policy_version 8742 (0.0007) -[2023-10-10 13:01:24,070][76542] Updated weights for policy 1, policy_version 8760 (0.0008) -[2023-10-10 13:01:24,328][76543] Updated weights for policy 0, policy_version 8752 (0.0008) -[2023-10-10 13:01:24,699][76543] Updated weights for policy 0, policy_version 8762 (0.0008) -[2023-10-10 13:01:26,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 17956864. Throughput: 0: 1820.2, 1: 1821.0. Samples: 4493370. Policy #0 lag: (min: 9.0, avg: 16.8, max: 41.0) -[2023-10-10 13:01:26,076][75634] Avg episode reward: [(0, '20.970'), (1, '18.120')] -[2023-10-10 13:01:26,077][76421] Saving new best policy, reward=18.120! -[2023-10-10 13:01:27,708][76542] Updated weights for policy 1, policy_version 8770 (0.0008) -[2023-10-10 13:01:28,086][76542] Updated weights for policy 1, policy_version 8780 (0.0008) -[2023-10-10 13:01:28,249][76543] Updated weights for policy 0, policy_version 8772 (0.0007) -[2023-10-10 13:01:28,454][76542] Updated weights for policy 1, policy_version 8790 (0.0007) -[2023-10-10 13:01:28,620][76543] Updated weights for policy 0, policy_version 8782 (0.0008) -[2023-10-10 13:01:28,825][76542] Updated weights for policy 1, policy_version 8800 (0.0007) -[2023-10-10 13:01:28,986][76543] Updated weights for policy 0, policy_version 8792 (0.0008) -[2023-10-10 13:01:31,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 18022400. Throughput: 0: 1824.3, 1: 1814.2. Samples: 4515020. Policy #0 lag: (min: 9.0, avg: 16.8, max: 41.0) -[2023-10-10 13:01:31,076][75634] Avg episode reward: [(0, '20.800'), (1, '17.590')] -[2023-10-10 13:01:32,705][76542] Updated weights for policy 1, policy_version 8810 (0.0009) -[2023-10-10 13:01:32,778][76543] Updated weights for policy 0, policy_version 8802 (0.0009) -[2023-10-10 13:01:33,070][76542] Updated weights for policy 1, policy_version 8820 (0.0007) -[2023-10-10 13:01:33,146][76543] Updated weights for policy 0, policy_version 8812 (0.0008) -[2023-10-10 13:01:33,444][76542] Updated weights for policy 1, policy_version 8830 (0.0009) -[2023-10-10 13:01:33,523][76543] Updated weights for policy 0, policy_version 8822 (0.0010) -[2023-10-10 13:01:33,894][76543] Updated weights for policy 0, policy_version 8832 (0.0010) -[2023-10-10 13:01:36,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 18087936. Throughput: 0: 1816.3, 1: 1809.1. Samples: 4525720. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-10 13:01:36,077][75634] Avg episode reward: [(0, '20.610'), (1, '18.950')] -[2023-10-10 13:01:36,078][76421] Saving new best policy, reward=18.950! -[2023-10-10 13:01:37,073][76542] Updated weights for policy 1, policy_version 8840 (0.0009) -[2023-10-10 13:01:37,447][76542] Updated weights for policy 1, policy_version 8850 (0.0007) -[2023-10-10 13:01:37,689][76543] Updated weights for policy 0, policy_version 8842 (0.0007) -[2023-10-10 13:01:37,811][76542] Updated weights for policy 1, policy_version 8860 (0.0008) -[2023-10-10 13:01:38,066][76543] Updated weights for policy 0, policy_version 8852 (0.0007) -[2023-10-10 13:01:38,440][76543] Updated weights for policy 0, policy_version 8862 (0.0009) -[2023-10-10 13:01:41,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 18153472. Throughput: 0: 1814.7, 1: 1811.9. Samples: 4547788. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-10 13:01:41,077][75634] Avg episode reward: [(0, '21.100'), (1, '19.140')] -[2023-10-10 13:01:41,079][76421] Saving new best policy, reward=19.140! -[2023-10-10 13:01:41,560][76542] Updated weights for policy 1, policy_version 8870 (0.0010) -[2023-10-10 13:01:41,927][76542] Updated weights for policy 1, policy_version 8880 (0.0008) -[2023-10-10 13:01:42,241][76543] Updated weights for policy 0, policy_version 8872 (0.0007) -[2023-10-10 13:01:42,297][76542] Updated weights for policy 1, policy_version 8890 (0.0008) -[2023-10-10 13:01:42,609][76543] Updated weights for policy 0, policy_version 8882 (0.0007) -[2023-10-10 13:01:42,981][76543] Updated weights for policy 0, policy_version 8892 (0.0008) -[2023-10-10 13:01:46,060][76542] Updated weights for policy 1, policy_version 8900 (0.0009) -[2023-10-10 13:01:46,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 18219008. Throughput: 0: 1817.7, 1: 1813.6. Samples: 4570394. Policy #0 lag: (min: 17.0, avg: 18.3, max: 35.0) -[2023-10-10 13:01:46,076][75634] Avg episode reward: [(0, '22.170'), (1, '18.090')] -[2023-10-10 13:01:46,423][76542] Updated weights for policy 1, policy_version 8910 (0.0008) -[2023-10-10 13:01:46,786][76543] Updated weights for policy 0, policy_version 8902 (0.0008) -[2023-10-10 13:01:46,791][76542] Updated weights for policy 1, policy_version 8920 (0.0007) -[2023-10-10 13:01:47,151][76543] Updated weights for policy 0, policy_version 8912 (0.0008) -[2023-10-10 13:01:47,524][76543] Updated weights for policy 0, policy_version 8922 (0.0011) -[2023-10-10 13:01:50,489][76542] Updated weights for policy 1, policy_version 8930 (0.0008) -[2023-10-10 13:01:50,856][76542] Updated weights for policy 1, policy_version 8940 (0.0008) -[2023-10-10 13:01:51,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 18284544. Throughput: 0: 1816.8, 1: 1800.6. Samples: 4580078. Policy #0 lag: (min: 17.0, avg: 18.3, max: 35.0) -[2023-10-10 13:01:51,076][75634] Avg episode reward: [(0, '22.810'), (1, '17.700')] -[2023-10-10 13:01:51,225][76542] Updated weights for policy 1, policy_version 8950 (0.0009) -[2023-10-10 13:01:51,299][76543] Updated weights for policy 0, policy_version 8932 (0.0008) -[2023-10-10 13:01:51,593][76542] Updated weights for policy 1, policy_version 8960 (0.0008) -[2023-10-10 13:01:51,674][76543] Updated weights for policy 0, policy_version 8942 (0.0009) -[2023-10-10 13:01:52,046][76543] Updated weights for policy 0, policy_version 8952 (0.0011) -[2023-10-10 13:01:55,221][76542] Updated weights for policy 1, policy_version 8970 (0.0007) -[2023-10-10 13:01:55,592][76542] Updated weights for policy 1, policy_version 8980 (0.0008) -[2023-10-10 13:01:55,706][76543] Updated weights for policy 0, policy_version 8962 (0.0009) -[2023-10-10 13:01:55,966][76542] Updated weights for policy 1, policy_version 8990 (0.0007) -[2023-10-10 13:01:56,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 18382848. Throughput: 0: 1822.0, 1: 1813.6. Samples: 4603134. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:01:56,076][75634] Avg episode reward: [(0, '23.000'), (1, '17.190')] -[2023-10-10 13:01:56,081][76543] Updated weights for policy 0, policy_version 8972 (0.0010) -[2023-10-10 13:01:56,452][76543] Updated weights for policy 0, policy_version 8982 (0.0008) -[2023-10-10 13:01:56,818][76543] Updated weights for policy 0, policy_version 8992 (0.0007) -[2023-10-10 13:01:59,765][76542] Updated weights for policy 1, policy_version 9000 (0.0011) -[2023-10-10 13:02:00,133][76542] Updated weights for policy 1, policy_version 9010 (0.0008) -[2023-10-10 13:02:00,502][76542] Updated weights for policy 1, policy_version 9020 (0.0007) -[2023-10-10 13:02:00,682][76543] Updated weights for policy 0, policy_version 9002 (0.0008) -[2023-10-10 13:02:01,048][76543] Updated weights for policy 0, policy_version 9012 (0.0007) -[2023-10-10 13:02:01,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 18448384. Throughput: 0: 1821.7, 1: 1808.8. Samples: 4624248. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:02:01,077][75634] Avg episode reward: [(0, '23.030'), (1, '17.550')] -[2023-10-10 13:02:01,422][76543] Updated weights for policy 0, policy_version 9022 (0.0008) -[2023-10-10 13:02:04,206][76542] Updated weights for policy 1, policy_version 9030 (0.0008) -[2023-10-10 13:02:04,598][76542] Updated weights for policy 1, policy_version 9040 (0.0008) -[2023-10-10 13:02:04,891][76543] Updated weights for policy 0, policy_version 9032 (0.0007) -[2023-10-10 13:02:04,960][76542] Updated weights for policy 1, policy_version 9050 (0.0009) -[2023-10-10 13:02:05,267][76543] Updated weights for policy 0, policy_version 9042 (0.0008) -[2023-10-10 13:02:05,645][76543] Updated weights for policy 0, policy_version 9052 (0.0010) -[2023-10-10 13:02:06,076][75634] Fps is (10 sec: 16384.0, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 18546688. Throughput: 0: 1815.9, 1: 1820.4. Samples: 4635872. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-10 13:02:06,076][75634] Avg episode reward: [(0, '23.750'), (1, '16.820')] -[2023-10-10 13:02:06,077][76362] Saving new best policy, reward=23.750! -[2023-10-10 13:02:08,515][76542] Updated weights for policy 1, policy_version 9060 (0.0010) -[2023-10-10 13:02:08,886][76542] Updated weights for policy 1, policy_version 9070 (0.0010) -[2023-10-10 13:02:09,251][76542] Updated weights for policy 1, policy_version 9080 (0.0008) -[2023-10-10 13:02:09,251][76543] Updated weights for policy 0, policy_version 9062 (0.0009) -[2023-10-10 13:02:09,624][76543] Updated weights for policy 0, policy_version 9072 (0.0009) -[2023-10-10 13:02:09,996][76543] Updated weights for policy 0, policy_version 9082 (0.0010) -[2023-10-10 13:02:11,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 18612224. Throughput: 0: 1817.1, 1: 1813.9. Samples: 4656768. Policy #0 lag: (min: 26.0, avg: 33.5, max: 58.0) -[2023-10-10 13:02:11,077][75634] Avg episode reward: [(0, '23.080'), (1, '17.550')] -[2023-10-10 13:02:13,116][76542] Updated weights for policy 1, policy_version 9090 (0.0008) -[2023-10-10 13:02:13,482][76542] Updated weights for policy 1, policy_version 9100 (0.0008) -[2023-10-10 13:02:13,681][76543] Updated weights for policy 0, policy_version 9092 (0.0008) -[2023-10-10 13:02:13,853][76542] Updated weights for policy 1, policy_version 9110 (0.0007) -[2023-10-10 13:02:14,054][76543] Updated weights for policy 0, policy_version 9102 (0.0009) -[2023-10-10 13:02:14,210][76542] Updated weights for policy 1, policy_version 9120 (0.0007) -[2023-10-10 13:02:14,416][76543] Updated weights for policy 0, policy_version 9112 (0.0007) -[2023-10-10 13:02:16,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 18677760. Throughput: 0: 1812.2, 1: 1815.9. Samples: 4678282. Policy #0 lag: (min: 26.0, avg: 33.5, max: 58.0) -[2023-10-10 13:02:16,077][75634] Avg episode reward: [(0, '23.250'), (1, '17.500')] -[2023-10-10 13:02:17,964][76542] Updated weights for policy 1, policy_version 9130 (0.0009) -[2023-10-10 13:02:18,085][76543] Updated weights for policy 0, policy_version 9122 (0.0008) -[2023-10-10 13:02:18,330][76542] Updated weights for policy 1, policy_version 9140 (0.0009) -[2023-10-10 13:02:18,457][76543] Updated weights for policy 0, policy_version 9132 (0.0009) -[2023-10-10 13:02:18,708][76542] Updated weights for policy 1, policy_version 9150 (0.0008) -[2023-10-10 13:02:18,828][76543] Updated weights for policy 0, policy_version 9142 (0.0009) -[2023-10-10 13:02:19,211][76543] Updated weights for policy 0, policy_version 9152 (0.0008) -[2023-10-10 13:02:21,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 18743296. Throughput: 0: 1822.4, 1: 1820.1. Samples: 4689630. Policy #0 lag: (min: 31.0, avg: 32.6, max: 59.0) -[2023-10-10 13:02:21,076][75634] Avg episode reward: [(0, '22.960'), (1, '17.160')] -[2023-10-10 13:02:22,342][76542] Updated weights for policy 1, policy_version 9160 (0.0007) -[2023-10-10 13:02:22,703][76542] Updated weights for policy 1, policy_version 9170 (0.0009) -[2023-10-10 13:02:22,957][76543] Updated weights for policy 0, policy_version 9162 (0.0008) -[2023-10-10 13:02:23,070][76542] Updated weights for policy 1, policy_version 9180 (0.0008) -[2023-10-10 13:02:23,329][76543] Updated weights for policy 0, policy_version 9172 (0.0008) -[2023-10-10 13:02:23,698][76543] Updated weights for policy 0, policy_version 9182 (0.0011) -[2023-10-10 13:02:26,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 18808832. Throughput: 0: 1809.2, 1: 1816.4. Samples: 4710938. Policy #0 lag: (min: 31.0, avg: 32.6, max: 59.0) -[2023-10-10 13:02:26,076][75634] Avg episode reward: [(0, '23.070'), (1, '15.740')] -[2023-10-10 13:02:26,690][76542] Updated weights for policy 1, policy_version 9190 (0.0007) -[2023-10-10 13:02:27,055][76542] Updated weights for policy 1, policy_version 9200 (0.0008) -[2023-10-10 13:02:27,363][76543] Updated weights for policy 0, policy_version 9192 (0.0008) -[2023-10-10 13:02:27,420][76542] Updated weights for policy 1, policy_version 9210 (0.0007) -[2023-10-10 13:02:27,745][76543] Updated weights for policy 0, policy_version 9202 (0.0008) -[2023-10-10 13:02:28,112][76543] Updated weights for policy 0, policy_version 9212 (0.0007) -[2023-10-10 13:02:30,968][76542] Updated weights for policy 1, policy_version 9220 (0.0009) -[2023-10-10 13:02:31,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 18874368. Throughput: 0: 1810.5, 1: 1815.1. Samples: 4733548. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:02:31,077][75634] Avg episode reward: [(0, '22.960'), (1, '16.210')] -[2023-10-10 13:02:31,088][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000009216_9437184.pth... -[2023-10-10 13:02:31,123][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000007520_7700480.pth -[2023-10-10 13:02:31,341][76542] Updated weights for policy 1, policy_version 9230 (0.0009) -[2023-10-10 13:02:31,707][76542] Updated weights for policy 1, policy_version 9240 (0.0009) -[2023-10-10 13:02:31,818][76543] Updated weights for policy 0, policy_version 9222 (0.0007) -[2023-10-10 13:02:31,997][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000009248_9469952.pth... -[2023-10-10 13:02:32,037][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000007520_7700480.pth -[2023-10-10 13:02:32,205][76543] Updated weights for policy 0, policy_version 9232 (0.0008) -[2023-10-10 13:02:32,576][76543] Updated weights for policy 0, policy_version 9242 (0.0008) -[2023-10-10 13:02:35,182][76542] Updated weights for policy 1, policy_version 9250 (0.0008) -[2023-10-10 13:02:35,550][76542] Updated weights for policy 1, policy_version 9260 (0.0009) -[2023-10-10 13:02:35,918][76542] Updated weights for policy 1, policy_version 9270 (0.0010) -[2023-10-10 13:02:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 18939904. Throughput: 0: 1817.7, 1: 1819.6. Samples: 4743756. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:02:36,076][75634] Avg episode reward: [(0, '22.560'), (1, '14.230')] -[2023-10-10 13:02:36,175][76543] Updated weights for policy 0, policy_version 9252 (0.0010) -[2023-10-10 13:02:36,286][76542] Updated weights for policy 1, policy_version 9280 (0.0007) -[2023-10-10 13:02:36,548][76543] Updated weights for policy 0, policy_version 9262 (0.0008) -[2023-10-10 13:02:36,927][76543] Updated weights for policy 0, policy_version 9272 (0.0010) -[2023-10-10 13:02:40,127][76542] Updated weights for policy 1, policy_version 9290 (0.0007) -[2023-10-10 13:02:40,498][76542] Updated weights for policy 1, policy_version 9300 (0.0007) -[2023-10-10 13:02:40,598][76543] Updated weights for policy 0, policy_version 9282 (0.0008) -[2023-10-10 13:02:40,870][76542] Updated weights for policy 1, policy_version 9310 (0.0007) -[2023-10-10 13:02:40,974][76543] Updated weights for policy 0, policy_version 9292 (0.0009) -[2023-10-10 13:02:41,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 19038208. Throughput: 0: 1819.2, 1: 1811.6. Samples: 4766516. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-10 13:02:41,077][75634] Avg episode reward: [(0, '22.460'), (1, '14.680')] -[2023-10-10 13:02:41,343][76543] Updated weights for policy 0, policy_version 9302 (0.0010) -[2023-10-10 13:02:41,711][76543] Updated weights for policy 0, policy_version 9312 (0.0011) -[2023-10-10 13:02:44,598][76542] Updated weights for policy 1, policy_version 9320 (0.0009) -[2023-10-10 13:02:44,958][76542] Updated weights for policy 1, policy_version 9330 (0.0009) -[2023-10-10 13:02:45,324][76542] Updated weights for policy 1, policy_version 9340 (0.0009) -[2023-10-10 13:02:45,427][76543] Updated weights for policy 0, policy_version 9322 (0.0008) -[2023-10-10 13:02:45,799][76543] Updated weights for policy 0, policy_version 9332 (0.0008) -[2023-10-10 13:02:46,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 19103744. Throughput: 0: 1814.0, 1: 1809.6. Samples: 4787310. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-10 13:02:46,076][75634] Avg episode reward: [(0, '23.430'), (1, '14.970')] -[2023-10-10 13:02:46,168][76543] Updated weights for policy 0, policy_version 9342 (0.0007) -[2023-10-10 13:02:49,215][76542] Updated weights for policy 1, policy_version 9350 (0.0009) -[2023-10-10 13:02:49,612][76542] Updated weights for policy 1, policy_version 9360 (0.0009) -[2023-10-10 13:02:49,975][76542] Updated weights for policy 1, policy_version 9370 (0.0008) -[2023-10-10 13:02:49,993][76543] Updated weights for policy 0, policy_version 9352 (0.0008) -[2023-10-10 13:02:50,364][76543] Updated weights for policy 0, policy_version 9362 (0.0010) -[2023-10-10 13:02:50,740][76543] Updated weights for policy 0, policy_version 9372 (0.0009) -[2023-10-10 13:02:51,076][75634] Fps is (10 sec: 16384.0, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 19202048. Throughput: 0: 1818.3, 1: 1803.3. Samples: 4798844. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:02:51,077][75634] Avg episode reward: [(0, '23.360'), (1, '16.480')] -[2023-10-10 13:02:53,744][76542] Updated weights for policy 1, policy_version 9380 (0.0007) -[2023-10-10 13:02:54,110][76542] Updated weights for policy 1, policy_version 9390 (0.0008) -[2023-10-10 13:02:54,248][76543] Updated weights for policy 0, policy_version 9382 (0.0007) -[2023-10-10 13:02:54,474][76542] Updated weights for policy 1, policy_version 9400 (0.0008) -[2023-10-10 13:02:54,618][76543] Updated weights for policy 0, policy_version 9392 (0.0008) -[2023-10-10 13:02:54,986][76543] Updated weights for policy 0, policy_version 9402 (0.0009) -[2023-10-10 13:02:56,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 19267584. Throughput: 0: 1823.6, 1: 1807.7. Samples: 4820174. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:02:56,077][75634] Avg episode reward: [(0, '22.900'), (1, '15.180')] -[2023-10-10 13:02:58,172][76542] Updated weights for policy 1, policy_version 9410 (0.0008) -[2023-10-10 13:02:58,538][76542] Updated weights for policy 1, policy_version 9420 (0.0008) -[2023-10-10 13:02:58,852][76543] Updated weights for policy 0, policy_version 9412 (0.0009) -[2023-10-10 13:02:58,911][76542] Updated weights for policy 1, policy_version 9430 (0.0008) -[2023-10-10 13:02:59,206][76543] Updated weights for policy 0, policy_version 9422 (0.0008) -[2023-10-10 13:02:59,276][76542] Updated weights for policy 1, policy_version 9440 (0.0009) -[2023-10-10 13:02:59,576][76543] Updated weights for policy 0, policy_version 9432 (0.0008) -[2023-10-10 13:03:01,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 19333120. Throughput: 0: 1816.5, 1: 1805.3. Samples: 4841262. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:03:01,076][75634] Avg episode reward: [(0, '21.980'), (1, '17.140')] -[2023-10-10 13:03:03,042][76542] Updated weights for policy 1, policy_version 9450 (0.0011) -[2023-10-10 13:03:03,246][76543] Updated weights for policy 0, policy_version 9442 (0.0009) -[2023-10-10 13:03:03,409][76542] Updated weights for policy 1, policy_version 9460 (0.0007) -[2023-10-10 13:03:03,627][76543] Updated weights for policy 0, policy_version 9452 (0.0008) -[2023-10-10 13:03:03,775][76542] Updated weights for policy 1, policy_version 9470 (0.0008) -[2023-10-10 13:03:03,996][76543] Updated weights for policy 0, policy_version 9462 (0.0010) -[2023-10-10 13:03:04,365][76543] Updated weights for policy 0, policy_version 9472 (0.0011) -[2023-10-10 13:03:06,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 19398656. Throughput: 0: 1819.5, 1: 1808.1. Samples: 4852874. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 13:03:06,077][75634] Avg episode reward: [(0, '22.450'), (1, '17.350')] -[2023-10-10 13:03:07,605][76542] Updated weights for policy 1, policy_version 9480 (0.0007) -[2023-10-10 13:03:07,961][76542] Updated weights for policy 1, policy_version 9490 (0.0008) -[2023-10-10 13:03:08,141][76543] Updated weights for policy 0, policy_version 9482 (0.0007) -[2023-10-10 13:03:08,342][76542] Updated weights for policy 1, policy_version 9500 (0.0008) -[2023-10-10 13:03:08,521][76543] Updated weights for policy 0, policy_version 9492 (0.0007) -[2023-10-10 13:03:08,893][76543] Updated weights for policy 0, policy_version 9502 (0.0009) -[2023-10-10 13:03:11,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 19464192. Throughput: 0: 1819.2, 1: 1800.4. Samples: 4873820. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 13:03:11,076][75634] Avg episode reward: [(0, '22.960'), (1, '16.970')] -[2023-10-10 13:03:12,003][76542] Updated weights for policy 1, policy_version 9510 (0.0009) -[2023-10-10 13:03:12,383][76542] Updated weights for policy 1, policy_version 9520 (0.0009) -[2023-10-10 13:03:12,428][76543] Updated weights for policy 0, policy_version 9512 (0.0009) -[2023-10-10 13:03:12,749][76542] Updated weights for policy 1, policy_version 9530 (0.0008) -[2023-10-10 13:03:12,795][76543] Updated weights for policy 0, policy_version 9522 (0.0009) -[2023-10-10 13:03:13,180][76543] Updated weights for policy 0, policy_version 9532 (0.0009) -[2023-10-10 13:03:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 19529728. Throughput: 0: 1827.2, 1: 1801.4. Samples: 4896838. Policy #0 lag: (min: 9.0, avg: 24.5, max: 41.0) -[2023-10-10 13:03:16,077][75634] Avg episode reward: [(0, '23.910'), (1, '16.910')] -[2023-10-10 13:03:16,089][76362] Saving new best policy, reward=23.910! -[2023-10-10 13:03:16,503][76542] Updated weights for policy 1, policy_version 9540 (0.0007) -[2023-10-10 13:03:16,803][76543] Updated weights for policy 0, policy_version 9542 (0.0009) -[2023-10-10 13:03:16,863][76542] Updated weights for policy 1, policy_version 9550 (0.0007) -[2023-10-10 13:03:17,178][76543] Updated weights for policy 0, policy_version 9552 (0.0008) -[2023-10-10 13:03:17,232][76542] Updated weights for policy 1, policy_version 9560 (0.0007) -[2023-10-10 13:03:17,547][76543] Updated weights for policy 0, policy_version 9562 (0.0008) -[2023-10-10 13:03:20,859][76542] Updated weights for policy 1, policy_version 9570 (0.0008) -[2023-10-10 13:03:21,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 19595264. Throughput: 0: 1820.5, 1: 1801.1. Samples: 4906728. Policy #0 lag: (min: 9.0, avg: 24.5, max: 41.0) -[2023-10-10 13:03:21,076][75634] Avg episode reward: [(0, '24.210'), (1, '16.970')] -[2023-10-10 13:03:21,077][76362] Saving new best policy, reward=24.210! -[2023-10-10 13:03:21,228][76542] Updated weights for policy 1, policy_version 9580 (0.0008) -[2023-10-10 13:03:21,434][76543] Updated weights for policy 0, policy_version 9572 (0.0008) -[2023-10-10 13:03:21,594][76542] Updated weights for policy 1, policy_version 9590 (0.0008) -[2023-10-10 13:03:21,804][76543] Updated weights for policy 0, policy_version 9582 (0.0008) -[2023-10-10 13:03:21,962][76542] Updated weights for policy 1, policy_version 9600 (0.0007) -[2023-10-10 13:03:22,175][76543] Updated weights for policy 0, policy_version 9592 (0.0008) -[2023-10-10 13:03:25,743][76543] Updated weights for policy 0, policy_version 9602 (0.0008) -[2023-10-10 13:03:25,782][76542] Updated weights for policy 1, policy_version 9610 (0.0009) -[2023-10-10 13:03:26,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14440.2). Total num frames: 19660800. Throughput: 0: 1818.1, 1: 1801.6. Samples: 4929402. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:03:26,076][75634] Avg episode reward: [(0, '23.040'), (1, '15.420')] -[2023-10-10 13:03:26,119][76543] Updated weights for policy 0, policy_version 9612 (0.0009) -[2023-10-10 13:03:26,158][76542] Updated weights for policy 1, policy_version 9620 (0.0009) -[2023-10-10 13:03:26,495][76543] Updated weights for policy 0, policy_version 9622 (0.0009) -[2023-10-10 13:03:26,531][76542] Updated weights for policy 1, policy_version 9630 (0.0008) -[2023-10-10 13:03:26,871][76543] Updated weights for policy 0, policy_version 9632 (0.0009) -[2023-10-10 13:03:30,114][76542] Updated weights for policy 1, policy_version 9640 (0.0007) -[2023-10-10 13:03:30,476][76542] Updated weights for policy 1, policy_version 9650 (0.0008) -[2023-10-10 13:03:30,636][76543] Updated weights for policy 0, policy_version 9642 (0.0009) -[2023-10-10 13:03:30,848][76542] Updated weights for policy 1, policy_version 9660 (0.0008) -[2023-10-10 13:03:31,012][76543] Updated weights for policy 0, policy_version 9652 (0.0009) -[2023-10-10 13:03:31,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 19759104. Throughput: 0: 1826.0, 1: 1810.8. Samples: 4950964. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:03:31,077][75634] Avg episode reward: [(0, '23.920'), (1, '15.260')] -[2023-10-10 13:03:31,381][76543] Updated weights for policy 0, policy_version 9662 (0.0008) -[2023-10-10 13:03:34,611][76542] Updated weights for policy 1, policy_version 9670 (0.0009) -[2023-10-10 13:03:34,805][76543] Updated weights for policy 0, policy_version 9672 (0.0008) -[2023-10-10 13:03:35,005][76542] Updated weights for policy 1, policy_version 9680 (0.0008) -[2023-10-10 13:03:35,181][76543] Updated weights for policy 0, policy_version 9682 (0.0009) -[2023-10-10 13:03:35,375][76542] Updated weights for policy 1, policy_version 9690 (0.0007) -[2023-10-10 13:03:35,548][76543] Updated weights for policy 0, policy_version 9692 (0.0007) -[2023-10-10 13:03:36,076][75634] Fps is (10 sec: 19660.7, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 19857408. Throughput: 0: 1826.8, 1: 1799.1. Samples: 4962008. Policy #0 lag: (min: 25.0, avg: 36.7, max: 57.0) -[2023-10-10 13:03:36,077][75634] Avg episode reward: [(0, '22.890'), (1, '15.750')] -[2023-10-10 13:03:39,089][76542] Updated weights for policy 1, policy_version 9700 (0.0007) -[2023-10-10 13:03:39,290][76543] Updated weights for policy 0, policy_version 9702 (0.0008) -[2023-10-10 13:03:39,454][76542] Updated weights for policy 1, policy_version 9710 (0.0010) -[2023-10-10 13:03:39,666][76543] Updated weights for policy 0, policy_version 9712 (0.0009) -[2023-10-10 13:03:39,820][76542] Updated weights for policy 1, policy_version 9720 (0.0010) -[2023-10-10 13:03:40,027][76543] Updated weights for policy 0, policy_version 9722 (0.0009) -[2023-10-10 13:03:41,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 19922944. Throughput: 0: 1821.3, 1: 1809.2. Samples: 4983548. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:03:41,076][75634] Avg episode reward: [(0, '22.940'), (1, '15.470')] -[2023-10-10 13:03:43,524][76542] Updated weights for policy 1, policy_version 9730 (0.0008) -[2023-10-10 13:03:43,745][76543] Updated weights for policy 0, policy_version 9732 (0.0009) -[2023-10-10 13:03:43,892][76542] Updated weights for policy 1, policy_version 9740 (0.0008) -[2023-10-10 13:03:44,111][76543] Updated weights for policy 0, policy_version 9742 (0.0007) -[2023-10-10 13:03:44,268][76542] Updated weights for policy 1, policy_version 9750 (0.0008) -[2023-10-10 13:03:44,495][76543] Updated weights for policy 0, policy_version 9752 (0.0010) -[2023-10-10 13:03:44,638][76542] Updated weights for policy 1, policy_version 9760 (0.0008) -[2023-10-10 13:03:46,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 19988480. Throughput: 0: 1823.0, 1: 1801.1. Samples: 5004350. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:03:46,077][75634] Avg episode reward: [(0, '23.190'), (1, '16.680')] -[2023-10-10 13:03:48,180][76543] Updated weights for policy 0, policy_version 9762 (0.0008) -[2023-10-10 13:03:48,438][76542] Updated weights for policy 1, policy_version 9770 (0.0007) -[2023-10-10 13:03:48,552][76543] Updated weights for policy 0, policy_version 9772 (0.0008) -[2023-10-10 13:03:48,808][76542] Updated weights for policy 1, policy_version 9780 (0.0007) -[2023-10-10 13:03:48,928][76543] Updated weights for policy 0, policy_version 9782 (0.0008) -[2023-10-10 13:03:49,176][76542] Updated weights for policy 1, policy_version 9790 (0.0009) -[2023-10-10 13:03:49,297][76543] Updated weights for policy 0, policy_version 9792 (0.0008) -[2023-10-10 13:03:51,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 20054016. Throughput: 0: 1817.9, 1: 1808.3. Samples: 5016052. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:03:51,076][75634] Avg episode reward: [(0, '23.030'), (1, '18.290')] -[2023-10-10 13:03:52,845][76542] Updated weights for policy 1, policy_version 9800 (0.0008) -[2023-10-10 13:03:52,962][76543] Updated weights for policy 0, policy_version 9802 (0.0008) -[2023-10-10 13:03:53,211][76542] Updated weights for policy 1, policy_version 9810 (0.0010) -[2023-10-10 13:03:53,340][76543] Updated weights for policy 0, policy_version 9812 (0.0009) -[2023-10-10 13:03:53,574][76542] Updated weights for policy 1, policy_version 9820 (0.0008) -[2023-10-10 13:03:53,717][76543] Updated weights for policy 0, policy_version 9822 (0.0009) -[2023-10-10 13:03:56,076][75634] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 20119552. Throughput: 0: 1818.2, 1: 1797.6. Samples: 5036532. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:03:56,076][75634] Avg episode reward: [(0, '24.210'), (1, '17.080')] -[2023-10-10 13:03:57,383][76542] Updated weights for policy 1, policy_version 9830 (0.0008) -[2023-10-10 13:03:57,433][76543] Updated weights for policy 0, policy_version 9832 (0.0007) -[2023-10-10 13:03:57,753][76542] Updated weights for policy 1, policy_version 9840 (0.0007) -[2023-10-10 13:03:57,816][76543] Updated weights for policy 0, policy_version 9842 (0.0008) -[2023-10-10 13:03:58,132][76542] Updated weights for policy 1, policy_version 9850 (0.0008) -[2023-10-10 13:03:58,174][76543] Updated weights for policy 0, policy_version 9852 (0.0008) -[2023-10-10 13:04:01,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 20185088. Throughput: 0: 1807.9, 1: 1793.9. Samples: 5058918. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-10 13:04:01,076][75634] Avg episode reward: [(0, '23.550'), (1, '17.280')] -[2023-10-10 13:04:01,861][76542] Updated weights for policy 1, policy_version 9860 (0.0007) -[2023-10-10 13:04:01,989][76543] Updated weights for policy 0, policy_version 9862 (0.0007) -[2023-10-10 13:04:02,227][76542] Updated weights for policy 1, policy_version 9870 (0.0008) -[2023-10-10 13:04:02,361][76543] Updated weights for policy 0, policy_version 9872 (0.0009) -[2023-10-10 13:04:02,599][76542] Updated weights for policy 1, policy_version 9880 (0.0008) -[2023-10-10 13:04:02,723][76543] Updated weights for policy 0, policy_version 9882 (0.0008) -[2023-10-10 13:04:06,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 20250624. Throughput: 0: 1809.7, 1: 1790.2. Samples: 5068724. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-10 13:04:06,077][75634] Avg episode reward: [(0, '22.660'), (1, '17.580')] -[2023-10-10 13:04:06,347][76542] Updated weights for policy 1, policy_version 9890 (0.0008) -[2023-10-10 13:04:06,398][76543] Updated weights for policy 0, policy_version 9892 (0.0008) -[2023-10-10 13:04:06,712][76542] Updated weights for policy 1, policy_version 9900 (0.0007) -[2023-10-10 13:04:06,773][76543] Updated weights for policy 0, policy_version 9902 (0.0008) -[2023-10-10 13:04:07,076][76542] Updated weights for policy 1, policy_version 9910 (0.0007) -[2023-10-10 13:04:07,144][76543] Updated weights for policy 0, policy_version 9912 (0.0008) -[2023-10-10 13:04:07,443][76542] Updated weights for policy 1, policy_version 9920 (0.0007) -[2023-10-10 13:04:10,755][76543] Updated weights for policy 0, policy_version 9922 (0.0008) -[2023-10-10 13:04:11,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 20316160. Throughput: 0: 1814.7, 1: 1795.6. Samples: 5091864. Policy #0 lag: (min: 24.0, avg: 43.1, max: 56.0) -[2023-10-10 13:04:11,077][75634] Avg episode reward: [(0, '22.120'), (1, '16.100')] -[2023-10-10 13:04:11,125][76543] Updated weights for policy 0, policy_version 9932 (0.0008) -[2023-10-10 13:04:11,167][76542] Updated weights for policy 1, policy_version 9930 (0.0008) -[2023-10-10 13:04:11,494][76543] Updated weights for policy 0, policy_version 9942 (0.0009) -[2023-10-10 13:04:11,531][76542] Updated weights for policy 1, policy_version 9940 (0.0008) -[2023-10-10 13:04:11,907][76542] Updated weights for policy 1, policy_version 9950 (0.0008) -[2023-10-10 13:04:15,315][76543] Updated weights for policy 0, policy_version 9953 (0.0007) -[2023-10-10 13:04:15,639][76542] Updated weights for policy 1, policy_version 9960 (0.0008) -[2023-10-10 13:04:15,720][76543] Updated weights for policy 0, policy_version 9963 (0.0009) -[2023-10-10 13:04:16,001][76542] Updated weights for policy 1, policy_version 9970 (0.0009) -[2023-10-10 13:04:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 20381696. Throughput: 0: 1818.4, 1: 1810.0. Samples: 5114238. Policy #0 lag: (min: 24.0, avg: 43.1, max: 56.0) -[2023-10-10 13:04:16,077][75634] Avg episode reward: [(0, '22.070'), (1, '15.620')] -[2023-10-10 13:04:16,088][76543] Updated weights for policy 0, policy_version 9973 (0.0009) -[2023-10-10 13:04:16,373][76542] Updated weights for policy 1, policy_version 9980 (0.0009) -[2023-10-10 13:04:16,448][76543] Updated weights for policy 0, policy_version 9983 (0.0007) -[2023-10-10 13:04:20,039][76543] Updated weights for policy 0, policy_version 9993 (0.0010) -[2023-10-10 13:04:20,304][76542] Updated weights for policy 1, policy_version 9990 (0.0008) -[2023-10-10 13:04:20,404][76543] Updated weights for policy 0, policy_version 10003 (0.0009) -[2023-10-10 13:04:20,698][76542] Updated weights for policy 1, policy_version 10000 (0.0008) -[2023-10-10 13:04:20,775][76543] Updated weights for policy 0, policy_version 10013 (0.0008) -[2023-10-10 13:04:21,065][76542] Updated weights for policy 1, policy_version 10010 (0.0008) -[2023-10-10 13:04:21,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 20480000. Throughput: 0: 1812.5, 1: 1800.0. Samples: 5124568. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:04:21,076][75634] Avg episode reward: [(0, '22.200'), (1, '17.740')] -[2023-10-10 13:04:24,333][76543] Updated weights for policy 0, policy_version 10023 (0.0007) -[2023-10-10 13:04:24,717][76543] Updated weights for policy 0, policy_version 10033 (0.0009) -[2023-10-10 13:04:24,786][76542] Updated weights for policy 1, policy_version 10020 (0.0009) -[2023-10-10 13:04:25,087][76543] Updated weights for policy 0, policy_version 10043 (0.0007) -[2023-10-10 13:04:25,159][76542] Updated weights for policy 1, policy_version 10030 (0.0008) -[2023-10-10 13:04:25,531][76542] Updated weights for policy 1, policy_version 10040 (0.0008) -[2023-10-10 13:04:26,076][75634] Fps is (10 sec: 19661.5, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 20578304. Throughput: 0: 1820.8, 1: 1813.4. Samples: 5147088. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:04:26,076][75634] Avg episode reward: [(0, '22.330'), (1, '17.910')] -[2023-10-10 13:04:28,772][76543] Updated weights for policy 0, policy_version 10053 (0.0008) -[2023-10-10 13:04:29,142][76543] Updated weights for policy 0, policy_version 10063 (0.0007) -[2023-10-10 13:04:29,202][76542] Updated weights for policy 1, policy_version 10050 (0.0007) -[2023-10-10 13:04:29,516][76543] Updated weights for policy 0, policy_version 10073 (0.0007) -[2023-10-10 13:04:29,568][76542] Updated weights for policy 1, policy_version 10060 (0.0007) -[2023-10-10 13:04:29,937][76542] Updated weights for policy 1, policy_version 10070 (0.0009) -[2023-10-10 13:04:30,308][76542] Updated weights for policy 1, policy_version 10080 (0.0009) -[2023-10-10 13:04:31,076][75634] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 20643840. Throughput: 0: 1829.1, 1: 1793.6. Samples: 5167370. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-10 13:04:31,077][75634] Avg episode reward: [(0, '22.410'), (1, '19.180')] -[2023-10-10 13:04:31,087][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000010080_10321920.pth... -[2023-10-10 13:04:31,087][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000010080_10321920.pth... -[2023-10-10 13:04:31,117][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000008384_8585216.pth -[2023-10-10 13:04:31,118][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000008384_8585216.pth -[2023-10-10 13:04:31,122][76421] Saving new best policy, reward=19.180! -[2023-10-10 13:04:33,013][76543] Updated weights for policy 0, policy_version 10083 (0.0010) -[2023-10-10 13:04:33,382][76543] Updated weights for policy 0, policy_version 10093 (0.0009) -[2023-10-10 13:04:33,747][76543] Updated weights for policy 0, policy_version 10103 (0.0009) -[2023-10-10 13:04:34,003][76542] Updated weights for policy 1, policy_version 10090 (0.0007) -[2023-10-10 13:04:34,374][76542] Updated weights for policy 1, policy_version 10100 (0.0007) -[2023-10-10 13:04:34,749][76542] Updated weights for policy 1, policy_version 10110 (0.0009) -[2023-10-10 13:04:36,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 20709376. Throughput: 0: 1830.1, 1: 1813.1. Samples: 5179996. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-10 13:04:36,077][75634] Avg episode reward: [(0, '21.860'), (1, '20.170')] -[2023-10-10 13:04:36,078][76421] Saving new best policy, reward=20.170! -[2023-10-10 13:04:37,390][76543] Updated weights for policy 0, policy_version 10113 (0.0008) -[2023-10-10 13:04:37,771][76543] Updated weights for policy 0, policy_version 10123 (0.0009) -[2023-10-10 13:04:38,149][76543] Updated weights for policy 0, policy_version 10133 (0.0008) -[2023-10-10 13:04:38,508][76543] Updated weights for policy 0, policy_version 10143 (0.0007) -[2023-10-10 13:04:38,516][76542] Updated weights for policy 1, policy_version 10120 (0.0008) -[2023-10-10 13:04:38,893][76542] Updated weights for policy 1, policy_version 10130 (0.0008) -[2023-10-10 13:04:39,267][76542] Updated weights for policy 1, policy_version 10140 (0.0008) -[2023-10-10 13:04:41,076][75634] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 20774912. Throughput: 0: 1841.2, 1: 1800.8. Samples: 5200422. Policy #0 lag: (min: 9.0, avg: 15.6, max: 41.0) -[2023-10-10 13:04:41,076][75634] Avg episode reward: [(0, '21.670'), (1, '18.630')] -[2023-10-10 13:04:42,133][76543] Updated weights for policy 0, policy_version 10153 (0.0010) -[2023-10-10 13:04:42,508][76543] Updated weights for policy 0, policy_version 10163 (0.0007) -[2023-10-10 13:04:42,875][76543] Updated weights for policy 0, policy_version 10173 (0.0007) -[2023-10-10 13:04:42,919][76542] Updated weights for policy 1, policy_version 10150 (0.0008) -[2023-10-10 13:04:43,288][76542] Updated weights for policy 1, policy_version 10160 (0.0008) -[2023-10-10 13:04:43,657][76542] Updated weights for policy 1, policy_version 10170 (0.0007) -[2023-10-10 13:04:46,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 20840448. Throughput: 0: 1842.5, 1: 1810.5. Samples: 5223306. Policy #0 lag: (min: 9.0, avg: 15.6, max: 41.0) -[2023-10-10 13:04:46,076][75634] Avg episode reward: [(0, '24.220'), (1, '17.680')] -[2023-10-10 13:04:46,085][76362] Saving new best policy, reward=24.220! -[2023-10-10 13:04:46,698][76543] Updated weights for policy 0, policy_version 10183 (0.0008) -[2023-10-10 13:04:47,069][76543] Updated weights for policy 0, policy_version 10193 (0.0009) -[2023-10-10 13:04:47,337][76542] Updated weights for policy 1, policy_version 10180 (0.0007) -[2023-10-10 13:04:47,442][76543] Updated weights for policy 0, policy_version 10203 (0.0008) -[2023-10-10 13:04:47,713][76542] Updated weights for policy 1, policy_version 10190 (0.0008) -[2023-10-10 13:04:48,083][76542] Updated weights for policy 1, policy_version 10200 (0.0008) -[2023-10-10 13:04:51,075][76543] Updated weights for policy 0, policy_version 10213 (0.0008) -[2023-10-10 13:04:51,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 20905984. Throughput: 0: 1841.2, 1: 1812.7. Samples: 5233148. Policy #0 lag: (min: 31.0, avg: 31.5, max: 45.0) -[2023-10-10 13:04:51,076][75634] Avg episode reward: [(0, '23.550'), (1, '17.640')] -[2023-10-10 13:04:51,442][76543] Updated weights for policy 0, policy_version 10223 (0.0009) -[2023-10-10 13:04:51,813][76543] Updated weights for policy 0, policy_version 10233 (0.0007) -[2023-10-10 13:04:51,815][76542] Updated weights for policy 1, policy_version 10210 (0.0007) -[2023-10-10 13:04:52,177][76542] Updated weights for policy 1, policy_version 10220 (0.0008) -[2023-10-10 13:04:52,556][76542] Updated weights for policy 1, policy_version 10230 (0.0009) -[2023-10-10 13:04:52,932][76542] Updated weights for policy 1, policy_version 10240 (0.0008) -[2023-10-10 13:04:55,512][76543] Updated weights for policy 0, policy_version 10243 (0.0007) -[2023-10-10 13:04:55,892][76543] Updated weights for policy 0, policy_version 10253 (0.0009) -[2023-10-10 13:04:56,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 20971520. Throughput: 0: 1839.5, 1: 1803.3. Samples: 5255792. Policy #0 lag: (min: 31.0, avg: 31.5, max: 45.0) -[2023-10-10 13:04:56,077][75634] Avg episode reward: [(0, '22.820'), (1, '18.200')] -[2023-10-10 13:04:56,255][76543] Updated weights for policy 0, policy_version 10263 (0.0008) -[2023-10-10 13:04:56,668][76542] Updated weights for policy 1, policy_version 10250 (0.0007) -[2023-10-10 13:04:57,037][76542] Updated weights for policy 1, policy_version 10260 (0.0007) -[2023-10-10 13:04:57,416][76542] Updated weights for policy 1, policy_version 10270 (0.0008) -[2023-10-10 13:04:59,946][76543] Updated weights for policy 0, policy_version 10273 (0.0007) -[2023-10-10 13:05:00,359][76543] Updated weights for policy 0, policy_version 10283 (0.0010) -[2023-10-10 13:05:00,739][76543] Updated weights for policy 0, policy_version 10293 (0.0007) -[2023-10-10 13:05:01,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 21037056. Throughput: 0: 1825.5, 1: 1818.3. Samples: 5278206. Policy #0 lag: (min: 31.0, avg: 31.5, max: 45.0) -[2023-10-10 13:05:01,076][75634] Avg episode reward: [(0, '23.120'), (1, '18.500')] -[2023-10-10 13:05:01,100][76542] Updated weights for policy 1, policy_version 10280 (0.0007) -[2023-10-10 13:05:01,114][76543] Updated weights for policy 0, policy_version 10303 (0.0009) -[2023-10-10 13:05:01,466][76542] Updated weights for policy 1, policy_version 10290 (0.0010) -[2023-10-10 13:05:01,837][76542] Updated weights for policy 1, policy_version 10300 (0.0009) -[2023-10-10 13:05:04,627][76543] Updated weights for policy 0, policy_version 10313 (0.0010) -[2023-10-10 13:05:05,000][76543] Updated weights for policy 0, policy_version 10323 (0.0010) -[2023-10-10 13:05:05,367][76543] Updated weights for policy 0, policy_version 10333 (0.0010) -[2023-10-10 13:05:05,633][76542] Updated weights for policy 1, policy_version 10310 (0.0009) -[2023-10-10 13:05:06,012][76542] Updated weights for policy 1, policy_version 10320 (0.0010) -[2023-10-10 13:05:06,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 21135360. Throughput: 0: 1837.4, 1: 1802.7. Samples: 5288372. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-10 13:05:06,076][75634] Avg episode reward: [(0, '24.230'), (1, '18.100')] -[2023-10-10 13:05:06,077][76362] Saving new best policy, reward=24.230! -[2023-10-10 13:05:06,389][76542] Updated weights for policy 1, policy_version 10330 (0.0010) -[2023-10-10 13:05:09,005][76543] Updated weights for policy 0, policy_version 10343 (0.0008) -[2023-10-10 13:05:09,377][76543] Updated weights for policy 0, policy_version 10353 (0.0008) -[2023-10-10 13:05:09,748][76543] Updated weights for policy 0, policy_version 10363 (0.0007) -[2023-10-10 13:05:10,095][76542] Updated weights for policy 1, policy_version 10340 (0.0009) -[2023-10-10 13:05:10,465][76542] Updated weights for policy 1, policy_version 10350 (0.0009) -[2023-10-10 13:05:10,838][76542] Updated weights for policy 1, policy_version 10360 (0.0008) -[2023-10-10 13:05:11,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 21200896. Throughput: 0: 1825.5, 1: 1807.6. Samples: 5310576. Policy #0 lag: (min: 22.0, avg: 23.6, max: 50.0) -[2023-10-10 13:05:11,076][75634] Avg episode reward: [(0, '23.450'), (1, '18.860')] -[2023-10-10 13:05:13,412][76543] Updated weights for policy 0, policy_version 10373 (0.0008) -[2023-10-10 13:05:13,786][76543] Updated weights for policy 0, policy_version 10383 (0.0010) -[2023-10-10 13:05:14,160][76543] Updated weights for policy 0, policy_version 10393 (0.0009) -[2023-10-10 13:05:14,648][76542] Updated weights for policy 1, policy_version 10370 (0.0009) -[2023-10-10 13:05:15,024][76542] Updated weights for policy 1, policy_version 10380 (0.0007) -[2023-10-10 13:05:15,397][76542] Updated weights for policy 1, policy_version 10390 (0.0007) -[2023-10-10 13:05:15,765][76542] Updated weights for policy 1, policy_version 10400 (0.0008) -[2023-10-10 13:05:16,076][75634] Fps is (10 sec: 16383.9, 60 sec: 15291.8, 300 sec: 14551.4). Total num frames: 21299200. Throughput: 0: 1830.6, 1: 1807.2. Samples: 5331068. Policy #0 lag: (min: 22.0, avg: 23.6, max: 50.0) -[2023-10-10 13:05:16,077][75634] Avg episode reward: [(0, '24.350'), (1, '19.580')] -[2023-10-10 13:05:16,088][76362] Saving new best policy, reward=24.350! -[2023-10-10 13:05:17,783][76543] Updated weights for policy 0, policy_version 10403 (0.0011) -[2023-10-10 13:05:18,145][76543] Updated weights for policy 0, policy_version 10413 (0.0009) -[2023-10-10 13:05:18,525][76543] Updated weights for policy 0, policy_version 10423 (0.0009) -[2023-10-10 13:05:19,416][76542] Updated weights for policy 1, policy_version 10410 (0.0009) -[2023-10-10 13:05:19,794][76542] Updated weights for policy 1, policy_version 10420 (0.0008) -[2023-10-10 13:05:20,169][76542] Updated weights for policy 1, policy_version 10430 (0.0008) -[2023-10-10 13:05:21,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 21364736. Throughput: 0: 1823.7, 1: 1807.2. Samples: 5343386. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:05:21,077][75634] Avg episode reward: [(0, '23.800'), (1, '18.120')] -[2023-10-10 13:05:22,219][76543] Updated weights for policy 0, policy_version 10433 (0.0008) -[2023-10-10 13:05:22,586][76543] Updated weights for policy 0, policy_version 10443 (0.0007) -[2023-10-10 13:05:22,963][76543] Updated weights for policy 0, policy_version 10453 (0.0008) -[2023-10-10 13:05:23,324][76543] Updated weights for policy 0, policy_version 10463 (0.0008) -[2023-10-10 13:05:23,793][76542] Updated weights for policy 1, policy_version 10440 (0.0010) -[2023-10-10 13:05:24,163][76542] Updated weights for policy 1, policy_version 10450 (0.0010) -[2023-10-10 13:05:24,530][76542] Updated weights for policy 1, policy_version 10460 (0.0011) -[2023-10-10 13:05:26,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 21430272. Throughput: 0: 1826.3, 1: 1807.4. Samples: 5363940. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:05:26,077][75634] Avg episode reward: [(0, '24.370'), (1, '19.330')] -[2023-10-10 13:05:26,077][76362] Saving new best policy, reward=24.370! -[2023-10-10 13:05:27,001][76543] Updated weights for policy 0, policy_version 10473 (0.0008) -[2023-10-10 13:05:27,380][76543] Updated weights for policy 0, policy_version 10483 (0.0007) -[2023-10-10 13:05:27,737][76543] Updated weights for policy 0, policy_version 10493 (0.0010) -[2023-10-10 13:05:28,317][76542] Updated weights for policy 1, policy_version 10470 (0.0007) -[2023-10-10 13:05:28,689][76542] Updated weights for policy 1, policy_version 10480 (0.0007) -[2023-10-10 13:05:29,054][76542] Updated weights for policy 1, policy_version 10490 (0.0008) -[2023-10-10 13:05:31,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 21495808. Throughput: 0: 1829.9, 1: 1798.5. Samples: 5386582. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:05:31,077][75634] Avg episode reward: [(0, '23.670'), (1, '20.310')] -[2023-10-10 13:05:31,089][76421] Saving new best policy, reward=20.310! -[2023-10-10 13:05:31,369][76543] Updated weights for policy 0, policy_version 10503 (0.0008) -[2023-10-10 13:05:31,746][76543] Updated weights for policy 0, policy_version 10513 (0.0009) -[2023-10-10 13:05:32,118][76543] Updated weights for policy 0, policy_version 10523 (0.0008) -[2023-10-10 13:05:32,792][76542] Updated weights for policy 1, policy_version 10500 (0.0011) -[2023-10-10 13:05:33,171][76542] Updated weights for policy 1, policy_version 10510 (0.0008) -[2023-10-10 13:05:33,542][76542] Updated weights for policy 1, policy_version 10520 (0.0009) -[2023-10-10 13:05:35,603][76543] Updated weights for policy 0, policy_version 10533 (0.0008) -[2023-10-10 13:05:35,975][76543] Updated weights for policy 0, policy_version 10543 (0.0008) -[2023-10-10 13:05:36,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 21561344. Throughput: 0: 1832.5, 1: 1802.3. Samples: 5396716. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 13:05:36,077][75634] Avg episode reward: [(0, '24.500'), (1, '20.890')] -[2023-10-10 13:05:36,079][76421] Saving new best policy, reward=20.890! -[2023-10-10 13:05:36,350][76543] Updated weights for policy 0, policy_version 10553 (0.0010) -[2023-10-10 13:05:36,609][76362] Saving new best policy, reward=24.500! -[2023-10-10 13:05:37,243][76542] Updated weights for policy 1, policy_version 10530 (0.0009) -[2023-10-10 13:05:37,607][76542] Updated weights for policy 1, policy_version 10540 (0.0007) -[2023-10-10 13:05:37,972][76542] Updated weights for policy 1, policy_version 10550 (0.0008) -[2023-10-10 13:05:38,342][76542] Updated weights for policy 1, policy_version 10560 (0.0008) -[2023-10-10 13:05:40,069][76543] Updated weights for policy 0, policy_version 10563 (0.0009) -[2023-10-10 13:05:40,442][76543] Updated weights for policy 0, policy_version 10573 (0.0008) -[2023-10-10 13:05:40,822][76543] Updated weights for policy 0, policy_version 10583 (0.0008) -[2023-10-10 13:05:41,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 21626880. Throughput: 0: 1832.2, 1: 1798.9. Samples: 5419192. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 13:05:41,077][75634] Avg episode reward: [(0, '22.500'), (1, '22.310')] -[2023-10-10 13:05:41,078][76421] Saving new best policy, reward=22.310! -[2023-10-10 13:05:42,204][76542] Updated weights for policy 1, policy_version 10570 (0.0009) -[2023-10-10 13:05:42,572][76542] Updated weights for policy 1, policy_version 10580 (0.0007) -[2023-10-10 13:05:42,940][76542] Updated weights for policy 1, policy_version 10590 (0.0010) -[2023-10-10 13:05:44,489][76543] Updated weights for policy 0, policy_version 10593 (0.0009) -[2023-10-10 13:05:44,865][76543] Updated weights for policy 0, policy_version 10603 (0.0009) -[2023-10-10 13:05:45,233][76543] Updated weights for policy 0, policy_version 10613 (0.0009) -[2023-10-10 13:05:45,603][76543] Updated weights for policy 0, policy_version 10623 (0.0009) -[2023-10-10 13:05:46,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 21725184. Throughput: 0: 1819.4, 1: 1802.7. Samples: 5441200. Policy #0 lag: (min: 25.0, avg: 26.2, max: 47.0) -[2023-10-10 13:05:46,077][75634] Avg episode reward: [(0, '23.510'), (1, '21.360')] -[2023-10-10 13:05:46,456][76542] Updated weights for policy 1, policy_version 10600 (0.0009) -[2023-10-10 13:05:46,819][76542] Updated weights for policy 1, policy_version 10610 (0.0010) -[2023-10-10 13:05:47,189][76542] Updated weights for policy 1, policy_version 10620 (0.0009) -[2023-10-10 13:05:49,415][76543] Updated weights for policy 0, policy_version 10633 (0.0010) -[2023-10-10 13:05:49,787][76543] Updated weights for policy 0, policy_version 10643 (0.0010) -[2023-10-10 13:05:50,160][76543] Updated weights for policy 0, policy_version 10653 (0.0010) -[2023-10-10 13:05:50,931][76542] Updated weights for policy 1, policy_version 10630 (0.0010) -[2023-10-10 13:05:51,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 21790720. Throughput: 0: 1834.0, 1: 1803.6. Samples: 5452062. Policy #0 lag: (min: 25.0, avg: 26.2, max: 47.0) -[2023-10-10 13:05:51,076][75634] Avg episode reward: [(0, '24.240'), (1, '21.360')] -[2023-10-10 13:05:51,325][76542] Updated weights for policy 1, policy_version 10640 (0.0007) -[2023-10-10 13:05:51,693][76542] Updated weights for policy 1, policy_version 10650 (0.0008) -[2023-10-10 13:05:53,728][76543] Updated weights for policy 0, policy_version 10663 (0.0009) -[2023-10-10 13:05:54,107][76543] Updated weights for policy 0, policy_version 10673 (0.0009) -[2023-10-10 13:05:54,478][76543] Updated weights for policy 0, policy_version 10683 (0.0008) -[2023-10-10 13:05:55,189][76542] Updated weights for policy 1, policy_version 10660 (0.0009) -[2023-10-10 13:05:55,559][76542] Updated weights for policy 1, policy_version 10670 (0.0010) -[2023-10-10 13:05:55,916][76542] Updated weights for policy 1, policy_version 10680 (0.0007) -[2023-10-10 13:05:56,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 21856256. Throughput: 0: 1822.8, 1: 1813.3. Samples: 5474200. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-10 13:05:56,077][75634] Avg episode reward: [(0, '24.480'), (1, '19.820')] -[2023-10-10 13:05:58,124][76543] Updated weights for policy 0, policy_version 10693 (0.0008) -[2023-10-10 13:05:58,499][76543] Updated weights for policy 0, policy_version 10703 (0.0010) -[2023-10-10 13:05:58,883][76543] Updated weights for policy 0, policy_version 10713 (0.0009) -[2023-10-10 13:05:59,730][76542] Updated weights for policy 1, policy_version 10690 (0.0007) -[2023-10-10 13:06:00,089][76542] Updated weights for policy 1, policy_version 10700 (0.0007) -[2023-10-10 13:06:00,460][76542] Updated weights for policy 1, policy_version 10710 (0.0007) -[2023-10-10 13:06:00,823][76542] Updated weights for policy 1, policy_version 10720 (0.0007) -[2023-10-10 13:06:01,076][75634] Fps is (10 sec: 16384.0, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 21954560. Throughput: 0: 1832.6, 1: 1818.6. Samples: 5495372. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-10 13:06:01,076][75634] Avg episode reward: [(0, '24.250'), (1, '19.280')] -[2023-10-10 13:06:02,408][76543] Updated weights for policy 0, policy_version 10723 (0.0010) -[2023-10-10 13:06:02,783][76543] Updated weights for policy 0, policy_version 10733 (0.0008) -[2023-10-10 13:06:03,161][76543] Updated weights for policy 0, policy_version 10743 (0.0008) -[2023-10-10 13:06:04,323][76542] Updated weights for policy 1, policy_version 10730 (0.0011) -[2023-10-10 13:06:04,687][76542] Updated weights for policy 1, policy_version 10740 (0.0011) -[2023-10-10 13:06:05,053][76542] Updated weights for policy 1, policy_version 10750 (0.0009) -[2023-10-10 13:06:06,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 22020096. Throughput: 0: 1822.7, 1: 1818.4. Samples: 5507232. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-10 13:06:06,077][75634] Avg episode reward: [(0, '24.510'), (1, '19.270')] -[2023-10-10 13:06:06,078][76362] Saving new best policy, reward=24.510! -[2023-10-10 13:06:06,900][76543] Updated weights for policy 0, policy_version 10753 (0.0008) -[2023-10-10 13:06:07,270][76543] Updated weights for policy 0, policy_version 10763 (0.0009) -[2023-10-10 13:06:07,644][76543] Updated weights for policy 0, policy_version 10773 (0.0010) -[2023-10-10 13:06:08,001][76543] Updated weights for policy 0, policy_version 10783 (0.0010) -[2023-10-10 13:06:08,858][76542] Updated weights for policy 1, policy_version 10760 (0.0008) -[2023-10-10 13:06:09,233][76542] Updated weights for policy 1, policy_version 10770 (0.0007) -[2023-10-10 13:06:09,601][76542] Updated weights for policy 1, policy_version 10780 (0.0007) -[2023-10-10 13:06:11,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 22085632. Throughput: 0: 1837.6, 1: 1820.5. Samples: 5528556. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 13:06:11,077][75634] Avg episode reward: [(0, '24.590'), (1, '19.740')] -[2023-10-10 13:06:11,078][76362] Saving new best policy, reward=24.590! -[2023-10-10 13:06:11,765][76543] Updated weights for policy 0, policy_version 10793 (0.0008) -[2023-10-10 13:06:12,130][76543] Updated weights for policy 0, policy_version 10803 (0.0009) -[2023-10-10 13:06:12,503][76543] Updated weights for policy 0, policy_version 10813 (0.0008) -[2023-10-10 13:06:13,201][76542] Updated weights for policy 1, policy_version 10790 (0.0010) -[2023-10-10 13:06:13,570][76542] Updated weights for policy 1, policy_version 10800 (0.0008) -[2023-10-10 13:06:13,948][76542] Updated weights for policy 1, policy_version 10810 (0.0008) -[2023-10-10 13:06:16,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 22151168. Throughput: 0: 1836.9, 1: 1823.6. Samples: 5551300. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 13:06:16,076][75634] Avg episode reward: [(0, '24.040'), (1, '19.220')] -[2023-10-10 13:06:16,175][76543] Updated weights for policy 0, policy_version 10823 (0.0007) -[2023-10-10 13:06:16,551][76543] Updated weights for policy 0, policy_version 10833 (0.0008) -[2023-10-10 13:06:16,919][76543] Updated weights for policy 0, policy_version 10843 (0.0008) -[2023-10-10 13:06:17,705][76542] Updated weights for policy 1, policy_version 10820 (0.0009) -[2023-10-10 13:06:18,066][76542] Updated weights for policy 1, policy_version 10830 (0.0008) -[2023-10-10 13:06:18,435][76542] Updated weights for policy 1, policy_version 10840 (0.0007) -[2023-10-10 13:06:20,603][76543] Updated weights for policy 0, policy_version 10853 (0.0008) -[2023-10-10 13:06:20,976][76543] Updated weights for policy 0, policy_version 10863 (0.0010) -[2023-10-10 13:06:21,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 22216704. Throughput: 0: 1834.3, 1: 1825.1. Samples: 5561386. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-10 13:06:21,076][75634] Avg episode reward: [(0, '23.290'), (1, '20.150')] -[2023-10-10 13:06:21,337][76543] Updated weights for policy 0, policy_version 10873 (0.0007) -[2023-10-10 13:06:22,153][76542] Updated weights for policy 1, policy_version 10850 (0.0010) -[2023-10-10 13:06:22,515][76542] Updated weights for policy 1, policy_version 10860 (0.0009) -[2023-10-10 13:06:22,878][76542] Updated weights for policy 1, policy_version 10870 (0.0010) -[2023-10-10 13:06:23,246][76542] Updated weights for policy 1, policy_version 10880 (0.0010) -[2023-10-10 13:06:25,020][76543] Updated weights for policy 0, policy_version 10883 (0.0008) -[2023-10-10 13:06:25,392][76543] Updated weights for policy 0, policy_version 10893 (0.0008) -[2023-10-10 13:06:25,770][76543] Updated weights for policy 0, policy_version 10903 (0.0007) -[2023-10-10 13:06:26,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 22282240. Throughput: 0: 1831.8, 1: 1831.0. Samples: 5584018. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-10 13:06:26,077][75634] Avg episode reward: [(0, '23.860'), (1, '20.800')] -[2023-10-10 13:06:26,892][76542] Updated weights for policy 1, policy_version 10890 (0.0007) -[2023-10-10 13:06:27,266][76542] Updated weights for policy 1, policy_version 10900 (0.0009) -[2023-10-10 13:06:27,625][76542] Updated weights for policy 1, policy_version 10910 (0.0010) -[2023-10-10 13:06:29,566][76543] Updated weights for policy 0, policy_version 10913 (0.0010) -[2023-10-10 13:06:29,930][76543] Updated weights for policy 0, policy_version 10923 (0.0009) -[2023-10-10 13:06:30,309][76543] Updated weights for policy 0, policy_version 10933 (0.0007) -[2023-10-10 13:06:30,678][76543] Updated weights for policy 0, policy_version 10943 (0.0008) -[2023-10-10 13:06:31,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 22380544. Throughput: 0: 1832.9, 1: 1829.9. Samples: 5606026. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:06:31,077][75634] Avg episode reward: [(0, '24.130'), (1, '20.140')] -[2023-10-10 13:06:31,087][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000010944_11206656.pth... -[2023-10-10 13:06:31,122][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000009216_9437184.pth -[2023-10-10 13:06:31,288][76542] Updated weights for policy 1, policy_version 10920 (0.0008) -[2023-10-10 13:06:31,654][76542] Updated weights for policy 1, policy_version 10930 (0.0008) -[2023-10-10 13:06:32,035][76542] Updated weights for policy 1, policy_version 10940 (0.0009) -[2023-10-10 13:06:32,172][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000010944_11206656.pth... -[2023-10-10 13:06:32,201][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000009248_9469952.pth -[2023-10-10 13:06:34,209][76543] Updated weights for policy 0, policy_version 10953 (0.0010) -[2023-10-10 13:06:34,575][76543] Updated weights for policy 0, policy_version 10963 (0.0008) -[2023-10-10 13:06:34,949][76543] Updated weights for policy 0, policy_version 10973 (0.0009) -[2023-10-10 13:06:35,664][76542] Updated weights for policy 1, policy_version 10950 (0.0008) -[2023-10-10 13:06:36,055][76542] Updated weights for policy 1, policy_version 10960 (0.0008) -[2023-10-10 13:06:36,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 22446080. Throughput: 0: 1832.0, 1: 1836.4. Samples: 5617140. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:06:36,077][75634] Avg episode reward: [(0, '24.180'), (1, '19.290')] -[2023-10-10 13:06:36,422][76542] Updated weights for policy 1, policy_version 10970 (0.0010) -[2023-10-10 13:06:38,445][76543] Updated weights for policy 0, policy_version 10983 (0.0008) -[2023-10-10 13:06:38,820][76543] Updated weights for policy 0, policy_version 10993 (0.0010) -[2023-10-10 13:06:39,193][76543] Updated weights for policy 0, policy_version 11003 (0.0011) -[2023-10-10 13:06:39,950][76542] Updated weights for policy 1, policy_version 10980 (0.0009) -[2023-10-10 13:06:40,316][76542] Updated weights for policy 1, policy_version 10990 (0.0008) -[2023-10-10 13:06:40,687][76542] Updated weights for policy 1, policy_version 11000 (0.0007) -[2023-10-10 13:06:41,076][75634] Fps is (10 sec: 16384.3, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 22544384. Throughput: 0: 1824.1, 1: 1829.3. Samples: 5638602. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:06:41,076][75634] Avg episode reward: [(0, '23.350'), (1, '20.360')] -[2023-10-10 13:06:42,859][76543] Updated weights for policy 0, policy_version 11013 (0.0010) -[2023-10-10 13:06:43,231][76543] Updated weights for policy 0, policy_version 11023 (0.0007) -[2023-10-10 13:06:43,605][76543] Updated weights for policy 0, policy_version 11033 (0.0009) -[2023-10-10 13:06:44,399][76542] Updated weights for policy 1, policy_version 11010 (0.0008) -[2023-10-10 13:06:44,764][76542] Updated weights for policy 1, policy_version 11020 (0.0009) -[2023-10-10 13:06:45,131][76542] Updated weights for policy 1, policy_version 11030 (0.0008) -[2023-10-10 13:06:45,505][76542] Updated weights for policy 1, policy_version 11040 (0.0008) -[2023-10-10 13:06:46,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 22609920. Throughput: 0: 1834.5, 1: 1822.2. Samples: 5659926. Policy #0 lag: (min: 26.0, avg: 26.7, max: 42.0) -[2023-10-10 13:06:46,077][75634] Avg episode reward: [(0, '23.430'), (1, '20.200')] -[2023-10-10 13:06:47,266][76543] Updated weights for policy 0, policy_version 11043 (0.0008) -[2023-10-10 13:06:47,649][76543] Updated weights for policy 0, policy_version 11053 (0.0007) -[2023-10-10 13:06:48,014][76543] Updated weights for policy 0, policy_version 11063 (0.0008) -[2023-10-10 13:06:49,190][76542] Updated weights for policy 1, policy_version 11050 (0.0007) -[2023-10-10 13:06:49,565][76542] Updated weights for policy 1, policy_version 11060 (0.0010) -[2023-10-10 13:06:49,927][76542] Updated weights for policy 1, policy_version 11070 (0.0010) -[2023-10-10 13:06:51,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 22675456. Throughput: 0: 1826.8, 1: 1823.7. Samples: 5671504. Policy #0 lag: (min: 26.0, avg: 26.7, max: 42.0) -[2023-10-10 13:06:51,077][75634] Avg episode reward: [(0, '22.010'), (1, '21.000')] -[2023-10-10 13:06:51,606][76543] Updated weights for policy 0, policy_version 11073 (0.0008) -[2023-10-10 13:06:51,971][76543] Updated weights for policy 0, policy_version 11083 (0.0010) -[2023-10-10 13:06:52,354][76543] Updated weights for policy 0, policy_version 11093 (0.0010) -[2023-10-10 13:06:52,737][76543] Updated weights for policy 0, policy_version 11103 (0.0007) -[2023-10-10 13:06:53,679][76542] Updated weights for policy 1, policy_version 11080 (0.0007) -[2023-10-10 13:06:54,051][76542] Updated weights for policy 1, policy_version 11090 (0.0008) -[2023-10-10 13:06:54,422][76542] Updated weights for policy 1, policy_version 11100 (0.0008) -[2023-10-10 13:06:56,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 22740992. Throughput: 0: 1828.3, 1: 1821.3. Samples: 5692786. Policy #0 lag: (min: 26.0, avg: 26.7, max: 42.0) -[2023-10-10 13:06:56,077][75634] Avg episode reward: [(0, '20.970'), (1, '21.370')] -[2023-10-10 13:06:56,405][76543] Updated weights for policy 0, policy_version 11113 (0.0011) -[2023-10-10 13:06:56,780][76543] Updated weights for policy 0, policy_version 11123 (0.0008) -[2023-10-10 13:06:57,150][76543] Updated weights for policy 0, policy_version 11133 (0.0010) -[2023-10-10 13:06:58,050][76542] Updated weights for policy 1, policy_version 11110 (0.0008) -[2023-10-10 13:06:58,422][76542] Updated weights for policy 1, policy_version 11120 (0.0010) -[2023-10-10 13:06:58,787][76542] Updated weights for policy 1, policy_version 11130 (0.0007) -[2023-10-10 13:07:00,812][76543] Updated weights for policy 0, policy_version 11143 (0.0010) -[2023-10-10 13:07:01,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 22806528. Throughput: 0: 1831.4, 1: 1818.7. Samples: 5715556. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:07:01,076][75634] Avg episode reward: [(0, '20.940'), (1, '21.960')] -[2023-10-10 13:07:01,194][76543] Updated weights for policy 0, policy_version 11153 (0.0010) -[2023-10-10 13:07:01,579][76543] Updated weights for policy 0, policy_version 11163 (0.0008) -[2023-10-10 13:07:02,566][76542] Updated weights for policy 1, policy_version 11140 (0.0008) -[2023-10-10 13:07:02,935][76542] Updated weights for policy 1, policy_version 11150 (0.0009) -[2023-10-10 13:07:03,302][76542] Updated weights for policy 1, policy_version 11160 (0.0008) -[2023-10-10 13:07:05,203][76543] Updated weights for policy 0, policy_version 11173 (0.0007) -[2023-10-10 13:07:05,595][76543] Updated weights for policy 0, policy_version 11183 (0.0009) -[2023-10-10 13:07:05,959][76543] Updated weights for policy 0, policy_version 11193 (0.0007) -[2023-10-10 13:07:06,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 22872064. Throughput: 0: 1838.6, 1: 1810.8. Samples: 5725610. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:07:06,077][75634] Avg episode reward: [(0, '21.210'), (1, '21.520')] -[2023-10-10 13:07:06,952][76542] Updated weights for policy 1, policy_version 11170 (0.0008) -[2023-10-10 13:07:07,320][76542] Updated weights for policy 1, policy_version 11180 (0.0009) -[2023-10-10 13:07:07,695][76542] Updated weights for policy 1, policy_version 11190 (0.0010) -[2023-10-10 13:07:08,057][76542] Updated weights for policy 1, policy_version 11200 (0.0008) -[2023-10-10 13:07:09,714][76543] Updated weights for policy 0, policy_version 11203 (0.0008) -[2023-10-10 13:07:10,084][76543] Updated weights for policy 0, policy_version 11213 (0.0010) -[2023-10-10 13:07:10,464][76543] Updated weights for policy 0, policy_version 11223 (0.0008) -[2023-10-10 13:07:11,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 22970368. Throughput: 0: 1834.5, 1: 1821.8. Samples: 5748550. Policy #0 lag: (min: 17.0, avg: 21.9, max: 49.0) -[2023-10-10 13:07:11,077][75634] Avg episode reward: [(0, '21.170'), (1, '20.660')] -[2023-10-10 13:07:11,641][76542] Updated weights for policy 1, policy_version 11210 (0.0009) -[2023-10-10 13:07:12,013][76542] Updated weights for policy 1, policy_version 11220 (0.0010) -[2023-10-10 13:07:12,381][76542] Updated weights for policy 1, policy_version 11230 (0.0007) -[2023-10-10 13:07:14,242][76543] Updated weights for policy 0, policy_version 11233 (0.0008) -[2023-10-10 13:07:14,626][76543] Updated weights for policy 0, policy_version 11243 (0.0011) -[2023-10-10 13:07:14,991][76543] Updated weights for policy 0, policy_version 11253 (0.0009) -[2023-10-10 13:07:15,371][76543] Updated weights for policy 0, policy_version 11263 (0.0008) -[2023-10-10 13:07:16,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 23035904. Throughput: 0: 1825.4, 1: 1817.9. Samples: 5769976. Policy #0 lag: (min: 17.0, avg: 21.9, max: 49.0) -[2023-10-10 13:07:16,076][75634] Avg episode reward: [(0, '21.800'), (1, '20.850')] -[2023-10-10 13:07:16,111][76542] Updated weights for policy 1, policy_version 11240 (0.0007) -[2023-10-10 13:07:16,478][76542] Updated weights for policy 1, policy_version 11250 (0.0007) -[2023-10-10 13:07:16,843][76542] Updated weights for policy 1, policy_version 11260 (0.0007) -[2023-10-10 13:07:19,091][76543] Updated weights for policy 0, policy_version 11273 (0.0009) -[2023-10-10 13:07:19,451][76543] Updated weights for policy 0, policy_version 11283 (0.0010) -[2023-10-10 13:07:19,826][76543] Updated weights for policy 0, policy_version 11293 (0.0009) -[2023-10-10 13:07:20,711][76542] Updated weights for policy 1, policy_version 11270 (0.0009) -[2023-10-10 13:07:21,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 23101440. Throughput: 0: 1829.8, 1: 1813.9. Samples: 5781104. Policy #0 lag: (min: 17.0, avg: 21.9, max: 49.0) -[2023-10-10 13:07:21,076][75634] Avg episode reward: [(0, '22.820'), (1, '20.440')] -[2023-10-10 13:07:21,095][76542] Updated weights for policy 1, policy_version 11280 (0.0010) -[2023-10-10 13:07:21,456][76542] Updated weights for policy 1, policy_version 11290 (0.0011) -[2023-10-10 13:07:23,354][76543] Updated weights for policy 0, policy_version 11303 (0.0010) -[2023-10-10 13:07:23,726][76543] Updated weights for policy 0, policy_version 11313 (0.0007) -[2023-10-10 13:07:24,105][76543] Updated weights for policy 0, policy_version 11323 (0.0008) -[2023-10-10 13:07:25,135][76542] Updated weights for policy 1, policy_version 11300 (0.0009) -[2023-10-10 13:07:25,506][76542] Updated weights for policy 1, policy_version 11310 (0.0007) -[2023-10-10 13:07:25,872][76542] Updated weights for policy 1, policy_version 11320 (0.0007) -[2023-10-10 13:07:26,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 23166976. Throughput: 0: 1824.7, 1: 1812.2. Samples: 5802264. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-10 13:07:26,077][75634] Avg episode reward: [(0, '24.800'), (1, '18.080')] -[2023-10-10 13:07:26,078][76362] Saving new best policy, reward=24.800! -[2023-10-10 13:07:27,663][76543] Updated weights for policy 0, policy_version 11333 (0.0008) -[2023-10-10 13:07:28,037][76543] Updated weights for policy 0, policy_version 11343 (0.0009) -[2023-10-10 13:07:28,408][76543] Updated weights for policy 0, policy_version 11353 (0.0010) -[2023-10-10 13:07:29,417][76542] Updated weights for policy 1, policy_version 11330 (0.0008) -[2023-10-10 13:07:29,792][76542] Updated weights for policy 1, policy_version 11340 (0.0009) -[2023-10-10 13:07:30,158][76542] Updated weights for policy 1, policy_version 11350 (0.0008) -[2023-10-10 13:07:30,523][76542] Updated weights for policy 1, policy_version 11360 (0.0011) -[2023-10-10 13:07:31,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 23265280. Throughput: 0: 1822.4, 1: 1813.2. Samples: 5823530. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-10 13:07:31,077][75634] Avg episode reward: [(0, '24.450'), (1, '19.710')] -[2023-10-10 13:07:32,185][76543] Updated weights for policy 0, policy_version 11363 (0.0009) -[2023-10-10 13:07:32,551][76543] Updated weights for policy 0, policy_version 11373 (0.0012) -[2023-10-10 13:07:32,926][76543] Updated weights for policy 0, policy_version 11383 (0.0010) -[2023-10-10 13:07:34,338][76542] Updated weights for policy 1, policy_version 11370 (0.0008) -[2023-10-10 13:07:34,703][76542] Updated weights for policy 1, policy_version 11380 (0.0008) -[2023-10-10 13:07:35,069][76542] Updated weights for policy 1, policy_version 11390 (0.0009) -[2023-10-10 13:07:36,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 23330816. Throughput: 0: 1818.4, 1: 1814.1. Samples: 5834962. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-10 13:07:36,076][75634] Avg episode reward: [(0, '24.250'), (1, '19.970')] -[2023-10-10 13:07:36,473][76543] Updated weights for policy 0, policy_version 11393 (0.0009) -[2023-10-10 13:07:36,836][76543] Updated weights for policy 0, policy_version 11403 (0.0009) -[2023-10-10 13:07:37,212][76543] Updated weights for policy 0, policy_version 11413 (0.0008) -[2023-10-10 13:07:37,583][76543] Updated weights for policy 0, policy_version 11423 (0.0008) -[2023-10-10 13:07:38,797][76542] Updated weights for policy 1, policy_version 11400 (0.0008) -[2023-10-10 13:07:39,169][76542] Updated weights for policy 1, policy_version 11410 (0.0007) -[2023-10-10 13:07:39,548][76542] Updated weights for policy 1, policy_version 11420 (0.0009) -[2023-10-10 13:07:41,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 23396352. Throughput: 0: 1820.4, 1: 1818.0. Samples: 5856516. Policy #0 lag: (min: 24.0, avg: 48.8, max: 56.0) -[2023-10-10 13:07:41,076][75634] Avg episode reward: [(0, '23.450'), (1, '19.810')] -[2023-10-10 13:07:41,385][76543] Updated weights for policy 0, policy_version 11433 (0.0009) -[2023-10-10 13:07:41,765][76543] Updated weights for policy 0, policy_version 11443 (0.0010) -[2023-10-10 13:07:42,140][76543] Updated weights for policy 0, policy_version 11453 (0.0008) -[2023-10-10 13:07:43,349][76542] Updated weights for policy 1, policy_version 11430 (0.0008) -[2023-10-10 13:07:43,719][76542] Updated weights for policy 1, policy_version 11440 (0.0008) -[2023-10-10 13:07:44,071][76542] Updated weights for policy 1, policy_version 11450 (0.0007) -[2023-10-10 13:07:45,935][76543] Updated weights for policy 0, policy_version 11463 (0.0010) -[2023-10-10 13:07:46,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 23461888. Throughput: 0: 1813.5, 1: 1824.0. Samples: 5879248. Policy #0 lag: (min: 24.0, avg: 48.8, max: 56.0) -[2023-10-10 13:07:46,077][75634] Avg episode reward: [(0, '22.760'), (1, '21.900')] -[2023-10-10 13:07:46,305][76543] Updated weights for policy 0, policy_version 11473 (0.0010) -[2023-10-10 13:07:46,674][76543] Updated weights for policy 0, policy_version 11483 (0.0011) -[2023-10-10 13:07:47,605][76542] Updated weights for policy 1, policy_version 11460 (0.0008) -[2023-10-10 13:07:47,976][76542] Updated weights for policy 1, policy_version 11470 (0.0008) -[2023-10-10 13:07:48,335][76542] Updated weights for policy 1, policy_version 11480 (0.0007) -[2023-10-10 13:07:50,306][76543] Updated weights for policy 0, policy_version 11493 (0.0009) -[2023-10-10 13:07:50,682][76543] Updated weights for policy 0, policy_version 11503 (0.0008) -[2023-10-10 13:07:51,059][76543] Updated weights for policy 0, policy_version 11513 (0.0007) -[2023-10-10 13:07:51,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 23527424. Throughput: 0: 1807.4, 1: 1828.6. Samples: 5889230. Policy #0 lag: (min: 24.0, avg: 48.8, max: 56.0) -[2023-10-10 13:07:51,076][75634] Avg episode reward: [(0, '23.420'), (1, '20.650')] -[2023-10-10 13:07:51,972][76542] Updated weights for policy 1, policy_version 11490 (0.0009) -[2023-10-10 13:07:52,344][76542] Updated weights for policy 1, policy_version 11500 (0.0007) -[2023-10-10 13:07:52,720][76542] Updated weights for policy 1, policy_version 11510 (0.0008) -[2023-10-10 13:07:53,080][76542] Updated weights for policy 1, policy_version 11520 (0.0010) -[2023-10-10 13:07:54,649][76543] Updated weights for policy 0, policy_version 11523 (0.0007) -[2023-10-10 13:07:55,025][76543] Updated weights for policy 0, policy_version 11533 (0.0008) -[2023-10-10 13:07:55,395][76543] Updated weights for policy 0, policy_version 11543 (0.0008) -[2023-10-10 13:07:56,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 23625728. Throughput: 0: 1819.2, 1: 1816.6. Samples: 5912158. Policy #0 lag: (min: 4.0, avg: 9.4, max: 36.0) -[2023-10-10 13:07:56,076][75634] Avg episode reward: [(0, '23.550'), (1, '20.460')] -[2023-10-10 13:07:56,934][76542] Updated weights for policy 1, policy_version 11530 (0.0011) -[2023-10-10 13:07:57,303][76542] Updated weights for policy 1, policy_version 11540 (0.0008) -[2023-10-10 13:07:57,677][76542] Updated weights for policy 1, policy_version 11550 (0.0007) -[2023-10-10 13:07:59,041][76543] Updated weights for policy 0, policy_version 11553 (0.0008) -[2023-10-10 13:07:59,412][76543] Updated weights for policy 0, policy_version 11563 (0.0009) -[2023-10-10 13:07:59,785][76543] Updated weights for policy 0, policy_version 11573 (0.0008) -[2023-10-10 13:08:00,160][76543] Updated weights for policy 0, policy_version 11583 (0.0009) -[2023-10-10 13:08:01,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 23691264. Throughput: 0: 1819.5, 1: 1814.5. Samples: 5933506. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:08:01,077][75634] Avg episode reward: [(0, '23.460'), (1, '19.780')] -[2023-10-10 13:08:01,458][76542] Updated weights for policy 1, policy_version 11560 (0.0009) -[2023-10-10 13:08:01,828][76542] Updated weights for policy 1, policy_version 11570 (0.0007) -[2023-10-10 13:08:02,200][76542] Updated weights for policy 1, policy_version 11580 (0.0008) -[2023-10-10 13:08:04,065][76543] Updated weights for policy 0, policy_version 11593 (0.0008) -[2023-10-10 13:08:04,438][76543] Updated weights for policy 0, policy_version 11603 (0.0008) -[2023-10-10 13:08:04,822][76543] Updated weights for policy 0, policy_version 11613 (0.0007) -[2023-10-10 13:08:06,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 23756800. Throughput: 0: 1823.0, 1: 1813.6. Samples: 5944752. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:08:06,077][75634] Avg episode reward: [(0, '24.200'), (1, '19.600')] -[2023-10-10 13:08:06,115][76542] Updated weights for policy 1, policy_version 11590 (0.0010) -[2023-10-10 13:08:06,510][76542] Updated weights for policy 1, policy_version 11600 (0.0011) -[2023-10-10 13:08:06,878][76542] Updated weights for policy 1, policy_version 11610 (0.0010) -[2023-10-10 13:08:08,377][76543] Updated weights for policy 0, policy_version 11623 (0.0008) -[2023-10-10 13:08:08,760][76543] Updated weights for policy 0, policy_version 11633 (0.0009) -[2023-10-10 13:08:09,136][76543] Updated weights for policy 0, policy_version 11643 (0.0009) -[2023-10-10 13:08:10,432][76542] Updated weights for policy 1, policy_version 11620 (0.0008) -[2023-10-10 13:08:10,792][76542] Updated weights for policy 1, policy_version 11630 (0.0007) -[2023-10-10 13:08:11,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 23822336. Throughput: 0: 1822.4, 1: 1815.8. Samples: 5965986. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:08:11,077][75634] Avg episode reward: [(0, '23.680'), (1, '18.620')] -[2023-10-10 13:08:11,165][76542] Updated weights for policy 1, policy_version 11640 (0.0008) -[2023-10-10 13:08:12,686][76543] Updated weights for policy 0, policy_version 11653 (0.0008) -[2023-10-10 13:08:13,049][76543] Updated weights for policy 0, policy_version 11663 (0.0007) -[2023-10-10 13:08:13,433][76543] Updated weights for policy 0, policy_version 11673 (0.0011) -[2023-10-10 13:08:14,696][76542] Updated weights for policy 1, policy_version 11650 (0.0008) -[2023-10-10 13:08:15,072][76542] Updated weights for policy 1, policy_version 11660 (0.0008) -[2023-10-10 13:08:15,442][76542] Updated weights for policy 1, policy_version 11670 (0.0009) -[2023-10-10 13:08:15,811][76542] Updated weights for policy 1, policy_version 11680 (0.0009) -[2023-10-10 13:08:16,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 23920640. Throughput: 0: 1822.8, 1: 1824.7. Samples: 5987668. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:08:16,077][75634] Avg episode reward: [(0, '24.170'), (1, '19.140')] -[2023-10-10 13:08:17,124][76543] Updated weights for policy 0, policy_version 11683 (0.0008) -[2023-10-10 13:08:17,491][76543] Updated weights for policy 0, policy_version 11693 (0.0011) -[2023-10-10 13:08:17,858][76543] Updated weights for policy 0, policy_version 11703 (0.0011) -[2023-10-10 13:08:19,371][76542] Updated weights for policy 1, policy_version 11690 (0.0011) -[2023-10-10 13:08:19,747][76542] Updated weights for policy 1, policy_version 11700 (0.0012) -[2023-10-10 13:08:20,098][76542] Updated weights for policy 1, policy_version 11710 (0.0009) -[2023-10-10 13:08:21,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 23986176. Throughput: 0: 1820.3, 1: 1825.3. Samples: 5999014. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:08:21,077][75634] Avg episode reward: [(0, '24.090'), (1, '19.580')] -[2023-10-10 13:08:21,676][76543] Updated weights for policy 0, policy_version 11713 (0.0009) -[2023-10-10 13:08:22,042][76543] Updated weights for policy 0, policy_version 11723 (0.0009) -[2023-10-10 13:08:22,421][76543] Updated weights for policy 0, policy_version 11733 (0.0008) -[2023-10-10 13:08:22,790][76543] Updated weights for policy 0, policy_version 11743 (0.0010) -[2023-10-10 13:08:23,654][76542] Updated weights for policy 1, policy_version 11720 (0.0008) -[2023-10-10 13:08:24,021][76542] Updated weights for policy 1, policy_version 11730 (0.0008) -[2023-10-10 13:08:24,395][76542] Updated weights for policy 1, policy_version 11740 (0.0009) -[2023-10-10 13:08:26,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 24051712. Throughput: 0: 1820.3, 1: 1821.4. Samples: 6020392. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:08:26,077][75634] Avg episode reward: [(0, '24.160'), (1, '20.850')] -[2023-10-10 13:08:26,607][76543] Updated weights for policy 0, policy_version 11753 (0.0011) -[2023-10-10 13:08:26,980][76543] Updated weights for policy 0, policy_version 11763 (0.0008) -[2023-10-10 13:08:27,353][76543] Updated weights for policy 0, policy_version 11773 (0.0008) -[2023-10-10 13:08:28,119][76542] Updated weights for policy 1, policy_version 11750 (0.0008) -[2023-10-10 13:08:28,494][76542] Updated weights for policy 1, policy_version 11760 (0.0009) -[2023-10-10 13:08:28,867][76542] Updated weights for policy 1, policy_version 11770 (0.0008) -[2023-10-10 13:08:31,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 24117248. Throughput: 0: 1821.7, 1: 1820.2. Samples: 6043134. Policy #0 lag: (min: 9.0, avg: 23.9, max: 41.0) -[2023-10-10 13:08:31,077][75634] Avg episode reward: [(0, '24.080'), (1, '21.590')] -[2023-10-10 13:08:31,093][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000011776_12058624.pth... -[2023-10-10 13:08:31,126][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000010080_10321920.pth -[2023-10-10 13:08:31,133][76543] Updated weights for policy 0, policy_version 11783 (0.0010) -[2023-10-10 13:08:31,506][76543] Updated weights for policy 0, policy_version 11793 (0.0007) -[2023-10-10 13:08:31,865][76543] Updated weights for policy 0, policy_version 11803 (0.0009) -[2023-10-10 13:08:32,053][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000011808_12091392.pth... -[2023-10-10 13:08:32,082][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000010080_10321920.pth -[2023-10-10 13:08:32,559][76542] Updated weights for policy 1, policy_version 11780 (0.0009) -[2023-10-10 13:08:32,923][76542] Updated weights for policy 1, policy_version 11790 (0.0010) -[2023-10-10 13:08:33,291][76542] Updated weights for policy 1, policy_version 11800 (0.0009) -[2023-10-10 13:08:35,403][76543] Updated weights for policy 0, policy_version 11813 (0.0010) -[2023-10-10 13:08:35,776][76543] Updated weights for policy 0, policy_version 11823 (0.0007) -[2023-10-10 13:08:36,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 24182784. Throughput: 0: 1822.2, 1: 1815.3. Samples: 6052916. Policy #0 lag: (min: 9.0, avg: 23.9, max: 41.0) -[2023-10-10 13:08:36,077][75634] Avg episode reward: [(0, '24.250'), (1, '21.770')] -[2023-10-10 13:08:36,155][76543] Updated weights for policy 0, policy_version 11833 (0.0007) -[2023-10-10 13:08:37,107][76542] Updated weights for policy 1, policy_version 11810 (0.0011) -[2023-10-10 13:08:37,467][76542] Updated weights for policy 1, policy_version 11820 (0.0008) -[2023-10-10 13:08:37,845][76542] Updated weights for policy 1, policy_version 11830 (0.0008) -[2023-10-10 13:08:38,202][76542] Updated weights for policy 1, policy_version 11840 (0.0010) -[2023-10-10 13:08:39,553][76543] Updated weights for policy 0, policy_version 11843 (0.0010) -[2023-10-10 13:08:39,916][76543] Updated weights for policy 0, policy_version 11853 (0.0009) -[2023-10-10 13:08:40,286][76543] Updated weights for policy 0, policy_version 11863 (0.0009) -[2023-10-10 13:08:41,076][75634] Fps is (10 sec: 16384.6, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 24281088. Throughput: 0: 1819.1, 1: 1816.4. Samples: 6075754. Policy #0 lag: (min: 26.0, avg: 41.9, max: 58.0) -[2023-10-10 13:08:41,076][75634] Avg episode reward: [(0, '21.630'), (1, '20.010')] -[2023-10-10 13:08:41,925][76542] Updated weights for policy 1, policy_version 11850 (0.0007) -[2023-10-10 13:08:42,295][76542] Updated weights for policy 1, policy_version 11860 (0.0008) -[2023-10-10 13:08:42,668][76542] Updated weights for policy 1, policy_version 11870 (0.0008) -[2023-10-10 13:08:44,097][76543] Updated weights for policy 0, policy_version 11873 (0.0011) -[2023-10-10 13:08:44,468][76543] Updated weights for policy 0, policy_version 11883 (0.0008) -[2023-10-10 13:08:44,840][76543] Updated weights for policy 0, policy_version 11893 (0.0009) -[2023-10-10 13:08:45,215][76543] Updated weights for policy 0, policy_version 11903 (0.0009) -[2023-10-10 13:08:46,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 24346624. Throughput: 0: 1817.2, 1: 1817.7. Samples: 6097076. Policy #0 lag: (min: 26.0, avg: 41.9, max: 58.0) -[2023-10-10 13:08:46,077][75634] Avg episode reward: [(0, '22.440'), (1, '19.290')] -[2023-10-10 13:08:46,363][76542] Updated weights for policy 1, policy_version 11880 (0.0008) -[2023-10-10 13:08:46,720][76542] Updated weights for policy 1, policy_version 11890 (0.0007) -[2023-10-10 13:08:47,092][76542] Updated weights for policy 1, policy_version 11900 (0.0007) -[2023-10-10 13:08:49,019][76543] Updated weights for policy 0, policy_version 11913 (0.0010) -[2023-10-10 13:08:49,384][76543] Updated weights for policy 0, policy_version 11923 (0.0009) -[2023-10-10 13:08:49,752][76543] Updated weights for policy 0, policy_version 11933 (0.0009) -[2023-10-10 13:08:50,926][76542] Updated weights for policy 1, policy_version 11910 (0.0008) -[2023-10-10 13:08:51,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 24412160. Throughput: 0: 1818.9, 1: 1816.7. Samples: 6108352. Policy #0 lag: (min: 26.0, avg: 41.9, max: 58.0) -[2023-10-10 13:08:51,077][75634] Avg episode reward: [(0, '22.560'), (1, '18.870')] -[2023-10-10 13:08:51,318][76542] Updated weights for policy 1, policy_version 11920 (0.0007) -[2023-10-10 13:08:51,687][76542] Updated weights for policy 1, policy_version 11930 (0.0008) -[2023-10-10 13:08:53,459][76543] Updated weights for policy 0, policy_version 11943 (0.0007) -[2023-10-10 13:08:53,838][76543] Updated weights for policy 0, policy_version 11953 (0.0010) -[2023-10-10 13:08:54,209][76543] Updated weights for policy 0, policy_version 11963 (0.0009) -[2023-10-10 13:08:55,374][76542] Updated weights for policy 1, policy_version 11940 (0.0007) -[2023-10-10 13:08:55,744][76542] Updated weights for policy 1, policy_version 11950 (0.0008) -[2023-10-10 13:08:56,076][75634] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 24477696. Throughput: 0: 1823.4, 1: 1814.9. Samples: 6129706. Policy #0 lag: (min: 27.0, avg: 34.8, max: 59.0) -[2023-10-10 13:08:56,076][75634] Avg episode reward: [(0, '22.040'), (1, '17.840')] -[2023-10-10 13:08:56,105][76542] Updated weights for policy 1, policy_version 11960 (0.0008) -[2023-10-10 13:08:57,782][76543] Updated weights for policy 0, policy_version 11973 (0.0009) -[2023-10-10 13:08:58,144][76543] Updated weights for policy 0, policy_version 11983 (0.0009) -[2023-10-10 13:08:58,508][76543] Updated weights for policy 0, policy_version 11993 (0.0010) -[2023-10-10 13:08:59,904][76542] Updated weights for policy 1, policy_version 11970 (0.0010) -[2023-10-10 13:09:00,272][76542] Updated weights for policy 1, policy_version 11980 (0.0008) -[2023-10-10 13:09:00,639][76542] Updated weights for policy 1, policy_version 11990 (0.0010) -[2023-10-10 13:09:00,999][76542] Updated weights for policy 1, policy_version 12000 (0.0009) -[2023-10-10 13:09:01,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 24576000. Throughput: 0: 1821.6, 1: 1816.7. Samples: 6151390. Policy #0 lag: (min: 27.0, avg: 34.8, max: 59.0) -[2023-10-10 13:09:01,077][75634] Avg episode reward: [(0, '21.690'), (1, '19.490')] -[2023-10-10 13:09:02,243][76543] Updated weights for policy 0, policy_version 12003 (0.0008) -[2023-10-10 13:09:02,619][76543] Updated weights for policy 0, policy_version 12013 (0.0009) -[2023-10-10 13:09:02,993][76543] Updated weights for policy 0, policy_version 12023 (0.0010) -[2023-10-10 13:09:04,572][76542] Updated weights for policy 1, policy_version 12010 (0.0009) -[2023-10-10 13:09:04,942][76542] Updated weights for policy 1, policy_version 12020 (0.0008) -[2023-10-10 13:09:05,307][76542] Updated weights for policy 1, policy_version 12030 (0.0008) -[2023-10-10 13:09:06,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 24641536. Throughput: 0: 1827.0, 1: 1807.9. Samples: 6162584. Policy #0 lag: (min: 27.0, avg: 34.8, max: 59.0) -[2023-10-10 13:09:06,077][75634] Avg episode reward: [(0, '21.600'), (1, '20.220')] -[2023-10-10 13:09:06,705][76543] Updated weights for policy 0, policy_version 12033 (0.0007) -[2023-10-10 13:09:07,082][76543] Updated weights for policy 0, policy_version 12043 (0.0009) -[2023-10-10 13:09:07,450][76543] Updated weights for policy 0, policy_version 12053 (0.0010) -[2023-10-10 13:09:07,820][76543] Updated weights for policy 0, policy_version 12063 (0.0009) -[2023-10-10 13:09:09,015][76542] Updated weights for policy 1, policy_version 12040 (0.0009) -[2023-10-10 13:09:09,388][76542] Updated weights for policy 1, policy_version 12050 (0.0011) -[2023-10-10 13:09:09,762][76542] Updated weights for policy 1, policy_version 12060 (0.0010) -[2023-10-10 13:09:11,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 24707072. Throughput: 0: 1823.7, 1: 1809.7. Samples: 6183896. Policy #0 lag: (min: 13.0, avg: 21.0, max: 45.0) -[2023-10-10 13:09:11,077][75634] Avg episode reward: [(0, '22.090'), (1, '20.560')] -[2023-10-10 13:09:11,429][76543] Updated weights for policy 0, policy_version 12073 (0.0007) -[2023-10-10 13:09:11,808][76543] Updated weights for policy 0, policy_version 12083 (0.0008) -[2023-10-10 13:09:12,186][76543] Updated weights for policy 0, policy_version 12093 (0.0010) -[2023-10-10 13:09:13,492][76542] Updated weights for policy 1, policy_version 12070 (0.0007) -[2023-10-10 13:09:13,861][76542] Updated weights for policy 1, policy_version 12080 (0.0008) -[2023-10-10 13:09:14,222][76542] Updated weights for policy 1, policy_version 12090 (0.0007) -[2023-10-10 13:09:15,771][76543] Updated weights for policy 0, policy_version 12103 (0.0008) -[2023-10-10 13:09:16,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 24772608. Throughput: 0: 1832.0, 1: 1811.1. Samples: 6207072. Policy #0 lag: (min: 13.0, avg: 21.0, max: 45.0) -[2023-10-10 13:09:16,076][75634] Avg episode reward: [(0, '20.290'), (1, '20.590')] -[2023-10-10 13:09:16,140][76543] Updated weights for policy 0, policy_version 12113 (0.0007) -[2023-10-10 13:09:16,513][76543] Updated weights for policy 0, policy_version 12123 (0.0007) -[2023-10-10 13:09:17,790][76542] Updated weights for policy 1, policy_version 12100 (0.0009) -[2023-10-10 13:09:18,157][76542] Updated weights for policy 1, policy_version 12110 (0.0009) -[2023-10-10 13:09:18,527][76542] Updated weights for policy 1, policy_version 12120 (0.0007) -[2023-10-10 13:09:20,174][76543] Updated weights for policy 0, policy_version 12133 (0.0009) -[2023-10-10 13:09:20,545][76543] Updated weights for policy 0, policy_version 12143 (0.0007) -[2023-10-10 13:09:20,916][76543] Updated weights for policy 0, policy_version 12153 (0.0008) -[2023-10-10 13:09:21,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 24838144. Throughput: 0: 1832.0, 1: 1818.2. Samples: 6217174. Policy #0 lag: (min: 13.0, avg: 21.0, max: 45.0) -[2023-10-10 13:09:21,077][75634] Avg episode reward: [(0, '20.020'), (1, '21.490')] -[2023-10-10 13:09:22,070][76542] Updated weights for policy 1, policy_version 12130 (0.0007) -[2023-10-10 13:09:22,440][76542] Updated weights for policy 1, policy_version 12140 (0.0007) -[2023-10-10 13:09:22,805][76542] Updated weights for policy 1, policy_version 12150 (0.0009) -[2023-10-10 13:09:23,176][76542] Updated weights for policy 1, policy_version 12160 (0.0011) -[2023-10-10 13:09:24,538][76543] Updated weights for policy 0, policy_version 12163 (0.0010) -[2023-10-10 13:09:24,913][76543] Updated weights for policy 0, policy_version 12173 (0.0008) -[2023-10-10 13:09:25,284][76543] Updated weights for policy 0, policy_version 12183 (0.0008) -[2023-10-10 13:09:26,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 24936448. Throughput: 0: 1826.4, 1: 1823.9. Samples: 6240016. Policy #0 lag: (min: 22.0, avg: 33.8, max: 54.0) -[2023-10-10 13:09:26,077][75634] Avg episode reward: [(0, '21.020'), (1, '20.290')] -[2023-10-10 13:09:26,701][76542] Updated weights for policy 1, policy_version 12170 (0.0010) -[2023-10-10 13:09:27,077][76542] Updated weights for policy 1, policy_version 12180 (0.0010) -[2023-10-10 13:09:27,438][76542] Updated weights for policy 1, policy_version 12190 (0.0007) -[2023-10-10 13:09:28,948][76543] Updated weights for policy 0, policy_version 12193 (0.0008) -[2023-10-10 13:09:29,317][76543] Updated weights for policy 0, policy_version 12203 (0.0009) -[2023-10-10 13:09:29,685][76543] Updated weights for policy 0, policy_version 12213 (0.0009) -[2023-10-10 13:09:30,058][76543] Updated weights for policy 0, policy_version 12223 (0.0010) -[2023-10-10 13:09:31,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 25001984. Throughput: 0: 1821.4, 1: 1824.9. Samples: 6261160. Policy #0 lag: (min: 22.0, avg: 33.8, max: 54.0) -[2023-10-10 13:09:31,076][75634] Avg episode reward: [(0, '20.180'), (1, '21.370')] -[2023-10-10 13:09:31,271][76542] Updated weights for policy 1, policy_version 12200 (0.0010) -[2023-10-10 13:09:31,639][76542] Updated weights for policy 1, policy_version 12210 (0.0009) -[2023-10-10 13:09:32,010][76542] Updated weights for policy 1, policy_version 12220 (0.0010) -[2023-10-10 13:09:33,653][76543] Updated weights for policy 0, policy_version 12233 (0.0009) -[2023-10-10 13:09:34,027][76543] Updated weights for policy 0, policy_version 12243 (0.0007) -[2023-10-10 13:09:34,391][76543] Updated weights for policy 0, policy_version 12253 (0.0007) -[2023-10-10 13:09:35,792][76542] Updated weights for policy 1, policy_version 12230 (0.0009) -[2023-10-10 13:09:36,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 25067520. Throughput: 0: 1823.4, 1: 1829.1. Samples: 6272714. Policy #0 lag: (min: 8.0, avg: 34.6, max: 40.0) -[2023-10-10 13:09:36,076][75634] Avg episode reward: [(0, '19.910'), (1, '22.830')] -[2023-10-10 13:09:36,183][76542] Updated weights for policy 1, policy_version 12240 (0.0008) -[2023-10-10 13:09:36,550][76542] Updated weights for policy 1, policy_version 12250 (0.0008) -[2023-10-10 13:09:36,767][76421] Saving new best policy, reward=22.830! -[2023-10-10 13:09:38,049][76543] Updated weights for policy 0, policy_version 12263 (0.0008) -[2023-10-10 13:09:38,413][76543] Updated weights for policy 0, policy_version 12273 (0.0007) -[2023-10-10 13:09:38,786][76543] Updated weights for policy 0, policy_version 12283 (0.0007) -[2023-10-10 13:09:40,165][76542] Updated weights for policy 1, policy_version 12260 (0.0007) -[2023-10-10 13:09:40,543][76542] Updated weights for policy 1, policy_version 12270 (0.0007) -[2023-10-10 13:09:40,904][76542] Updated weights for policy 1, policy_version 12280 (0.0008) -[2023-10-10 13:09:41,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 25133056. Throughput: 0: 1818.5, 1: 1826.6. Samples: 6293736. Policy #0 lag: (min: 8.0, avg: 34.6, max: 40.0) -[2023-10-10 13:09:41,077][75634] Avg episode reward: [(0, '21.280'), (1, '23.020')] -[2023-10-10 13:09:41,200][76421] Saving new best policy, reward=23.020! -[2023-10-10 13:09:42,601][76543] Updated weights for policy 0, policy_version 12293 (0.0007) -[2023-10-10 13:09:42,976][76543] Updated weights for policy 0, policy_version 12303 (0.0010) -[2023-10-10 13:09:43,346][76543] Updated weights for policy 0, policy_version 12313 (0.0009) -[2023-10-10 13:09:44,405][76542] Updated weights for policy 1, policy_version 12290 (0.0007) -[2023-10-10 13:09:44,781][76542] Updated weights for policy 1, policy_version 12300 (0.0010) -[2023-10-10 13:09:45,135][76542] Updated weights for policy 1, policy_version 12310 (0.0007) -[2023-10-10 13:09:45,510][76542] Updated weights for policy 1, policy_version 12320 (0.0007) -[2023-10-10 13:09:46,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 25231360. Throughput: 0: 1816.9, 1: 1824.5. Samples: 6315252. Policy #0 lag: (min: 8.0, avg: 34.6, max: 40.0) -[2023-10-10 13:09:46,076][75634] Avg episode reward: [(0, '21.060'), (1, '21.150')] -[2023-10-10 13:09:47,086][76543] Updated weights for policy 0, policy_version 12323 (0.0008) -[2023-10-10 13:09:47,459][76543] Updated weights for policy 0, policy_version 12333 (0.0008) -[2023-10-10 13:09:47,833][76543] Updated weights for policy 0, policy_version 12343 (0.0010) -[2023-10-10 13:09:49,313][76542] Updated weights for policy 1, policy_version 12330 (0.0008) -[2023-10-10 13:09:49,694][76542] Updated weights for policy 1, policy_version 12340 (0.0009) -[2023-10-10 13:09:50,059][76542] Updated weights for policy 1, policy_version 12350 (0.0007) -[2023-10-10 13:09:51,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 25296896. Throughput: 0: 1816.1, 1: 1832.8. Samples: 6326786. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:09:51,076][75634] Avg episode reward: [(0, '21.310'), (1, '22.380')] -[2023-10-10 13:09:51,500][76543] Updated weights for policy 0, policy_version 12353 (0.0009) -[2023-10-10 13:09:51,872][76543] Updated weights for policy 0, policy_version 12363 (0.0009) -[2023-10-10 13:09:52,244][76543] Updated weights for policy 0, policy_version 12373 (0.0008) -[2023-10-10 13:09:52,615][76543] Updated weights for policy 0, policy_version 12383 (0.0007) -[2023-10-10 13:09:53,708][76542] Updated weights for policy 1, policy_version 12360 (0.0008) -[2023-10-10 13:09:54,077][76542] Updated weights for policy 1, policy_version 12370 (0.0008) -[2023-10-10 13:09:54,446][76542] Updated weights for policy 1, policy_version 12380 (0.0009) -[2023-10-10 13:09:56,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 25362432. Throughput: 0: 1823.3, 1: 1825.9. Samples: 6348108. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:09:56,077][75634] Avg episode reward: [(0, '20.970'), (1, '19.690')] -[2023-10-10 13:09:56,462][76543] Updated weights for policy 0, policy_version 12393 (0.0009) -[2023-10-10 13:09:56,846][76543] Updated weights for policy 0, policy_version 12403 (0.0009) -[2023-10-10 13:09:57,213][76543] Updated weights for policy 0, policy_version 12413 (0.0009) -[2023-10-10 13:09:58,096][76542] Updated weights for policy 1, policy_version 12390 (0.0009) -[2023-10-10 13:09:58,466][76542] Updated weights for policy 1, policy_version 12400 (0.0010) -[2023-10-10 13:09:58,832][76542] Updated weights for policy 1, policy_version 12410 (0.0011) -[2023-10-10 13:10:00,963][76543] Updated weights for policy 0, policy_version 12423 (0.0010) -[2023-10-10 13:10:01,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 25427968. Throughput: 0: 1815.4, 1: 1826.3. Samples: 6370950. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:10:01,077][75634] Avg episode reward: [(0, '21.900'), (1, '18.540')] -[2023-10-10 13:10:01,335][76543] Updated weights for policy 0, policy_version 12433 (0.0008) -[2023-10-10 13:10:01,701][76543] Updated weights for policy 0, policy_version 12443 (0.0008) -[2023-10-10 13:10:02,616][76542] Updated weights for policy 1, policy_version 12420 (0.0009) -[2023-10-10 13:10:02,985][76542] Updated weights for policy 1, policy_version 12430 (0.0008) -[2023-10-10 13:10:03,360][76542] Updated weights for policy 1, policy_version 12440 (0.0008) -[2023-10-10 13:10:05,402][76543] Updated weights for policy 0, policy_version 12453 (0.0009) -[2023-10-10 13:10:05,772][76543] Updated weights for policy 0, policy_version 12463 (0.0007) -[2023-10-10 13:10:06,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 25493504. Throughput: 0: 1814.1, 1: 1820.6. Samples: 6380734. Policy #0 lag: (min: 22.0, avg: 38.7, max: 40.0) -[2023-10-10 13:10:06,076][75634] Avg episode reward: [(0, '21.150'), (1, '18.770')] -[2023-10-10 13:10:06,149][76543] Updated weights for policy 0, policy_version 12473 (0.0008) -[2023-10-10 13:10:07,148][76542] Updated weights for policy 1, policy_version 12450 (0.0010) -[2023-10-10 13:10:07,520][76542] Updated weights for policy 1, policy_version 12460 (0.0009) -[2023-10-10 13:10:07,884][76542] Updated weights for policy 1, policy_version 12470 (0.0009) -[2023-10-10 13:10:08,264][76542] Updated weights for policy 1, policy_version 12480 (0.0009) -[2023-10-10 13:10:09,856][76543] Updated weights for policy 0, policy_version 12483 (0.0009) -[2023-10-10 13:10:10,229][76543] Updated weights for policy 0, policy_version 12493 (0.0008) -[2023-10-10 13:10:10,599][76543] Updated weights for policy 0, policy_version 12503 (0.0007) -[2023-10-10 13:10:11,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 25591808. Throughput: 0: 1814.9, 1: 1813.3. Samples: 6403286. Policy #0 lag: (min: 22.0, avg: 38.7, max: 40.0) -[2023-10-10 13:10:11,076][75634] Avg episode reward: [(0, '21.930'), (1, '20.570')] -[2023-10-10 13:10:12,054][76542] Updated weights for policy 1, policy_version 12490 (0.0008) -[2023-10-10 13:10:12,426][76542] Updated weights for policy 1, policy_version 12500 (0.0008) -[2023-10-10 13:10:12,801][76542] Updated weights for policy 1, policy_version 12510 (0.0008) -[2023-10-10 13:10:14,190][76543] Updated weights for policy 0, policy_version 12513 (0.0007) -[2023-10-10 13:10:14,554][76543] Updated weights for policy 0, policy_version 12523 (0.0009) -[2023-10-10 13:10:14,936][76543] Updated weights for policy 0, policy_version 12533 (0.0007) -[2023-10-10 13:10:15,307][76543] Updated weights for policy 0, policy_version 12543 (0.0007) -[2023-10-10 13:10:16,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 25657344. Throughput: 0: 1821.3, 1: 1814.9. Samples: 6424790. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) -[2023-10-10 13:10:16,077][75634] Avg episode reward: [(0, '21.900'), (1, '20.930')] -[2023-10-10 13:10:16,618][76542] Updated weights for policy 1, policy_version 12520 (0.0008) -[2023-10-10 13:10:16,995][76542] Updated weights for policy 1, policy_version 12530 (0.0009) -[2023-10-10 13:10:17,360][76542] Updated weights for policy 1, policy_version 12540 (0.0008) -[2023-10-10 13:10:18,968][76543] Updated weights for policy 0, policy_version 12553 (0.0008) -[2023-10-10 13:10:19,333][76543] Updated weights for policy 0, policy_version 12563 (0.0008) -[2023-10-10 13:10:19,705][76543] Updated weights for policy 0, policy_version 12573 (0.0008) -[2023-10-10 13:10:20,992][76542] Updated weights for policy 1, policy_version 12550 (0.0008) -[2023-10-10 13:10:21,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 25722880. Throughput: 0: 1818.4, 1: 1810.8. Samples: 6436026. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) -[2023-10-10 13:10:21,076][75634] Avg episode reward: [(0, '22.610'), (1, '21.510')] -[2023-10-10 13:10:21,378][76542] Updated weights for policy 1, policy_version 12560 (0.0009) -[2023-10-10 13:10:21,748][76542] Updated weights for policy 1, policy_version 12570 (0.0007) -[2023-10-10 13:10:23,191][76543] Updated weights for policy 0, policy_version 12583 (0.0009) -[2023-10-10 13:10:23,572][76543] Updated weights for policy 0, policy_version 12593 (0.0009) -[2023-10-10 13:10:23,941][76543] Updated weights for policy 0, policy_version 12603 (0.0007) -[2023-10-10 13:10:25,238][76542] Updated weights for policy 1, policy_version 12580 (0.0008) -[2023-10-10 13:10:25,609][76542] Updated weights for policy 1, policy_version 12590 (0.0007) -[2023-10-10 13:10:25,977][76542] Updated weights for policy 1, policy_version 12600 (0.0007) -[2023-10-10 13:10:26,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 25788416. Throughput: 0: 1824.8, 1: 1819.1. Samples: 6457710. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) -[2023-10-10 13:10:26,077][75634] Avg episode reward: [(0, '24.350'), (1, '22.500')] -[2023-10-10 13:10:27,627][76543] Updated weights for policy 0, policy_version 12613 (0.0007) -[2023-10-10 13:10:28,017][76543] Updated weights for policy 0, policy_version 12623 (0.0010) -[2023-10-10 13:10:28,401][76543] Updated weights for policy 0, policy_version 12633 (0.0010) -[2023-10-10 13:10:29,777][76542] Updated weights for policy 1, policy_version 12610 (0.0007) -[2023-10-10 13:10:30,148][76542] Updated weights for policy 1, policy_version 12620 (0.0007) -[2023-10-10 13:10:30,511][76542] Updated weights for policy 1, policy_version 12630 (0.0008) -[2023-10-10 13:10:30,879][76542] Updated weights for policy 1, policy_version 12640 (0.0010) -[2023-10-10 13:10:31,076][75634] Fps is (10 sec: 16383.5, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 25886720. Throughput: 0: 1827.9, 1: 1815.5. Samples: 6479202. Policy #0 lag: (min: 19.0, avg: 25.7, max: 51.0) -[2023-10-10 13:10:31,077][75634] Avg episode reward: [(0, '24.890'), (1, '24.480')] -[2023-10-10 13:10:31,086][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000012640_12943360.pth... -[2023-10-10 13:10:31,086][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000012640_12943360.pth... -[2023-10-10 13:10:31,129][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000010944_11206656.pth -[2023-10-10 13:10:31,131][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000010944_11206656.pth -[2023-10-10 13:10:31,134][76362] Saving new best policy, reward=24.890! -[2023-10-10 13:10:31,135][76421] Saving new best policy, reward=24.480! -[2023-10-10 13:10:32,089][76543] Updated weights for policy 0, policy_version 12643 (0.0009) -[2023-10-10 13:10:32,455][76543] Updated weights for policy 0, policy_version 12653 (0.0009) -[2023-10-10 13:10:32,831][76543] Updated weights for policy 0, policy_version 12663 (0.0008) -[2023-10-10 13:10:34,493][76542] Updated weights for policy 1, policy_version 12650 (0.0011) -[2023-10-10 13:10:34,866][76542] Updated weights for policy 1, policy_version 12660 (0.0007) -[2023-10-10 13:10:35,237][76542] Updated weights for policy 1, policy_version 12670 (0.0007) -[2023-10-10 13:10:36,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 25952256. Throughput: 0: 1824.1, 1: 1811.8. Samples: 6490404. Policy #0 lag: (min: 19.0, avg: 25.7, max: 51.0) -[2023-10-10 13:10:36,076][75634] Avg episode reward: [(0, '24.850'), (1, '24.710')] -[2023-10-10 13:10:36,077][76421] Saving new best policy, reward=24.710! -[2023-10-10 13:10:36,585][76543] Updated weights for policy 0, policy_version 12673 (0.0009) -[2023-10-10 13:10:36,964][76543] Updated weights for policy 0, policy_version 12683 (0.0011) -[2023-10-10 13:10:37,329][76543] Updated weights for policy 0, policy_version 12693 (0.0010) -[2023-10-10 13:10:37,708][76543] Updated weights for policy 0, policy_version 12703 (0.0010) -[2023-10-10 13:10:39,016][76542] Updated weights for policy 1, policy_version 12680 (0.0007) -[2023-10-10 13:10:39,388][76542] Updated weights for policy 1, policy_version 12690 (0.0008) -[2023-10-10 13:10:39,744][76542] Updated weights for policy 1, policy_version 12700 (0.0011) -[2023-10-10 13:10:41,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 26017792. Throughput: 0: 1816.6, 1: 1820.0. Samples: 6511756. Policy #0 lag: (min: 19.0, avg: 25.7, max: 51.0) -[2023-10-10 13:10:41,077][75634] Avg episode reward: [(0, '24.270'), (1, '25.710')] -[2023-10-10 13:10:41,078][76421] Saving new best policy, reward=25.710! -[2023-10-10 13:10:41,442][76543] Updated weights for policy 0, policy_version 12713 (0.0010) -[2023-10-10 13:10:41,809][76543] Updated weights for policy 0, policy_version 12723 (0.0007) -[2023-10-10 13:10:42,186][76543] Updated weights for policy 0, policy_version 12733 (0.0008) -[2023-10-10 13:10:43,481][76542] Updated weights for policy 1, policy_version 12710 (0.0009) -[2023-10-10 13:10:43,859][76542] Updated weights for policy 1, policy_version 12720 (0.0007) -[2023-10-10 13:10:44,218][76542] Updated weights for policy 1, policy_version 12730 (0.0009) -[2023-10-10 13:10:45,781][76543] Updated weights for policy 0, policy_version 12743 (0.0007) -[2023-10-10 13:10:46,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 26083328. Throughput: 0: 1819.9, 1: 1809.8. Samples: 6534288. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:10:46,077][75634] Avg episode reward: [(0, '25.520'), (1, '25.330')] -[2023-10-10 13:10:46,152][76543] Updated weights for policy 0, policy_version 12753 (0.0009) -[2023-10-10 13:10:46,523][76543] Updated weights for policy 0, policy_version 12763 (0.0010) -[2023-10-10 13:10:46,705][76362] Saving new best policy, reward=25.520! -[2023-10-10 13:10:47,980][76542] Updated weights for policy 1, policy_version 12740 (0.0009) -[2023-10-10 13:10:48,348][76542] Updated weights for policy 1, policy_version 12750 (0.0010) -[2023-10-10 13:10:48,718][76542] Updated weights for policy 1, policy_version 12760 (0.0008) -[2023-10-10 13:10:50,260][76543] Updated weights for policy 0, policy_version 12773 (0.0009) -[2023-10-10 13:10:50,636][76543] Updated weights for policy 0, policy_version 12783 (0.0009) -[2023-10-10 13:10:51,008][76543] Updated weights for policy 0, policy_version 12793 (0.0009) -[2023-10-10 13:10:51,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 26148864. Throughput: 0: 1818.5, 1: 1820.2. Samples: 6544476. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:10:51,076][75634] Avg episode reward: [(0, '26.610'), (1, '24.090')] -[2023-10-10 13:10:51,265][76362] Saving new best policy, reward=26.610! -[2023-10-10 13:10:52,417][76542] Updated weights for policy 1, policy_version 12770 (0.0007) -[2023-10-10 13:10:52,785][76542] Updated weights for policy 1, policy_version 12780 (0.0008) -[2023-10-10 13:10:53,153][76542] Updated weights for policy 1, policy_version 12790 (0.0009) -[2023-10-10 13:10:53,530][76542] Updated weights for policy 1, policy_version 12800 (0.0010) -[2023-10-10 13:10:54,588][76543] Updated weights for policy 0, policy_version 12803 (0.0008) -[2023-10-10 13:10:54,964][76543] Updated weights for policy 0, policy_version 12813 (0.0010) -[2023-10-10 13:10:55,342][76543] Updated weights for policy 0, policy_version 12823 (0.0007) -[2023-10-10 13:10:56,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 26247168. Throughput: 0: 1826.0, 1: 1816.8. Samples: 6567216. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-10 13:10:56,076][75634] Avg episode reward: [(0, '27.950'), (1, '23.210')] -[2023-10-10 13:10:56,077][76362] Saving new best policy, reward=27.950! -[2023-10-10 13:10:57,173][76542] Updated weights for policy 1, policy_version 12810 (0.0008) -[2023-10-10 13:10:57,532][76542] Updated weights for policy 1, policy_version 12820 (0.0007) -[2023-10-10 13:10:57,901][76542] Updated weights for policy 1, policy_version 12830 (0.0009) -[2023-10-10 13:10:59,014][76543] Updated weights for policy 0, policy_version 12833 (0.0008) -[2023-10-10 13:10:59,386][76543] Updated weights for policy 0, policy_version 12843 (0.0008) -[2023-10-10 13:10:59,754][76543] Updated weights for policy 0, policy_version 12853 (0.0007) -[2023-10-10 13:11:00,121][76543] Updated weights for policy 0, policy_version 12863 (0.0007) -[2023-10-10 13:11:01,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 26312704. Throughput: 0: 1823.4, 1: 1816.9. Samples: 6588604. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-10 13:11:01,077][75634] Avg episode reward: [(0, '26.630'), (1, '24.620')] -[2023-10-10 13:11:01,642][76542] Updated weights for policy 1, policy_version 12840 (0.0008) -[2023-10-10 13:11:02,015][76542] Updated weights for policy 1, policy_version 12850 (0.0010) -[2023-10-10 13:11:02,386][76542] Updated weights for policy 1, policy_version 12860 (0.0008) -[2023-10-10 13:11:03,921][76543] Updated weights for policy 0, policy_version 12873 (0.0008) -[2023-10-10 13:11:04,295][76543] Updated weights for policy 0, policy_version 12883 (0.0008) -[2023-10-10 13:11:04,673][76543] Updated weights for policy 0, policy_version 12893 (0.0011) -[2023-10-10 13:11:06,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 26378240. Throughput: 0: 1824.5, 1: 1816.6. Samples: 6599874. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-10 13:11:06,077][75634] Avg episode reward: [(0, '25.410'), (1, '22.150')] -[2023-10-10 13:11:06,206][76542] Updated weights for policy 1, policy_version 12870 (0.0007) -[2023-10-10 13:11:06,574][76542] Updated weights for policy 1, policy_version 12880 (0.0009) -[2023-10-10 13:11:06,941][76542] Updated weights for policy 1, policy_version 12890 (0.0011) -[2023-10-10 13:11:08,489][76543] Updated weights for policy 0, policy_version 12903 (0.0009) -[2023-10-10 13:11:08,851][76543] Updated weights for policy 0, policy_version 12913 (0.0008) -[2023-10-10 13:11:09,223][76543] Updated weights for policy 0, policy_version 12923 (0.0010) -[2023-10-10 13:11:10,508][76542] Updated weights for policy 1, policy_version 12900 (0.0009) -[2023-10-10 13:11:10,875][76542] Updated weights for policy 1, policy_version 12910 (0.0008) -[2023-10-10 13:11:11,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 26443776. Throughput: 0: 1820.5, 1: 1813.4. Samples: 6621234. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 13:11:11,076][75634] Avg episode reward: [(0, '25.680'), (1, '22.260')] -[2023-10-10 13:11:11,250][76542] Updated weights for policy 1, policy_version 12920 (0.0007) -[2023-10-10 13:11:12,907][76543] Updated weights for policy 0, policy_version 12933 (0.0011) -[2023-10-10 13:11:13,291][76543] Updated weights for policy 0, policy_version 12943 (0.0009) -[2023-10-10 13:11:13,663][76543] Updated weights for policy 0, policy_version 12953 (0.0007) -[2023-10-10 13:11:15,068][76542] Updated weights for policy 1, policy_version 12930 (0.0009) -[2023-10-10 13:11:15,431][76542] Updated weights for policy 1, policy_version 12940 (0.0012) -[2023-10-10 13:11:15,798][76542] Updated weights for policy 1, policy_version 12950 (0.0011) -[2023-10-10 13:11:16,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 26509312. Throughput: 0: 1812.2, 1: 1820.5. Samples: 6642674. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 13:11:16,076][75634] Avg episode reward: [(0, '24.480'), (1, '23.020')] -[2023-10-10 13:11:16,169][76542] Updated weights for policy 1, policy_version 12960 (0.0008) -[2023-10-10 13:11:17,418][76543] Updated weights for policy 0, policy_version 12963 (0.0007) -[2023-10-10 13:11:17,808][76543] Updated weights for policy 0, policy_version 12973 (0.0010) -[2023-10-10 13:11:18,177][76543] Updated weights for policy 0, policy_version 12983 (0.0009) -[2023-10-10 13:11:19,751][76542] Updated weights for policy 1, policy_version 12970 (0.0007) -[2023-10-10 13:11:20,121][76542] Updated weights for policy 1, policy_version 12980 (0.0008) -[2023-10-10 13:11:20,498][76542] Updated weights for policy 1, policy_version 12990 (0.0008) -[2023-10-10 13:11:21,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 26607616. Throughput: 0: 1822.4, 1: 1808.5. Samples: 6653796. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 13:11:21,076][75634] Avg episode reward: [(0, '24.140'), (1, '21.770')] -[2023-10-10 13:11:21,821][76543] Updated weights for policy 0, policy_version 12993 (0.0008) -[2023-10-10 13:11:22,200][76543] Updated weights for policy 0, policy_version 13003 (0.0009) -[2023-10-10 13:11:22,582][76543] Updated weights for policy 0, policy_version 13013 (0.0007) -[2023-10-10 13:11:22,946][76543] Updated weights for policy 0, policy_version 13023 (0.0009) -[2023-10-10 13:11:24,117][76542] Updated weights for policy 1, policy_version 13000 (0.0009) -[2023-10-10 13:11:24,492][76542] Updated weights for policy 1, policy_version 13010 (0.0010) -[2023-10-10 13:11:24,876][76542] Updated weights for policy 1, policy_version 13020 (0.0012) -[2023-10-10 13:11:26,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 26673152. Throughput: 0: 1818.5, 1: 1817.6. Samples: 6675380. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-10 13:11:26,076][75634] Avg episode reward: [(0, '23.920'), (1, '20.390')] -[2023-10-10 13:11:26,449][76543] Updated weights for policy 0, policy_version 13033 (0.0011) -[2023-10-10 13:11:26,821][76543] Updated weights for policy 0, policy_version 13043 (0.0007) -[2023-10-10 13:11:27,199][76543] Updated weights for policy 0, policy_version 13053 (0.0011) -[2023-10-10 13:11:28,459][76542] Updated weights for policy 1, policy_version 13030 (0.0010) -[2023-10-10 13:11:28,830][76542] Updated weights for policy 1, policy_version 13040 (0.0010) -[2023-10-10 13:11:29,201][76542] Updated weights for policy 1, policy_version 13050 (0.0010) -[2023-10-10 13:11:30,889][76543] Updated weights for policy 0, policy_version 13063 (0.0010) -[2023-10-10 13:11:31,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 26738688. Throughput: 0: 1818.4, 1: 1819.9. Samples: 6698014. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-10 13:11:31,076][75634] Avg episode reward: [(0, '22.840'), (1, '21.300')] -[2023-10-10 13:11:31,255][76543] Updated weights for policy 0, policy_version 13073 (0.0011) -[2023-10-10 13:11:31,642][76543] Updated weights for policy 0, policy_version 13083 (0.0011) -[2023-10-10 13:11:32,777][76542] Updated weights for policy 1, policy_version 13060 (0.0010) -[2023-10-10 13:11:33,137][76542] Updated weights for policy 1, policy_version 13070 (0.0007) -[2023-10-10 13:11:33,505][76542] Updated weights for policy 1, policy_version 13080 (0.0008) -[2023-10-10 13:11:35,298][76543] Updated weights for policy 0, policy_version 13093 (0.0008) -[2023-10-10 13:11:35,683][76543] Updated weights for policy 0, policy_version 13103 (0.0007) -[2023-10-10 13:11:36,044][76543] Updated weights for policy 0, policy_version 13113 (0.0009) -[2023-10-10 13:11:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 26804224. Throughput: 0: 1823.9, 1: 1817.8. Samples: 6708350. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-10 13:11:36,076][75634] Avg episode reward: [(0, '23.810'), (1, '22.730')] -[2023-10-10 13:11:37,129][76542] Updated weights for policy 1, policy_version 13090 (0.0007) -[2023-10-10 13:11:37,499][76542] Updated weights for policy 1, policy_version 13100 (0.0007) -[2023-10-10 13:11:37,862][76542] Updated weights for policy 1, policy_version 13110 (0.0009) -[2023-10-10 13:11:38,235][76542] Updated weights for policy 1, policy_version 13120 (0.0009) -[2023-10-10 13:11:39,688][76543] Updated weights for policy 0, policy_version 13123 (0.0009) -[2023-10-10 13:11:40,061][76543] Updated weights for policy 0, policy_version 13133 (0.0008) -[2023-10-10 13:11:40,438][76543] Updated weights for policy 0, policy_version 13143 (0.0008) -[2023-10-10 13:11:41,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 26902528. Throughput: 0: 1807.3, 1: 1830.8. Samples: 6730934. Policy #0 lag: (min: 31.0, avg: 49.1, max: 63.0) -[2023-10-10 13:11:41,077][75634] Avg episode reward: [(0, '22.930'), (1, '21.320')] -[2023-10-10 13:11:41,697][76542] Updated weights for policy 1, policy_version 13130 (0.0007) -[2023-10-10 13:11:42,065][76542] Updated weights for policy 1, policy_version 13140 (0.0010) -[2023-10-10 13:11:42,445][76542] Updated weights for policy 1, policy_version 13150 (0.0010) -[2023-10-10 13:11:44,146][76543] Updated weights for policy 0, policy_version 13153 (0.0008) -[2023-10-10 13:11:44,518][76543] Updated weights for policy 0, policy_version 13163 (0.0010) -[2023-10-10 13:11:44,890][76543] Updated weights for policy 0, policy_version 13173 (0.0009) -[2023-10-10 13:11:45,272][76543] Updated weights for policy 0, policy_version 13183 (0.0008) -[2023-10-10 13:11:46,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 26968064. Throughput: 0: 1808.4, 1: 1832.0. Samples: 6752426. Policy #0 lag: (min: 31.0, avg: 49.1, max: 63.0) -[2023-10-10 13:11:46,077][75634] Avg episode reward: [(0, '24.810'), (1, '22.410')] -[2023-10-10 13:11:46,263][76542] Updated weights for policy 1, policy_version 13160 (0.0009) -[2023-10-10 13:11:46,641][76542] Updated weights for policy 1, policy_version 13170 (0.0011) -[2023-10-10 13:11:47,005][76542] Updated weights for policy 1, policy_version 13180 (0.0007) -[2023-10-10 13:11:49,030][76543] Updated weights for policy 0, policy_version 13193 (0.0009) -[2023-10-10 13:11:49,409][76543] Updated weights for policy 0, policy_version 13203 (0.0010) -[2023-10-10 13:11:49,779][76543] Updated weights for policy 0, policy_version 13213 (0.0009) -[2023-10-10 13:11:50,799][76542] Updated weights for policy 1, policy_version 13190 (0.0009) -[2023-10-10 13:11:51,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 27033600. Throughput: 0: 1806.5, 1: 1832.6. Samples: 6763636. Policy #0 lag: (min: 11.0, avg: 14.8, max: 43.0) -[2023-10-10 13:11:51,076][75634] Avg episode reward: [(0, '26.570'), (1, '22.200')] -[2023-10-10 13:11:51,180][76542] Updated weights for policy 1, policy_version 13200 (0.0011) -[2023-10-10 13:11:51,544][76542] Updated weights for policy 1, policy_version 13210 (0.0008) -[2023-10-10 13:11:53,598][76543] Updated weights for policy 0, policy_version 13223 (0.0011) -[2023-10-10 13:11:53,973][76543] Updated weights for policy 0, policy_version 13233 (0.0010) -[2023-10-10 13:11:54,352][76543] Updated weights for policy 0, policy_version 13243 (0.0010) -[2023-10-10 13:11:55,201][76542] Updated weights for policy 1, policy_version 13220 (0.0008) -[2023-10-10 13:11:55,570][76542] Updated weights for policy 1, policy_version 13230 (0.0009) -[2023-10-10 13:11:55,941][76542] Updated weights for policy 1, policy_version 13240 (0.0009) -[2023-10-10 13:11:56,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 27099136. Throughput: 0: 1812.4, 1: 1826.0. Samples: 6784962. Policy #0 lag: (min: 11.0, avg: 14.8, max: 43.0) -[2023-10-10 13:11:56,076][75634] Avg episode reward: [(0, '26.190'), (1, '22.990')] -[2023-10-10 13:11:58,063][76543] Updated weights for policy 0, policy_version 13253 (0.0010) -[2023-10-10 13:11:58,447][76543] Updated weights for policy 0, policy_version 13263 (0.0007) -[2023-10-10 13:11:58,826][76543] Updated weights for policy 0, policy_version 13273 (0.0007) -[2023-10-10 13:11:59,684][76542] Updated weights for policy 1, policy_version 13250 (0.0009) -[2023-10-10 13:12:00,047][76542] Updated weights for policy 1, policy_version 13260 (0.0008) -[2023-10-10 13:12:00,416][76542] Updated weights for policy 1, policy_version 13270 (0.0007) -[2023-10-10 13:12:00,776][76542] Updated weights for policy 1, policy_version 13280 (0.0009) -[2023-10-10 13:12:01,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 27197440. Throughput: 0: 1812.7, 1: 1819.1. Samples: 6806106. Policy #0 lag: (min: 11.0, avg: 14.8, max: 43.0) -[2023-10-10 13:12:01,077][75634] Avg episode reward: [(0, '26.360'), (1, '24.080')] -[2023-10-10 13:12:02,390][76543] Updated weights for policy 0, policy_version 13283 (0.0009) -[2023-10-10 13:12:02,772][76543] Updated weights for policy 0, policy_version 13293 (0.0008) -[2023-10-10 13:12:03,148][76543] Updated weights for policy 0, policy_version 13303 (0.0010) -[2023-10-10 13:12:04,312][76542] Updated weights for policy 1, policy_version 13290 (0.0011) -[2023-10-10 13:12:04,681][76542] Updated weights for policy 1, policy_version 13300 (0.0009) -[2023-10-10 13:12:05,047][76542] Updated weights for policy 1, policy_version 13310 (0.0010) -[2023-10-10 13:12:06,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 27262976. Throughput: 0: 1813.1, 1: 1836.5. Samples: 6818026. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 13:12:06,076][75634] Avg episode reward: [(0, '25.770'), (1, '22.190')] -[2023-10-10 13:12:06,902][76543] Updated weights for policy 0, policy_version 13313 (0.0008) -[2023-10-10 13:12:07,280][76543] Updated weights for policy 0, policy_version 13323 (0.0007) -[2023-10-10 13:12:07,652][76543] Updated weights for policy 0, policy_version 13333 (0.0009) -[2023-10-10 13:12:08,039][76543] Updated weights for policy 0, policy_version 13343 (0.0010) -[2023-10-10 13:12:08,637][76542] Updated weights for policy 1, policy_version 13320 (0.0008) -[2023-10-10 13:12:09,005][76542] Updated weights for policy 1, policy_version 13330 (0.0010) -[2023-10-10 13:12:09,374][76542] Updated weights for policy 1, policy_version 13340 (0.0010) -[2023-10-10 13:12:11,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 27328512. Throughput: 0: 1811.4, 1: 1826.9. Samples: 6839104. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 13:12:11,076][75634] Avg episode reward: [(0, '25.660'), (1, '22.720')] -[2023-10-10 13:12:11,737][76543] Updated weights for policy 0, policy_version 13353 (0.0008) -[2023-10-10 13:12:12,104][76543] Updated weights for policy 0, policy_version 13363 (0.0007) -[2023-10-10 13:12:12,471][76543] Updated weights for policy 0, policy_version 13373 (0.0008) -[2023-10-10 13:12:12,915][76542] Updated weights for policy 1, policy_version 13350 (0.0011) -[2023-10-10 13:12:13,285][76542] Updated weights for policy 1, policy_version 13360 (0.0010) -[2023-10-10 13:12:13,648][76542] Updated weights for policy 1, policy_version 13370 (0.0008) -[2023-10-10 13:12:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 27394048. Throughput: 0: 1810.7, 1: 1833.6. Samples: 6862006. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 13:12:16,076][75634] Avg episode reward: [(0, '26.540'), (1, '24.060')] -[2023-10-10 13:12:16,082][76543] Updated weights for policy 0, policy_version 13383 (0.0007) -[2023-10-10 13:12:16,455][76543] Updated weights for policy 0, policy_version 13393 (0.0007) -[2023-10-10 13:12:16,821][76543] Updated weights for policy 0, policy_version 13403 (0.0009) -[2023-10-10 13:12:17,380][76542] Updated weights for policy 1, policy_version 13380 (0.0010) -[2023-10-10 13:12:17,755][76542] Updated weights for policy 1, policy_version 13390 (0.0009) -[2023-10-10 13:12:18,128][76542] Updated weights for policy 1, policy_version 13400 (0.0009) -[2023-10-10 13:12:20,586][76543] Updated weights for policy 0, policy_version 13413 (0.0008) -[2023-10-10 13:12:20,951][76543] Updated weights for policy 0, policy_version 13423 (0.0010) -[2023-10-10 13:12:21,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 27459584. Throughput: 0: 1812.8, 1: 1826.7. Samples: 6872126. Policy #0 lag: (min: 20.0, avg: 21.9, max: 50.0) -[2023-10-10 13:12:21,077][75634] Avg episode reward: [(0, '25.730'), (1, '22.260')] -[2023-10-10 13:12:21,326][76543] Updated weights for policy 0, policy_version 13433 (0.0009) -[2023-10-10 13:12:21,870][76542] Updated weights for policy 1, policy_version 13410 (0.0008) -[2023-10-10 13:12:22,240][76542] Updated weights for policy 1, policy_version 13420 (0.0009) -[2023-10-10 13:12:22,600][76542] Updated weights for policy 1, policy_version 13430 (0.0008) -[2023-10-10 13:12:22,958][76542] Updated weights for policy 1, policy_version 13440 (0.0010) -[2023-10-10 13:12:24,910][76543] Updated weights for policy 0, policy_version 13443 (0.0010) -[2023-10-10 13:12:25,282][76543] Updated weights for policy 0, policy_version 13453 (0.0009) -[2023-10-10 13:12:25,653][76543] Updated weights for policy 0, policy_version 13463 (0.0007) -[2023-10-10 13:12:26,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 27557888. Throughput: 0: 1821.7, 1: 1825.5. Samples: 6895056. Policy #0 lag: (min: 20.0, avg: 21.9, max: 50.0) -[2023-10-10 13:12:26,076][75634] Avg episode reward: [(0, '25.180'), (1, '20.420')] -[2023-10-10 13:12:26,673][76542] Updated weights for policy 1, policy_version 13450 (0.0008) -[2023-10-10 13:12:27,036][76542] Updated weights for policy 1, policy_version 13460 (0.0009) -[2023-10-10 13:12:27,403][76542] Updated weights for policy 1, policy_version 13470 (0.0009) -[2023-10-10 13:12:29,264][76543] Updated weights for policy 0, policy_version 13473 (0.0009) -[2023-10-10 13:12:29,653][76543] Updated weights for policy 0, policy_version 13483 (0.0010) -[2023-10-10 13:12:30,017][76543] Updated weights for policy 0, policy_version 13493 (0.0011) -[2023-10-10 13:12:30,394][76543] Updated weights for policy 0, policy_version 13503 (0.0009) -[2023-10-10 13:12:31,012][76542] Updated weights for policy 1, policy_version 13480 (0.0008) -[2023-10-10 13:12:31,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 27623424. Throughput: 0: 1831.3, 1: 1824.7. Samples: 6916946. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) -[2023-10-10 13:12:31,077][75634] Avg episode reward: [(0, '24.240'), (1, '23.310')] -[2023-10-10 13:12:31,086][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000013504_13828096.pth... -[2023-10-10 13:12:31,120][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000011808_12091392.pth -[2023-10-10 13:12:31,376][76542] Updated weights for policy 1, policy_version 13490 (0.0007) -[2023-10-10 13:12:31,760][76542] Updated weights for policy 1, policy_version 13500 (0.0007) -[2023-10-10 13:12:31,902][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000013504_13828096.pth... -[2023-10-10 13:12:31,940][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000011776_12058624.pth -[2023-10-10 13:12:33,948][76543] Updated weights for policy 0, policy_version 13513 (0.0009) -[2023-10-10 13:12:34,327][76543] Updated weights for policy 0, policy_version 13523 (0.0008) -[2023-10-10 13:12:34,700][76543] Updated weights for policy 0, policy_version 13533 (0.0009) -[2023-10-10 13:12:35,533][76542] Updated weights for policy 1, policy_version 13510 (0.0009) -[2023-10-10 13:12:35,917][76542] Updated weights for policy 1, policy_version 13520 (0.0009) -[2023-10-10 13:12:36,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 27688960. Throughput: 0: 1830.7, 1: 1829.2. Samples: 6928330. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) -[2023-10-10 13:12:36,076][75634] Avg episode reward: [(0, '26.230'), (1, '24.370')] -[2023-10-10 13:12:36,278][76542] Updated weights for policy 1, policy_version 13530 (0.0008) -[2023-10-10 13:12:38,374][76543] Updated weights for policy 0, policy_version 13543 (0.0010) -[2023-10-10 13:12:38,741][76543] Updated weights for policy 0, policy_version 13553 (0.0009) -[2023-10-10 13:12:39,116][76543] Updated weights for policy 0, policy_version 13563 (0.0011) -[2023-10-10 13:12:40,008][76542] Updated weights for policy 1, policy_version 13540 (0.0008) -[2023-10-10 13:12:40,387][76542] Updated weights for policy 1, policy_version 13550 (0.0009) -[2023-10-10 13:12:40,764][76542] Updated weights for policy 1, policy_version 13560 (0.0007) -[2023-10-10 13:12:41,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 27787264. Throughput: 0: 1822.2, 1: 1834.6. Samples: 6949516. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) -[2023-10-10 13:12:41,077][75634] Avg episode reward: [(0, '26.030'), (1, '24.160')] -[2023-10-10 13:12:42,903][76543] Updated weights for policy 0, policy_version 13573 (0.0010) -[2023-10-10 13:12:43,296][76543] Updated weights for policy 0, policy_version 13583 (0.0009) -[2023-10-10 13:12:43,662][76543] Updated weights for policy 0, policy_version 13593 (0.0007) -[2023-10-10 13:12:44,309][76542] Updated weights for policy 1, policy_version 13570 (0.0007) -[2023-10-10 13:12:44,681][76542] Updated weights for policy 1, policy_version 13580 (0.0009) -[2023-10-10 13:12:45,044][76542] Updated weights for policy 1, policy_version 13590 (0.0008) -[2023-10-10 13:12:45,415][76542] Updated weights for policy 1, policy_version 13600 (0.0007) -[2023-10-10 13:12:46,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 27852800. Throughput: 0: 1825.6, 1: 1835.9. Samples: 6970872. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:12:46,076][75634] Avg episode reward: [(0, '26.380'), (1, '23.230')] -[2023-10-10 13:12:47,304][76543] Updated weights for policy 0, policy_version 13603 (0.0007) -[2023-10-10 13:12:47,672][76543] Updated weights for policy 0, policy_version 13613 (0.0009) -[2023-10-10 13:12:48,054][76543] Updated weights for policy 0, policy_version 13623 (0.0007) -[2023-10-10 13:12:49,049][76542] Updated weights for policy 1, policy_version 13610 (0.0007) -[2023-10-10 13:12:49,409][76542] Updated weights for policy 1, policy_version 13620 (0.0009) -[2023-10-10 13:12:49,789][76542] Updated weights for policy 1, policy_version 13630 (0.0009) -[2023-10-10 13:12:51,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 27918336. Throughput: 0: 1823.5, 1: 1835.2. Samples: 6982664. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:12:51,077][75634] Avg episode reward: [(0, '25.960'), (1, '23.510')] -[2023-10-10 13:12:51,652][76543] Updated weights for policy 0, policy_version 13633 (0.0007) -[2023-10-10 13:12:52,018][76543] Updated weights for policy 0, policy_version 13643 (0.0011) -[2023-10-10 13:12:52,395][76543] Updated weights for policy 0, policy_version 13653 (0.0008) -[2023-10-10 13:12:52,760][76543] Updated weights for policy 0, policy_version 13663 (0.0008) -[2023-10-10 13:12:53,515][76542] Updated weights for policy 1, policy_version 13640 (0.0009) -[2023-10-10 13:12:53,879][76542] Updated weights for policy 1, policy_version 13650 (0.0009) -[2023-10-10 13:12:54,252][76542] Updated weights for policy 1, policy_version 13660 (0.0009) -[2023-10-10 13:12:56,076][75634] Fps is (10 sec: 13106.7, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 27983872. Throughput: 0: 1832.5, 1: 1832.1. Samples: 7004012. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:12:56,077][75634] Avg episode reward: [(0, '25.300'), (1, '22.660')] -[2023-10-10 13:12:56,447][76543] Updated weights for policy 0, policy_version 13673 (0.0010) -[2023-10-10 13:12:56,821][76543] Updated weights for policy 0, policy_version 13683 (0.0009) -[2023-10-10 13:12:57,195][76543] Updated weights for policy 0, policy_version 13693 (0.0008) -[2023-10-10 13:12:58,101][76542] Updated weights for policy 1, policy_version 13670 (0.0008) -[2023-10-10 13:12:58,472][76542] Updated weights for policy 1, policy_version 13680 (0.0008) -[2023-10-10 13:12:58,840][76542] Updated weights for policy 1, policy_version 13690 (0.0008) -[2023-10-10 13:13:00,880][76543] Updated weights for policy 0, policy_version 13703 (0.0009) -[2023-10-10 13:13:01,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 28049408. Throughput: 0: 1829.5, 1: 1827.2. Samples: 7026558. Policy #0 lag: (min: 21.0, avg: 24.0, max: 53.0) -[2023-10-10 13:13:01,077][75634] Avg episode reward: [(0, '29.190'), (1, '22.760')] -[2023-10-10 13:13:01,254][76543] Updated weights for policy 0, policy_version 13713 (0.0008) -[2023-10-10 13:13:01,636][76543] Updated weights for policy 0, policy_version 13723 (0.0008) -[2023-10-10 13:13:01,817][76362] Saving new best policy, reward=29.190! -[2023-10-10 13:13:02,527][76542] Updated weights for policy 1, policy_version 13700 (0.0008) -[2023-10-10 13:13:02,902][76542] Updated weights for policy 1, policy_version 13710 (0.0009) -[2023-10-10 13:13:03,273][76542] Updated weights for policy 1, policy_version 13720 (0.0007) -[2023-10-10 13:13:05,432][76543] Updated weights for policy 0, policy_version 13733 (0.0009) -[2023-10-10 13:13:05,808][76543] Updated weights for policy 0, policy_version 13743 (0.0007) -[2023-10-10 13:13:06,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 28114944. Throughput: 0: 1823.7, 1: 1827.4. Samples: 7036428. Policy #0 lag: (min: 21.0, avg: 24.0, max: 53.0) -[2023-10-10 13:13:06,077][75634] Avg episode reward: [(0, '29.590'), (1, '22.360')] -[2023-10-10 13:13:06,164][76543] Updated weights for policy 0, policy_version 13753 (0.0007) -[2023-10-10 13:13:06,416][76362] Saving new best policy, reward=29.590! -[2023-10-10 13:13:06,855][76542] Updated weights for policy 1, policy_version 13730 (0.0007) -[2023-10-10 13:13:07,230][76542] Updated weights for policy 1, policy_version 13740 (0.0009) -[2023-10-10 13:13:07,598][76542] Updated weights for policy 1, policy_version 13750 (0.0011) -[2023-10-10 13:13:07,960][76542] Updated weights for policy 1, policy_version 13760 (0.0007) -[2023-10-10 13:13:09,850][76543] Updated weights for policy 0, policy_version 13763 (0.0008) -[2023-10-10 13:13:10,223][76543] Updated weights for policy 0, policy_version 13773 (0.0011) -[2023-10-10 13:13:10,588][76543] Updated weights for policy 0, policy_version 13783 (0.0010) -[2023-10-10 13:13:11,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 28213248. Throughput: 0: 1821.7, 1: 1827.6. Samples: 7059278. Policy #0 lag: (min: 31.0, avg: 33.0, max: 62.0) -[2023-10-10 13:13:11,077][75634] Avg episode reward: [(0, '28.860'), (1, '23.680')] -[2023-10-10 13:13:11,695][76542] Updated weights for policy 1, policy_version 13770 (0.0010) -[2023-10-10 13:13:12,053][76542] Updated weights for policy 1, policy_version 13780 (0.0008) -[2023-10-10 13:13:12,428][76542] Updated weights for policy 1, policy_version 13790 (0.0007) -[2023-10-10 13:13:14,222][76543] Updated weights for policy 0, policy_version 13793 (0.0010) -[2023-10-10 13:13:14,594][76543] Updated weights for policy 0, policy_version 13803 (0.0011) -[2023-10-10 13:13:14,966][76543] Updated weights for policy 0, policy_version 13813 (0.0009) -[2023-10-10 13:13:15,332][76543] Updated weights for policy 0, policy_version 13823 (0.0008) -[2023-10-10 13:13:16,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 28278784. Throughput: 0: 1812.4, 1: 1826.3. Samples: 7080686. Policy #0 lag: (min: 31.0, avg: 33.0, max: 62.0) -[2023-10-10 13:13:16,076][75634] Avg episode reward: [(0, '29.020'), (1, '25.510')] -[2023-10-10 13:13:16,149][76542] Updated weights for policy 1, policy_version 13800 (0.0008) -[2023-10-10 13:13:16,506][76542] Updated weights for policy 1, policy_version 13810 (0.0007) -[2023-10-10 13:13:16,877][76542] Updated weights for policy 1, policy_version 13820 (0.0007) -[2023-10-10 13:13:19,181][76543] Updated weights for policy 0, policy_version 13833 (0.0007) -[2023-10-10 13:13:19,545][76543] Updated weights for policy 0, policy_version 13843 (0.0008) -[2023-10-10 13:13:19,930][76543] Updated weights for policy 0, policy_version 13853 (0.0009) -[2023-10-10 13:13:20,679][76542] Updated weights for policy 1, policy_version 13830 (0.0009) -[2023-10-10 13:13:21,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 28344320. Throughput: 0: 1810.5, 1: 1822.4. Samples: 7091814. Policy #0 lag: (min: 31.0, avg: 33.0, max: 62.0) -[2023-10-10 13:13:21,076][75634] Avg episode reward: [(0, '30.630'), (1, '25.450')] -[2023-10-10 13:13:21,077][76362] Saving new best policy, reward=30.630! -[2023-10-10 13:13:21,079][76542] Updated weights for policy 1, policy_version 13840 (0.0008) -[2023-10-10 13:13:21,436][76542] Updated weights for policy 1, policy_version 13850 (0.0011) -[2023-10-10 13:13:23,512][76543] Updated weights for policy 0, policy_version 13863 (0.0008) -[2023-10-10 13:13:23,879][76543] Updated weights for policy 0, policy_version 13873 (0.0008) -[2023-10-10 13:13:24,247][76543] Updated weights for policy 0, policy_version 13883 (0.0008) -[2023-10-10 13:13:25,101][76542] Updated weights for policy 1, policy_version 13860 (0.0010) -[2023-10-10 13:13:25,475][76542] Updated weights for policy 1, policy_version 13870 (0.0008) -[2023-10-10 13:13:25,839][76542] Updated weights for policy 1, policy_version 13880 (0.0007) -[2023-10-10 13:13:26,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 28409856. Throughput: 0: 1818.7, 1: 1821.6. Samples: 7113326. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-10 13:13:26,077][75634] Avg episode reward: [(0, '30.540'), (1, '24.760')] -[2023-10-10 13:13:27,998][76543] Updated weights for policy 0, policy_version 13893 (0.0010) -[2023-10-10 13:13:28,386][76543] Updated weights for policy 0, policy_version 13903 (0.0010) -[2023-10-10 13:13:28,761][76543] Updated weights for policy 0, policy_version 13913 (0.0009) -[2023-10-10 13:13:29,379][76542] Updated weights for policy 1, policy_version 13890 (0.0009) -[2023-10-10 13:13:29,761][76542] Updated weights for policy 1, policy_version 13900 (0.0009) -[2023-10-10 13:13:30,129][76542] Updated weights for policy 1, policy_version 13910 (0.0010) -[2023-10-10 13:13:30,493][76542] Updated weights for policy 1, policy_version 13920 (0.0009) -[2023-10-10 13:13:31,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 28508160. Throughput: 0: 1816.7, 1: 1818.3. Samples: 7134448. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-10 13:13:31,077][75634] Avg episode reward: [(0, '29.300'), (1, '23.620')] -[2023-10-10 13:13:32,490][76543] Updated weights for policy 0, policy_version 13923 (0.0008) -[2023-10-10 13:13:32,856][76543] Updated weights for policy 0, policy_version 13933 (0.0008) -[2023-10-10 13:13:33,220][76543] Updated weights for policy 0, policy_version 13943 (0.0007) -[2023-10-10 13:13:34,192][76542] Updated weights for policy 1, policy_version 13930 (0.0008) -[2023-10-10 13:13:34,561][76542] Updated weights for policy 1, policy_version 13940 (0.0012) -[2023-10-10 13:13:34,927][76542] Updated weights for policy 1, policy_version 13950 (0.0011) -[2023-10-10 13:13:36,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 28573696. Throughput: 0: 1817.2, 1: 1817.7. Samples: 7146236. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-10 13:13:36,077][75634] Avg episode reward: [(0, '29.070'), (1, '22.680')] -[2023-10-10 13:13:36,838][76543] Updated weights for policy 0, policy_version 13953 (0.0007) -[2023-10-10 13:13:37,209][76543] Updated weights for policy 0, policy_version 13963 (0.0007) -[2023-10-10 13:13:37,588][76543] Updated weights for policy 0, policy_version 13973 (0.0008) -[2023-10-10 13:13:37,964][76543] Updated weights for policy 0, policy_version 13983 (0.0008) -[2023-10-10 13:13:38,707][76542] Updated weights for policy 1, policy_version 13960 (0.0010) -[2023-10-10 13:13:39,078][76542] Updated weights for policy 1, policy_version 13970 (0.0010) -[2023-10-10 13:13:39,453][76542] Updated weights for policy 1, policy_version 13980 (0.0011) -[2023-10-10 13:13:41,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 28639232. Throughput: 0: 1811.9, 1: 1814.0. Samples: 7167176. Policy #0 lag: (min: 25.0, avg: 53.3, max: 56.0) -[2023-10-10 13:13:41,076][75634] Avg episode reward: [(0, '26.810'), (1, '22.310')] -[2023-10-10 13:13:41,628][76543] Updated weights for policy 0, policy_version 13993 (0.0007) -[2023-10-10 13:13:42,000][76543] Updated weights for policy 0, policy_version 14003 (0.0009) -[2023-10-10 13:13:42,376][76543] Updated weights for policy 0, policy_version 14013 (0.0007) -[2023-10-10 13:13:43,159][76542] Updated weights for policy 1, policy_version 13990 (0.0010) -[2023-10-10 13:13:43,526][76542] Updated weights for policy 1, policy_version 14000 (0.0008) -[2023-10-10 13:13:43,901][76542] Updated weights for policy 1, policy_version 14010 (0.0010) -[2023-10-10 13:13:46,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 28704768. Throughput: 0: 1818.0, 1: 1812.6. Samples: 7189934. Policy #0 lag: (min: 25.0, avg: 53.3, max: 56.0) -[2023-10-10 13:13:46,076][75634] Avg episode reward: [(0, '26.650'), (1, '24.050')] -[2023-10-10 13:13:46,080][76543] Updated weights for policy 0, policy_version 14023 (0.0011) -[2023-10-10 13:13:46,450][76543] Updated weights for policy 0, policy_version 14033 (0.0012) -[2023-10-10 13:13:46,818][76543] Updated weights for policy 0, policy_version 14043 (0.0008) -[2023-10-10 13:13:47,602][76542] Updated weights for policy 1, policy_version 14020 (0.0010) -[2023-10-10 13:13:47,973][76542] Updated weights for policy 1, policy_version 14030 (0.0011) -[2023-10-10 13:13:48,342][76542] Updated weights for policy 1, policy_version 14040 (0.0010) -[2023-10-10 13:13:50,533][76543] Updated weights for policy 0, policy_version 14053 (0.0008) -[2023-10-10 13:13:50,902][76543] Updated weights for policy 0, policy_version 14063 (0.0010) -[2023-10-10 13:13:51,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 28770304. Throughput: 0: 1815.3, 1: 1813.0. Samples: 7199702. Policy #0 lag: (min: 25.0, avg: 53.3, max: 56.0) -[2023-10-10 13:13:51,077][75634] Avg episode reward: [(0, '26.830'), (1, '24.960')] -[2023-10-10 13:13:51,272][76543] Updated weights for policy 0, policy_version 14073 (0.0011) -[2023-10-10 13:13:51,969][76542] Updated weights for policy 1, policy_version 14050 (0.0008) -[2023-10-10 13:13:52,347][76542] Updated weights for policy 1, policy_version 14060 (0.0008) -[2023-10-10 13:13:52,722][76542] Updated weights for policy 1, policy_version 14070 (0.0008) -[2023-10-10 13:13:53,079][76542] Updated weights for policy 1, policy_version 14080 (0.0007) -[2023-10-10 13:13:54,970][76543] Updated weights for policy 0, policy_version 14083 (0.0010) -[2023-10-10 13:13:55,349][76543] Updated weights for policy 0, policy_version 14093 (0.0008) -[2023-10-10 13:13:55,717][76543] Updated weights for policy 0, policy_version 14103 (0.0010) -[2023-10-10 13:13:56,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 28868608. Throughput: 0: 1818.8, 1: 1812.7. Samples: 7222694. Policy #0 lag: (min: 3.0, avg: 3.1, max: 8.0) -[2023-10-10 13:13:56,076][75634] Avg episode reward: [(0, '25.080'), (1, '25.860')] -[2023-10-10 13:13:56,077][76421] Saving new best policy, reward=25.860! -[2023-10-10 13:13:56,724][76542] Updated weights for policy 1, policy_version 14090 (0.0007) -[2023-10-10 13:13:57,089][76542] Updated weights for policy 1, policy_version 14100 (0.0009) -[2023-10-10 13:13:57,458][76542] Updated weights for policy 1, policy_version 14110 (0.0007) -[2023-10-10 13:13:59,362][76543] Updated weights for policy 0, policy_version 14113 (0.0010) -[2023-10-10 13:13:59,738][76543] Updated weights for policy 0, policy_version 14123 (0.0010) -[2023-10-10 13:14:00,108][76543] Updated weights for policy 0, policy_version 14133 (0.0009) -[2023-10-10 13:14:00,475][76543] Updated weights for policy 0, policy_version 14143 (0.0007) -[2023-10-10 13:14:01,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 28934144. Throughput: 0: 1829.2, 1: 1817.3. Samples: 7244780. Policy #0 lag: (min: 3.0, avg: 3.1, max: 8.0) -[2023-10-10 13:14:01,076][75634] Avg episode reward: [(0, '25.320'), (1, '26.450')] -[2023-10-10 13:14:01,110][76542] Updated weights for policy 1, policy_version 14120 (0.0009) -[2023-10-10 13:14:01,491][76542] Updated weights for policy 1, policy_version 14130 (0.0007) -[2023-10-10 13:14:01,860][76542] Updated weights for policy 1, policy_version 14140 (0.0007) -[2023-10-10 13:14:01,996][76421] Saving new best policy, reward=26.450! -[2023-10-10 13:14:04,151][76543] Updated weights for policy 0, policy_version 14153 (0.0009) -[2023-10-10 13:14:04,509][76543] Updated weights for policy 0, policy_version 14163 (0.0010) -[2023-10-10 13:14:04,887][76543] Updated weights for policy 0, policy_version 14173 (0.0009) -[2023-10-10 13:14:05,586][76542] Updated weights for policy 1, policy_version 14150 (0.0007) -[2023-10-10 13:14:05,956][76542] Updated weights for policy 1, policy_version 14160 (0.0008) -[2023-10-10 13:14:06,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 28999680. Throughput: 0: 1826.6, 1: 1816.3. Samples: 7255744. Policy #0 lag: (min: 30.0, avg: 45.3, max: 62.0) -[2023-10-10 13:14:06,076][75634] Avg episode reward: [(0, '26.270'), (1, '26.040')] -[2023-10-10 13:14:06,320][76542] Updated weights for policy 1, policy_version 14170 (0.0008) -[2023-10-10 13:14:08,574][76543] Updated weights for policy 0, policy_version 14183 (0.0009) -[2023-10-10 13:14:08,935][76543] Updated weights for policy 0, policy_version 14193 (0.0009) -[2023-10-10 13:14:09,306][76543] Updated weights for policy 0, policy_version 14203 (0.0008) -[2023-10-10 13:14:10,049][76542] Updated weights for policy 1, policy_version 14180 (0.0008) -[2023-10-10 13:14:10,418][76542] Updated weights for policy 1, policy_version 14190 (0.0011) -[2023-10-10 13:14:10,783][76542] Updated weights for policy 1, policy_version 14200 (0.0009) -[2023-10-10 13:14:11,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 29065216. Throughput: 0: 1827.9, 1: 1820.9. Samples: 7277522. Policy #0 lag: (min: 30.0, avg: 45.3, max: 62.0) -[2023-10-10 13:14:11,076][75634] Avg episode reward: [(0, '26.350'), (1, '26.990')] -[2023-10-10 13:14:11,077][76421] Saving new best policy, reward=26.990! -[2023-10-10 13:14:13,000][76543] Updated weights for policy 0, policy_version 14213 (0.0010) -[2023-10-10 13:14:13,391][76543] Updated weights for policy 0, policy_version 14223 (0.0011) -[2023-10-10 13:14:13,764][76543] Updated weights for policy 0, policy_version 14233 (0.0009) -[2023-10-10 13:14:14,367][76542] Updated weights for policy 1, policy_version 14210 (0.0010) -[2023-10-10 13:14:14,732][76542] Updated weights for policy 1, policy_version 14220 (0.0010) -[2023-10-10 13:14:15,100][76542] Updated weights for policy 1, policy_version 14230 (0.0008) -[2023-10-10 13:14:15,473][76542] Updated weights for policy 1, policy_version 14240 (0.0007) -[2023-10-10 13:14:16,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 29163520. Throughput: 0: 1822.2, 1: 1821.7. Samples: 7298422. Policy #0 lag: (min: 30.0, avg: 45.3, max: 62.0) -[2023-10-10 13:14:16,076][75634] Avg episode reward: [(0, '26.350'), (1, '23.270')] -[2023-10-10 13:14:17,370][76543] Updated weights for policy 0, policy_version 14243 (0.0008) -[2023-10-10 13:14:17,748][76543] Updated weights for policy 0, policy_version 14253 (0.0009) -[2023-10-10 13:14:18,118][76543] Updated weights for policy 0, policy_version 14263 (0.0011) -[2023-10-10 13:14:19,045][76542] Updated weights for policy 1, policy_version 14250 (0.0010) -[2023-10-10 13:14:19,403][76542] Updated weights for policy 1, policy_version 14260 (0.0011) -[2023-10-10 13:14:19,769][76542] Updated weights for policy 1, policy_version 14270 (0.0010) -[2023-10-10 13:14:21,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 29229056. Throughput: 0: 1821.3, 1: 1825.9. Samples: 7310360. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:14:21,076][75634] Avg episode reward: [(0, '26.240'), (1, '24.620')] -[2023-10-10 13:14:21,722][76543] Updated weights for policy 0, policy_version 14273 (0.0009) -[2023-10-10 13:14:22,101][76543] Updated weights for policy 0, policy_version 14283 (0.0010) -[2023-10-10 13:14:22,469][76543] Updated weights for policy 0, policy_version 14293 (0.0009) -[2023-10-10 13:14:22,840][76543] Updated weights for policy 0, policy_version 14303 (0.0011) -[2023-10-10 13:14:23,397][76542] Updated weights for policy 1, policy_version 14280 (0.0012) -[2023-10-10 13:14:23,773][76542] Updated weights for policy 1, policy_version 14290 (0.0008) -[2023-10-10 13:14:24,143][76542] Updated weights for policy 1, policy_version 14300 (0.0008) -[2023-10-10 13:14:26,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 29294592. Throughput: 0: 1822.0, 1: 1832.6. Samples: 7331630. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:14:26,076][75634] Avg episode reward: [(0, '25.060'), (1, '23.610')] -[2023-10-10 13:14:26,494][76543] Updated weights for policy 0, policy_version 14313 (0.0009) -[2023-10-10 13:14:26,866][76543] Updated weights for policy 0, policy_version 14323 (0.0008) -[2023-10-10 13:14:27,244][76543] Updated weights for policy 0, policy_version 14333 (0.0010) -[2023-10-10 13:14:27,786][76542] Updated weights for policy 1, policy_version 14310 (0.0009) -[2023-10-10 13:14:28,158][76542] Updated weights for policy 1, policy_version 14320 (0.0007) -[2023-10-10 13:14:28,533][76542] Updated weights for policy 1, policy_version 14330 (0.0009) -[2023-10-10 13:14:30,900][76543] Updated weights for policy 0, policy_version 14343 (0.0009) -[2023-10-10 13:14:31,076][75634] Fps is (10 sec: 13106.7, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 29360128. Throughput: 0: 1817.6, 1: 1840.3. Samples: 7354538. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:14:31,077][75634] Avg episode reward: [(0, '24.300'), (1, '24.610')] -[2023-10-10 13:14:31,088][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000014336_14680064.pth... -[2023-10-10 13:14:31,124][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000012640_12943360.pth -[2023-10-10 13:14:31,282][76543] Updated weights for policy 0, policy_version 14353 (0.0007) -[2023-10-10 13:14:31,652][76543] Updated weights for policy 0, policy_version 14363 (0.0011) -[2023-10-10 13:14:31,836][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000014368_14712832.pth... -[2023-10-10 13:14:31,866][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000012640_12943360.pth -[2023-10-10 13:14:32,119][76542] Updated weights for policy 1, policy_version 14340 (0.0008) -[2023-10-10 13:14:32,494][76542] Updated weights for policy 1, policy_version 14350 (0.0010) -[2023-10-10 13:14:32,857][76542] Updated weights for policy 1, policy_version 14360 (0.0009) -[2023-10-10 13:14:35,418][76543] Updated weights for policy 0, policy_version 14373 (0.0008) -[2023-10-10 13:14:35,789][76543] Updated weights for policy 0, policy_version 14383 (0.0007) -[2023-10-10 13:14:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 29425664. Throughput: 0: 1820.4, 1: 1843.2. Samples: 7364564. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-10 13:14:36,076][75634] Avg episode reward: [(0, '25.130'), (1, '25.140')] -[2023-10-10 13:14:36,156][76543] Updated weights for policy 0, policy_version 14393 (0.0010) -[2023-10-10 13:14:36,453][76542] Updated weights for policy 1, policy_version 14370 (0.0008) -[2023-10-10 13:14:36,818][76542] Updated weights for policy 1, policy_version 14380 (0.0009) -[2023-10-10 13:14:37,186][76542] Updated weights for policy 1, policy_version 14390 (0.0010) -[2023-10-10 13:14:37,550][76542] Updated weights for policy 1, policy_version 14400 (0.0009) -[2023-10-10 13:14:39,772][76543] Updated weights for policy 0, policy_version 14403 (0.0010) -[2023-10-10 13:14:40,149][76543] Updated weights for policy 0, policy_version 14413 (0.0010) -[2023-10-10 13:14:40,527][76543] Updated weights for policy 0, policy_version 14423 (0.0008) -[2023-10-10 13:14:41,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 29523968. Throughput: 0: 1822.1, 1: 1838.8. Samples: 7387434. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-10 13:14:41,077][75634] Avg episode reward: [(0, '25.280'), (1, '25.710')] -[2023-10-10 13:14:41,319][76542] Updated weights for policy 1, policy_version 14410 (0.0007) -[2023-10-10 13:14:41,694][76542] Updated weights for policy 1, policy_version 14420 (0.0008) -[2023-10-10 13:14:42,054][76542] Updated weights for policy 1, policy_version 14430 (0.0008) -[2023-10-10 13:14:44,167][76543] Updated weights for policy 0, policy_version 14433 (0.0009) -[2023-10-10 13:14:44,535][76543] Updated weights for policy 0, policy_version 14443 (0.0010) -[2023-10-10 13:14:44,913][76543] Updated weights for policy 0, policy_version 14453 (0.0010) -[2023-10-10 13:14:45,276][76543] Updated weights for policy 0, policy_version 14463 (0.0007) -[2023-10-10 13:14:45,637][76542] Updated weights for policy 1, policy_version 14440 (0.0008) -[2023-10-10 13:14:46,005][76542] Updated weights for policy 1, policy_version 14450 (0.0007) -[2023-10-10 13:14:46,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 29589504. Throughput: 0: 1814.8, 1: 1829.6. Samples: 7408778. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:14:46,076][75634] Avg episode reward: [(0, '25.220'), (1, '25.880')] -[2023-10-10 13:14:46,367][76542] Updated weights for policy 1, policy_version 14460 (0.0008) -[2023-10-10 13:14:49,121][76543] Updated weights for policy 0, policy_version 14473 (0.0007) -[2023-10-10 13:14:49,492][76543] Updated weights for policy 0, policy_version 14483 (0.0009) -[2023-10-10 13:14:49,861][76543] Updated weights for policy 0, policy_version 14493 (0.0010) -[2023-10-10 13:14:50,122][76542] Updated weights for policy 1, policy_version 14470 (0.0008) -[2023-10-10 13:14:50,495][76542] Updated weights for policy 1, policy_version 14480 (0.0010) -[2023-10-10 13:14:50,872][76542] Updated weights for policy 1, policy_version 14490 (0.0011) -[2023-10-10 13:14:51,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 29655040. Throughput: 0: 1821.3, 1: 1842.1. Samples: 7420596. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:14:51,077][75634] Avg episode reward: [(0, '26.800'), (1, '26.220')] -[2023-10-10 13:14:53,370][76543] Updated weights for policy 0, policy_version 14503 (0.0007) -[2023-10-10 13:14:53,751][76543] Updated weights for policy 0, policy_version 14513 (0.0007) -[2023-10-10 13:14:54,128][76543] Updated weights for policy 0, policy_version 14523 (0.0008) -[2023-10-10 13:14:54,725][76542] Updated weights for policy 1, policy_version 14500 (0.0010) -[2023-10-10 13:14:55,126][76542] Updated weights for policy 1, policy_version 14510 (0.0008) -[2023-10-10 13:14:55,501][76542] Updated weights for policy 1, policy_version 14520 (0.0009) -[2023-10-10 13:14:56,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 29753344. Throughput: 0: 1820.5, 1: 1826.9. Samples: 7441658. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:14:56,077][75634] Avg episode reward: [(0, '27.410'), (1, '26.720')] -[2023-10-10 13:14:57,833][76543] Updated weights for policy 0, policy_version 14533 (0.0009) -[2023-10-10 13:14:58,230][76543] Updated weights for policy 0, policy_version 14543 (0.0009) -[2023-10-10 13:14:58,607][76543] Updated weights for policy 0, policy_version 14553 (0.0007) -[2023-10-10 13:14:59,130][76542] Updated weights for policy 1, policy_version 14530 (0.0008) -[2023-10-10 13:14:59,499][76542] Updated weights for policy 1, policy_version 14540 (0.0011) -[2023-10-10 13:14:59,856][76542] Updated weights for policy 1, policy_version 14550 (0.0008) -[2023-10-10 13:15:00,227][76542] Updated weights for policy 1, policy_version 14560 (0.0008) -[2023-10-10 13:15:01,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 29818880. Throughput: 0: 1828.4, 1: 1827.1. Samples: 7462920. Policy #0 lag: (min: 31.0, avg: 45.5, max: 63.0) -[2023-10-10 13:15:01,076][75634] Avg episode reward: [(0, '28.800'), (1, '25.650')] -[2023-10-10 13:15:02,012][76543] Updated weights for policy 0, policy_version 14563 (0.0009) -[2023-10-10 13:15:02,393][76543] Updated weights for policy 0, policy_version 14573 (0.0010) -[2023-10-10 13:15:02,779][76543] Updated weights for policy 0, policy_version 14583 (0.0008) -[2023-10-10 13:15:04,072][76542] Updated weights for policy 1, policy_version 14570 (0.0007) -[2023-10-10 13:15:04,447][76542] Updated weights for policy 1, policy_version 14580 (0.0009) -[2023-10-10 13:15:04,827][76542] Updated weights for policy 1, policy_version 14590 (0.0011) -[2023-10-10 13:15:06,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 29884416. Throughput: 0: 1820.3, 1: 1823.1. Samples: 7474314. Policy #0 lag: (min: 31.0, avg: 45.5, max: 63.0) -[2023-10-10 13:15:06,077][75634] Avg episode reward: [(0, '29.120'), (1, '28.230')] -[2023-10-10 13:15:06,079][76421] Saving new best policy, reward=28.230! -[2023-10-10 13:15:06,470][76543] Updated weights for policy 0, policy_version 14593 (0.0010) -[2023-10-10 13:15:06,835][76543] Updated weights for policy 0, policy_version 14603 (0.0010) -[2023-10-10 13:15:07,214][76543] Updated weights for policy 0, policy_version 14613 (0.0009) -[2023-10-10 13:15:07,587][76543] Updated weights for policy 0, policy_version 14623 (0.0011) -[2023-10-10 13:15:08,631][76542] Updated weights for policy 1, policy_version 14600 (0.0008) -[2023-10-10 13:15:09,004][76542] Updated weights for policy 1, policy_version 14610 (0.0007) -[2023-10-10 13:15:09,375][76542] Updated weights for policy 1, policy_version 14620 (0.0008) -[2023-10-10 13:15:11,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 29949952. Throughput: 0: 1827.7, 1: 1812.7. Samples: 7495450. Policy #0 lag: (min: 31.0, avg: 45.5, max: 63.0) -[2023-10-10 13:15:11,077][75634] Avg episode reward: [(0, '27.810'), (1, '25.910')] -[2023-10-10 13:15:11,221][76543] Updated weights for policy 0, policy_version 14633 (0.0010) -[2023-10-10 13:15:11,587][76543] Updated weights for policy 0, policy_version 14643 (0.0009) -[2023-10-10 13:15:11,966][76543] Updated weights for policy 0, policy_version 14653 (0.0007) -[2023-10-10 13:15:12,871][76542] Updated weights for policy 1, policy_version 14630 (0.0008) -[2023-10-10 13:15:13,246][76542] Updated weights for policy 1, policy_version 14640 (0.0010) -[2023-10-10 13:15:13,621][76542] Updated weights for policy 1, policy_version 14650 (0.0011) -[2023-10-10 13:15:15,735][76543] Updated weights for policy 0, policy_version 14663 (0.0009) -[2023-10-10 13:15:16,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 30015488. Throughput: 0: 1826.7, 1: 1813.7. Samples: 7518356. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-10 13:15:16,077][75634] Avg episode reward: [(0, '27.420'), (1, '25.160')] -[2023-10-10 13:15:16,115][76543] Updated weights for policy 0, policy_version 14673 (0.0009) -[2023-10-10 13:15:16,489][76543] Updated weights for policy 0, policy_version 14683 (0.0008) -[2023-10-10 13:15:17,325][76542] Updated weights for policy 1, policy_version 14660 (0.0008) -[2023-10-10 13:15:17,700][76542] Updated weights for policy 1, policy_version 14670 (0.0010) -[2023-10-10 13:15:18,064][76542] Updated weights for policy 1, policy_version 14680 (0.0010) -[2023-10-10 13:15:20,190][76543] Updated weights for policy 0, policy_version 14693 (0.0007) -[2023-10-10 13:15:20,562][76543] Updated weights for policy 0, policy_version 14703 (0.0008) -[2023-10-10 13:15:20,937][76543] Updated weights for policy 0, policy_version 14713 (0.0008) -[2023-10-10 13:15:21,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 30081024. Throughput: 0: 1827.3, 1: 1810.0. Samples: 7528240. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-10 13:15:21,076][75634] Avg episode reward: [(0, '27.090'), (1, '24.880')] -[2023-10-10 13:15:21,713][76542] Updated weights for policy 1, policy_version 14690 (0.0009) -[2023-10-10 13:15:22,079][76542] Updated weights for policy 1, policy_version 14700 (0.0010) -[2023-10-10 13:15:22,453][76542] Updated weights for policy 1, policy_version 14710 (0.0007) -[2023-10-10 13:15:22,826][76542] Updated weights for policy 1, policy_version 14720 (0.0008) -[2023-10-10 13:15:24,690][76543] Updated weights for policy 0, policy_version 14723 (0.0007) -[2023-10-10 13:15:25,074][76543] Updated weights for policy 0, policy_version 14733 (0.0008) -[2023-10-10 13:15:25,452][76543] Updated weights for policy 0, policy_version 14743 (0.0008) -[2023-10-10 13:15:26,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 30179328. Throughput: 0: 1825.1, 1: 1815.5. Samples: 7551260. Policy #0 lag: (min: 5.0, avg: 10.7, max: 37.0) -[2023-10-10 13:15:26,077][75634] Avg episode reward: [(0, '27.180'), (1, '24.570')] -[2023-10-10 13:15:26,457][76542] Updated weights for policy 1, policy_version 14730 (0.0007) -[2023-10-10 13:15:26,822][76542] Updated weights for policy 1, policy_version 14740 (0.0007) -[2023-10-10 13:15:27,183][76542] Updated weights for policy 1, policy_version 14750 (0.0008) -[2023-10-10 13:15:29,086][76543] Updated weights for policy 0, policy_version 14753 (0.0008) -[2023-10-10 13:15:29,456][76543] Updated weights for policy 0, policy_version 14763 (0.0010) -[2023-10-10 13:15:29,842][76543] Updated weights for policy 0, policy_version 14773 (0.0010) -[2023-10-10 13:15:30,213][76543] Updated weights for policy 0, policy_version 14783 (0.0010) -[2023-10-10 13:15:30,831][76542] Updated weights for policy 1, policy_version 14760 (0.0010) -[2023-10-10 13:15:31,076][75634] Fps is (10 sec: 16383.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 30244864. Throughput: 0: 1822.0, 1: 1822.5. Samples: 7572782. Policy #0 lag: (min: 5.0, avg: 10.7, max: 37.0) -[2023-10-10 13:15:31,077][75634] Avg episode reward: [(0, '28.520'), (1, '24.390')] -[2023-10-10 13:15:31,198][76542] Updated weights for policy 1, policy_version 14770 (0.0008) -[2023-10-10 13:15:31,566][76542] Updated weights for policy 1, policy_version 14780 (0.0009) -[2023-10-10 13:15:33,839][76543] Updated weights for policy 0, policy_version 14793 (0.0007) -[2023-10-10 13:15:34,216][76543] Updated weights for policy 0, policy_version 14803 (0.0008) -[2023-10-10 13:15:34,592][76543] Updated weights for policy 0, policy_version 14813 (0.0008) -[2023-10-10 13:15:35,281][76542] Updated weights for policy 1, policy_version 14790 (0.0010) -[2023-10-10 13:15:35,655][76542] Updated weights for policy 1, policy_version 14800 (0.0012) -[2023-10-10 13:15:36,024][76542] Updated weights for policy 1, policy_version 14810 (0.0008) -[2023-10-10 13:15:36,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 30310400. Throughput: 0: 1825.3, 1: 1813.8. Samples: 7584354. Policy #0 lag: (min: 5.0, avg: 10.7, max: 37.0) -[2023-10-10 13:15:36,076][75634] Avg episode reward: [(0, '27.730'), (1, '23.870')] -[2023-10-10 13:15:38,331][76543] Updated weights for policy 0, policy_version 14823 (0.0008) -[2023-10-10 13:15:38,700][76543] Updated weights for policy 0, policy_version 14833 (0.0008) -[2023-10-10 13:15:39,066][76543] Updated weights for policy 0, policy_version 14843 (0.0007) -[2023-10-10 13:15:39,737][76542] Updated weights for policy 1, policy_version 14820 (0.0008) -[2023-10-10 13:15:40,126][76542] Updated weights for policy 1, policy_version 14830 (0.0009) -[2023-10-10 13:15:40,481][76542] Updated weights for policy 1, policy_version 14840 (0.0008) -[2023-10-10 13:15:41,076][75634] Fps is (10 sec: 16384.5, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 30408704. Throughput: 0: 1821.0, 1: 1827.8. Samples: 7605852. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-10 13:15:41,076][75634] Avg episode reward: [(0, '28.080'), (1, '24.650')] -[2023-10-10 13:15:42,757][76543] Updated weights for policy 0, policy_version 14853 (0.0008) -[2023-10-10 13:15:43,146][76543] Updated weights for policy 0, policy_version 14863 (0.0011) -[2023-10-10 13:15:43,514][76543] Updated weights for policy 0, policy_version 14873 (0.0009) -[2023-10-10 13:15:44,177][76542] Updated weights for policy 1, policy_version 14850 (0.0008) -[2023-10-10 13:15:44,540][76542] Updated weights for policy 1, policy_version 14860 (0.0007) -[2023-10-10 13:15:44,910][76542] Updated weights for policy 1, policy_version 14870 (0.0010) -[2023-10-10 13:15:45,281][76542] Updated weights for policy 1, policy_version 14880 (0.0009) -[2023-10-10 13:15:46,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 30474240. Throughput: 0: 1820.4, 1: 1823.0. Samples: 7626876. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-10 13:15:46,077][75634] Avg episode reward: [(0, '26.370'), (1, '26.180')] -[2023-10-10 13:15:47,140][76543] Updated weights for policy 0, policy_version 14883 (0.0008) -[2023-10-10 13:15:47,514][76543] Updated weights for policy 0, policy_version 14893 (0.0008) -[2023-10-10 13:15:47,874][76543] Updated weights for policy 0, policy_version 14903 (0.0007) -[2023-10-10 13:15:49,073][76542] Updated weights for policy 1, policy_version 14890 (0.0007) -[2023-10-10 13:15:49,439][76542] Updated weights for policy 1, policy_version 14900 (0.0007) -[2023-10-10 13:15:49,808][76542] Updated weights for policy 1, policy_version 14910 (0.0011) -[2023-10-10 13:15:51,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 30539776. Throughput: 0: 1826.8, 1: 1818.3. Samples: 7638344. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-10 13:15:51,077][75634] Avg episode reward: [(0, '25.770'), (1, '28.980')] -[2023-10-10 13:15:51,079][76421] Saving new best policy, reward=28.980! -[2023-10-10 13:15:51,466][76543] Updated weights for policy 0, policy_version 14913 (0.0008) -[2023-10-10 13:15:51,840][76543] Updated weights for policy 0, policy_version 14923 (0.0008) -[2023-10-10 13:15:52,221][76543] Updated weights for policy 0, policy_version 14933 (0.0008) -[2023-10-10 13:15:52,586][76543] Updated weights for policy 0, policy_version 14943 (0.0007) -[2023-10-10 13:15:53,426][76542] Updated weights for policy 1, policy_version 14920 (0.0009) -[2023-10-10 13:15:53,804][76542] Updated weights for policy 1, policy_version 14930 (0.0007) -[2023-10-10 13:15:54,176][76542] Updated weights for policy 1, policy_version 14940 (0.0007) -[2023-10-10 13:15:56,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 30605312. Throughput: 0: 1827.3, 1: 1824.6. Samples: 7659784. Policy #0 lag: (min: 5.0, avg: 5.0, max: 7.0) -[2023-10-10 13:15:56,076][75634] Avg episode reward: [(0, '26.040'), (1, '29.930')] -[2023-10-10 13:15:56,077][76421] Saving new best policy, reward=29.930! -[2023-10-10 13:15:56,316][76543] Updated weights for policy 0, policy_version 14953 (0.0009) -[2023-10-10 13:15:56,688][76543] Updated weights for policy 0, policy_version 14963 (0.0008) -[2023-10-10 13:15:57,068][76543] Updated weights for policy 0, policy_version 14973 (0.0008) -[2023-10-10 13:15:57,770][76542] Updated weights for policy 1, policy_version 14950 (0.0008) -[2023-10-10 13:15:58,137][76542] Updated weights for policy 1, policy_version 14960 (0.0007) -[2023-10-10 13:15:58,516][76542] Updated weights for policy 1, policy_version 14970 (0.0008) -[2023-10-10 13:16:00,798][76543] Updated weights for policy 0, policy_version 14983 (0.0009) -[2023-10-10 13:16:01,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 30670848. Throughput: 0: 1826.0, 1: 1821.0. Samples: 7682470. Policy #0 lag: (min: 5.0, avg: 5.0, max: 7.0) -[2023-10-10 13:16:01,076][75634] Avg episode reward: [(0, '24.910'), (1, '28.560')] -[2023-10-10 13:16:01,172][76543] Updated weights for policy 0, policy_version 14993 (0.0009) -[2023-10-10 13:16:01,540][76543] Updated weights for policy 0, policy_version 15003 (0.0008) -[2023-10-10 13:16:02,290][76542] Updated weights for policy 1, policy_version 14980 (0.0008) -[2023-10-10 13:16:02,667][76542] Updated weights for policy 1, policy_version 14990 (0.0010) -[2023-10-10 13:16:03,038][76542] Updated weights for policy 1, policy_version 15000 (0.0010) -[2023-10-10 13:16:05,192][76543] Updated weights for policy 0, policy_version 15013 (0.0009) -[2023-10-10 13:16:05,562][76543] Updated weights for policy 0, policy_version 15023 (0.0008) -[2023-10-10 13:16:05,937][76543] Updated weights for policy 0, policy_version 15033 (0.0008) -[2023-10-10 13:16:06,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 30736384. Throughput: 0: 1825.4, 1: 1821.9. Samples: 7692368. Policy #0 lag: (min: 5.0, avg: 5.0, max: 7.0) -[2023-10-10 13:16:06,076][75634] Avg episode reward: [(0, '25.100'), (1, '28.080')] -[2023-10-10 13:16:06,707][76542] Updated weights for policy 1, policy_version 15010 (0.0010) -[2023-10-10 13:16:07,075][76542] Updated weights for policy 1, policy_version 15020 (0.0009) -[2023-10-10 13:16:07,440][76542] Updated weights for policy 1, policy_version 15030 (0.0008) -[2023-10-10 13:16:07,815][76542] Updated weights for policy 1, policy_version 15040 (0.0008) -[2023-10-10 13:16:09,649][76543] Updated weights for policy 0, policy_version 15043 (0.0008) -[2023-10-10 13:16:10,021][76543] Updated weights for policy 0, policy_version 15053 (0.0008) -[2023-10-10 13:16:10,391][76543] Updated weights for policy 0, policy_version 15063 (0.0007) -[2023-10-10 13:16:11,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 30834688. Throughput: 0: 1826.0, 1: 1818.0. Samples: 7715242. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:16:11,077][75634] Avg episode reward: [(0, '24.640'), (1, '26.110')] -[2023-10-10 13:16:11,645][76542] Updated weights for policy 1, policy_version 15050 (0.0007) -[2023-10-10 13:16:12,012][76542] Updated weights for policy 1, policy_version 15060 (0.0008) -[2023-10-10 13:16:12,384][76542] Updated weights for policy 1, policy_version 15070 (0.0009) -[2023-10-10 13:16:13,893][76543] Updated weights for policy 0, policy_version 15073 (0.0007) -[2023-10-10 13:16:14,260][76543] Updated weights for policy 0, policy_version 15083 (0.0008) -[2023-10-10 13:16:14,637][76543] Updated weights for policy 0, policy_version 15093 (0.0008) -[2023-10-10 13:16:15,013][76543] Updated weights for policy 0, policy_version 15103 (0.0008) -[2023-10-10 13:16:16,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 30900224. Throughput: 0: 1830.5, 1: 1813.6. Samples: 7736762. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:16:16,077][75634] Avg episode reward: [(0, '24.850'), (1, '25.210')] -[2023-10-10 13:16:16,196][76542] Updated weights for policy 1, policy_version 15080 (0.0008) -[2023-10-10 13:16:16,559][76542] Updated weights for policy 1, policy_version 15090 (0.0007) -[2023-10-10 13:16:16,925][76542] Updated weights for policy 1, policy_version 15100 (0.0010) -[2023-10-10 13:16:18,466][76543] Updated weights for policy 0, policy_version 15113 (0.0008) -[2023-10-10 13:16:18,830][76543] Updated weights for policy 0, policy_version 15123 (0.0008) -[2023-10-10 13:16:19,195][76543] Updated weights for policy 0, policy_version 15133 (0.0007) -[2023-10-10 13:16:20,743][76542] Updated weights for policy 1, policy_version 15110 (0.0010) -[2023-10-10 13:16:21,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 30965760. Throughput: 0: 1834.8, 1: 1812.3. Samples: 7748472. Policy #0 lag: (min: 24.0, avg: 50.1, max: 56.0) -[2023-10-10 13:16:21,077][75634] Avg episode reward: [(0, '25.060'), (1, '23.260')] -[2023-10-10 13:16:21,113][76542] Updated weights for policy 1, policy_version 15120 (0.0010) -[2023-10-10 13:16:21,488][76542] Updated weights for policy 1, policy_version 15130 (0.0009) -[2023-10-10 13:16:22,911][76543] Updated weights for policy 0, policy_version 15143 (0.0010) -[2023-10-10 13:16:23,286][76543] Updated weights for policy 0, policy_version 15153 (0.0009) -[2023-10-10 13:16:23,663][76543] Updated weights for policy 0, policy_version 15163 (0.0007) -[2023-10-10 13:16:25,292][76542] Updated weights for policy 1, policy_version 15140 (0.0009) -[2023-10-10 13:16:25,693][76542] Updated weights for policy 1, policy_version 15150 (0.0007) -[2023-10-10 13:16:26,059][76542] Updated weights for policy 1, policy_version 15160 (0.0008) -[2023-10-10 13:16:26,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 31031296. Throughput: 0: 1836.1, 1: 1808.0. Samples: 7769836. Policy #0 lag: (min: 24.0, avg: 50.1, max: 56.0) -[2023-10-10 13:16:26,077][75634] Avg episode reward: [(0, '25.450'), (1, '23.620')] -[2023-10-10 13:16:27,379][76543] Updated weights for policy 0, policy_version 15173 (0.0007) -[2023-10-10 13:16:27,758][76543] Updated weights for policy 0, policy_version 15183 (0.0007) -[2023-10-10 13:16:28,118][76543] Updated weights for policy 0, policy_version 15193 (0.0008) -[2023-10-10 13:16:29,842][76542] Updated weights for policy 1, policy_version 15170 (0.0010) -[2023-10-10 13:16:30,213][76542] Updated weights for policy 1, policy_version 15180 (0.0009) -[2023-10-10 13:16:30,578][76542] Updated weights for policy 1, policy_version 15190 (0.0008) -[2023-10-10 13:16:30,948][76542] Updated weights for policy 1, policy_version 15200 (0.0009) -[2023-10-10 13:16:31,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 31129600. Throughput: 0: 1846.6, 1: 1806.1. Samples: 7791250. Policy #0 lag: (min: 24.0, avg: 50.1, max: 56.0) -[2023-10-10 13:16:31,077][75634] Avg episode reward: [(0, '25.520'), (1, '23.110')] -[2023-10-10 13:16:31,088][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000015200_15564800.pth... -[2023-10-10 13:16:31,088][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000015200_15564800.pth... -[2023-10-10 13:16:31,127][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000013504_13828096.pth -[2023-10-10 13:16:31,128][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000013504_13828096.pth -[2023-10-10 13:16:31,864][76543] Updated weights for policy 0, policy_version 15203 (0.0010) -[2023-10-10 13:16:32,269][76543] Updated weights for policy 0, policy_version 15213 (0.0008) -[2023-10-10 13:16:32,646][76543] Updated weights for policy 0, policy_version 15223 (0.0008) -[2023-10-10 13:16:34,496][76542] Updated weights for policy 1, policy_version 15210 (0.0008) -[2023-10-10 13:16:34,863][76542] Updated weights for policy 1, policy_version 15220 (0.0008) -[2023-10-10 13:16:35,220][76542] Updated weights for policy 1, policy_version 15230 (0.0008) -[2023-10-10 13:16:36,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 31195136. Throughput: 0: 1838.3, 1: 1805.1. Samples: 7802298. Policy #0 lag: (min: 31.0, avg: 47.0, max: 63.0) -[2023-10-10 13:16:36,076][75634] Avg episode reward: [(0, '26.750'), (1, '24.000')] -[2023-10-10 13:16:36,200][76543] Updated weights for policy 0, policy_version 15233 (0.0008) -[2023-10-10 13:16:36,569][76543] Updated weights for policy 0, policy_version 15243 (0.0011) -[2023-10-10 13:16:36,948][76543] Updated weights for policy 0, policy_version 15253 (0.0011) -[2023-10-10 13:16:37,327][76543] Updated weights for policy 0, policy_version 15263 (0.0008) -[2023-10-10 13:16:38,888][76542] Updated weights for policy 1, policy_version 15240 (0.0008) -[2023-10-10 13:16:39,263][76542] Updated weights for policy 1, policy_version 15250 (0.0009) -[2023-10-10 13:16:39,640][76542] Updated weights for policy 1, policy_version 15260 (0.0008) -[2023-10-10 13:16:40,861][76543] Updated weights for policy 0, policy_version 15273 (0.0008) -[2023-10-10 13:16:41,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 31260672. Throughput: 0: 1840.7, 1: 1814.6. Samples: 7824270. Policy #0 lag: (min: 31.0, avg: 47.0, max: 63.0) -[2023-10-10 13:16:41,077][75634] Avg episode reward: [(0, '27.090'), (1, '24.660')] -[2023-10-10 13:16:41,232][76543] Updated weights for policy 0, policy_version 15283 (0.0007) -[2023-10-10 13:16:41,603][76543] Updated weights for policy 0, policy_version 15293 (0.0009) -[2023-10-10 13:16:43,266][76542] Updated weights for policy 1, policy_version 15270 (0.0008) -[2023-10-10 13:16:43,634][76542] Updated weights for policy 1, policy_version 15280 (0.0007) -[2023-10-10 13:16:44,009][76542] Updated weights for policy 1, policy_version 15290 (0.0010) -[2023-10-10 13:16:45,208][76543] Updated weights for policy 0, policy_version 15303 (0.0008) -[2023-10-10 13:16:45,568][76543] Updated weights for policy 0, policy_version 15313 (0.0009) -[2023-10-10 13:16:45,942][76543] Updated weights for policy 0, policy_version 15323 (0.0010) -[2023-10-10 13:16:46,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 31326208. Throughput: 0: 1840.0, 1: 1813.0. Samples: 7846858. Policy #0 lag: (min: 31.0, avg: 47.0, max: 63.0) -[2023-10-10 13:16:46,077][75634] Avg episode reward: [(0, '27.260'), (1, '24.200')] -[2023-10-10 13:16:47,658][76542] Updated weights for policy 1, policy_version 15300 (0.0009) -[2023-10-10 13:16:48,027][76542] Updated weights for policy 1, policy_version 15310 (0.0010) -[2023-10-10 13:16:48,406][76542] Updated weights for policy 1, policy_version 15320 (0.0009) -[2023-10-10 13:16:49,412][76543] Updated weights for policy 0, policy_version 15333 (0.0007) -[2023-10-10 13:16:49,795][76543] Updated weights for policy 0, policy_version 15343 (0.0009) -[2023-10-10 13:16:50,172][76543] Updated weights for policy 0, policy_version 15353 (0.0010) -[2023-10-10 13:16:51,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 31424512. Throughput: 0: 1851.9, 1: 1812.0. Samples: 7857240. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:16:51,076][75634] Avg episode reward: [(0, '27.600'), (1, '25.490')] -[2023-10-10 13:16:52,014][76542] Updated weights for policy 1, policy_version 15330 (0.0009) -[2023-10-10 13:16:52,383][76542] Updated weights for policy 1, policy_version 15340 (0.0009) -[2023-10-10 13:16:52,745][76542] Updated weights for policy 1, policy_version 15350 (0.0008) -[2023-10-10 13:16:53,111][76542] Updated weights for policy 1, policy_version 15360 (0.0010) -[2023-10-10 13:16:53,883][76543] Updated weights for policy 0, policy_version 15363 (0.0008) -[2023-10-10 13:16:54,259][76543] Updated weights for policy 0, policy_version 15373 (0.0007) -[2023-10-10 13:16:54,638][76543] Updated weights for policy 0, policy_version 15383 (0.0010) -[2023-10-10 13:16:56,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 31490048. Throughput: 0: 1842.7, 1: 1812.9. Samples: 7879744. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:16:56,077][75634] Avg episode reward: [(0, '28.250'), (1, '26.020')] -[2023-10-10 13:16:56,775][76542] Updated weights for policy 1, policy_version 15370 (0.0008) -[2023-10-10 13:16:57,141][76542] Updated weights for policy 1, policy_version 15380 (0.0007) -[2023-10-10 13:16:57,514][76542] Updated weights for policy 1, policy_version 15390 (0.0009) -[2023-10-10 13:16:58,221][76543] Updated weights for policy 0, policy_version 15393 (0.0008) -[2023-10-10 13:16:58,586][76543] Updated weights for policy 0, policy_version 15403 (0.0007) -[2023-10-10 13:16:58,961][76543] Updated weights for policy 0, policy_version 15413 (0.0007) -[2023-10-10 13:16:59,323][76543] Updated weights for policy 0, policy_version 15423 (0.0007) -[2023-10-10 13:17:01,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 31555584. Throughput: 0: 1851.4, 1: 1812.4. Samples: 7901632. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:17:01,077][75634] Avg episode reward: [(0, '29.680'), (1, '27.500')] -[2023-10-10 13:17:01,272][76542] Updated weights for policy 1, policy_version 15400 (0.0009) -[2023-10-10 13:17:01,631][76542] Updated weights for policy 1, policy_version 15410 (0.0009) -[2023-10-10 13:17:02,000][76542] Updated weights for policy 1, policy_version 15420 (0.0008) -[2023-10-10 13:17:03,038][76543] Updated weights for policy 0, policy_version 15433 (0.0010) -[2023-10-10 13:17:03,399][76543] Updated weights for policy 0, policy_version 15443 (0.0010) -[2023-10-10 13:17:03,776][76543] Updated weights for policy 0, policy_version 15453 (0.0009) -[2023-10-10 13:17:05,592][76542] Updated weights for policy 1, policy_version 15430 (0.0008) -[2023-10-10 13:17:05,961][76542] Updated weights for policy 1, policy_version 15440 (0.0010) -[2023-10-10 13:17:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 31621120. Throughput: 0: 1828.1, 1: 1814.5. Samples: 7912390. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:17:06,077][75634] Avg episode reward: [(0, '28.520'), (1, '28.280')] -[2023-10-10 13:17:06,330][76542] Updated weights for policy 1, policy_version 15450 (0.0010) -[2023-10-10 13:17:07,432][76543] Updated weights for policy 0, policy_version 15463 (0.0009) -[2023-10-10 13:17:07,807][76543] Updated weights for policy 0, policy_version 15473 (0.0010) -[2023-10-10 13:17:08,166][76543] Updated weights for policy 0, policy_version 15483 (0.0009) -[2023-10-10 13:17:09,993][76542] Updated weights for policy 1, policy_version 15460 (0.0008) -[2023-10-10 13:17:10,374][76542] Updated weights for policy 1, policy_version 15470 (0.0007) -[2023-10-10 13:17:10,730][76542] Updated weights for policy 1, policy_version 15480 (0.0009) -[2023-10-10 13:17:11,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 31719424. Throughput: 0: 1840.1, 1: 1818.0. Samples: 7934452. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:17:11,077][75634] Avg episode reward: [(0, '28.110'), (1, '29.960')] -[2023-10-10 13:17:11,079][76421] Saving new best policy, reward=29.960! -[2023-10-10 13:17:11,831][76543] Updated weights for policy 0, policy_version 15493 (0.0007) -[2023-10-10 13:17:12,207][76543] Updated weights for policy 0, policy_version 15503 (0.0007) -[2023-10-10 13:17:12,580][76543] Updated weights for policy 0, policy_version 15513 (0.0007) -[2023-10-10 13:17:14,445][76542] Updated weights for policy 1, policy_version 15490 (0.0007) -[2023-10-10 13:17:14,820][76542] Updated weights for policy 1, policy_version 15500 (0.0010) -[2023-10-10 13:17:15,182][76542] Updated weights for policy 1, policy_version 15510 (0.0009) -[2023-10-10 13:17:15,556][76542] Updated weights for policy 1, policy_version 15520 (0.0011) -[2023-10-10 13:17:16,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 31784960. Throughput: 0: 1841.3, 1: 1819.1. Samples: 7955966. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-10-10 13:17:16,077][75634] Avg episode reward: [(0, '27.940'), (1, '30.660')] -[2023-10-10 13:17:16,086][76421] Saving new best policy, reward=30.660! -[2023-10-10 13:17:16,196][76543] Updated weights for policy 0, policy_version 15523 (0.0007) -[2023-10-10 13:17:16,575][76543] Updated weights for policy 0, policy_version 15533 (0.0008) -[2023-10-10 13:17:16,943][76543] Updated weights for policy 0, policy_version 15543 (0.0008) -[2023-10-10 13:17:19,153][76542] Updated weights for policy 1, policy_version 15530 (0.0008) -[2023-10-10 13:17:19,527][76542] Updated weights for policy 1, policy_version 15540 (0.0010) -[2023-10-10 13:17:19,895][76542] Updated weights for policy 1, policy_version 15550 (0.0010) -[2023-10-10 13:17:20,608][76543] Updated weights for policy 0, policy_version 15553 (0.0007) -[2023-10-10 13:17:21,022][76543] Updated weights for policy 0, policy_version 15563 (0.0008) -[2023-10-10 13:17:21,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 31850496. Throughput: 0: 1845.0, 1: 1828.7. Samples: 7967612. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-10-10 13:17:21,077][75634] Avg episode reward: [(0, '29.130'), (1, '29.330')] -[2023-10-10 13:17:21,404][76543] Updated weights for policy 0, policy_version 15573 (0.0010) -[2023-10-10 13:17:21,769][76543] Updated weights for policy 0, policy_version 15583 (0.0009) -[2023-10-10 13:17:23,632][76542] Updated weights for policy 1, policy_version 15560 (0.0010) -[2023-10-10 13:17:24,001][76542] Updated weights for policy 1, policy_version 15570 (0.0007) -[2023-10-10 13:17:24,373][76542] Updated weights for policy 1, policy_version 15580 (0.0007) -[2023-10-10 13:17:25,264][76543] Updated weights for policy 0, policy_version 15593 (0.0008) -[2023-10-10 13:17:25,636][76543] Updated weights for policy 0, policy_version 15603 (0.0007) -[2023-10-10 13:17:26,013][76543] Updated weights for policy 0, policy_version 15613 (0.0008) -[2023-10-10 13:17:26,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 31916032. Throughput: 0: 1844.0, 1: 1822.2. Samples: 7989252. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-10-10 13:17:26,077][75634] Avg episode reward: [(0, '28.710'), (1, '28.220')] -[2023-10-10 13:17:27,924][76542] Updated weights for policy 1, policy_version 15590 (0.0009) -[2023-10-10 13:17:28,289][76542] Updated weights for policy 1, policy_version 15600 (0.0010) -[2023-10-10 13:17:28,665][76542] Updated weights for policy 1, policy_version 15610 (0.0009) -[2023-10-10 13:17:29,726][76543] Updated weights for policy 0, policy_version 15623 (0.0008) -[2023-10-10 13:17:30,106][76543] Updated weights for policy 0, policy_version 15633 (0.0011) -[2023-10-10 13:17:30,477][76543] Updated weights for policy 0, policy_version 15643 (0.0009) -[2023-10-10 13:17:31,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 32014336. Throughput: 0: 1826.4, 1: 1824.8. Samples: 8011164. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-10 13:17:31,077][75634] Avg episode reward: [(0, '28.300'), (1, '27.250')] -[2023-10-10 13:17:32,317][76542] Updated weights for policy 1, policy_version 15620 (0.0009) -[2023-10-10 13:17:32,691][76542] Updated weights for policy 1, policy_version 15630 (0.0008) -[2023-10-10 13:17:33,057][76542] Updated weights for policy 1, policy_version 15640 (0.0007) -[2023-10-10 13:17:34,044][76543] Updated weights for policy 0, policy_version 15653 (0.0009) -[2023-10-10 13:17:34,417][76543] Updated weights for policy 0, policy_version 15663 (0.0008) -[2023-10-10 13:17:34,784][76543] Updated weights for policy 0, policy_version 15673 (0.0008) -[2023-10-10 13:17:36,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 32079872. Throughput: 0: 1839.5, 1: 1827.2. Samples: 8022244. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-10 13:17:36,077][75634] Avg episode reward: [(0, '27.660'), (1, '26.100')] -[2023-10-10 13:17:36,800][76542] Updated weights for policy 1, policy_version 15650 (0.0008) -[2023-10-10 13:17:37,161][76542] Updated weights for policy 1, policy_version 15660 (0.0008) -[2023-10-10 13:17:37,533][76542] Updated weights for policy 1, policy_version 15670 (0.0010) -[2023-10-10 13:17:37,900][76542] Updated weights for policy 1, policy_version 15680 (0.0008) -[2023-10-10 13:17:38,408][76543] Updated weights for policy 0, policy_version 15683 (0.0008) -[2023-10-10 13:17:38,772][76543] Updated weights for policy 0, policy_version 15693 (0.0008) -[2023-10-10 13:17:39,159][76543] Updated weights for policy 0, policy_version 15703 (0.0008) -[2023-10-10 13:17:41,076][75634] Fps is (10 sec: 13107.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 32145408. Throughput: 0: 1823.2, 1: 1822.4. Samples: 8043794. Policy #0 lag: (min: 1.0, avg: 4.4, max: 33.0) -[2023-10-10 13:17:41,076][75634] Avg episode reward: [(0, '27.920'), (1, '25.490')] -[2023-10-10 13:17:41,712][76542] Updated weights for policy 1, policy_version 15690 (0.0007) -[2023-10-10 13:17:42,087][76542] Updated weights for policy 1, policy_version 15700 (0.0008) -[2023-10-10 13:17:42,463][76542] Updated weights for policy 1, policy_version 15710 (0.0008) -[2023-10-10 13:17:42,879][76543] Updated weights for policy 0, policy_version 15713 (0.0008) -[2023-10-10 13:17:43,258][76543] Updated weights for policy 0, policy_version 15723 (0.0010) -[2023-10-10 13:17:43,621][76543] Updated weights for policy 0, policy_version 15733 (0.0010) -[2023-10-10 13:17:43,988][76543] Updated weights for policy 0, policy_version 15743 (0.0009) -[2023-10-10 13:17:46,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 32210944. Throughput: 0: 1835.6, 1: 1822.1. Samples: 8066230. Policy #0 lag: (min: 1.0, avg: 4.4, max: 33.0) -[2023-10-10 13:17:46,077][75634] Avg episode reward: [(0, '27.140'), (1, '26.990')] -[2023-10-10 13:17:46,324][76542] Updated weights for policy 1, policy_version 15720 (0.0010) -[2023-10-10 13:17:46,692][76542] Updated weights for policy 1, policy_version 15730 (0.0010) -[2023-10-10 13:17:47,057][76542] Updated weights for policy 1, policy_version 15740 (0.0010) -[2023-10-10 13:17:47,663][76543] Updated weights for policy 0, policy_version 15753 (0.0007) -[2023-10-10 13:17:48,037][76543] Updated weights for policy 0, policy_version 15763 (0.0008) -[2023-10-10 13:17:48,412][76543] Updated weights for policy 0, policy_version 15773 (0.0008) -[2023-10-10 13:17:50,759][76542] Updated weights for policy 1, policy_version 15750 (0.0010) -[2023-10-10 13:17:51,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 32276480. Throughput: 0: 1830.8, 1: 1823.5. Samples: 8076834. Policy #0 lag: (min: 1.0, avg: 4.4, max: 33.0) -[2023-10-10 13:17:51,077][75634] Avg episode reward: [(0, '25.710'), (1, '25.740')] -[2023-10-10 13:17:51,119][76542] Updated weights for policy 1, policy_version 15760 (0.0009) -[2023-10-10 13:17:51,491][76542] Updated weights for policy 1, policy_version 15770 (0.0007) -[2023-10-10 13:17:52,118][76543] Updated weights for policy 0, policy_version 15783 (0.0008) -[2023-10-10 13:17:52,489][76543] Updated weights for policy 0, policy_version 15793 (0.0009) -[2023-10-10 13:17:52,866][76543] Updated weights for policy 0, policy_version 15803 (0.0010) -[2023-10-10 13:17:55,168][76542] Updated weights for policy 1, policy_version 15780 (0.0007) -[2023-10-10 13:17:55,574][76542] Updated weights for policy 1, policy_version 15790 (0.0007) -[2023-10-10 13:17:55,936][76542] Updated weights for policy 1, policy_version 15800 (0.0010) -[2023-10-10 13:17:56,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 32342016. Throughput: 0: 1838.0, 1: 1823.4. Samples: 8099216. Policy #0 lag: (min: 2.0, avg: 2.4, max: 12.0) -[2023-10-10 13:17:56,077][75634] Avg episode reward: [(0, '26.310'), (1, '26.150')] -[2023-10-10 13:17:56,508][76543] Updated weights for policy 0, policy_version 15813 (0.0008) -[2023-10-10 13:17:56,876][76543] Updated weights for policy 0, policy_version 15823 (0.0009) -[2023-10-10 13:17:57,249][76543] Updated weights for policy 0, policy_version 15833 (0.0011) -[2023-10-10 13:17:59,485][76542] Updated weights for policy 1, policy_version 15810 (0.0010) -[2023-10-10 13:17:59,858][76542] Updated weights for policy 1, policy_version 15820 (0.0010) -[2023-10-10 13:18:00,236][76542] Updated weights for policy 1, policy_version 15830 (0.0009) -[2023-10-10 13:18:00,608][76542] Updated weights for policy 1, policy_version 15840 (0.0008) -[2023-10-10 13:18:01,072][76543] Updated weights for policy 0, policy_version 15843 (0.0010) -[2023-10-10 13:18:01,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 32440320. Throughput: 0: 1830.7, 1: 1823.4. Samples: 8120402. Policy #0 lag: (min: 2.0, avg: 2.4, max: 12.0) -[2023-10-10 13:18:01,076][75634] Avg episode reward: [(0, '24.750'), (1, '26.040')] -[2023-10-10 13:18:01,444][76543] Updated weights for policy 0, policy_version 15853 (0.0007) -[2023-10-10 13:18:01,813][76543] Updated weights for policy 0, policy_version 15863 (0.0007) -[2023-10-10 13:18:04,203][76542] Updated weights for policy 1, policy_version 15850 (0.0008) -[2023-10-10 13:18:04,576][76542] Updated weights for policy 1, policy_version 15860 (0.0009) -[2023-10-10 13:18:04,946][76542] Updated weights for policy 1, policy_version 15870 (0.0009) -[2023-10-10 13:18:05,614][76543] Updated weights for policy 0, policy_version 15873 (0.0007) -[2023-10-10 13:18:05,992][76543] Updated weights for policy 0, policy_version 15883 (0.0007) -[2023-10-10 13:18:06,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 32505856. Throughput: 0: 1828.2, 1: 1821.8. Samples: 8131860. Policy #0 lag: (min: 2.0, avg: 2.4, max: 12.0) -[2023-10-10 13:18:06,077][75634] Avg episode reward: [(0, '23.910'), (1, '26.950')] -[2023-10-10 13:18:06,361][76543] Updated weights for policy 0, policy_version 15893 (0.0008) -[2023-10-10 13:18:06,730][76543] Updated weights for policy 0, policy_version 15903 (0.0007) -[2023-10-10 13:18:08,636][76542] Updated weights for policy 1, policy_version 15880 (0.0008) -[2023-10-10 13:18:08,991][76542] Updated weights for policy 1, policy_version 15890 (0.0007) -[2023-10-10 13:18:09,365][76542] Updated weights for policy 1, policy_version 15900 (0.0009) -[2023-10-10 13:18:10,279][76543] Updated weights for policy 0, policy_version 15913 (0.0007) -[2023-10-10 13:18:10,643][76543] Updated weights for policy 0, policy_version 15923 (0.0010) -[2023-10-10 13:18:11,034][76543] Updated weights for policy 0, policy_version 15933 (0.0010) -[2023-10-10 13:18:11,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 32571392. Throughput: 0: 1821.8, 1: 1818.8. Samples: 8153076. Policy #0 lag: (min: 0.0, avg: 27.8, max: 32.0) -[2023-10-10 13:18:11,077][75634] Avg episode reward: [(0, '24.200'), (1, '24.410')] -[2023-10-10 13:18:13,133][76542] Updated weights for policy 1, policy_version 15910 (0.0007) -[2023-10-10 13:18:13,506][76542] Updated weights for policy 1, policy_version 15920 (0.0008) -[2023-10-10 13:18:13,882][76542] Updated weights for policy 1, policy_version 15930 (0.0011) -[2023-10-10 13:18:14,698][76543] Updated weights for policy 0, policy_version 15943 (0.0011) -[2023-10-10 13:18:15,070][76543] Updated weights for policy 0, policy_version 15953 (0.0007) -[2023-10-10 13:18:15,449][76543] Updated weights for policy 0, policy_version 15963 (0.0007) -[2023-10-10 13:18:16,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 32669696. Throughput: 0: 1822.4, 1: 1817.4. Samples: 8174956. Policy #0 lag: (min: 0.0, avg: 27.8, max: 32.0) -[2023-10-10 13:18:16,077][75634] Avg episode reward: [(0, '24.450'), (1, '23.700')] -[2023-10-10 13:18:17,727][76542] Updated weights for policy 1, policy_version 15940 (0.0010) -[2023-10-10 13:18:18,102][76542] Updated weights for policy 1, policy_version 15950 (0.0010) -[2023-10-10 13:18:18,469][76542] Updated weights for policy 1, policy_version 15960 (0.0010) -[2023-10-10 13:18:19,098][76543] Updated weights for policy 0, policy_version 15973 (0.0007) -[2023-10-10 13:18:19,475][76543] Updated weights for policy 0, policy_version 15983 (0.0010) -[2023-10-10 13:18:19,857][76543] Updated weights for policy 0, policy_version 15993 (0.0010) -[2023-10-10 13:18:21,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 32735232. Throughput: 0: 1822.8, 1: 1812.6. Samples: 8185840. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-10 13:18:21,076][75634] Avg episode reward: [(0, '23.980'), (1, '24.710')] -[2023-10-10 13:18:22,220][76542] Updated weights for policy 1, policy_version 15970 (0.0008) -[2023-10-10 13:18:22,583][76542] Updated weights for policy 1, policy_version 15980 (0.0011) -[2023-10-10 13:18:22,957][76542] Updated weights for policy 1, policy_version 15990 (0.0008) -[2023-10-10 13:18:23,333][76542] Updated weights for policy 1, policy_version 16000 (0.0009) -[2023-10-10 13:18:23,551][76543] Updated weights for policy 0, policy_version 16003 (0.0009) -[2023-10-10 13:18:23,929][76543] Updated weights for policy 0, policy_version 16013 (0.0009) -[2023-10-10 13:18:24,316][76543] Updated weights for policy 0, policy_version 16023 (0.0010) -[2023-10-10 13:18:26,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 32800768. Throughput: 0: 1823.0, 1: 1813.1. Samples: 8207418. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-10 13:18:26,076][75634] Avg episode reward: [(0, '24.160'), (1, '26.140')] -[2023-10-10 13:18:26,985][76542] Updated weights for policy 1, policy_version 16010 (0.0008) -[2023-10-10 13:18:27,358][76542] Updated weights for policy 1, policy_version 16020 (0.0009) -[2023-10-10 13:18:27,732][76542] Updated weights for policy 1, policy_version 16030 (0.0008) -[2023-10-10 13:18:28,048][76543] Updated weights for policy 0, policy_version 16033 (0.0010) -[2023-10-10 13:18:28,423][76543] Updated weights for policy 0, policy_version 16043 (0.0008) -[2023-10-10 13:18:28,795][76543] Updated weights for policy 0, policy_version 16053 (0.0008) -[2023-10-10 13:18:29,176][76543] Updated weights for policy 0, policy_version 16063 (0.0009) -[2023-10-10 13:18:31,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 32866304. Throughput: 0: 1817.9, 1: 1814.0. Samples: 8229664. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-10 13:18:31,077][75634] Avg episode reward: [(0, '23.520'), (1, '26.650')] -[2023-10-10 13:18:31,087][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000016064_16449536.pth... -[2023-10-10 13:18:31,121][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000014368_14712832.pth -[2023-10-10 13:18:31,369][76542] Updated weights for policy 1, policy_version 16040 (0.0007) -[2023-10-10 13:18:31,736][76542] Updated weights for policy 1, policy_version 16050 (0.0007) -[2023-10-10 13:18:32,107][76542] Updated weights for policy 1, policy_version 16060 (0.0008) -[2023-10-10 13:18:32,249][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000016064_16449536.pth... -[2023-10-10 13:18:32,288][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000014336_14680064.pth -[2023-10-10 13:18:32,814][76543] Updated weights for policy 0, policy_version 16073 (0.0007) -[2023-10-10 13:18:33,183][76543] Updated weights for policy 0, policy_version 16083 (0.0008) -[2023-10-10 13:18:33,566][76543] Updated weights for policy 0, policy_version 16093 (0.0008) -[2023-10-10 13:18:35,694][76542] Updated weights for policy 1, policy_version 16070 (0.0009) -[2023-10-10 13:18:36,060][76542] Updated weights for policy 1, policy_version 16080 (0.0009) -[2023-10-10 13:18:36,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 32931840. Throughput: 0: 1817.1, 1: 1810.5. Samples: 8240072. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:18:36,076][75634] Avg episode reward: [(0, '24.120'), (1, '25.770')] -[2023-10-10 13:18:36,428][76542] Updated weights for policy 1, policy_version 16090 (0.0008) -[2023-10-10 13:18:37,040][76543] Updated weights for policy 0, policy_version 16103 (0.0010) -[2023-10-10 13:18:37,417][76543] Updated weights for policy 0, policy_version 16113 (0.0010) -[2023-10-10 13:18:37,795][76543] Updated weights for policy 0, policy_version 16123 (0.0008) -[2023-10-10 13:18:40,233][76542] Updated weights for policy 1, policy_version 16100 (0.0007) -[2023-10-10 13:18:40,637][76542] Updated weights for policy 1, policy_version 16110 (0.0009) -[2023-10-10 13:18:40,998][76542] Updated weights for policy 1, policy_version 16120 (0.0009) -[2023-10-10 13:18:41,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 32997376. Throughput: 0: 1818.5, 1: 1807.9. Samples: 8262406. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:18:41,077][75634] Avg episode reward: [(0, '24.530'), (1, '26.240')] -[2023-10-10 13:18:41,604][76543] Updated weights for policy 0, policy_version 16133 (0.0009) -[2023-10-10 13:18:41,987][76543] Updated weights for policy 0, policy_version 16143 (0.0007) -[2023-10-10 13:18:42,363][76543] Updated weights for policy 0, policy_version 16153 (0.0011) -[2023-10-10 13:18:44,473][76542] Updated weights for policy 1, policy_version 16130 (0.0009) -[2023-10-10 13:18:44,846][76542] Updated weights for policy 1, policy_version 16140 (0.0007) -[2023-10-10 13:18:45,219][76542] Updated weights for policy 1, policy_version 16150 (0.0010) -[2023-10-10 13:18:45,593][76542] Updated weights for policy 1, policy_version 16160 (0.0008) -[2023-10-10 13:18:45,925][76543] Updated weights for policy 0, policy_version 16163 (0.0010) -[2023-10-10 13:18:46,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 33095680. Throughput: 0: 1819.5, 1: 1811.7. Samples: 8283806. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:18:46,076][75634] Avg episode reward: [(0, '24.240'), (1, '28.370')] -[2023-10-10 13:18:46,297][76543] Updated weights for policy 0, policy_version 16173 (0.0007) -[2023-10-10 13:18:46,667][76543] Updated weights for policy 0, policy_version 16183 (0.0010) -[2023-10-10 13:18:49,378][76542] Updated weights for policy 1, policy_version 16170 (0.0008) -[2023-10-10 13:18:49,737][76542] Updated weights for policy 1, policy_version 16180 (0.0007) -[2023-10-10 13:18:50,108][76542] Updated weights for policy 1, policy_version 16190 (0.0007) -[2023-10-10 13:18:50,323][76543] Updated weights for policy 0, policy_version 16193 (0.0009) -[2023-10-10 13:18:50,692][76543] Updated weights for policy 0, policy_version 16203 (0.0008) -[2023-10-10 13:18:51,060][76543] Updated weights for policy 0, policy_version 16213 (0.0009) -[2023-10-10 13:18:51,076][75634] Fps is (10 sec: 16384.5, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 33161216. Throughput: 0: 1819.7, 1: 1810.6. Samples: 8295224. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:18:51,076][75634] Avg episode reward: [(0, '26.020'), (1, '30.240')] -[2023-10-10 13:18:51,433][76543] Updated weights for policy 0, policy_version 16223 (0.0009) -[2023-10-10 13:18:53,650][76542] Updated weights for policy 1, policy_version 16200 (0.0008) -[2023-10-10 13:18:54,013][76542] Updated weights for policy 1, policy_version 16210 (0.0007) -[2023-10-10 13:18:54,383][76542] Updated weights for policy 1, policy_version 16220 (0.0010) -[2023-10-10 13:18:55,142][76543] Updated weights for policy 0, policy_version 16233 (0.0009) -[2023-10-10 13:18:55,514][76543] Updated weights for policy 0, policy_version 16243 (0.0007) -[2023-10-10 13:18:55,887][76543] Updated weights for policy 0, policy_version 16253 (0.0007) -[2023-10-10 13:18:56,076][75634] Fps is (10 sec: 16383.8, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 33259520. Throughput: 0: 1824.0, 1: 1811.2. Samples: 8316660. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:18:56,077][75634] Avg episode reward: [(0, '24.630'), (1, '29.650')] -[2023-10-10 13:18:58,035][76542] Updated weights for policy 1, policy_version 16230 (0.0011) -[2023-10-10 13:18:58,401][76542] Updated weights for policy 1, policy_version 16240 (0.0008) -[2023-10-10 13:18:58,779][76542] Updated weights for policy 1, policy_version 16250 (0.0010) -[2023-10-10 13:18:59,689][76543] Updated weights for policy 0, policy_version 16263 (0.0008) -[2023-10-10 13:19:00,061][76543] Updated weights for policy 0, policy_version 16273 (0.0010) -[2023-10-10 13:19:00,443][76543] Updated weights for policy 0, policy_version 16283 (0.0010) -[2023-10-10 13:19:01,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 33325056. Throughput: 0: 1814.9, 1: 1820.0. Samples: 8338528. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-10 13:19:01,076][75634] Avg episode reward: [(0, '26.060'), (1, '28.190')] -[2023-10-10 13:19:02,527][76542] Updated weights for policy 1, policy_version 16260 (0.0010) -[2023-10-10 13:19:02,894][76542] Updated weights for policy 1, policy_version 16270 (0.0009) -[2023-10-10 13:19:03,265][76542] Updated weights for policy 1, policy_version 16280 (0.0007) -[2023-10-10 13:19:04,197][76543] Updated weights for policy 0, policy_version 16293 (0.0008) -[2023-10-10 13:19:04,561][76543] Updated weights for policy 0, policy_version 16303 (0.0009) -[2023-10-10 13:19:04,937][76543] Updated weights for policy 0, policy_version 16313 (0.0008) -[2023-10-10 13:19:06,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 33390592. Throughput: 0: 1816.0, 1: 1818.2. Samples: 8349376. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-10 13:19:06,077][75634] Avg episode reward: [(0, '26.480'), (1, '27.620')] -[2023-10-10 13:19:06,974][76542] Updated weights for policy 1, policy_version 16290 (0.0010) -[2023-10-10 13:19:07,340][76542] Updated weights for policy 1, policy_version 16300 (0.0009) -[2023-10-10 13:19:07,706][76542] Updated weights for policy 1, policy_version 16310 (0.0008) -[2023-10-10 13:19:08,081][76542] Updated weights for policy 1, policy_version 16320 (0.0009) -[2023-10-10 13:19:08,672][76543] Updated weights for policy 0, policy_version 16323 (0.0008) -[2023-10-10 13:19:09,043][76543] Updated weights for policy 0, policy_version 16333 (0.0008) -[2023-10-10 13:19:09,407][76543] Updated weights for policy 0, policy_version 16343 (0.0009) -[2023-10-10 13:19:11,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 33456128. Throughput: 0: 1819.4, 1: 1826.3. Samples: 8371478. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-10 13:19:11,077][75634] Avg episode reward: [(0, '27.480'), (1, '27.950')] -[2023-10-10 13:19:11,871][76542] Updated weights for policy 1, policy_version 16330 (0.0007) -[2023-10-10 13:19:12,245][76542] Updated weights for policy 1, policy_version 16340 (0.0007) -[2023-10-10 13:19:12,625][76542] Updated weights for policy 1, policy_version 16350 (0.0008) -[2023-10-10 13:19:12,987][76543] Updated weights for policy 0, policy_version 16353 (0.0008) -[2023-10-10 13:19:13,360][76543] Updated weights for policy 0, policy_version 16363 (0.0010) -[2023-10-10 13:19:13,727][76543] Updated weights for policy 0, policy_version 16373 (0.0007) -[2023-10-10 13:19:14,100][76543] Updated weights for policy 0, policy_version 16383 (0.0007) -[2023-10-10 13:19:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 33521664. Throughput: 0: 1817.1, 1: 1819.9. Samples: 8393326. Policy #0 lag: (min: 8.0, avg: 35.2, max: 40.0) -[2023-10-10 13:19:16,077][75634] Avg episode reward: [(0, '31.780'), (1, '28.540')] -[2023-10-10 13:19:16,087][76362] Saving new best policy, reward=31.780! -[2023-10-10 13:19:16,304][76542] Updated weights for policy 1, policy_version 16360 (0.0009) -[2023-10-10 13:19:16,686][76542] Updated weights for policy 1, policy_version 16370 (0.0007) -[2023-10-10 13:19:17,060][76542] Updated weights for policy 1, policy_version 16380 (0.0008) -[2023-10-10 13:19:17,795][76543] Updated weights for policy 0, policy_version 16393 (0.0010) -[2023-10-10 13:19:18,158][76543] Updated weights for policy 0, policy_version 16403 (0.0008) -[2023-10-10 13:19:18,516][76543] Updated weights for policy 0, policy_version 16413 (0.0008) -[2023-10-10 13:19:20,794][76542] Updated weights for policy 1, policy_version 16390 (0.0008) -[2023-10-10 13:19:21,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 33587200. Throughput: 0: 1819.5, 1: 1819.1. Samples: 8403808. Policy #0 lag: (min: 8.0, avg: 35.2, max: 40.0) -[2023-10-10 13:19:21,076][75634] Avg episode reward: [(0, '32.600'), (1, '28.140')] -[2023-10-10 13:19:21,077][76362] Saving new best policy, reward=32.600! -[2023-10-10 13:19:21,171][76542] Updated weights for policy 1, policy_version 16400 (0.0008) -[2023-10-10 13:19:21,538][76542] Updated weights for policy 1, policy_version 16410 (0.0008) -[2023-10-10 13:19:22,170][76543] Updated weights for policy 0, policy_version 16423 (0.0008) -[2023-10-10 13:19:22,533][76543] Updated weights for policy 0, policy_version 16433 (0.0010) -[2023-10-10 13:19:22,914][76543] Updated weights for policy 0, policy_version 16443 (0.0011) -[2023-10-10 13:19:25,315][76542] Updated weights for policy 1, policy_version 16420 (0.0009) -[2023-10-10 13:19:25,715][76542] Updated weights for policy 1, policy_version 16430 (0.0009) -[2023-10-10 13:19:26,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 33652736. Throughput: 0: 1818.2, 1: 1816.9. Samples: 8425986. Policy #0 lag: (min: 8.0, avg: 35.2, max: 40.0) -[2023-10-10 13:19:26,076][75634] Avg episode reward: [(0, '30.530'), (1, '28.330')] -[2023-10-10 13:19:26,080][76542] Updated weights for policy 1, policy_version 16440 (0.0007) -[2023-10-10 13:19:26,576][76543] Updated weights for policy 0, policy_version 16453 (0.0010) -[2023-10-10 13:19:26,948][76543] Updated weights for policy 0, policy_version 16463 (0.0007) -[2023-10-10 13:19:27,330][76543] Updated weights for policy 0, policy_version 16473 (0.0010) -[2023-10-10 13:19:29,690][76542] Updated weights for policy 1, policy_version 16450 (0.0009) -[2023-10-10 13:19:30,055][76542] Updated weights for policy 1, policy_version 16460 (0.0008) -[2023-10-10 13:19:30,426][76542] Updated weights for policy 1, policy_version 16470 (0.0007) -[2023-10-10 13:19:30,788][76542] Updated weights for policy 1, policy_version 16480 (0.0008) -[2023-10-10 13:19:31,027][76543] Updated weights for policy 0, policy_version 16483 (0.0008) -[2023-10-10 13:19:31,076][75634] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 33751040. Throughput: 0: 1822.2, 1: 1819.4. Samples: 8447676. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) -[2023-10-10 13:19:31,077][75634] Avg episode reward: [(0, '30.920'), (1, '27.120')] -[2023-10-10 13:19:31,403][76543] Updated weights for policy 0, policy_version 16493 (0.0009) -[2023-10-10 13:19:31,782][76543] Updated weights for policy 0, policy_version 16503 (0.0011) -[2023-10-10 13:19:34,352][76542] Updated weights for policy 1, policy_version 16490 (0.0008) -[2023-10-10 13:19:34,714][76542] Updated weights for policy 1, policy_version 16500 (0.0008) -[2023-10-10 13:19:35,087][76542] Updated weights for policy 1, policy_version 16510 (0.0010) -[2023-10-10 13:19:35,432][76543] Updated weights for policy 0, policy_version 16513 (0.0007) -[2023-10-10 13:19:35,803][76543] Updated weights for policy 0, policy_version 16523 (0.0009) -[2023-10-10 13:19:36,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 33816576. Throughput: 0: 1823.4, 1: 1816.7. Samples: 8459028. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) -[2023-10-10 13:19:36,076][75634] Avg episode reward: [(0, '30.330'), (1, '28.970')] -[2023-10-10 13:19:36,179][76543] Updated weights for policy 0, policy_version 16533 (0.0009) -[2023-10-10 13:19:36,561][76543] Updated weights for policy 0, policy_version 16543 (0.0008) -[2023-10-10 13:19:38,786][76542] Updated weights for policy 1, policy_version 16520 (0.0007) -[2023-10-10 13:19:39,157][76542] Updated weights for policy 1, policy_version 16530 (0.0009) -[2023-10-10 13:19:39,524][76542] Updated weights for policy 1, policy_version 16540 (0.0008) -[2023-10-10 13:19:40,271][76543] Updated weights for policy 0, policy_version 16553 (0.0008) -[2023-10-10 13:19:40,644][76543] Updated weights for policy 0, policy_version 16563 (0.0009) -[2023-10-10 13:19:41,017][76543] Updated weights for policy 0, policy_version 16573 (0.0009) -[2023-10-10 13:19:41,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 33882112. Throughput: 0: 1826.0, 1: 1817.2. Samples: 8480600. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) -[2023-10-10 13:19:41,076][75634] Avg episode reward: [(0, '28.860'), (1, '29.670')] -[2023-10-10 13:19:43,165][76542] Updated weights for policy 1, policy_version 16550 (0.0008) -[2023-10-10 13:19:43,545][76542] Updated weights for policy 1, policy_version 16560 (0.0008) -[2023-10-10 13:19:43,919][76542] Updated weights for policy 1, policy_version 16570 (0.0008) -[2023-10-10 13:19:44,524][76543] Updated weights for policy 0, policy_version 16583 (0.0008) -[2023-10-10 13:19:44,892][76543] Updated weights for policy 0, policy_version 16593 (0.0010) -[2023-10-10 13:19:45,263][76543] Updated weights for policy 0, policy_version 16603 (0.0011) -[2023-10-10 13:19:46,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 33980416. Throughput: 0: 1829.5, 1: 1816.2. Samples: 8502584. Policy #0 lag: (min: 9.0, avg: 19.0, max: 41.0) -[2023-10-10 13:19:46,076][75634] Avg episode reward: [(0, '24.820'), (1, '29.720')] -[2023-10-10 13:19:47,653][76542] Updated weights for policy 1, policy_version 16580 (0.0008) -[2023-10-10 13:19:48,015][76542] Updated weights for policy 1, policy_version 16590 (0.0010) -[2023-10-10 13:19:48,382][76542] Updated weights for policy 1, policy_version 16600 (0.0010) -[2023-10-10 13:19:49,000][76543] Updated weights for policy 0, policy_version 16613 (0.0007) -[2023-10-10 13:19:49,360][76543] Updated weights for policy 0, policy_version 16623 (0.0008) -[2023-10-10 13:19:49,728][76543] Updated weights for policy 0, policy_version 16633 (0.0008) -[2023-10-10 13:19:51,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 34045952. Throughput: 0: 1831.6, 1: 1818.5. Samples: 8513632. Policy #0 lag: (min: 9.0, avg: 19.0, max: 41.0) -[2023-10-10 13:19:51,076][75634] Avg episode reward: [(0, '25.190'), (1, '26.980')] -[2023-10-10 13:19:52,134][76542] Updated weights for policy 1, policy_version 16610 (0.0007) -[2023-10-10 13:19:52,508][76542] Updated weights for policy 1, policy_version 16620 (0.0007) -[2023-10-10 13:19:52,876][76542] Updated weights for policy 1, policy_version 16630 (0.0009) -[2023-10-10 13:19:53,246][76542] Updated weights for policy 1, policy_version 16640 (0.0008) -[2023-10-10 13:19:53,364][76543] Updated weights for policy 0, policy_version 16643 (0.0009) -[2023-10-10 13:19:53,732][76543] Updated weights for policy 0, policy_version 16653 (0.0007) -[2023-10-10 13:19:54,111][76543] Updated weights for policy 0, policy_version 16663 (0.0008) -[2023-10-10 13:19:56,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 34111488. Throughput: 0: 1826.9, 1: 1811.7. Samples: 8535214. Policy #0 lag: (min: 23.0, avg: 31.0, max: 55.0) -[2023-10-10 13:19:56,076][75634] Avg episode reward: [(0, '25.420'), (1, '26.380')] -[2023-10-10 13:19:56,830][76542] Updated weights for policy 1, policy_version 16650 (0.0008) -[2023-10-10 13:19:57,204][76542] Updated weights for policy 1, policy_version 16660 (0.0008) -[2023-10-10 13:19:57,571][76542] Updated weights for policy 1, policy_version 16670 (0.0007) -[2023-10-10 13:19:57,738][76543] Updated weights for policy 0, policy_version 16673 (0.0009) -[2023-10-10 13:19:58,105][76543] Updated weights for policy 0, policy_version 16683 (0.0010) -[2023-10-10 13:19:58,480][76543] Updated weights for policy 0, policy_version 16693 (0.0008) -[2023-10-10 13:19:58,855][76543] Updated weights for policy 0, policy_version 16703 (0.0009) -[2023-10-10 13:20:01,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 34177024. Throughput: 0: 1835.5, 1: 1823.0. Samples: 8557960. Policy #0 lag: (min: 23.0, avg: 31.0, max: 55.0) -[2023-10-10 13:20:01,076][75634] Avg episode reward: [(0, '26.910'), (1, '27.370')] -[2023-10-10 13:20:01,301][76542] Updated weights for policy 1, policy_version 16680 (0.0008) -[2023-10-10 13:20:01,668][76542] Updated weights for policy 1, policy_version 16690 (0.0010) -[2023-10-10 13:20:02,043][76542] Updated weights for policy 1, policy_version 16700 (0.0008) -[2023-10-10 13:20:02,619][76543] Updated weights for policy 0, policy_version 16713 (0.0010) -[2023-10-10 13:20:02,996][76543] Updated weights for policy 0, policy_version 16723 (0.0008) -[2023-10-10 13:20:03,361][76543] Updated weights for policy 0, policy_version 16733 (0.0007) -[2023-10-10 13:20:05,614][76542] Updated weights for policy 1, policy_version 16710 (0.0007) -[2023-10-10 13:20:05,980][76542] Updated weights for policy 1, policy_version 16720 (0.0011) -[2023-10-10 13:20:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 34242560. Throughput: 0: 1829.6, 1: 1823.9. Samples: 8568214. Policy #0 lag: (min: 23.0, avg: 31.0, max: 55.0) -[2023-10-10 13:20:06,076][75634] Avg episode reward: [(0, '27.900'), (1, '29.610')] -[2023-10-10 13:20:06,340][76542] Updated weights for policy 1, policy_version 16730 (0.0007) -[2023-10-10 13:20:06,965][76543] Updated weights for policy 0, policy_version 16743 (0.0009) -[2023-10-10 13:20:07,348][76543] Updated weights for policy 0, policy_version 16753 (0.0010) -[2023-10-10 13:20:07,717][76543] Updated weights for policy 0, policy_version 16763 (0.0010) -[2023-10-10 13:20:10,110][76542] Updated weights for policy 1, policy_version 16740 (0.0008) -[2023-10-10 13:20:10,487][76542] Updated weights for policy 1, policy_version 16750 (0.0010) -[2023-10-10 13:20:10,845][76542] Updated weights for policy 1, policy_version 16760 (0.0010) -[2023-10-10 13:20:11,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 34308096. Throughput: 0: 1830.2, 1: 1829.0. Samples: 8590648. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-10 13:20:11,077][75634] Avg episode reward: [(0, '27.970'), (1, '29.880')] -[2023-10-10 13:20:11,302][76543] Updated weights for policy 0, policy_version 16773 (0.0008) -[2023-10-10 13:20:11,670][76543] Updated weights for policy 0, policy_version 16783 (0.0009) -[2023-10-10 13:20:12,048][76543] Updated weights for policy 0, policy_version 16793 (0.0009) -[2023-10-10 13:20:14,663][76542] Updated weights for policy 1, policy_version 16770 (0.0010) -[2023-10-10 13:20:15,039][76542] Updated weights for policy 1, policy_version 16780 (0.0010) -[2023-10-10 13:20:15,401][76542] Updated weights for policy 1, policy_version 16790 (0.0009) -[2023-10-10 13:20:15,702][76543] Updated weights for policy 0, policy_version 16803 (0.0008) -[2023-10-10 13:20:15,772][76542] Updated weights for policy 1, policy_version 16800 (0.0009) -[2023-10-10 13:20:16,063][76543] Updated weights for policy 0, policy_version 16813 (0.0007) -[2023-10-10 13:20:16,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 34406400. Throughput: 0: 1830.2, 1: 1824.5. Samples: 8612138. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-10 13:20:16,077][75634] Avg episode reward: [(0, '28.110'), (1, '27.330')] -[2023-10-10 13:20:16,429][76543] Updated weights for policy 0, policy_version 16823 (0.0007) -[2023-10-10 13:20:19,402][76542] Updated weights for policy 1, policy_version 16810 (0.0008) -[2023-10-10 13:20:19,770][76542] Updated weights for policy 1, policy_version 16820 (0.0007) -[2023-10-10 13:20:20,141][76542] Updated weights for policy 1, policy_version 16830 (0.0008) -[2023-10-10 13:20:20,230][76543] Updated weights for policy 0, policy_version 16833 (0.0008) -[2023-10-10 13:20:20,611][76543] Updated weights for policy 0, policy_version 16843 (0.0011) -[2023-10-10 13:20:20,985][76543] Updated weights for policy 0, policy_version 16853 (0.0009) -[2023-10-10 13:20:21,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 34471936. Throughput: 0: 1830.4, 1: 1825.6. Samples: 8623550. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-10 13:20:21,076][75634] Avg episode reward: [(0, '27.730'), (1, '27.770')] -[2023-10-10 13:20:21,356][76543] Updated weights for policy 0, policy_version 16863 (0.0009) -[2023-10-10 13:20:23,808][76542] Updated weights for policy 1, policy_version 16840 (0.0009) -[2023-10-10 13:20:24,173][76542] Updated weights for policy 1, policy_version 16850 (0.0010) -[2023-10-10 13:20:24,541][76542] Updated weights for policy 1, policy_version 16860 (0.0010) -[2023-10-10 13:20:25,027][76543] Updated weights for policy 0, policy_version 16873 (0.0009) -[2023-10-10 13:20:25,394][76543] Updated weights for policy 0, policy_version 16883 (0.0008) -[2023-10-10 13:20:25,774][76543] Updated weights for policy 0, policy_version 16893 (0.0009) -[2023-10-10 13:20:26,076][75634] Fps is (10 sec: 16384.1, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 34570240. Throughput: 0: 1827.2, 1: 1820.5. Samples: 8644748. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-10 13:20:26,076][75634] Avg episode reward: [(0, '28.660'), (1, '28.770')] -[2023-10-10 13:20:28,203][76542] Updated weights for policy 1, policy_version 16870 (0.0009) -[2023-10-10 13:20:28,574][76542] Updated weights for policy 1, policy_version 16880 (0.0010) -[2023-10-10 13:20:28,933][76542] Updated weights for policy 1, policy_version 16890 (0.0009) -[2023-10-10 13:20:29,468][76543] Updated weights for policy 0, policy_version 16903 (0.0008) -[2023-10-10 13:20:29,835][76543] Updated weights for policy 0, policy_version 16913 (0.0008) -[2023-10-10 13:20:30,206][76543] Updated weights for policy 0, policy_version 16923 (0.0009) -[2023-10-10 13:20:31,076][75634] Fps is (10 sec: 16383.4, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 34635776. Throughput: 0: 1821.6, 1: 1819.9. Samples: 8666456. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-10 13:20:31,077][75634] Avg episode reward: [(0, '27.340'), (1, '29.610')] -[2023-10-10 13:20:31,089][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000016928_17334272.pth... -[2023-10-10 13:20:31,090][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000016896_17301504.pth... -[2023-10-10 13:20:31,124][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000015200_15564800.pth -[2023-10-10 13:20:31,128][76362] Saving a milestone ./train_atari/atari_defender_APPO/checkpoint_p0/milestones/checkpoint_000016928_17334272.pth -[2023-10-10 13:20:31,135][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000015200_15564800.pth -[2023-10-10 13:20:31,140][76421] Saving a milestone ./train_atari/atari_defender_APPO/checkpoint_p1/milestones/checkpoint_000016896_17301504.pth -[2023-10-10 13:20:32,639][76542] Updated weights for policy 1, policy_version 16900 (0.0008) -[2023-10-10 13:20:33,009][76542] Updated weights for policy 1, policy_version 16910 (0.0008) -[2023-10-10 13:20:33,383][76542] Updated weights for policy 1, policy_version 16920 (0.0008) -[2023-10-10 13:20:33,790][76543] Updated weights for policy 0, policy_version 16933 (0.0009) -[2023-10-10 13:20:34,174][76543] Updated weights for policy 0, policy_version 16943 (0.0009) -[2023-10-10 13:20:34,543][76543] Updated weights for policy 0, policy_version 16953 (0.0010) -[2023-10-10 13:20:36,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 34701312. Throughput: 0: 1822.4, 1: 1818.7. Samples: 8677482. Policy #0 lag: (min: 12.0, avg: 22.8, max: 44.0) -[2023-10-10 13:20:36,077][75634] Avg episode reward: [(0, '27.470'), (1, '28.360')] -[2023-10-10 13:20:37,144][76542] Updated weights for policy 1, policy_version 16930 (0.0008) -[2023-10-10 13:20:37,514][76542] Updated weights for policy 1, policy_version 16940 (0.0007) -[2023-10-10 13:20:37,880][76542] Updated weights for policy 1, policy_version 16950 (0.0010) -[2023-10-10 13:20:38,216][76543] Updated weights for policy 0, policy_version 16963 (0.0008) -[2023-10-10 13:20:38,243][76542] Updated weights for policy 1, policy_version 16960 (0.0007) -[2023-10-10 13:20:38,589][76543] Updated weights for policy 0, policy_version 16973 (0.0009) -[2023-10-10 13:20:38,964][76543] Updated weights for policy 0, policy_version 16983 (0.0009) -[2023-10-10 13:20:41,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 34766848. Throughput: 0: 1815.6, 1: 1820.0. Samples: 8698820. Policy #0 lag: (min: 12.0, avg: 22.8, max: 44.0) -[2023-10-10 13:20:41,077][75634] Avg episode reward: [(0, '26.030'), (1, '29.290')] -[2023-10-10 13:20:42,069][76542] Updated weights for policy 1, policy_version 16970 (0.0008) -[2023-10-10 13:20:42,435][76542] Updated weights for policy 1, policy_version 16980 (0.0010) -[2023-10-10 13:20:42,623][76543] Updated weights for policy 0, policy_version 16993 (0.0009) -[2023-10-10 13:20:42,804][76542] Updated weights for policy 1, policy_version 16990 (0.0008) -[2023-10-10 13:20:43,001][76543] Updated weights for policy 0, policy_version 17003 (0.0008) -[2023-10-10 13:20:43,362][76543] Updated weights for policy 0, policy_version 17013 (0.0008) -[2023-10-10 13:20:43,733][76543] Updated weights for policy 0, policy_version 17023 (0.0008) -[2023-10-10 13:20:46,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 34832384. Throughput: 0: 1821.1, 1: 1810.6. Samples: 8721384. Policy #0 lag: (min: 12.0, avg: 22.8, max: 44.0) -[2023-10-10 13:20:46,077][75634] Avg episode reward: [(0, '27.150'), (1, '30.920')] -[2023-10-10 13:20:46,090][76421] Saving new best policy, reward=30.920! -[2023-10-10 13:20:46,602][76542] Updated weights for policy 1, policy_version 17000 (0.0008) -[2023-10-10 13:20:46,971][76542] Updated weights for policy 1, policy_version 17010 (0.0008) -[2023-10-10 13:20:47,343][76542] Updated weights for policy 1, policy_version 17020 (0.0009) -[2023-10-10 13:20:47,422][76543] Updated weights for policy 0, policy_version 17033 (0.0010) -[2023-10-10 13:20:47,802][76543] Updated weights for policy 0, policy_version 17043 (0.0010) -[2023-10-10 13:20:48,180][76543] Updated weights for policy 0, policy_version 17053 (0.0007) -[2023-10-10 13:20:50,999][76542] Updated weights for policy 1, policy_version 17030 (0.0009) -[2023-10-10 13:20:51,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 34897920. Throughput: 0: 1820.7, 1: 1813.1. Samples: 8731740. Policy #0 lag: (min: 23.0, avg: 30.3, max: 55.0) -[2023-10-10 13:20:51,077][75634] Avg episode reward: [(0, '28.230'), (1, '32.120')] -[2023-10-10 13:20:51,376][76542] Updated weights for policy 1, policy_version 17040 (0.0009) -[2023-10-10 13:20:51,752][76542] Updated weights for policy 1, policy_version 17050 (0.0008) -[2023-10-10 13:20:51,754][76543] Updated weights for policy 0, policy_version 17063 (0.0009) -[2023-10-10 13:20:51,975][76421] Saving new best policy, reward=32.120! -[2023-10-10 13:20:52,116][76543] Updated weights for policy 0, policy_version 17073 (0.0008) -[2023-10-10 13:20:52,486][76543] Updated weights for policy 0, policy_version 17083 (0.0009) -[2023-10-10 13:20:55,534][76542] Updated weights for policy 1, policy_version 17060 (0.0009) -[2023-10-10 13:20:55,915][76542] Updated weights for policy 1, policy_version 17070 (0.0008) -[2023-10-10 13:20:56,059][76543] Updated weights for policy 0, policy_version 17093 (0.0007) -[2023-10-10 13:20:56,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 34963456. Throughput: 0: 1830.1, 1: 1802.8. Samples: 8754126. Policy #0 lag: (min: 23.0, avg: 30.3, max: 55.0) -[2023-10-10 13:20:56,076][75634] Avg episode reward: [(0, '27.430'), (1, '30.020')] -[2023-10-10 13:20:56,280][76542] Updated weights for policy 1, policy_version 17080 (0.0007) -[2023-10-10 13:20:56,430][76543] Updated weights for policy 0, policy_version 17103 (0.0007) -[2023-10-10 13:20:56,801][76543] Updated weights for policy 0, policy_version 17113 (0.0009) -[2023-10-10 13:21:00,031][76542] Updated weights for policy 1, policy_version 17090 (0.0008) -[2023-10-10 13:21:00,400][76542] Updated weights for policy 1, policy_version 17100 (0.0008) -[2023-10-10 13:21:00,493][76543] Updated weights for policy 0, policy_version 17123 (0.0008) -[2023-10-10 13:21:00,763][76542] Updated weights for policy 1, policy_version 17110 (0.0008) -[2023-10-10 13:21:00,854][76543] Updated weights for policy 0, policy_version 17133 (0.0007) -[2023-10-10 13:21:01,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 35028992. Throughput: 0: 1828.2, 1: 1813.5. Samples: 8776012. Policy #0 lag: (min: 23.0, avg: 30.3, max: 55.0) -[2023-10-10 13:21:01,076][75634] Avg episode reward: [(0, '27.370'), (1, '29.200')] -[2023-10-10 13:21:01,134][76542] Updated weights for policy 1, policy_version 17120 (0.0007) -[2023-10-10 13:21:01,227][76543] Updated weights for policy 0, policy_version 17143 (0.0007) -[2023-10-10 13:21:04,806][76542] Updated weights for policy 1, policy_version 17130 (0.0009) -[2023-10-10 13:21:04,887][76543] Updated weights for policy 0, policy_version 17153 (0.0009) -[2023-10-10 13:21:05,167][76542] Updated weights for policy 1, policy_version 17140 (0.0008) -[2023-10-10 13:21:05,263][76543] Updated weights for policy 0, policy_version 17163 (0.0008) -[2023-10-10 13:21:05,532][76542] Updated weights for policy 1, policy_version 17150 (0.0009) -[2023-10-10 13:21:05,631][76543] Updated weights for policy 0, policy_version 17173 (0.0007) -[2023-10-10 13:21:06,008][76543] Updated weights for policy 0, policy_version 17183 (0.0009) -[2023-10-10 13:21:06,076][75634] Fps is (10 sec: 19660.3, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 35160064. Throughput: 0: 1826.4, 1: 1801.2. Samples: 8786796. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:21:06,077][75634] Avg episode reward: [(0, '29.050'), (1, '31.670')] -[2023-10-10 13:21:09,275][76542] Updated weights for policy 1, policy_version 17160 (0.0008) -[2023-10-10 13:21:09,632][76543] Updated weights for policy 0, policy_version 17193 (0.0008) -[2023-10-10 13:21:09,652][76542] Updated weights for policy 1, policy_version 17170 (0.0009) -[2023-10-10 13:21:09,994][76543] Updated weights for policy 0, policy_version 17203 (0.0007) -[2023-10-10 13:21:10,013][76542] Updated weights for policy 1, policy_version 17180 (0.0009) -[2023-10-10 13:21:10,370][76543] Updated weights for policy 0, policy_version 17213 (0.0009) -[2023-10-10 13:21:11,076][75634] Fps is (10 sec: 19660.3, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 35225600. Throughput: 0: 1829.0, 1: 1820.6. Samples: 8808980. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:21:11,077][75634] Avg episode reward: [(0, '29.030'), (1, '29.830')] -[2023-10-10 13:21:13,737][76542] Updated weights for policy 1, policy_version 17190 (0.0009) -[2023-10-10 13:21:14,039][76543] Updated weights for policy 0, policy_version 17223 (0.0008) -[2023-10-10 13:21:14,101][76542] Updated weights for policy 1, policy_version 17200 (0.0008) -[2023-10-10 13:21:14,412][76543] Updated weights for policy 0, policy_version 17233 (0.0009) -[2023-10-10 13:21:14,467][76542] Updated weights for policy 1, policy_version 17210 (0.0009) -[2023-10-10 13:21:14,778][76543] Updated weights for policy 0, policy_version 17243 (0.0008) -[2023-10-10 13:21:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 35291136. Throughput: 0: 1826.1, 1: 1796.3. Samples: 8829464. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-10 13:21:16,077][75634] Avg episode reward: [(0, '29.980'), (1, '29.700')] -[2023-10-10 13:21:18,262][76542] Updated weights for policy 1, policy_version 17220 (0.0008) -[2023-10-10 13:21:18,406][76543] Updated weights for policy 0, policy_version 17253 (0.0009) -[2023-10-10 13:21:18,624][76542] Updated weights for policy 1, policy_version 17230 (0.0007) -[2023-10-10 13:21:18,772][76543] Updated weights for policy 0, policy_version 17263 (0.0007) -[2023-10-10 13:21:19,002][76542] Updated weights for policy 1, policy_version 17240 (0.0007) -[2023-10-10 13:21:19,149][76543] Updated weights for policy 0, policy_version 17273 (0.0010) -[2023-10-10 13:21:21,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 35356672. Throughput: 0: 1831.5, 1: 1812.1. Samples: 8841442. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-10 13:21:21,077][75634] Avg episode reward: [(0, '28.740'), (1, '29.210')] -[2023-10-10 13:21:22,658][76542] Updated weights for policy 1, policy_version 17250 (0.0008) -[2023-10-10 13:21:22,969][76543] Updated weights for policy 0, policy_version 17283 (0.0009) -[2023-10-10 13:21:23,022][76542] Updated weights for policy 1, policy_version 17260 (0.0009) -[2023-10-10 13:21:23,346][76543] Updated weights for policy 0, policy_version 17293 (0.0007) -[2023-10-10 13:21:23,383][76542] Updated weights for policy 1, policy_version 17270 (0.0008) -[2023-10-10 13:21:23,719][76543] Updated weights for policy 0, policy_version 17303 (0.0007) -[2023-10-10 13:21:23,749][76542] Updated weights for policy 1, policy_version 17280 (0.0008) -[2023-10-10 13:21:26,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 35422208. Throughput: 0: 1832.7, 1: 1794.4. Samples: 8862038. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-10 13:21:26,077][75634] Avg episode reward: [(0, '28.190'), (1, '29.850')] -[2023-10-10 13:21:27,242][76543] Updated weights for policy 0, policy_version 17313 (0.0007) -[2023-10-10 13:21:27,430][76542] Updated weights for policy 1, policy_version 17290 (0.0010) -[2023-10-10 13:21:27,616][76543] Updated weights for policy 0, policy_version 17323 (0.0007) -[2023-10-10 13:21:27,795][76542] Updated weights for policy 1, policy_version 17300 (0.0009) -[2023-10-10 13:21:27,988][76543] Updated weights for policy 0, policy_version 17333 (0.0008) -[2023-10-10 13:21:28,162][76542] Updated weights for policy 1, policy_version 17310 (0.0008) -[2023-10-10 13:21:28,358][76543] Updated weights for policy 0, policy_version 17343 (0.0008) -[2023-10-10 13:21:31,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 35487744. Throughput: 0: 1835.7, 1: 1803.4. Samples: 8885144. Policy #0 lag: (min: 15.0, avg: 21.9, max: 47.0) -[2023-10-10 13:21:31,077][75634] Avg episode reward: [(0, '28.680'), (1, '27.160')] -[2023-10-10 13:21:31,755][76542] Updated weights for policy 1, policy_version 17320 (0.0007) -[2023-10-10 13:21:32,039][76543] Updated weights for policy 0, policy_version 17353 (0.0008) -[2023-10-10 13:21:32,126][76542] Updated weights for policy 1, policy_version 17330 (0.0008) -[2023-10-10 13:21:32,409][76543] Updated weights for policy 0, policy_version 17363 (0.0008) -[2023-10-10 13:21:32,499][76542] Updated weights for policy 1, policy_version 17340 (0.0008) -[2023-10-10 13:21:32,776][76543] Updated weights for policy 0, policy_version 17373 (0.0007) -[2023-10-10 13:21:36,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 35553280. Throughput: 0: 1822.4, 1: 1802.8. Samples: 8894872. Policy #0 lag: (min: 15.0, avg: 21.9, max: 47.0) -[2023-10-10 13:21:36,077][75634] Avg episode reward: [(0, '26.820'), (1, '26.430')] -[2023-10-10 13:21:36,108][76542] Updated weights for policy 1, policy_version 17350 (0.0007) -[2023-10-10 13:21:36,482][76542] Updated weights for policy 1, policy_version 17360 (0.0008) -[2023-10-10 13:21:36,564][76543] Updated weights for policy 0, policy_version 17383 (0.0008) -[2023-10-10 13:21:36,850][76542] Updated weights for policy 1, policy_version 17370 (0.0008) -[2023-10-10 13:21:36,933][76543] Updated weights for policy 0, policy_version 17393 (0.0010) -[2023-10-10 13:21:37,306][76543] Updated weights for policy 0, policy_version 17403 (0.0008) -[2023-10-10 13:21:40,729][76542] Updated weights for policy 1, policy_version 17380 (0.0007) -[2023-10-10 13:21:40,956][76543] Updated weights for policy 0, policy_version 17413 (0.0008) -[2023-10-10 13:21:41,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 35618816. Throughput: 0: 1826.6, 1: 1811.9. Samples: 8917860. Policy #0 lag: (min: 15.0, avg: 21.9, max: 47.0) -[2023-10-10 13:21:41,076][75634] Avg episode reward: [(0, '27.330'), (1, '28.050')] -[2023-10-10 13:21:41,125][76542] Updated weights for policy 1, policy_version 17390 (0.0007) -[2023-10-10 13:21:41,329][76543] Updated weights for policy 0, policy_version 17423 (0.0007) -[2023-10-10 13:21:41,492][76542] Updated weights for policy 1, policy_version 17400 (0.0008) -[2023-10-10 13:21:41,704][76543] Updated weights for policy 0, policy_version 17433 (0.0009) -[2023-10-10 13:21:45,291][76542] Updated weights for policy 1, policy_version 17410 (0.0007) -[2023-10-10 13:21:45,503][76543] Updated weights for policy 0, policy_version 17443 (0.0008) -[2023-10-10 13:21:45,655][76542] Updated weights for policy 1, policy_version 17420 (0.0008) -[2023-10-10 13:21:45,869][76543] Updated weights for policy 0, policy_version 17453 (0.0007) -[2023-10-10 13:21:46,025][76542] Updated weights for policy 1, policy_version 17430 (0.0007) -[2023-10-10 13:21:46,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 35684352. Throughput: 0: 1825.6, 1: 1812.1. Samples: 8939710. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:21:46,076][75634] Avg episode reward: [(0, '28.720'), (1, '27.200')] -[2023-10-10 13:21:46,244][76543] Updated weights for policy 0, policy_version 17463 (0.0008) -[2023-10-10 13:21:46,392][76542] Updated weights for policy 1, policy_version 17440 (0.0008) -[2023-10-10 13:21:49,936][76543] Updated weights for policy 0, policy_version 17473 (0.0009) -[2023-10-10 13:21:50,245][76542] Updated weights for policy 1, policy_version 17450 (0.0007) -[2023-10-10 13:21:50,310][76543] Updated weights for policy 0, policy_version 17483 (0.0008) -[2023-10-10 13:21:50,606][76542] Updated weights for policy 1, policy_version 17460 (0.0007) -[2023-10-10 13:21:50,683][76543] Updated weights for policy 0, policy_version 17493 (0.0009) -[2023-10-10 13:21:50,978][76542] Updated weights for policy 1, policy_version 17470 (0.0008) -[2023-10-10 13:21:51,056][76543] Updated weights for policy 0, policy_version 17503 (0.0007) -[2023-10-10 13:21:51,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 35782656. Throughput: 0: 1826.7, 1: 1798.1. Samples: 8949910. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:21:51,076][75634] Avg episode reward: [(0, '26.830'), (1, '26.700')] -[2023-10-10 13:21:54,761][76542] Updated weights for policy 1, policy_version 17480 (0.0008) -[2023-10-10 13:21:54,793][76543] Updated weights for policy 0, policy_version 17513 (0.0008) -[2023-10-10 13:21:55,126][76542] Updated weights for policy 1, policy_version 17490 (0.0007) -[2023-10-10 13:21:55,165][76543] Updated weights for policy 0, policy_version 17523 (0.0009) -[2023-10-10 13:21:55,493][76542] Updated weights for policy 1, policy_version 17500 (0.0007) -[2023-10-10 13:21:55,528][76543] Updated weights for policy 0, policy_version 17533 (0.0007) -[2023-10-10 13:21:56,076][75634] Fps is (10 sec: 19660.2, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 35880960. Throughput: 0: 1826.4, 1: 1805.7. Samples: 8972426. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-10 13:21:56,077][75634] Avg episode reward: [(0, '27.410'), (1, '28.150')] -[2023-10-10 13:21:59,148][76542] Updated weights for policy 1, policy_version 17510 (0.0008) -[2023-10-10 13:21:59,189][76543] Updated weights for policy 0, policy_version 17543 (0.0009) -[2023-10-10 13:21:59,515][76542] Updated weights for policy 1, policy_version 17520 (0.0009) -[2023-10-10 13:21:59,577][76543] Updated weights for policy 0, policy_version 17553 (0.0007) -[2023-10-10 13:21:59,876][76542] Updated weights for policy 1, policy_version 17530 (0.0007) -[2023-10-10 13:21:59,952][76543] Updated weights for policy 0, policy_version 17563 (0.0009) -[2023-10-10 13:22:01,076][75634] Fps is (10 sec: 16383.7, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 35946496. Throughput: 0: 1823.7, 1: 1798.5. Samples: 8992462. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-10 13:22:01,077][75634] Avg episode reward: [(0, '27.980'), (1, '30.280')] -[2023-10-10 13:22:03,584][76543] Updated weights for policy 0, policy_version 17573 (0.0007) -[2023-10-10 13:22:03,672][76542] Updated weights for policy 1, policy_version 17540 (0.0008) -[2023-10-10 13:22:03,959][76543] Updated weights for policy 0, policy_version 17583 (0.0009) -[2023-10-10 13:22:04,038][76542] Updated weights for policy 1, policy_version 17550 (0.0008) -[2023-10-10 13:22:04,325][76543] Updated weights for policy 0, policy_version 17593 (0.0010) -[2023-10-10 13:22:04,403][76542] Updated weights for policy 1, policy_version 17560 (0.0008) -[2023-10-10 13:22:06,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 36012032. Throughput: 0: 1823.8, 1: 1811.0. Samples: 9005010. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-10 13:22:06,077][75634] Avg episode reward: [(0, '29.470'), (1, '32.670')] -[2023-10-10 13:22:06,079][76421] Saving new best policy, reward=32.670! -[2023-10-10 13:22:07,994][76542] Updated weights for policy 1, policy_version 17570 (0.0008) -[2023-10-10 13:22:08,044][76543] Updated weights for policy 0, policy_version 17603 (0.0009) -[2023-10-10 13:22:08,368][76542] Updated weights for policy 1, policy_version 17580 (0.0008) -[2023-10-10 13:22:08,421][76543] Updated weights for policy 0, policy_version 17613 (0.0008) -[2023-10-10 13:22:08,728][76542] Updated weights for policy 1, policy_version 17590 (0.0007) -[2023-10-10 13:22:08,787][76543] Updated weights for policy 0, policy_version 17623 (0.0007) -[2023-10-10 13:22:09,096][76542] Updated weights for policy 1, policy_version 17600 (0.0008) -[2023-10-10 13:22:11,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 36077568. Throughput: 0: 1820.1, 1: 1802.3. Samples: 9025048. Policy #0 lag: (min: 24.0, avg: 52.1, max: 56.0) -[2023-10-10 13:22:11,076][75634] Avg episode reward: [(0, '31.320'), (1, '30.820')] -[2023-10-10 13:22:12,523][76543] Updated weights for policy 0, policy_version 17633 (0.0007) -[2023-10-10 13:22:12,723][76542] Updated weights for policy 1, policy_version 17610 (0.0008) -[2023-10-10 13:22:12,883][76543] Updated weights for policy 0, policy_version 17643 (0.0008) -[2023-10-10 13:22:13,091][76542] Updated weights for policy 1, policy_version 17620 (0.0008) -[2023-10-10 13:22:13,260][76543] Updated weights for policy 0, policy_version 17653 (0.0008) -[2023-10-10 13:22:13,465][76542] Updated weights for policy 1, policy_version 17630 (0.0008) -[2023-10-10 13:22:13,622][76543] Updated weights for policy 0, policy_version 17663 (0.0007) -[2023-10-10 13:22:16,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 36143104. Throughput: 0: 1815.6, 1: 1802.6. Samples: 9047962. Policy #0 lag: (min: 24.0, avg: 52.1, max: 56.0) -[2023-10-10 13:22:16,077][75634] Avg episode reward: [(0, '32.480'), (1, '31.270')] -[2023-10-10 13:22:17,145][76542] Updated weights for policy 1, policy_version 17640 (0.0008) -[2023-10-10 13:22:17,229][76543] Updated weights for policy 0, policy_version 17673 (0.0008) -[2023-10-10 13:22:17,514][76542] Updated weights for policy 1, policy_version 17650 (0.0008) -[2023-10-10 13:22:17,592][76543] Updated weights for policy 0, policy_version 17683 (0.0007) -[2023-10-10 13:22:17,871][76542] Updated weights for policy 1, policy_version 17660 (0.0009) -[2023-10-10 13:22:17,969][76543] Updated weights for policy 0, policy_version 17693 (0.0010) -[2023-10-10 13:22:21,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 36208640. Throughput: 0: 1823.8, 1: 1802.7. Samples: 9058066. Policy #0 lag: (min: 24.0, avg: 52.1, max: 56.0) -[2023-10-10 13:22:21,077][75634] Avg episode reward: [(0, '35.160'), (1, '30.710')] -[2023-10-10 13:22:21,078][76362] Saving new best policy, reward=35.160! -[2023-10-10 13:22:21,619][76543] Updated weights for policy 0, policy_version 17703 (0.0008) -[2023-10-10 13:22:21,661][76542] Updated weights for policy 1, policy_version 17670 (0.0009) -[2023-10-10 13:22:21,985][76543] Updated weights for policy 0, policy_version 17713 (0.0008) -[2023-10-10 13:22:22,031][76542] Updated weights for policy 1, policy_version 17680 (0.0007) -[2023-10-10 13:22:22,356][76543] Updated weights for policy 0, policy_version 17723 (0.0008) -[2023-10-10 13:22:22,402][76542] Updated weights for policy 1, policy_version 17690 (0.0008) -[2023-10-10 13:22:26,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 36274176. Throughput: 0: 1816.9, 1: 1801.2. Samples: 9080676. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:22:26,076][75634] Avg episode reward: [(0, '33.100'), (1, '32.500')] -[2023-10-10 13:22:26,098][76542] Updated weights for policy 1, policy_version 17700 (0.0008) -[2023-10-10 13:22:26,101][76543] Updated weights for policy 0, policy_version 17733 (0.0007) -[2023-10-10 13:22:26,471][76543] Updated weights for policy 0, policy_version 17743 (0.0009) -[2023-10-10 13:22:26,493][76542] Updated weights for policy 1, policy_version 17710 (0.0008) -[2023-10-10 13:22:26,832][76543] Updated weights for policy 0, policy_version 17753 (0.0008) -[2023-10-10 13:22:26,852][76542] Updated weights for policy 1, policy_version 17720 (0.0007) -[2023-10-10 13:22:30,425][76543] Updated weights for policy 0, policy_version 17763 (0.0008) -[2023-10-10 13:22:30,549][76542] Updated weights for policy 1, policy_version 17730 (0.0009) -[2023-10-10 13:22:30,795][76543] Updated weights for policy 0, policy_version 17773 (0.0008) -[2023-10-10 13:22:30,920][76542] Updated weights for policy 1, policy_version 17740 (0.0008) -[2023-10-10 13:22:31,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 36339712. Throughput: 0: 1814.7, 1: 1814.1. Samples: 9103004. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:22:31,076][75634] Avg episode reward: [(0, '32.840'), (1, '30.260')] -[2023-10-10 13:22:31,169][76543] Updated weights for policy 0, policy_version 17783 (0.0007) -[2023-10-10 13:22:31,288][76542] Updated weights for policy 1, policy_version 17750 (0.0007) -[2023-10-10 13:22:31,506][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000017792_18219008.pth... -[2023-10-10 13:22:31,539][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000016064_16449536.pth -[2023-10-10 13:22:31,653][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000017760_18186240.pth... -[2023-10-10 13:22:31,659][76542] Updated weights for policy 1, policy_version 17760 (0.0009) -[2023-10-10 13:22:31,691][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000016064_16449536.pth -[2023-10-10 13:22:35,017][76543] Updated weights for policy 0, policy_version 17793 (0.0007) -[2023-10-10 13:22:35,337][76542] Updated weights for policy 1, policy_version 17770 (0.0008) -[2023-10-10 13:22:35,373][76543] Updated weights for policy 0, policy_version 17803 (0.0007) -[2023-10-10 13:22:35,708][76542] Updated weights for policy 1, policy_version 17780 (0.0010) -[2023-10-10 13:22:35,745][76543] Updated weights for policy 0, policy_version 17813 (0.0008) -[2023-10-10 13:22:36,067][76542] Updated weights for policy 1, policy_version 17790 (0.0009) -[2023-10-10 13:22:36,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 36405248. Throughput: 0: 1811.2, 1: 1814.1. Samples: 9113048. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:22:36,076][75634] Avg episode reward: [(0, '31.510'), (1, '28.930')] -[2023-10-10 13:22:36,121][76543] Updated weights for policy 0, policy_version 17823 (0.0008) -[2023-10-10 13:22:39,816][76543] Updated weights for policy 0, policy_version 17833 (0.0008) -[2023-10-10 13:22:39,821][76542] Updated weights for policy 1, policy_version 17800 (0.0009) -[2023-10-10 13:22:40,187][76543] Updated weights for policy 0, policy_version 17843 (0.0007) -[2023-10-10 13:22:40,188][76542] Updated weights for policy 1, policy_version 17810 (0.0008) -[2023-10-10 13:22:40,551][76542] Updated weights for policy 1, policy_version 17820 (0.0008) -[2023-10-10 13:22:40,552][76543] Updated weights for policy 0, policy_version 17853 (0.0008) -[2023-10-10 13:22:41,076][75634] Fps is (10 sec: 19660.4, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 36536320. Throughput: 0: 1809.2, 1: 1817.6. Samples: 9135632. Policy #0 lag: (min: 18.0, avg: 18.0, max: 20.0) -[2023-10-10 13:22:41,077][75634] Avg episode reward: [(0, '30.890'), (1, '28.080')] -[2023-10-10 13:22:44,360][76543] Updated weights for policy 0, policy_version 17863 (0.0009) -[2023-10-10 13:22:44,390][76542] Updated weights for policy 1, policy_version 17830 (0.0009) -[2023-10-10 13:22:44,735][76543] Updated weights for policy 0, policy_version 17873 (0.0007) -[2023-10-10 13:22:44,762][76542] Updated weights for policy 1, policy_version 17840 (0.0008) -[2023-10-10 13:22:45,112][76543] Updated weights for policy 0, policy_version 17883 (0.0007) -[2023-10-10 13:22:45,125][76542] Updated weights for policy 1, policy_version 17850 (0.0008) -[2023-10-10 13:22:46,076][75634] Fps is (10 sec: 19660.8, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 36601856. Throughput: 0: 1809.7, 1: 1813.4. Samples: 9155500. Policy #0 lag: (min: 18.0, avg: 18.0, max: 20.0) -[2023-10-10 13:22:46,076][75634] Avg episode reward: [(0, '30.660'), (1, '29.000')] -[2023-10-10 13:22:48,720][76543] Updated weights for policy 0, policy_version 17893 (0.0008) -[2023-10-10 13:22:48,858][76542] Updated weights for policy 1, policy_version 17860 (0.0008) -[2023-10-10 13:22:49,100][76543] Updated weights for policy 0, policy_version 17903 (0.0010) -[2023-10-10 13:22:49,228][76542] Updated weights for policy 1, policy_version 17870 (0.0008) -[2023-10-10 13:22:49,464][76543] Updated weights for policy 0, policy_version 17913 (0.0007) -[2023-10-10 13:22:49,604][76542] Updated weights for policy 1, policy_version 17880 (0.0007) -[2023-10-10 13:22:51,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 36667392. Throughput: 0: 1808.8, 1: 1818.4. Samples: 9168236. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-10 13:22:51,077][75634] Avg episode reward: [(0, '30.820'), (1, '29.820')] -[2023-10-10 13:22:53,325][76543] Updated weights for policy 0, policy_version 17923 (0.0007) -[2023-10-10 13:22:53,388][76542] Updated weights for policy 1, policy_version 17890 (0.0008) -[2023-10-10 13:22:53,695][76543] Updated weights for policy 0, policy_version 17933 (0.0009) -[2023-10-10 13:22:53,752][76542] Updated weights for policy 1, policy_version 17900 (0.0007) -[2023-10-10 13:22:54,075][76543] Updated weights for policy 0, policy_version 17943 (0.0008) -[2023-10-10 13:22:54,113][76542] Updated weights for policy 1, policy_version 17910 (0.0009) -[2023-10-10 13:22:54,475][76542] Updated weights for policy 1, policy_version 17920 (0.0010) -[2023-10-10 13:22:56,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 36732928. Throughput: 0: 1812.8, 1: 1812.2. Samples: 9188170. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-10 13:22:56,077][75634] Avg episode reward: [(0, '30.020'), (1, '29.260')] -[2023-10-10 13:22:57,608][76543] Updated weights for policy 0, policy_version 17953 (0.0010) -[2023-10-10 13:22:57,976][76543] Updated weights for policy 0, policy_version 17963 (0.0010) -[2023-10-10 13:22:58,199][76542] Updated weights for policy 1, policy_version 17930 (0.0009) -[2023-10-10 13:22:58,350][76543] Updated weights for policy 0, policy_version 17973 (0.0008) -[2023-10-10 13:22:58,571][76542] Updated weights for policy 1, policy_version 17940 (0.0008) -[2023-10-10 13:22:58,721][76543] Updated weights for policy 0, policy_version 17983 (0.0007) -[2023-10-10 13:22:58,930][76542] Updated weights for policy 1, policy_version 17950 (0.0009) -[2023-10-10 13:23:01,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 36798464. Throughput: 0: 1808.5, 1: 1799.6. Samples: 9210328. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-10 13:23:01,077][75634] Avg episode reward: [(0, '28.520'), (1, '28.940')] -[2023-10-10 13:23:02,582][76542] Updated weights for policy 1, policy_version 17960 (0.0008) -[2023-10-10 13:23:02,605][76543] Updated weights for policy 0, policy_version 17993 (0.0008) -[2023-10-10 13:23:02,948][76542] Updated weights for policy 1, policy_version 17970 (0.0008) -[2023-10-10 13:23:02,981][76543] Updated weights for policy 0, policy_version 18003 (0.0008) -[2023-10-10 13:23:03,318][76542] Updated weights for policy 1, policy_version 17980 (0.0008) -[2023-10-10 13:23:03,349][76543] Updated weights for policy 0, policy_version 18013 (0.0009) -[2023-10-10 13:23:06,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 36864000. Throughput: 0: 1810.6, 1: 1802.6. Samples: 9220660. Policy #0 lag: (min: 24.0, avg: 42.0, max: 56.0) -[2023-10-10 13:23:06,077][75634] Avg episode reward: [(0, '28.780'), (1, '29.090')] -[2023-10-10 13:23:07,076][76542] Updated weights for policy 1, policy_version 17990 (0.0008) -[2023-10-10 13:23:07,114][76543] Updated weights for policy 0, policy_version 18023 (0.0009) -[2023-10-10 13:23:07,440][76542] Updated weights for policy 1, policy_version 18000 (0.0009) -[2023-10-10 13:23:07,484][76543] Updated weights for policy 0, policy_version 18033 (0.0009) -[2023-10-10 13:23:07,808][76542] Updated weights for policy 1, policy_version 18010 (0.0008) -[2023-10-10 13:23:07,863][76543] Updated weights for policy 0, policy_version 18043 (0.0008) -[2023-10-10 13:23:11,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 36929536. Throughput: 0: 1802.2, 1: 1808.0. Samples: 9243134. Policy #0 lag: (min: 24.0, avg: 42.0, max: 56.0) -[2023-10-10 13:23:11,077][75634] Avg episode reward: [(0, '26.450'), (1, '30.400')] -[2023-10-10 13:23:11,473][76543] Updated weights for policy 0, policy_version 18053 (0.0008) -[2023-10-10 13:23:11,571][76542] Updated weights for policy 1, policy_version 18020 (0.0007) -[2023-10-10 13:23:11,843][76543] Updated weights for policy 0, policy_version 18063 (0.0009) -[2023-10-10 13:23:11,975][76542] Updated weights for policy 1, policy_version 18030 (0.0008) -[2023-10-10 13:23:12,215][76543] Updated weights for policy 0, policy_version 18073 (0.0007) -[2023-10-10 13:23:12,345][76542] Updated weights for policy 1, policy_version 18040 (0.0007) -[2023-10-10 13:23:15,889][76542] Updated weights for policy 1, policy_version 18050 (0.0008) -[2023-10-10 13:23:16,010][76543] Updated weights for policy 0, policy_version 18083 (0.0008) -[2023-10-10 13:23:16,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 36995072. Throughput: 0: 1808.7, 1: 1816.0. Samples: 9266118. Policy #0 lag: (min: 24.0, avg: 42.0, max: 56.0) -[2023-10-10 13:23:16,076][75634] Avg episode reward: [(0, '26.330'), (1, '30.220')] -[2023-10-10 13:23:16,253][76542] Updated weights for policy 1, policy_version 18060 (0.0008) -[2023-10-10 13:23:16,373][76543] Updated weights for policy 0, policy_version 18093 (0.0009) -[2023-10-10 13:23:16,627][76542] Updated weights for policy 1, policy_version 18070 (0.0007) -[2023-10-10 13:23:16,750][76543] Updated weights for policy 0, policy_version 18103 (0.0007) -[2023-10-10 13:23:16,999][76542] Updated weights for policy 1, policy_version 18080 (0.0008) -[2023-10-10 13:23:20,417][76543] Updated weights for policy 0, policy_version 18113 (0.0009) -[2023-10-10 13:23:20,681][76542] Updated weights for policy 1, policy_version 18090 (0.0007) -[2023-10-10 13:23:20,788][76543] Updated weights for policy 0, policy_version 18123 (0.0007) -[2023-10-10 13:23:21,042][76542] Updated weights for policy 1, policy_version 18100 (0.0008) -[2023-10-10 13:23:21,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 37060608. Throughput: 0: 1808.4, 1: 1806.0. Samples: 9275698. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-10 13:23:21,077][75634] Avg episode reward: [(0, '26.690'), (1, '30.330')] -[2023-10-10 13:23:21,149][76543] Updated weights for policy 0, policy_version 18133 (0.0008) -[2023-10-10 13:23:21,412][76542] Updated weights for policy 1, policy_version 18110 (0.0007) -[2023-10-10 13:23:21,525][76543] Updated weights for policy 0, policy_version 18143 (0.0009) -[2023-10-10 13:23:25,083][76543] Updated weights for policy 0, policy_version 18153 (0.0008) -[2023-10-10 13:23:25,168][76542] Updated weights for policy 1, policy_version 18120 (0.0008) -[2023-10-10 13:23:25,462][76543] Updated weights for policy 0, policy_version 18163 (0.0009) -[2023-10-10 13:23:25,524][76542] Updated weights for policy 1, policy_version 18130 (0.0008) -[2023-10-10 13:23:25,828][76543] Updated weights for policy 0, policy_version 18173 (0.0008) -[2023-10-10 13:23:25,892][76542] Updated weights for policy 1, policy_version 18140 (0.0008) -[2023-10-10 13:23:26,076][75634] Fps is (10 sec: 19660.9, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 37191680. Throughput: 0: 1817.8, 1: 1808.5. Samples: 9298814. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-10 13:23:26,076][75634] Avg episode reward: [(0, '27.050'), (1, '29.450')] -[2023-10-10 13:23:29,607][76542] Updated weights for policy 1, policy_version 18150 (0.0009) -[2023-10-10 13:23:29,676][76543] Updated weights for policy 0, policy_version 18183 (0.0007) -[2023-10-10 13:23:29,976][76542] Updated weights for policy 1, policy_version 18160 (0.0008) -[2023-10-10 13:23:30,044][76543] Updated weights for policy 0, policy_version 18193 (0.0009) -[2023-10-10 13:23:30,349][76542] Updated weights for policy 1, policy_version 18170 (0.0008) -[2023-10-10 13:23:30,423][76543] Updated weights for policy 0, policy_version 18203 (0.0008) -[2023-10-10 13:23:31,076][75634] Fps is (10 sec: 19660.9, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 37257216. Throughput: 0: 1825.8, 1: 1803.3. Samples: 9318812. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-10 13:23:31,077][75634] Avg episode reward: [(0, '28.550'), (1, '29.210')] -[2023-10-10 13:23:34,033][76542] Updated weights for policy 1, policy_version 18180 (0.0008) -[2023-10-10 13:23:34,037][76543] Updated weights for policy 0, policy_version 18213 (0.0008) -[2023-10-10 13:23:34,405][76543] Updated weights for policy 0, policy_version 18223 (0.0008) -[2023-10-10 13:23:34,406][76542] Updated weights for policy 1, policy_version 18190 (0.0008) -[2023-10-10 13:23:34,769][76542] Updated weights for policy 1, policy_version 18200 (0.0008) -[2023-10-10 13:23:34,776][76543] Updated weights for policy 0, policy_version 18233 (0.0007) -[2023-10-10 13:23:36,076][75634] Fps is (10 sec: 13107.1, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 37322752. Throughput: 0: 1813.8, 1: 1811.5. Samples: 9331374. Policy #0 lag: (min: 23.0, avg: 31.7, max: 32.0) -[2023-10-10 13:23:36,076][75634] Avg episode reward: [(0, '29.410'), (1, '29.910')] -[2023-10-10 13:23:38,373][76543] Updated weights for policy 0, policy_version 18243 (0.0009) -[2023-10-10 13:23:38,449][76542] Updated weights for policy 1, policy_version 18210 (0.0007) -[2023-10-10 13:23:38,748][76543] Updated weights for policy 0, policy_version 18253 (0.0008) -[2023-10-10 13:23:38,820][76542] Updated weights for policy 1, policy_version 18220 (0.0007) -[2023-10-10 13:23:39,120][76543] Updated weights for policy 0, policy_version 18263 (0.0008) -[2023-10-10 13:23:39,187][76542] Updated weights for policy 1, policy_version 18230 (0.0009) -[2023-10-10 13:23:39,553][76542] Updated weights for policy 1, policy_version 18240 (0.0009) -[2023-10-10 13:23:41,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 37388288. Throughput: 0: 1820.5, 1: 1815.0. Samples: 9351770. Policy #0 lag: (min: 23.0, avg: 31.7, max: 32.0) -[2023-10-10 13:23:41,077][75634] Avg episode reward: [(0, '27.850'), (1, '29.260')] -[2023-10-10 13:23:42,784][76543] Updated weights for policy 0, policy_version 18273 (0.0008) -[2023-10-10 13:23:43,154][76543] Updated weights for policy 0, policy_version 18283 (0.0008) -[2023-10-10 13:23:43,312][76542] Updated weights for policy 1, policy_version 18250 (0.0010) -[2023-10-10 13:23:43,530][76543] Updated weights for policy 0, policy_version 18293 (0.0008) -[2023-10-10 13:23:43,673][76542] Updated weights for policy 1, policy_version 18260 (0.0008) -[2023-10-10 13:23:43,903][76543] Updated weights for policy 0, policy_version 18303 (0.0008) -[2023-10-10 13:23:44,049][76542] Updated weights for policy 1, policy_version 18270 (0.0009) -[2023-10-10 13:23:46,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 37453824. Throughput: 0: 1819.8, 1: 1819.4. Samples: 9374094. Policy #0 lag: (min: 23.0, avg: 31.7, max: 32.0) -[2023-10-10 13:23:46,077][75634] Avg episode reward: [(0, '27.450'), (1, '29.800')] -[2023-10-10 13:23:47,592][76543] Updated weights for policy 0, policy_version 18313 (0.0008) -[2023-10-10 13:23:47,687][76542] Updated weights for policy 1, policy_version 18280 (0.0008) -[2023-10-10 13:23:47,962][76543] Updated weights for policy 0, policy_version 18323 (0.0008) -[2023-10-10 13:23:48,055][76542] Updated weights for policy 1, policy_version 18290 (0.0008) -[2023-10-10 13:23:48,335][76543] Updated weights for policy 0, policy_version 18333 (0.0007) -[2023-10-10 13:23:48,417][76542] Updated weights for policy 1, policy_version 18300 (0.0008) -[2023-10-10 13:23:51,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 37519360. Throughput: 0: 1821.0, 1: 1816.3. Samples: 9384338. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:23:51,077][75634] Avg episode reward: [(0, '27.300'), (1, '29.230')] -[2023-10-10 13:23:52,086][76542] Updated weights for policy 1, policy_version 18310 (0.0007) -[2023-10-10 13:23:52,124][76543] Updated weights for policy 0, policy_version 18343 (0.0007) -[2023-10-10 13:23:52,450][76542] Updated weights for policy 1, policy_version 18320 (0.0007) -[2023-10-10 13:23:52,496][76543] Updated weights for policy 0, policy_version 18353 (0.0009) -[2023-10-10 13:23:52,829][76542] Updated weights for policy 1, policy_version 18330 (0.0008) -[2023-10-10 13:23:52,858][76543] Updated weights for policy 0, policy_version 18363 (0.0009) -[2023-10-10 13:23:56,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 37584896. Throughput: 0: 1822.0, 1: 1812.1. Samples: 9406668. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:23:56,076][75634] Avg episode reward: [(0, '26.950'), (1, '29.100')] -[2023-10-10 13:23:56,676][76543] Updated weights for policy 0, policy_version 18373 (0.0007) -[2023-10-10 13:23:56,682][76542] Updated weights for policy 1, policy_version 18340 (0.0008) -[2023-10-10 13:23:57,052][76543] Updated weights for policy 0, policy_version 18383 (0.0007) -[2023-10-10 13:23:57,084][76542] Updated weights for policy 1, policy_version 18350 (0.0007) -[2023-10-10 13:23:57,423][76543] Updated weights for policy 0, policy_version 18393 (0.0008) -[2023-10-10 13:23:57,443][76542] Updated weights for policy 1, policy_version 18360 (0.0008) -[2023-10-10 13:24:01,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 37650432. Throughput: 0: 1809.3, 1: 1805.1. Samples: 9428768. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:24:01,076][75634] Avg episode reward: [(0, '28.050'), (1, '30.830')] -[2023-10-10 13:24:01,145][76543] Updated weights for policy 0, policy_version 18403 (0.0007) -[2023-10-10 13:24:01,157][76542] Updated weights for policy 1, policy_version 18370 (0.0009) -[2023-10-10 13:24:01,517][76543] Updated weights for policy 0, policy_version 18413 (0.0008) -[2023-10-10 13:24:01,519][76542] Updated weights for policy 1, policy_version 18380 (0.0009) -[2023-10-10 13:24:01,886][76543] Updated weights for policy 0, policy_version 18423 (0.0007) -[2023-10-10 13:24:01,889][76542] Updated weights for policy 1, policy_version 18390 (0.0008) -[2023-10-10 13:24:02,250][76542] Updated weights for policy 1, policy_version 18400 (0.0010) -[2023-10-10 13:24:05,710][76543] Updated weights for policy 0, policy_version 18433 (0.0008) -[2023-10-10 13:24:05,748][76542] Updated weights for policy 1, policy_version 18410 (0.0007) -[2023-10-10 13:24:06,074][76543] Updated weights for policy 0, policy_version 18443 (0.0007) -[2023-10-10 13:24:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 37715968. Throughput: 0: 1811.6, 1: 1808.3. Samples: 9438592. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:24:06,076][75634] Avg episode reward: [(0, '28.330'), (1, '28.620')] -[2023-10-10 13:24:06,118][76542] Updated weights for policy 1, policy_version 18420 (0.0009) -[2023-10-10 13:24:06,447][76543] Updated weights for policy 0, policy_version 18453 (0.0007) -[2023-10-10 13:24:06,484][76542] Updated weights for policy 1, policy_version 18430 (0.0008) -[2023-10-10 13:24:06,827][76543] Updated weights for policy 0, policy_version 18463 (0.0009) -[2023-10-10 13:24:10,120][76542] Updated weights for policy 1, policy_version 18440 (0.0008) -[2023-10-10 13:24:10,483][76542] Updated weights for policy 1, policy_version 18450 (0.0008) -[2023-10-10 13:24:10,616][76543] Updated weights for policy 0, policy_version 18473 (0.0009) -[2023-10-10 13:24:10,863][76542] Updated weights for policy 1, policy_version 18460 (0.0008) -[2023-10-10 13:24:10,986][76543] Updated weights for policy 0, policy_version 18483 (0.0007) -[2023-10-10 13:24:11,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 37814272. Throughput: 0: 1793.8, 1: 1817.6. Samples: 9461328. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:24:11,077][75634] Avg episode reward: [(0, '29.640'), (1, '28.370')] -[2023-10-10 13:24:11,361][76543] Updated weights for policy 0, policy_version 18493 (0.0011) -[2023-10-10 13:24:14,500][76542] Updated weights for policy 1, policy_version 18470 (0.0009) -[2023-10-10 13:24:14,874][76542] Updated weights for policy 1, policy_version 18480 (0.0008) -[2023-10-10 13:24:15,040][76543] Updated weights for policy 0, policy_version 18503 (0.0007) -[2023-10-10 13:24:15,235][76542] Updated weights for policy 1, policy_version 18490 (0.0008) -[2023-10-10 13:24:15,414][76543] Updated weights for policy 0, policy_version 18513 (0.0008) -[2023-10-10 13:24:15,782][76543] Updated weights for policy 0, policy_version 18523 (0.0007) -[2023-10-10 13:24:16,076][75634] Fps is (10 sec: 19660.6, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 37912576. Throughput: 0: 1805.0, 1: 1822.0. Samples: 9482024. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:24:16,077][75634] Avg episode reward: [(0, '29.430'), (1, '27.570')] -[2023-10-10 13:24:18,920][76542] Updated weights for policy 1, policy_version 18500 (0.0009) -[2023-10-10 13:24:19,288][76542] Updated weights for policy 1, policy_version 18510 (0.0008) -[2023-10-10 13:24:19,466][76543] Updated weights for policy 0, policy_version 18533 (0.0008) -[2023-10-10 13:24:19,667][76542] Updated weights for policy 1, policy_version 18520 (0.0008) -[2023-10-10 13:24:19,826][76543] Updated weights for policy 0, policy_version 18543 (0.0008) -[2023-10-10 13:24:20,200][76543] Updated weights for policy 0, policy_version 18553 (0.0008) -[2023-10-10 13:24:21,076][75634] Fps is (10 sec: 16383.8, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 37978112. Throughput: 0: 1797.2, 1: 1819.8. Samples: 9494140. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:24:21,077][75634] Avg episode reward: [(0, '29.150'), (1, '27.650')] -[2023-10-10 13:24:23,359][76542] Updated weights for policy 1, policy_version 18530 (0.0009) -[2023-10-10 13:24:23,733][76542] Updated weights for policy 1, policy_version 18540 (0.0009) -[2023-10-10 13:24:23,847][76543] Updated weights for policy 0, policy_version 18563 (0.0007) -[2023-10-10 13:24:24,100][76542] Updated weights for policy 1, policy_version 18550 (0.0008) -[2023-10-10 13:24:24,212][76543] Updated weights for policy 0, policy_version 18573 (0.0007) -[2023-10-10 13:24:24,465][76542] Updated weights for policy 1, policy_version 18560 (0.0009) -[2023-10-10 13:24:24,584][76543] Updated weights for policy 0, policy_version 18583 (0.0008) -[2023-10-10 13:24:26,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 38043648. Throughput: 0: 1808.0, 1: 1819.9. Samples: 9515022. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:24:26,076][75634] Avg episode reward: [(0, '29.260'), (1, '27.050')] -[2023-10-10 13:24:28,127][76542] Updated weights for policy 1, policy_version 18570 (0.0010) -[2023-10-10 13:24:28,284][76543] Updated weights for policy 0, policy_version 18593 (0.0008) -[2023-10-10 13:24:28,494][76542] Updated weights for policy 1, policy_version 18580 (0.0007) -[2023-10-10 13:24:28,657][76543] Updated weights for policy 0, policy_version 18603 (0.0009) -[2023-10-10 13:24:28,865][76542] Updated weights for policy 1, policy_version 18590 (0.0008) -[2023-10-10 13:24:29,034][76543] Updated weights for policy 0, policy_version 18613 (0.0010) -[2023-10-10 13:24:29,403][76543] Updated weights for policy 0, policy_version 18623 (0.0007) -[2023-10-10 13:24:31,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 38109184. Throughput: 0: 1790.0, 1: 1823.7. Samples: 9536714. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:24:31,077][75634] Avg episode reward: [(0, '29.200'), (1, '27.730')] -[2023-10-10 13:24:31,089][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000018592_19038208.pth... -[2023-10-10 13:24:31,089][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000018624_19070976.pth... -[2023-10-10 13:24:31,121][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000016896_17301504.pth -[2023-10-10 13:24:31,127][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000016928_17334272.pth -[2023-10-10 13:24:32,537][76542] Updated weights for policy 1, policy_version 18600 (0.0010) -[2023-10-10 13:24:32,906][76542] Updated weights for policy 1, policy_version 18610 (0.0008) -[2023-10-10 13:24:33,124][76543] Updated weights for policy 0, policy_version 18633 (0.0008) -[2023-10-10 13:24:33,270][76542] Updated weights for policy 1, policy_version 18620 (0.0007) -[2023-10-10 13:24:33,502][76543] Updated weights for policy 0, policy_version 18643 (0.0008) -[2023-10-10 13:24:33,872][76543] Updated weights for policy 0, policy_version 18653 (0.0007) -[2023-10-10 13:24:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 38174720. Throughput: 0: 1803.8, 1: 1825.1. Samples: 9547638. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:24:36,076][75634] Avg episode reward: [(0, '29.820'), (1, '30.320')] -[2023-10-10 13:24:36,944][76542] Updated weights for policy 1, policy_version 18630 (0.0009) -[2023-10-10 13:24:37,302][76542] Updated weights for policy 1, policy_version 18640 (0.0008) -[2023-10-10 13:24:37,483][76543] Updated weights for policy 0, policy_version 18663 (0.0008) -[2023-10-10 13:24:37,676][76542] Updated weights for policy 1, policy_version 18650 (0.0009) -[2023-10-10 13:24:37,849][76543] Updated weights for policy 0, policy_version 18673 (0.0008) -[2023-10-10 13:24:38,223][76543] Updated weights for policy 0, policy_version 18683 (0.0008) -[2023-10-10 13:24:41,076][75634] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 38240256. Throughput: 0: 1791.5, 1: 1825.5. Samples: 9569432. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:24:41,076][75634] Avg episode reward: [(0, '29.070'), (1, '27.480')] -[2023-10-10 13:24:41,512][76542] Updated weights for policy 1, policy_version 18660 (0.0010) -[2023-10-10 13:24:41,913][76542] Updated weights for policy 1, policy_version 18670 (0.0009) -[2023-10-10 13:24:41,958][76543] Updated weights for policy 0, policy_version 18693 (0.0009) -[2023-10-10 13:24:42,278][76542] Updated weights for policy 1, policy_version 18680 (0.0009) -[2023-10-10 13:24:42,325][76543] Updated weights for policy 0, policy_version 18703 (0.0009) -[2023-10-10 13:24:42,690][76543] Updated weights for policy 0, policy_version 18713 (0.0008) -[2023-10-10 13:24:45,873][76542] Updated weights for policy 1, policy_version 18690 (0.0007) -[2023-10-10 13:24:46,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 38305792. Throughput: 0: 1794.5, 1: 1837.0. Samples: 9592188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:24:46,076][75634] Avg episode reward: [(0, '29.920'), (1, '27.450')] -[2023-10-10 13:24:46,230][76542] Updated weights for policy 1, policy_version 18700 (0.0007) -[2023-10-10 13:24:46,455][76543] Updated weights for policy 0, policy_version 18723 (0.0008) -[2023-10-10 13:24:46,601][76542] Updated weights for policy 1, policy_version 18710 (0.0008) -[2023-10-10 13:24:46,831][76543] Updated weights for policy 0, policy_version 18733 (0.0009) -[2023-10-10 13:24:46,974][76542] Updated weights for policy 1, policy_version 18720 (0.0007) -[2023-10-10 13:24:47,204][76543] Updated weights for policy 0, policy_version 18743 (0.0010) -[2023-10-10 13:24:50,612][76542] Updated weights for policy 1, policy_version 18730 (0.0012) -[2023-10-10 13:24:50,904][76543] Updated weights for policy 0, policy_version 18753 (0.0009) -[2023-10-10 13:24:50,987][76542] Updated weights for policy 1, policy_version 18740 (0.0009) -[2023-10-10 13:24:51,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 38371328. Throughput: 0: 1797.2, 1: 1836.3. Samples: 9602100. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:24:51,077][75634] Avg episode reward: [(0, '31.050'), (1, '27.690')] -[2023-10-10 13:24:51,267][76543] Updated weights for policy 0, policy_version 18763 (0.0008) -[2023-10-10 13:24:51,362][76542] Updated weights for policy 1, policy_version 18750 (0.0007) -[2023-10-10 13:24:51,641][76543] Updated weights for policy 0, policy_version 18773 (0.0009) -[2023-10-10 13:24:52,020][76543] Updated weights for policy 0, policy_version 18783 (0.0009) -[2023-10-10 13:24:54,798][76542] Updated weights for policy 1, policy_version 18760 (0.0008) -[2023-10-10 13:24:55,172][76542] Updated weights for policy 1, policy_version 18770 (0.0008) -[2023-10-10 13:24:55,544][76542] Updated weights for policy 1, policy_version 18780 (0.0007) -[2023-10-10 13:24:55,774][76543] Updated weights for policy 0, policy_version 18793 (0.0008) -[2023-10-10 13:24:56,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 38469632. Throughput: 0: 1802.3, 1: 1832.4. Samples: 9624892. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:24:56,077][75634] Avg episode reward: [(0, '31.820'), (1, '28.440')] -[2023-10-10 13:24:56,145][76543] Updated weights for policy 0, policy_version 18803 (0.0008) -[2023-10-10 13:24:56,513][76543] Updated weights for policy 0, policy_version 18813 (0.0008) -[2023-10-10 13:24:59,406][76542] Updated weights for policy 1, policy_version 18790 (0.0008) -[2023-10-10 13:24:59,772][76542] Updated weights for policy 1, policy_version 18800 (0.0009) -[2023-10-10 13:25:00,141][76542] Updated weights for policy 1, policy_version 18810 (0.0009) -[2023-10-10 13:25:00,178][76543] Updated weights for policy 0, policy_version 18823 (0.0008) -[2023-10-10 13:25:00,559][76543] Updated weights for policy 0, policy_version 18833 (0.0008) -[2023-10-10 13:25:00,936][76543] Updated weights for policy 0, policy_version 18843 (0.0010) -[2023-10-10 13:25:01,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 38535168. Throughput: 0: 1814.1, 1: 1830.6. Samples: 9646036. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:25:01,077][75634] Avg episode reward: [(0, '32.690'), (1, '28.380')] -[2023-10-10 13:25:03,932][76542] Updated weights for policy 1, policy_version 18820 (0.0008) -[2023-10-10 13:25:04,300][76542] Updated weights for policy 1, policy_version 18830 (0.0008) -[2023-10-10 13:25:04,451][76543] Updated weights for policy 0, policy_version 18853 (0.0008) -[2023-10-10 13:25:04,666][76542] Updated weights for policy 1, policy_version 18840 (0.0008) -[2023-10-10 13:25:04,819][76543] Updated weights for policy 0, policy_version 18863 (0.0007) -[2023-10-10 13:25:05,200][76543] Updated weights for policy 0, policy_version 18873 (0.0007) -[2023-10-10 13:25:06,076][75634] Fps is (10 sec: 16384.0, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 38633472. Throughput: 0: 1813.9, 1: 1822.9. Samples: 9657796. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:25:06,077][75634] Avg episode reward: [(0, '31.430'), (1, '28.360')] -[2023-10-10 13:25:08,375][76542] Updated weights for policy 1, policy_version 18850 (0.0009) -[2023-10-10 13:25:08,735][76542] Updated weights for policy 1, policy_version 18860 (0.0010) -[2023-10-10 13:25:08,752][76543] Updated weights for policy 0, policy_version 18883 (0.0009) -[2023-10-10 13:25:09,107][76542] Updated weights for policy 1, policy_version 18870 (0.0008) -[2023-10-10 13:25:09,123][76543] Updated weights for policy 0, policy_version 18893 (0.0007) -[2023-10-10 13:25:09,467][76542] Updated weights for policy 1, policy_version 18880 (0.0007) -[2023-10-10 13:25:09,489][76543] Updated weights for policy 0, policy_version 18903 (0.0007) -[2023-10-10 13:25:11,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 38699008. Throughput: 0: 1810.7, 1: 1820.7. Samples: 9678436. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:25:11,077][75634] Avg episode reward: [(0, '31.120'), (1, '27.670')] -[2023-10-10 13:25:13,064][76543] Updated weights for policy 0, policy_version 18913 (0.0010) -[2023-10-10 13:25:13,268][76542] Updated weights for policy 1, policy_version 18890 (0.0007) -[2023-10-10 13:25:13,441][76543] Updated weights for policy 0, policy_version 18923 (0.0008) -[2023-10-10 13:25:13,629][76542] Updated weights for policy 1, policy_version 18900 (0.0010) -[2023-10-10 13:25:13,799][76543] Updated weights for policy 0, policy_version 18933 (0.0007) -[2023-10-10 13:25:13,998][76542] Updated weights for policy 1, policy_version 18910 (0.0007) -[2023-10-10 13:25:14,174][76543] Updated weights for policy 0, policy_version 18943 (0.0008) -[2023-10-10 13:25:16,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 38764544. Throughput: 0: 1827.4, 1: 1819.0. Samples: 9700800. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:25:16,076][75634] Avg episode reward: [(0, '28.900'), (1, '28.750')] -[2023-10-10 13:25:17,812][76542] Updated weights for policy 1, policy_version 18920 (0.0007) -[2023-10-10 13:25:17,840][76543] Updated weights for policy 0, policy_version 18953 (0.0008) -[2023-10-10 13:25:18,175][76542] Updated weights for policy 1, policy_version 18930 (0.0008) -[2023-10-10 13:25:18,207][76543] Updated weights for policy 0, policy_version 18963 (0.0007) -[2023-10-10 13:25:18,540][76542] Updated weights for policy 1, policy_version 18940 (0.0008) -[2023-10-10 13:25:18,579][76543] Updated weights for policy 0, policy_version 18973 (0.0009) -[2023-10-10 13:25:21,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 38830080. Throughput: 0: 1824.5, 1: 1815.1. Samples: 9711420. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:25:21,077][75634] Avg episode reward: [(0, '28.460'), (1, '28.400')] -[2023-10-10 13:25:22,259][76542] Updated weights for policy 1, policy_version 18950 (0.0007) -[2023-10-10 13:25:22,422][76543] Updated weights for policy 0, policy_version 18983 (0.0008) -[2023-10-10 13:25:22,628][76542] Updated weights for policy 1, policy_version 18960 (0.0007) -[2023-10-10 13:25:22,789][76543] Updated weights for policy 0, policy_version 18993 (0.0007) -[2023-10-10 13:25:22,991][76542] Updated weights for policy 1, policy_version 18970 (0.0008) -[2023-10-10 13:25:23,152][76543] Updated weights for policy 0, policy_version 19003 (0.0008) -[2023-10-10 13:25:26,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.2). Total num frames: 38895616. Throughput: 0: 1831.7, 1: 1812.3. Samples: 9733410. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:25:26,077][75634] Avg episode reward: [(0, '30.180'), (1, '26.910')] -[2023-10-10 13:25:26,666][76542] Updated weights for policy 1, policy_version 18980 (0.0009) -[2023-10-10 13:25:26,906][76543] Updated weights for policy 0, policy_version 19013 (0.0007) -[2023-10-10 13:25:27,031][76542] Updated weights for policy 1, policy_version 18990 (0.0008) -[2023-10-10 13:25:27,280][76543] Updated weights for policy 0, policy_version 19023 (0.0009) -[2023-10-10 13:25:27,395][76542] Updated weights for policy 1, policy_version 19000 (0.0007) -[2023-10-10 13:25:27,661][76543] Updated weights for policy 0, policy_version 19033 (0.0008) -[2023-10-10 13:25:31,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.2). Total num frames: 38961152. Throughput: 0: 1832.9, 1: 1808.7. Samples: 9756058. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:25:31,076][75634] Avg episode reward: [(0, '28.460'), (1, '24.910')] -[2023-10-10 13:25:31,088][76542] Updated weights for policy 1, policy_version 19010 (0.0008) -[2023-10-10 13:25:31,449][76543] Updated weights for policy 0, policy_version 19043 (0.0007) -[2023-10-10 13:25:31,466][76542] Updated weights for policy 1, policy_version 19020 (0.0010) -[2023-10-10 13:25:31,826][76542] Updated weights for policy 1, policy_version 19030 (0.0009) -[2023-10-10 13:25:31,830][76543] Updated weights for policy 0, policy_version 19053 (0.0008) -[2023-10-10 13:25:32,191][76542] Updated weights for policy 1, policy_version 19040 (0.0007) -[2023-10-10 13:25:32,201][76543] Updated weights for policy 0, policy_version 19063 (0.0007) -[2023-10-10 13:25:35,810][76542] Updated weights for policy 1, policy_version 19050 (0.0008) -[2023-10-10 13:25:35,886][76543] Updated weights for policy 0, policy_version 19073 (0.0008) -[2023-10-10 13:25:36,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 39026688. Throughput: 0: 1832.8, 1: 1804.7. Samples: 9765786. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:25:36,076][75634] Avg episode reward: [(0, '27.880'), (1, '28.310')] -[2023-10-10 13:25:36,185][76542] Updated weights for policy 1, policy_version 19060 (0.0010) -[2023-10-10 13:25:36,266][76543] Updated weights for policy 0, policy_version 19083 (0.0007) -[2023-10-10 13:25:36,558][76542] Updated weights for policy 1, policy_version 19070 (0.0007) -[2023-10-10 13:25:36,636][76543] Updated weights for policy 0, policy_version 19093 (0.0008) -[2023-10-10 13:25:37,005][76543] Updated weights for policy 0, policy_version 19103 (0.0008) -[2023-10-10 13:25:40,207][76542] Updated weights for policy 1, policy_version 19080 (0.0008) -[2023-10-10 13:25:40,575][76542] Updated weights for policy 1, policy_version 19090 (0.0007) -[2023-10-10 13:25:40,822][76543] Updated weights for policy 0, policy_version 19113 (0.0007) -[2023-10-10 13:25:40,949][76542] Updated weights for policy 1, policy_version 19100 (0.0009) -[2023-10-10 13:25:41,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 39092224. Throughput: 0: 1834.3, 1: 1807.3. Samples: 9788766. Policy #0 lag: (min: 26.0, avg: 34.0, max: 58.0) -[2023-10-10 13:25:41,076][75634] Avg episode reward: [(0, '27.180'), (1, '29.100')] -[2023-10-10 13:25:41,203][76543] Updated weights for policy 0, policy_version 19123 (0.0009) -[2023-10-10 13:25:41,573][76543] Updated weights for policy 0, policy_version 19133 (0.0011) -[2023-10-10 13:25:44,611][76542] Updated weights for policy 1, policy_version 19110 (0.0008) -[2023-10-10 13:25:44,976][76542] Updated weights for policy 1, policy_version 19120 (0.0007) -[2023-10-10 13:25:45,258][76543] Updated weights for policy 0, policy_version 19143 (0.0009) -[2023-10-10 13:25:45,345][76542] Updated weights for policy 1, policy_version 19130 (0.0007) -[2023-10-10 13:25:45,636][76543] Updated weights for policy 0, policy_version 19153 (0.0007) -[2023-10-10 13:25:46,007][76543] Updated weights for policy 0, policy_version 19163 (0.0007) -[2023-10-10 13:25:46,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 39190528. Throughput: 0: 1831.6, 1: 1804.5. Samples: 9809660. Policy #0 lag: (min: 26.0, avg: 34.0, max: 58.0) -[2023-10-10 13:25:46,077][75634] Avg episode reward: [(0, '27.320'), (1, '27.900')] -[2023-10-10 13:25:48,943][76542] Updated weights for policy 1, policy_version 19140 (0.0007) -[2023-10-10 13:25:49,312][76542] Updated weights for policy 1, policy_version 19150 (0.0009) -[2023-10-10 13:25:49,583][76543] Updated weights for policy 0, policy_version 19173 (0.0007) -[2023-10-10 13:25:49,685][76542] Updated weights for policy 1, policy_version 19160 (0.0007) -[2023-10-10 13:25:49,966][76543] Updated weights for policy 0, policy_version 19183 (0.0009) -[2023-10-10 13:25:50,342][76543] Updated weights for policy 0, policy_version 19193 (0.0008) -[2023-10-10 13:25:51,076][75634] Fps is (10 sec: 19660.9, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 39288832. Throughput: 0: 1827.8, 1: 1812.4. Samples: 9821602. Policy #0 lag: (min: 26.0, avg: 34.0, max: 58.0) -[2023-10-10 13:25:51,076][75634] Avg episode reward: [(0, '27.320'), (1, '26.890')] -[2023-10-10 13:25:53,394][76542] Updated weights for policy 1, policy_version 19170 (0.0008) -[2023-10-10 13:25:53,763][76542] Updated weights for policy 1, policy_version 19180 (0.0007) -[2023-10-10 13:25:54,009][76543] Updated weights for policy 0, policy_version 19203 (0.0008) -[2023-10-10 13:25:54,130][76542] Updated weights for policy 1, policy_version 19190 (0.0007) -[2023-10-10 13:25:54,383][76543] Updated weights for policy 0, policy_version 19213 (0.0008) -[2023-10-10 13:25:54,495][76542] Updated weights for policy 1, policy_version 19200 (0.0008) -[2023-10-10 13:25:54,762][76543] Updated weights for policy 0, policy_version 19223 (0.0009) -[2023-10-10 13:25:56,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 39354368. Throughput: 0: 1831.9, 1: 1809.1. Samples: 9842282. Policy #0 lag: (min: 26.0, avg: 30.2, max: 58.0) -[2023-10-10 13:25:56,077][75634] Avg episode reward: [(0, '26.290'), (1, '28.110')] -[2023-10-10 13:25:58,255][76542] Updated weights for policy 1, policy_version 19210 (0.0009) -[2023-10-10 13:25:58,330][76543] Updated weights for policy 0, policy_version 19233 (0.0009) -[2023-10-10 13:25:58,622][76542] Updated weights for policy 1, policy_version 19220 (0.0007) -[2023-10-10 13:25:58,695][76543] Updated weights for policy 0, policy_version 19243 (0.0008) -[2023-10-10 13:25:58,997][76542] Updated weights for policy 1, policy_version 19230 (0.0008) -[2023-10-10 13:25:59,069][76543] Updated weights for policy 0, policy_version 19253 (0.0008) -[2023-10-10 13:25:59,441][76543] Updated weights for policy 0, policy_version 19263 (0.0008) -[2023-10-10 13:26:01,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 39419904. Throughput: 0: 1816.4, 1: 1812.4. Samples: 9864098. Policy #0 lag: (min: 26.0, avg: 30.2, max: 58.0) -[2023-10-10 13:26:01,076][75634] Avg episode reward: [(0, '28.390'), (1, '24.710')] -[2023-10-10 13:26:02,857][76542] Updated weights for policy 1, policy_version 19240 (0.0008) -[2023-10-10 13:26:03,103][76543] Updated weights for policy 0, policy_version 19273 (0.0007) -[2023-10-10 13:26:03,227][76542] Updated weights for policy 1, policy_version 19250 (0.0007) -[2023-10-10 13:26:03,473][76543] Updated weights for policy 0, policy_version 19283 (0.0008) -[2023-10-10 13:26:03,592][76542] Updated weights for policy 1, policy_version 19260 (0.0009) -[2023-10-10 13:26:03,843][76543] Updated weights for policy 0, policy_version 19293 (0.0009) -[2023-10-10 13:26:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 39485440. Throughput: 0: 1820.6, 1: 1814.4. Samples: 9874998. Policy #0 lag: (min: 26.0, avg: 30.2, max: 58.0) -[2023-10-10 13:26:06,077][75634] Avg episode reward: [(0, '28.790'), (1, '25.760')] -[2023-10-10 13:26:07,229][76542] Updated weights for policy 1, policy_version 19270 (0.0009) -[2023-10-10 13:26:07,602][76542] Updated weights for policy 1, policy_version 19280 (0.0008) -[2023-10-10 13:26:07,653][76543] Updated weights for policy 0, policy_version 19303 (0.0008) -[2023-10-10 13:26:07,975][76542] Updated weights for policy 1, policy_version 19290 (0.0008) -[2023-10-10 13:26:08,025][76543] Updated weights for policy 0, policy_version 19313 (0.0008) -[2023-10-10 13:26:08,401][76543] Updated weights for policy 0, policy_version 19323 (0.0008) -[2023-10-10 13:26:11,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 39550976. Throughput: 0: 1810.1, 1: 1815.9. Samples: 9896580. Policy #0 lag: (min: 26.0, avg: 30.2, max: 58.0) -[2023-10-10 13:26:11,077][75634] Avg episode reward: [(0, '31.230'), (1, '26.830')] -[2023-10-10 13:26:11,722][76542] Updated weights for policy 1, policy_version 19300 (0.0007) -[2023-10-10 13:26:12,079][76543] Updated weights for policy 0, policy_version 19333 (0.0008) -[2023-10-10 13:26:12,126][76542] Updated weights for policy 1, policy_version 19310 (0.0009) -[2023-10-10 13:26:12,459][76543] Updated weights for policy 0, policy_version 19343 (0.0008) -[2023-10-10 13:26:12,493][76542] Updated weights for policy 1, policy_version 19320 (0.0009) -[2023-10-10 13:26:12,824][76543] Updated weights for policy 0, policy_version 19353 (0.0009) -[2023-10-10 13:26:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 39616512. Throughput: 0: 1813.3, 1: 1812.5. Samples: 9919222. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-10 13:26:16,077][75634] Avg episode reward: [(0, '30.870'), (1, '26.130')] -[2023-10-10 13:26:16,098][76542] Updated weights for policy 1, policy_version 19330 (0.0008) -[2023-10-10 13:26:16,473][76542] Updated weights for policy 1, policy_version 19340 (0.0007) -[2023-10-10 13:26:16,538][76543] Updated weights for policy 0, policy_version 19363 (0.0009) -[2023-10-10 13:26:16,847][76542] Updated weights for policy 1, policy_version 19350 (0.0008) -[2023-10-10 13:26:16,920][76543] Updated weights for policy 0, policy_version 19373 (0.0007) -[2023-10-10 13:26:17,219][76542] Updated weights for policy 1, policy_version 19360 (0.0010) -[2023-10-10 13:26:17,287][76543] Updated weights for policy 0, policy_version 19383 (0.0008) -[2023-10-10 13:26:20,927][76542] Updated weights for policy 1, policy_version 19370 (0.0010) -[2023-10-10 13:26:21,012][76543] Updated weights for policy 0, policy_version 19393 (0.0008) -[2023-10-10 13:26:21,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 39682048. Throughput: 0: 1812.5, 1: 1814.8. Samples: 9929014. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-10 13:26:21,077][75634] Avg episode reward: [(0, '29.910'), (1, '26.650')] -[2023-10-10 13:26:21,293][76542] Updated weights for policy 1, policy_version 19380 (0.0008) -[2023-10-10 13:26:21,374][76543] Updated weights for policy 0, policy_version 19403 (0.0007) -[2023-10-10 13:26:21,659][76542] Updated weights for policy 1, policy_version 19390 (0.0008) -[2023-10-10 13:26:21,755][76543] Updated weights for policy 0, policy_version 19413 (0.0008) -[2023-10-10 13:26:22,130][76543] Updated weights for policy 0, policy_version 19423 (0.0010) -[2023-10-10 13:26:25,446][76542] Updated weights for policy 1, policy_version 19400 (0.0008) -[2023-10-10 13:26:25,816][76542] Updated weights for policy 1, policy_version 19410 (0.0009) -[2023-10-10 13:26:25,895][76543] Updated weights for policy 0, policy_version 19433 (0.0007) -[2023-10-10 13:26:26,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 39747584. Throughput: 0: 1808.1, 1: 1812.2. Samples: 9951680. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-10 13:26:26,077][75634] Avg episode reward: [(0, '29.850'), (1, '27.570')] -[2023-10-10 13:26:26,180][76542] Updated weights for policy 1, policy_version 19420 (0.0009) -[2023-10-10 13:26:26,268][76543] Updated weights for policy 0, policy_version 19443 (0.0008) -[2023-10-10 13:26:26,637][76543] Updated weights for policy 0, policy_version 19453 (0.0008) -[2023-10-10 13:26:29,913][76542] Updated weights for policy 1, policy_version 19430 (0.0009) -[2023-10-10 13:26:30,282][76542] Updated weights for policy 1, policy_version 19440 (0.0009) -[2023-10-10 13:26:30,494][76543] Updated weights for policy 0, policy_version 19463 (0.0008) -[2023-10-10 13:26:30,651][76542] Updated weights for policy 1, policy_version 19450 (0.0009) -[2023-10-10 13:26:30,865][76543] Updated weights for policy 0, policy_version 19473 (0.0010) -[2023-10-10 13:26:31,076][75634] Fps is (10 sec: 16383.5, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 39845888. Throughput: 0: 1806.4, 1: 1820.2. Samples: 9972856. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-10 13:26:31,077][75634] Avg episode reward: [(0, '29.180'), (1, '27.210')] -[2023-10-10 13:26:31,088][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000019456_19922944.pth... -[2023-10-10 13:26:31,123][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000017760_18186240.pth -[2023-10-10 13:26:31,244][76543] Updated weights for policy 0, policy_version 19483 (0.0009) -[2023-10-10 13:26:31,420][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000019488_19955712.pth... -[2023-10-10 13:26:31,449][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000017792_18219008.pth -[2023-10-10 13:26:34,173][76542] Updated weights for policy 1, policy_version 19460 (0.0010) -[2023-10-10 13:26:34,532][76542] Updated weights for policy 1, policy_version 19470 (0.0009) -[2023-10-10 13:26:34,909][76542] Updated weights for policy 1, policy_version 19480 (0.0009) -[2023-10-10 13:26:34,970][76543] Updated weights for policy 0, policy_version 19493 (0.0008) -[2023-10-10 13:26:35,346][76543] Updated weights for policy 0, policy_version 19503 (0.0008) -[2023-10-10 13:26:35,719][76543] Updated weights for policy 0, policy_version 19513 (0.0008) -[2023-10-10 13:26:36,076][75634] Fps is (10 sec: 19661.0, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 39944192. Throughput: 0: 1794.0, 1: 1818.8. Samples: 9984182. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-10 13:26:36,077][75634] Avg episode reward: [(0, '31.090'), (1, '28.110')] -[2023-10-10 13:26:38,683][76542] Updated weights for policy 1, policy_version 19490 (0.0007) -[2023-10-10 13:26:39,049][76542] Updated weights for policy 1, policy_version 19500 (0.0007) -[2023-10-10 13:26:39,275][76543] Updated weights for policy 0, policy_version 19523 (0.0010) -[2023-10-10 13:26:39,412][76542] Updated weights for policy 1, policy_version 19510 (0.0007) -[2023-10-10 13:26:39,637][76543] Updated weights for policy 0, policy_version 19533 (0.0007) -[2023-10-10 13:26:39,779][76542] Updated weights for policy 1, policy_version 19520 (0.0009) -[2023-10-10 13:26:40,019][76543] Updated weights for policy 0, policy_version 19543 (0.0009) -[2023-10-10 13:26:41,076][75634] Fps is (10 sec: 16384.1, 60 sec: 15291.6, 300 sec: 14662.3). Total num frames: 40009728. Throughput: 0: 1808.0, 1: 1824.0. Samples: 10005720. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-10 13:26:41,077][75634] Avg episode reward: [(0, '29.810'), (1, '29.790')] -[2023-10-10 13:26:43,536][76542] Updated weights for policy 1, policy_version 19530 (0.0010) -[2023-10-10 13:26:43,678][76543] Updated weights for policy 0, policy_version 19553 (0.0010) -[2023-10-10 13:26:43,907][76542] Updated weights for policy 1, policy_version 19540 (0.0009) -[2023-10-10 13:26:44,050][76543] Updated weights for policy 0, policy_version 19563 (0.0009) -[2023-10-10 13:26:44,270][76542] Updated weights for policy 1, policy_version 19550 (0.0007) -[2023-10-10 13:26:44,412][76543] Updated weights for policy 0, policy_version 19573 (0.0007) -[2023-10-10 13:26:44,788][76543] Updated weights for policy 0, policy_version 19583 (0.0007) -[2023-10-10 13:26:46,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 40075264. Throughput: 0: 1800.6, 1: 1813.6. Samples: 10026736. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-10 13:26:46,077][75634] Avg episode reward: [(0, '29.720'), (1, '29.170')] -[2023-10-10 13:26:48,044][76542] Updated weights for policy 1, policy_version 19560 (0.0011) -[2023-10-10 13:26:48,413][76542] Updated weights for policy 1, policy_version 19570 (0.0008) -[2023-10-10 13:26:48,658][76543] Updated weights for policy 0, policy_version 19593 (0.0007) -[2023-10-10 13:26:48,788][76542] Updated weights for policy 1, policy_version 19580 (0.0008) -[2023-10-10 13:26:49,044][76543] Updated weights for policy 0, policy_version 19603 (0.0008) -[2023-10-10 13:26:49,410][76543] Updated weights for policy 0, policy_version 19613 (0.0009) -[2023-10-10 13:26:51,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 40140800. Throughput: 0: 1810.8, 1: 1820.3. Samples: 10038396. Policy #0 lag: (min: 24.0, avg: 47.7, max: 56.0) -[2023-10-10 13:26:51,077][75634] Avg episode reward: [(0, '29.050'), (1, '29.630')] -[2023-10-10 13:26:52,461][76542] Updated weights for policy 1, policy_version 19590 (0.0010) -[2023-10-10 13:26:52,825][76542] Updated weights for policy 1, policy_version 19600 (0.0007) -[2023-10-10 13:26:52,981][76543] Updated weights for policy 0, policy_version 19623 (0.0008) -[2023-10-10 13:26:53,199][76542] Updated weights for policy 1, policy_version 19610 (0.0009) -[2023-10-10 13:26:53,354][76543] Updated weights for policy 0, policy_version 19633 (0.0007) -[2023-10-10 13:26:53,716][76543] Updated weights for policy 0, policy_version 19643 (0.0009) -[2023-10-10 13:26:56,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 40206336. Throughput: 0: 1805.9, 1: 1810.7. Samples: 10059326. Policy #0 lag: (min: 24.0, avg: 47.7, max: 56.0) -[2023-10-10 13:26:56,077][75634] Avg episode reward: [(0, '30.320'), (1, '29.650')] -[2023-10-10 13:26:57,076][76542] Updated weights for policy 1, policy_version 19620 (0.0009) -[2023-10-10 13:26:57,381][76543] Updated weights for policy 0, policy_version 19653 (0.0008) -[2023-10-10 13:26:57,483][76542] Updated weights for policy 1, policy_version 19630 (0.0007) -[2023-10-10 13:26:57,752][76543] Updated weights for policy 0, policy_version 19663 (0.0008) -[2023-10-10 13:26:57,847][76542] Updated weights for policy 1, policy_version 19640 (0.0008) -[2023-10-10 13:26:58,127][76543] Updated weights for policy 0, policy_version 19673 (0.0008) -[2023-10-10 13:27:01,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 40271872. Throughput: 0: 1808.8, 1: 1805.8. Samples: 10081876. Policy #0 lag: (min: 24.0, avg: 47.7, max: 56.0) -[2023-10-10 13:27:01,076][75634] Avg episode reward: [(0, '30.500'), (1, '29.120')] -[2023-10-10 13:27:01,628][76542] Updated weights for policy 1, policy_version 19650 (0.0008) -[2023-10-10 13:27:01,815][76543] Updated weights for policy 0, policy_version 19683 (0.0008) -[2023-10-10 13:27:01,995][76542] Updated weights for policy 1, policy_version 19660 (0.0007) -[2023-10-10 13:27:02,184][76543] Updated weights for policy 0, policy_version 19693 (0.0007) -[2023-10-10 13:27:02,372][76542] Updated weights for policy 1, policy_version 19670 (0.0008) -[2023-10-10 13:27:02,552][76543] Updated weights for policy 0, policy_version 19703 (0.0008) -[2023-10-10 13:27:02,737][76542] Updated weights for policy 1, policy_version 19680 (0.0007) -[2023-10-10 13:27:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 40337408. Throughput: 0: 1807.7, 1: 1806.2. Samples: 10091638. Policy #0 lag: (min: 24.0, avg: 47.7, max: 56.0) -[2023-10-10 13:27:06,077][75634] Avg episode reward: [(0, '32.430'), (1, '30.850')] -[2023-10-10 13:27:06,239][76542] Updated weights for policy 1, policy_version 19690 (0.0008) -[2023-10-10 13:27:06,250][76543] Updated weights for policy 0, policy_version 19713 (0.0008) -[2023-10-10 13:27:06,603][76542] Updated weights for policy 1, policy_version 19700 (0.0008) -[2023-10-10 13:27:06,620][76543] Updated weights for policy 0, policy_version 19723 (0.0007) -[2023-10-10 13:27:06,965][76542] Updated weights for policy 1, policy_version 19710 (0.0008) -[2023-10-10 13:27:06,992][76543] Updated weights for policy 0, policy_version 19733 (0.0008) -[2023-10-10 13:27:07,364][76543] Updated weights for policy 0, policy_version 19743 (0.0008) -[2023-10-10 13:27:10,853][76542] Updated weights for policy 1, policy_version 19720 (0.0009) -[2023-10-10 13:27:11,062][76543] Updated weights for policy 0, policy_version 19753 (0.0008) -[2023-10-10 13:27:11,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.2). Total num frames: 40402944. Throughput: 0: 1813.7, 1: 1805.3. Samples: 10114536. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) -[2023-10-10 13:27:11,076][75634] Avg episode reward: [(0, '31.530'), (1, '29.780')] -[2023-10-10 13:27:11,218][76542] Updated weights for policy 1, policy_version 19730 (0.0009) -[2023-10-10 13:27:11,433][76543] Updated weights for policy 0, policy_version 19763 (0.0009) -[2023-10-10 13:27:11,584][76542] Updated weights for policy 1, policy_version 19740 (0.0009) -[2023-10-10 13:27:11,817][76543] Updated weights for policy 0, policy_version 19773 (0.0009) -[2023-10-10 13:27:15,321][76542] Updated weights for policy 1, policy_version 19750 (0.0008) -[2023-10-10 13:27:15,485][76543] Updated weights for policy 0, policy_version 19783 (0.0008) -[2023-10-10 13:27:15,694][76542] Updated weights for policy 1, policy_version 19760 (0.0007) -[2023-10-10 13:27:15,868][76543] Updated weights for policy 0, policy_version 19793 (0.0007) -[2023-10-10 13:27:16,068][76542] Updated weights for policy 1, policy_version 19770 (0.0009) -[2023-10-10 13:27:16,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 40468480. Throughput: 0: 1825.6, 1: 1809.3. Samples: 10136426. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) -[2023-10-10 13:27:16,076][75634] Avg episode reward: [(0, '30.770'), (1, '30.390')] -[2023-10-10 13:27:16,224][76543] Updated weights for policy 0, policy_version 19803 (0.0008) -[2023-10-10 13:27:19,632][76542] Updated weights for policy 1, policy_version 19780 (0.0008) -[2023-10-10 13:27:19,804][76543] Updated weights for policy 0, policy_version 19813 (0.0009) -[2023-10-10 13:27:20,001][76542] Updated weights for policy 1, policy_version 19790 (0.0009) -[2023-10-10 13:27:20,170][76543] Updated weights for policy 0, policy_version 19823 (0.0007) -[2023-10-10 13:27:20,368][76542] Updated weights for policy 1, policy_version 19800 (0.0008) -[2023-10-10 13:27:20,544][76543] Updated weights for policy 0, policy_version 19833 (0.0007) -[2023-10-10 13:27:21,076][75634] Fps is (10 sec: 19660.9, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 40599552. Throughput: 0: 1825.9, 1: 1793.8. Samples: 10147068. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) -[2023-10-10 13:27:21,076][75634] Avg episode reward: [(0, '30.190'), (1, '30.610')] -[2023-10-10 13:27:24,000][76542] Updated weights for policy 1, policy_version 19810 (0.0008) -[2023-10-10 13:27:24,179][76543] Updated weights for policy 0, policy_version 19843 (0.0009) -[2023-10-10 13:27:24,364][76542] Updated weights for policy 1, policy_version 19820 (0.0009) -[2023-10-10 13:27:24,545][76543] Updated weights for policy 0, policy_version 19853 (0.0007) -[2023-10-10 13:27:24,731][76542] Updated weights for policy 1, policy_version 19830 (0.0009) -[2023-10-10 13:27:24,925][76543] Updated weights for policy 0, policy_version 19863 (0.0007) -[2023-10-10 13:27:25,100][76542] Updated weights for policy 1, policy_version 19840 (0.0008) -[2023-10-10 13:27:26,076][75634] Fps is (10 sec: 19660.6, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 40665088. Throughput: 0: 1822.0, 1: 1804.4. Samples: 10168908. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:27:26,077][75634] Avg episode reward: [(0, '33.070'), (1, '28.790')] -[2023-10-10 13:27:28,678][76543] Updated weights for policy 0, policy_version 19873 (0.0007) -[2023-10-10 13:27:28,870][76542] Updated weights for policy 1, policy_version 19850 (0.0008) -[2023-10-10 13:27:29,057][76543] Updated weights for policy 0, policy_version 19883 (0.0009) -[2023-10-10 13:27:29,243][76542] Updated weights for policy 1, policy_version 19860 (0.0008) -[2023-10-10 13:27:29,428][76543] Updated weights for policy 0, policy_version 19893 (0.0008) -[2023-10-10 13:27:29,604][76542] Updated weights for policy 1, policy_version 19870 (0.0008) -[2023-10-10 13:27:29,793][76543] Updated weights for policy 0, policy_version 19903 (0.0007) -[2023-10-10 13:27:31,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 40730624. Throughput: 0: 1821.7, 1: 1800.8. Samples: 10189750. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:27:31,077][75634] Avg episode reward: [(0, '33.620'), (1, '31.840')] -[2023-10-10 13:27:33,323][76542] Updated weights for policy 1, policy_version 19880 (0.0009) -[2023-10-10 13:27:33,626][76543] Updated weights for policy 0, policy_version 19913 (0.0007) -[2023-10-10 13:27:33,694][76542] Updated weights for policy 1, policy_version 19890 (0.0007) -[2023-10-10 13:27:34,002][76543] Updated weights for policy 0, policy_version 19923 (0.0007) -[2023-10-10 13:27:34,068][76542] Updated weights for policy 1, policy_version 19900 (0.0008) -[2023-10-10 13:27:34,371][76543] Updated weights for policy 0, policy_version 19933 (0.0008) -[2023-10-10 13:27:36,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 40796160. Throughput: 0: 1819.8, 1: 1806.5. Samples: 10201582. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:27:36,077][75634] Avg episode reward: [(0, '32.540'), (1, '27.950')] -[2023-10-10 13:27:37,744][76542] Updated weights for policy 1, policy_version 19910 (0.0009) -[2023-10-10 13:27:38,118][76542] Updated weights for policy 1, policy_version 19920 (0.0009) -[2023-10-10 13:27:38,141][76543] Updated weights for policy 0, policy_version 19943 (0.0008) -[2023-10-10 13:27:38,485][76542] Updated weights for policy 1, policy_version 19930 (0.0008) -[2023-10-10 13:27:38,519][76543] Updated weights for policy 0, policy_version 19953 (0.0007) -[2023-10-10 13:27:38,901][76543] Updated weights for policy 0, policy_version 19963 (0.0007) -[2023-10-10 13:27:41,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 40861696. Throughput: 0: 1815.8, 1: 1806.4. Samples: 10222326. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:27:41,077][75634] Avg episode reward: [(0, '31.670'), (1, '28.150')] -[2023-10-10 13:27:42,126][76542] Updated weights for policy 1, policy_version 19940 (0.0008) -[2023-10-10 13:27:42,396][76543] Updated weights for policy 0, policy_version 19973 (0.0008) -[2023-10-10 13:27:42,527][76542] Updated weights for policy 1, policy_version 19950 (0.0010) -[2023-10-10 13:27:42,770][76543] Updated weights for policy 0, policy_version 19983 (0.0007) -[2023-10-10 13:27:42,885][76542] Updated weights for policy 1, policy_version 19960 (0.0008) -[2023-10-10 13:27:43,148][76543] Updated weights for policy 0, policy_version 19993 (0.0008) -[2023-10-10 13:27:46,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 40927232. Throughput: 0: 1815.1, 1: 1812.8. Samples: 10245132. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:27:46,076][75634] Avg episode reward: [(0, '30.550'), (1, '28.550')] -[2023-10-10 13:27:46,547][76542] Updated weights for policy 1, policy_version 19970 (0.0007) -[2023-10-10 13:27:46,855][76543] Updated weights for policy 0, policy_version 20003 (0.0008) -[2023-10-10 13:27:46,918][76542] Updated weights for policy 1, policy_version 19980 (0.0007) -[2023-10-10 13:27:47,232][76543] Updated weights for policy 0, policy_version 20013 (0.0008) -[2023-10-10 13:27:47,279][76542] Updated weights for policy 1, policy_version 19990 (0.0011) -[2023-10-10 13:27:47,597][76543] Updated weights for policy 0, policy_version 20023 (0.0007) -[2023-10-10 13:27:47,643][76542] Updated weights for policy 1, policy_version 20000 (0.0009) -[2023-10-10 13:27:51,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 40992768. Throughput: 0: 1817.4, 1: 1814.0. Samples: 10255048. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:27:51,076][75634] Avg episode reward: [(0, '30.470'), (1, '28.360')] -[2023-10-10 13:27:51,187][76543] Updated weights for policy 0, policy_version 20033 (0.0008) -[2023-10-10 13:27:51,388][76542] Updated weights for policy 1, policy_version 20010 (0.0007) -[2023-10-10 13:27:51,550][76543] Updated weights for policy 0, policy_version 20043 (0.0007) -[2023-10-10 13:27:51,744][76542] Updated weights for policy 1, policy_version 20020 (0.0008) -[2023-10-10 13:27:51,925][76543] Updated weights for policy 0, policy_version 20053 (0.0008) -[2023-10-10 13:27:52,112][76542] Updated weights for policy 1, policy_version 20030 (0.0007) -[2023-10-10 13:27:52,296][76543] Updated weights for policy 0, policy_version 20063 (0.0007) -[2023-10-10 13:27:55,790][76542] Updated weights for policy 1, policy_version 20040 (0.0008) -[2023-10-10 13:27:56,007][76543] Updated weights for policy 0, policy_version 20073 (0.0009) -[2023-10-10 13:27:56,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 41058304. Throughput: 0: 1815.7, 1: 1813.6. Samples: 10277856. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:27:56,076][75634] Avg episode reward: [(0, '32.950'), (1, '26.610')] -[2023-10-10 13:27:56,159][76542] Updated weights for policy 1, policy_version 20050 (0.0007) -[2023-10-10 13:27:56,386][76543] Updated weights for policy 0, policy_version 20083 (0.0008) -[2023-10-10 13:27:56,520][76542] Updated weights for policy 1, policy_version 20060 (0.0008) -[2023-10-10 13:27:56,760][76543] Updated weights for policy 0, policy_version 20093 (0.0007) -[2023-10-10 13:28:00,187][76542] Updated weights for policy 1, policy_version 20070 (0.0008) -[2023-10-10 13:28:00,399][76543] Updated weights for policy 0, policy_version 20103 (0.0008) -[2023-10-10 13:28:00,559][76542] Updated weights for policy 1, policy_version 20080 (0.0009) -[2023-10-10 13:28:00,775][76543] Updated weights for policy 0, policy_version 20113 (0.0008) -[2023-10-10 13:28:00,928][76542] Updated weights for policy 1, policy_version 20090 (0.0007) -[2023-10-10 13:28:01,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 41123840. Throughput: 0: 1810.4, 1: 1814.9. Samples: 10299566. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:28:01,076][75634] Avg episode reward: [(0, '30.510'), (1, '25.590')] -[2023-10-10 13:28:01,152][76543] Updated weights for policy 0, policy_version 20123 (0.0009) -[2023-10-10 13:28:04,533][76542] Updated weights for policy 1, policy_version 20100 (0.0008) -[2023-10-10 13:28:04,873][76543] Updated weights for policy 0, policy_version 20133 (0.0010) -[2023-10-10 13:28:04,900][76542] Updated weights for policy 1, policy_version 20110 (0.0008) -[2023-10-10 13:28:05,241][76543] Updated weights for policy 0, policy_version 20143 (0.0007) -[2023-10-10 13:28:05,259][76542] Updated weights for policy 1, policy_version 20120 (0.0008) -[2023-10-10 13:28:05,626][76543] Updated weights for policy 0, policy_version 20153 (0.0008) -[2023-10-10 13:28:06,076][75634] Fps is (10 sec: 19660.9, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 41254912. Throughput: 0: 1814.3, 1: 1817.0. Samples: 10310474. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:28:06,076][75634] Avg episode reward: [(0, '30.670'), (1, '25.600')] -[2023-10-10 13:28:09,066][76542] Updated weights for policy 1, policy_version 20130 (0.0009) -[2023-10-10 13:28:09,433][76542] Updated weights for policy 1, policy_version 20140 (0.0008) -[2023-10-10 13:28:09,489][76543] Updated weights for policy 0, policy_version 20163 (0.0009) -[2023-10-10 13:28:09,794][76542] Updated weights for policy 1, policy_version 20150 (0.0008) -[2023-10-10 13:28:09,857][76543] Updated weights for policy 0, policy_version 20173 (0.0008) -[2023-10-10 13:28:10,160][76542] Updated weights for policy 1, policy_version 20160 (0.0010) -[2023-10-10 13:28:10,224][76543] Updated weights for policy 0, policy_version 20183 (0.0007) -[2023-10-10 13:28:11,076][75634] Fps is (10 sec: 19660.6, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 41320448. Throughput: 0: 1817.1, 1: 1815.8. Samples: 10332388. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:28:11,077][75634] Avg episode reward: [(0, '29.800'), (1, '25.710')] -[2023-10-10 13:28:13,858][76542] Updated weights for policy 1, policy_version 20170 (0.0007) -[2023-10-10 13:28:13,893][76543] Updated weights for policy 0, policy_version 20193 (0.0009) -[2023-10-10 13:28:14,218][76542] Updated weights for policy 1, policy_version 20180 (0.0007) -[2023-10-10 13:28:14,260][76543] Updated weights for policy 0, policy_version 20203 (0.0008) -[2023-10-10 13:28:14,587][76542] Updated weights for policy 1, policy_version 20190 (0.0008) -[2023-10-10 13:28:14,633][76543] Updated weights for policy 0, policy_version 20213 (0.0010) -[2023-10-10 13:28:15,006][76543] Updated weights for policy 0, policy_version 20223 (0.0010) -[2023-10-10 13:28:16,076][75634] Fps is (10 sec: 13107.2, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 41385984. Throughput: 0: 1810.1, 1: 1815.7. Samples: 10352910. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:28:16,076][75634] Avg episode reward: [(0, '29.770'), (1, '29.460')] -[2023-10-10 13:28:18,387][76542] Updated weights for policy 1, policy_version 20200 (0.0007) -[2023-10-10 13:28:18,753][76542] Updated weights for policy 1, policy_version 20210 (0.0010) -[2023-10-10 13:28:18,813][76543] Updated weights for policy 0, policy_version 20233 (0.0007) -[2023-10-10 13:28:19,115][76542] Updated weights for policy 1, policy_version 20220 (0.0007) -[2023-10-10 13:28:19,183][76543] Updated weights for policy 0, policy_version 20243 (0.0009) -[2023-10-10 13:28:19,556][76543] Updated weights for policy 0, policy_version 20253 (0.0009) -[2023-10-10 13:28:21,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 41451520. Throughput: 0: 1814.1, 1: 1817.7. Samples: 10365010. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-10 13:28:21,076][75634] Avg episode reward: [(0, '29.200'), (1, '28.120')] -[2023-10-10 13:28:22,826][76542] Updated weights for policy 1, policy_version 20230 (0.0008) -[2023-10-10 13:28:23,138][76543] Updated weights for policy 0, policy_version 20263 (0.0008) -[2023-10-10 13:28:23,197][76542] Updated weights for policy 1, policy_version 20240 (0.0007) -[2023-10-10 13:28:23,515][76543] Updated weights for policy 0, policy_version 20273 (0.0007) -[2023-10-10 13:28:23,559][76542] Updated weights for policy 1, policy_version 20250 (0.0007) -[2023-10-10 13:28:23,887][76543] Updated weights for policy 0, policy_version 20283 (0.0008) -[2023-10-10 13:28:26,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 41517056. Throughput: 0: 1817.4, 1: 1814.9. Samples: 10385778. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-10 13:28:26,077][75634] Avg episode reward: [(0, '29.850'), (1, '29.240')] -[2023-10-10 13:28:27,463][76543] Updated weights for policy 0, policy_version 20293 (0.0009) -[2023-10-10 13:28:27,521][76542] Updated weights for policy 1, policy_version 20260 (0.0009) -[2023-10-10 13:28:27,850][76543] Updated weights for policy 0, policy_version 20303 (0.0008) -[2023-10-10 13:28:27,912][76542] Updated weights for policy 1, policy_version 20270 (0.0009) -[2023-10-10 13:28:28,207][76543] Updated weights for policy 0, policy_version 20313 (0.0009) -[2023-10-10 13:28:28,281][76542] Updated weights for policy 1, policy_version 20280 (0.0009) -[2023-10-10 13:28:31,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 41582592. Throughput: 0: 1820.8, 1: 1809.2. Samples: 10408482. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-10 13:28:31,077][75634] Avg episode reward: [(0, '31.910'), (1, '30.540')] -[2023-10-10 13:28:31,085][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000020288_20774912.pth... -[2023-10-10 13:28:31,085][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000020320_20807680.pth... -[2023-10-10 13:28:31,116][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000018592_19038208.pth -[2023-10-10 13:28:31,118][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000018624_19070976.pth -[2023-10-10 13:28:32,027][76543] Updated weights for policy 0, policy_version 20323 (0.0008) -[2023-10-10 13:28:32,035][76542] Updated weights for policy 1, policy_version 20290 (0.0009) -[2023-10-10 13:28:32,390][76542] Updated weights for policy 1, policy_version 20300 (0.0007) -[2023-10-10 13:28:32,398][76543] Updated weights for policy 0, policy_version 20333 (0.0009) -[2023-10-10 13:28:32,756][76542] Updated weights for policy 1, policy_version 20310 (0.0008) -[2023-10-10 13:28:32,774][76543] Updated weights for policy 0, policy_version 20343 (0.0009) -[2023-10-10 13:28:33,129][76542] Updated weights for policy 1, policy_version 20320 (0.0009) -[2023-10-10 13:28:36,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 41648128. Throughput: 0: 1815.5, 1: 1805.3. Samples: 10417984. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-10 13:28:36,077][75634] Avg episode reward: [(0, '30.030'), (1, '31.110')] -[2023-10-10 13:28:36,476][76543] Updated weights for policy 0, policy_version 20353 (0.0010) -[2023-10-10 13:28:36,844][76543] Updated weights for policy 0, policy_version 20363 (0.0009) -[2023-10-10 13:28:36,888][76542] Updated weights for policy 1, policy_version 20330 (0.0007) -[2023-10-10 13:28:37,209][76543] Updated weights for policy 0, policy_version 20373 (0.0008) -[2023-10-10 13:28:37,259][76542] Updated weights for policy 1, policy_version 20340 (0.0008) -[2023-10-10 13:28:37,581][76543] Updated weights for policy 0, policy_version 20383 (0.0007) -[2023-10-10 13:28:37,625][76542] Updated weights for policy 1, policy_version 20350 (0.0009) -[2023-10-10 13:28:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 41713664. Throughput: 0: 1811.1, 1: 1803.7. Samples: 10440524. Policy #0 lag: (min: 18.0, avg: 18.3, max: 31.0) -[2023-10-10 13:28:41,077][75634] Avg episode reward: [(0, '30.390'), (1, '27.910')] -[2023-10-10 13:28:41,163][76542] Updated weights for policy 1, policy_version 20360 (0.0008) -[2023-10-10 13:28:41,355][76543] Updated weights for policy 0, policy_version 20393 (0.0008) -[2023-10-10 13:28:41,538][76542] Updated weights for policy 1, policy_version 20370 (0.0007) -[2023-10-10 13:28:41,730][76543] Updated weights for policy 0, policy_version 20403 (0.0007) -[2023-10-10 13:28:41,910][76542] Updated weights for policy 1, policy_version 20380 (0.0009) -[2023-10-10 13:28:42,100][76543] Updated weights for policy 0, policy_version 20413 (0.0008) -[2023-10-10 13:28:45,580][76542] Updated weights for policy 1, policy_version 20390 (0.0008) -[2023-10-10 13:28:45,950][76542] Updated weights for policy 1, policy_version 20400 (0.0009) -[2023-10-10 13:28:46,021][76543] Updated weights for policy 0, policy_version 20423 (0.0009) -[2023-10-10 13:28:46,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 41779200. Throughput: 0: 1810.2, 1: 1819.1. Samples: 10462884. Policy #0 lag: (min: 18.0, avg: 18.3, max: 31.0) -[2023-10-10 13:28:46,076][75634] Avg episode reward: [(0, '34.320'), (1, '28.340')] -[2023-10-10 13:28:46,315][76542] Updated weights for policy 1, policy_version 20410 (0.0009) -[2023-10-10 13:28:46,415][76543] Updated weights for policy 0, policy_version 20433 (0.0008) -[2023-10-10 13:28:46,776][76543] Updated weights for policy 0, policy_version 20443 (0.0008) -[2023-10-10 13:28:50,008][76542] Updated weights for policy 1, policy_version 20420 (0.0007) -[2023-10-10 13:28:50,284][76543] Updated weights for policy 0, policy_version 20453 (0.0007) -[2023-10-10 13:28:50,388][76542] Updated weights for policy 1, policy_version 20430 (0.0008) -[2023-10-10 13:28:50,640][76543] Updated weights for policy 0, policy_version 20463 (0.0008) -[2023-10-10 13:28:50,750][76542] Updated weights for policy 1, policy_version 20440 (0.0009) -[2023-10-10 13:28:51,015][76543] Updated weights for policy 0, policy_version 20473 (0.0009) -[2023-10-10 13:28:51,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 41877504. Throughput: 0: 1804.0, 1: 1806.6. Samples: 10472952. Policy #0 lag: (min: 18.0, avg: 18.3, max: 31.0) -[2023-10-10 13:28:51,077][75634] Avg episode reward: [(0, '32.490'), (1, '31.960')] -[2023-10-10 13:28:54,397][76542] Updated weights for policy 1, policy_version 20450 (0.0009) -[2023-10-10 13:28:54,755][76543] Updated weights for policy 0, policy_version 20483 (0.0008) -[2023-10-10 13:28:54,774][76542] Updated weights for policy 1, policy_version 20460 (0.0008) -[2023-10-10 13:28:55,126][76543] Updated weights for policy 0, policy_version 20493 (0.0007) -[2023-10-10 13:28:55,134][76542] Updated weights for policy 1, policy_version 20470 (0.0007) -[2023-10-10 13:28:55,501][76542] Updated weights for policy 1, policy_version 20480 (0.0007) -[2023-10-10 13:28:55,513][76543] Updated weights for policy 0, policy_version 20503 (0.0009) -[2023-10-10 13:28:56,076][75634] Fps is (10 sec: 19660.4, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 41975808. Throughput: 0: 1803.0, 1: 1817.4. Samples: 10495304. Policy #0 lag: (min: 30.0, avg: 37.4, max: 62.0) -[2023-10-10 13:28:56,077][75634] Avg episode reward: [(0, '32.330'), (1, '31.910')] -[2023-10-10 13:28:59,111][76542] Updated weights for policy 1, policy_version 20490 (0.0012) -[2023-10-10 13:28:59,257][76543] Updated weights for policy 0, policy_version 20513 (0.0010) -[2023-10-10 13:28:59,470][76542] Updated weights for policy 1, policy_version 20500 (0.0007) -[2023-10-10 13:28:59,625][76543] Updated weights for policy 0, policy_version 20523 (0.0009) -[2023-10-10 13:28:59,847][76542] Updated weights for policy 1, policy_version 20510 (0.0008) -[2023-10-10 13:28:59,993][76543] Updated weights for policy 0, policy_version 20533 (0.0010) -[2023-10-10 13:29:00,365][76543] Updated weights for policy 0, policy_version 20543 (0.0007) -[2023-10-10 13:29:01,076][75634] Fps is (10 sec: 16384.0, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 42041344. Throughput: 0: 1809.9, 1: 1810.6. Samples: 10515834. Policy #0 lag: (min: 30.0, avg: 37.4, max: 62.0) -[2023-10-10 13:29:01,077][75634] Avg episode reward: [(0, '31.980'), (1, '30.320')] -[2023-10-10 13:29:03,472][76542] Updated weights for policy 1, policy_version 20520 (0.0008) -[2023-10-10 13:29:03,841][76542] Updated weights for policy 1, policy_version 20530 (0.0008) -[2023-10-10 13:29:04,204][76542] Updated weights for policy 1, policy_version 20540 (0.0007) -[2023-10-10 13:29:04,241][76543] Updated weights for policy 0, policy_version 20553 (0.0010) -[2023-10-10 13:29:04,608][76543] Updated weights for policy 0, policy_version 20563 (0.0011) -[2023-10-10 13:29:04,993][76543] Updated weights for policy 0, policy_version 20573 (0.0010) -[2023-10-10 13:29:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 42106880. Throughput: 0: 1797.8, 1: 1818.7. Samples: 10527754. Policy #0 lag: (min: 30.0, avg: 37.4, max: 62.0) -[2023-10-10 13:29:06,077][75634] Avg episode reward: [(0, '31.930'), (1, '32.210')] -[2023-10-10 13:29:07,860][76542] Updated weights for policy 1, policy_version 20550 (0.0009) -[2023-10-10 13:29:08,232][76542] Updated weights for policy 1, policy_version 20560 (0.0008) -[2023-10-10 13:29:08,602][76542] Updated weights for policy 1, policy_version 20570 (0.0007) -[2023-10-10 13:29:08,785][76543] Updated weights for policy 0, policy_version 20583 (0.0009) -[2023-10-10 13:29:09,147][76543] Updated weights for policy 0, policy_version 20593 (0.0009) -[2023-10-10 13:29:09,521][76543] Updated weights for policy 0, policy_version 20603 (0.0010) -[2023-10-10 13:29:11,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 42172416. Throughput: 0: 1807.6, 1: 1816.0. Samples: 10548840. Policy #0 lag: (min: 30.0, avg: 37.4, max: 62.0) -[2023-10-10 13:29:11,077][75634] Avg episode reward: [(0, '30.890'), (1, '32.040')] -[2023-10-10 13:29:12,399][76542] Updated weights for policy 1, policy_version 20580 (0.0007) -[2023-10-10 13:29:12,789][76542] Updated weights for policy 1, policy_version 20590 (0.0008) -[2023-10-10 13:29:13,144][76543] Updated weights for policy 0, policy_version 20613 (0.0009) -[2023-10-10 13:29:13,153][76542] Updated weights for policy 1, policy_version 20600 (0.0008) -[2023-10-10 13:29:13,521][76543] Updated weights for policy 0, policy_version 20623 (0.0007) -[2023-10-10 13:29:13,886][76543] Updated weights for policy 0, policy_version 20633 (0.0008) -[2023-10-10 13:29:16,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 42237952. Throughput: 0: 1788.5, 1: 1826.6. Samples: 10571162. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 13:29:16,076][75634] Avg episode reward: [(0, '31.430'), (1, '29.910')] -[2023-10-10 13:29:16,644][76542] Updated weights for policy 1, policy_version 20610 (0.0009) -[2023-10-10 13:29:17,022][76542] Updated weights for policy 1, policy_version 20620 (0.0008) -[2023-10-10 13:29:17,391][76542] Updated weights for policy 1, policy_version 20630 (0.0007) -[2023-10-10 13:29:17,590][76543] Updated weights for policy 0, policy_version 20643 (0.0008) -[2023-10-10 13:29:17,758][76542] Updated weights for policy 1, policy_version 20640 (0.0007) -[2023-10-10 13:29:17,958][76543] Updated weights for policy 0, policy_version 20653 (0.0009) -[2023-10-10 13:29:18,344][76543] Updated weights for policy 0, policy_version 20663 (0.0007) -[2023-10-10 13:29:21,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 42303488. Throughput: 0: 1806.9, 1: 1837.2. Samples: 10581966. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 13:29:21,077][75634] Avg episode reward: [(0, '33.680'), (1, '27.720')] -[2023-10-10 13:29:21,424][76542] Updated weights for policy 1, policy_version 20650 (0.0010) -[2023-10-10 13:29:21,795][76542] Updated weights for policy 1, policy_version 20660 (0.0008) -[2023-10-10 13:29:21,854][76543] Updated weights for policy 0, policy_version 20673 (0.0009) -[2023-10-10 13:29:22,154][76542] Updated weights for policy 1, policy_version 20670 (0.0007) -[2023-10-10 13:29:22,229][76543] Updated weights for policy 0, policy_version 20683 (0.0008) -[2023-10-10 13:29:22,604][76543] Updated weights for policy 0, policy_version 20693 (0.0010) -[2023-10-10 13:29:22,978][76543] Updated weights for policy 0, policy_version 20703 (0.0007) -[2023-10-10 13:29:25,918][76542] Updated weights for policy 1, policy_version 20680 (0.0008) -[2023-10-10 13:29:26,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 42369024. Throughput: 0: 1798.3, 1: 1836.9. Samples: 10604110. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 13:29:26,076][75634] Avg episode reward: [(0, '32.430'), (1, '27.700')] -[2023-10-10 13:29:26,281][76542] Updated weights for policy 1, policy_version 20690 (0.0008) -[2023-10-10 13:29:26,658][76542] Updated weights for policy 1, policy_version 20700 (0.0008) -[2023-10-10 13:29:26,730][76543] Updated weights for policy 0, policy_version 20713 (0.0009) -[2023-10-10 13:29:27,110][76543] Updated weights for policy 0, policy_version 20723 (0.0011) -[2023-10-10 13:29:27,470][76543] Updated weights for policy 0, policy_version 20733 (0.0009) -[2023-10-10 13:29:30,297][76542] Updated weights for policy 1, policy_version 20710 (0.0008) -[2023-10-10 13:29:30,661][76542] Updated weights for policy 1, policy_version 20720 (0.0009) -[2023-10-10 13:29:31,024][76542] Updated weights for policy 1, policy_version 20730 (0.0008) -[2023-10-10 13:29:31,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 42434560. Throughput: 0: 1802.6, 1: 1823.9. Samples: 10626080. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 13:29:31,077][75634] Avg episode reward: [(0, '33.120'), (1, '29.210')] -[2023-10-10 13:29:31,164][76543] Updated weights for policy 0, policy_version 20743 (0.0010) -[2023-10-10 13:29:31,543][76543] Updated weights for policy 0, policy_version 20753 (0.0008) -[2023-10-10 13:29:31,918][76543] Updated weights for policy 0, policy_version 20763 (0.0008) -[2023-10-10 13:29:34,709][76542] Updated weights for policy 1, policy_version 20740 (0.0008) -[2023-10-10 13:29:35,075][76542] Updated weights for policy 1, policy_version 20750 (0.0008) -[2023-10-10 13:29:35,454][76542] Updated weights for policy 1, policy_version 20760 (0.0008) -[2023-10-10 13:29:35,640][76543] Updated weights for policy 0, policy_version 20773 (0.0009) -[2023-10-10 13:29:36,021][76543] Updated weights for policy 0, policy_version 20783 (0.0008) -[2023-10-10 13:29:36,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 42532864. Throughput: 0: 1803.8, 1: 1830.5. Samples: 10636494. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:29:36,076][75634] Avg episode reward: [(0, '32.020'), (1, '27.790')] -[2023-10-10 13:29:36,395][76543] Updated weights for policy 0, policy_version 20793 (0.0007) -[2023-10-10 13:29:38,984][76542] Updated weights for policy 1, policy_version 20770 (0.0008) -[2023-10-10 13:29:39,352][76542] Updated weights for policy 1, policy_version 20780 (0.0009) -[2023-10-10 13:29:39,716][76542] Updated weights for policy 1, policy_version 20790 (0.0008) -[2023-10-10 13:29:40,084][76542] Updated weights for policy 1, policy_version 20800 (0.0008) -[2023-10-10 13:29:40,207][76543] Updated weights for policy 0, policy_version 20803 (0.0008) -[2023-10-10 13:29:40,583][76543] Updated weights for policy 0, policy_version 20813 (0.0009) -[2023-10-10 13:29:40,952][76543] Updated weights for policy 0, policy_version 20823 (0.0011) -[2023-10-10 13:29:41,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 42598400. Throughput: 0: 1796.0, 1: 1824.6. Samples: 10658234. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:29:41,077][75634] Avg episode reward: [(0, '33.140'), (1, '31.270')] -[2023-10-10 13:29:43,859][76542] Updated weights for policy 1, policy_version 20810 (0.0008) -[2023-10-10 13:29:44,216][76542] Updated weights for policy 1, policy_version 20820 (0.0008) -[2023-10-10 13:29:44,560][76543] Updated weights for policy 0, policy_version 20833 (0.0008) -[2023-10-10 13:29:44,589][76542] Updated weights for policy 1, policy_version 20830 (0.0008) -[2023-10-10 13:29:44,935][76543] Updated weights for policy 0, policy_version 20843 (0.0009) -[2023-10-10 13:29:45,310][76543] Updated weights for policy 0, policy_version 20853 (0.0011) -[2023-10-10 13:29:45,682][76543] Updated weights for policy 0, policy_version 20863 (0.0010) -[2023-10-10 13:29:46,076][75634] Fps is (10 sec: 16383.6, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 42696704. Throughput: 0: 1811.5, 1: 1835.0. Samples: 10679928. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:29:46,077][75634] Avg episode reward: [(0, '33.030'), (1, '31.360')] -[2023-10-10 13:29:48,346][76542] Updated weights for policy 1, policy_version 20840 (0.0008) -[2023-10-10 13:29:48,714][76542] Updated weights for policy 1, policy_version 20850 (0.0007) -[2023-10-10 13:29:49,085][76542] Updated weights for policy 1, policy_version 20860 (0.0007) -[2023-10-10 13:29:49,357][76543] Updated weights for policy 0, policy_version 20873 (0.0011) -[2023-10-10 13:29:49,738][76543] Updated weights for policy 0, policy_version 20883 (0.0009) -[2023-10-10 13:29:50,121][76543] Updated weights for policy 0, policy_version 20893 (0.0011) -[2023-10-10 13:29:51,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 42762240. Throughput: 0: 1810.4, 1: 1824.5. Samples: 10691324. Policy #0 lag: (min: 3.0, avg: 6.5, max: 35.0) -[2023-10-10 13:29:51,077][75634] Avg episode reward: [(0, '35.510'), (1, '31.730')] -[2023-10-10 13:29:51,078][76362] Saving new best policy, reward=35.510! -[2023-10-10 13:29:52,740][76542] Updated weights for policy 1, policy_version 20870 (0.0009) -[2023-10-10 13:29:53,099][76542] Updated weights for policy 1, policy_version 20880 (0.0010) -[2023-10-10 13:29:53,473][76542] Updated weights for policy 1, policy_version 20890 (0.0007) -[2023-10-10 13:29:53,708][76543] Updated weights for policy 0, policy_version 20903 (0.0008) -[2023-10-10 13:29:54,071][76543] Updated weights for policy 0, policy_version 20913 (0.0008) -[2023-10-10 13:29:54,447][76543] Updated weights for policy 0, policy_version 20923 (0.0009) -[2023-10-10 13:29:56,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 42827776. Throughput: 0: 1811.9, 1: 1826.9. Samples: 10712584. Policy #0 lag: (min: 3.0, avg: 6.5, max: 35.0) -[2023-10-10 13:29:56,076][75634] Avg episode reward: [(0, '32.330'), (1, '32.160')] -[2023-10-10 13:29:57,153][76542] Updated weights for policy 1, policy_version 20900 (0.0009) -[2023-10-10 13:29:57,531][76542] Updated weights for policy 1, policy_version 20910 (0.0010) -[2023-10-10 13:29:57,909][76542] Updated weights for policy 1, policy_version 20920 (0.0010) -[2023-10-10 13:29:58,037][76543] Updated weights for policy 0, policy_version 20933 (0.0010) -[2023-10-10 13:29:58,415][76543] Updated weights for policy 0, policy_version 20943 (0.0009) -[2023-10-10 13:29:58,777][76543] Updated weights for policy 0, policy_version 20953 (0.0008) -[2023-10-10 13:30:01,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 42893312. Throughput: 0: 1820.4, 1: 1825.9. Samples: 10735248. Policy #0 lag: (min: 3.0, avg: 6.5, max: 35.0) -[2023-10-10 13:30:01,077][75634] Avg episode reward: [(0, '33.130'), (1, '29.050')] -[2023-10-10 13:30:01,544][76542] Updated weights for policy 1, policy_version 20930 (0.0008) -[2023-10-10 13:30:01,904][76542] Updated weights for policy 1, policy_version 20940 (0.0007) -[2023-10-10 13:30:02,274][76542] Updated weights for policy 1, policy_version 20950 (0.0008) -[2023-10-10 13:30:02,437][76543] Updated weights for policy 0, policy_version 20963 (0.0008) -[2023-10-10 13:30:02,648][76542] Updated weights for policy 1, policy_version 20960 (0.0007) -[2023-10-10 13:30:02,808][76543] Updated weights for policy 0, policy_version 20973 (0.0008) -[2023-10-10 13:30:03,182][76543] Updated weights for policy 0, policy_version 20983 (0.0007) -[2023-10-10 13:30:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 42958848. Throughput: 0: 1817.9, 1: 1818.8. Samples: 10745618. Policy #0 lag: (min: 3.0, avg: 6.5, max: 35.0) -[2023-10-10 13:30:06,077][75634] Avg episode reward: [(0, '32.760'), (1, '28.720')] -[2023-10-10 13:30:06,563][76542] Updated weights for policy 1, policy_version 20970 (0.0008) -[2023-10-10 13:30:06,930][76542] Updated weights for policy 1, policy_version 20980 (0.0008) -[2023-10-10 13:30:06,942][76543] Updated weights for policy 0, policy_version 20993 (0.0009) -[2023-10-10 13:30:07,285][76542] Updated weights for policy 1, policy_version 20990 (0.0007) -[2023-10-10 13:30:07,302][76543] Updated weights for policy 0, policy_version 21003 (0.0008) -[2023-10-10 13:30:07,674][76543] Updated weights for policy 0, policy_version 21013 (0.0007) -[2023-10-10 13:30:08,045][76543] Updated weights for policy 0, policy_version 21023 (0.0010) -[2023-10-10 13:30:11,022][76542] Updated weights for policy 1, policy_version 21000 (0.0007) -[2023-10-10 13:30:11,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 43024384. Throughput: 0: 1818.1, 1: 1815.1. Samples: 10767606. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:30:11,076][75634] Avg episode reward: [(0, '32.060'), (1, '28.500')] -[2023-10-10 13:30:11,389][76542] Updated weights for policy 1, policy_version 21010 (0.0009) -[2023-10-10 13:30:11,765][76542] Updated weights for policy 1, policy_version 21020 (0.0007) -[2023-10-10 13:30:11,803][76543] Updated weights for policy 0, policy_version 21033 (0.0007) -[2023-10-10 13:30:12,173][76543] Updated weights for policy 0, policy_version 21043 (0.0011) -[2023-10-10 13:30:12,548][76543] Updated weights for policy 0, policy_version 21053 (0.0009) -[2023-10-10 13:30:15,266][76542] Updated weights for policy 1, policy_version 21030 (0.0007) -[2023-10-10 13:30:15,637][76542] Updated weights for policy 1, policy_version 21040 (0.0009) -[2023-10-10 13:30:16,008][76542] Updated weights for policy 1, policy_version 21050 (0.0009) -[2023-10-10 13:30:16,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 43089920. Throughput: 0: 1821.1, 1: 1820.9. Samples: 10789970. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:30:16,076][75634] Avg episode reward: [(0, '32.430'), (1, '28.560')] -[2023-10-10 13:30:16,161][76543] Updated weights for policy 0, policy_version 21063 (0.0008) -[2023-10-10 13:30:16,535][76543] Updated weights for policy 0, policy_version 21073 (0.0010) -[2023-10-10 13:30:16,904][76543] Updated weights for policy 0, policy_version 21083 (0.0008) -[2023-10-10 13:30:19,758][76542] Updated weights for policy 1, policy_version 21060 (0.0007) -[2023-10-10 13:30:20,135][76542] Updated weights for policy 1, policy_version 21070 (0.0008) -[2023-10-10 13:30:20,503][76542] Updated weights for policy 1, policy_version 21080 (0.0009) -[2023-10-10 13:30:20,588][76543] Updated weights for policy 0, policy_version 21093 (0.0009) -[2023-10-10 13:30:20,956][76543] Updated weights for policy 0, policy_version 21103 (0.0009) -[2023-10-10 13:30:21,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 43188224. Throughput: 0: 1821.2, 1: 1824.0. Samples: 10800530. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:30:21,076][75634] Avg episode reward: [(0, '31.850'), (1, '28.670')] -[2023-10-10 13:30:21,318][76543] Updated weights for policy 0, policy_version 21113 (0.0007) -[2023-10-10 13:30:24,280][76542] Updated weights for policy 1, policy_version 21090 (0.0008) -[2023-10-10 13:30:24,647][76542] Updated weights for policy 1, policy_version 21100 (0.0011) -[2023-10-10 13:30:24,905][76543] Updated weights for policy 0, policy_version 21123 (0.0008) -[2023-10-10 13:30:25,013][76542] Updated weights for policy 1, policy_version 21110 (0.0009) -[2023-10-10 13:30:25,266][76543] Updated weights for policy 0, policy_version 21133 (0.0007) -[2023-10-10 13:30:25,378][76542] Updated weights for policy 1, policy_version 21120 (0.0009) -[2023-10-10 13:30:25,635][76543] Updated weights for policy 0, policy_version 21143 (0.0008) -[2023-10-10 13:30:26,076][75634] Fps is (10 sec: 19660.4, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 43286528. Throughput: 0: 1835.9, 1: 1820.4. Samples: 10822764. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:30:26,077][75634] Avg episode reward: [(0, '32.720'), (1, '28.540')] -[2023-10-10 13:30:29,058][76542] Updated weights for policy 1, policy_version 21130 (0.0008) -[2023-10-10 13:30:29,356][76543] Updated weights for policy 0, policy_version 21153 (0.0007) -[2023-10-10 13:30:29,424][76542] Updated weights for policy 1, policy_version 21140 (0.0009) -[2023-10-10 13:30:29,729][76543] Updated weights for policy 0, policy_version 21163 (0.0007) -[2023-10-10 13:30:29,786][76542] Updated weights for policy 1, policy_version 21150 (0.0008) -[2023-10-10 13:30:30,103][76543] Updated weights for policy 0, policy_version 21173 (0.0007) -[2023-10-10 13:30:30,460][76543] Updated weights for policy 0, policy_version 21183 (0.0007) -[2023-10-10 13:30:31,076][75634] Fps is (10 sec: 16383.6, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 43352064. Throughput: 0: 1825.5, 1: 1818.1. Samples: 10843890. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:30:31,077][75634] Avg episode reward: [(0, '32.770'), (1, '29.550')] -[2023-10-10 13:30:31,087][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000021152_21659648.pth... -[2023-10-10 13:30:31,087][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000021184_21692416.pth... -[2023-10-10 13:30:31,117][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000019456_19922944.pth -[2023-10-10 13:30:31,132][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000019488_19955712.pth -[2023-10-10 13:30:33,276][76542] Updated weights for policy 1, policy_version 21160 (0.0009) -[2023-10-10 13:30:33,654][76542] Updated weights for policy 1, policy_version 21170 (0.0011) -[2023-10-10 13:30:34,020][76542] Updated weights for policy 1, policy_version 21180 (0.0009) -[2023-10-10 13:30:34,246][76543] Updated weights for policy 0, policy_version 21193 (0.0011) -[2023-10-10 13:30:34,615][76543] Updated weights for policy 0, policy_version 21203 (0.0011) -[2023-10-10 13:30:34,990][76543] Updated weights for policy 0, policy_version 21213 (0.0009) -[2023-10-10 13:30:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 43417600. Throughput: 0: 1826.1, 1: 1818.9. Samples: 10855350. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:30:36,077][75634] Avg episode reward: [(0, '33.310'), (1, '32.720')] -[2023-10-10 13:30:36,078][76421] Saving new best policy, reward=32.720! -[2023-10-10 13:30:37,691][76542] Updated weights for policy 1, policy_version 21190 (0.0008) -[2023-10-10 13:30:38,055][76542] Updated weights for policy 1, policy_version 21200 (0.0010) -[2023-10-10 13:30:38,433][76542] Updated weights for policy 1, policy_version 21210 (0.0008) -[2023-10-10 13:30:38,739][76543] Updated weights for policy 0, policy_version 21223 (0.0008) -[2023-10-10 13:30:39,110][76543] Updated weights for policy 0, policy_version 21233 (0.0009) -[2023-10-10 13:30:39,478][76543] Updated weights for policy 0, policy_version 21243 (0.0009) -[2023-10-10 13:30:41,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 43483136. Throughput: 0: 1826.2, 1: 1818.2. Samples: 10876580. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:30:41,077][75634] Avg episode reward: [(0, '33.430'), (1, '31.320')] -[2023-10-10 13:30:42,253][76542] Updated weights for policy 1, policy_version 21220 (0.0009) -[2023-10-10 13:30:42,643][76542] Updated weights for policy 1, policy_version 21230 (0.0009) -[2023-10-10 13:30:43,007][76542] Updated weights for policy 1, policy_version 21240 (0.0009) -[2023-10-10 13:30:43,102][76543] Updated weights for policy 0, policy_version 21253 (0.0008) -[2023-10-10 13:30:43,477][76543] Updated weights for policy 0, policy_version 21263 (0.0009) -[2023-10-10 13:30:43,852][76543] Updated weights for policy 0, policy_version 21273 (0.0010) -[2023-10-10 13:30:46,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 43548672. Throughput: 0: 1815.7, 1: 1815.4. Samples: 10898648. Policy #0 lag: (min: 31.0, avg: 46.5, max: 63.0) -[2023-10-10 13:30:46,077][75634] Avg episode reward: [(0, '31.180'), (1, '29.400')] -[2023-10-10 13:30:46,632][76542] Updated weights for policy 1, policy_version 21250 (0.0007) -[2023-10-10 13:30:46,999][76542] Updated weights for policy 1, policy_version 21260 (0.0008) -[2023-10-10 13:30:47,360][76542] Updated weights for policy 1, policy_version 21270 (0.0009) -[2023-10-10 13:30:47,639][76543] Updated weights for policy 0, policy_version 21283 (0.0007) -[2023-10-10 13:30:47,739][76542] Updated weights for policy 1, policy_version 21280 (0.0007) -[2023-10-10 13:30:48,008][76543] Updated weights for policy 0, policy_version 21293 (0.0009) -[2023-10-10 13:30:48,384][76543] Updated weights for policy 0, policy_version 21303 (0.0008) -[2023-10-10 13:30:51,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 43614208. Throughput: 0: 1820.3, 1: 1818.8. Samples: 10909378. Policy #0 lag: (min: 31.0, avg: 46.5, max: 63.0) -[2023-10-10 13:30:51,077][75634] Avg episode reward: [(0, '31.720'), (1, '28.970')] -[2023-10-10 13:30:51,444][76542] Updated weights for policy 1, policy_version 21290 (0.0010) -[2023-10-10 13:30:51,814][76542] Updated weights for policy 1, policy_version 21300 (0.0008) -[2023-10-10 13:30:52,074][76543] Updated weights for policy 0, policy_version 21313 (0.0009) -[2023-10-10 13:30:52,190][76542] Updated weights for policy 1, policy_version 21310 (0.0009) -[2023-10-10 13:30:52,448][76543] Updated weights for policy 0, policy_version 21323 (0.0007) -[2023-10-10 13:30:52,821][76543] Updated weights for policy 0, policy_version 21333 (0.0007) -[2023-10-10 13:30:53,192][76543] Updated weights for policy 0, policy_version 21343 (0.0007) -[2023-10-10 13:30:55,946][76542] Updated weights for policy 1, policy_version 21320 (0.0009) -[2023-10-10 13:30:56,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 43679744. Throughput: 0: 1819.7, 1: 1824.8. Samples: 10931608. Policy #0 lag: (min: 31.0, avg: 46.5, max: 63.0) -[2023-10-10 13:30:56,076][75634] Avg episode reward: [(0, '30.800'), (1, '33.390')] -[2023-10-10 13:30:56,315][76542] Updated weights for policy 1, policy_version 21330 (0.0009) -[2023-10-10 13:30:56,685][76542] Updated weights for policy 1, policy_version 21340 (0.0008) -[2023-10-10 13:30:56,833][76421] Saving new best policy, reward=33.390! -[2023-10-10 13:30:56,853][76543] Updated weights for policy 0, policy_version 21353 (0.0007) -[2023-10-10 13:30:57,221][76543] Updated weights for policy 0, policy_version 21363 (0.0010) -[2023-10-10 13:30:57,591][76543] Updated weights for policy 0, policy_version 21373 (0.0010) -[2023-10-10 13:31:00,511][76542] Updated weights for policy 1, policy_version 21350 (0.0007) -[2023-10-10 13:31:00,877][76542] Updated weights for policy 1, policy_version 21360 (0.0007) -[2023-10-10 13:31:01,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 43745280. Throughput: 0: 1818.1, 1: 1824.4. Samples: 10953884. Policy #0 lag: (min: 31.0, avg: 46.5, max: 63.0) -[2023-10-10 13:31:01,077][75634] Avg episode reward: [(0, '30.030'), (1, '32.620')] -[2023-10-10 13:31:01,243][76543] Updated weights for policy 0, policy_version 21383 (0.0007) -[2023-10-10 13:31:01,254][76542] Updated weights for policy 1, policy_version 21370 (0.0008) -[2023-10-10 13:31:01,613][76543] Updated weights for policy 0, policy_version 21393 (0.0007) -[2023-10-10 13:31:02,001][76543] Updated weights for policy 0, policy_version 21403 (0.0007) -[2023-10-10 13:31:04,807][76542] Updated weights for policy 1, policy_version 21380 (0.0008) -[2023-10-10 13:31:05,172][76542] Updated weights for policy 1, policy_version 21390 (0.0009) -[2023-10-10 13:31:05,544][76542] Updated weights for policy 1, policy_version 21400 (0.0009) -[2023-10-10 13:31:05,724][76543] Updated weights for policy 0, policy_version 21413 (0.0007) -[2023-10-10 13:31:06,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 43843584. Throughput: 0: 1817.6, 1: 1825.7. Samples: 10964478. Policy #0 lag: (min: 12.0, avg: 14.2, max: 44.0) -[2023-10-10 13:31:06,076][75634] Avg episode reward: [(0, '29.280'), (1, '33.120')] -[2023-10-10 13:31:06,090][76543] Updated weights for policy 0, policy_version 21423 (0.0010) -[2023-10-10 13:31:06,458][76543] Updated weights for policy 0, policy_version 21433 (0.0007) -[2023-10-10 13:31:09,156][76542] Updated weights for policy 1, policy_version 21410 (0.0008) -[2023-10-10 13:31:09,526][76542] Updated weights for policy 1, policy_version 21420 (0.0007) -[2023-10-10 13:31:09,893][76542] Updated weights for policy 1, policy_version 21430 (0.0008) -[2023-10-10 13:31:09,999][76543] Updated weights for policy 0, policy_version 21443 (0.0008) -[2023-10-10 13:31:10,261][76542] Updated weights for policy 1, policy_version 21440 (0.0008) -[2023-10-10 13:31:10,362][76543] Updated weights for policy 0, policy_version 21453 (0.0008) -[2023-10-10 13:31:10,732][76543] Updated weights for policy 0, policy_version 21463 (0.0008) -[2023-10-10 13:31:11,076][75634] Fps is (10 sec: 19661.0, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 43941888. Throughput: 0: 1810.9, 1: 1829.7. Samples: 10986592. Policy #0 lag: (min: 12.0, avg: 14.2, max: 44.0) -[2023-10-10 13:31:11,076][75634] Avg episode reward: [(0, '28.250'), (1, '29.670')] -[2023-10-10 13:31:13,826][76542] Updated weights for policy 1, policy_version 21450 (0.0010) -[2023-10-10 13:31:14,192][76542] Updated weights for policy 1, policy_version 21460 (0.0010) -[2023-10-10 13:31:14,474][76543] Updated weights for policy 0, policy_version 21473 (0.0009) -[2023-10-10 13:31:14,567][76542] Updated weights for policy 1, policy_version 21470 (0.0007) -[2023-10-10 13:31:14,847][76543] Updated weights for policy 0, policy_version 21483 (0.0010) -[2023-10-10 13:31:15,224][76543] Updated weights for policy 0, policy_version 21493 (0.0009) -[2023-10-10 13:31:15,596][76543] Updated weights for policy 0, policy_version 21503 (0.0008) -[2023-10-10 13:31:16,076][75634] Fps is (10 sec: 16384.0, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 44007424. Throughput: 0: 1815.3, 1: 1828.7. Samples: 11007866. Policy #0 lag: (min: 12.0, avg: 14.2, max: 44.0) -[2023-10-10 13:31:16,076][75634] Avg episode reward: [(0, '30.920'), (1, '32.300')] -[2023-10-10 13:31:18,122][76542] Updated weights for policy 1, policy_version 21480 (0.0008) -[2023-10-10 13:31:18,492][76542] Updated weights for policy 1, policy_version 21490 (0.0008) -[2023-10-10 13:31:18,873][76542] Updated weights for policy 1, policy_version 21500 (0.0008) -[2023-10-10 13:31:19,213][76543] Updated weights for policy 0, policy_version 21513 (0.0009) -[2023-10-10 13:31:19,580][76543] Updated weights for policy 0, policy_version 21523 (0.0009) -[2023-10-10 13:31:19,955][76543] Updated weights for policy 0, policy_version 21533 (0.0009) -[2023-10-10 13:31:21,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 44072960. Throughput: 0: 1817.5, 1: 1825.7. Samples: 11019294. Policy #0 lag: (min: 10.0, avg: 10.0, max: 12.0) -[2023-10-10 13:31:21,077][75634] Avg episode reward: [(0, '32.680'), (1, '32.450')] -[2023-10-10 13:31:22,564][76542] Updated weights for policy 1, policy_version 21510 (0.0008) -[2023-10-10 13:31:22,937][76542] Updated weights for policy 1, policy_version 21520 (0.0007) -[2023-10-10 13:31:23,302][76542] Updated weights for policy 1, policy_version 21530 (0.0007) -[2023-10-10 13:31:23,675][76543] Updated weights for policy 0, policy_version 21543 (0.0009) -[2023-10-10 13:31:24,051][76543] Updated weights for policy 0, policy_version 21553 (0.0008) -[2023-10-10 13:31:24,417][76543] Updated weights for policy 0, policy_version 21563 (0.0011) -[2023-10-10 13:31:26,076][75634] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 44138496. Throughput: 0: 1815.1, 1: 1834.4. Samples: 11040812. Policy #0 lag: (min: 10.0, avg: 10.0, max: 12.0) -[2023-10-10 13:31:26,077][75634] Avg episode reward: [(0, '32.010'), (1, '33.390')] -[2023-10-10 13:31:26,989][76542] Updated weights for policy 1, policy_version 21540 (0.0009) -[2023-10-10 13:31:27,385][76542] Updated weights for policy 1, policy_version 21550 (0.0007) -[2023-10-10 13:31:27,740][76542] Updated weights for policy 1, policy_version 21560 (0.0008) -[2023-10-10 13:31:28,081][76543] Updated weights for policy 0, policy_version 21573 (0.0009) -[2023-10-10 13:31:28,456][76543] Updated weights for policy 0, policy_version 21583 (0.0008) -[2023-10-10 13:31:28,832][76543] Updated weights for policy 0, policy_version 21593 (0.0008) -[2023-10-10 13:31:31,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 44204032. Throughput: 0: 1820.2, 1: 1840.4. Samples: 11063374. Policy #0 lag: (min: 10.0, avg: 10.0, max: 12.0) -[2023-10-10 13:31:31,077][75634] Avg episode reward: [(0, '30.760'), (1, '33.560')] -[2023-10-10 13:31:31,084][76421] Saving new best policy, reward=33.560! -[2023-10-10 13:31:31,380][76542] Updated weights for policy 1, policy_version 21570 (0.0010) -[2023-10-10 13:31:31,750][76542] Updated weights for policy 1, policy_version 21580 (0.0009) -[2023-10-10 13:31:32,116][76542] Updated weights for policy 1, policy_version 21590 (0.0008) -[2023-10-10 13:31:32,471][76543] Updated weights for policy 0, policy_version 21603 (0.0007) -[2023-10-10 13:31:32,491][76542] Updated weights for policy 1, policy_version 21600 (0.0010) -[2023-10-10 13:31:32,839][76543] Updated weights for policy 0, policy_version 21613 (0.0007) -[2023-10-10 13:31:33,215][76543] Updated weights for policy 0, policy_version 21623 (0.0011) -[2023-10-10 13:31:36,076][75634] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14440.2). Total num frames: 44269568. Throughput: 0: 1818.4, 1: 1834.7. Samples: 11073766. Policy #0 lag: (min: 10.0, avg: 10.0, max: 12.0) -[2023-10-10 13:31:36,076][75634] Avg episode reward: [(0, '32.490'), (1, '32.090')] -[2023-10-10 13:31:36,244][76542] Updated weights for policy 1, policy_version 21610 (0.0008) -[2023-10-10 13:31:36,625][76542] Updated weights for policy 1, policy_version 21620 (0.0009) -[2023-10-10 13:31:36,928][76543] Updated weights for policy 0, policy_version 21633 (0.0008) -[2023-10-10 13:31:36,992][76542] Updated weights for policy 1, policy_version 21630 (0.0008) -[2023-10-10 13:31:37,301][76543] Updated weights for policy 0, policy_version 21643 (0.0010) -[2023-10-10 13:31:37,671][76543] Updated weights for policy 0, policy_version 21653 (0.0008) -[2023-10-10 13:31:38,050][76543] Updated weights for policy 0, policy_version 21663 (0.0010) -[2023-10-10 13:31:40,522][76542] Updated weights for policy 1, policy_version 21640 (0.0009) -[2023-10-10 13:31:40,893][76542] Updated weights for policy 1, policy_version 21650 (0.0010) -[2023-10-10 13:31:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 44335104. Throughput: 0: 1817.5, 1: 1838.8. Samples: 11096138. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-10 13:31:41,076][75634] Avg episode reward: [(0, '31.560'), (1, '34.130')] -[2023-10-10 13:31:41,262][76542] Updated weights for policy 1, policy_version 21660 (0.0009) -[2023-10-10 13:31:41,400][76421] Saving new best policy, reward=34.130! -[2023-10-10 13:31:41,783][76543] Updated weights for policy 0, policy_version 21673 (0.0008) -[2023-10-10 13:31:42,159][76543] Updated weights for policy 0, policy_version 21683 (0.0008) -[2023-10-10 13:31:42,527][76543] Updated weights for policy 0, policy_version 21693 (0.0009) -[2023-10-10 13:31:44,915][76542] Updated weights for policy 1, policy_version 21670 (0.0008) -[2023-10-10 13:31:45,288][76542] Updated weights for policy 1, policy_version 21680 (0.0008) -[2023-10-10 13:31:45,655][76542] Updated weights for policy 1, policy_version 21690 (0.0009) -[2023-10-10 13:31:46,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 44433408. Throughput: 0: 1813.7, 1: 1822.9. Samples: 11117530. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-10 13:31:46,077][75634] Avg episode reward: [(0, '29.650'), (1, '30.900')] -[2023-10-10 13:31:46,367][76543] Updated weights for policy 0, policy_version 21703 (0.0009) -[2023-10-10 13:31:46,752][76543] Updated weights for policy 0, policy_version 21713 (0.0007) -[2023-10-10 13:31:47,121][76543] Updated weights for policy 0, policy_version 21723 (0.0009) -[2023-10-10 13:31:49,355][76542] Updated weights for policy 1, policy_version 21700 (0.0007) -[2023-10-10 13:31:49,711][76542] Updated weights for policy 1, policy_version 21710 (0.0009) -[2023-10-10 13:31:50,089][76542] Updated weights for policy 1, policy_version 21720 (0.0008) -[2023-10-10 13:31:50,737][76543] Updated weights for policy 0, policy_version 21733 (0.0009) -[2023-10-10 13:31:51,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 44498944. Throughput: 0: 1815.7, 1: 1831.5. Samples: 11128606. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-10 13:31:51,077][75634] Avg episode reward: [(0, '30.120'), (1, '29.900')] -[2023-10-10 13:31:51,100][76543] Updated weights for policy 0, policy_version 21743 (0.0008) -[2023-10-10 13:31:51,478][76543] Updated weights for policy 0, policy_version 21753 (0.0007) -[2023-10-10 13:31:53,819][76542] Updated weights for policy 1, policy_version 21730 (0.0009) -[2023-10-10 13:31:54,196][76542] Updated weights for policy 1, policy_version 21740 (0.0010) -[2023-10-10 13:31:54,562][76542] Updated weights for policy 1, policy_version 21750 (0.0008) -[2023-10-10 13:31:54,926][76542] Updated weights for policy 1, policy_version 21760 (0.0011) -[2023-10-10 13:31:55,061][76543] Updated weights for policy 0, policy_version 21763 (0.0008) -[2023-10-10 13:31:55,431][76543] Updated weights for policy 0, policy_version 21773 (0.0007) -[2023-10-10 13:31:55,813][76543] Updated weights for policy 0, policy_version 21783 (0.0007) -[2023-10-10 13:31:56,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 44564480. Throughput: 0: 1824.3, 1: 1820.5. Samples: 11150608. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-10 13:31:56,076][75634] Avg episode reward: [(0, '31.110'), (1, '27.320')] -[2023-10-10 13:31:58,646][76542] Updated weights for policy 1, policy_version 21770 (0.0007) -[2023-10-10 13:31:59,005][76542] Updated weights for policy 1, policy_version 21780 (0.0007) -[2023-10-10 13:31:59,377][76542] Updated weights for policy 1, policy_version 21790 (0.0008) -[2023-10-10 13:31:59,517][76543] Updated weights for policy 0, policy_version 21793 (0.0008) -[2023-10-10 13:31:59,890][76543] Updated weights for policy 0, policy_version 21803 (0.0009) -[2023-10-10 13:32:00,271][76543] Updated weights for policy 0, policy_version 21813 (0.0009) -[2023-10-10 13:32:00,640][76543] Updated weights for policy 0, policy_version 21823 (0.0008) -[2023-10-10 13:32:01,076][75634] Fps is (10 sec: 16384.2, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 44662784. Throughput: 0: 1828.6, 1: 1826.8. Samples: 11172360. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:32:01,077][75634] Avg episode reward: [(0, '30.850'), (1, '29.940')] -[2023-10-10 13:32:03,099][76542] Updated weights for policy 1, policy_version 21800 (0.0008) -[2023-10-10 13:32:03,467][76542] Updated weights for policy 1, policy_version 21810 (0.0008) -[2023-10-10 13:32:03,837][76542] Updated weights for policy 1, policy_version 21820 (0.0007) -[2023-10-10 13:32:04,280][76543] Updated weights for policy 0, policy_version 21833 (0.0010) -[2023-10-10 13:32:04,648][76543] Updated weights for policy 0, policy_version 21843 (0.0010) -[2023-10-10 13:32:05,025][76543] Updated weights for policy 0, policy_version 21853 (0.0009) -[2023-10-10 13:32:06,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 44728320. Throughput: 0: 1825.0, 1: 1829.2. Samples: 11183732. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:32:06,076][75634] Avg episode reward: [(0, '32.970'), (1, '27.850')] -[2023-10-10 13:32:07,475][76542] Updated weights for policy 1, policy_version 21830 (0.0009) -[2023-10-10 13:32:07,851][76542] Updated weights for policy 1, policy_version 21840 (0.0007) -[2023-10-10 13:32:08,207][76542] Updated weights for policy 1, policy_version 21850 (0.0008) -[2023-10-10 13:32:08,724][76543] Updated weights for policy 0, policy_version 21863 (0.0009) -[2023-10-10 13:32:09,098][76543] Updated weights for policy 0, policy_version 21873 (0.0010) -[2023-10-10 13:32:09,464][76543] Updated weights for policy 0, policy_version 21883 (0.0010) -[2023-10-10 13:32:11,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14662.3). Total num frames: 44793856. Throughput: 0: 1826.8, 1: 1833.7. Samples: 11205534. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:32:11,077][75634] Avg episode reward: [(0, '34.570'), (1, '30.660')] -[2023-10-10 13:32:12,055][76542] Updated weights for policy 1, policy_version 21860 (0.0009) -[2023-10-10 13:32:12,440][76542] Updated weights for policy 1, policy_version 21870 (0.0008) -[2023-10-10 13:32:12,806][76542] Updated weights for policy 1, policy_version 21880 (0.0008) -[2023-10-10 13:32:13,078][76543] Updated weights for policy 0, policy_version 21893 (0.0009) -[2023-10-10 13:32:13,458][76543] Updated weights for policy 0, policy_version 21903 (0.0009) -[2023-10-10 13:32:13,836][76543] Updated weights for policy 0, policy_version 21913 (0.0009) -[2023-10-10 13:32:16,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 44859392. Throughput: 0: 1828.0, 1: 1823.4. Samples: 11227686. Policy #0 lag: (min: 6.0, avg: 13.5, max: 38.0) -[2023-10-10 13:32:16,077][75634] Avg episode reward: [(0, '34.270'), (1, '33.470')] -[2023-10-10 13:32:16,416][76542] Updated weights for policy 1, policy_version 21890 (0.0007) -[2023-10-10 13:32:16,792][76542] Updated weights for policy 1, policy_version 21900 (0.0007) -[2023-10-10 13:32:17,161][76542] Updated weights for policy 1, policy_version 21910 (0.0008) -[2023-10-10 13:32:17,524][76543] Updated weights for policy 0, policy_version 21923 (0.0010) -[2023-10-10 13:32:17,527][76542] Updated weights for policy 1, policy_version 21920 (0.0008) -[2023-10-10 13:32:17,900][76543] Updated weights for policy 0, policy_version 21933 (0.0009) -[2023-10-10 13:32:18,270][76543] Updated weights for policy 0, policy_version 21943 (0.0008) -[2023-10-10 13:32:21,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 44924928. Throughput: 0: 1826.7, 1: 1828.1. Samples: 11238234. Policy #0 lag: (min: 6.0, avg: 13.5, max: 38.0) -[2023-10-10 13:32:21,076][75634] Avg episode reward: [(0, '33.360'), (1, '33.770')] -[2023-10-10 13:32:21,193][76542] Updated weights for policy 1, policy_version 21930 (0.0007) -[2023-10-10 13:32:21,560][76542] Updated weights for policy 1, policy_version 21940 (0.0010) -[2023-10-10 13:32:21,930][76542] Updated weights for policy 1, policy_version 21950 (0.0009) -[2023-10-10 13:32:22,016][76543] Updated weights for policy 0, policy_version 21953 (0.0009) -[2023-10-10 13:32:22,388][76543] Updated weights for policy 0, policy_version 21963 (0.0010) -[2023-10-10 13:32:22,761][76543] Updated weights for policy 0, policy_version 21973 (0.0007) -[2023-10-10 13:32:23,134][76543] Updated weights for policy 0, policy_version 21983 (0.0007) -[2023-10-10 13:32:25,539][76542] Updated weights for policy 1, policy_version 21960 (0.0007) -[2023-10-10 13:32:25,918][76542] Updated weights for policy 1, policy_version 21970 (0.0007) -[2023-10-10 13:32:26,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 44990464. Throughput: 0: 1826.5, 1: 1823.5. Samples: 11260388. Policy #0 lag: (min: 6.0, avg: 13.5, max: 38.0) -[2023-10-10 13:32:26,077][75634] Avg episode reward: [(0, '33.250'), (1, '34.150')] -[2023-10-10 13:32:26,280][76542] Updated weights for policy 1, policy_version 21980 (0.0007) -[2023-10-10 13:32:26,424][76421] Saving new best policy, reward=34.150! -[2023-10-10 13:32:26,639][76543] Updated weights for policy 0, policy_version 21993 (0.0009) -[2023-10-10 13:32:27,015][76543] Updated weights for policy 0, policy_version 22003 (0.0008) -[2023-10-10 13:32:27,385][76543] Updated weights for policy 0, policy_version 22013 (0.0008) -[2023-10-10 13:32:30,073][76542] Updated weights for policy 1, policy_version 21990 (0.0010) -[2023-10-10 13:32:30,445][76542] Updated weights for policy 1, policy_version 22000 (0.0011) -[2023-10-10 13:32:30,814][76542] Updated weights for policy 1, policy_version 22010 (0.0007) -[2023-10-10 13:32:30,930][76543] Updated weights for policy 0, policy_version 22023 (0.0008) -[2023-10-10 13:32:31,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 45088768. Throughput: 0: 1835.7, 1: 1826.4. Samples: 11282324. Policy #0 lag: (min: 6.0, avg: 13.5, max: 38.0) -[2023-10-10 13:32:31,076][75634] Avg episode reward: [(0, '32.310'), (1, '32.570')] -[2023-10-10 13:32:31,083][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000022016_22544384.pth... -[2023-10-10 13:32:31,116][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000020288_20774912.pth -[2023-10-10 13:32:31,307][76543] Updated weights for policy 0, policy_version 22033 (0.0007) -[2023-10-10 13:32:31,678][76543] Updated weights for policy 0, policy_version 22043 (0.0007) -[2023-10-10 13:32:31,866][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000022048_22577152.pth... -[2023-10-10 13:32:31,904][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000020320_20807680.pth -[2023-10-10 13:32:34,492][76542] Updated weights for policy 1, policy_version 22020 (0.0008) -[2023-10-10 13:32:34,859][76542] Updated weights for policy 1, policy_version 22030 (0.0008) -[2023-10-10 13:32:35,225][76542] Updated weights for policy 1, policy_version 22040 (0.0007) -[2023-10-10 13:32:35,365][76543] Updated weights for policy 0, policy_version 22053 (0.0008) -[2023-10-10 13:32:35,743][76543] Updated weights for policy 0, policy_version 22063 (0.0007) -[2023-10-10 13:32:36,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 45154304. Throughput: 0: 1838.9, 1: 1824.1. Samples: 11293444. Policy #0 lag: (min: 21.0, avg: 25.4, max: 53.0) -[2023-10-10 13:32:36,077][75634] Avg episode reward: [(0, '32.790'), (1, '32.690')] -[2023-10-10 13:32:36,120][76543] Updated weights for policy 0, policy_version 22073 (0.0008) -[2023-10-10 13:32:38,776][76542] Updated weights for policy 1, policy_version 22050 (0.0007) -[2023-10-10 13:32:39,146][76542] Updated weights for policy 1, policy_version 22060 (0.0008) -[2023-10-10 13:32:39,516][76542] Updated weights for policy 1, policy_version 22070 (0.0009) -[2023-10-10 13:32:39,794][76543] Updated weights for policy 0, policy_version 22083 (0.0009) -[2023-10-10 13:32:39,879][76542] Updated weights for policy 1, policy_version 22080 (0.0009) -[2023-10-10 13:32:40,162][76543] Updated weights for policy 0, policy_version 22093 (0.0011) -[2023-10-10 13:32:40,539][76543] Updated weights for policy 0, policy_version 22103 (0.0010) -[2023-10-10 13:32:41,076][75634] Fps is (10 sec: 16383.9, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 45252608. Throughput: 0: 1827.9, 1: 1827.3. Samples: 11315092. Policy #0 lag: (min: 21.0, avg: 25.4, max: 53.0) -[2023-10-10 13:32:41,077][75634] Avg episode reward: [(0, '29.700'), (1, '30.490')] -[2023-10-10 13:32:43,563][76542] Updated weights for policy 1, policy_version 22090 (0.0008) -[2023-10-10 13:32:43,930][76542] Updated weights for policy 1, policy_version 22100 (0.0009) -[2023-10-10 13:32:44,218][76543] Updated weights for policy 0, policy_version 22113 (0.0007) -[2023-10-10 13:32:44,291][76542] Updated weights for policy 1, policy_version 22110 (0.0008) -[2023-10-10 13:32:44,589][76543] Updated weights for policy 0, policy_version 22123 (0.0008) -[2023-10-10 13:32:44,960][76543] Updated weights for policy 0, policy_version 22133 (0.0009) -[2023-10-10 13:32:45,337][76543] Updated weights for policy 0, policy_version 22143 (0.0009) -[2023-10-10 13:32:46,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 45318144. Throughput: 0: 1820.2, 1: 1833.7. Samples: 11336784. Policy #0 lag: (min: 21.0, avg: 25.4, max: 53.0) -[2023-10-10 13:32:46,077][75634] Avg episode reward: [(0, '28.880'), (1, '28.600')] -[2023-10-10 13:32:47,795][76542] Updated weights for policy 1, policy_version 22120 (0.0010) -[2023-10-10 13:32:48,161][76542] Updated weights for policy 1, policy_version 22130 (0.0008) -[2023-10-10 13:32:48,523][76542] Updated weights for policy 1, policy_version 22140 (0.0007) -[2023-10-10 13:32:48,984][76543] Updated weights for policy 0, policy_version 22153 (0.0009) -[2023-10-10 13:32:49,366][76543] Updated weights for policy 0, policy_version 22163 (0.0008) -[2023-10-10 13:32:49,741][76543] Updated weights for policy 0, policy_version 22173 (0.0008) -[2023-10-10 13:32:51,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 45383680. Throughput: 0: 1828.9, 1: 1820.0. Samples: 11347932. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:32:51,076][75634] Avg episode reward: [(0, '31.570'), (1, '30.000')] -[2023-10-10 13:32:52,272][76542] Updated weights for policy 1, policy_version 22150 (0.0008) -[2023-10-10 13:32:52,644][76542] Updated weights for policy 1, policy_version 22160 (0.0008) -[2023-10-10 13:32:53,006][76542] Updated weights for policy 1, policy_version 22170 (0.0009) -[2023-10-10 13:32:53,401][76543] Updated weights for policy 0, policy_version 22183 (0.0008) -[2023-10-10 13:32:53,778][76543] Updated weights for policy 0, policy_version 22193 (0.0007) -[2023-10-10 13:32:54,145][76543] Updated weights for policy 0, policy_version 22203 (0.0008) -[2023-10-10 13:32:56,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 45449216. Throughput: 0: 1821.7, 1: 1819.0. Samples: 11369366. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:32:56,077][75634] Avg episode reward: [(0, '32.160'), (1, '30.160')] -[2023-10-10 13:32:56,727][76542] Updated weights for policy 1, policy_version 22180 (0.0008) -[2023-10-10 13:32:57,091][76542] Updated weights for policy 1, policy_version 22190 (0.0009) -[2023-10-10 13:32:57,471][76542] Updated weights for policy 1, policy_version 22200 (0.0010) -[2023-10-10 13:32:57,852][76543] Updated weights for policy 0, policy_version 22213 (0.0008) -[2023-10-10 13:32:58,229][76543] Updated weights for policy 0, policy_version 22223 (0.0008) -[2023-10-10 13:32:58,602][76543] Updated weights for policy 0, policy_version 22233 (0.0008) -[2023-10-10 13:33:01,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 45514752. Throughput: 0: 1826.3, 1: 1828.0. Samples: 11392126. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:33:01,076][75634] Avg episode reward: [(0, '32.200'), (1, '32.180')] -[2023-10-10 13:33:01,085][76542] Updated weights for policy 1, policy_version 22210 (0.0009) -[2023-10-10 13:33:01,465][76542] Updated weights for policy 1, policy_version 22220 (0.0011) -[2023-10-10 13:33:01,830][76542] Updated weights for policy 1, policy_version 22230 (0.0010) -[2023-10-10 13:33:02,198][76542] Updated weights for policy 1, policy_version 22240 (0.0008) -[2023-10-10 13:33:02,311][76543] Updated weights for policy 0, policy_version 22243 (0.0007) -[2023-10-10 13:33:02,682][76543] Updated weights for policy 0, policy_version 22253 (0.0007) -[2023-10-10 13:33:03,051][76543] Updated weights for policy 0, policy_version 22263 (0.0007) -[2023-10-10 13:33:05,953][76542] Updated weights for policy 1, policy_version 22250 (0.0008) -[2023-10-10 13:33:06,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 45580288. Throughput: 0: 1820.8, 1: 1823.6. Samples: 11402234. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:33:06,076][75634] Avg episode reward: [(0, '32.680'), (1, '34.290')] -[2023-10-10 13:33:06,315][76542] Updated weights for policy 1, policy_version 22260 (0.0007) -[2023-10-10 13:33:06,612][76543] Updated weights for policy 0, policy_version 22273 (0.0007) -[2023-10-10 13:33:06,681][76542] Updated weights for policy 1, policy_version 22270 (0.0007) -[2023-10-10 13:33:06,758][76421] Saving new best policy, reward=34.290! -[2023-10-10 13:33:06,983][76543] Updated weights for policy 0, policy_version 22283 (0.0008) -[2023-10-10 13:33:07,360][76543] Updated weights for policy 0, policy_version 22293 (0.0009) -[2023-10-10 13:33:07,736][76543] Updated weights for policy 0, policy_version 22303 (0.0007) -[2023-10-10 13:33:10,461][76542] Updated weights for policy 1, policy_version 22280 (0.0007) -[2023-10-10 13:33:10,832][76542] Updated weights for policy 1, policy_version 22290 (0.0008) -[2023-10-10 13:33:11,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 45645824. Throughput: 0: 1836.1, 1: 1820.7. Samples: 11424942. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:33:11,076][75634] Avg episode reward: [(0, '31.500'), (1, '33.950')] -[2023-10-10 13:33:11,200][76542] Updated weights for policy 1, policy_version 22300 (0.0008) -[2023-10-10 13:33:11,427][76543] Updated weights for policy 0, policy_version 22313 (0.0009) -[2023-10-10 13:33:11,797][76543] Updated weights for policy 0, policy_version 22323 (0.0008) -[2023-10-10 13:33:12,162][76543] Updated weights for policy 0, policy_version 22333 (0.0009) -[2023-10-10 13:33:14,829][76542] Updated weights for policy 1, policy_version 22310 (0.0008) -[2023-10-10 13:33:15,197][76542] Updated weights for policy 1, policy_version 22320 (0.0009) -[2023-10-10 13:33:15,570][76542] Updated weights for policy 1, policy_version 22330 (0.0007) -[2023-10-10 13:33:15,930][76543] Updated weights for policy 0, policy_version 22343 (0.0010) -[2023-10-10 13:33:16,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 45744128. Throughput: 0: 1826.5, 1: 1822.9. Samples: 11446548. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:33:16,077][75634] Avg episode reward: [(0, '32.160'), (1, '32.360')] -[2023-10-10 13:33:16,320][76543] Updated weights for policy 0, policy_version 22353 (0.0010) -[2023-10-10 13:33:16,698][76543] Updated weights for policy 0, policy_version 22363 (0.0010) -[2023-10-10 13:33:19,290][76542] Updated weights for policy 1, policy_version 22340 (0.0009) -[2023-10-10 13:33:19,658][76542] Updated weights for policy 1, policy_version 22350 (0.0011) -[2023-10-10 13:33:20,032][76542] Updated weights for policy 1, policy_version 22360 (0.0008) -[2023-10-10 13:33:20,302][76543] Updated weights for policy 0, policy_version 22373 (0.0010) -[2023-10-10 13:33:20,683][76543] Updated weights for policy 0, policy_version 22383 (0.0008) -[2023-10-10 13:33:21,051][76543] Updated weights for policy 0, policy_version 22393 (0.0009) -[2023-10-10 13:33:21,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 45809664. Throughput: 0: 1821.7, 1: 1825.3. Samples: 11457560. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:33:21,077][75634] Avg episode reward: [(0, '34.690'), (1, '30.750')] -[2023-10-10 13:33:23,897][76542] Updated weights for policy 1, policy_version 22370 (0.0009) -[2023-10-10 13:33:24,265][76542] Updated weights for policy 1, policy_version 22380 (0.0009) -[2023-10-10 13:33:24,629][76542] Updated weights for policy 1, policy_version 22390 (0.0009) -[2023-10-10 13:33:24,811][76543] Updated weights for policy 0, policy_version 22403 (0.0009) -[2023-10-10 13:33:24,998][76542] Updated weights for policy 1, policy_version 22400 (0.0008) -[2023-10-10 13:33:25,181][76543] Updated weights for policy 0, policy_version 22413 (0.0009) -[2023-10-10 13:33:25,550][76543] Updated weights for policy 0, policy_version 22423 (0.0009) -[2023-10-10 13:33:26,076][75634] Fps is (10 sec: 16384.2, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 45907968. Throughput: 0: 1825.3, 1: 1819.5. Samples: 11479108. Policy #0 lag: (min: 23.0, avg: 26.1, max: 55.0) -[2023-10-10 13:33:26,077][75634] Avg episode reward: [(0, '32.970'), (1, '27.930')] -[2023-10-10 13:33:28,537][76542] Updated weights for policy 1, policy_version 22410 (0.0011) -[2023-10-10 13:33:28,905][76542] Updated weights for policy 1, policy_version 22420 (0.0010) -[2023-10-10 13:33:29,230][76543] Updated weights for policy 0, policy_version 22433 (0.0011) -[2023-10-10 13:33:29,270][76542] Updated weights for policy 1, policy_version 22430 (0.0007) -[2023-10-10 13:33:29,603][76543] Updated weights for policy 0, policy_version 22443 (0.0008) -[2023-10-10 13:33:29,972][76543] Updated weights for policy 0, policy_version 22453 (0.0011) -[2023-10-10 13:33:30,344][76543] Updated weights for policy 0, policy_version 22463 (0.0011) -[2023-10-10 13:33:31,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 45973504. Throughput: 0: 1824.2, 1: 1807.4. Samples: 11500206. Policy #0 lag: (min: 23.0, avg: 26.1, max: 55.0) -[2023-10-10 13:33:31,076][75634] Avg episode reward: [(0, '32.470'), (1, '29.070')] -[2023-10-10 13:33:33,067][76542] Updated weights for policy 1, policy_version 22440 (0.0007) -[2023-10-10 13:33:33,444][76542] Updated weights for policy 1, policy_version 22450 (0.0008) -[2023-10-10 13:33:33,822][76542] Updated weights for policy 1, policy_version 22460 (0.0009) -[2023-10-10 13:33:34,259][76543] Updated weights for policy 0, policy_version 22473 (0.0009) -[2023-10-10 13:33:34,627][76543] Updated weights for policy 0, policy_version 22483 (0.0008) -[2023-10-10 13:33:34,999][76543] Updated weights for policy 0, policy_version 22493 (0.0007) -[2023-10-10 13:33:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 46039040. Throughput: 0: 1823.3, 1: 1814.6. Samples: 11511638. Policy #0 lag: (min: 23.0, avg: 26.1, max: 55.0) -[2023-10-10 13:33:36,077][75634] Avg episode reward: [(0, '33.420'), (1, '30.240')] -[2023-10-10 13:33:37,569][76542] Updated weights for policy 1, policy_version 22470 (0.0007) -[2023-10-10 13:33:37,937][76542] Updated weights for policy 1, policy_version 22480 (0.0007) -[2023-10-10 13:33:38,313][76542] Updated weights for policy 1, policy_version 22490 (0.0008) -[2023-10-10 13:33:38,728][76543] Updated weights for policy 0, policy_version 22503 (0.0008) -[2023-10-10 13:33:39,109][76543] Updated weights for policy 0, policy_version 22513 (0.0009) -[2023-10-10 13:33:39,472][76543] Updated weights for policy 0, policy_version 22523 (0.0008) -[2023-10-10 13:33:41,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14662.3). Total num frames: 46104576. Throughput: 0: 1828.6, 1: 1806.8. Samples: 11532956. Policy #0 lag: (min: 23.0, avg: 26.1, max: 55.0) -[2023-10-10 13:33:41,077][75634] Avg episode reward: [(0, '34.680'), (1, '31.850')] -[2023-10-10 13:33:42,213][76542] Updated weights for policy 1, policy_version 22500 (0.0009) -[2023-10-10 13:33:42,611][76542] Updated weights for policy 1, policy_version 22510 (0.0009) -[2023-10-10 13:33:42,990][76542] Updated weights for policy 1, policy_version 22520 (0.0007) -[2023-10-10 13:33:43,018][76543] Updated weights for policy 0, policy_version 22533 (0.0008) -[2023-10-10 13:33:43,396][76543] Updated weights for policy 0, policy_version 22543 (0.0010) -[2023-10-10 13:33:43,768][76543] Updated weights for policy 0, policy_version 22553 (0.0011) -[2023-10-10 13:33:46,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 46170112. Throughput: 0: 1817.5, 1: 1798.0. Samples: 11554824. Policy #0 lag: (min: 31.0, avg: 33.6, max: 62.0) -[2023-10-10 13:33:46,077][75634] Avg episode reward: [(0, '33.740'), (1, '32.700')] -[2023-10-10 13:33:46,658][76542] Updated weights for policy 1, policy_version 22530 (0.0010) -[2023-10-10 13:33:47,023][76542] Updated weights for policy 1, policy_version 22540 (0.0008) -[2023-10-10 13:33:47,396][76542] Updated weights for policy 1, policy_version 22550 (0.0007) -[2023-10-10 13:33:47,522][76543] Updated weights for policy 0, policy_version 22563 (0.0010) -[2023-10-10 13:33:47,769][76542] Updated weights for policy 1, policy_version 22560 (0.0008) -[2023-10-10 13:33:47,883][76543] Updated weights for policy 0, policy_version 22573 (0.0008) -[2023-10-10 13:33:48,260][76543] Updated weights for policy 0, policy_version 22583 (0.0008) -[2023-10-10 13:33:51,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 46235648. Throughput: 0: 1820.4, 1: 1801.4. Samples: 11565214. Policy #0 lag: (min: 31.0, avg: 33.6, max: 62.0) -[2023-10-10 13:33:51,076][75634] Avg episode reward: [(0, '34.480'), (1, '32.590')] -[2023-10-10 13:33:51,447][76542] Updated weights for policy 1, policy_version 22570 (0.0007) -[2023-10-10 13:33:51,827][76542] Updated weights for policy 1, policy_version 22580 (0.0007) -[2023-10-10 13:33:51,938][76543] Updated weights for policy 0, policy_version 22593 (0.0007) -[2023-10-10 13:33:52,200][76542] Updated weights for policy 1, policy_version 22590 (0.0009) -[2023-10-10 13:33:52,309][76543] Updated weights for policy 0, policy_version 22603 (0.0008) -[2023-10-10 13:33:52,690][76543] Updated weights for policy 0, policy_version 22613 (0.0007) -[2023-10-10 13:33:53,058][76543] Updated weights for policy 0, policy_version 22623 (0.0009) -[2023-10-10 13:33:55,830][76542] Updated weights for policy 1, policy_version 22600 (0.0009) -[2023-10-10 13:33:56,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 46301184. Throughput: 0: 1805.1, 1: 1800.4. Samples: 11587188. Policy #0 lag: (min: 31.0, avg: 33.6, max: 62.0) -[2023-10-10 13:33:56,077][75634] Avg episode reward: [(0, '35.800'), (1, '33.180')] -[2023-10-10 13:33:56,079][76362] Saving new best policy, reward=35.800! -[2023-10-10 13:33:56,207][76542] Updated weights for policy 1, policy_version 22610 (0.0008) -[2023-10-10 13:33:56,570][76542] Updated weights for policy 1, policy_version 22620 (0.0008) -[2023-10-10 13:33:56,778][76543] Updated weights for policy 0, policy_version 22633 (0.0007) -[2023-10-10 13:33:57,157][76543] Updated weights for policy 0, policy_version 22643 (0.0009) -[2023-10-10 13:33:57,524][76543] Updated weights for policy 0, policy_version 22653 (0.0007) -[2023-10-10 13:33:59,985][76542] Updated weights for policy 1, policy_version 22630 (0.0008) -[2023-10-10 13:34:00,359][76542] Updated weights for policy 1, policy_version 22640 (0.0009) -[2023-10-10 13:34:00,726][76542] Updated weights for policy 1, policy_version 22650 (0.0009) -[2023-10-10 13:34:01,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 46399488. Throughput: 0: 1805.6, 1: 1805.8. Samples: 11609058. Policy #0 lag: (min: 31.0, avg: 33.6, max: 62.0) -[2023-10-10 13:34:01,077][75634] Avg episode reward: [(0, '35.360'), (1, '31.440')] -[2023-10-10 13:34:01,364][76543] Updated weights for policy 0, policy_version 22663 (0.0007) -[2023-10-10 13:34:01,738][76543] Updated weights for policy 0, policy_version 22673 (0.0010) -[2023-10-10 13:34:02,103][76543] Updated weights for policy 0, policy_version 22683 (0.0009) -[2023-10-10 13:34:04,259][76542] Updated weights for policy 1, policy_version 22660 (0.0009) -[2023-10-10 13:34:04,633][76542] Updated weights for policy 1, policy_version 22670 (0.0009) -[2023-10-10 13:34:04,995][76542] Updated weights for policy 1, policy_version 22680 (0.0009) -[2023-10-10 13:34:05,841][76543] Updated weights for policy 0, policy_version 22693 (0.0009) -[2023-10-10 13:34:06,076][75634] Fps is (10 sec: 16384.5, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 46465024. Throughput: 0: 1804.6, 1: 1806.7. Samples: 11620070. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:34:06,076][75634] Avg episode reward: [(0, '35.390'), (1, '33.640')] -[2023-10-10 13:34:06,212][76543] Updated weights for policy 0, policy_version 22703 (0.0007) -[2023-10-10 13:34:06,589][76543] Updated weights for policy 0, policy_version 22713 (0.0008) -[2023-10-10 13:34:08,676][76542] Updated weights for policy 1, policy_version 22690 (0.0007) -[2023-10-10 13:34:09,050][76542] Updated weights for policy 1, policy_version 22700 (0.0007) -[2023-10-10 13:34:09,411][76542] Updated weights for policy 1, policy_version 22710 (0.0009) -[2023-10-10 13:34:09,779][76542] Updated weights for policy 1, policy_version 22720 (0.0010) -[2023-10-10 13:34:10,301][76543] Updated weights for policy 0, policy_version 22723 (0.0009) -[2023-10-10 13:34:10,668][76543] Updated weights for policy 0, policy_version 22733 (0.0009) -[2023-10-10 13:34:11,051][76543] Updated weights for policy 0, policy_version 22743 (0.0011) -[2023-10-10 13:34:11,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 46530560. Throughput: 0: 1801.6, 1: 1808.7. Samples: 11641572. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:34:11,077][75634] Avg episode reward: [(0, '34.460'), (1, '33.910')] -[2023-10-10 13:34:13,466][76542] Updated weights for policy 1, policy_version 22730 (0.0010) -[2023-10-10 13:34:13,844][76542] Updated weights for policy 1, policy_version 22740 (0.0010) -[2023-10-10 13:34:14,221][76542] Updated weights for policy 1, policy_version 22750 (0.0011) -[2023-10-10 13:34:14,613][76543] Updated weights for policy 0, policy_version 22753 (0.0009) -[2023-10-10 13:34:14,981][76543] Updated weights for policy 0, policy_version 22763 (0.0007) -[2023-10-10 13:34:15,359][76543] Updated weights for policy 0, policy_version 22773 (0.0007) -[2023-10-10 13:34:15,729][76543] Updated weights for policy 0, policy_version 22783 (0.0008) -[2023-10-10 13:34:16,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 46628864. Throughput: 0: 1808.8, 1: 1821.0. Samples: 11663546. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:34:16,076][75634] Avg episode reward: [(0, '31.900'), (1, '33.340')] -[2023-10-10 13:34:18,015][76542] Updated weights for policy 1, policy_version 22760 (0.0008) -[2023-10-10 13:34:18,388][76542] Updated weights for policy 1, policy_version 22770 (0.0007) -[2023-10-10 13:34:18,752][76542] Updated weights for policy 1, policy_version 22780 (0.0009) -[2023-10-10 13:34:19,518][76543] Updated weights for policy 0, policy_version 22793 (0.0009) -[2023-10-10 13:34:19,891][76543] Updated weights for policy 0, policy_version 22803 (0.0008) -[2023-10-10 13:34:20,257][76543] Updated weights for policy 0, policy_version 22813 (0.0008) -[2023-10-10 13:34:21,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 46694400. Throughput: 0: 1798.5, 1: 1819.2. Samples: 11674432. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) -[2023-10-10 13:34:21,077][75634] Avg episode reward: [(0, '32.180'), (1, '33.220')] -[2023-10-10 13:34:22,490][76542] Updated weights for policy 1, policy_version 22790 (0.0009) -[2023-10-10 13:34:22,863][76542] Updated weights for policy 1, policy_version 22800 (0.0008) -[2023-10-10 13:34:23,231][76542] Updated weights for policy 1, policy_version 22810 (0.0008) -[2023-10-10 13:34:24,138][76543] Updated weights for policy 0, policy_version 22823 (0.0009) -[2023-10-10 13:34:24,516][76543] Updated weights for policy 0, policy_version 22833 (0.0010) -[2023-10-10 13:34:24,878][76543] Updated weights for policy 0, policy_version 22843 (0.0008) -[2023-10-10 13:34:26,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14662.3). Total num frames: 46759936. Throughput: 0: 1807.1, 1: 1828.0. Samples: 11696536. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) -[2023-10-10 13:34:26,077][75634] Avg episode reward: [(0, '32.100'), (1, '35.080')] -[2023-10-10 13:34:26,079][76421] Saving new best policy, reward=35.080! -[2023-10-10 13:34:26,925][76542] Updated weights for policy 1, policy_version 22820 (0.0009) -[2023-10-10 13:34:27,333][76542] Updated weights for policy 1, policy_version 22830 (0.0011) -[2023-10-10 13:34:27,695][76542] Updated weights for policy 1, policy_version 22840 (0.0009) -[2023-10-10 13:34:28,420][76543] Updated weights for policy 0, policy_version 22853 (0.0007) -[2023-10-10 13:34:28,786][76543] Updated weights for policy 0, policy_version 22863 (0.0008) -[2023-10-10 13:34:29,151][76543] Updated weights for policy 0, policy_version 22873 (0.0007) -[2023-10-10 13:34:31,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 46825472. Throughput: 0: 1801.9, 1: 1831.9. Samples: 11718342. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) -[2023-10-10 13:34:31,077][75634] Avg episode reward: [(0, '29.180'), (1, '35.310')] -[2023-10-10 13:34:31,090][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000022880_23429120.pth... -[2023-10-10 13:34:31,091][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000022848_23396352.pth... -[2023-10-10 13:34:31,127][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000021184_21692416.pth -[2023-10-10 13:34:31,132][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000021152_21659648.pth -[2023-10-10 13:34:31,136][76421] Saving new best policy, reward=35.310! -[2023-10-10 13:34:31,404][76542] Updated weights for policy 1, policy_version 22850 (0.0009) -[2023-10-10 13:34:31,769][76542] Updated weights for policy 1, policy_version 22860 (0.0008) -[2023-10-10 13:34:32,140][76542] Updated weights for policy 1, policy_version 22870 (0.0008) -[2023-10-10 13:34:32,504][76542] Updated weights for policy 1, policy_version 22880 (0.0009) -[2023-10-10 13:34:32,734][76543] Updated weights for policy 0, policy_version 22883 (0.0010) -[2023-10-10 13:34:33,108][76543] Updated weights for policy 0, policy_version 22893 (0.0009) -[2023-10-10 13:34:33,479][76543] Updated weights for policy 0, policy_version 22903 (0.0008) -[2023-10-10 13:34:36,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 46891008. Throughput: 0: 1812.9, 1: 1833.2. Samples: 11729288. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) -[2023-10-10 13:34:36,076][75634] Avg episode reward: [(0, '29.420'), (1, '33.230')] -[2023-10-10 13:34:36,176][76542] Updated weights for policy 1, policy_version 22890 (0.0008) -[2023-10-10 13:34:36,541][76542] Updated weights for policy 1, policy_version 22900 (0.0007) -[2023-10-10 13:34:36,910][76542] Updated weights for policy 1, policy_version 22910 (0.0009) -[2023-10-10 13:34:37,121][76543] Updated weights for policy 0, policy_version 22913 (0.0007) -[2023-10-10 13:34:37,488][76543] Updated weights for policy 0, policy_version 22923 (0.0009) -[2023-10-10 13:34:37,865][76543] Updated weights for policy 0, policy_version 22933 (0.0008) -[2023-10-10 13:34:38,235][76543] Updated weights for policy 0, policy_version 22943 (0.0007) -[2023-10-10 13:34:40,456][76542] Updated weights for policy 1, policy_version 22920 (0.0009) -[2023-10-10 13:34:40,831][76542] Updated weights for policy 1, policy_version 22930 (0.0009) -[2023-10-10 13:34:41,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 46956544. Throughput: 0: 1814.9, 1: 1839.4. Samples: 11751632. Policy #0 lag: (min: 13.0, avg: 19.5, max: 45.0) -[2023-10-10 13:34:41,077][75634] Avg episode reward: [(0, '31.850'), (1, '32.580')] -[2023-10-10 13:34:41,205][76542] Updated weights for policy 1, policy_version 22940 (0.0007) -[2023-10-10 13:34:41,913][76543] Updated weights for policy 0, policy_version 22953 (0.0007) -[2023-10-10 13:34:42,275][76543] Updated weights for policy 0, policy_version 22963 (0.0009) -[2023-10-10 13:34:42,663][76543] Updated weights for policy 0, policy_version 22973 (0.0010) -[2023-10-10 13:34:45,066][76542] Updated weights for policy 1, policy_version 22950 (0.0009) -[2023-10-10 13:34:45,436][76542] Updated weights for policy 1, policy_version 22960 (0.0012) -[2023-10-10 13:34:45,816][76542] Updated weights for policy 1, policy_version 22970 (0.0011) -[2023-10-10 13:34:46,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 47054848. Throughput: 0: 1813.9, 1: 1822.6. Samples: 11772700. Policy #0 lag: (min: 13.0, avg: 19.5, max: 45.0) -[2023-10-10 13:34:46,076][75634] Avg episode reward: [(0, '33.780'), (1, '32.770')] -[2023-10-10 13:34:46,403][76543] Updated weights for policy 0, policy_version 22983 (0.0010) -[2023-10-10 13:34:46,780][76543] Updated weights for policy 0, policy_version 22993 (0.0008) -[2023-10-10 13:34:47,144][76543] Updated weights for policy 0, policy_version 23003 (0.0008) -[2023-10-10 13:34:49,659][76542] Updated weights for policy 1, policy_version 22980 (0.0009) -[2023-10-10 13:34:50,039][76542] Updated weights for policy 1, policy_version 22990 (0.0009) -[2023-10-10 13:34:50,414][76542] Updated weights for policy 1, policy_version 23000 (0.0008) -[2023-10-10 13:34:50,842][76543] Updated weights for policy 0, policy_version 23013 (0.0007) -[2023-10-10 13:34:51,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 47120384. Throughput: 0: 1817.5, 1: 1813.9. Samples: 11783480. Policy #0 lag: (min: 13.0, avg: 19.5, max: 45.0) -[2023-10-10 13:34:51,076][75634] Avg episode reward: [(0, '35.240'), (1, '32.350')] -[2023-10-10 13:34:51,215][76543] Updated weights for policy 0, policy_version 23023 (0.0007) -[2023-10-10 13:34:51,586][76543] Updated weights for policy 0, policy_version 23033 (0.0008) -[2023-10-10 13:34:54,148][76542] Updated weights for policy 1, policy_version 23010 (0.0008) -[2023-10-10 13:34:54,514][76542] Updated weights for policy 1, policy_version 23020 (0.0009) -[2023-10-10 13:34:54,884][76542] Updated weights for policy 1, policy_version 23030 (0.0010) -[2023-10-10 13:34:55,258][76542] Updated weights for policy 1, policy_version 23040 (0.0010) -[2023-10-10 13:34:55,304][76543] Updated weights for policy 0, policy_version 23043 (0.0007) -[2023-10-10 13:34:55,667][76543] Updated weights for policy 0, policy_version 23053 (0.0008) -[2023-10-10 13:34:56,035][76543] Updated weights for policy 0, policy_version 23063 (0.0007) -[2023-10-10 13:34:56,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 47185920. Throughput: 0: 1820.1, 1: 1826.3. Samples: 11805662. Policy #0 lag: (min: 13.0, avg: 19.5, max: 45.0) -[2023-10-10 13:34:56,076][75634] Avg episode reward: [(0, '35.410'), (1, '29.750')] -[2023-10-10 13:34:58,923][76542] Updated weights for policy 1, policy_version 23050 (0.0009) -[2023-10-10 13:34:59,286][76542] Updated weights for policy 1, policy_version 23060 (0.0008) -[2023-10-10 13:34:59,593][76543] Updated weights for policy 0, policy_version 23073 (0.0008) -[2023-10-10 13:34:59,664][76542] Updated weights for policy 1, policy_version 23070 (0.0008) -[2023-10-10 13:34:59,958][76543] Updated weights for policy 0, policy_version 23083 (0.0010) -[2023-10-10 13:35:00,341][76543] Updated weights for policy 0, policy_version 23093 (0.0009) -[2023-10-10 13:35:00,716][76543] Updated weights for policy 0, policy_version 23103 (0.0011) -[2023-10-10 13:35:01,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 47284224. Throughput: 0: 1829.0, 1: 1816.4. Samples: 11827588. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-10 13:35:01,077][75634] Avg episode reward: [(0, '36.170'), (1, '29.440')] -[2023-10-10 13:35:01,087][76362] Saving new best policy, reward=36.170! -[2023-10-10 13:35:03,231][76542] Updated weights for policy 1, policy_version 23080 (0.0010) -[2023-10-10 13:35:03,607][76542] Updated weights for policy 1, policy_version 23090 (0.0009) -[2023-10-10 13:35:03,979][76542] Updated weights for policy 1, policy_version 23100 (0.0010) -[2023-10-10 13:35:04,356][76543] Updated weights for policy 0, policy_version 23113 (0.0009) -[2023-10-10 13:35:04,728][76543] Updated weights for policy 0, policy_version 23123 (0.0008) -[2023-10-10 13:35:05,102][76543] Updated weights for policy 0, policy_version 23133 (0.0007) -[2023-10-10 13:35:06,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 47349760. Throughput: 0: 1828.4, 1: 1823.9. Samples: 11838782. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-10 13:35:06,076][75634] Avg episode reward: [(0, '36.270'), (1, '31.900')] -[2023-10-10 13:35:06,077][76362] Saving new best policy, reward=36.270! -[2023-10-10 13:35:07,611][76542] Updated weights for policy 1, policy_version 23110 (0.0007) -[2023-10-10 13:35:07,984][76542] Updated weights for policy 1, policy_version 23120 (0.0009) -[2023-10-10 13:35:08,360][76542] Updated weights for policy 1, policy_version 23130 (0.0008) -[2023-10-10 13:35:08,809][76543] Updated weights for policy 0, policy_version 23143 (0.0008) -[2023-10-10 13:35:09,180][76543] Updated weights for policy 0, policy_version 23153 (0.0010) -[2023-10-10 13:35:09,542][76543] Updated weights for policy 0, policy_version 23163 (0.0010) -[2023-10-10 13:35:11,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 47415296. Throughput: 0: 1822.5, 1: 1817.6. Samples: 11860340. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-10 13:35:11,077][75634] Avg episode reward: [(0, '36.690'), (1, '29.780')] -[2023-10-10 13:35:11,077][76362] Saving new best policy, reward=36.690! -[2023-10-10 13:35:12,070][76542] Updated weights for policy 1, policy_version 23140 (0.0007) -[2023-10-10 13:35:12,463][76542] Updated weights for policy 1, policy_version 23150 (0.0008) -[2023-10-10 13:35:12,817][76542] Updated weights for policy 1, policy_version 23160 (0.0011) -[2023-10-10 13:35:13,198][76543] Updated weights for policy 0, policy_version 23173 (0.0008) -[2023-10-10 13:35:13,558][76543] Updated weights for policy 0, policy_version 23183 (0.0009) -[2023-10-10 13:35:13,930][76543] Updated weights for policy 0, policy_version 23193 (0.0008) -[2023-10-10 13:35:16,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 47480832. Throughput: 0: 1827.5, 1: 1821.6. Samples: 11882552. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-10 13:35:16,077][75634] Avg episode reward: [(0, '34.080'), (1, '30.480')] -[2023-10-10 13:35:16,422][76542] Updated weights for policy 1, policy_version 23170 (0.0010) -[2023-10-10 13:35:16,804][76542] Updated weights for policy 1, policy_version 23180 (0.0008) -[2023-10-10 13:35:17,170][76542] Updated weights for policy 1, policy_version 23190 (0.0009) -[2023-10-10 13:35:17,542][76542] Updated weights for policy 1, policy_version 23200 (0.0008) -[2023-10-10 13:35:17,688][76543] Updated weights for policy 0, policy_version 23203 (0.0009) -[2023-10-10 13:35:18,061][76543] Updated weights for policy 0, policy_version 23213 (0.0008) -[2023-10-10 13:35:18,435][76543] Updated weights for policy 0, policy_version 23223 (0.0007) -[2023-10-10 13:35:21,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 47546368. Throughput: 0: 1823.3, 1: 1819.6. Samples: 11893222. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-10 13:35:21,077][75634] Avg episode reward: [(0, '32.710'), (1, '33.700')] -[2023-10-10 13:35:21,156][76542] Updated weights for policy 1, policy_version 23210 (0.0007) -[2023-10-10 13:35:21,523][76542] Updated weights for policy 1, policy_version 23220 (0.0007) -[2023-10-10 13:35:21,896][76542] Updated weights for policy 1, policy_version 23230 (0.0010) -[2023-10-10 13:35:21,984][76543] Updated weights for policy 0, policy_version 23233 (0.0008) -[2023-10-10 13:35:22,352][76543] Updated weights for policy 0, policy_version 23243 (0.0009) -[2023-10-10 13:35:22,724][76543] Updated weights for policy 0, policy_version 23253 (0.0008) -[2023-10-10 13:35:23,104][76543] Updated weights for policy 0, policy_version 23263 (0.0009) -[2023-10-10 13:35:25,355][76542] Updated weights for policy 1, policy_version 23240 (0.0007) -[2023-10-10 13:35:25,713][76542] Updated weights for policy 1, policy_version 23250 (0.0008) -[2023-10-10 13:35:26,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 47611904. Throughput: 0: 1820.9, 1: 1823.5. Samples: 11915630. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-10 13:35:26,076][75634] Avg episode reward: [(0, '33.870'), (1, '34.950')] -[2023-10-10 13:35:26,083][76542] Updated weights for policy 1, policy_version 23260 (0.0008) -[2023-10-10 13:35:26,820][76543] Updated weights for policy 0, policy_version 23273 (0.0009) -[2023-10-10 13:35:27,194][76543] Updated weights for policy 0, policy_version 23283 (0.0009) -[2023-10-10 13:35:27,557][76543] Updated weights for policy 0, policy_version 23293 (0.0009) -[2023-10-10 13:35:29,779][76542] Updated weights for policy 1, policy_version 23270 (0.0008) -[2023-10-10 13:35:30,146][76542] Updated weights for policy 1, policy_version 23280 (0.0008) -[2023-10-10 13:35:30,518][76542] Updated weights for policy 1, policy_version 23290 (0.0008) -[2023-10-10 13:35:31,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 47710208. Throughput: 0: 1822.9, 1: 1831.8. Samples: 11937162. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-10 13:35:31,077][75634] Avg episode reward: [(0, '36.350'), (1, '35.150')] -[2023-10-10 13:35:31,276][76543] Updated weights for policy 0, policy_version 23303 (0.0012) -[2023-10-10 13:35:31,649][76543] Updated weights for policy 0, policy_version 23313 (0.0010) -[2023-10-10 13:35:32,008][76543] Updated weights for policy 0, policy_version 23323 (0.0007) -[2023-10-10 13:35:34,049][76542] Updated weights for policy 1, policy_version 23300 (0.0008) -[2023-10-10 13:35:34,420][76542] Updated weights for policy 1, policy_version 23310 (0.0009) -[2023-10-10 13:35:34,790][76542] Updated weights for policy 1, policy_version 23320 (0.0008) -[2023-10-10 13:35:35,620][76543] Updated weights for policy 0, policy_version 23333 (0.0009) -[2023-10-10 13:35:35,997][76543] Updated weights for policy 0, policy_version 23343 (0.0009) -[2023-10-10 13:35:36,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 47775744. Throughput: 0: 1821.9, 1: 1847.5. Samples: 11948602. Policy #0 lag: (min: 6.0, avg: 19.6, max: 38.0) -[2023-10-10 13:35:36,076][75634] Avg episode reward: [(0, '34.270'), (1, '32.860')] -[2023-10-10 13:35:36,366][76543] Updated weights for policy 0, policy_version 23353 (0.0009) -[2023-10-10 13:35:38,442][76542] Updated weights for policy 1, policy_version 23330 (0.0010) -[2023-10-10 13:35:38,818][76542] Updated weights for policy 1, policy_version 23340 (0.0008) -[2023-10-10 13:35:39,198][76542] Updated weights for policy 1, policy_version 23350 (0.0007) -[2023-10-10 13:35:39,559][76542] Updated weights for policy 1, policy_version 23360 (0.0010) -[2023-10-10 13:35:40,110][76543] Updated weights for policy 0, policy_version 23363 (0.0008) -[2023-10-10 13:35:40,483][76543] Updated weights for policy 0, policy_version 23373 (0.0008) -[2023-10-10 13:35:40,863][76543] Updated weights for policy 0, policy_version 23383 (0.0008) -[2023-10-10 13:35:41,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 47841280. Throughput: 0: 1818.3, 1: 1827.1. Samples: 11969706. Policy #0 lag: (min: 6.0, avg: 19.6, max: 38.0) -[2023-10-10 13:35:41,077][75634] Avg episode reward: [(0, '34.860'), (1, '33.350')] -[2023-10-10 13:35:43,176][76542] Updated weights for policy 1, policy_version 23370 (0.0011) -[2023-10-10 13:35:43,545][76542] Updated weights for policy 1, policy_version 23380 (0.0009) -[2023-10-10 13:35:43,905][76542] Updated weights for policy 1, policy_version 23390 (0.0010) -[2023-10-10 13:35:44,624][76543] Updated weights for policy 0, policy_version 23393 (0.0009) -[2023-10-10 13:35:44,992][76543] Updated weights for policy 0, policy_version 23403 (0.0007) -[2023-10-10 13:35:45,366][76543] Updated weights for policy 0, policy_version 23413 (0.0008) -[2023-10-10 13:35:45,737][76543] Updated weights for policy 0, policy_version 23423 (0.0010) -[2023-10-10 13:35:46,076][75634] Fps is (10 sec: 16383.5, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 47939584. Throughput: 0: 1806.4, 1: 1840.8. Samples: 11991716. Policy #0 lag: (min: 6.0, avg: 19.6, max: 38.0) -[2023-10-10 13:35:46,077][75634] Avg episode reward: [(0, '34.830'), (1, '34.490')] -[2023-10-10 13:35:47,545][76542] Updated weights for policy 1, policy_version 23400 (0.0009) -[2023-10-10 13:35:47,917][76542] Updated weights for policy 1, policy_version 23410 (0.0007) -[2023-10-10 13:35:48,289][76542] Updated weights for policy 1, policy_version 23420 (0.0008) -[2023-10-10 13:35:49,280][76543] Updated weights for policy 0, policy_version 23433 (0.0009) -[2023-10-10 13:35:49,654][76543] Updated weights for policy 0, policy_version 23443 (0.0010) -[2023-10-10 13:35:50,025][76543] Updated weights for policy 0, policy_version 23453 (0.0011) -[2023-10-10 13:35:51,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 48005120. Throughput: 0: 1807.2, 1: 1828.5. Samples: 12002390. Policy #0 lag: (min: 20.0, avg: 24.3, max: 52.0) -[2023-10-10 13:35:51,076][75634] Avg episode reward: [(0, '35.370'), (1, '33.730')] -[2023-10-10 13:35:51,901][76542] Updated weights for policy 1, policy_version 23430 (0.0008) -[2023-10-10 13:35:52,258][76542] Updated weights for policy 1, policy_version 23440 (0.0007) -[2023-10-10 13:35:52,629][76542] Updated weights for policy 1, policy_version 23450 (0.0009) -[2023-10-10 13:35:53,786][76543] Updated weights for policy 0, policy_version 23463 (0.0008) -[2023-10-10 13:35:54,152][76543] Updated weights for policy 0, policy_version 23473 (0.0007) -[2023-10-10 13:35:54,518][76543] Updated weights for policy 0, policy_version 23483 (0.0011) -[2023-10-10 13:35:56,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 48070656. Throughput: 0: 1808.7, 1: 1841.0. Samples: 12024574. Policy #0 lag: (min: 20.0, avg: 24.3, max: 52.0) -[2023-10-10 13:35:56,077][75634] Avg episode reward: [(0, '32.470'), (1, '30.910')] -[2023-10-10 13:35:56,322][76542] Updated weights for policy 1, policy_version 23460 (0.0008) -[2023-10-10 13:35:56,685][76542] Updated weights for policy 1, policy_version 23470 (0.0009) -[2023-10-10 13:35:57,058][76542] Updated weights for policy 1, policy_version 23480 (0.0007) -[2023-10-10 13:35:58,233][76543] Updated weights for policy 0, policy_version 23493 (0.0010) -[2023-10-10 13:35:58,601][76543] Updated weights for policy 0, policy_version 23503 (0.0008) -[2023-10-10 13:35:58,971][76543] Updated weights for policy 0, policy_version 23513 (0.0007) -[2023-10-10 13:36:00,794][76542] Updated weights for policy 1, policy_version 23490 (0.0007) -[2023-10-10 13:36:01,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 48136192. Throughput: 0: 1815.1, 1: 1839.3. Samples: 12046998. Policy #0 lag: (min: 20.0, avg: 24.3, max: 52.0) -[2023-10-10 13:36:01,076][75634] Avg episode reward: [(0, '29.790'), (1, '31.600')] -[2023-10-10 13:36:01,203][76542] Updated weights for policy 1, policy_version 23500 (0.0007) -[2023-10-10 13:36:01,570][76542] Updated weights for policy 1, policy_version 23510 (0.0011) -[2023-10-10 13:36:01,937][76542] Updated weights for policy 1, policy_version 23520 (0.0007) -[2023-10-10 13:36:02,667][76543] Updated weights for policy 0, policy_version 23523 (0.0007) -[2023-10-10 13:36:03,044][76543] Updated weights for policy 0, policy_version 23533 (0.0009) -[2023-10-10 13:36:03,414][76543] Updated weights for policy 0, policy_version 23543 (0.0010) -[2023-10-10 13:36:05,728][76542] Updated weights for policy 1, policy_version 23530 (0.0007) -[2023-10-10 13:36:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 48201728. Throughput: 0: 1812.8, 1: 1837.3. Samples: 12057478. Policy #0 lag: (min: 20.0, avg: 24.3, max: 52.0) -[2023-10-10 13:36:06,077][75634] Avg episode reward: [(0, '31.080'), (1, '30.280')] -[2023-10-10 13:36:06,103][76542] Updated weights for policy 1, policy_version 23540 (0.0008) -[2023-10-10 13:36:06,467][76542] Updated weights for policy 1, policy_version 23550 (0.0010) -[2023-10-10 13:36:07,157][76543] Updated weights for policy 0, policy_version 23553 (0.0008) -[2023-10-10 13:36:07,525][76543] Updated weights for policy 0, policy_version 23563 (0.0010) -[2023-10-10 13:36:07,891][76543] Updated weights for policy 0, policy_version 23573 (0.0009) -[2023-10-10 13:36:08,264][76543] Updated weights for policy 0, policy_version 23583 (0.0009) -[2023-10-10 13:36:10,299][76542] Updated weights for policy 1, policy_version 23560 (0.0011) -[2023-10-10 13:36:10,668][76542] Updated weights for policy 1, policy_version 23570 (0.0010) -[2023-10-10 13:36:11,045][76542] Updated weights for policy 1, policy_version 23580 (0.0008) -[2023-10-10 13:36:11,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 48267264. Throughput: 0: 1809.8, 1: 1831.3. Samples: 12079480. Policy #0 lag: (min: 26.0, avg: 30.4, max: 58.0) -[2023-10-10 13:36:11,076][75634] Avg episode reward: [(0, '28.380'), (1, '27.440')] -[2023-10-10 13:36:12,090][76543] Updated weights for policy 0, policy_version 23593 (0.0009) -[2023-10-10 13:36:12,461][76543] Updated weights for policy 0, policy_version 23603 (0.0008) -[2023-10-10 13:36:12,830][76543] Updated weights for policy 0, policy_version 23613 (0.0008) -[2023-10-10 13:36:14,624][76542] Updated weights for policy 1, policy_version 23590 (0.0009) -[2023-10-10 13:36:14,996][76542] Updated weights for policy 1, policy_version 23600 (0.0007) -[2023-10-10 13:36:15,360][76542] Updated weights for policy 1, policy_version 23610 (0.0007) -[2023-10-10 13:36:16,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 48365568. Throughput: 0: 1812.0, 1: 1831.0. Samples: 12101096. Policy #0 lag: (min: 26.0, avg: 30.4, max: 58.0) -[2023-10-10 13:36:16,076][75634] Avg episode reward: [(0, '29.430'), (1, '30.000')] -[2023-10-10 13:36:16,617][76543] Updated weights for policy 0, policy_version 23623 (0.0008) -[2023-10-10 13:36:16,995][76543] Updated weights for policy 0, policy_version 23633 (0.0008) -[2023-10-10 13:36:17,375][76543] Updated weights for policy 0, policy_version 23643 (0.0009) -[2023-10-10 13:36:18,871][76542] Updated weights for policy 1, policy_version 23620 (0.0007) -[2023-10-10 13:36:19,238][76542] Updated weights for policy 1, policy_version 23630 (0.0008) -[2023-10-10 13:36:19,609][76542] Updated weights for policy 1, policy_version 23640 (0.0010) -[2023-10-10 13:36:21,038][76543] Updated weights for policy 0, policy_version 23653 (0.0009) -[2023-10-10 13:36:21,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 48431104. Throughput: 0: 1812.2, 1: 1831.5. Samples: 12112566. Policy #0 lag: (min: 26.0, avg: 30.4, max: 58.0) -[2023-10-10 13:36:21,077][75634] Avg episode reward: [(0, '34.160'), (1, '29.930')] -[2023-10-10 13:36:21,409][76543] Updated weights for policy 0, policy_version 23663 (0.0009) -[2023-10-10 13:36:21,783][76543] Updated weights for policy 0, policy_version 23673 (0.0010) -[2023-10-10 13:36:23,150][76542] Updated weights for policy 1, policy_version 23650 (0.0009) -[2023-10-10 13:36:23,509][76542] Updated weights for policy 1, policy_version 23660 (0.0010) -[2023-10-10 13:36:23,888][76542] Updated weights for policy 1, policy_version 23670 (0.0010) -[2023-10-10 13:36:24,251][76542] Updated weights for policy 1, policy_version 23680 (0.0010) -[2023-10-10 13:36:25,483][76543] Updated weights for policy 0, policy_version 23683 (0.0008) -[2023-10-10 13:36:25,856][76543] Updated weights for policy 0, policy_version 23693 (0.0009) -[2023-10-10 13:36:26,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 48496640. Throughput: 0: 1817.1, 1: 1836.6. Samples: 12134122. Policy #0 lag: (min: 26.0, avg: 30.4, max: 58.0) -[2023-10-10 13:36:26,076][75634] Avg episode reward: [(0, '34.790'), (1, '29.920')] -[2023-10-10 13:36:26,225][76543] Updated weights for policy 0, policy_version 23703 (0.0009) -[2023-10-10 13:36:27,878][76542] Updated weights for policy 1, policy_version 23690 (0.0007) -[2023-10-10 13:36:28,252][76542] Updated weights for policy 1, policy_version 23700 (0.0008) -[2023-10-10 13:36:28,616][76542] Updated weights for policy 1, policy_version 23710 (0.0008) -[2023-10-10 13:36:29,809][76543] Updated weights for policy 0, policy_version 23713 (0.0009) -[2023-10-10 13:36:30,174][76543] Updated weights for policy 0, policy_version 23723 (0.0009) -[2023-10-10 13:36:30,546][76543] Updated weights for policy 0, policy_version 23733 (0.0009) -[2023-10-10 13:36:30,914][76543] Updated weights for policy 0, policy_version 23743 (0.0009) -[2023-10-10 13:36:31,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 48594944. Throughput: 0: 1829.7, 1: 1839.5. Samples: 12156830. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-10 13:36:31,076][75634] Avg episode reward: [(0, '35.160'), (1, '31.270')] -[2023-10-10 13:36:31,084][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000023744_24313856.pth... -[2023-10-10 13:36:31,084][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000023712_24281088.pth... -[2023-10-10 13:36:31,115][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000022016_22544384.pth -[2023-10-10 13:36:31,123][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000022048_22577152.pth -[2023-10-10 13:36:32,258][76542] Updated weights for policy 1, policy_version 23720 (0.0011) -[2023-10-10 13:36:32,624][76542] Updated weights for policy 1, policy_version 23730 (0.0008) -[2023-10-10 13:36:32,998][76542] Updated weights for policy 1, policy_version 23740 (0.0007) -[2023-10-10 13:36:34,574][76543] Updated weights for policy 0, policy_version 23753 (0.0009) -[2023-10-10 13:36:34,949][76543] Updated weights for policy 0, policy_version 23763 (0.0009) -[2023-10-10 13:36:35,315][76543] Updated weights for policy 0, policy_version 23773 (0.0008) -[2023-10-10 13:36:36,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 48660480. Throughput: 0: 1827.7, 1: 1842.4. Samples: 12167542. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-10 13:36:36,076][75634] Avg episode reward: [(0, '35.520'), (1, '33.560')] -[2023-10-10 13:36:36,650][76542] Updated weights for policy 1, policy_version 23750 (0.0008) -[2023-10-10 13:36:37,022][76542] Updated weights for policy 1, policy_version 23760 (0.0009) -[2023-10-10 13:36:37,386][76542] Updated weights for policy 1, policy_version 23770 (0.0011) -[2023-10-10 13:36:39,020][76543] Updated weights for policy 0, policy_version 23783 (0.0009) -[2023-10-10 13:36:39,382][76543] Updated weights for policy 0, policy_version 23793 (0.0008) -[2023-10-10 13:36:39,755][76543] Updated weights for policy 0, policy_version 23803 (0.0007) -[2023-10-10 13:36:40,992][76542] Updated weights for policy 1, policy_version 23780 (0.0010) -[2023-10-10 13:36:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 48726016. Throughput: 0: 1828.1, 1: 1839.3. Samples: 12189608. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-10 13:36:41,076][75634] Avg episode reward: [(0, '35.020'), (1, '31.230')] -[2023-10-10 13:36:41,366][76542] Updated weights for policy 1, policy_version 23790 (0.0010) -[2023-10-10 13:36:41,726][76542] Updated weights for policy 1, policy_version 23800 (0.0007) -[2023-10-10 13:36:43,197][76543] Updated weights for policy 0, policy_version 23813 (0.0010) -[2023-10-10 13:36:43,570][76543] Updated weights for policy 0, policy_version 23823 (0.0009) -[2023-10-10 13:36:43,942][76543] Updated weights for policy 0, policy_version 23833 (0.0009) -[2023-10-10 13:36:45,483][76542] Updated weights for policy 1, policy_version 23810 (0.0009) -[2023-10-10 13:36:45,895][76542] Updated weights for policy 1, policy_version 23820 (0.0010) -[2023-10-10 13:36:46,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 48791552. Throughput: 0: 1819.9, 1: 1828.7. Samples: 12211188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:36:46,077][75634] Avg episode reward: [(0, '37.260'), (1, '32.630')] -[2023-10-10 13:36:46,085][76362] Saving new best policy, reward=37.260! -[2023-10-10 13:36:46,263][76542] Updated weights for policy 1, policy_version 23830 (0.0010) -[2023-10-10 13:36:46,642][76542] Updated weights for policy 1, policy_version 23840 (0.0009) -[2023-10-10 13:36:47,835][76543] Updated weights for policy 0, policy_version 23843 (0.0009) -[2023-10-10 13:36:48,217][76543] Updated weights for policy 0, policy_version 23853 (0.0010) -[2023-10-10 13:36:48,576][76543] Updated weights for policy 0, policy_version 23863 (0.0010) -[2023-10-10 13:36:50,448][76542] Updated weights for policy 1, policy_version 23850 (0.0009) -[2023-10-10 13:36:50,812][76542] Updated weights for policy 1, policy_version 23860 (0.0008) -[2023-10-10 13:36:51,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 48857088. Throughput: 0: 1825.5, 1: 1833.4. Samples: 12222130. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:36:51,076][75634] Avg episode reward: [(0, '31.330'), (1, '29.450')] -[2023-10-10 13:36:51,184][76542] Updated weights for policy 1, policy_version 23870 (0.0008) -[2023-10-10 13:36:52,173][76543] Updated weights for policy 0, policy_version 23873 (0.0010) -[2023-10-10 13:36:52,544][76543] Updated weights for policy 0, policy_version 23883 (0.0007) -[2023-10-10 13:36:52,912][76543] Updated weights for policy 0, policy_version 23893 (0.0007) -[2023-10-10 13:36:53,279][76543] Updated weights for policy 0, policy_version 23903 (0.0007) -[2023-10-10 13:36:54,902][76542] Updated weights for policy 1, policy_version 23880 (0.0010) -[2023-10-10 13:36:55,260][76542] Updated weights for policy 1, policy_version 23890 (0.0011) -[2023-10-10 13:36:55,621][76542] Updated weights for policy 1, policy_version 23900 (0.0009) -[2023-10-10 13:36:56,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 48955392. Throughput: 0: 1823.5, 1: 1834.2. Samples: 12244074. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:36:56,077][75634] Avg episode reward: [(0, '30.360'), (1, '32.040')] -[2023-10-10 13:36:56,789][76543] Updated weights for policy 0, policy_version 23913 (0.0008) -[2023-10-10 13:36:57,163][76543] Updated weights for policy 0, policy_version 23923 (0.0008) -[2023-10-10 13:36:57,532][76543] Updated weights for policy 0, policy_version 23933 (0.0010) -[2023-10-10 13:36:59,239][76542] Updated weights for policy 1, policy_version 23910 (0.0009) -[2023-10-10 13:36:59,611][76542] Updated weights for policy 1, policy_version 23920 (0.0007) -[2023-10-10 13:36:59,988][76542] Updated weights for policy 1, policy_version 23930 (0.0008) -[2023-10-10 13:37:01,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 49020928. Throughput: 0: 1829.8, 1: 1827.7. Samples: 12265686. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:37:01,076][75634] Avg episode reward: [(0, '31.230'), (1, '35.250')] -[2023-10-10 13:37:01,206][76543] Updated weights for policy 0, policy_version 23943 (0.0009) -[2023-10-10 13:37:01,586][76543] Updated weights for policy 0, policy_version 23953 (0.0008) -[2023-10-10 13:37:01,961][76543] Updated weights for policy 0, policy_version 23963 (0.0007) -[2023-10-10 13:37:03,581][76542] Updated weights for policy 1, policy_version 23940 (0.0007) -[2023-10-10 13:37:03,945][76542] Updated weights for policy 1, policy_version 23950 (0.0007) -[2023-10-10 13:37:04,309][76542] Updated weights for policy 1, policy_version 23960 (0.0009) -[2023-10-10 13:37:05,651][76543] Updated weights for policy 0, policy_version 23973 (0.0007) -[2023-10-10 13:37:06,018][76543] Updated weights for policy 0, policy_version 23983 (0.0007) -[2023-10-10 13:37:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 49086464. Throughput: 0: 1829.5, 1: 1823.6. Samples: 12276956. Policy #0 lag: (min: 30.0, avg: 30.0, max: 32.0) -[2023-10-10 13:37:06,076][75634] Avg episode reward: [(0, '31.510'), (1, '33.810')] -[2023-10-10 13:37:06,396][76543] Updated weights for policy 0, policy_version 23993 (0.0010) -[2023-10-10 13:37:07,877][76542] Updated weights for policy 1, policy_version 23970 (0.0009) -[2023-10-10 13:37:08,250][76542] Updated weights for policy 1, policy_version 23980 (0.0010) -[2023-10-10 13:37:08,619][76542] Updated weights for policy 1, policy_version 23990 (0.0007) -[2023-10-10 13:37:08,989][76542] Updated weights for policy 1, policy_version 24000 (0.0007) -[2023-10-10 13:37:10,136][76543] Updated weights for policy 0, policy_version 24003 (0.0009) -[2023-10-10 13:37:10,500][76543] Updated weights for policy 0, policy_version 24013 (0.0010) -[2023-10-10 13:37:10,869][76543] Updated weights for policy 0, policy_version 24023 (0.0008) -[2023-10-10 13:37:11,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 49152000. Throughput: 0: 1830.8, 1: 1829.4. Samples: 12298834. Policy #0 lag: (min: 30.0, avg: 30.0, max: 32.0) -[2023-10-10 13:37:11,076][75634] Avg episode reward: [(0, '31.980'), (1, '32.660')] -[2023-10-10 13:37:12,660][76542] Updated weights for policy 1, policy_version 24010 (0.0011) -[2023-10-10 13:37:13,021][76542] Updated weights for policy 1, policy_version 24020 (0.0011) -[2023-10-10 13:37:13,396][76542] Updated weights for policy 1, policy_version 24030 (0.0011) -[2023-10-10 13:37:14,766][76543] Updated weights for policy 0, policy_version 24033 (0.0010) -[2023-10-10 13:37:15,134][76543] Updated weights for policy 0, policy_version 24043 (0.0011) -[2023-10-10 13:37:15,501][76543] Updated weights for policy 0, policy_version 24053 (0.0010) -[2023-10-10 13:37:15,878][76543] Updated weights for policy 0, policy_version 24063 (0.0010) -[2023-10-10 13:37:16,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 49250304. Throughput: 0: 1819.9, 1: 1824.2. Samples: 12320812. Policy #0 lag: (min: 30.0, avg: 30.0, max: 32.0) -[2023-10-10 13:37:16,076][75634] Avg episode reward: [(0, '31.630'), (1, '33.120')] -[2023-10-10 13:37:17,175][76542] Updated weights for policy 1, policy_version 24040 (0.0011) -[2023-10-10 13:37:17,547][76542] Updated weights for policy 1, policy_version 24050 (0.0008) -[2023-10-10 13:37:17,917][76542] Updated weights for policy 1, policy_version 24060 (0.0007) -[2023-10-10 13:37:19,667][76543] Updated weights for policy 0, policy_version 24073 (0.0009) -[2023-10-10 13:37:20,048][76543] Updated weights for policy 0, policy_version 24083 (0.0011) -[2023-10-10 13:37:20,406][76543] Updated weights for policy 0, policy_version 24093 (0.0007) -[2023-10-10 13:37:21,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 49315840. Throughput: 0: 1816.0, 1: 1818.3. Samples: 12331088. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) -[2023-10-10 13:37:21,076][75634] Avg episode reward: [(0, '31.270'), (1, '33.280')] -[2023-10-10 13:37:21,446][76542] Updated weights for policy 1, policy_version 24070 (0.0007) -[2023-10-10 13:37:21,819][76542] Updated weights for policy 1, policy_version 24080 (0.0011) -[2023-10-10 13:37:22,181][76542] Updated weights for policy 1, policy_version 24090 (0.0008) -[2023-10-10 13:37:24,130][76543] Updated weights for policy 0, policy_version 24103 (0.0007) -[2023-10-10 13:37:24,499][76543] Updated weights for policy 0, policy_version 24113 (0.0007) -[2023-10-10 13:37:24,870][76543] Updated weights for policy 0, policy_version 24123 (0.0009) -[2023-10-10 13:37:26,024][76542] Updated weights for policy 1, policy_version 24100 (0.0007) -[2023-10-10 13:37:26,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 49381376. Throughput: 0: 1823.8, 1: 1820.9. Samples: 12353620. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) -[2023-10-10 13:37:26,077][75634] Avg episode reward: [(0, '33.450'), (1, '29.400')] -[2023-10-10 13:37:26,396][76542] Updated weights for policy 1, policy_version 24110 (0.0007) -[2023-10-10 13:37:26,761][76542] Updated weights for policy 1, policy_version 24120 (0.0007) -[2023-10-10 13:37:28,488][76543] Updated weights for policy 0, policy_version 24133 (0.0009) -[2023-10-10 13:37:28,860][76543] Updated weights for policy 0, policy_version 24143 (0.0008) -[2023-10-10 13:37:29,220][76543] Updated weights for policy 0, policy_version 24153 (0.0008) -[2023-10-10 13:37:30,657][76542] Updated weights for policy 1, policy_version 24130 (0.0008) -[2023-10-10 13:37:31,073][76542] Updated weights for policy 1, policy_version 24140 (0.0008) -[2023-10-10 13:37:31,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 49446912. Throughput: 0: 1822.1, 1: 1826.3. Samples: 12375364. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) -[2023-10-10 13:37:31,076][75634] Avg episode reward: [(0, '33.560'), (1, '28.830')] -[2023-10-10 13:37:31,433][76542] Updated weights for policy 1, policy_version 24150 (0.0008) -[2023-10-10 13:37:31,802][76542] Updated weights for policy 1, policy_version 24160 (0.0009) -[2023-10-10 13:37:32,910][76543] Updated weights for policy 0, policy_version 24163 (0.0009) -[2023-10-10 13:37:33,280][76543] Updated weights for policy 0, policy_version 24173 (0.0010) -[2023-10-10 13:37:33,653][76543] Updated weights for policy 0, policy_version 24183 (0.0010) -[2023-10-10 13:37:35,613][76542] Updated weights for policy 1, policy_version 24170 (0.0008) -[2023-10-10 13:37:35,989][76542] Updated weights for policy 1, policy_version 24180 (0.0009) -[2023-10-10 13:37:36,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 49512448. Throughput: 0: 1827.9, 1: 1823.6. Samples: 12386450. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) -[2023-10-10 13:37:36,076][75634] Avg episode reward: [(0, '34.330'), (1, '29.830')] -[2023-10-10 13:37:36,365][76542] Updated weights for policy 1, policy_version 24190 (0.0010) -[2023-10-10 13:37:37,314][76543] Updated weights for policy 0, policy_version 24193 (0.0009) -[2023-10-10 13:37:37,691][76543] Updated weights for policy 0, policy_version 24203 (0.0008) -[2023-10-10 13:37:38,059][76543] Updated weights for policy 0, policy_version 24213 (0.0009) -[2023-10-10 13:37:38,436][76543] Updated weights for policy 0, policy_version 24223 (0.0008) -[2023-10-10 13:37:40,088][76542] Updated weights for policy 1, policy_version 24200 (0.0008) -[2023-10-10 13:37:40,449][76542] Updated weights for policy 1, policy_version 24210 (0.0009) -[2023-10-10 13:37:40,811][76542] Updated weights for policy 1, policy_version 24220 (0.0009) -[2023-10-10 13:37:41,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 49610752. Throughput: 0: 1825.6, 1: 1821.1. Samples: 12408174. Policy #0 lag: (min: 17.0, avg: 31.5, max: 32.0) -[2023-10-10 13:37:41,077][75634] Avg episode reward: [(0, '34.890'), (1, '32.960')] -[2023-10-10 13:37:42,053][76543] Updated weights for policy 0, policy_version 24233 (0.0009) -[2023-10-10 13:37:42,431][76543] Updated weights for policy 0, policy_version 24243 (0.0009) -[2023-10-10 13:37:42,800][76543] Updated weights for policy 0, policy_version 24253 (0.0012) -[2023-10-10 13:37:44,473][76542] Updated weights for policy 1, policy_version 24230 (0.0009) -[2023-10-10 13:37:44,844][76542] Updated weights for policy 1, policy_version 24240 (0.0009) -[2023-10-10 13:37:45,217][76542] Updated weights for policy 1, policy_version 24250 (0.0007) -[2023-10-10 13:37:46,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 49676288. Throughput: 0: 1825.3, 1: 1818.8. Samples: 12429670. Policy #0 lag: (min: 17.0, avg: 31.5, max: 32.0) -[2023-10-10 13:37:46,077][75634] Avg episode reward: [(0, '33.770'), (1, '33.070')] -[2023-10-10 13:37:46,451][76543] Updated weights for policy 0, policy_version 24263 (0.0008) -[2023-10-10 13:37:46,821][76543] Updated weights for policy 0, policy_version 24273 (0.0008) -[2023-10-10 13:37:47,194][76543] Updated weights for policy 0, policy_version 24283 (0.0009) -[2023-10-10 13:37:48,886][76542] Updated weights for policy 1, policy_version 24260 (0.0009) -[2023-10-10 13:37:49,256][76542] Updated weights for policy 1, policy_version 24270 (0.0009) -[2023-10-10 13:37:49,624][76542] Updated weights for policy 1, policy_version 24280 (0.0009) -[2023-10-10 13:37:50,819][76543] Updated weights for policy 0, policy_version 24293 (0.0010) -[2023-10-10 13:37:51,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 49741824. Throughput: 0: 1824.2, 1: 1818.9. Samples: 12440896. Policy #0 lag: (min: 17.0, avg: 31.5, max: 32.0) -[2023-10-10 13:37:51,076][75634] Avg episode reward: [(0, '33.770'), (1, '35.240')] -[2023-10-10 13:37:51,194][76543] Updated weights for policy 0, policy_version 24303 (0.0010) -[2023-10-10 13:37:51,570][76543] Updated weights for policy 0, policy_version 24313 (0.0009) -[2023-10-10 13:37:53,209][76542] Updated weights for policy 1, policy_version 24290 (0.0008) -[2023-10-10 13:37:53,580][76542] Updated weights for policy 1, policy_version 24300 (0.0011) -[2023-10-10 13:37:53,945][76542] Updated weights for policy 1, policy_version 24310 (0.0008) -[2023-10-10 13:37:54,307][76542] Updated weights for policy 1, policy_version 24320 (0.0007) -[2023-10-10 13:37:55,224][76543] Updated weights for policy 0, policy_version 24323 (0.0010) -[2023-10-10 13:37:55,600][76543] Updated weights for policy 0, policy_version 24333 (0.0008) -[2023-10-10 13:37:55,974][76543] Updated weights for policy 0, policy_version 24343 (0.0010) -[2023-10-10 13:37:56,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 49807360. Throughput: 0: 1823.0, 1: 1815.0. Samples: 12462544. Policy #0 lag: (min: 17.0, avg: 31.5, max: 32.0) -[2023-10-10 13:37:56,077][75634] Avg episode reward: [(0, '33.550'), (1, '33.060')] -[2023-10-10 13:37:57,956][76542] Updated weights for policy 1, policy_version 24330 (0.0010) -[2023-10-10 13:37:58,320][76542] Updated weights for policy 1, policy_version 24340 (0.0008) -[2023-10-10 13:37:58,687][76542] Updated weights for policy 1, policy_version 24350 (0.0010) -[2023-10-10 13:37:59,714][76543] Updated weights for policy 0, policy_version 24353 (0.0011) -[2023-10-10 13:38:00,079][76543] Updated weights for policy 0, policy_version 24363 (0.0008) -[2023-10-10 13:38:00,451][76543] Updated weights for policy 0, policy_version 24373 (0.0007) -[2023-10-10 13:38:00,825][76543] Updated weights for policy 0, policy_version 24383 (0.0007) -[2023-10-10 13:38:01,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 49905664. Throughput: 0: 1824.0, 1: 1826.7. Samples: 12485096. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-10 13:38:01,076][75634] Avg episode reward: [(0, '34.380'), (1, '33.840')] -[2023-10-10 13:38:02,334][76542] Updated weights for policy 1, policy_version 24360 (0.0009) -[2023-10-10 13:38:02,694][76542] Updated weights for policy 1, policy_version 24370 (0.0009) -[2023-10-10 13:38:03,067][76542] Updated weights for policy 1, policy_version 24380 (0.0009) -[2023-10-10 13:38:04,448][76543] Updated weights for policy 0, policy_version 24393 (0.0009) -[2023-10-10 13:38:04,824][76543] Updated weights for policy 0, policy_version 24403 (0.0008) -[2023-10-10 13:38:05,196][76543] Updated weights for policy 0, policy_version 24413 (0.0007) -[2023-10-10 13:38:06,076][75634] Fps is (10 sec: 16384.5, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 49971200. Throughput: 0: 1828.2, 1: 1832.5. Samples: 12495820. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-10 13:38:06,076][75634] Avg episode reward: [(0, '33.380'), (1, '32.090')] -[2023-10-10 13:38:06,732][76542] Updated weights for policy 1, policy_version 24390 (0.0010) -[2023-10-10 13:38:07,098][76542] Updated weights for policy 1, policy_version 24400 (0.0010) -[2023-10-10 13:38:07,465][76542] Updated weights for policy 1, policy_version 24410 (0.0010) -[2023-10-10 13:38:08,734][76543] Updated weights for policy 0, policy_version 24423 (0.0007) -[2023-10-10 13:38:09,100][76543] Updated weights for policy 0, policy_version 24433 (0.0007) -[2023-10-10 13:38:09,471][76543] Updated weights for policy 0, policy_version 24443 (0.0007) -[2023-10-10 13:38:11,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 50036736. Throughput: 0: 1818.4, 1: 1826.3. Samples: 12517628. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-10 13:38:11,077][75634] Avg episode reward: [(0, '35.050'), (1, '28.870')] -[2023-10-10 13:38:11,116][76542] Updated weights for policy 1, policy_version 24420 (0.0009) -[2023-10-10 13:38:11,495][76542] Updated weights for policy 1, policy_version 24430 (0.0008) -[2023-10-10 13:38:11,867][76542] Updated weights for policy 1, policy_version 24440 (0.0008) -[2023-10-10 13:38:13,263][76543] Updated weights for policy 0, policy_version 24453 (0.0008) -[2023-10-10 13:38:13,636][76543] Updated weights for policy 0, policy_version 24463 (0.0008) -[2023-10-10 13:38:14,020][76543] Updated weights for policy 0, policy_version 24473 (0.0007) -[2023-10-10 13:38:15,518][76542] Updated weights for policy 1, policy_version 24450 (0.0009) -[2023-10-10 13:38:15,906][76542] Updated weights for policy 1, policy_version 24460 (0.0009) -[2023-10-10 13:38:16,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 50102272. Throughput: 0: 1825.7, 1: 1824.4. Samples: 12539618. Policy #0 lag: (min: 31.0, avg: 42.3, max: 63.0) -[2023-10-10 13:38:16,077][75634] Avg episode reward: [(0, '34.630'), (1, '27.420')] -[2023-10-10 13:38:16,275][76542] Updated weights for policy 1, policy_version 24470 (0.0009) -[2023-10-10 13:38:16,647][76542] Updated weights for policy 1, policy_version 24480 (0.0009) -[2023-10-10 13:38:17,627][76543] Updated weights for policy 0, policy_version 24483 (0.0009) -[2023-10-10 13:38:18,006][76543] Updated weights for policy 0, policy_version 24493 (0.0009) -[2023-10-10 13:38:18,388][76543] Updated weights for policy 0, policy_version 24503 (0.0011) -[2023-10-10 13:38:20,411][76542] Updated weights for policy 1, policy_version 24490 (0.0009) -[2023-10-10 13:38:20,772][76542] Updated weights for policy 1, policy_version 24500 (0.0007) -[2023-10-10 13:38:21,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 50167808. Throughput: 0: 1815.3, 1: 1827.4. Samples: 12550370. Policy #0 lag: (min: 31.0, avg: 42.3, max: 63.0) -[2023-10-10 13:38:21,076][75634] Avg episode reward: [(0, '32.600'), (1, '27.730')] -[2023-10-10 13:38:21,151][76542] Updated weights for policy 1, policy_version 24510 (0.0011) -[2023-10-10 13:38:22,128][76543] Updated weights for policy 0, policy_version 24513 (0.0009) -[2023-10-10 13:38:22,497][76543] Updated weights for policy 0, policy_version 24523 (0.0009) -[2023-10-10 13:38:22,861][76543] Updated weights for policy 0, policy_version 24533 (0.0009) -[2023-10-10 13:38:23,235][76543] Updated weights for policy 0, policy_version 24543 (0.0010) -[2023-10-10 13:38:24,626][76542] Updated weights for policy 1, policy_version 24520 (0.0011) -[2023-10-10 13:38:24,987][76542] Updated weights for policy 1, policy_version 24530 (0.0010) -[2023-10-10 13:38:25,357][76542] Updated weights for policy 1, policy_version 24540 (0.0008) -[2023-10-10 13:38:26,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 50266112. Throughput: 0: 1822.8, 1: 1820.9. Samples: 12572140. Policy #0 lag: (min: 31.0, avg: 42.3, max: 63.0) -[2023-10-10 13:38:26,077][75634] Avg episode reward: [(0, '33.160'), (1, '32.420')] -[2023-10-10 13:38:27,003][76543] Updated weights for policy 0, policy_version 24553 (0.0010) -[2023-10-10 13:38:27,370][76543] Updated weights for policy 0, policy_version 24563 (0.0008) -[2023-10-10 13:38:27,740][76543] Updated weights for policy 0, policy_version 24573 (0.0008) -[2023-10-10 13:38:29,044][76542] Updated weights for policy 1, policy_version 24550 (0.0007) -[2023-10-10 13:38:29,403][76542] Updated weights for policy 1, policy_version 24560 (0.0007) -[2023-10-10 13:38:29,776][76542] Updated weights for policy 1, policy_version 24570 (0.0009) -[2023-10-10 13:38:31,076][75634] Fps is (10 sec: 16383.5, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 50331648. Throughput: 0: 1818.5, 1: 1833.1. Samples: 12593996. Policy #0 lag: (min: 31.0, avg: 42.3, max: 63.0) -[2023-10-10 13:38:31,077][75634] Avg episode reward: [(0, '32.590'), (1, '32.410')] -[2023-10-10 13:38:31,087][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000024576_25165824.pth... -[2023-10-10 13:38:31,123][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000022848_23396352.pth -[2023-10-10 13:38:31,364][76543] Updated weights for policy 0, policy_version 24583 (0.0007) -[2023-10-10 13:38:31,748][76543] Updated weights for policy 0, policy_version 24593 (0.0009) -[2023-10-10 13:38:32,122][76543] Updated weights for policy 0, policy_version 24603 (0.0007) -[2023-10-10 13:38:32,303][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000024608_25198592.pth... -[2023-10-10 13:38:32,332][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000022880_23429120.pth -[2023-10-10 13:38:33,497][76542] Updated weights for policy 1, policy_version 24580 (0.0007) -[2023-10-10 13:38:33,864][76542] Updated weights for policy 1, policy_version 24590 (0.0008) -[2023-10-10 13:38:34,242][76542] Updated weights for policy 1, policy_version 24600 (0.0009) -[2023-10-10 13:38:35,686][76543] Updated weights for policy 0, policy_version 24613 (0.0007) -[2023-10-10 13:38:36,062][76543] Updated weights for policy 0, policy_version 24623 (0.0008) -[2023-10-10 13:38:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 50397184. Throughput: 0: 1817.7, 1: 1825.6. Samples: 12604844. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) -[2023-10-10 13:38:36,076][75634] Avg episode reward: [(0, '32.670'), (1, '33.010')] -[2023-10-10 13:38:36,440][76543] Updated weights for policy 0, policy_version 24633 (0.0008) -[2023-10-10 13:38:37,923][76542] Updated weights for policy 1, policy_version 24610 (0.0009) -[2023-10-10 13:38:38,292][76542] Updated weights for policy 1, policy_version 24620 (0.0007) -[2023-10-10 13:38:38,658][76542] Updated weights for policy 1, policy_version 24630 (0.0008) -[2023-10-10 13:38:39,032][76542] Updated weights for policy 1, policy_version 24640 (0.0007) -[2023-10-10 13:38:40,252][76543] Updated weights for policy 0, policy_version 24643 (0.0009) -[2023-10-10 13:38:40,622][76543] Updated weights for policy 0, policy_version 24653 (0.0008) -[2023-10-10 13:38:40,996][76543] Updated weights for policy 0, policy_version 24663 (0.0007) -[2023-10-10 13:38:41,076][75634] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 50462720. Throughput: 0: 1813.5, 1: 1827.5. Samples: 12626386. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) -[2023-10-10 13:38:41,076][75634] Avg episode reward: [(0, '31.320'), (1, '34.970')] -[2023-10-10 13:38:42,637][76542] Updated weights for policy 1, policy_version 24650 (0.0010) -[2023-10-10 13:38:43,004][76542] Updated weights for policy 1, policy_version 24660 (0.0007) -[2023-10-10 13:38:43,377][76542] Updated weights for policy 1, policy_version 24670 (0.0007) -[2023-10-10 13:38:44,638][76543] Updated weights for policy 0, policy_version 24673 (0.0008) -[2023-10-10 13:38:45,006][76543] Updated weights for policy 0, policy_version 24683 (0.0008) -[2023-10-10 13:38:45,378][76543] Updated weights for policy 0, policy_version 24693 (0.0007) -[2023-10-10 13:38:45,748][76543] Updated weights for policy 0, policy_version 24703 (0.0007) -[2023-10-10 13:38:46,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 50561024. Throughput: 0: 1812.7, 1: 1817.3. Samples: 12648450. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) -[2023-10-10 13:38:46,077][75634] Avg episode reward: [(0, '31.350'), (1, '33.680')] -[2023-10-10 13:38:47,131][76542] Updated weights for policy 1, policy_version 24680 (0.0010) -[2023-10-10 13:38:47,498][76542] Updated weights for policy 1, policy_version 24690 (0.0009) -[2023-10-10 13:38:47,862][76542] Updated weights for policy 1, policy_version 24700 (0.0007) -[2023-10-10 13:38:49,497][76543] Updated weights for policy 0, policy_version 24713 (0.0010) -[2023-10-10 13:38:49,878][76543] Updated weights for policy 0, policy_version 24723 (0.0010) -[2023-10-10 13:38:50,258][76543] Updated weights for policy 0, policy_version 24733 (0.0008) -[2023-10-10 13:38:51,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 50626560. Throughput: 0: 1812.0, 1: 1817.2. Samples: 12659136. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-10 13:38:51,076][75634] Avg episode reward: [(0, '30.860'), (1, '33.980')] -[2023-10-10 13:38:51,606][76542] Updated weights for policy 1, policy_version 24710 (0.0008) -[2023-10-10 13:38:51,967][76542] Updated weights for policy 1, policy_version 24720 (0.0007) -[2023-10-10 13:38:52,340][76542] Updated weights for policy 1, policy_version 24730 (0.0009) -[2023-10-10 13:38:53,800][76543] Updated weights for policy 0, policy_version 24743 (0.0008) -[2023-10-10 13:38:54,173][76543] Updated weights for policy 0, policy_version 24753 (0.0009) -[2023-10-10 13:38:54,539][76543] Updated weights for policy 0, policy_version 24763 (0.0008) -[2023-10-10 13:38:56,027][76542] Updated weights for policy 1, policy_version 24740 (0.0008) -[2023-10-10 13:38:56,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 50692096. Throughput: 0: 1817.3, 1: 1817.5. Samples: 12681194. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-10 13:38:56,076][75634] Avg episode reward: [(0, '32.230'), (1, '30.050')] -[2023-10-10 13:38:56,390][76542] Updated weights for policy 1, policy_version 24750 (0.0007) -[2023-10-10 13:38:56,763][76542] Updated weights for policy 1, policy_version 24760 (0.0009) -[2023-10-10 13:38:58,396][76543] Updated weights for policy 0, policy_version 24773 (0.0007) -[2023-10-10 13:38:58,766][76543] Updated weights for policy 0, policy_version 24783 (0.0008) -[2023-10-10 13:38:59,132][76543] Updated weights for policy 0, policy_version 24793 (0.0009) -[2023-10-10 13:39:00,477][76542] Updated weights for policy 1, policy_version 24770 (0.0007) -[2023-10-10 13:39:00,877][76542] Updated weights for policy 1, policy_version 24780 (0.0009) -[2023-10-10 13:39:01,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 50757632. Throughput: 0: 1812.7, 1: 1817.4. Samples: 12702970. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-10 13:39:01,077][75634] Avg episode reward: [(0, '32.890'), (1, '32.040')] -[2023-10-10 13:39:01,243][76542] Updated weights for policy 1, policy_version 24790 (0.0008) -[2023-10-10 13:39:01,622][76542] Updated weights for policy 1, policy_version 24800 (0.0008) -[2023-10-10 13:39:02,913][76543] Updated weights for policy 0, policy_version 24803 (0.0009) -[2023-10-10 13:39:03,281][76543] Updated weights for policy 0, policy_version 24813 (0.0009) -[2023-10-10 13:39:03,656][76543] Updated weights for policy 0, policy_version 24823 (0.0008) -[2023-10-10 13:39:05,436][76542] Updated weights for policy 1, policy_version 24810 (0.0010) -[2023-10-10 13:39:05,802][76542] Updated weights for policy 1, policy_version 24820 (0.0009) -[2023-10-10 13:39:06,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 50823168. Throughput: 0: 1817.2, 1: 1823.0. Samples: 12714178. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-10 13:39:06,076][75634] Avg episode reward: [(0, '32.920'), (1, '29.690')] -[2023-10-10 13:39:06,172][76542] Updated weights for policy 1, policy_version 24830 (0.0008) -[2023-10-10 13:39:07,310][76543] Updated weights for policy 0, policy_version 24833 (0.0008) -[2023-10-10 13:39:07,680][76543] Updated weights for policy 0, policy_version 24843 (0.0010) -[2023-10-10 13:39:08,045][76543] Updated weights for policy 0, policy_version 24853 (0.0010) -[2023-10-10 13:39:08,418][76543] Updated weights for policy 0, policy_version 24863 (0.0009) -[2023-10-10 13:39:09,922][76542] Updated weights for policy 1, policy_version 24840 (0.0008) -[2023-10-10 13:39:10,284][76542] Updated weights for policy 1, policy_version 24850 (0.0009) -[2023-10-10 13:39:10,656][76542] Updated weights for policy 1, policy_version 24860 (0.0008) -[2023-10-10 13:39:11,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 50921472. Throughput: 0: 1810.2, 1: 1820.4. Samples: 12735520. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-10 13:39:11,077][75634] Avg episode reward: [(0, '35.050'), (1, '31.560')] -[2023-10-10 13:39:12,050][76543] Updated weights for policy 0, policy_version 24873 (0.0010) -[2023-10-10 13:39:12,426][76543] Updated weights for policy 0, policy_version 24883 (0.0008) -[2023-10-10 13:39:12,799][76543] Updated weights for policy 0, policy_version 24893 (0.0008) -[2023-10-10 13:39:14,386][76542] Updated weights for policy 1, policy_version 24870 (0.0008) -[2023-10-10 13:39:14,755][76542] Updated weights for policy 1, policy_version 24880 (0.0008) -[2023-10-10 13:39:15,121][76542] Updated weights for policy 1, policy_version 24890 (0.0008) -[2023-10-10 13:39:16,076][75634] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 50987008. Throughput: 0: 1810.6, 1: 1810.4. Samples: 12756940. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-10 13:39:16,077][75634] Avg episode reward: [(0, '31.850'), (1, '32.570')] -[2023-10-10 13:39:16,480][76543] Updated weights for policy 0, policy_version 24903 (0.0009) -[2023-10-10 13:39:16,860][76543] Updated weights for policy 0, policy_version 24913 (0.0009) -[2023-10-10 13:39:17,243][76543] Updated weights for policy 0, policy_version 24923 (0.0009) -[2023-10-10 13:39:18,716][76542] Updated weights for policy 1, policy_version 24900 (0.0009) -[2023-10-10 13:39:19,091][76542] Updated weights for policy 1, policy_version 24910 (0.0009) -[2023-10-10 13:39:19,452][76542] Updated weights for policy 1, policy_version 24920 (0.0008) -[2023-10-10 13:39:20,904][76543] Updated weights for policy 0, policy_version 24933 (0.0009) -[2023-10-10 13:39:21,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 51052544. Throughput: 0: 1815.5, 1: 1818.7. Samples: 12768384. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-10 13:39:21,077][75634] Avg episode reward: [(0, '31.260'), (1, '34.950')] -[2023-10-10 13:39:21,280][76543] Updated weights for policy 0, policy_version 24943 (0.0007) -[2023-10-10 13:39:21,654][76543] Updated weights for policy 0, policy_version 24953 (0.0010) -[2023-10-10 13:39:23,197][76542] Updated weights for policy 1, policy_version 24930 (0.0008) -[2023-10-10 13:39:23,560][76542] Updated weights for policy 1, policy_version 24940 (0.0008) -[2023-10-10 13:39:23,928][76542] Updated weights for policy 1, policy_version 24950 (0.0008) -[2023-10-10 13:39:24,296][76542] Updated weights for policy 1, policy_version 24960 (0.0011) -[2023-10-10 13:39:25,313][76543] Updated weights for policy 0, policy_version 24963 (0.0007) -[2023-10-10 13:39:25,693][76543] Updated weights for policy 0, policy_version 24973 (0.0008) -[2023-10-10 13:39:26,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 51118080. Throughput: 0: 1820.0, 1: 1812.4. Samples: 12789844. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-10 13:39:26,077][75634] Avg episode reward: [(0, '32.120'), (1, '37.250')] -[2023-10-10 13:39:26,078][76421] Saving new best policy, reward=37.250! -[2023-10-10 13:39:26,080][76543] Updated weights for policy 0, policy_version 24983 (0.0009) -[2023-10-10 13:39:27,924][76542] Updated weights for policy 1, policy_version 24970 (0.0010) -[2023-10-10 13:39:28,290][76542] Updated weights for policy 1, policy_version 24980 (0.0009) -[2023-10-10 13:39:28,662][76542] Updated weights for policy 1, policy_version 24990 (0.0007) -[2023-10-10 13:39:29,732][76543] Updated weights for policy 0, policy_version 24993 (0.0008) -[2023-10-10 13:39:30,105][76543] Updated weights for policy 0, policy_version 25003 (0.0009) -[2023-10-10 13:39:30,474][76543] Updated weights for policy 0, policy_version 25013 (0.0009) -[2023-10-10 13:39:30,852][76543] Updated weights for policy 0, policy_version 25023 (0.0009) -[2023-10-10 13:39:31,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 51216384. Throughput: 0: 1825.3, 1: 1816.8. Samples: 12812340. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 13:39:31,077][75634] Avg episode reward: [(0, '33.480'), (1, '32.220')] -[2023-10-10 13:39:32,278][76542] Updated weights for policy 1, policy_version 25000 (0.0008) -[2023-10-10 13:39:32,652][76542] Updated weights for policy 1, policy_version 25010 (0.0008) -[2023-10-10 13:39:33,012][76542] Updated weights for policy 1, policy_version 25020 (0.0009) -[2023-10-10 13:39:34,366][76543] Updated weights for policy 0, policy_version 25033 (0.0010) -[2023-10-10 13:39:34,732][76543] Updated weights for policy 0, policy_version 25043 (0.0009) -[2023-10-10 13:39:35,114][76543] Updated weights for policy 0, policy_version 25053 (0.0010) -[2023-10-10 13:39:36,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 51281920. Throughput: 0: 1828.9, 1: 1813.8. Samples: 12823060. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 13:39:36,076][75634] Avg episode reward: [(0, '34.270'), (1, '34.140')] -[2023-10-10 13:39:36,673][76542] Updated weights for policy 1, policy_version 25030 (0.0009) -[2023-10-10 13:39:37,046][76542] Updated weights for policy 1, policy_version 25040 (0.0007) -[2023-10-10 13:39:37,412][76542] Updated weights for policy 1, policy_version 25050 (0.0009) -[2023-10-10 13:39:38,819][76543] Updated weights for policy 0, policy_version 25063 (0.0008) -[2023-10-10 13:39:39,188][76543] Updated weights for policy 0, policy_version 25073 (0.0008) -[2023-10-10 13:39:39,564][76543] Updated weights for policy 0, policy_version 25083 (0.0009) -[2023-10-10 13:39:40,985][76542] Updated weights for policy 1, policy_version 25060 (0.0008) -[2023-10-10 13:39:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 51347456. Throughput: 0: 1823.9, 1: 1820.8. Samples: 12845202. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 13:39:41,076][75634] Avg episode reward: [(0, '36.540'), (1, '35.120')] -[2023-10-10 13:39:41,362][76542] Updated weights for policy 1, policy_version 25070 (0.0008) -[2023-10-10 13:39:41,731][76542] Updated weights for policy 1, policy_version 25080 (0.0009) -[2023-10-10 13:39:43,245][76543] Updated weights for policy 0, policy_version 25093 (0.0008) -[2023-10-10 13:39:43,616][76543] Updated weights for policy 0, policy_version 25103 (0.0009) -[2023-10-10 13:39:43,981][76543] Updated weights for policy 0, policy_version 25113 (0.0009) -[2023-10-10 13:39:45,385][76542] Updated weights for policy 1, policy_version 25090 (0.0008) -[2023-10-10 13:39:45,763][76542] Updated weights for policy 1, policy_version 25100 (0.0009) -[2023-10-10 13:39:46,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 51412992. Throughput: 0: 1822.0, 1: 1816.3. Samples: 12866690. Policy #0 lag: (min: 10.0, avg: 13.0, max: 42.0) -[2023-10-10 13:39:46,077][75634] Avg episode reward: [(0, '36.240'), (1, '35.320')] -[2023-10-10 13:39:46,126][76542] Updated weights for policy 1, policy_version 25110 (0.0008) -[2023-10-10 13:39:46,497][76542] Updated weights for policy 1, policy_version 25120 (0.0008) -[2023-10-10 13:39:47,584][76543] Updated weights for policy 0, policy_version 25123 (0.0008) -[2023-10-10 13:39:47,952][76543] Updated weights for policy 0, policy_version 25133 (0.0009) -[2023-10-10 13:39:48,325][76543] Updated weights for policy 0, policy_version 25143 (0.0010) -[2023-10-10 13:39:50,286][76542] Updated weights for policy 1, policy_version 25130 (0.0008) -[2023-10-10 13:39:50,659][76542] Updated weights for policy 1, policy_version 25140 (0.0009) -[2023-10-10 13:39:51,032][76542] Updated weights for policy 1, policy_version 25150 (0.0009) -[2023-10-10 13:39:51,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 51478528. Throughput: 0: 1818.0, 1: 1821.3. Samples: 12877944. Policy #0 lag: (min: 10.0, avg: 13.0, max: 42.0) -[2023-10-10 13:39:51,076][75634] Avg episode reward: [(0, '36.260'), (1, '32.810')] -[2023-10-10 13:39:51,852][76543] Updated weights for policy 0, policy_version 25153 (0.0009) -[2023-10-10 13:39:52,227][76543] Updated weights for policy 0, policy_version 25163 (0.0007) -[2023-10-10 13:39:52,594][76543] Updated weights for policy 0, policy_version 25173 (0.0008) -[2023-10-10 13:39:52,972][76543] Updated weights for policy 0, policy_version 25183 (0.0009) -[2023-10-10 13:39:54,502][76542] Updated weights for policy 1, policy_version 25160 (0.0009) -[2023-10-10 13:39:54,876][76542] Updated weights for policy 1, policy_version 25170 (0.0008) -[2023-10-10 13:39:55,243][76542] Updated weights for policy 1, policy_version 25180 (0.0008) -[2023-10-10 13:39:56,076][75634] Fps is (10 sec: 16384.5, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 51576832. Throughput: 0: 1831.8, 1: 1821.0. Samples: 12899896. Policy #0 lag: (min: 10.0, avg: 13.0, max: 42.0) -[2023-10-10 13:39:56,076][75634] Avg episode reward: [(0, '37.070'), (1, '29.590')] -[2023-10-10 13:39:56,768][76543] Updated weights for policy 0, policy_version 25193 (0.0007) -[2023-10-10 13:39:57,135][76543] Updated weights for policy 0, policy_version 25203 (0.0008) -[2023-10-10 13:39:57,515][76543] Updated weights for policy 0, policy_version 25213 (0.0010) -[2023-10-10 13:39:59,035][76542] Updated weights for policy 1, policy_version 25190 (0.0009) -[2023-10-10 13:39:59,405][76542] Updated weights for policy 1, policy_version 25200 (0.0010) -[2023-10-10 13:39:59,775][76542] Updated weights for policy 1, policy_version 25210 (0.0008) -[2023-10-10 13:40:01,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 51642368. Throughput: 0: 1830.9, 1: 1831.3. Samples: 12921738. Policy #0 lag: (min: 10.0, avg: 13.0, max: 42.0) -[2023-10-10 13:40:01,076][75634] Avg episode reward: [(0, '36.330'), (1, '30.680')] -[2023-10-10 13:40:01,219][76543] Updated weights for policy 0, policy_version 25223 (0.0007) -[2023-10-10 13:40:01,596][76543] Updated weights for policy 0, policy_version 25233 (0.0008) -[2023-10-10 13:40:01,984][76543] Updated weights for policy 0, policy_version 25243 (0.0008) -[2023-10-10 13:40:03,371][76542] Updated weights for policy 1, policy_version 25220 (0.0010) -[2023-10-10 13:40:03,743][76542] Updated weights for policy 1, policy_version 25230 (0.0009) -[2023-10-10 13:40:04,115][76542] Updated weights for policy 1, policy_version 25240 (0.0009) -[2023-10-10 13:40:05,486][76543] Updated weights for policy 0, policy_version 25253 (0.0007) -[2023-10-10 13:40:05,866][76543] Updated weights for policy 0, policy_version 25263 (0.0007) -[2023-10-10 13:40:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 51707904. Throughput: 0: 1828.7, 1: 1815.9. Samples: 12932392. Policy #0 lag: (min: 25.0, avg: 28.1, max: 57.0) -[2023-10-10 13:40:06,076][75634] Avg episode reward: [(0, '33.180'), (1, '32.500')] -[2023-10-10 13:40:06,232][76543] Updated weights for policy 0, policy_version 25273 (0.0008) -[2023-10-10 13:40:07,895][76542] Updated weights for policy 1, policy_version 25250 (0.0010) -[2023-10-10 13:40:08,257][76542] Updated weights for policy 1, policy_version 25260 (0.0009) -[2023-10-10 13:40:08,622][76542] Updated weights for policy 1, policy_version 25270 (0.0009) -[2023-10-10 13:40:08,990][76542] Updated weights for policy 1, policy_version 25280 (0.0007) -[2023-10-10 13:40:09,907][76543] Updated weights for policy 0, policy_version 25283 (0.0007) -[2023-10-10 13:40:10,280][76543] Updated weights for policy 0, policy_version 25293 (0.0007) -[2023-10-10 13:40:10,648][76543] Updated weights for policy 0, policy_version 25303 (0.0009) -[2023-10-10 13:40:11,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 51806208. Throughput: 0: 1828.0, 1: 1826.4. Samples: 12954292. Policy #0 lag: (min: 25.0, avg: 28.1, max: 57.0) -[2023-10-10 13:40:11,077][75634] Avg episode reward: [(0, '35.180'), (1, '34.020')] -[2023-10-10 13:40:12,721][76542] Updated weights for policy 1, policy_version 25290 (0.0008) -[2023-10-10 13:40:13,076][76542] Updated weights for policy 1, policy_version 25300 (0.0009) -[2023-10-10 13:40:13,458][76542] Updated weights for policy 1, policy_version 25310 (0.0008) -[2023-10-10 13:40:14,417][76543] Updated weights for policy 0, policy_version 25313 (0.0008) -[2023-10-10 13:40:14,792][76543] Updated weights for policy 0, policy_version 25323 (0.0009) -[2023-10-10 13:40:15,164][76543] Updated weights for policy 0, policy_version 25333 (0.0010) -[2023-10-10 13:40:15,533][76543] Updated weights for policy 0, policy_version 25343 (0.0007) -[2023-10-10 13:40:16,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 51871744. Throughput: 0: 1820.0, 1: 1818.0. Samples: 12976050. Policy #0 lag: (min: 25.0, avg: 28.1, max: 57.0) -[2023-10-10 13:40:16,076][75634] Avg episode reward: [(0, '37.610'), (1, '31.370')] -[2023-10-10 13:40:16,083][76362] Saving new best policy, reward=37.610! -[2023-10-10 13:40:17,213][76542] Updated weights for policy 1, policy_version 25320 (0.0009) -[2023-10-10 13:40:17,578][76542] Updated weights for policy 1, policy_version 25330 (0.0009) -[2023-10-10 13:40:17,951][76542] Updated weights for policy 1, policy_version 25340 (0.0009) -[2023-10-10 13:40:19,108][76543] Updated weights for policy 0, policy_version 25353 (0.0009) -[2023-10-10 13:40:19,482][76543] Updated weights for policy 0, policy_version 25363 (0.0010) -[2023-10-10 13:40:19,852][76543] Updated weights for policy 0, policy_version 25373 (0.0009) -[2023-10-10 13:40:21,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 51937280. Throughput: 0: 1835.2, 1: 1815.0. Samples: 12987320. Policy #0 lag: (min: 18.0, avg: 18.1, max: 22.0) -[2023-10-10 13:40:21,076][75634] Avg episode reward: [(0, '35.730'), (1, '30.560')] -[2023-10-10 13:40:21,626][76542] Updated weights for policy 1, policy_version 25350 (0.0009) -[2023-10-10 13:40:21,994][76542] Updated weights for policy 1, policy_version 25360 (0.0007) -[2023-10-10 13:40:22,361][76542] Updated weights for policy 1, policy_version 25370 (0.0009) -[2023-10-10 13:40:23,349][76543] Updated weights for policy 0, policy_version 25383 (0.0007) -[2023-10-10 13:40:23,726][76543] Updated weights for policy 0, policy_version 25393 (0.0008) -[2023-10-10 13:40:24,090][76543] Updated weights for policy 0, policy_version 25403 (0.0008) -[2023-10-10 13:40:26,043][76542] Updated weights for policy 1, policy_version 25380 (0.0008) -[2023-10-10 13:40:26,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 52002816. Throughput: 0: 1827.2, 1: 1816.7. Samples: 13009178. Policy #0 lag: (min: 18.0, avg: 18.1, max: 22.0) -[2023-10-10 13:40:26,077][75634] Avg episode reward: [(0, '36.240'), (1, '33.520')] -[2023-10-10 13:40:26,418][76542] Updated weights for policy 1, policy_version 25390 (0.0008) -[2023-10-10 13:40:26,788][76542] Updated weights for policy 1, policy_version 25400 (0.0007) -[2023-10-10 13:40:27,975][76543] Updated weights for policy 0, policy_version 25413 (0.0009) -[2023-10-10 13:40:28,341][76543] Updated weights for policy 0, policy_version 25423 (0.0008) -[2023-10-10 13:40:28,704][76543] Updated weights for policy 0, policy_version 25433 (0.0008) -[2023-10-10 13:40:30,408][76542] Updated weights for policy 1, policy_version 25410 (0.0011) -[2023-10-10 13:40:30,769][76542] Updated weights for policy 1, policy_version 25420 (0.0008) -[2023-10-10 13:40:31,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 52068352. Throughput: 0: 1837.7, 1: 1819.9. Samples: 13031280. Policy #0 lag: (min: 18.0, avg: 18.1, max: 22.0) -[2023-10-10 13:40:31,076][75634] Avg episode reward: [(0, '36.500'), (1, '30.530')] -[2023-10-10 13:40:31,084][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000025440_26050560.pth... -[2023-10-10 13:40:31,125][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000023744_24313856.pth -[2023-10-10 13:40:31,131][76362] Saving a milestone ./train_atari/atari_defender_APPO/checkpoint_p0/milestones/checkpoint_000025440_26050560.pth -[2023-10-10 13:40:31,148][76542] Updated weights for policy 1, policy_version 25430 (0.0009) -[2023-10-10 13:40:31,511][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000025440_26050560.pth... -[2023-10-10 13:40:31,511][76542] Updated weights for policy 1, policy_version 25440 (0.0008) -[2023-10-10 13:40:31,551][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000023712_24281088.pth -[2023-10-10 13:40:31,557][76421] Saving a milestone ./train_atari/atari_defender_APPO/checkpoint_p1/milestones/checkpoint_000025440_26050560.pth -[2023-10-10 13:40:32,444][76543] Updated weights for policy 0, policy_version 25443 (0.0008) -[2023-10-10 13:40:32,814][76543] Updated weights for policy 0, policy_version 25453 (0.0008) -[2023-10-10 13:40:33,182][76543] Updated weights for policy 0, policy_version 25463 (0.0010) -[2023-10-10 13:40:35,266][76542] Updated weights for policy 1, policy_version 25450 (0.0009) -[2023-10-10 13:40:35,620][76542] Updated weights for policy 1, policy_version 25460 (0.0007) -[2023-10-10 13:40:35,986][76542] Updated weights for policy 1, policy_version 25470 (0.0009) -[2023-10-10 13:40:36,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 52166656. Throughput: 0: 1832.2, 1: 1817.0. Samples: 13042160. Policy #0 lag: (min: 18.0, avg: 18.1, max: 22.0) -[2023-10-10 13:40:36,077][75634] Avg episode reward: [(0, '35.120'), (1, '31.040')] -[2023-10-10 13:40:36,924][76543] Updated weights for policy 0, policy_version 25473 (0.0007) -[2023-10-10 13:40:37,289][76543] Updated weights for policy 0, policy_version 25483 (0.0008) -[2023-10-10 13:40:37,653][76543] Updated weights for policy 0, policy_version 25493 (0.0007) -[2023-10-10 13:40:38,028][76543] Updated weights for policy 0, policy_version 25503 (0.0008) -[2023-10-10 13:40:39,779][76542] Updated weights for policy 1, policy_version 25480 (0.0008) -[2023-10-10 13:40:40,148][76542] Updated weights for policy 1, policy_version 25490 (0.0009) -[2023-10-10 13:40:40,512][76542] Updated weights for policy 1, policy_version 25500 (0.0009) -[2023-10-10 13:40:41,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 52232192. Throughput: 0: 1835.6, 1: 1815.2. Samples: 13064182. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 13:40:41,076][75634] Avg episode reward: [(0, '34.740'), (1, '30.090')] -[2023-10-10 13:40:41,534][76543] Updated weights for policy 0, policy_version 25513 (0.0010) -[2023-10-10 13:40:41,912][76543] Updated weights for policy 0, policy_version 25523 (0.0008) -[2023-10-10 13:40:42,280][76543] Updated weights for policy 0, policy_version 25533 (0.0007) -[2023-10-10 13:40:44,248][76542] Updated weights for policy 1, policy_version 25510 (0.0009) -[2023-10-10 13:40:44,614][76542] Updated weights for policy 1, policy_version 25520 (0.0011) -[2023-10-10 13:40:44,988][76542] Updated weights for policy 1, policy_version 25530 (0.0008) -[2023-10-10 13:40:45,930][76543] Updated weights for policy 0, policy_version 25543 (0.0008) -[2023-10-10 13:40:46,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 52297728. Throughput: 0: 1837.2, 1: 1810.8. Samples: 13085898. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 13:40:46,076][75634] Avg episode reward: [(0, '34.900'), (1, '31.680')] -[2023-10-10 13:40:46,300][76543] Updated weights for policy 0, policy_version 25553 (0.0010) -[2023-10-10 13:40:46,680][76543] Updated weights for policy 0, policy_version 25563 (0.0007) -[2023-10-10 13:40:48,680][76542] Updated weights for policy 1, policy_version 25540 (0.0009) -[2023-10-10 13:40:49,054][76542] Updated weights for policy 1, policy_version 25550 (0.0007) -[2023-10-10 13:40:49,414][76542] Updated weights for policy 1, policy_version 25560 (0.0009) -[2023-10-10 13:40:50,272][76543] Updated weights for policy 0, policy_version 25573 (0.0008) -[2023-10-10 13:40:50,648][76543] Updated weights for policy 0, policy_version 25583 (0.0008) -[2023-10-10 13:40:51,010][76543] Updated weights for policy 0, policy_version 25593 (0.0009) -[2023-10-10 13:40:51,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 52363264. Throughput: 0: 1834.8, 1: 1819.5. Samples: 13096832. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 13:40:51,076][75634] Avg episode reward: [(0, '34.950'), (1, '37.330')] -[2023-10-10 13:40:51,077][76421] Saving new best policy, reward=37.330! -[2023-10-10 13:40:53,112][76542] Updated weights for policy 1, policy_version 25570 (0.0010) -[2023-10-10 13:40:53,478][76542] Updated weights for policy 1, policy_version 25580 (0.0012) -[2023-10-10 13:40:53,849][76542] Updated weights for policy 1, policy_version 25590 (0.0008) -[2023-10-10 13:40:54,216][76542] Updated weights for policy 1, policy_version 25600 (0.0008) -[2023-10-10 13:40:54,909][76543] Updated weights for policy 0, policy_version 25603 (0.0009) -[2023-10-10 13:40:55,270][76543] Updated weights for policy 0, policy_version 25613 (0.0007) -[2023-10-10 13:40:55,642][76543] Updated weights for policy 0, policy_version 25623 (0.0007) -[2023-10-10 13:40:56,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 52461568. Throughput: 0: 1830.3, 1: 1812.3. Samples: 13118210. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 13:40:56,077][75634] Avg episode reward: [(0, '33.060'), (1, '35.030')] -[2023-10-10 13:40:57,834][76542] Updated weights for policy 1, policy_version 25610 (0.0008) -[2023-10-10 13:40:58,198][76542] Updated weights for policy 1, policy_version 25620 (0.0007) -[2023-10-10 13:40:58,575][76542] Updated weights for policy 1, policy_version 25630 (0.0008) -[2023-10-10 13:40:59,324][76543] Updated weights for policy 0, policy_version 25633 (0.0007) -[2023-10-10 13:40:59,692][76543] Updated weights for policy 0, policy_version 25643 (0.0007) -[2023-10-10 13:41:00,058][76543] Updated weights for policy 0, policy_version 25653 (0.0009) -[2023-10-10 13:41:00,435][76543] Updated weights for policy 0, policy_version 25663 (0.0009) -[2023-10-10 13:41:01,076][75634] Fps is (10 sec: 16383.4, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 52527104. Throughput: 0: 1827.2, 1: 1814.8. Samples: 13139942. Policy #0 lag: (min: 9.0, avg: 17.8, max: 41.0) -[2023-10-10 13:41:01,077][75634] Avg episode reward: [(0, '33.390'), (1, '33.460')] -[2023-10-10 13:41:02,318][76542] Updated weights for policy 1, policy_version 25640 (0.0007) -[2023-10-10 13:41:02,681][76542] Updated weights for policy 1, policy_version 25650 (0.0008) -[2023-10-10 13:41:03,045][76542] Updated weights for policy 1, policy_version 25660 (0.0007) -[2023-10-10 13:41:04,111][76543] Updated weights for policy 0, policy_version 25673 (0.0007) -[2023-10-10 13:41:04,493][76543] Updated weights for policy 0, policy_version 25683 (0.0011) -[2023-10-10 13:41:04,861][76543] Updated weights for policy 0, policy_version 25693 (0.0011) -[2023-10-10 13:41:06,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 52592640. Throughput: 0: 1820.1, 1: 1818.5. Samples: 13151058. Policy #0 lag: (min: 9.0, avg: 17.8, max: 41.0) -[2023-10-10 13:41:06,076][75634] Avg episode reward: [(0, '32.050'), (1, '35.390')] -[2023-10-10 13:41:06,750][76542] Updated weights for policy 1, policy_version 25670 (0.0007) -[2023-10-10 13:41:07,109][76542] Updated weights for policy 1, policy_version 25680 (0.0009) -[2023-10-10 13:41:07,477][76542] Updated weights for policy 1, policy_version 25690 (0.0007) -[2023-10-10 13:41:08,623][76543] Updated weights for policy 0, policy_version 25703 (0.0010) -[2023-10-10 13:41:08,998][76543] Updated weights for policy 0, policy_version 25713 (0.0009) -[2023-10-10 13:41:09,380][76543] Updated weights for policy 0, policy_version 25723 (0.0008) -[2023-10-10 13:41:11,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 52658176. Throughput: 0: 1822.0, 1: 1809.6. Samples: 13172600. Policy #0 lag: (min: 9.0, avg: 17.8, max: 41.0) -[2023-10-10 13:41:11,077][75634] Avg episode reward: [(0, '32.760'), (1, '32.630')] -[2023-10-10 13:41:11,329][76542] Updated weights for policy 1, policy_version 25700 (0.0007) -[2023-10-10 13:41:11,701][76542] Updated weights for policy 1, policy_version 25710 (0.0009) -[2023-10-10 13:41:12,081][76542] Updated weights for policy 1, policy_version 25720 (0.0009) -[2023-10-10 13:41:12,889][76543] Updated weights for policy 0, policy_version 25733 (0.0008) -[2023-10-10 13:41:13,257][76543] Updated weights for policy 0, policy_version 25743 (0.0008) -[2023-10-10 13:41:13,629][76543] Updated weights for policy 0, policy_version 25753 (0.0007) -[2023-10-10 13:41:15,926][76542] Updated weights for policy 1, policy_version 25730 (0.0007) -[2023-10-10 13:41:16,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 52723712. Throughput: 0: 1828.7, 1: 1814.0. Samples: 13195204. Policy #0 lag: (min: 9.0, avg: 17.8, max: 41.0) -[2023-10-10 13:41:16,076][75634] Avg episode reward: [(0, '31.850'), (1, '32.400')] -[2023-10-10 13:41:16,303][76542] Updated weights for policy 1, policy_version 25740 (0.0007) -[2023-10-10 13:41:16,664][76542] Updated weights for policy 1, policy_version 25750 (0.0007) -[2023-10-10 13:41:17,039][76542] Updated weights for policy 1, policy_version 25760 (0.0008) -[2023-10-10 13:41:17,190][76543] Updated weights for policy 0, policy_version 25763 (0.0007) -[2023-10-10 13:41:17,559][76543] Updated weights for policy 0, policy_version 25773 (0.0007) -[2023-10-10 13:41:17,920][76543] Updated weights for policy 0, policy_version 25783 (0.0010) -[2023-10-10 13:41:20,756][76542] Updated weights for policy 1, policy_version 25770 (0.0007) -[2023-10-10 13:41:21,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 52789248. Throughput: 0: 1825.3, 1: 1803.4. Samples: 13205454. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-10 13:41:21,077][75634] Avg episode reward: [(0, '30.640'), (1, '29.540')] -[2023-10-10 13:41:21,126][76542] Updated weights for policy 1, policy_version 25780 (0.0007) -[2023-10-10 13:41:21,502][76542] Updated weights for policy 1, policy_version 25790 (0.0007) -[2023-10-10 13:41:21,632][76543] Updated weights for policy 0, policy_version 25793 (0.0009) -[2023-10-10 13:41:21,997][76543] Updated weights for policy 0, policy_version 25803 (0.0008) -[2023-10-10 13:41:22,371][76543] Updated weights for policy 0, policy_version 25813 (0.0011) -[2023-10-10 13:41:22,743][76543] Updated weights for policy 0, policy_version 25823 (0.0008) -[2023-10-10 13:41:25,191][76542] Updated weights for policy 1, policy_version 25800 (0.0008) -[2023-10-10 13:41:25,560][76542] Updated weights for policy 1, policy_version 25810 (0.0007) -[2023-10-10 13:41:25,927][76542] Updated weights for policy 1, policy_version 25820 (0.0008) -[2023-10-10 13:41:26,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 52887552. Throughput: 0: 1829.8, 1: 1816.0. Samples: 13228244. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-10 13:41:26,076][75634] Avg episode reward: [(0, '28.560'), (1, '29.830')] -[2023-10-10 13:41:26,288][76543] Updated weights for policy 0, policy_version 25833 (0.0008) -[2023-10-10 13:41:26,654][76543] Updated weights for policy 0, policy_version 25843 (0.0007) -[2023-10-10 13:41:27,030][76543] Updated weights for policy 0, policy_version 25853 (0.0007) -[2023-10-10 13:41:29,647][76542] Updated weights for policy 1, policy_version 25830 (0.0008) -[2023-10-10 13:41:30,016][76542] Updated weights for policy 1, policy_version 25840 (0.0007) -[2023-10-10 13:41:30,380][76542] Updated weights for policy 1, policy_version 25850 (0.0009) -[2023-10-10 13:41:30,738][76543] Updated weights for policy 0, policy_version 25863 (0.0008) -[2023-10-10 13:41:31,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 52953088. Throughput: 0: 1825.1, 1: 1809.3. Samples: 13249446. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-10 13:41:31,076][75634] Avg episode reward: [(0, '28.540'), (1, '32.810')] -[2023-10-10 13:41:31,104][76543] Updated weights for policy 0, policy_version 25873 (0.0009) -[2023-10-10 13:41:31,484][76543] Updated weights for policy 0, policy_version 25883 (0.0009) -[2023-10-10 13:41:34,055][76542] Updated weights for policy 1, policy_version 25860 (0.0008) -[2023-10-10 13:41:34,428][76542] Updated weights for policy 1, policy_version 25870 (0.0009) -[2023-10-10 13:41:34,799][76542] Updated weights for policy 1, policy_version 25880 (0.0008) -[2023-10-10 13:41:35,105][76543] Updated weights for policy 0, policy_version 25893 (0.0009) -[2023-10-10 13:41:35,486][76543] Updated weights for policy 0, policy_version 25903 (0.0008) -[2023-10-10 13:41:35,861][76543] Updated weights for policy 0, policy_version 25913 (0.0008) -[2023-10-10 13:41:36,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 53018624. Throughput: 0: 1829.9, 1: 1817.3. Samples: 13260956. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-10 13:41:36,077][75634] Avg episode reward: [(0, '29.600'), (1, '33.170')] -[2023-10-10 13:41:38,356][76542] Updated weights for policy 1, policy_version 25890 (0.0007) -[2023-10-10 13:41:38,721][76542] Updated weights for policy 1, policy_version 25900 (0.0007) -[2023-10-10 13:41:39,087][76542] Updated weights for policy 1, policy_version 25910 (0.0008) -[2023-10-10 13:41:39,362][76543] Updated weights for policy 0, policy_version 25923 (0.0007) -[2023-10-10 13:41:39,454][76542] Updated weights for policy 1, policy_version 25920 (0.0008) -[2023-10-10 13:41:39,730][76543] Updated weights for policy 0, policy_version 25933 (0.0007) -[2023-10-10 13:41:40,105][76543] Updated weights for policy 0, policy_version 25943 (0.0008) -[2023-10-10 13:41:41,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 53116928. Throughput: 0: 1838.8, 1: 1815.2. Samples: 13282642. Policy #0 lag: (min: 31.0, avg: 33.3, max: 59.0) -[2023-10-10 13:41:41,077][75634] Avg episode reward: [(0, '30.700'), (1, '30.530')] -[2023-10-10 13:41:43,271][76542] Updated weights for policy 1, policy_version 25930 (0.0010) -[2023-10-10 13:41:43,635][76542] Updated weights for policy 1, policy_version 25940 (0.0007) -[2023-10-10 13:41:43,660][76543] Updated weights for policy 0, policy_version 25953 (0.0009) -[2023-10-10 13:41:44,006][76542] Updated weights for policy 1, policy_version 25950 (0.0008) -[2023-10-10 13:41:44,027][76543] Updated weights for policy 0, policy_version 25963 (0.0008) -[2023-10-10 13:41:44,402][76543] Updated weights for policy 0, policy_version 25973 (0.0009) -[2023-10-10 13:41:44,771][76543] Updated weights for policy 0, policy_version 25983 (0.0008) -[2023-10-10 13:41:46,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 53182464. Throughput: 0: 1836.6, 1: 1814.6. Samples: 13304248. Policy #0 lag: (min: 31.0, avg: 33.3, max: 59.0) -[2023-10-10 13:41:46,077][75634] Avg episode reward: [(0, '30.950'), (1, '29.680')] -[2023-10-10 13:41:47,529][76542] Updated weights for policy 1, policy_version 25960 (0.0008) -[2023-10-10 13:41:47,902][76542] Updated weights for policy 1, policy_version 25970 (0.0011) -[2023-10-10 13:41:48,265][76542] Updated weights for policy 1, policy_version 25980 (0.0008) -[2023-10-10 13:41:48,510][76543] Updated weights for policy 0, policy_version 25993 (0.0009) -[2023-10-10 13:41:48,891][76543] Updated weights for policy 0, policy_version 26003 (0.0007) -[2023-10-10 13:41:49,259][76543] Updated weights for policy 0, policy_version 26013 (0.0009) -[2023-10-10 13:41:51,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 53248000. Throughput: 0: 1842.5, 1: 1811.4. Samples: 13315486. Policy #0 lag: (min: 31.0, avg: 33.3, max: 59.0) -[2023-10-10 13:41:51,077][75634] Avg episode reward: [(0, '30.620'), (1, '33.570')] -[2023-10-10 13:41:51,977][76542] Updated weights for policy 1, policy_version 25990 (0.0008) -[2023-10-10 13:41:52,341][76542] Updated weights for policy 1, policy_version 26000 (0.0007) -[2023-10-10 13:41:52,715][76542] Updated weights for policy 1, policy_version 26010 (0.0009) -[2023-10-10 13:41:52,879][76543] Updated weights for policy 0, policy_version 26023 (0.0009) -[2023-10-10 13:41:53,245][76543] Updated weights for policy 0, policy_version 26033 (0.0008) -[2023-10-10 13:41:53,623][76543] Updated weights for policy 0, policy_version 26043 (0.0007) -[2023-10-10 13:41:56,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 53313536. Throughput: 0: 1837.7, 1: 1813.3. Samples: 13336894. Policy #0 lag: (min: 31.0, avg: 33.3, max: 59.0) -[2023-10-10 13:41:56,077][75634] Avg episode reward: [(0, '33.750'), (1, '31.110')] -[2023-10-10 13:41:56,510][76542] Updated weights for policy 1, policy_version 26020 (0.0008) -[2023-10-10 13:41:56,891][76542] Updated weights for policy 1, policy_version 26030 (0.0011) -[2023-10-10 13:41:57,248][76543] Updated weights for policy 0, policy_version 26053 (0.0008) -[2023-10-10 13:41:57,252][76542] Updated weights for policy 1, policy_version 26040 (0.0009) -[2023-10-10 13:41:57,612][76543] Updated weights for policy 0, policy_version 26063 (0.0008) -[2023-10-10 13:41:57,987][76543] Updated weights for policy 0, policy_version 26073 (0.0009) -[2023-10-10 13:42:00,862][76542] Updated weights for policy 1, policy_version 26050 (0.0010) -[2023-10-10 13:42:01,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 53379072. Throughput: 0: 1840.9, 1: 1816.8. Samples: 13359800. Policy #0 lag: (min: 31.0, avg: 33.3, max: 59.0) -[2023-10-10 13:42:01,077][75634] Avg episode reward: [(0, '33.340'), (1, '31.250')] -[2023-10-10 13:42:01,232][76542] Updated weights for policy 1, policy_version 26060 (0.0011) -[2023-10-10 13:42:01,555][76543] Updated weights for policy 0, policy_version 26083 (0.0007) -[2023-10-10 13:42:01,597][76542] Updated weights for policy 1, policy_version 26070 (0.0007) -[2023-10-10 13:42:01,925][76543] Updated weights for policy 0, policy_version 26093 (0.0009) -[2023-10-10 13:42:01,966][76542] Updated weights for policy 1, policy_version 26080 (0.0007) -[2023-10-10 13:42:02,296][76543] Updated weights for policy 0, policy_version 26103 (0.0011) -[2023-10-10 13:42:05,819][76542] Updated weights for policy 1, policy_version 26090 (0.0008) -[2023-10-10 13:42:06,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 53444608. Throughput: 0: 1836.5, 1: 1815.8. Samples: 13369810. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) -[2023-10-10 13:42:06,077][75634] Avg episode reward: [(0, '32.280'), (1, '32.920')] -[2023-10-10 13:42:06,184][76542] Updated weights for policy 1, policy_version 26100 (0.0008) -[2023-10-10 13:42:06,250][76543] Updated weights for policy 0, policy_version 26113 (0.0010) -[2023-10-10 13:42:06,552][76542] Updated weights for policy 1, policy_version 26110 (0.0008) -[2023-10-10 13:42:06,624][76543] Updated weights for policy 0, policy_version 26123 (0.0010) -[2023-10-10 13:42:06,987][76543] Updated weights for policy 0, policy_version 26133 (0.0010) -[2023-10-10 13:42:07,360][76543] Updated weights for policy 0, policy_version 26143 (0.0010) -[2023-10-10 13:42:10,429][76542] Updated weights for policy 1, policy_version 26120 (0.0007) -[2023-10-10 13:42:10,805][76542] Updated weights for policy 1, policy_version 26130 (0.0008) -[2023-10-10 13:42:10,898][76543] Updated weights for policy 0, policy_version 26153 (0.0008) -[2023-10-10 13:42:11,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 53510144. Throughput: 0: 1834.1, 1: 1812.6. Samples: 13392344. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) -[2023-10-10 13:42:11,076][75634] Avg episode reward: [(0, '30.730'), (1, '34.030')] -[2023-10-10 13:42:11,169][76542] Updated weights for policy 1, policy_version 26140 (0.0008) -[2023-10-10 13:42:11,271][76543] Updated weights for policy 0, policy_version 26163 (0.0008) -[2023-10-10 13:42:11,653][76543] Updated weights for policy 0, policy_version 26173 (0.0008) -[2023-10-10 13:42:15,030][76542] Updated weights for policy 1, policy_version 26150 (0.0008) -[2023-10-10 13:42:15,268][76543] Updated weights for policy 0, policy_version 26183 (0.0008) -[2023-10-10 13:42:15,395][76542] Updated weights for policy 1, policy_version 26160 (0.0007) -[2023-10-10 13:42:15,645][76543] Updated weights for policy 0, policy_version 26193 (0.0008) -[2023-10-10 13:42:15,764][76542] Updated weights for policy 1, policy_version 26170 (0.0008) -[2023-10-10 13:42:16,014][76543] Updated weights for policy 0, policy_version 26203 (0.0007) -[2023-10-10 13:42:16,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 53608448. Throughput: 0: 1833.8, 1: 1814.2. Samples: 13413604. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) -[2023-10-10 13:42:16,077][75634] Avg episode reward: [(0, '31.740'), (1, '34.360')] -[2023-10-10 13:42:19,355][76542] Updated weights for policy 1, policy_version 26180 (0.0008) -[2023-10-10 13:42:19,723][76542] Updated weights for policy 1, policy_version 26190 (0.0007) -[2023-10-10 13:42:19,738][76543] Updated weights for policy 0, policy_version 26213 (0.0009) -[2023-10-10 13:42:20,088][76542] Updated weights for policy 1, policy_version 26200 (0.0009) -[2023-10-10 13:42:20,096][76543] Updated weights for policy 0, policy_version 26223 (0.0008) -[2023-10-10 13:42:20,471][76543] Updated weights for policy 0, policy_version 26233 (0.0008) -[2023-10-10 13:42:21,076][75634] Fps is (10 sec: 19660.8, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 53706752. Throughput: 0: 1837.8, 1: 1804.1. Samples: 13424844. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) -[2023-10-10 13:42:21,076][75634] Avg episode reward: [(0, '31.140'), (1, '34.690')] -[2023-10-10 13:42:23,832][76542] Updated weights for policy 1, policy_version 26210 (0.0009) -[2023-10-10 13:42:24,162][76543] Updated weights for policy 0, policy_version 26243 (0.0008) -[2023-10-10 13:42:24,197][76542] Updated weights for policy 1, policy_version 26220 (0.0009) -[2023-10-10 13:42:24,529][76543] Updated weights for policy 0, policy_version 26253 (0.0008) -[2023-10-10 13:42:24,560][76542] Updated weights for policy 1, policy_version 26230 (0.0010) -[2023-10-10 13:42:24,902][76543] Updated weights for policy 0, policy_version 26263 (0.0007) -[2023-10-10 13:42:24,921][76542] Updated weights for policy 1, policy_version 26240 (0.0008) -[2023-10-10 13:42:26,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 53772288. Throughput: 0: 1826.1, 1: 1811.5. Samples: 13446332. Policy #0 lag: (min: 31.0, avg: 43.2, max: 63.0) -[2023-10-10 13:42:26,077][75634] Avg episode reward: [(0, '30.650'), (1, '35.640')] -[2023-10-10 13:42:28,528][76542] Updated weights for policy 1, policy_version 26250 (0.0008) -[2023-10-10 13:42:28,688][76543] Updated weights for policy 0, policy_version 26273 (0.0009) -[2023-10-10 13:42:28,892][76542] Updated weights for policy 1, policy_version 26260 (0.0009) -[2023-10-10 13:42:29,060][76543] Updated weights for policy 0, policy_version 26283 (0.0010) -[2023-10-10 13:42:29,257][76542] Updated weights for policy 1, policy_version 26270 (0.0008) -[2023-10-10 13:42:29,423][76543] Updated weights for policy 0, policy_version 26293 (0.0008) -[2023-10-10 13:42:29,798][76543] Updated weights for policy 0, policy_version 26303 (0.0010) -[2023-10-10 13:42:31,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 53837824. Throughput: 0: 1822.5, 1: 1797.7. Samples: 13467158. Policy #0 lag: (min: 31.0, avg: 43.2, max: 63.0) -[2023-10-10 13:42:31,076][75634] Avg episode reward: [(0, '32.210'), (1, '34.780')] -[2023-10-10 13:42:31,084][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000026304_26935296.pth... -[2023-10-10 13:42:31,085][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000026272_26902528.pth... -[2023-10-10 13:42:31,114][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000024608_25198592.pth -[2023-10-10 13:42:31,116][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000024576_25165824.pth -[2023-10-10 13:42:32,941][76542] Updated weights for policy 1, policy_version 26280 (0.0010) -[2023-10-10 13:42:33,304][76542] Updated weights for policy 1, policy_version 26290 (0.0010) -[2023-10-10 13:42:33,574][76543] Updated weights for policy 0, policy_version 26313 (0.0009) -[2023-10-10 13:42:33,659][76542] Updated weights for policy 1, policy_version 26300 (0.0007) -[2023-10-10 13:42:33,945][76543] Updated weights for policy 0, policy_version 26323 (0.0007) -[2023-10-10 13:42:34,314][76543] Updated weights for policy 0, policy_version 26333 (0.0008) -[2023-10-10 13:42:36,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 53903360. Throughput: 0: 1824.8, 1: 1807.1. Samples: 13478922. Policy #0 lag: (min: 31.0, avg: 43.2, max: 63.0) -[2023-10-10 13:42:36,076][75634] Avg episode reward: [(0, '30.600'), (1, '35.700')] -[2023-10-10 13:42:37,306][76542] Updated weights for policy 1, policy_version 26310 (0.0007) -[2023-10-10 13:42:37,666][76542] Updated weights for policy 1, policy_version 26320 (0.0009) -[2023-10-10 13:42:38,016][76543] Updated weights for policy 0, policy_version 26343 (0.0008) -[2023-10-10 13:42:38,031][76542] Updated weights for policy 1, policy_version 26330 (0.0009) -[2023-10-10 13:42:38,383][76543] Updated weights for policy 0, policy_version 26353 (0.0007) -[2023-10-10 13:42:38,753][76543] Updated weights for policy 0, policy_version 26363 (0.0007) -[2023-10-10 13:42:41,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 53968896. Throughput: 0: 1818.4, 1: 1800.8. Samples: 13499758. Policy #0 lag: (min: 31.0, avg: 43.2, max: 63.0) -[2023-10-10 13:42:41,077][75634] Avg episode reward: [(0, '29.680'), (1, '32.390')] -[2023-10-10 13:42:41,804][76542] Updated weights for policy 1, policy_version 26340 (0.0009) -[2023-10-10 13:42:42,174][76542] Updated weights for policy 1, policy_version 26350 (0.0010) -[2023-10-10 13:42:42,498][76543] Updated weights for policy 0, policy_version 26373 (0.0008) -[2023-10-10 13:42:42,534][76542] Updated weights for policy 1, policy_version 26360 (0.0009) -[2023-10-10 13:42:42,867][76543] Updated weights for policy 0, policy_version 26383 (0.0007) -[2023-10-10 13:42:43,234][76543] Updated weights for policy 0, policy_version 26393 (0.0008) -[2023-10-10 13:42:46,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 54034432. Throughput: 0: 1815.5, 1: 1798.5. Samples: 13522432. Policy #0 lag: (min: 31.0, avg: 43.2, max: 63.0) -[2023-10-10 13:42:46,077][75634] Avg episode reward: [(0, '30.890'), (1, '31.850')] -[2023-10-10 13:42:46,279][76542] Updated weights for policy 1, policy_version 26370 (0.0008) -[2023-10-10 13:42:46,657][76542] Updated weights for policy 1, policy_version 26380 (0.0007) -[2023-10-10 13:42:47,019][76542] Updated weights for policy 1, policy_version 26390 (0.0007) -[2023-10-10 13:42:47,042][76543] Updated weights for policy 0, policy_version 26403 (0.0007) -[2023-10-10 13:42:47,384][76542] Updated weights for policy 1, policy_version 26400 (0.0009) -[2023-10-10 13:42:47,405][76543] Updated weights for policy 0, policy_version 26413 (0.0008) -[2023-10-10 13:42:47,777][76543] Updated weights for policy 0, policy_version 26423 (0.0010) -[2023-10-10 13:42:51,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 54099968. Throughput: 0: 1808.6, 1: 1802.9. Samples: 13532326. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-10 13:42:51,077][75634] Avg episode reward: [(0, '33.120'), (1, '30.990')] -[2023-10-10 13:42:51,098][76542] Updated weights for policy 1, policy_version 26410 (0.0009) -[2023-10-10 13:42:51,471][76542] Updated weights for policy 1, policy_version 26420 (0.0010) -[2023-10-10 13:42:51,621][76543] Updated weights for policy 0, policy_version 26433 (0.0010) -[2023-10-10 13:42:51,834][76542] Updated weights for policy 1, policy_version 26430 (0.0009) -[2023-10-10 13:42:51,993][76543] Updated weights for policy 0, policy_version 26443 (0.0008) -[2023-10-10 13:42:52,354][76543] Updated weights for policy 0, policy_version 26453 (0.0008) -[2023-10-10 13:42:52,727][76543] Updated weights for policy 0, policy_version 26463 (0.0010) -[2023-10-10 13:42:55,544][76542] Updated weights for policy 1, policy_version 26440 (0.0009) -[2023-10-10 13:42:55,914][76542] Updated weights for policy 1, policy_version 26450 (0.0009) -[2023-10-10 13:42:56,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 54165504. Throughput: 0: 1807.1, 1: 1807.1. Samples: 13554984. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-10 13:42:56,077][75634] Avg episode reward: [(0, '33.290'), (1, '30.280')] -[2023-10-10 13:42:56,281][76542] Updated weights for policy 1, policy_version 26460 (0.0007) -[2023-10-10 13:42:56,465][76543] Updated weights for policy 0, policy_version 26473 (0.0008) -[2023-10-10 13:42:56,834][76543] Updated weights for policy 0, policy_version 26483 (0.0009) -[2023-10-10 13:42:57,208][76543] Updated weights for policy 0, policy_version 26493 (0.0007) -[2023-10-10 13:42:59,925][76542] Updated weights for policy 1, policy_version 26470 (0.0009) -[2023-10-10 13:43:00,289][76542] Updated weights for policy 1, policy_version 26480 (0.0010) -[2023-10-10 13:43:00,657][76542] Updated weights for policy 1, policy_version 26490 (0.0007) -[2023-10-10 13:43:00,930][76543] Updated weights for policy 0, policy_version 26503 (0.0007) -[2023-10-10 13:43:01,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 54263808. Throughput: 0: 1802.6, 1: 1814.3. Samples: 13576366. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-10 13:43:01,076][75634] Avg episode reward: [(0, '30.430'), (1, '28.770')] -[2023-10-10 13:43:01,304][76543] Updated weights for policy 0, policy_version 26513 (0.0008) -[2023-10-10 13:43:01,670][76543] Updated weights for policy 0, policy_version 26523 (0.0008) -[2023-10-10 13:43:04,491][76542] Updated weights for policy 1, policy_version 26500 (0.0009) -[2023-10-10 13:43:04,858][76542] Updated weights for policy 1, policy_version 26510 (0.0008) -[2023-10-10 13:43:05,220][76542] Updated weights for policy 1, policy_version 26520 (0.0009) -[2023-10-10 13:43:05,395][76543] Updated weights for policy 0, policy_version 26533 (0.0008) -[2023-10-10 13:43:05,765][76543] Updated weights for policy 0, policy_version 26543 (0.0008) -[2023-10-10 13:43:06,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 54329344. Throughput: 0: 1798.8, 1: 1815.7. Samples: 13587494. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-10 13:43:06,076][75634] Avg episode reward: [(0, '29.780'), (1, '29.450')] -[2023-10-10 13:43:06,128][76543] Updated weights for policy 0, policy_version 26553 (0.0008) -[2023-10-10 13:43:08,917][76542] Updated weights for policy 1, policy_version 26530 (0.0007) -[2023-10-10 13:43:09,291][76542] Updated weights for policy 1, policy_version 26540 (0.0007) -[2023-10-10 13:43:09,647][76542] Updated weights for policy 1, policy_version 26550 (0.0008) -[2023-10-10 13:43:09,885][76543] Updated weights for policy 0, policy_version 26563 (0.0009) -[2023-10-10 13:43:10,015][76542] Updated weights for policy 1, policy_version 26560 (0.0008) -[2023-10-10 13:43:10,280][76543] Updated weights for policy 0, policy_version 26573 (0.0008) -[2023-10-10 13:43:10,650][76543] Updated weights for policy 0, policy_version 26583 (0.0008) -[2023-10-10 13:43:11,076][75634] Fps is (10 sec: 16383.8, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 54427648. Throughput: 0: 1801.9, 1: 1816.2. Samples: 13609146. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 13:43:11,077][75634] Avg episode reward: [(0, '30.330'), (1, '32.280')] -[2023-10-10 13:43:13,808][76542] Updated weights for policy 1, policy_version 26570 (0.0010) -[2023-10-10 13:43:14,179][76542] Updated weights for policy 1, policy_version 26580 (0.0007) -[2023-10-10 13:43:14,356][76543] Updated weights for policy 0, policy_version 26593 (0.0008) -[2023-10-10 13:43:14,548][76542] Updated weights for policy 1, policy_version 26590 (0.0010) -[2023-10-10 13:43:14,712][76543] Updated weights for policy 0, policy_version 26603 (0.0008) -[2023-10-10 13:43:15,089][76543] Updated weights for policy 0, policy_version 26613 (0.0009) -[2023-10-10 13:43:15,461][76543] Updated weights for policy 0, policy_version 26623 (0.0008) -[2023-10-10 13:43:16,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 54493184. Throughput: 0: 1806.3, 1: 1814.2. Samples: 13630080. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 13:43:16,077][75634] Avg episode reward: [(0, '31.710'), (1, '32.660')] -[2023-10-10 13:43:18,232][76542] Updated weights for policy 1, policy_version 26600 (0.0009) -[2023-10-10 13:43:18,597][76542] Updated weights for policy 1, policy_version 26610 (0.0008) -[2023-10-10 13:43:18,965][76542] Updated weights for policy 1, policy_version 26620 (0.0007) -[2023-10-10 13:43:19,033][76543] Updated weights for policy 0, policy_version 26633 (0.0008) -[2023-10-10 13:43:19,410][76543] Updated weights for policy 0, policy_version 26643 (0.0007) -[2023-10-10 13:43:19,775][76543] Updated weights for policy 0, policy_version 26653 (0.0009) -[2023-10-10 13:43:21,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 54558720. Throughput: 0: 1796.8, 1: 1819.8. Samples: 13641670. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 13:43:21,077][75634] Avg episode reward: [(0, '32.950'), (1, '32.160')] -[2023-10-10 13:43:22,632][76542] Updated weights for policy 1, policy_version 26630 (0.0007) -[2023-10-10 13:43:23,000][76542] Updated weights for policy 1, policy_version 26640 (0.0007) -[2023-10-10 13:43:23,372][76542] Updated weights for policy 1, policy_version 26650 (0.0007) -[2023-10-10 13:43:23,510][76543] Updated weights for policy 0, policy_version 26663 (0.0009) -[2023-10-10 13:43:23,886][76543] Updated weights for policy 0, policy_version 26673 (0.0011) -[2023-10-10 13:43:24,259][76543] Updated weights for policy 0, policy_version 26683 (0.0009) -[2023-10-10 13:43:26,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 54624256. Throughput: 0: 1804.3, 1: 1818.7. Samples: 13662792. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 13:43:26,077][75634] Avg episode reward: [(0, '30.210'), (1, '36.460')] -[2023-10-10 13:43:26,835][76542] Updated weights for policy 1, policy_version 26660 (0.0007) -[2023-10-10 13:43:27,209][76542] Updated weights for policy 1, policy_version 26670 (0.0008) -[2023-10-10 13:43:27,583][76542] Updated weights for policy 1, policy_version 26680 (0.0008) -[2023-10-10 13:43:27,899][76543] Updated weights for policy 0, policy_version 26693 (0.0009) -[2023-10-10 13:43:28,274][76543] Updated weights for policy 0, policy_version 26703 (0.0009) -[2023-10-10 13:43:28,654][76543] Updated weights for policy 0, policy_version 26713 (0.0010) -[2023-10-10 13:43:31,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 54689792. Throughput: 0: 1796.1, 1: 1824.6. Samples: 13685364. Policy #0 lag: (min: 24.0, avg: 47.4, max: 56.0) -[2023-10-10 13:43:31,076][75634] Avg episode reward: [(0, '33.010'), (1, '32.040')] -[2023-10-10 13:43:31,396][76542] Updated weights for policy 1, policy_version 26690 (0.0008) -[2023-10-10 13:43:31,764][76542] Updated weights for policy 1, policy_version 26700 (0.0007) -[2023-10-10 13:43:32,128][76542] Updated weights for policy 1, policy_version 26710 (0.0008) -[2023-10-10 13:43:32,388][76543] Updated weights for policy 0, policy_version 26723 (0.0010) -[2023-10-10 13:43:32,495][76542] Updated weights for policy 1, policy_version 26720 (0.0007) -[2023-10-10 13:43:32,751][76543] Updated weights for policy 0, policy_version 26733 (0.0008) -[2023-10-10 13:43:33,121][76543] Updated weights for policy 0, policy_version 26743 (0.0008) -[2023-10-10 13:43:36,031][76542] Updated weights for policy 1, policy_version 26730 (0.0007) -[2023-10-10 13:43:36,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 54755328. Throughput: 0: 1807.3, 1: 1821.6. Samples: 13695626. Policy #0 lag: (min: 24.0, avg: 47.4, max: 56.0) -[2023-10-10 13:43:36,076][75634] Avg episode reward: [(0, '33.920'), (1, '31.620')] -[2023-10-10 13:43:36,403][76542] Updated weights for policy 1, policy_version 26740 (0.0009) -[2023-10-10 13:43:36,776][76542] Updated weights for policy 1, policy_version 26750 (0.0009) -[2023-10-10 13:43:36,786][76543] Updated weights for policy 0, policy_version 26753 (0.0008) -[2023-10-10 13:43:37,164][76543] Updated weights for policy 0, policy_version 26763 (0.0008) -[2023-10-10 13:43:37,539][76543] Updated weights for policy 0, policy_version 26773 (0.0008) -[2023-10-10 13:43:37,909][76543] Updated weights for policy 0, policy_version 26783 (0.0008) -[2023-10-10 13:43:40,672][76542] Updated weights for policy 1, policy_version 26760 (0.0008) -[2023-10-10 13:43:41,048][76542] Updated weights for policy 1, policy_version 26770 (0.0007) -[2023-10-10 13:43:41,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 54820864. Throughput: 0: 1803.3, 1: 1822.1. Samples: 13718128. Policy #0 lag: (min: 24.0, avg: 47.4, max: 56.0) -[2023-10-10 13:43:41,076][75634] Avg episode reward: [(0, '33.100'), (1, '31.800')] -[2023-10-10 13:43:41,412][76542] Updated weights for policy 1, policy_version 26780 (0.0008) -[2023-10-10 13:43:41,639][76543] Updated weights for policy 0, policy_version 26793 (0.0009) -[2023-10-10 13:43:42,018][76543] Updated weights for policy 0, policy_version 26803 (0.0010) -[2023-10-10 13:43:42,390][76543] Updated weights for policy 0, policy_version 26813 (0.0010) -[2023-10-10 13:43:44,965][76542] Updated weights for policy 1, policy_version 26790 (0.0009) -[2023-10-10 13:43:45,334][76542] Updated weights for policy 1, policy_version 26800 (0.0011) -[2023-10-10 13:43:45,698][76542] Updated weights for policy 1, policy_version 26810 (0.0011) -[2023-10-10 13:43:46,062][76543] Updated weights for policy 0, policy_version 26823 (0.0008) -[2023-10-10 13:43:46,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 54919168. Throughput: 0: 1808.8, 1: 1820.0. Samples: 13739658. Policy #0 lag: (min: 24.0, avg: 47.4, max: 56.0) -[2023-10-10 13:43:46,076][75634] Avg episode reward: [(0, '33.770'), (1, '31.390')] -[2023-10-10 13:43:46,442][76543] Updated weights for policy 0, policy_version 26833 (0.0007) -[2023-10-10 13:43:46,811][76543] Updated weights for policy 0, policy_version 26843 (0.0007) -[2023-10-10 13:43:49,253][76542] Updated weights for policy 1, policy_version 26820 (0.0008) -[2023-10-10 13:43:49,628][76542] Updated weights for policy 1, policy_version 26830 (0.0008) -[2023-10-10 13:43:49,989][76542] Updated weights for policy 1, policy_version 26840 (0.0009) -[2023-10-10 13:43:50,379][76543] Updated weights for policy 0, policy_version 26853 (0.0008) -[2023-10-10 13:43:50,761][76543] Updated weights for policy 0, policy_version 26863 (0.0010) -[2023-10-10 13:43:51,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 54984704. Throughput: 0: 1810.2, 1: 1815.6. Samples: 13750652. Policy #0 lag: (min: 24.0, avg: 47.4, max: 56.0) -[2023-10-10 13:43:51,076][75634] Avg episode reward: [(0, '34.990'), (1, '33.040')] -[2023-10-10 13:43:51,134][76543] Updated weights for policy 0, policy_version 26873 (0.0010) -[2023-10-10 13:43:53,761][76542] Updated weights for policy 1, policy_version 26850 (0.0009) -[2023-10-10 13:43:54,138][76542] Updated weights for policy 1, policy_version 26860 (0.0008) -[2023-10-10 13:43:54,502][76542] Updated weights for policy 1, policy_version 26870 (0.0008) -[2023-10-10 13:43:54,855][76543] Updated weights for policy 0, policy_version 26883 (0.0009) -[2023-10-10 13:43:54,874][76542] Updated weights for policy 1, policy_version 26880 (0.0010) -[2023-10-10 13:43:55,251][76543] Updated weights for policy 0, policy_version 26893 (0.0008) -[2023-10-10 13:43:55,629][76543] Updated weights for policy 0, policy_version 26903 (0.0007) -[2023-10-10 13:43:56,076][75634] Fps is (10 sec: 16383.6, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 55083008. Throughput: 0: 1816.5, 1: 1815.6. Samples: 13772594. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:43:56,077][75634] Avg episode reward: [(0, '33.980'), (1, '32.060')] -[2023-10-10 13:43:58,587][76542] Updated weights for policy 1, policy_version 26890 (0.0008) -[2023-10-10 13:43:58,959][76542] Updated weights for policy 1, policy_version 26900 (0.0007) -[2023-10-10 13:43:59,229][76543] Updated weights for policy 0, policy_version 26913 (0.0007) -[2023-10-10 13:43:59,334][76542] Updated weights for policy 1, policy_version 26910 (0.0009) -[2023-10-10 13:43:59,590][76543] Updated weights for policy 0, policy_version 26923 (0.0008) -[2023-10-10 13:43:59,964][76543] Updated weights for policy 0, policy_version 26933 (0.0010) -[2023-10-10 13:44:00,328][76543] Updated weights for policy 0, policy_version 26943 (0.0010) -[2023-10-10 13:44:01,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 55148544. Throughput: 0: 1811.0, 1: 1823.2. Samples: 13793616. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:44:01,077][75634] Avg episode reward: [(0, '36.310'), (1, '32.100')] -[2023-10-10 13:44:03,062][76542] Updated weights for policy 1, policy_version 26920 (0.0010) -[2023-10-10 13:44:03,425][76542] Updated weights for policy 1, policy_version 26930 (0.0009) -[2023-10-10 13:44:03,796][76542] Updated weights for policy 1, policy_version 26940 (0.0007) -[2023-10-10 13:44:03,916][76543] Updated weights for policy 0, policy_version 26953 (0.0007) -[2023-10-10 13:44:04,289][76543] Updated weights for policy 0, policy_version 26963 (0.0008) -[2023-10-10 13:44:04,661][76543] Updated weights for policy 0, policy_version 26973 (0.0008) -[2023-10-10 13:44:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 55214080. Throughput: 0: 1818.7, 1: 1820.0. Samples: 13805412. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:44:06,077][75634] Avg episode reward: [(0, '34.700'), (1, '35.490')] -[2023-10-10 13:44:07,605][76542] Updated weights for policy 1, policy_version 26950 (0.0009) -[2023-10-10 13:44:07,976][76542] Updated weights for policy 1, policy_version 26960 (0.0010) -[2023-10-10 13:44:08,348][76542] Updated weights for policy 1, policy_version 26970 (0.0009) -[2023-10-10 13:44:08,411][76543] Updated weights for policy 0, policy_version 26983 (0.0007) -[2023-10-10 13:44:08,785][76543] Updated weights for policy 0, policy_version 26993 (0.0009) -[2023-10-10 13:44:09,164][76543] Updated weights for policy 0, policy_version 27003 (0.0010) -[2023-10-10 13:44:11,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 55279616. Throughput: 0: 1816.8, 1: 1815.2. Samples: 13826230. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:44:11,076][75634] Avg episode reward: [(0, '33.770'), (1, '35.950')] -[2023-10-10 13:44:11,970][76542] Updated weights for policy 1, policy_version 26980 (0.0007) -[2023-10-10 13:44:12,334][76542] Updated weights for policy 1, policy_version 26990 (0.0007) -[2023-10-10 13:44:12,708][76542] Updated weights for policy 1, policy_version 27000 (0.0007) -[2023-10-10 13:44:12,891][76543] Updated weights for policy 0, policy_version 27013 (0.0009) -[2023-10-10 13:44:13,267][76543] Updated weights for policy 0, policy_version 27023 (0.0009) -[2023-10-10 13:44:13,637][76543] Updated weights for policy 0, policy_version 27033 (0.0009) -[2023-10-10 13:44:16,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 55345152. Throughput: 0: 1815.2, 1: 1814.7. Samples: 13848706. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-10 13:44:16,076][75634] Avg episode reward: [(0, '30.240'), (1, '36.010')] -[2023-10-10 13:44:16,222][76542] Updated weights for policy 1, policy_version 27010 (0.0009) -[2023-10-10 13:44:16,583][76542] Updated weights for policy 1, policy_version 27020 (0.0009) -[2023-10-10 13:44:16,961][76542] Updated weights for policy 1, policy_version 27030 (0.0008) -[2023-10-10 13:44:17,300][76543] Updated weights for policy 0, policy_version 27043 (0.0009) -[2023-10-10 13:44:17,316][76542] Updated weights for policy 1, policy_version 27040 (0.0007) -[2023-10-10 13:44:17,673][76543] Updated weights for policy 0, policy_version 27053 (0.0008) -[2023-10-10 13:44:18,039][76543] Updated weights for policy 0, policy_version 27063 (0.0007) -[2023-10-10 13:44:20,978][76542] Updated weights for policy 1, policy_version 27050 (0.0009) -[2023-10-10 13:44:21,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 55410688. Throughput: 0: 1815.7, 1: 1817.8. Samples: 13859134. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-10 13:44:21,076][75634] Avg episode reward: [(0, '31.530'), (1, '34.880')] -[2023-10-10 13:44:21,348][76542] Updated weights for policy 1, policy_version 27060 (0.0009) -[2023-10-10 13:44:21,710][76542] Updated weights for policy 1, policy_version 27070 (0.0007) -[2023-10-10 13:44:21,715][76543] Updated weights for policy 0, policy_version 27073 (0.0007) -[2023-10-10 13:44:22,075][76543] Updated weights for policy 0, policy_version 27083 (0.0009) -[2023-10-10 13:44:22,443][76543] Updated weights for policy 0, policy_version 27093 (0.0010) -[2023-10-10 13:44:22,814][76543] Updated weights for policy 0, policy_version 27103 (0.0009) -[2023-10-10 13:44:25,549][76542] Updated weights for policy 1, policy_version 27080 (0.0009) -[2023-10-10 13:44:25,913][76542] Updated weights for policy 1, policy_version 27090 (0.0011) -[2023-10-10 13:44:26,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 55476224. Throughput: 0: 1817.7, 1: 1820.5. Samples: 13881846. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-10 13:44:26,077][75634] Avg episode reward: [(0, '32.880'), (1, '33.880')] -[2023-10-10 13:44:26,285][76542] Updated weights for policy 1, policy_version 27100 (0.0009) -[2023-10-10 13:44:26,464][76543] Updated weights for policy 0, policy_version 27113 (0.0008) -[2023-10-10 13:44:26,837][76543] Updated weights for policy 0, policy_version 27123 (0.0009) -[2023-10-10 13:44:27,202][76543] Updated weights for policy 0, policy_version 27133 (0.0011) -[2023-10-10 13:44:30,150][76542] Updated weights for policy 1, policy_version 27110 (0.0009) -[2023-10-10 13:44:30,516][76542] Updated weights for policy 1, policy_version 27120 (0.0010) -[2023-10-10 13:44:30,878][76542] Updated weights for policy 1, policy_version 27130 (0.0007) -[2023-10-10 13:44:30,884][76543] Updated weights for policy 0, policy_version 27143 (0.0010) -[2023-10-10 13:44:31,076][75634] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 55541760. Throughput: 0: 1830.2, 1: 1823.3. Samples: 13904070. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-10 13:44:31,077][75634] Avg episode reward: [(0, '33.260'), (1, '36.300')] -[2023-10-10 13:44:31,092][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000027136_27787264.pth... -[2023-10-10 13:44:31,131][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000025440_26050560.pth -[2023-10-10 13:44:31,268][76543] Updated weights for policy 0, policy_version 27153 (0.0009) -[2023-10-10 13:44:31,633][76543] Updated weights for policy 0, policy_version 27163 (0.0010) -[2023-10-10 13:44:31,816][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000027168_27820032.pth... -[2023-10-10 13:44:31,846][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000025440_26050560.pth -[2023-10-10 13:44:34,565][76542] Updated weights for policy 1, policy_version 27140 (0.0007) -[2023-10-10 13:44:34,935][76542] Updated weights for policy 1, policy_version 27150 (0.0007) -[2023-10-10 13:44:35,276][76543] Updated weights for policy 0, policy_version 27173 (0.0008) -[2023-10-10 13:44:35,301][76542] Updated weights for policy 1, policy_version 27160 (0.0009) -[2023-10-10 13:44:35,656][76543] Updated weights for policy 0, policy_version 27183 (0.0007) -[2023-10-10 13:44:36,031][76543] Updated weights for policy 0, policy_version 27193 (0.0007) -[2023-10-10 13:44:36,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 55640064. Throughput: 0: 1825.2, 1: 1823.0. Samples: 13914824. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-10 13:44:36,077][75634] Avg episode reward: [(0, '30.790'), (1, '36.730')] -[2023-10-10 13:44:38,966][76542] Updated weights for policy 1, policy_version 27170 (0.0007) -[2023-10-10 13:44:39,339][76542] Updated weights for policy 1, policy_version 27180 (0.0009) -[2023-10-10 13:44:39,700][76542] Updated weights for policy 1, policy_version 27190 (0.0010) -[2023-10-10 13:44:39,824][76543] Updated weights for policy 0, policy_version 27203 (0.0009) -[2023-10-10 13:44:40,070][76542] Updated weights for policy 1, policy_version 27200 (0.0009) -[2023-10-10 13:44:40,212][76543] Updated weights for policy 0, policy_version 27213 (0.0009) -[2023-10-10 13:44:40,592][76543] Updated weights for policy 0, policy_version 27223 (0.0009) -[2023-10-10 13:44:41,076][75634] Fps is (10 sec: 19661.3, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 55738368. Throughput: 0: 1825.4, 1: 1822.9. Samples: 13936770. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:44:41,077][75634] Avg episode reward: [(0, '33.320'), (1, '33.240')] -[2023-10-10 13:44:43,627][76542] Updated weights for policy 1, policy_version 27210 (0.0008) -[2023-10-10 13:44:43,996][76542] Updated weights for policy 1, policy_version 27220 (0.0008) -[2023-10-10 13:44:44,228][76543] Updated weights for policy 0, policy_version 27233 (0.0008) -[2023-10-10 13:44:44,361][76542] Updated weights for policy 1, policy_version 27230 (0.0008) -[2023-10-10 13:44:44,601][76543] Updated weights for policy 0, policy_version 27243 (0.0008) -[2023-10-10 13:44:44,970][76543] Updated weights for policy 0, policy_version 27253 (0.0009) -[2023-10-10 13:44:45,346][76543] Updated weights for policy 0, policy_version 27263 (0.0009) -[2023-10-10 13:44:46,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 55803904. Throughput: 0: 1827.6, 1: 1824.7. Samples: 13957966. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:44:46,077][75634] Avg episode reward: [(0, '35.660'), (1, '33.290')] -[2023-10-10 13:44:48,180][76542] Updated weights for policy 1, policy_version 27240 (0.0008) -[2023-10-10 13:44:48,554][76542] Updated weights for policy 1, policy_version 27250 (0.0008) -[2023-10-10 13:44:48,927][76542] Updated weights for policy 1, policy_version 27260 (0.0007) -[2023-10-10 13:44:48,977][76543] Updated weights for policy 0, policy_version 27273 (0.0007) -[2023-10-10 13:44:49,352][76543] Updated weights for policy 0, policy_version 27283 (0.0008) -[2023-10-10 13:44:49,723][76543] Updated weights for policy 0, policy_version 27293 (0.0009) -[2023-10-10 13:44:51,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 55869440. Throughput: 0: 1823.9, 1: 1822.4. Samples: 13969498. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:44:51,076][75634] Avg episode reward: [(0, '34.690'), (1, '33.560')] -[2023-10-10 13:44:52,618][76542] Updated weights for policy 1, policy_version 27270 (0.0007) -[2023-10-10 13:44:52,988][76542] Updated weights for policy 1, policy_version 27280 (0.0008) -[2023-10-10 13:44:53,350][76543] Updated weights for policy 0, policy_version 27303 (0.0008) -[2023-10-10 13:44:53,359][76542] Updated weights for policy 1, policy_version 27290 (0.0007) -[2023-10-10 13:44:53,719][76543] Updated weights for policy 0, policy_version 27313 (0.0008) -[2023-10-10 13:44:54,096][76543] Updated weights for policy 0, policy_version 27323 (0.0010) -[2023-10-10 13:44:56,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 55934976. Throughput: 0: 1827.9, 1: 1825.6. Samples: 13990638. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:44:56,077][75634] Avg episode reward: [(0, '34.380'), (1, '32.970')] -[2023-10-10 13:44:56,923][76542] Updated weights for policy 1, policy_version 27300 (0.0008) -[2023-10-10 13:44:57,295][76542] Updated weights for policy 1, policy_version 27310 (0.0008) -[2023-10-10 13:44:57,641][76543] Updated weights for policy 0, policy_version 27333 (0.0008) -[2023-10-10 13:44:57,663][76542] Updated weights for policy 1, policy_version 27320 (0.0007) -[2023-10-10 13:44:58,011][76543] Updated weights for policy 0, policy_version 27343 (0.0009) -[2023-10-10 13:44:58,382][76543] Updated weights for policy 0, policy_version 27353 (0.0010) -[2023-10-10 13:45:01,076][75634] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 56000512. Throughput: 0: 1839.6, 1: 1820.6. Samples: 14013416. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:45:01,077][75634] Avg episode reward: [(0, '30.820'), (1, '31.890')] -[2023-10-10 13:45:01,498][76542] Updated weights for policy 1, policy_version 27330 (0.0009) -[2023-10-10 13:45:01,871][76542] Updated weights for policy 1, policy_version 27340 (0.0008) -[2023-10-10 13:45:02,175][76543] Updated weights for policy 0, policy_version 27363 (0.0009) -[2023-10-10 13:45:02,247][76542] Updated weights for policy 1, policy_version 27350 (0.0009) -[2023-10-10 13:45:02,550][76543] Updated weights for policy 0, policy_version 27373 (0.0007) -[2023-10-10 13:45:02,621][76542] Updated weights for policy 1, policy_version 27360 (0.0009) -[2023-10-10 13:45:02,924][76543] Updated weights for policy 0, policy_version 27383 (0.0007) -[2023-10-10 13:45:06,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 56066048. Throughput: 0: 1831.7, 1: 1816.1. Samples: 14023288. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:45:06,076][75634] Avg episode reward: [(0, '31.560'), (1, '31.520')] -[2023-10-10 13:45:06,326][76542] Updated weights for policy 1, policy_version 27370 (0.0008) -[2023-10-10 13:45:06,579][76543] Updated weights for policy 0, policy_version 27393 (0.0009) -[2023-10-10 13:45:06,700][76542] Updated weights for policy 1, policy_version 27380 (0.0008) -[2023-10-10 13:45:06,955][76543] Updated weights for policy 0, policy_version 27403 (0.0008) -[2023-10-10 13:45:07,070][76542] Updated weights for policy 1, policy_version 27390 (0.0007) -[2023-10-10 13:45:07,323][76543] Updated weights for policy 0, policy_version 27413 (0.0007) -[2023-10-10 13:45:07,701][76543] Updated weights for policy 0, policy_version 27423 (0.0007) -[2023-10-10 13:45:10,895][76542] Updated weights for policy 1, policy_version 27400 (0.0009) -[2023-10-10 13:45:11,076][75634] Fps is (10 sec: 13107.8, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 56131584. Throughput: 0: 1833.4, 1: 1811.6. Samples: 14045868. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:45:11,076][75634] Avg episode reward: [(0, '29.630'), (1, '32.010')] -[2023-10-10 13:45:11,270][76542] Updated weights for policy 1, policy_version 27410 (0.0008) -[2023-10-10 13:45:11,421][76543] Updated weights for policy 0, policy_version 27433 (0.0009) -[2023-10-10 13:45:11,645][76542] Updated weights for policy 1, policy_version 27420 (0.0008) -[2023-10-10 13:45:11,805][76543] Updated weights for policy 0, policy_version 27443 (0.0008) -[2023-10-10 13:45:12,175][76543] Updated weights for policy 0, policy_version 27453 (0.0009) -[2023-10-10 13:45:15,221][76542] Updated weights for policy 1, policy_version 27430 (0.0008) -[2023-10-10 13:45:15,586][76542] Updated weights for policy 1, policy_version 27440 (0.0008) -[2023-10-10 13:45:15,909][76543] Updated weights for policy 0, policy_version 27463 (0.0007) -[2023-10-10 13:45:15,958][76542] Updated weights for policy 1, policy_version 27450 (0.0008) -[2023-10-10 13:45:16,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 56197120. Throughput: 0: 1821.9, 1: 1813.0. Samples: 14067640. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:45:16,076][75634] Avg episode reward: [(0, '29.180'), (1, '33.110')] -[2023-10-10 13:45:16,277][76543] Updated weights for policy 0, policy_version 27473 (0.0007) -[2023-10-10 13:45:16,652][76543] Updated weights for policy 0, policy_version 27483 (0.0011) -[2023-10-10 13:45:19,486][76542] Updated weights for policy 1, policy_version 27460 (0.0009) -[2023-10-10 13:45:19,855][76542] Updated weights for policy 1, policy_version 27470 (0.0009) -[2023-10-10 13:45:20,220][76542] Updated weights for policy 1, policy_version 27480 (0.0008) -[2023-10-10 13:45:20,368][76543] Updated weights for policy 0, policy_version 27493 (0.0009) -[2023-10-10 13:45:20,737][76543] Updated weights for policy 0, policy_version 27503 (0.0007) -[2023-10-10 13:45:21,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 56295424. Throughput: 0: 1821.7, 1: 1811.8. Samples: 14078332. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:45:21,077][75634] Avg episode reward: [(0, '30.400'), (1, '32.350')] -[2023-10-10 13:45:21,109][76543] Updated weights for policy 0, policy_version 27513 (0.0010) -[2023-10-10 13:45:23,885][76542] Updated weights for policy 1, policy_version 27490 (0.0009) -[2023-10-10 13:45:24,246][76542] Updated weights for policy 1, policy_version 27500 (0.0009) -[2023-10-10 13:45:24,615][76542] Updated weights for policy 1, policy_version 27510 (0.0008) -[2023-10-10 13:45:24,781][76543] Updated weights for policy 0, policy_version 27523 (0.0008) -[2023-10-10 13:45:24,986][76542] Updated weights for policy 1, policy_version 27520 (0.0008) -[2023-10-10 13:45:25,147][76543] Updated weights for policy 0, policy_version 27533 (0.0007) -[2023-10-10 13:45:25,521][76543] Updated weights for policy 0, policy_version 27543 (0.0008) -[2023-10-10 13:45:26,076][75634] Fps is (10 sec: 19660.7, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 56393728. Throughput: 0: 1817.3, 1: 1814.9. Samples: 14100216. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:45:26,076][75634] Avg episode reward: [(0, '32.140'), (1, '32.540')] -[2023-10-10 13:45:28,741][76542] Updated weights for policy 1, policy_version 27530 (0.0009) -[2023-10-10 13:45:29,115][76542] Updated weights for policy 1, policy_version 27540 (0.0008) -[2023-10-10 13:45:29,197][76543] Updated weights for policy 0, policy_version 27553 (0.0010) -[2023-10-10 13:45:29,478][76542] Updated weights for policy 1, policy_version 27550 (0.0008) -[2023-10-10 13:45:29,629][76543] Updated weights for policy 0, policy_version 27563 (0.0009) -[2023-10-10 13:45:29,997][76543] Updated weights for policy 0, policy_version 27573 (0.0008) -[2023-10-10 13:45:30,365][76543] Updated weights for policy 0, policy_version 27583 (0.0008) -[2023-10-10 13:45:31,076][75634] Fps is (10 sec: 16384.2, 60 sec: 15291.8, 300 sec: 14551.2). Total num frames: 56459264. Throughput: 0: 1815.3, 1: 1808.2. Samples: 14121024. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:45:31,076][75634] Avg episode reward: [(0, '32.930'), (1, '34.920')] -[2023-10-10 13:45:33,260][76542] Updated weights for policy 1, policy_version 27560 (0.0008) -[2023-10-10 13:45:33,633][76542] Updated weights for policy 1, policy_version 27570 (0.0007) -[2023-10-10 13:45:34,002][76542] Updated weights for policy 1, policy_version 27580 (0.0007) -[2023-10-10 13:45:34,166][76543] Updated weights for policy 0, policy_version 27593 (0.0008) -[2023-10-10 13:45:34,539][76543] Updated weights for policy 0, policy_version 27603 (0.0010) -[2023-10-10 13:45:34,907][76543] Updated weights for policy 0, policy_version 27613 (0.0010) -[2023-10-10 13:45:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 56524800. Throughput: 0: 1809.4, 1: 1818.5. Samples: 14132756. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:45:36,076][75634] Avg episode reward: [(0, '34.740'), (1, '31.950')] -[2023-10-10 13:45:37,669][76542] Updated weights for policy 1, policy_version 27590 (0.0010) -[2023-10-10 13:45:38,036][76542] Updated weights for policy 1, policy_version 27600 (0.0010) -[2023-10-10 13:45:38,400][76542] Updated weights for policy 1, policy_version 27610 (0.0011) -[2023-10-10 13:45:38,759][76543] Updated weights for policy 0, policy_version 27623 (0.0008) -[2023-10-10 13:45:39,132][76543] Updated weights for policy 0, policy_version 27633 (0.0008) -[2023-10-10 13:45:39,508][76543] Updated weights for policy 0, policy_version 27643 (0.0009) -[2023-10-10 13:45:41,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 56590336. Throughput: 0: 1814.6, 1: 1816.0. Samples: 14154014. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:45:41,077][75634] Avg episode reward: [(0, '34.620'), (1, '29.870')] -[2023-10-10 13:45:42,142][76542] Updated weights for policy 1, policy_version 27620 (0.0008) -[2023-10-10 13:45:42,512][76542] Updated weights for policy 1, policy_version 27630 (0.0007) -[2023-10-10 13:45:42,879][76542] Updated weights for policy 1, policy_version 27640 (0.0010) -[2023-10-10 13:45:43,178][76543] Updated weights for policy 0, policy_version 27653 (0.0009) -[2023-10-10 13:45:43,560][76543] Updated weights for policy 0, policy_version 27663 (0.0008) -[2023-10-10 13:45:43,933][76543] Updated weights for policy 0, policy_version 27673 (0.0008) -[2023-10-10 13:45:46,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 56655872. Throughput: 0: 1801.4, 1: 1815.0. Samples: 14176154. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 13:45:46,076][75634] Avg episode reward: [(0, '32.470'), (1, '30.950')] -[2023-10-10 13:45:46,683][76542] Updated weights for policy 1, policy_version 27650 (0.0008) -[2023-10-10 13:45:47,052][76542] Updated weights for policy 1, policy_version 27660 (0.0009) -[2023-10-10 13:45:47,418][76543] Updated weights for policy 0, policy_version 27683 (0.0010) -[2023-10-10 13:45:47,423][76542] Updated weights for policy 1, policy_version 27670 (0.0008) -[2023-10-10 13:45:47,787][76543] Updated weights for policy 0, policy_version 27693 (0.0008) -[2023-10-10 13:45:47,788][76542] Updated weights for policy 1, policy_version 27680 (0.0008) -[2023-10-10 13:45:48,158][76543] Updated weights for policy 0, policy_version 27703 (0.0008) -[2023-10-10 13:45:51,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 56721408. Throughput: 0: 1813.1, 1: 1817.1. Samples: 14186646. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 13:45:51,076][75634] Avg episode reward: [(0, '34.710'), (1, '32.180')] -[2023-10-10 13:45:51,393][76542] Updated weights for policy 1, policy_version 27690 (0.0008) -[2023-10-10 13:45:51,763][76542] Updated weights for policy 1, policy_version 27700 (0.0008) -[2023-10-10 13:45:51,921][76543] Updated weights for policy 0, policy_version 27713 (0.0007) -[2023-10-10 13:45:52,131][76542] Updated weights for policy 1, policy_version 27710 (0.0007) -[2023-10-10 13:45:52,293][76543] Updated weights for policy 0, policy_version 27723 (0.0009) -[2023-10-10 13:45:52,660][76543] Updated weights for policy 0, policy_version 27733 (0.0010) -[2023-10-10 13:45:53,039][76543] Updated weights for policy 0, policy_version 27743 (0.0010) -[2023-10-10 13:45:55,940][76542] Updated weights for policy 1, policy_version 27720 (0.0010) -[2023-10-10 13:45:56,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 56786944. Throughput: 0: 1804.7, 1: 1816.8. Samples: 14208836. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 13:45:56,077][75634] Avg episode reward: [(0, '34.610'), (1, '33.790')] -[2023-10-10 13:45:56,321][76542] Updated weights for policy 1, policy_version 27730 (0.0010) -[2023-10-10 13:45:56,685][76542] Updated weights for policy 1, policy_version 27740 (0.0007) -[2023-10-10 13:45:56,720][76543] Updated weights for policy 0, policy_version 27753 (0.0008) -[2023-10-10 13:45:57,093][76543] Updated weights for policy 0, policy_version 27763 (0.0007) -[2023-10-10 13:45:57,467][76543] Updated weights for policy 0, policy_version 27773 (0.0009) -[2023-10-10 13:46:00,387][76542] Updated weights for policy 1, policy_version 27750 (0.0007) -[2023-10-10 13:46:00,752][76542] Updated weights for policy 1, policy_version 27760 (0.0009) -[2023-10-10 13:46:01,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.6, 300 sec: 14440.1). Total num frames: 56852480. Throughput: 0: 1802.0, 1: 1821.5. Samples: 14230698. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 13:46:01,076][75634] Avg episode reward: [(0, '32.890'), (1, '34.850')] -[2023-10-10 13:46:01,118][76542] Updated weights for policy 1, policy_version 27770 (0.0008) -[2023-10-10 13:46:01,202][76543] Updated weights for policy 0, policy_version 27783 (0.0009) -[2023-10-10 13:46:01,569][76543] Updated weights for policy 0, policy_version 27793 (0.0009) -[2023-10-10 13:46:01,937][76543] Updated weights for policy 0, policy_version 27803 (0.0009) -[2023-10-10 13:46:04,664][76542] Updated weights for policy 1, policy_version 27780 (0.0008) -[2023-10-10 13:46:05,037][76542] Updated weights for policy 1, policy_version 27790 (0.0011) -[2023-10-10 13:46:05,409][76542] Updated weights for policy 1, policy_version 27800 (0.0010) -[2023-10-10 13:46:05,715][76543] Updated weights for policy 0, policy_version 27813 (0.0008) -[2023-10-10 13:46:06,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 56950784. Throughput: 0: 1807.4, 1: 1816.2. Samples: 14241394. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 13:46:06,077][75634] Avg episode reward: [(0, '33.360'), (1, '34.550')] -[2023-10-10 13:46:06,091][76543] Updated weights for policy 0, policy_version 27823 (0.0010) -[2023-10-10 13:46:06,460][76543] Updated weights for policy 0, policy_version 27833 (0.0007) -[2023-10-10 13:46:09,179][76542] Updated weights for policy 1, policy_version 27810 (0.0009) -[2023-10-10 13:46:09,553][76542] Updated weights for policy 1, policy_version 27820 (0.0008) -[2023-10-10 13:46:09,912][76542] Updated weights for policy 1, policy_version 27830 (0.0008) -[2023-10-10 13:46:10,079][76543] Updated weights for policy 0, policy_version 27843 (0.0007) -[2023-10-10 13:46:10,282][76542] Updated weights for policy 1, policy_version 27840 (0.0008) -[2023-10-10 13:46:10,450][76543] Updated weights for policy 0, policy_version 27853 (0.0009) -[2023-10-10 13:46:10,821][76543] Updated weights for policy 0, policy_version 27863 (0.0008) -[2023-10-10 13:46:11,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 57016320. Throughput: 0: 1805.6, 1: 1818.9. Samples: 14263316. Policy #0 lag: (min: 4.0, avg: 5.2, max: 28.0) -[2023-10-10 13:46:11,076][75634] Avg episode reward: [(0, '31.490'), (1, '36.380')] -[2023-10-10 13:46:13,991][76542] Updated weights for policy 1, policy_version 27850 (0.0007) -[2023-10-10 13:46:14,360][76542] Updated weights for policy 1, policy_version 27860 (0.0009) -[2023-10-10 13:46:14,590][76543] Updated weights for policy 0, policy_version 27873 (0.0007) -[2023-10-10 13:46:14,732][76542] Updated weights for policy 1, policy_version 27870 (0.0008) -[2023-10-10 13:46:15,013][76543] Updated weights for policy 0, policy_version 27883 (0.0009) -[2023-10-10 13:46:15,374][76543] Updated weights for policy 0, policy_version 27893 (0.0008) -[2023-10-10 13:46:15,750][76543] Updated weights for policy 0, policy_version 27903 (0.0007) -[2023-10-10 13:46:16,076][75634] Fps is (10 sec: 16383.9, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 57114624. Throughput: 0: 1815.0, 1: 1815.1. Samples: 14284380. Policy #0 lag: (min: 4.0, avg: 5.2, max: 28.0) -[2023-10-10 13:46:16,077][75634] Avg episode reward: [(0, '30.900'), (1, '33.760')] -[2023-10-10 13:46:18,408][76542] Updated weights for policy 1, policy_version 27880 (0.0008) -[2023-10-10 13:46:18,779][76542] Updated weights for policy 1, policy_version 27890 (0.0009) -[2023-10-10 13:46:19,158][76542] Updated weights for policy 1, policy_version 27900 (0.0009) -[2023-10-10 13:46:19,416][76543] Updated weights for policy 0, policy_version 27913 (0.0010) -[2023-10-10 13:46:19,787][76543] Updated weights for policy 0, policy_version 27923 (0.0009) -[2023-10-10 13:46:20,154][76543] Updated weights for policy 0, policy_version 27933 (0.0007) -[2023-10-10 13:46:21,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 57180160. Throughput: 0: 1805.8, 1: 1817.0. Samples: 14295782. Policy #0 lag: (min: 4.0, avg: 5.2, max: 28.0) -[2023-10-10 13:46:21,077][75634] Avg episode reward: [(0, '32.280'), (1, '28.190')] -[2023-10-10 13:46:22,855][76542] Updated weights for policy 1, policy_version 27910 (0.0009) -[2023-10-10 13:46:23,215][76542] Updated weights for policy 1, policy_version 27920 (0.0007) -[2023-10-10 13:46:23,589][76542] Updated weights for policy 1, policy_version 27930 (0.0007) -[2023-10-10 13:46:23,815][76543] Updated weights for policy 0, policy_version 27943 (0.0008) -[2023-10-10 13:46:24,178][76543] Updated weights for policy 0, policy_version 27953 (0.0009) -[2023-10-10 13:46:24,554][76543] Updated weights for policy 0, policy_version 27963 (0.0008) -[2023-10-10 13:46:26,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 57245696. Throughput: 0: 1808.6, 1: 1810.9. Samples: 14316894. Policy #0 lag: (min: 4.0, avg: 5.2, max: 28.0) -[2023-10-10 13:46:26,076][75634] Avg episode reward: [(0, '35.940'), (1, '27.910')] -[2023-10-10 13:46:27,227][76542] Updated weights for policy 1, policy_version 27940 (0.0007) -[2023-10-10 13:46:27,594][76542] Updated weights for policy 1, policy_version 27950 (0.0007) -[2023-10-10 13:46:27,972][76542] Updated weights for policy 1, policy_version 27960 (0.0007) -[2023-10-10 13:46:28,306][76543] Updated weights for policy 0, policy_version 27973 (0.0009) -[2023-10-10 13:46:28,678][76543] Updated weights for policy 0, policy_version 27983 (0.0007) -[2023-10-10 13:46:29,059][76543] Updated weights for policy 0, policy_version 27993 (0.0010) -[2023-10-10 13:46:31,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 57311232. Throughput: 0: 1809.8, 1: 1820.5. Samples: 14339518. Policy #0 lag: (min: 2.0, avg: 5.2, max: 34.0) -[2023-10-10 13:46:31,077][75634] Avg episode reward: [(0, '31.410'), (1, '29.010')] -[2023-10-10 13:46:31,089][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000028000_28672000.pth... -[2023-10-10 13:46:31,090][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000027968_28639232.pth... -[2023-10-10 13:46:31,123][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000026272_26902528.pth -[2023-10-10 13:46:31,125][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000026304_26935296.pth -[2023-10-10 13:46:31,647][76542] Updated weights for policy 1, policy_version 27970 (0.0007) -[2023-10-10 13:46:32,006][76542] Updated weights for policy 1, policy_version 27980 (0.0007) -[2023-10-10 13:46:32,374][76542] Updated weights for policy 1, policy_version 27990 (0.0007) -[2023-10-10 13:46:32,675][76543] Updated weights for policy 0, policy_version 28003 (0.0009) -[2023-10-10 13:46:32,740][76542] Updated weights for policy 1, policy_version 28000 (0.0008) -[2023-10-10 13:46:33,057][76543] Updated weights for policy 0, policy_version 28013 (0.0008) -[2023-10-10 13:46:33,439][76543] Updated weights for policy 0, policy_version 28023 (0.0011) -[2023-10-10 13:46:36,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 57376768. Throughput: 0: 1812.6, 1: 1817.4. Samples: 14349998. Policy #0 lag: (min: 2.0, avg: 5.2, max: 34.0) -[2023-10-10 13:46:36,077][75634] Avg episode reward: [(0, '31.150'), (1, '29.380')] -[2023-10-10 13:46:36,450][76542] Updated weights for policy 1, policy_version 28010 (0.0008) -[2023-10-10 13:46:36,829][76542] Updated weights for policy 1, policy_version 28020 (0.0011) -[2023-10-10 13:46:37,151][76543] Updated weights for policy 0, policy_version 28033 (0.0009) -[2023-10-10 13:46:37,190][76542] Updated weights for policy 1, policy_version 28030 (0.0009) -[2023-10-10 13:46:37,521][76543] Updated weights for policy 0, policy_version 28043 (0.0008) -[2023-10-10 13:46:37,898][76543] Updated weights for policy 0, policy_version 28053 (0.0008) -[2023-10-10 13:46:38,267][76543] Updated weights for policy 0, policy_version 28063 (0.0010) -[2023-10-10 13:46:40,955][76542] Updated weights for policy 1, policy_version 28040 (0.0010) -[2023-10-10 13:46:41,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 57442304. Throughput: 0: 1811.3, 1: 1820.1. Samples: 14372250. Policy #0 lag: (min: 2.0, avg: 5.2, max: 34.0) -[2023-10-10 13:46:41,076][75634] Avg episode reward: [(0, '30.710'), (1, '33.720')] -[2023-10-10 13:46:41,327][76542] Updated weights for policy 1, policy_version 28050 (0.0007) -[2023-10-10 13:46:41,703][76542] Updated weights for policy 1, policy_version 28060 (0.0009) -[2023-10-10 13:46:41,937][76543] Updated weights for policy 0, policy_version 28073 (0.0008) -[2023-10-10 13:46:42,317][76543] Updated weights for policy 0, policy_version 28083 (0.0008) -[2023-10-10 13:46:42,697][76543] Updated weights for policy 0, policy_version 28093 (0.0007) -[2023-10-10 13:46:45,350][76542] Updated weights for policy 1, policy_version 28070 (0.0009) -[2023-10-10 13:46:45,726][76542] Updated weights for policy 1, policy_version 28080 (0.0007) -[2023-10-10 13:46:46,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 57507840. Throughput: 0: 1814.2, 1: 1821.5. Samples: 14394304. Policy #0 lag: (min: 2.0, avg: 5.2, max: 34.0) -[2023-10-10 13:46:46,076][75634] Avg episode reward: [(0, '31.340'), (1, '34.130')] -[2023-10-10 13:46:46,099][76542] Updated weights for policy 1, policy_version 28090 (0.0010) -[2023-10-10 13:46:46,271][76543] Updated weights for policy 0, policy_version 28103 (0.0008) -[2023-10-10 13:46:46,636][76543] Updated weights for policy 0, policy_version 28113 (0.0008) -[2023-10-10 13:46:47,016][76543] Updated weights for policy 0, policy_version 28123 (0.0009) -[2023-10-10 13:46:49,758][76542] Updated weights for policy 1, policy_version 28100 (0.0009) -[2023-10-10 13:46:50,135][76542] Updated weights for policy 1, policy_version 28110 (0.0008) -[2023-10-10 13:46:50,500][76542] Updated weights for policy 1, policy_version 28120 (0.0008) -[2023-10-10 13:46:50,820][76543] Updated weights for policy 0, policy_version 28133 (0.0008) -[2023-10-10 13:46:51,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 57606144. Throughput: 0: 1812.0, 1: 1823.9. Samples: 14405010. Policy #0 lag: (min: 2.0, avg: 5.2, max: 34.0) -[2023-10-10 13:46:51,076][75634] Avg episode reward: [(0, '35.070'), (1, '33.400')] -[2023-10-10 13:46:51,189][76543] Updated weights for policy 0, policy_version 28143 (0.0011) -[2023-10-10 13:46:51,567][76543] Updated weights for policy 0, policy_version 28153 (0.0008) -[2023-10-10 13:46:54,151][76542] Updated weights for policy 1, policy_version 28130 (0.0008) -[2023-10-10 13:46:54,518][76542] Updated weights for policy 1, policy_version 28140 (0.0009) -[2023-10-10 13:46:54,884][76542] Updated weights for policy 1, policy_version 28150 (0.0009) -[2023-10-10 13:46:55,220][76543] Updated weights for policy 0, policy_version 28163 (0.0007) -[2023-10-10 13:46:55,249][76542] Updated weights for policy 1, policy_version 28160 (0.0008) -[2023-10-10 13:46:55,595][76543] Updated weights for policy 0, policy_version 28173 (0.0008) -[2023-10-10 13:46:55,977][76543] Updated weights for policy 0, policy_version 28183 (0.0009) -[2023-10-10 13:46:56,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 57671680. Throughput: 0: 1809.2, 1: 1826.7. Samples: 14426936. Policy #0 lag: (min: 1.0, avg: 4.1, max: 33.0) -[2023-10-10 13:46:56,077][75634] Avg episode reward: [(0, '37.020'), (1, '33.680')] -[2023-10-10 13:46:58,919][76542] Updated weights for policy 1, policy_version 28170 (0.0009) -[2023-10-10 13:46:59,284][76542] Updated weights for policy 1, policy_version 28180 (0.0010) -[2023-10-10 13:46:59,572][76543] Updated weights for policy 0, policy_version 28193 (0.0008) -[2023-10-10 13:46:59,658][76542] Updated weights for policy 1, policy_version 28190 (0.0010) -[2023-10-10 13:46:59,958][76543] Updated weights for policy 0, policy_version 28203 (0.0007) -[2023-10-10 13:47:00,317][76543] Updated weights for policy 0, policy_version 28213 (0.0008) -[2023-10-10 13:47:00,694][76543] Updated weights for policy 0, policy_version 28223 (0.0009) -[2023-10-10 13:47:01,076][75634] Fps is (10 sec: 16384.1, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 57769984. Throughput: 0: 1815.7, 1: 1826.7. Samples: 14448286. Policy #0 lag: (min: 1.0, avg: 4.1, max: 33.0) -[2023-10-10 13:47:01,076][75634] Avg episode reward: [(0, '32.380'), (1, '32.200')] -[2023-10-10 13:47:03,408][76542] Updated weights for policy 1, policy_version 28200 (0.0008) -[2023-10-10 13:47:03,775][76542] Updated weights for policy 1, policy_version 28210 (0.0008) -[2023-10-10 13:47:04,141][76542] Updated weights for policy 1, policy_version 28220 (0.0009) -[2023-10-10 13:47:04,378][76543] Updated weights for policy 0, policy_version 28233 (0.0008) -[2023-10-10 13:47:04,743][76543] Updated weights for policy 0, policy_version 28243 (0.0009) -[2023-10-10 13:47:05,114][76543] Updated weights for policy 0, policy_version 28253 (0.0008) -[2023-10-10 13:47:06,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 57835520. Throughput: 0: 1818.0, 1: 1820.8. Samples: 14459528. Policy #0 lag: (min: 1.0, avg: 4.1, max: 33.0) -[2023-10-10 13:47:06,076][75634] Avg episode reward: [(0, '35.310'), (1, '31.220')] -[2023-10-10 13:47:07,734][76542] Updated weights for policy 1, policy_version 28230 (0.0007) -[2023-10-10 13:47:08,102][76542] Updated weights for policy 1, policy_version 28240 (0.0007) -[2023-10-10 13:47:08,478][76542] Updated weights for policy 1, policy_version 28250 (0.0008) -[2023-10-10 13:47:08,712][76543] Updated weights for policy 0, policy_version 28263 (0.0009) -[2023-10-10 13:47:09,083][76543] Updated weights for policy 0, policy_version 28273 (0.0009) -[2023-10-10 13:47:09,451][76543] Updated weights for policy 0, policy_version 28283 (0.0008) -[2023-10-10 13:47:11,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 57901056. Throughput: 0: 1817.9, 1: 1819.2. Samples: 14480564. Policy #0 lag: (min: 1.0, avg: 4.1, max: 33.0) -[2023-10-10 13:47:11,076][75634] Avg episode reward: [(0, '35.300'), (1, '31.800')] -[2023-10-10 13:47:12,346][76542] Updated weights for policy 1, policy_version 28260 (0.0009) -[2023-10-10 13:47:12,719][76542] Updated weights for policy 1, policy_version 28270 (0.0008) -[2023-10-10 13:47:13,075][76542] Updated weights for policy 1, policy_version 28280 (0.0008) -[2023-10-10 13:47:13,136][76543] Updated weights for policy 0, policy_version 28293 (0.0010) -[2023-10-10 13:47:13,514][76543] Updated weights for policy 0, policy_version 28303 (0.0009) -[2023-10-10 13:47:13,874][76543] Updated weights for policy 0, policy_version 28313 (0.0009) -[2023-10-10 13:47:16,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 57966592. Throughput: 0: 1820.3, 1: 1803.0. Samples: 14502566. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 13:47:16,077][75634] Avg episode reward: [(0, '34.470'), (1, '34.230')] -[2023-10-10 13:47:16,874][76542] Updated weights for policy 1, policy_version 28290 (0.0008) -[2023-10-10 13:47:17,251][76542] Updated weights for policy 1, policy_version 28300 (0.0008) -[2023-10-10 13:47:17,614][76542] Updated weights for policy 1, policy_version 28310 (0.0010) -[2023-10-10 13:47:17,761][76543] Updated weights for policy 0, policy_version 28323 (0.0008) -[2023-10-10 13:47:17,985][76542] Updated weights for policy 1, policy_version 28320 (0.0008) -[2023-10-10 13:47:18,130][76543] Updated weights for policy 0, policy_version 28333 (0.0010) -[2023-10-10 13:47:18,511][76543] Updated weights for policy 0, policy_version 28343 (0.0009) -[2023-10-10 13:47:21,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 58032128. Throughput: 0: 1823.7, 1: 1802.8. Samples: 14513192. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 13:47:21,076][75634] Avg episode reward: [(0, '35.220'), (1, '33.590')] -[2023-10-10 13:47:21,493][76542] Updated weights for policy 1, policy_version 28330 (0.0008) -[2023-10-10 13:47:21,860][76542] Updated weights for policy 1, policy_version 28340 (0.0007) -[2023-10-10 13:47:22,233][76542] Updated weights for policy 1, policy_version 28350 (0.0008) -[2023-10-10 13:47:22,294][76543] Updated weights for policy 0, policy_version 28353 (0.0008) -[2023-10-10 13:47:22,672][76543] Updated weights for policy 0, policy_version 28363 (0.0009) -[2023-10-10 13:47:23,056][76543] Updated weights for policy 0, policy_version 28373 (0.0009) -[2023-10-10 13:47:23,416][76543] Updated weights for policy 0, policy_version 28383 (0.0011) -[2023-10-10 13:47:25,975][76542] Updated weights for policy 1, policy_version 28360 (0.0007) -[2023-10-10 13:47:26,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 58097664. Throughput: 0: 1818.3, 1: 1805.8. Samples: 14535334. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 13:47:26,077][75634] Avg episode reward: [(0, '33.560'), (1, '34.270')] -[2023-10-10 13:47:26,344][76542] Updated weights for policy 1, policy_version 28370 (0.0010) -[2023-10-10 13:47:26,716][76542] Updated weights for policy 1, policy_version 28380 (0.0010) -[2023-10-10 13:47:27,207][76543] Updated weights for policy 0, policy_version 28393 (0.0007) -[2023-10-10 13:47:27,581][76543] Updated weights for policy 0, policy_version 28403 (0.0009) -[2023-10-10 13:47:27,954][76543] Updated weights for policy 0, policy_version 28413 (0.0007) -[2023-10-10 13:47:30,473][76542] Updated weights for policy 1, policy_version 28390 (0.0008) -[2023-10-10 13:47:30,848][76542] Updated weights for policy 1, policy_version 28400 (0.0009) -[2023-10-10 13:47:31,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 58163200. Throughput: 0: 1813.9, 1: 1808.9. Samples: 14557330. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 13:47:31,077][75634] Avg episode reward: [(0, '33.650'), (1, '33.130')] -[2023-10-10 13:47:31,215][76542] Updated weights for policy 1, policy_version 28410 (0.0009) -[2023-10-10 13:47:31,589][76543] Updated weights for policy 0, policy_version 28423 (0.0009) -[2023-10-10 13:47:31,957][76543] Updated weights for policy 0, policy_version 28433 (0.0009) -[2023-10-10 13:47:32,329][76543] Updated weights for policy 0, policy_version 28443 (0.0008) -[2023-10-10 13:47:34,902][76542] Updated weights for policy 1, policy_version 28420 (0.0009) -[2023-10-10 13:47:35,275][76542] Updated weights for policy 1, policy_version 28430 (0.0010) -[2023-10-10 13:47:35,643][76542] Updated weights for policy 1, policy_version 28440 (0.0008) -[2023-10-10 13:47:36,069][76543] Updated weights for policy 0, policy_version 28453 (0.0010) -[2023-10-10 13:47:36,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 58261504. Throughput: 0: 1814.8, 1: 1803.9. Samples: 14567852. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 13:47:36,076][75634] Avg episode reward: [(0, '34.800'), (1, '33.560')] -[2023-10-10 13:47:36,450][76543] Updated weights for policy 0, policy_version 28463 (0.0009) -[2023-10-10 13:47:36,809][76543] Updated weights for policy 0, policy_version 28473 (0.0011) -[2023-10-10 13:47:39,290][76542] Updated weights for policy 1, policy_version 28450 (0.0008) -[2023-10-10 13:47:39,658][76542] Updated weights for policy 1, policy_version 28460 (0.0008) -[2023-10-10 13:47:40,028][76542] Updated weights for policy 1, policy_version 28470 (0.0010) -[2023-10-10 13:47:40,395][76542] Updated weights for policy 1, policy_version 28480 (0.0009) -[2023-10-10 13:47:40,482][76543] Updated weights for policy 0, policy_version 28483 (0.0009) -[2023-10-10 13:47:40,845][76543] Updated weights for policy 0, policy_version 28493 (0.0009) -[2023-10-10 13:47:41,076][75634] Fps is (10 sec: 16384.5, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 58327040. Throughput: 0: 1815.8, 1: 1808.0. Samples: 14590004. Policy #0 lag: (min: 31.0, avg: 32.8, max: 61.0) -[2023-10-10 13:47:41,076][75634] Avg episode reward: [(0, '32.710'), (1, '33.340')] -[2023-10-10 13:47:41,226][76543] Updated weights for policy 0, policy_version 28503 (0.0009) -[2023-10-10 13:47:44,133][76542] Updated weights for policy 1, policy_version 28490 (0.0008) -[2023-10-10 13:47:44,497][76542] Updated weights for policy 1, policy_version 28500 (0.0011) -[2023-10-10 13:47:44,870][76542] Updated weights for policy 1, policy_version 28510 (0.0010) -[2023-10-10 13:47:44,950][76543] Updated weights for policy 0, policy_version 28513 (0.0010) -[2023-10-10 13:47:45,347][76543] Updated weights for policy 0, policy_version 28523 (0.0008) -[2023-10-10 13:47:45,727][76543] Updated weights for policy 0, policy_version 28533 (0.0008) -[2023-10-10 13:47:46,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 58392576. Throughput: 0: 1822.3, 1: 1801.6. Samples: 14611366. Policy #0 lag: (min: 31.0, avg: 32.8, max: 61.0) -[2023-10-10 13:47:46,077][75634] Avg episode reward: [(0, '35.080'), (1, '33.070')] -[2023-10-10 13:47:46,098][76543] Updated weights for policy 0, policy_version 28543 (0.0007) -[2023-10-10 13:47:48,754][76542] Updated weights for policy 1, policy_version 28520 (0.0008) -[2023-10-10 13:47:49,127][76542] Updated weights for policy 1, policy_version 28530 (0.0008) -[2023-10-10 13:47:49,494][76542] Updated weights for policy 1, policy_version 28540 (0.0007) -[2023-10-10 13:47:49,725][76543] Updated weights for policy 0, policy_version 28553 (0.0009) -[2023-10-10 13:47:50,093][76543] Updated weights for policy 0, policy_version 28563 (0.0007) -[2023-10-10 13:47:50,460][76543] Updated weights for policy 0, policy_version 28573 (0.0007) -[2023-10-10 13:47:51,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 58490880. Throughput: 0: 1815.1, 1: 1810.8. Samples: 14622696. Policy #0 lag: (min: 31.0, avg: 32.8, max: 61.0) -[2023-10-10 13:47:51,077][75634] Avg episode reward: [(0, '35.840'), (1, '33.880')] -[2023-10-10 13:47:53,240][76542] Updated weights for policy 1, policy_version 28550 (0.0008) -[2023-10-10 13:47:53,608][76542] Updated weights for policy 1, policy_version 28560 (0.0008) -[2023-10-10 13:47:53,978][76542] Updated weights for policy 1, policy_version 28570 (0.0007) -[2023-10-10 13:47:54,063][76543] Updated weights for policy 0, policy_version 28583 (0.0008) -[2023-10-10 13:47:54,433][76543] Updated weights for policy 0, policy_version 28593 (0.0008) -[2023-10-10 13:47:54,807][76543] Updated weights for policy 0, policy_version 28603 (0.0007) -[2023-10-10 13:47:56,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 58556416. Throughput: 0: 1826.9, 1: 1803.2. Samples: 14643920. Policy #0 lag: (min: 31.0, avg: 32.8, max: 61.0) -[2023-10-10 13:47:56,077][75634] Avg episode reward: [(0, '33.210'), (1, '34.340')] -[2023-10-10 13:47:57,680][76542] Updated weights for policy 1, policy_version 28580 (0.0008) -[2023-10-10 13:47:58,047][76542] Updated weights for policy 1, policy_version 28590 (0.0009) -[2023-10-10 13:47:58,417][76542] Updated weights for policy 1, policy_version 28600 (0.0009) -[2023-10-10 13:47:58,496][76543] Updated weights for policy 0, policy_version 28613 (0.0008) -[2023-10-10 13:47:58,864][76543] Updated weights for policy 0, policy_version 28623 (0.0008) -[2023-10-10 13:47:59,234][76543] Updated weights for policy 0, policy_version 28633 (0.0008) -[2023-10-10 13:48:01,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 58621952. Throughput: 0: 1812.6, 1: 1813.4. Samples: 14665738. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 13:48:01,077][75634] Avg episode reward: [(0, '32.740'), (1, '37.610')] -[2023-10-10 13:48:01,089][76421] Saving new best policy, reward=37.610! -[2023-10-10 13:48:02,212][76542] Updated weights for policy 1, policy_version 28610 (0.0007) -[2023-10-10 13:48:02,578][76542] Updated weights for policy 1, policy_version 28620 (0.0009) -[2023-10-10 13:48:02,947][76542] Updated weights for policy 1, policy_version 28630 (0.0010) -[2023-10-10 13:48:02,965][76543] Updated weights for policy 0, policy_version 28643 (0.0007) -[2023-10-10 13:48:03,307][76542] Updated weights for policy 1, policy_version 28640 (0.0009) -[2023-10-10 13:48:03,350][76543] Updated weights for policy 0, policy_version 28653 (0.0007) -[2023-10-10 13:48:03,720][76543] Updated weights for policy 0, policy_version 28663 (0.0010) -[2023-10-10 13:48:06,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 58687488. Throughput: 0: 1816.7, 1: 1814.3. Samples: 14676584. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 13:48:06,076][75634] Avg episode reward: [(0, '35.590'), (1, '35.940')] -[2023-10-10 13:48:06,993][76542] Updated weights for policy 1, policy_version 28650 (0.0011) -[2023-10-10 13:48:07,355][76542] Updated weights for policy 1, policy_version 28660 (0.0008) -[2023-10-10 13:48:07,506][76543] Updated weights for policy 0, policy_version 28673 (0.0010) -[2023-10-10 13:48:07,725][76542] Updated weights for policy 1, policy_version 28670 (0.0008) -[2023-10-10 13:48:07,877][76543] Updated weights for policy 0, policy_version 28683 (0.0007) -[2023-10-10 13:48:08,239][76543] Updated weights for policy 0, policy_version 28693 (0.0009) -[2023-10-10 13:48:08,612][76543] Updated weights for policy 0, policy_version 28703 (0.0009) -[2023-10-10 13:48:11,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 58753024. Throughput: 0: 1812.4, 1: 1811.3. Samples: 14698400. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 13:48:11,077][75634] Avg episode reward: [(0, '34.430'), (1, '31.850')] -[2023-10-10 13:48:11,383][76542] Updated weights for policy 1, policy_version 28680 (0.0010) -[2023-10-10 13:48:11,751][76542] Updated weights for policy 1, policy_version 28690 (0.0011) -[2023-10-10 13:48:12,117][76542] Updated weights for policy 1, policy_version 28700 (0.0008) -[2023-10-10 13:48:12,150][76543] Updated weights for policy 0, policy_version 28713 (0.0008) -[2023-10-10 13:48:12,522][76543] Updated weights for policy 0, policy_version 28723 (0.0007) -[2023-10-10 13:48:12,886][76543] Updated weights for policy 0, policy_version 28733 (0.0008) -[2023-10-10 13:48:15,803][76542] Updated weights for policy 1, policy_version 28710 (0.0007) -[2023-10-10 13:48:16,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 58818560. Throughput: 0: 1824.1, 1: 1822.7. Samples: 14721432. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 13:48:16,076][75634] Avg episode reward: [(0, '35.140'), (1, '30.120')] -[2023-10-10 13:48:16,173][76542] Updated weights for policy 1, policy_version 28720 (0.0008) -[2023-10-10 13:48:16,512][76543] Updated weights for policy 0, policy_version 28743 (0.0007) -[2023-10-10 13:48:16,533][76542] Updated weights for policy 1, policy_version 28730 (0.0007) -[2023-10-10 13:48:16,883][76543] Updated weights for policy 0, policy_version 28753 (0.0008) -[2023-10-10 13:48:17,258][76543] Updated weights for policy 0, policy_version 28763 (0.0010) -[2023-10-10 13:48:20,031][76542] Updated weights for policy 1, policy_version 28740 (0.0007) -[2023-10-10 13:48:20,397][76542] Updated weights for policy 1, policy_version 28750 (0.0007) -[2023-10-10 13:48:20,759][76542] Updated weights for policy 1, policy_version 28760 (0.0007) -[2023-10-10 13:48:20,829][76543] Updated weights for policy 0, policy_version 28773 (0.0008) -[2023-10-10 13:48:21,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 58916864. Throughput: 0: 1821.7, 1: 1816.0. Samples: 14731550. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 13:48:21,077][75634] Avg episode reward: [(0, '35.270'), (1, '29.960')] -[2023-10-10 13:48:21,199][76543] Updated weights for policy 0, policy_version 28783 (0.0009) -[2023-10-10 13:48:21,570][76543] Updated weights for policy 0, policy_version 28793 (0.0008) -[2023-10-10 13:48:24,506][76542] Updated weights for policy 1, policy_version 28770 (0.0007) -[2023-10-10 13:48:24,863][76542] Updated weights for policy 1, policy_version 28780 (0.0010) -[2023-10-10 13:48:25,233][76542] Updated weights for policy 1, policy_version 28790 (0.0010) -[2023-10-10 13:48:25,239][76543] Updated weights for policy 0, policy_version 28803 (0.0008) -[2023-10-10 13:48:25,609][76543] Updated weights for policy 0, policy_version 28813 (0.0007) -[2023-10-10 13:48:25,610][76542] Updated weights for policy 1, policy_version 28800 (0.0007) -[2023-10-10 13:48:25,985][76543] Updated weights for policy 0, policy_version 28823 (0.0007) -[2023-10-10 13:48:26,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 58982400. Throughput: 0: 1825.4, 1: 1819.4. Samples: 14754022. Policy #0 lag: (min: 24.0, avg: 51.3, max: 56.0) -[2023-10-10 13:48:26,077][75634] Avg episode reward: [(0, '34.750'), (1, '30.940')] -[2023-10-10 13:48:29,300][76542] Updated weights for policy 1, policy_version 28810 (0.0009) -[2023-10-10 13:48:29,641][76543] Updated weights for policy 0, policy_version 28833 (0.0009) -[2023-10-10 13:48:29,666][76542] Updated weights for policy 1, policy_version 28820 (0.0008) -[2023-10-10 13:48:30,008][76543] Updated weights for policy 0, policy_version 28843 (0.0008) -[2023-10-10 13:48:30,034][76542] Updated weights for policy 1, policy_version 28830 (0.0007) -[2023-10-10 13:48:30,380][76543] Updated weights for policy 0, policy_version 28853 (0.0009) -[2023-10-10 13:48:30,753][76543] Updated weights for policy 0, policy_version 28863 (0.0011) -[2023-10-10 13:48:31,076][75634] Fps is (10 sec: 16384.2, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 59080704. Throughput: 0: 1824.0, 1: 1816.3. Samples: 14775178. Policy #0 lag: (min: 24.0, avg: 51.3, max: 56.0) -[2023-10-10 13:48:31,076][75634] Avg episode reward: [(0, '34.140'), (1, '31.070')] -[2023-10-10 13:48:31,087][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000028864_29556736.pth... -[2023-10-10 13:48:31,087][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000028832_29523968.pth... -[2023-10-10 13:48:31,141][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000027136_27787264.pth -[2023-10-10 13:48:31,142][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000027168_27820032.pth -[2023-10-10 13:48:33,847][76542] Updated weights for policy 1, policy_version 28840 (0.0009) -[2023-10-10 13:48:34,217][76542] Updated weights for policy 1, policy_version 28850 (0.0008) -[2023-10-10 13:48:34,469][76543] Updated weights for policy 0, policy_version 28873 (0.0008) -[2023-10-10 13:48:34,594][76542] Updated weights for policy 1, policy_version 28860 (0.0009) -[2023-10-10 13:48:34,840][76543] Updated weights for policy 0, policy_version 28883 (0.0008) -[2023-10-10 13:48:35,207][76543] Updated weights for policy 0, policy_version 28893 (0.0009) -[2023-10-10 13:48:36,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 59146240. Throughput: 0: 1834.5, 1: 1820.7. Samples: 14787180. Policy #0 lag: (min: 24.0, avg: 51.3, max: 56.0) -[2023-10-10 13:48:36,076][75634] Avg episode reward: [(0, '35.850'), (1, '33.140')] -[2023-10-10 13:48:38,414][76542] Updated weights for policy 1, policy_version 28870 (0.0010) -[2023-10-10 13:48:38,732][76543] Updated weights for policy 0, policy_version 28903 (0.0009) -[2023-10-10 13:48:38,788][76542] Updated weights for policy 1, policy_version 28880 (0.0008) -[2023-10-10 13:48:39,100][76543] Updated weights for policy 0, policy_version 28913 (0.0007) -[2023-10-10 13:48:39,158][76542] Updated weights for policy 1, policy_version 28890 (0.0008) -[2023-10-10 13:48:39,473][76543] Updated weights for policy 0, policy_version 28923 (0.0007) -[2023-10-10 13:48:41,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 59211776. Throughput: 0: 1821.1, 1: 1816.4. Samples: 14807604. Policy #0 lag: (min: 24.0, avg: 51.3, max: 56.0) -[2023-10-10 13:48:41,076][75634] Avg episode reward: [(0, '32.580'), (1, '30.300')] -[2023-10-10 13:48:42,725][76542] Updated weights for policy 1, policy_version 28900 (0.0009) -[2023-10-10 13:48:43,099][76542] Updated weights for policy 1, policy_version 28910 (0.0008) -[2023-10-10 13:48:43,335][76543] Updated weights for policy 0, policy_version 28933 (0.0008) -[2023-10-10 13:48:43,460][76542] Updated weights for policy 1, policy_version 28920 (0.0008) -[2023-10-10 13:48:43,710][76543] Updated weights for policy 0, policy_version 28943 (0.0007) -[2023-10-10 13:48:44,090][76543] Updated weights for policy 0, policy_version 28953 (0.0010) -[2023-10-10 13:48:46,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 59277312. Throughput: 0: 1824.4, 1: 1815.4. Samples: 14829528. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-10 13:48:46,077][75634] Avg episode reward: [(0, '33.050'), (1, '31.670')] -[2023-10-10 13:48:47,145][76542] Updated weights for policy 1, policy_version 28930 (0.0008) -[2023-10-10 13:48:47,511][76542] Updated weights for policy 1, policy_version 28940 (0.0009) -[2023-10-10 13:48:47,751][76543] Updated weights for policy 0, policy_version 28963 (0.0008) -[2023-10-10 13:48:47,882][76542] Updated weights for policy 1, policy_version 28950 (0.0009) -[2023-10-10 13:48:48,122][76543] Updated weights for policy 0, policy_version 28973 (0.0007) -[2023-10-10 13:48:48,249][76542] Updated weights for policy 1, policy_version 28960 (0.0009) -[2023-10-10 13:48:48,488][76543] Updated weights for policy 0, policy_version 28983 (0.0008) -[2023-10-10 13:48:51,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 59342848. Throughput: 0: 1822.5, 1: 1818.4. Samples: 14840428. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-10 13:48:51,076][75634] Avg episode reward: [(0, '34.010'), (1, '34.100')] -[2023-10-10 13:48:52,019][76542] Updated weights for policy 1, policy_version 28970 (0.0008) -[2023-10-10 13:48:52,070][76543] Updated weights for policy 0, policy_version 28993 (0.0008) -[2023-10-10 13:48:52,390][76542] Updated weights for policy 1, policy_version 28980 (0.0009) -[2023-10-10 13:48:52,433][76543] Updated weights for policy 0, policy_version 29003 (0.0008) -[2023-10-10 13:48:52,753][76542] Updated weights for policy 1, policy_version 28990 (0.0010) -[2023-10-10 13:48:52,817][76543] Updated weights for policy 0, policy_version 29013 (0.0007) -[2023-10-10 13:48:53,184][76543] Updated weights for policy 0, policy_version 29023 (0.0007) -[2023-10-10 13:48:56,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 59408384. Throughput: 0: 1834.0, 1: 1812.0. Samples: 14862468. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-10 13:48:56,077][75634] Avg episode reward: [(0, '34.100'), (1, '31.010')] -[2023-10-10 13:48:56,452][76542] Updated weights for policy 1, policy_version 29000 (0.0008) -[2023-10-10 13:48:56,799][76543] Updated weights for policy 0, policy_version 29033 (0.0009) -[2023-10-10 13:48:56,831][76542] Updated weights for policy 1, policy_version 29010 (0.0007) -[2023-10-10 13:48:57,163][76543] Updated weights for policy 0, policy_version 29043 (0.0010) -[2023-10-10 13:48:57,198][76542] Updated weights for policy 1, policy_version 29020 (0.0008) -[2023-10-10 13:48:57,527][76543] Updated weights for policy 0, policy_version 29053 (0.0011) -[2023-10-10 13:49:00,805][76542] Updated weights for policy 1, policy_version 29030 (0.0009) -[2023-10-10 13:49:01,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 59473920. Throughput: 0: 1824.4, 1: 1811.0. Samples: 14885026. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-10 13:49:01,076][75634] Avg episode reward: [(0, '34.690'), (1, '31.840')] -[2023-10-10 13:49:01,165][76542] Updated weights for policy 1, policy_version 29040 (0.0008) -[2023-10-10 13:49:01,241][76543] Updated weights for policy 0, policy_version 29063 (0.0007) -[2023-10-10 13:49:01,532][76542] Updated weights for policy 1, policy_version 29050 (0.0008) -[2023-10-10 13:49:01,601][76543] Updated weights for policy 0, policy_version 29073 (0.0008) -[2023-10-10 13:49:01,971][76543] Updated weights for policy 0, policy_version 29083 (0.0007) -[2023-10-10 13:49:05,350][76542] Updated weights for policy 1, policy_version 29060 (0.0008) -[2023-10-10 13:49:05,682][76543] Updated weights for policy 0, policy_version 29093 (0.0008) -[2023-10-10 13:49:05,719][76542] Updated weights for policy 1, policy_version 29070 (0.0008) -[2023-10-10 13:49:06,050][76543] Updated weights for policy 0, policy_version 29103 (0.0007) -[2023-10-10 13:49:06,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 59539456. Throughput: 0: 1827.4, 1: 1808.5. Samples: 14895166. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-10 13:49:06,077][75634] Avg episode reward: [(0, '37.190'), (1, '34.390')] -[2023-10-10 13:49:06,083][76542] Updated weights for policy 1, policy_version 29080 (0.0009) -[2023-10-10 13:49:06,413][76543] Updated weights for policy 0, policy_version 29113 (0.0009) -[2023-10-10 13:49:09,724][76542] Updated weights for policy 1, policy_version 29090 (0.0008) -[2023-10-10 13:49:10,096][76542] Updated weights for policy 1, policy_version 29100 (0.0008) -[2023-10-10 13:49:10,167][76543] Updated weights for policy 0, policy_version 29123 (0.0008) -[2023-10-10 13:49:10,463][76542] Updated weights for policy 1, policy_version 29110 (0.0007) -[2023-10-10 13:49:10,546][76543] Updated weights for policy 0, policy_version 29133 (0.0009) -[2023-10-10 13:49:10,833][76542] Updated weights for policy 1, policy_version 29120 (0.0008) -[2023-10-10 13:49:10,903][76543] Updated weights for policy 0, policy_version 29143 (0.0009) -[2023-10-10 13:49:11,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 59637760. Throughput: 0: 1824.2, 1: 1816.3. Samples: 14917846. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-10 13:49:11,076][75634] Avg episode reward: [(0, '37.130'), (1, '35.190')] -[2023-10-10 13:49:14,471][76542] Updated weights for policy 1, policy_version 29130 (0.0007) -[2023-10-10 13:49:14,656][76543] Updated weights for policy 0, policy_version 29153 (0.0010) -[2023-10-10 13:49:14,839][76542] Updated weights for policy 1, policy_version 29140 (0.0007) -[2023-10-10 13:49:15,031][76543] Updated weights for policy 0, policy_version 29163 (0.0007) -[2023-10-10 13:49:15,211][76542] Updated weights for policy 1, policy_version 29150 (0.0009) -[2023-10-10 13:49:15,396][76543] Updated weights for policy 0, policy_version 29173 (0.0007) -[2023-10-10 13:49:15,764][76543] Updated weights for policy 0, policy_version 29183 (0.0008) -[2023-10-10 13:49:16,076][75634] Fps is (10 sec: 19661.5, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 59736064. Throughput: 0: 1816.8, 1: 1815.2. Samples: 14938620. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-10 13:49:16,076][75634] Avg episode reward: [(0, '37.240'), (1, '32.710')] -[2023-10-10 13:49:18,844][76542] Updated weights for policy 1, policy_version 29160 (0.0010) -[2023-10-10 13:49:19,206][76542] Updated weights for policy 1, policy_version 29170 (0.0007) -[2023-10-10 13:49:19,489][76543] Updated weights for policy 0, policy_version 29193 (0.0008) -[2023-10-10 13:49:19,574][76542] Updated weights for policy 1, policy_version 29180 (0.0009) -[2023-10-10 13:49:19,860][76543] Updated weights for policy 0, policy_version 29203 (0.0009) -[2023-10-10 13:49:20,233][76543] Updated weights for policy 0, policy_version 29213 (0.0008) -[2023-10-10 13:49:21,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 59801600. Throughput: 0: 1812.8, 1: 1819.3. Samples: 14950626. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-10 13:49:21,076][75634] Avg episode reward: [(0, '37.460'), (1, '30.780')] -[2023-10-10 13:49:23,130][76542] Updated weights for policy 1, policy_version 29190 (0.0009) -[2023-10-10 13:49:23,503][76542] Updated weights for policy 1, policy_version 29200 (0.0008) -[2023-10-10 13:49:23,813][76543] Updated weights for policy 0, policy_version 29223 (0.0008) -[2023-10-10 13:49:23,872][76542] Updated weights for policy 1, policy_version 29210 (0.0008) -[2023-10-10 13:49:24,190][76543] Updated weights for policy 0, policy_version 29233 (0.0008) -[2023-10-10 13:49:24,556][76543] Updated weights for policy 0, policy_version 29243 (0.0010) -[2023-10-10 13:49:26,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 59867136. Throughput: 0: 1821.1, 1: 1823.5. Samples: 14971614. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-10 13:49:26,077][75634] Avg episode reward: [(0, '37.120'), (1, '32.940')] -[2023-10-10 13:49:27,704][76542] Updated weights for policy 1, policy_version 29220 (0.0007) -[2023-10-10 13:49:28,068][76542] Updated weights for policy 1, policy_version 29230 (0.0008) -[2023-10-10 13:49:28,103][76543] Updated weights for policy 0, policy_version 29253 (0.0008) -[2023-10-10 13:49:28,439][76542] Updated weights for policy 1, policy_version 29240 (0.0007) -[2023-10-10 13:49:28,480][76543] Updated weights for policy 0, policy_version 29263 (0.0007) -[2023-10-10 13:49:28,848][76543] Updated weights for policy 0, policy_version 29273 (0.0007) -[2023-10-10 13:49:31,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 59932672. Throughput: 0: 1825.3, 1: 1823.0. Samples: 14993702. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:49:31,077][75634] Avg episode reward: [(0, '35.680'), (1, '30.130')] -[2023-10-10 13:49:32,191][76542] Updated weights for policy 1, policy_version 29250 (0.0009) -[2023-10-10 13:49:32,563][76542] Updated weights for policy 1, policy_version 29260 (0.0008) -[2023-10-10 13:49:32,614][76543] Updated weights for policy 0, policy_version 29283 (0.0008) -[2023-10-10 13:49:32,934][76542] Updated weights for policy 1, policy_version 29270 (0.0009) -[2023-10-10 13:49:32,982][76543] Updated weights for policy 0, policy_version 29293 (0.0007) -[2023-10-10 13:49:33,301][76542] Updated weights for policy 1, policy_version 29280 (0.0009) -[2023-10-10 13:49:33,343][76543] Updated weights for policy 0, policy_version 29303 (0.0009) -[2023-10-10 13:49:36,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 59998208. Throughput: 0: 1820.4, 1: 1821.0. Samples: 15004294. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:49:36,076][75634] Avg episode reward: [(0, '33.250'), (1, '31.570')] -[2023-10-10 13:49:36,990][76542] Updated weights for policy 1, policy_version 29290 (0.0007) -[2023-10-10 13:49:37,090][76543] Updated weights for policy 0, policy_version 29313 (0.0008) -[2023-10-10 13:49:37,366][76542] Updated weights for policy 1, policy_version 29300 (0.0008) -[2023-10-10 13:49:37,471][76543] Updated weights for policy 0, policy_version 29323 (0.0009) -[2023-10-10 13:49:37,730][76542] Updated weights for policy 1, policy_version 29310 (0.0008) -[2023-10-10 13:49:37,844][76543] Updated weights for policy 0, policy_version 29333 (0.0009) -[2023-10-10 13:49:38,211][76543] Updated weights for policy 0, policy_version 29343 (0.0008) -[2023-10-10 13:49:41,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 60063744. Throughput: 0: 1819.3, 1: 1823.6. Samples: 15026398. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:49:41,077][75634] Avg episode reward: [(0, '32.560'), (1, '34.630')] -[2023-10-10 13:49:41,627][76542] Updated weights for policy 1, policy_version 29320 (0.0008) -[2023-10-10 13:49:41,905][76543] Updated weights for policy 0, policy_version 29353 (0.0007) -[2023-10-10 13:49:41,994][76542] Updated weights for policy 1, policy_version 29330 (0.0008) -[2023-10-10 13:49:42,276][76543] Updated weights for policy 0, policy_version 29363 (0.0008) -[2023-10-10 13:49:42,366][76542] Updated weights for policy 1, policy_version 29340 (0.0007) -[2023-10-10 13:49:42,658][76543] Updated weights for policy 0, policy_version 29373 (0.0007) -[2023-10-10 13:49:46,046][76542] Updated weights for policy 1, policy_version 29350 (0.0007) -[2023-10-10 13:49:46,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 60129280. Throughput: 0: 1825.8, 1: 1824.1. Samples: 15049274. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:49:46,077][75634] Avg episode reward: [(0, '31.470'), (1, '38.010')] -[2023-10-10 13:49:46,171][76543] Updated weights for policy 0, policy_version 29383 (0.0009) -[2023-10-10 13:49:46,418][76542] Updated weights for policy 1, policy_version 29360 (0.0010) -[2023-10-10 13:49:46,543][76543] Updated weights for policy 0, policy_version 29393 (0.0008) -[2023-10-10 13:49:46,792][76542] Updated weights for policy 1, policy_version 29370 (0.0008) -[2023-10-10 13:49:46,912][76543] Updated weights for policy 0, policy_version 29403 (0.0009) -[2023-10-10 13:49:47,014][76421] Saving new best policy, reward=38.010! -[2023-10-10 13:49:50,521][76542] Updated weights for policy 1, policy_version 29380 (0.0009) -[2023-10-10 13:49:50,686][76543] Updated weights for policy 0, policy_version 29413 (0.0009) -[2023-10-10 13:49:50,896][76542] Updated weights for policy 1, policy_version 29390 (0.0009) -[2023-10-10 13:49:51,053][76543] Updated weights for policy 0, policy_version 29423 (0.0008) -[2023-10-10 13:49:51,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 60194816. Throughput: 0: 1824.1, 1: 1820.6. Samples: 15059176. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:49:51,077][75634] Avg episode reward: [(0, '31.080'), (1, '37.110')] -[2023-10-10 13:49:51,259][76542] Updated weights for policy 1, policy_version 29400 (0.0008) -[2023-10-10 13:49:51,424][76543] Updated weights for policy 0, policy_version 29433 (0.0007) -[2023-10-10 13:49:54,848][76542] Updated weights for policy 1, policy_version 29410 (0.0008) -[2023-10-10 13:49:55,153][76543] Updated weights for policy 0, policy_version 29443 (0.0008) -[2023-10-10 13:49:55,219][76542] Updated weights for policy 1, policy_version 29420 (0.0007) -[2023-10-10 13:49:55,527][76543] Updated weights for policy 0, policy_version 29453 (0.0009) -[2023-10-10 13:49:55,586][76542] Updated weights for policy 1, policy_version 29430 (0.0007) -[2023-10-10 13:49:55,905][76543] Updated weights for policy 0, policy_version 29463 (0.0007) -[2023-10-10 13:49:55,950][76542] Updated weights for policy 1, policy_version 29440 (0.0007) -[2023-10-10 13:49:56,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 60293120. Throughput: 0: 1828.6, 1: 1820.3. Samples: 15082048. Policy #0 lag: (min: 19.0, avg: 28.4, max: 51.0) -[2023-10-10 13:49:56,077][75634] Avg episode reward: [(0, '32.390'), (1, '35.180')] -[2023-10-10 13:49:59,450][76543] Updated weights for policy 0, policy_version 29473 (0.0008) -[2023-10-10 13:49:59,686][76542] Updated weights for policy 1, policy_version 29450 (0.0008) -[2023-10-10 13:49:59,806][76543] Updated weights for policy 0, policy_version 29483 (0.0009) -[2023-10-10 13:50:00,056][76542] Updated weights for policy 1, policy_version 29460 (0.0009) -[2023-10-10 13:50:00,185][76543] Updated weights for policy 0, policy_version 29493 (0.0007) -[2023-10-10 13:50:00,421][76542] Updated weights for policy 1, policy_version 29470 (0.0009) -[2023-10-10 13:50:00,554][76543] Updated weights for policy 0, policy_version 29503 (0.0007) -[2023-10-10 13:50:01,076][75634] Fps is (10 sec: 19660.8, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 60391424. Throughput: 0: 1821.1, 1: 1812.0. Samples: 15102112. Policy #0 lag: (min: 19.0, avg: 28.4, max: 51.0) -[2023-10-10 13:50:01,077][75634] Avg episode reward: [(0, '34.450'), (1, '34.700')] -[2023-10-10 13:50:03,917][76542] Updated weights for policy 1, policy_version 29480 (0.0008) -[2023-10-10 13:50:04,195][76543] Updated weights for policy 0, policy_version 29513 (0.0008) -[2023-10-10 13:50:04,289][76542] Updated weights for policy 1, policy_version 29490 (0.0008) -[2023-10-10 13:50:04,559][76543] Updated weights for policy 0, policy_version 29523 (0.0009) -[2023-10-10 13:50:04,653][76542] Updated weights for policy 1, policy_version 29500 (0.0010) -[2023-10-10 13:50:04,932][76543] Updated weights for policy 0, policy_version 29533 (0.0009) -[2023-10-10 13:50:06,076][75634] Fps is (10 sec: 16383.9, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 60456960. Throughput: 0: 1832.6, 1: 1816.7. Samples: 15114848. Policy #0 lag: (min: 19.0, avg: 28.4, max: 51.0) -[2023-10-10 13:50:06,077][75634] Avg episode reward: [(0, '33.450'), (1, '34.430')] -[2023-10-10 13:50:08,443][76543] Updated weights for policy 0, policy_version 29543 (0.0009) -[2023-10-10 13:50:08,493][76542] Updated weights for policy 1, policy_version 29510 (0.0008) -[2023-10-10 13:50:08,801][76543] Updated weights for policy 0, policy_version 29553 (0.0009) -[2023-10-10 13:50:08,860][76542] Updated weights for policy 1, policy_version 29520 (0.0007) -[2023-10-10 13:50:09,174][76543] Updated weights for policy 0, policy_version 29563 (0.0009) -[2023-10-10 13:50:09,234][76542] Updated weights for policy 1, policy_version 29530 (0.0007) -[2023-10-10 13:50:11,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 60522496. Throughput: 0: 1819.7, 1: 1804.1. Samples: 15134684. Policy #0 lag: (min: 19.0, avg: 28.4, max: 51.0) -[2023-10-10 13:50:11,076][75634] Avg episode reward: [(0, '33.840'), (1, '31.630')] -[2023-10-10 13:50:12,900][76543] Updated weights for policy 0, policy_version 29573 (0.0007) -[2023-10-10 13:50:13,117][76542] Updated weights for policy 1, policy_version 29540 (0.0009) -[2023-10-10 13:50:13,266][76543] Updated weights for policy 0, policy_version 29583 (0.0007) -[2023-10-10 13:50:13,480][76542] Updated weights for policy 1, policy_version 29550 (0.0008) -[2023-10-10 13:50:13,634][76543] Updated weights for policy 0, policy_version 29593 (0.0007) -[2023-10-10 13:50:13,849][76542] Updated weights for policy 1, policy_version 29560 (0.0008) -[2023-10-10 13:50:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 60588032. Throughput: 0: 1833.1, 1: 1798.9. Samples: 15157140. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:50:16,077][75634] Avg episode reward: [(0, '33.390'), (1, '29.340')] -[2023-10-10 13:50:17,328][76543] Updated weights for policy 0, policy_version 29603 (0.0008) -[2023-10-10 13:50:17,465][76542] Updated weights for policy 1, policy_version 29570 (0.0008) -[2023-10-10 13:50:17,698][76543] Updated weights for policy 0, policy_version 29613 (0.0008) -[2023-10-10 13:50:17,827][76542] Updated weights for policy 1, policy_version 29580 (0.0007) -[2023-10-10 13:50:18,061][76543] Updated weights for policy 0, policy_version 29623 (0.0008) -[2023-10-10 13:50:18,196][76542] Updated weights for policy 1, policy_version 29590 (0.0008) -[2023-10-10 13:50:18,568][76542] Updated weights for policy 1, policy_version 29600 (0.0008) -[2023-10-10 13:50:21,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 60653568. Throughput: 0: 1823.1, 1: 1798.9. Samples: 15167286. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:50:21,077][75634] Avg episode reward: [(0, '32.710'), (1, '35.600')] -[2023-10-10 13:50:21,855][76543] Updated weights for policy 0, policy_version 29633 (0.0008) -[2023-10-10 13:50:22,235][76543] Updated weights for policy 0, policy_version 29643 (0.0007) -[2023-10-10 13:50:22,287][76542] Updated weights for policy 1, policy_version 29610 (0.0007) -[2023-10-10 13:50:22,610][76543] Updated weights for policy 0, policy_version 29653 (0.0007) -[2023-10-10 13:50:22,661][76542] Updated weights for policy 1, policy_version 29620 (0.0007) -[2023-10-10 13:50:22,971][76543] Updated weights for policy 0, policy_version 29663 (0.0010) -[2023-10-10 13:50:23,021][76542] Updated weights for policy 1, policy_version 29630 (0.0007) -[2023-10-10 13:50:26,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 60719104. Throughput: 0: 1831.5, 1: 1798.4. Samples: 15189746. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:50:26,077][75634] Avg episode reward: [(0, '33.680'), (1, '37.700')] -[2023-10-10 13:50:26,683][76543] Updated weights for policy 0, policy_version 29673 (0.0008) -[2023-10-10 13:50:26,788][76542] Updated weights for policy 1, policy_version 29640 (0.0009) -[2023-10-10 13:50:27,065][76543] Updated weights for policy 0, policy_version 29683 (0.0009) -[2023-10-10 13:50:27,160][76542] Updated weights for policy 1, policy_version 29650 (0.0009) -[2023-10-10 13:50:27,423][76543] Updated weights for policy 0, policy_version 29693 (0.0008) -[2023-10-10 13:50:27,528][76542] Updated weights for policy 1, policy_version 29660 (0.0010) -[2023-10-10 13:50:31,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 60784640. Throughput: 0: 1826.1, 1: 1802.9. Samples: 15212580. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:50:31,076][75634] Avg episode reward: [(0, '32.970'), (1, '34.320')] -[2023-10-10 13:50:31,112][76543] Updated weights for policy 0, policy_version 29703 (0.0008) -[2023-10-10 13:50:31,186][76542] Updated weights for policy 1, policy_version 29670 (0.0008) -[2023-10-10 13:50:31,490][76543] Updated weights for policy 0, policy_version 29713 (0.0009) -[2023-10-10 13:50:31,553][76542] Updated weights for policy 1, policy_version 29680 (0.0009) -[2023-10-10 13:50:31,856][76543] Updated weights for policy 0, policy_version 29723 (0.0008) -[2023-10-10 13:50:31,919][76542] Updated weights for policy 1, policy_version 29690 (0.0007) -[2023-10-10 13:50:32,042][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000029728_30441472.pth... -[2023-10-10 13:50:32,071][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000028000_28672000.pth -[2023-10-10 13:50:32,145][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000029696_30408704.pth... -[2023-10-10 13:50:32,184][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000027968_28639232.pth -[2023-10-10 13:50:35,648][76542] Updated weights for policy 1, policy_version 29700 (0.0007) -[2023-10-10 13:50:35,740][76543] Updated weights for policy 0, policy_version 29733 (0.0008) -[2023-10-10 13:50:36,021][76542] Updated weights for policy 1, policy_version 29710 (0.0008) -[2023-10-10 13:50:36,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 60850176. Throughput: 0: 1822.4, 1: 1802.3. Samples: 15222286. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:50:36,076][75634] Avg episode reward: [(0, '34.040'), (1, '30.530')] -[2023-10-10 13:50:36,104][76543] Updated weights for policy 0, policy_version 29743 (0.0007) -[2023-10-10 13:50:36,379][76542] Updated weights for policy 1, policy_version 29720 (0.0008) -[2023-10-10 13:50:36,479][76543] Updated weights for policy 0, policy_version 29753 (0.0007) -[2023-10-10 13:50:40,191][76542] Updated weights for policy 1, policy_version 29730 (0.0009) -[2023-10-10 13:50:40,301][76543] Updated weights for policy 0, policy_version 29763 (0.0007) -[2023-10-10 13:50:40,568][76542] Updated weights for policy 1, policy_version 29740 (0.0007) -[2023-10-10 13:50:40,663][76543] Updated weights for policy 0, policy_version 29773 (0.0009) -[2023-10-10 13:50:40,935][76542] Updated weights for policy 1, policy_version 29750 (0.0008) -[2023-10-10 13:50:41,034][76543] Updated weights for policy 0, policy_version 29783 (0.0007) -[2023-10-10 13:50:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 60915712. Throughput: 0: 1819.3, 1: 1799.0. Samples: 15244868. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-10 13:50:41,076][75634] Avg episode reward: [(0, '32.840'), (1, '31.460')] -[2023-10-10 13:50:41,298][76542] Updated weights for policy 1, policy_version 29760 (0.0008) -[2023-10-10 13:50:44,762][76543] Updated weights for policy 0, policy_version 29793 (0.0007) -[2023-10-10 13:50:45,091][76542] Updated weights for policy 1, policy_version 29770 (0.0007) -[2023-10-10 13:50:45,130][76543] Updated weights for policy 0, policy_version 29803 (0.0008) -[2023-10-10 13:50:45,459][76542] Updated weights for policy 1, policy_version 29780 (0.0007) -[2023-10-10 13:50:45,498][76543] Updated weights for policy 0, policy_version 29813 (0.0008) -[2023-10-10 13:50:45,817][76542] Updated weights for policy 1, policy_version 29790 (0.0008) -[2023-10-10 13:50:45,872][76543] Updated weights for policy 0, policy_version 29823 (0.0009) -[2023-10-10 13:50:46,076][75634] Fps is (10 sec: 19660.7, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 61046784. Throughput: 0: 1826.8, 1: 1806.8. Samples: 15265628. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-10 13:50:46,077][75634] Avg episode reward: [(0, '32.330'), (1, '33.080')] -[2023-10-10 13:50:49,447][76542] Updated weights for policy 1, policy_version 29800 (0.0007) -[2023-10-10 13:50:49,704][76543] Updated weights for policy 0, policy_version 29833 (0.0008) -[2023-10-10 13:50:49,810][76542] Updated weights for policy 1, policy_version 29810 (0.0009) -[2023-10-10 13:50:50,077][76543] Updated weights for policy 0, policy_version 29843 (0.0008) -[2023-10-10 13:50:50,183][76542] Updated weights for policy 1, policy_version 29820 (0.0007) -[2023-10-10 13:50:50,461][76543] Updated weights for policy 0, policy_version 29853 (0.0007) -[2023-10-10 13:50:51,076][75634] Fps is (10 sec: 19660.2, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 61112320. Throughput: 0: 1809.9, 1: 1801.2. Samples: 15277350. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-10 13:50:51,077][75634] Avg episode reward: [(0, '33.340'), (1, '34.120')] -[2023-10-10 13:50:53,895][76542] Updated weights for policy 1, policy_version 29830 (0.0008) -[2023-10-10 13:50:54,009][76543] Updated weights for policy 0, policy_version 29863 (0.0009) -[2023-10-10 13:50:54,264][76542] Updated weights for policy 1, policy_version 29840 (0.0008) -[2023-10-10 13:50:54,383][76543] Updated weights for policy 0, policy_version 29873 (0.0009) -[2023-10-10 13:50:54,638][76542] Updated weights for policy 1, policy_version 29850 (0.0009) -[2023-10-10 13:50:54,748][76543] Updated weights for policy 0, policy_version 29883 (0.0008) -[2023-10-10 13:50:56,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 61177856. Throughput: 0: 1822.7, 1: 1816.0. Samples: 15298424. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-10 13:50:56,076][75634] Avg episode reward: [(0, '35.190'), (1, '33.630')] -[2023-10-10 13:50:58,238][76542] Updated weights for policy 1, policy_version 29860 (0.0009) -[2023-10-10 13:50:58,407][76543] Updated weights for policy 0, policy_version 29893 (0.0007) -[2023-10-10 13:50:58,600][76542] Updated weights for policy 1, policy_version 29870 (0.0008) -[2023-10-10 13:50:58,780][76543] Updated weights for policy 0, policy_version 29903 (0.0008) -[2023-10-10 13:50:58,966][76542] Updated weights for policy 1, policy_version 29880 (0.0007) -[2023-10-10 13:50:59,151][76543] Updated weights for policy 0, policy_version 29913 (0.0008) -[2023-10-10 13:51:01,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 61243392. Throughput: 0: 1804.7, 1: 1813.8. Samples: 15319972. Policy #0 lag: (min: 12.0, avg: 20.3, max: 44.0) -[2023-10-10 13:51:01,077][75634] Avg episode reward: [(0, '33.890'), (1, '35.920')] -[2023-10-10 13:51:02,762][76542] Updated weights for policy 1, policy_version 29890 (0.0008) -[2023-10-10 13:51:02,770][76543] Updated weights for policy 0, policy_version 29923 (0.0010) -[2023-10-10 13:51:03,125][76542] Updated weights for policy 1, policy_version 29900 (0.0009) -[2023-10-10 13:51:03,137][76543] Updated weights for policy 0, policy_version 29933 (0.0007) -[2023-10-10 13:51:03,492][76542] Updated weights for policy 1, policy_version 29910 (0.0009) -[2023-10-10 13:51:03,511][76543] Updated weights for policy 0, policy_version 29943 (0.0008) -[2023-10-10 13:51:03,863][76542] Updated weights for policy 1, policy_version 29920 (0.0008) -[2023-10-10 13:51:06,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 61308928. Throughput: 0: 1822.2, 1: 1817.1. Samples: 15331056. Policy #0 lag: (min: 12.0, avg: 20.3, max: 44.0) -[2023-10-10 13:51:06,077][75634] Avg episode reward: [(0, '33.010'), (1, '36.530')] -[2023-10-10 13:51:07,240][76543] Updated weights for policy 0, policy_version 29953 (0.0008) -[2023-10-10 13:51:07,501][76542] Updated weights for policy 1, policy_version 29930 (0.0009) -[2023-10-10 13:51:07,613][76543] Updated weights for policy 0, policy_version 29963 (0.0007) -[2023-10-10 13:51:07,873][76542] Updated weights for policy 1, policy_version 29940 (0.0009) -[2023-10-10 13:51:07,974][76543] Updated weights for policy 0, policy_version 29973 (0.0008) -[2023-10-10 13:51:08,240][76542] Updated weights for policy 1, policy_version 29950 (0.0007) -[2023-10-10 13:51:08,341][76543] Updated weights for policy 0, policy_version 29983 (0.0008) -[2023-10-10 13:51:11,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 61374464. Throughput: 0: 1803.6, 1: 1816.6. Samples: 15352656. Policy #0 lag: (min: 12.0, avg: 20.3, max: 44.0) -[2023-10-10 13:51:11,077][75634] Avg episode reward: [(0, '32.010'), (1, '34.570')] -[2023-10-10 13:51:12,077][76542] Updated weights for policy 1, policy_version 29960 (0.0008) -[2023-10-10 13:51:12,225][76543] Updated weights for policy 0, policy_version 29993 (0.0007) -[2023-10-10 13:51:12,441][76542] Updated weights for policy 1, policy_version 29970 (0.0007) -[2023-10-10 13:51:12,590][76543] Updated weights for policy 0, policy_version 30003 (0.0008) -[2023-10-10 13:51:12,798][76542] Updated weights for policy 1, policy_version 29980 (0.0007) -[2023-10-10 13:51:12,965][76543] Updated weights for policy 0, policy_version 30013 (0.0008) -[2023-10-10 13:51:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 61440000. Throughput: 0: 1798.0, 1: 1811.0. Samples: 15374986. Policy #0 lag: (min: 12.0, avg: 20.3, max: 44.0) -[2023-10-10 13:51:16,077][75634] Avg episode reward: [(0, '31.940'), (1, '30.110')] -[2023-10-10 13:51:16,470][76542] Updated weights for policy 1, policy_version 29990 (0.0008) -[2023-10-10 13:51:16,760][76543] Updated weights for policy 0, policy_version 30023 (0.0008) -[2023-10-10 13:51:16,842][76542] Updated weights for policy 1, policy_version 30000 (0.0008) -[2023-10-10 13:51:17,143][76543] Updated weights for policy 0, policy_version 30033 (0.0009) -[2023-10-10 13:51:17,200][76542] Updated weights for policy 1, policy_version 30010 (0.0008) -[2023-10-10 13:51:17,511][76543] Updated weights for policy 0, policy_version 30043 (0.0007) -[2023-10-10 13:51:20,808][76542] Updated weights for policy 1, policy_version 30020 (0.0008) -[2023-10-10 13:51:21,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 61505536. Throughput: 0: 1803.4, 1: 1809.3. Samples: 15384858. Policy #0 lag: (min: 12.0, avg: 20.3, max: 44.0) -[2023-10-10 13:51:21,076][75634] Avg episode reward: [(0, '32.170'), (1, '27.450')] -[2023-10-10 13:51:21,104][76543] Updated weights for policy 0, policy_version 30053 (0.0008) -[2023-10-10 13:51:21,169][76542] Updated weights for policy 1, policy_version 30030 (0.0008) -[2023-10-10 13:51:21,480][76543] Updated weights for policy 0, policy_version 30063 (0.0008) -[2023-10-10 13:51:21,543][76542] Updated weights for policy 1, policy_version 30040 (0.0008) -[2023-10-10 13:51:21,850][76543] Updated weights for policy 0, policy_version 30073 (0.0008) -[2023-10-10 13:51:25,092][76542] Updated weights for policy 1, policy_version 30050 (0.0008) -[2023-10-10 13:51:25,455][76542] Updated weights for policy 1, policy_version 30060 (0.0008) -[2023-10-10 13:51:25,510][76543] Updated weights for policy 0, policy_version 30083 (0.0009) -[2023-10-10 13:51:25,821][76542] Updated weights for policy 1, policy_version 30070 (0.0008) -[2023-10-10 13:51:25,870][76543] Updated weights for policy 0, policy_version 30093 (0.0008) -[2023-10-10 13:51:26,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14440.2). Total num frames: 61571072. Throughput: 0: 1805.2, 1: 1815.4. Samples: 15407798. Policy #0 lag: (min: 30.0, avg: 38.0, max: 62.0) -[2023-10-10 13:51:26,076][75634] Avg episode reward: [(0, '33.780'), (1, '29.380')] -[2023-10-10 13:51:26,192][76542] Updated weights for policy 1, policy_version 30080 (0.0008) -[2023-10-10 13:51:26,252][76543] Updated weights for policy 0, policy_version 30103 (0.0010) -[2023-10-10 13:51:29,957][76543] Updated weights for policy 0, policy_version 30113 (0.0009) -[2023-10-10 13:51:29,970][76542] Updated weights for policy 1, policy_version 30090 (0.0009) -[2023-10-10 13:51:30,328][76543] Updated weights for policy 0, policy_version 30123 (0.0009) -[2023-10-10 13:51:30,333][76542] Updated weights for policy 1, policy_version 30100 (0.0009) -[2023-10-10 13:51:30,699][76542] Updated weights for policy 1, policy_version 30110 (0.0009) -[2023-10-10 13:51:30,701][76543] Updated weights for policy 0, policy_version 30133 (0.0009) -[2023-10-10 13:51:31,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 61669376. Throughput: 0: 1815.1, 1: 1810.4. Samples: 15428772. Policy #0 lag: (min: 30.0, avg: 38.0, max: 62.0) -[2023-10-10 13:51:31,076][75634] Avg episode reward: [(0, '33.730'), (1, '33.330')] -[2023-10-10 13:51:31,078][76543] Updated weights for policy 0, policy_version 30143 (0.0009) -[2023-10-10 13:51:34,386][76542] Updated weights for policy 1, policy_version 30120 (0.0010) -[2023-10-10 13:51:34,746][76542] Updated weights for policy 1, policy_version 30130 (0.0010) -[2023-10-10 13:51:34,788][76543] Updated weights for policy 0, policy_version 30153 (0.0009) -[2023-10-10 13:51:35,117][76542] Updated weights for policy 1, policy_version 30140 (0.0007) -[2023-10-10 13:51:35,166][76543] Updated weights for policy 0, policy_version 30163 (0.0007) -[2023-10-10 13:51:35,537][76543] Updated weights for policy 0, policy_version 30173 (0.0009) -[2023-10-10 13:51:36,076][75634] Fps is (10 sec: 19660.3, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 61767680. Throughput: 0: 1810.2, 1: 1814.0. Samples: 15440442. Policy #0 lag: (min: 30.0, avg: 38.0, max: 62.0) -[2023-10-10 13:51:36,077][75634] Avg episode reward: [(0, '34.970'), (1, '30.670')] -[2023-10-10 13:51:38,844][76542] Updated weights for policy 1, policy_version 30150 (0.0008) -[2023-10-10 13:51:39,209][76542] Updated weights for policy 1, policy_version 30160 (0.0007) -[2023-10-10 13:51:39,242][76543] Updated weights for policy 0, policy_version 30183 (0.0009) -[2023-10-10 13:51:39,580][76542] Updated weights for policy 1, policy_version 30170 (0.0008) -[2023-10-10 13:51:39,599][76543] Updated weights for policy 0, policy_version 30193 (0.0008) -[2023-10-10 13:51:39,972][76543] Updated weights for policy 0, policy_version 30203 (0.0008) -[2023-10-10 13:51:41,076][75634] Fps is (10 sec: 16383.8, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 61833216. Throughput: 0: 1810.8, 1: 1807.9. Samples: 15461266. Policy #0 lag: (min: 30.0, avg: 38.0, max: 62.0) -[2023-10-10 13:51:41,077][75634] Avg episode reward: [(0, '33.120'), (1, '30.200')] -[2023-10-10 13:51:43,368][76542] Updated weights for policy 1, policy_version 30180 (0.0008) -[2023-10-10 13:51:43,509][76543] Updated weights for policy 0, policy_version 30213 (0.0009) -[2023-10-10 13:51:43,747][76542] Updated weights for policy 1, policy_version 30190 (0.0008) -[2023-10-10 13:51:43,882][76543] Updated weights for policy 0, policy_version 30223 (0.0008) -[2023-10-10 13:51:44,103][76542] Updated weights for policy 1, policy_version 30200 (0.0009) -[2023-10-10 13:51:44,245][76543] Updated weights for policy 0, policy_version 30233 (0.0008) -[2023-10-10 13:51:46,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 61898752. Throughput: 0: 1809.4, 1: 1807.8. Samples: 15482748. Policy #0 lag: (min: 10.0, avg: 10.1, max: 15.0) -[2023-10-10 13:51:46,077][75634] Avg episode reward: [(0, '31.130'), (1, '29.900')] -[2023-10-10 13:51:47,962][76543] Updated weights for policy 0, policy_version 30243 (0.0010) -[2023-10-10 13:51:47,964][76542] Updated weights for policy 1, policy_version 30210 (0.0008) -[2023-10-10 13:51:48,331][76543] Updated weights for policy 0, policy_version 30253 (0.0008) -[2023-10-10 13:51:48,345][76542] Updated weights for policy 1, policy_version 30220 (0.0008) -[2023-10-10 13:51:48,703][76542] Updated weights for policy 1, policy_version 30230 (0.0007) -[2023-10-10 13:51:48,706][76543] Updated weights for policy 0, policy_version 30263 (0.0008) -[2023-10-10 13:51:49,073][76542] Updated weights for policy 1, policy_version 30240 (0.0007) -[2023-10-10 13:51:51,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 61964288. Throughput: 0: 1809.1, 1: 1810.1. Samples: 15493918. Policy #0 lag: (min: 10.0, avg: 10.1, max: 15.0) -[2023-10-10 13:51:51,077][75634] Avg episode reward: [(0, '33.640'), (1, '33.000')] -[2023-10-10 13:51:52,311][76543] Updated weights for policy 0, policy_version 30273 (0.0008) -[2023-10-10 13:51:52,681][76543] Updated weights for policy 0, policy_version 30283 (0.0007) -[2023-10-10 13:51:52,682][76542] Updated weights for policy 1, policy_version 30250 (0.0009) -[2023-10-10 13:51:53,038][76543] Updated weights for policy 0, policy_version 30293 (0.0008) -[2023-10-10 13:51:53,050][76542] Updated weights for policy 1, policy_version 30260 (0.0007) -[2023-10-10 13:51:53,405][76543] Updated weights for policy 0, policy_version 30303 (0.0008) -[2023-10-10 13:51:53,422][76542] Updated weights for policy 1, policy_version 30270 (0.0007) -[2023-10-10 13:51:56,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 62029824. Throughput: 0: 1808.6, 1: 1798.1. Samples: 15514956. Policy #0 lag: (min: 10.0, avg: 10.1, max: 15.0) -[2023-10-10 13:51:56,076][75634] Avg episode reward: [(0, '33.620'), (1, '35.950')] -[2023-10-10 13:51:57,097][76543] Updated weights for policy 0, policy_version 30313 (0.0009) -[2023-10-10 13:51:57,348][76542] Updated weights for policy 1, policy_version 30280 (0.0010) -[2023-10-10 13:51:57,456][76543] Updated weights for policy 0, policy_version 30323 (0.0007) -[2023-10-10 13:51:57,726][76542] Updated weights for policy 1, policy_version 30290 (0.0009) -[2023-10-10 13:51:57,820][76543] Updated weights for policy 0, policy_version 30333 (0.0008) -[2023-10-10 13:51:58,087][76542] Updated weights for policy 1, policy_version 30300 (0.0009) -[2023-10-10 13:52:01,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 62095360. Throughput: 0: 1813.2, 1: 1795.2. Samples: 15537364. Policy #0 lag: (min: 10.0, avg: 10.1, max: 15.0) -[2023-10-10 13:52:01,077][75634] Avg episode reward: [(0, '32.290'), (1, '34.390')] -[2023-10-10 13:52:01,635][76543] Updated weights for policy 0, policy_version 30343 (0.0007) -[2023-10-10 13:52:01,979][76542] Updated weights for policy 1, policy_version 30310 (0.0009) -[2023-10-10 13:52:02,008][76543] Updated weights for policy 0, policy_version 30353 (0.0007) -[2023-10-10 13:52:02,346][76542] Updated weights for policy 1, policy_version 30320 (0.0007) -[2023-10-10 13:52:02,385][76543] Updated weights for policy 0, policy_version 30363 (0.0007) -[2023-10-10 13:52:02,716][76542] Updated weights for policy 1, policy_version 30330 (0.0009) -[2023-10-10 13:52:05,968][76543] Updated weights for policy 0, policy_version 30373 (0.0008) -[2023-10-10 13:52:06,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 62160896. Throughput: 0: 1812.0, 1: 1795.0. Samples: 15547174. Policy #0 lag: (min: 10.0, avg: 10.1, max: 15.0) -[2023-10-10 13:52:06,076][75634] Avg episode reward: [(0, '34.020'), (1, '34.270')] -[2023-10-10 13:52:06,354][76543] Updated weights for policy 0, policy_version 30383 (0.0007) -[2023-10-10 13:52:06,424][76542] Updated weights for policy 1, policy_version 30340 (0.0008) -[2023-10-10 13:52:06,714][76543] Updated weights for policy 0, policy_version 30393 (0.0007) -[2023-10-10 13:52:06,802][76542] Updated weights for policy 1, policy_version 30350 (0.0008) -[2023-10-10 13:52:07,168][76542] Updated weights for policy 1, policy_version 30360 (0.0010) -[2023-10-10 13:52:10,472][76543] Updated weights for policy 0, policy_version 30403 (0.0007) -[2023-10-10 13:52:10,839][76543] Updated weights for policy 0, policy_version 30413 (0.0007) -[2023-10-10 13:52:10,862][76542] Updated weights for policy 1, policy_version 30370 (0.0011) -[2023-10-10 13:52:11,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14440.2). Total num frames: 62226432. Throughput: 0: 1813.2, 1: 1792.7. Samples: 15570062. Policy #0 lag: (min: 13.0, avg: 13.0, max: 15.0) -[2023-10-10 13:52:11,076][75634] Avg episode reward: [(0, '34.310'), (1, '36.470')] -[2023-10-10 13:52:11,205][76543] Updated weights for policy 0, policy_version 30423 (0.0008) -[2023-10-10 13:52:11,226][76542] Updated weights for policy 1, policy_version 30380 (0.0008) -[2023-10-10 13:52:11,600][76542] Updated weights for policy 1, policy_version 30390 (0.0007) -[2023-10-10 13:52:11,968][76542] Updated weights for policy 1, policy_version 30400 (0.0007) -[2023-10-10 13:52:14,848][76543] Updated weights for policy 0, policy_version 30433 (0.0007) -[2023-10-10 13:52:15,226][76543] Updated weights for policy 0, policy_version 30443 (0.0009) -[2023-10-10 13:52:15,597][76543] Updated weights for policy 0, policy_version 30453 (0.0009) -[2023-10-10 13:52:15,645][76542] Updated weights for policy 1, policy_version 30410 (0.0010) -[2023-10-10 13:52:15,976][76543] Updated weights for policy 0, policy_version 30463 (0.0009) -[2023-10-10 13:52:16,009][76542] Updated weights for policy 1, policy_version 30420 (0.0008) -[2023-10-10 13:52:16,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 62324736. Throughput: 0: 1813.5, 1: 1818.4. Samples: 15592206. Policy #0 lag: (min: 13.0, avg: 13.0, max: 15.0) -[2023-10-10 13:52:16,076][75634] Avg episode reward: [(0, '33.430'), (1, '36.510')] -[2023-10-10 13:52:16,382][76542] Updated weights for policy 1, policy_version 30430 (0.0008) -[2023-10-10 13:52:19,630][76543] Updated weights for policy 0, policy_version 30473 (0.0011) -[2023-10-10 13:52:20,015][76543] Updated weights for policy 0, policy_version 30483 (0.0009) -[2023-10-10 13:52:20,035][76542] Updated weights for policy 1, policy_version 30440 (0.0008) -[2023-10-10 13:52:20,374][76543] Updated weights for policy 0, policy_version 30493 (0.0009) -[2023-10-10 13:52:20,417][76542] Updated weights for policy 1, policy_version 30450 (0.0007) -[2023-10-10 13:52:20,791][76542] Updated weights for policy 1, policy_version 30460 (0.0010) -[2023-10-10 13:52:21,076][75634] Fps is (10 sec: 19660.7, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 62423040. Throughput: 0: 1824.8, 1: 1794.1. Samples: 15603288. Policy #0 lag: (min: 13.0, avg: 13.0, max: 15.0) -[2023-10-10 13:52:21,076][75634] Avg episode reward: [(0, '32.840'), (1, '32.790')] -[2023-10-10 13:52:24,116][76543] Updated weights for policy 0, policy_version 30503 (0.0009) -[2023-10-10 13:52:24,484][76543] Updated weights for policy 0, policy_version 30513 (0.0008) -[2023-10-10 13:52:24,573][76542] Updated weights for policy 1, policy_version 30470 (0.0008) -[2023-10-10 13:52:24,847][76543] Updated weights for policy 0, policy_version 30523 (0.0008) -[2023-10-10 13:52:24,937][76542] Updated weights for policy 1, policy_version 30480 (0.0008) -[2023-10-10 13:52:25,302][76542] Updated weights for policy 1, policy_version 30490 (0.0010) -[2023-10-10 13:52:26,076][75634] Fps is (10 sec: 16384.1, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 62488576. Throughput: 0: 1824.2, 1: 1816.2. Samples: 15625084. Policy #0 lag: (min: 13.0, avg: 13.0, max: 15.0) -[2023-10-10 13:52:26,076][75634] Avg episode reward: [(0, '36.660'), (1, '30.650')] -[2023-10-10 13:52:28,662][76543] Updated weights for policy 0, policy_version 30533 (0.0009) -[2023-10-10 13:52:28,842][76542] Updated weights for policy 1, policy_version 30500 (0.0007) -[2023-10-10 13:52:29,020][76543] Updated weights for policy 0, policy_version 30543 (0.0009) -[2023-10-10 13:52:29,205][76542] Updated weights for policy 1, policy_version 30510 (0.0009) -[2023-10-10 13:52:29,395][76543] Updated weights for policy 0, policy_version 30553 (0.0008) -[2023-10-10 13:52:29,574][76542] Updated weights for policy 1, policy_version 30520 (0.0009) -[2023-10-10 13:52:31,076][75634] Fps is (10 sec: 13106.7, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 62554112. Throughput: 0: 1820.8, 1: 1802.6. Samples: 15645804. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-10 13:52:31,077][75634] Avg episode reward: [(0, '37.010'), (1, '33.150')] -[2023-10-10 13:52:31,089][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000030528_31260672.pth... -[2023-10-10 13:52:31,089][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000030560_31293440.pth... -[2023-10-10 13:52:31,141][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000028832_29523968.pth -[2023-10-10 13:52:31,141][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000028864_29556736.pth -[2023-10-10 13:52:33,099][76543] Updated weights for policy 0, policy_version 30563 (0.0009) -[2023-10-10 13:52:33,384][76542] Updated weights for policy 1, policy_version 30530 (0.0007) -[2023-10-10 13:52:33,472][76543] Updated weights for policy 0, policy_version 30573 (0.0008) -[2023-10-10 13:52:33,752][76542] Updated weights for policy 1, policy_version 30540 (0.0007) -[2023-10-10 13:52:33,835][76543] Updated weights for policy 0, policy_version 30583 (0.0007) -[2023-10-10 13:52:34,117][76542] Updated weights for policy 1, policy_version 30550 (0.0008) -[2023-10-10 13:52:34,493][76542] Updated weights for policy 1, policy_version 30560 (0.0009) -[2023-10-10 13:52:36,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 62619648. Throughput: 0: 1822.4, 1: 1818.7. Samples: 15657768. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-10 13:52:36,077][75634] Avg episode reward: [(0, '37.560'), (1, '36.230')] -[2023-10-10 13:52:37,647][76543] Updated weights for policy 0, policy_version 30593 (0.0007) -[2023-10-10 13:52:38,017][76543] Updated weights for policy 0, policy_version 30603 (0.0008) -[2023-10-10 13:52:38,222][76542] Updated weights for policy 1, policy_version 30570 (0.0008) -[2023-10-10 13:52:38,383][76543] Updated weights for policy 0, policy_version 30613 (0.0007) -[2023-10-10 13:52:38,578][76542] Updated weights for policy 1, policy_version 30580 (0.0009) -[2023-10-10 13:52:38,748][76543] Updated weights for policy 0, policy_version 30623 (0.0007) -[2023-10-10 13:52:38,947][76542] Updated weights for policy 1, policy_version 30590 (0.0009) -[2023-10-10 13:52:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 62685184. Throughput: 0: 1816.9, 1: 1809.7. Samples: 15678154. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-10 13:52:41,077][75634] Avg episode reward: [(0, '38.900'), (1, '35.400')] -[2023-10-10 13:52:41,078][76362] Saving new best policy, reward=38.900! -[2023-10-10 13:52:42,388][76543] Updated weights for policy 0, policy_version 30633 (0.0007) -[2023-10-10 13:52:42,690][76542] Updated weights for policy 1, policy_version 30600 (0.0009) -[2023-10-10 13:52:42,754][76543] Updated weights for policy 0, policy_version 30643 (0.0007) -[2023-10-10 13:52:43,065][76542] Updated weights for policy 1, policy_version 30610 (0.0009) -[2023-10-10 13:52:43,126][76543] Updated weights for policy 0, policy_version 30653 (0.0008) -[2023-10-10 13:52:43,434][76542] Updated weights for policy 1, policy_version 30620 (0.0008) -[2023-10-10 13:52:46,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 62750720. Throughput: 0: 1818.6, 1: 1814.5. Samples: 15700854. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-10 13:52:46,076][75634] Avg episode reward: [(0, '38.100'), (1, '38.350')] -[2023-10-10 13:52:46,086][76421] Saving new best policy, reward=38.350! -[2023-10-10 13:52:46,782][76543] Updated weights for policy 0, policy_version 30663 (0.0009) -[2023-10-10 13:52:47,126][76542] Updated weights for policy 1, policy_version 30630 (0.0008) -[2023-10-10 13:52:47,148][76543] Updated weights for policy 0, policy_version 30673 (0.0008) -[2023-10-10 13:52:47,490][76542] Updated weights for policy 1, policy_version 30640 (0.0008) -[2023-10-10 13:52:47,515][76543] Updated weights for policy 0, policy_version 30683 (0.0007) -[2023-10-10 13:52:47,855][76542] Updated weights for policy 1, policy_version 30650 (0.0009) -[2023-10-10 13:52:51,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 62816256. Throughput: 0: 1818.3, 1: 1814.7. Samples: 15710658. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-10 13:52:51,076][75634] Avg episode reward: [(0, '39.080'), (1, '35.700')] -[2023-10-10 13:52:51,261][76543] Updated weights for policy 0, policy_version 30693 (0.0008) -[2023-10-10 13:52:51,559][76542] Updated weights for policy 1, policy_version 30660 (0.0008) -[2023-10-10 13:52:51,636][76543] Updated weights for policy 0, policy_version 30703 (0.0007) -[2023-10-10 13:52:51,934][76542] Updated weights for policy 1, policy_version 30670 (0.0007) -[2023-10-10 13:52:51,997][76543] Updated weights for policy 0, policy_version 30713 (0.0008) -[2023-10-10 13:52:52,256][76362] Saving new best policy, reward=39.080! -[2023-10-10 13:52:52,297][76542] Updated weights for policy 1, policy_version 30680 (0.0008) -[2023-10-10 13:52:55,625][76543] Updated weights for policy 0, policy_version 30723 (0.0007) -[2023-10-10 13:52:55,962][76542] Updated weights for policy 1, policy_version 30690 (0.0007) -[2023-10-10 13:52:56,003][76543] Updated weights for policy 0, policy_version 30733 (0.0007) -[2023-10-10 13:52:56,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 62881792. Throughput: 0: 1814.4, 1: 1812.6. Samples: 15733276. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-10 13:52:56,076][75634] Avg episode reward: [(0, '35.150'), (1, '38.760')] -[2023-10-10 13:52:56,335][76542] Updated weights for policy 1, policy_version 30700 (0.0008) -[2023-10-10 13:52:56,377][76543] Updated weights for policy 0, policy_version 30743 (0.0008) -[2023-10-10 13:52:56,707][76542] Updated weights for policy 1, policy_version 30710 (0.0008) -[2023-10-10 13:52:57,070][76421] Saving new best policy, reward=38.760! -[2023-10-10 13:52:57,070][76542] Updated weights for policy 1, policy_version 30720 (0.0008) -[2023-10-10 13:52:59,920][76543] Updated weights for policy 0, policy_version 30753 (0.0007) -[2023-10-10 13:53:00,299][76543] Updated weights for policy 0, policy_version 30763 (0.0010) -[2023-10-10 13:53:00,678][76543] Updated weights for policy 0, policy_version 30773 (0.0007) -[2023-10-10 13:53:00,850][76542] Updated weights for policy 1, policy_version 30730 (0.0010) -[2023-10-10 13:53:01,050][76543] Updated weights for policy 0, policy_version 30783 (0.0007) -[2023-10-10 13:53:01,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 62947328. Throughput: 0: 1817.5, 1: 1809.6. Samples: 15755426. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-10 13:53:01,077][75634] Avg episode reward: [(0, '34.690'), (1, '38.860')] -[2023-10-10 13:53:01,219][76542] Updated weights for policy 1, policy_version 30740 (0.0010) -[2023-10-10 13:53:01,588][76542] Updated weights for policy 1, policy_version 30750 (0.0010) -[2023-10-10 13:53:01,658][76421] Saving new best policy, reward=38.860! -[2023-10-10 13:53:04,841][76543] Updated weights for policy 0, policy_version 30793 (0.0007) -[2023-10-10 13:53:05,209][76543] Updated weights for policy 0, policy_version 30803 (0.0007) -[2023-10-10 13:53:05,243][76542] Updated weights for policy 1, policy_version 30760 (0.0007) -[2023-10-10 13:53:05,581][76543] Updated weights for policy 0, policy_version 30813 (0.0007) -[2023-10-10 13:53:05,610][76542] Updated weights for policy 1, policy_version 30770 (0.0007) -[2023-10-10 13:53:05,988][76542] Updated weights for policy 1, policy_version 30780 (0.0008) -[2023-10-10 13:53:06,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 63045632. Throughput: 0: 1808.5, 1: 1806.8. Samples: 15765976. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-10 13:53:06,077][75634] Avg episode reward: [(0, '37.130'), (1, '34.790')] -[2023-10-10 13:53:09,395][76543] Updated weights for policy 0, policy_version 30823 (0.0010) -[2023-10-10 13:53:09,673][76542] Updated weights for policy 1, policy_version 30790 (0.0009) -[2023-10-10 13:53:09,758][76543] Updated weights for policy 0, policy_version 30833 (0.0007) -[2023-10-10 13:53:10,040][76542] Updated weights for policy 1, policy_version 30800 (0.0009) -[2023-10-10 13:53:10,129][76543] Updated weights for policy 0, policy_version 30843 (0.0009) -[2023-10-10 13:53:10,410][76542] Updated weights for policy 1, policy_version 30810 (0.0007) -[2023-10-10 13:53:11,076][75634] Fps is (10 sec: 19661.0, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 63143936. Throughput: 0: 1812.6, 1: 1810.2. Samples: 15788112. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-10 13:53:11,076][75634] Avg episode reward: [(0, '34.900'), (1, '36.910')] -[2023-10-10 13:53:13,869][76543] Updated weights for policy 0, policy_version 30853 (0.0008) -[2023-10-10 13:53:14,070][76542] Updated weights for policy 1, policy_version 30820 (0.0007) -[2023-10-10 13:53:14,237][76543] Updated weights for policy 0, policy_version 30863 (0.0008) -[2023-10-10 13:53:14,434][76542] Updated weights for policy 1, policy_version 30830 (0.0007) -[2023-10-10 13:53:14,601][76543] Updated weights for policy 0, policy_version 30873 (0.0009) -[2023-10-10 13:53:14,805][76542] Updated weights for policy 1, policy_version 30840 (0.0007) -[2023-10-10 13:53:16,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 63209472. Throughput: 0: 1804.9, 1: 1807.0. Samples: 15808340. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 13:53:16,077][75634] Avg episode reward: [(0, '35.980'), (1, '39.810')] -[2023-10-10 13:53:16,090][76421] Saving new best policy, reward=39.810! -[2023-10-10 13:53:18,423][76543] Updated weights for policy 0, policy_version 30883 (0.0010) -[2023-10-10 13:53:18,597][76542] Updated weights for policy 1, policy_version 30850 (0.0009) -[2023-10-10 13:53:18,786][76543] Updated weights for policy 0, policy_version 30893 (0.0008) -[2023-10-10 13:53:18,964][76542] Updated weights for policy 1, policy_version 30860 (0.0008) -[2023-10-10 13:53:19,159][76543] Updated weights for policy 0, policy_version 30903 (0.0010) -[2023-10-10 13:53:19,335][76542] Updated weights for policy 1, policy_version 30870 (0.0008) -[2023-10-10 13:53:19,702][76542] Updated weights for policy 1, policy_version 30880 (0.0010) -[2023-10-10 13:53:21,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 63275008. Throughput: 0: 1814.7, 1: 1813.3. Samples: 15821028. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 13:53:21,077][75634] Avg episode reward: [(0, '32.560'), (1, '38.800')] -[2023-10-10 13:53:22,856][76543] Updated weights for policy 0, policy_version 30913 (0.0010) -[2023-10-10 13:53:23,226][76543] Updated weights for policy 0, policy_version 30923 (0.0008) -[2023-10-10 13:53:23,427][76542] Updated weights for policy 1, policy_version 30890 (0.0008) -[2023-10-10 13:53:23,591][76543] Updated weights for policy 0, policy_version 30933 (0.0008) -[2023-10-10 13:53:23,789][76542] Updated weights for policy 1, policy_version 30900 (0.0008) -[2023-10-10 13:53:23,969][76543] Updated weights for policy 0, policy_version 30943 (0.0009) -[2023-10-10 13:53:24,163][76542] Updated weights for policy 1, policy_version 30910 (0.0009) -[2023-10-10 13:53:26,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 63340544. Throughput: 0: 1810.9, 1: 1810.1. Samples: 15841098. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 13:53:26,077][75634] Avg episode reward: [(0, '31.350'), (1, '32.090')] -[2023-10-10 13:53:27,751][76543] Updated weights for policy 0, policy_version 30953 (0.0007) -[2023-10-10 13:53:27,870][76542] Updated weights for policy 1, policy_version 30920 (0.0009) -[2023-10-10 13:53:28,117][76543] Updated weights for policy 0, policy_version 30963 (0.0009) -[2023-10-10 13:53:28,241][76542] Updated weights for policy 1, policy_version 30930 (0.0009) -[2023-10-10 13:53:28,491][76543] Updated weights for policy 0, policy_version 30973 (0.0007) -[2023-10-10 13:53:28,608][76542] Updated weights for policy 1, policy_version 30940 (0.0007) -[2023-10-10 13:53:31,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 63406080. Throughput: 0: 1804.2, 1: 1806.6. Samples: 15863340. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 13:53:31,077][75634] Avg episode reward: [(0, '30.900'), (1, '31.420')] -[2023-10-10 13:53:32,109][76543] Updated weights for policy 0, policy_version 30983 (0.0008) -[2023-10-10 13:53:32,423][76542] Updated weights for policy 1, policy_version 30950 (0.0008) -[2023-10-10 13:53:32,494][76543] Updated weights for policy 0, policy_version 30993 (0.0008) -[2023-10-10 13:53:32,793][76542] Updated weights for policy 1, policy_version 30960 (0.0007) -[2023-10-10 13:53:32,861][76543] Updated weights for policy 0, policy_version 31003 (0.0009) -[2023-10-10 13:53:33,160][76542] Updated weights for policy 1, policy_version 30970 (0.0010) -[2023-10-10 13:53:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 63471616. Throughput: 0: 1805.3, 1: 1808.1. Samples: 15873262. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 13:53:36,077][75634] Avg episode reward: [(0, '35.290'), (1, '32.660')] -[2023-10-10 13:53:36,444][76543] Updated weights for policy 0, policy_version 31013 (0.0009) -[2023-10-10 13:53:36,816][76543] Updated weights for policy 0, policy_version 31023 (0.0008) -[2023-10-10 13:53:36,954][76542] Updated weights for policy 1, policy_version 30980 (0.0007) -[2023-10-10 13:53:37,185][76543] Updated weights for policy 0, policy_version 31033 (0.0007) -[2023-10-10 13:53:37,322][76542] Updated weights for policy 1, policy_version 30990 (0.0007) -[2023-10-10 13:53:37,697][76542] Updated weights for policy 1, policy_version 31000 (0.0008) -[2023-10-10 13:53:40,952][76543] Updated weights for policy 0, policy_version 31043 (0.0008) -[2023-10-10 13:53:41,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 63537152. Throughput: 0: 1811.0, 1: 1805.7. Samples: 15896028. Policy #0 lag: (min: 30.0, avg: 34.2, max: 62.0) -[2023-10-10 13:53:41,076][75634] Avg episode reward: [(0, '36.210'), (1, '32.560')] -[2023-10-10 13:53:41,328][76543] Updated weights for policy 0, policy_version 31053 (0.0009) -[2023-10-10 13:53:41,466][76542] Updated weights for policy 1, policy_version 31010 (0.0009) -[2023-10-10 13:53:41,694][76543] Updated weights for policy 0, policy_version 31063 (0.0007) -[2023-10-10 13:53:41,839][76542] Updated weights for policy 1, policy_version 31020 (0.0007) -[2023-10-10 13:53:42,203][76542] Updated weights for policy 1, policy_version 31030 (0.0009) -[2023-10-10 13:53:42,575][76542] Updated weights for policy 1, policy_version 31040 (0.0011) -[2023-10-10 13:53:45,444][76543] Updated weights for policy 0, policy_version 31073 (0.0010) -[2023-10-10 13:53:45,819][76543] Updated weights for policy 0, policy_version 31083 (0.0009) -[2023-10-10 13:53:46,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 63602688. Throughput: 0: 1815.1, 1: 1810.0. Samples: 15918558. Policy #0 lag: (min: 30.0, avg: 34.2, max: 62.0) -[2023-10-10 13:53:46,077][75634] Avg episode reward: [(0, '36.250'), (1, '31.140')] -[2023-10-10 13:53:46,186][76543] Updated weights for policy 0, policy_version 31093 (0.0007) -[2023-10-10 13:53:46,344][76542] Updated weights for policy 1, policy_version 31050 (0.0008) -[2023-10-10 13:53:46,560][76543] Updated weights for policy 0, policy_version 31103 (0.0007) -[2023-10-10 13:53:46,716][76542] Updated weights for policy 1, policy_version 31060 (0.0009) -[2023-10-10 13:53:47,087][76542] Updated weights for policy 1, policy_version 31070 (0.0007) -[2023-10-10 13:53:50,271][76543] Updated weights for policy 0, policy_version 31113 (0.0007) -[2023-10-10 13:53:50,645][76543] Updated weights for policy 0, policy_version 31123 (0.0010) -[2023-10-10 13:53:50,755][76542] Updated weights for policy 1, policy_version 31080 (0.0007) -[2023-10-10 13:53:51,016][76543] Updated weights for policy 0, policy_version 31133 (0.0009) -[2023-10-10 13:53:51,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 63668224. Throughput: 0: 1805.8, 1: 1802.7. Samples: 15928356. Policy #0 lag: (min: 30.0, avg: 34.2, max: 62.0) -[2023-10-10 13:53:51,077][75634] Avg episode reward: [(0, '34.600'), (1, '32.160')] -[2023-10-10 13:53:51,123][76542] Updated weights for policy 1, policy_version 31090 (0.0010) -[2023-10-10 13:53:51,488][76542] Updated weights for policy 1, policy_version 31100 (0.0008) -[2023-10-10 13:53:54,575][76543] Updated weights for policy 0, policy_version 31143 (0.0009) -[2023-10-10 13:53:54,946][76543] Updated weights for policy 0, policy_version 31153 (0.0009) -[2023-10-10 13:53:55,188][76542] Updated weights for policy 1, policy_version 31110 (0.0008) -[2023-10-10 13:53:55,318][76543] Updated weights for policy 0, policy_version 31163 (0.0008) -[2023-10-10 13:53:55,564][76542] Updated weights for policy 1, policy_version 31120 (0.0009) -[2023-10-10 13:53:55,943][76542] Updated weights for policy 1, policy_version 31130 (0.0009) -[2023-10-10 13:53:56,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 63766528. Throughput: 0: 1815.5, 1: 1812.4. Samples: 15951368. Policy #0 lag: (min: 30.0, avg: 34.2, max: 62.0) -[2023-10-10 13:53:56,076][75634] Avg episode reward: [(0, '31.910'), (1, '33.650')] -[2023-10-10 13:53:58,939][76543] Updated weights for policy 0, policy_version 31173 (0.0008) -[2023-10-10 13:53:59,306][76543] Updated weights for policy 0, policy_version 31183 (0.0009) -[2023-10-10 13:53:59,567][76542] Updated weights for policy 1, policy_version 31140 (0.0008) -[2023-10-10 13:53:59,682][76543] Updated weights for policy 0, policy_version 31193 (0.0008) -[2023-10-10 13:53:59,933][76542] Updated weights for policy 1, policy_version 31150 (0.0007) -[2023-10-10 13:54:00,302][76542] Updated weights for policy 1, policy_version 31160 (0.0007) -[2023-10-10 13:54:01,076][75634] Fps is (10 sec: 19661.1, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 63864832. Throughput: 0: 1820.5, 1: 1800.9. Samples: 15971300. Policy #0 lag: (min: 31.0, avg: 31.9, max: 52.0) -[2023-10-10 13:54:01,076][75634] Avg episode reward: [(0, '32.370'), (1, '36.160')] -[2023-10-10 13:54:03,323][76543] Updated weights for policy 0, policy_version 31203 (0.0009) -[2023-10-10 13:54:03,696][76543] Updated weights for policy 0, policy_version 31213 (0.0008) -[2023-10-10 13:54:03,937][76542] Updated weights for policy 1, policy_version 31170 (0.0008) -[2023-10-10 13:54:04,069][76543] Updated weights for policy 0, policy_version 31223 (0.0007) -[2023-10-10 13:54:04,306][76542] Updated weights for policy 1, policy_version 31180 (0.0008) -[2023-10-10 13:54:04,670][76542] Updated weights for policy 1, policy_version 31190 (0.0007) -[2023-10-10 13:54:05,042][76542] Updated weights for policy 1, policy_version 31200 (0.0008) -[2023-10-10 13:54:06,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 63930368. Throughput: 0: 1821.1, 1: 1808.2. Samples: 15984346. Policy #0 lag: (min: 31.0, avg: 31.9, max: 52.0) -[2023-10-10 13:54:06,076][75634] Avg episode reward: [(0, '35.450'), (1, '34.860')] -[2023-10-10 13:54:07,733][76543] Updated weights for policy 0, policy_version 31233 (0.0009) -[2023-10-10 13:54:08,097][76543] Updated weights for policy 0, policy_version 31243 (0.0011) -[2023-10-10 13:54:08,466][76543] Updated weights for policy 0, policy_version 31253 (0.0009) -[2023-10-10 13:54:08,835][76543] Updated weights for policy 0, policy_version 31263 (0.0007) -[2023-10-10 13:54:08,842][76542] Updated weights for policy 1, policy_version 31210 (0.0008) -[2023-10-10 13:54:09,217][76542] Updated weights for policy 1, policy_version 31220 (0.0008) -[2023-10-10 13:54:09,587][76542] Updated weights for policy 1, policy_version 31230 (0.0008) -[2023-10-10 13:54:11,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 63995904. Throughput: 0: 1823.3, 1: 1798.8. Samples: 16004094. Policy #0 lag: (min: 31.0, avg: 31.9, max: 52.0) -[2023-10-10 13:54:11,077][75634] Avg episode reward: [(0, '32.840'), (1, '33.710')] -[2023-10-10 13:54:12,573][76543] Updated weights for policy 0, policy_version 31273 (0.0008) -[2023-10-10 13:54:12,941][76543] Updated weights for policy 0, policy_version 31283 (0.0008) -[2023-10-10 13:54:13,278][76542] Updated weights for policy 1, policy_version 31240 (0.0009) -[2023-10-10 13:54:13,316][76543] Updated weights for policy 0, policy_version 31293 (0.0009) -[2023-10-10 13:54:13,651][76542] Updated weights for policy 1, policy_version 31250 (0.0008) -[2023-10-10 13:54:14,025][76542] Updated weights for policy 1, policy_version 31260 (0.0008) -[2023-10-10 13:54:16,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 64061440. Throughput: 0: 1828.6, 1: 1803.8. Samples: 16026800. Policy #0 lag: (min: 31.0, avg: 31.9, max: 52.0) -[2023-10-10 13:54:16,076][75634] Avg episode reward: [(0, '30.760'), (1, '36.950')] -[2023-10-10 13:54:16,973][76543] Updated weights for policy 0, policy_version 31303 (0.0009) -[2023-10-10 13:54:17,345][76543] Updated weights for policy 0, policy_version 31313 (0.0008) -[2023-10-10 13:54:17,520][76542] Updated weights for policy 1, policy_version 31270 (0.0009) -[2023-10-10 13:54:17,717][76543] Updated weights for policy 0, policy_version 31323 (0.0007) -[2023-10-10 13:54:17,882][76542] Updated weights for policy 1, policy_version 31280 (0.0007) -[2023-10-10 13:54:18,248][76542] Updated weights for policy 1, policy_version 31290 (0.0010) -[2023-10-10 13:54:21,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 64126976. Throughput: 0: 1829.2, 1: 1808.3. Samples: 16036948. Policy #0 lag: (min: 31.0, avg: 31.9, max: 52.0) -[2023-10-10 13:54:21,077][75634] Avg episode reward: [(0, '33.500'), (1, '35.750')] -[2023-10-10 13:54:21,481][76543] Updated weights for policy 0, policy_version 31333 (0.0007) -[2023-10-10 13:54:21,858][76543] Updated weights for policy 0, policy_version 31343 (0.0010) -[2023-10-10 13:54:22,077][76542] Updated weights for policy 1, policy_version 31300 (0.0007) -[2023-10-10 13:54:22,230][76543] Updated weights for policy 0, policy_version 31353 (0.0008) -[2023-10-10 13:54:22,450][76542] Updated weights for policy 1, policy_version 31310 (0.0008) -[2023-10-10 13:54:22,821][76542] Updated weights for policy 1, policy_version 31320 (0.0007) -[2023-10-10 13:54:25,833][76543] Updated weights for policy 0, policy_version 31363 (0.0009) -[2023-10-10 13:54:26,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 64192512. Throughput: 0: 1824.0, 1: 1813.0. Samples: 16059690. Policy #0 lag: (min: 5.0, avg: 12.4, max: 37.0) -[2023-10-10 13:54:26,076][75634] Avg episode reward: [(0, '32.370'), (1, '35.490')] -[2023-10-10 13:54:26,209][76543] Updated weights for policy 0, policy_version 31373 (0.0007) -[2023-10-10 13:54:26,509][76542] Updated weights for policy 1, policy_version 31330 (0.0007) -[2023-10-10 13:54:26,584][76543] Updated weights for policy 0, policy_version 31383 (0.0008) -[2023-10-10 13:54:26,874][76542] Updated weights for policy 1, policy_version 31340 (0.0008) -[2023-10-10 13:54:27,241][76542] Updated weights for policy 1, policy_version 31350 (0.0009) -[2023-10-10 13:54:27,606][76542] Updated weights for policy 1, policy_version 31360 (0.0008) -[2023-10-10 13:54:30,256][76543] Updated weights for policy 0, policy_version 31393 (0.0009) -[2023-10-10 13:54:30,633][76543] Updated weights for policy 0, policy_version 31403 (0.0009) -[2023-10-10 13:54:30,999][76543] Updated weights for policy 0, policy_version 31413 (0.0008) -[2023-10-10 13:54:31,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 64258048. Throughput: 0: 1823.3, 1: 1826.3. Samples: 16082792. Policy #0 lag: (min: 5.0, avg: 12.4, max: 37.0) -[2023-10-10 13:54:31,077][75634] Avg episode reward: [(0, '32.400'), (1, '37.170')] -[2023-10-10 13:54:31,104][76542] Updated weights for policy 1, policy_version 31370 (0.0009) -[2023-10-10 13:54:31,379][76543] Updated weights for policy 0, policy_version 31423 (0.0007) -[2023-10-10 13:54:31,411][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000031424_32178176.pth... -[2023-10-10 13:54:31,444][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000029728_30441472.pth -[2023-10-10 13:54:31,475][76542] Updated weights for policy 1, policy_version 31380 (0.0007) -[2023-10-10 13:54:31,846][76542] Updated weights for policy 1, policy_version 31390 (0.0008) -[2023-10-10 13:54:31,914][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000031392_32145408.pth... -[2023-10-10 13:54:31,953][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000029696_30408704.pth -[2023-10-10 13:54:35,093][76543] Updated weights for policy 0, policy_version 31433 (0.0010) -[2023-10-10 13:54:35,428][76542] Updated weights for policy 1, policy_version 31400 (0.0008) -[2023-10-10 13:54:35,467][76543] Updated weights for policy 0, policy_version 31443 (0.0008) -[2023-10-10 13:54:35,795][76542] Updated weights for policy 1, policy_version 31410 (0.0007) -[2023-10-10 13:54:35,838][76543] Updated weights for policy 0, policy_version 31453 (0.0007) -[2023-10-10 13:54:36,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 64356352. Throughput: 0: 1825.2, 1: 1827.1. Samples: 16092708. Policy #0 lag: (min: 5.0, avg: 12.4, max: 37.0) -[2023-10-10 13:54:36,076][75634] Avg episode reward: [(0, '31.950'), (1, '34.900')] -[2023-10-10 13:54:36,164][76542] Updated weights for policy 1, policy_version 31420 (0.0010) -[2023-10-10 13:54:39,514][76543] Updated weights for policy 0, policy_version 31463 (0.0008) -[2023-10-10 13:54:39,860][76542] Updated weights for policy 1, policy_version 31430 (0.0009) -[2023-10-10 13:54:39,884][76543] Updated weights for policy 0, policy_version 31473 (0.0007) -[2023-10-10 13:54:40,233][76542] Updated weights for policy 1, policy_version 31440 (0.0008) -[2023-10-10 13:54:40,241][76543] Updated weights for policy 0, policy_version 31483 (0.0007) -[2023-10-10 13:54:40,600][76542] Updated weights for policy 1, policy_version 31450 (0.0009) -[2023-10-10 13:54:41,076][75634] Fps is (10 sec: 19661.0, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 64454656. Throughput: 0: 1820.0, 1: 1824.7. Samples: 16115376. Policy #0 lag: (min: 5.0, avg: 12.4, max: 37.0) -[2023-10-10 13:54:41,076][75634] Avg episode reward: [(0, '35.070'), (1, '35.230')] -[2023-10-10 13:54:43,958][76543] Updated weights for policy 0, policy_version 31493 (0.0008) -[2023-10-10 13:54:44,322][76543] Updated weights for policy 0, policy_version 31503 (0.0009) -[2023-10-10 13:54:44,446][76542] Updated weights for policy 1, policy_version 31460 (0.0009) -[2023-10-10 13:54:44,689][76543] Updated weights for policy 0, policy_version 31513 (0.0009) -[2023-10-10 13:54:44,819][76542] Updated weights for policy 1, policy_version 31470 (0.0009) -[2023-10-10 13:54:45,183][76542] Updated weights for policy 1, policy_version 31480 (0.0007) -[2023-10-10 13:54:46,076][75634] Fps is (10 sec: 16384.0, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 64520192. Throughput: 0: 1813.6, 1: 1829.3. Samples: 16135230. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-10 13:54:46,076][75634] Avg episode reward: [(0, '35.510'), (1, '34.100')] -[2023-10-10 13:54:48,489][76543] Updated weights for policy 0, policy_version 31523 (0.0008) -[2023-10-10 13:54:48,850][76543] Updated weights for policy 0, policy_version 31533 (0.0007) -[2023-10-10 13:54:48,871][76542] Updated weights for policy 1, policy_version 31490 (0.0008) -[2023-10-10 13:54:49,231][76543] Updated weights for policy 0, policy_version 31543 (0.0008) -[2023-10-10 13:54:49,247][76542] Updated weights for policy 1, policy_version 31500 (0.0007) -[2023-10-10 13:54:49,616][76542] Updated weights for policy 1, policy_version 31510 (0.0009) -[2023-10-10 13:54:49,986][76542] Updated weights for policy 1, policy_version 31520 (0.0010) -[2023-10-10 13:54:51,076][75634] Fps is (10 sec: 13107.0, 60 sec: 15291.7, 300 sec: 14551.2). Total num frames: 64585728. Throughput: 0: 1813.9, 1: 1827.6. Samples: 16148216. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-10 13:54:51,077][75634] Avg episode reward: [(0, '35.220'), (1, '34.100')] -[2023-10-10 13:54:52,880][76543] Updated weights for policy 0, policy_version 31553 (0.0009) -[2023-10-10 13:54:53,255][76543] Updated weights for policy 0, policy_version 31563 (0.0009) -[2023-10-10 13:54:53,622][76543] Updated weights for policy 0, policy_version 31573 (0.0008) -[2023-10-10 13:54:53,680][76542] Updated weights for policy 1, policy_version 31530 (0.0009) -[2023-10-10 13:54:53,993][76543] Updated weights for policy 0, policy_version 31583 (0.0009) -[2023-10-10 13:54:54,051][76542] Updated weights for policy 1, policy_version 31540 (0.0009) -[2023-10-10 13:54:54,420][76542] Updated weights for policy 1, policy_version 31550 (0.0010) -[2023-10-10 13:54:56,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 64651264. Throughput: 0: 1812.8, 1: 1828.2. Samples: 16167936. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-10 13:54:56,076][75634] Avg episode reward: [(0, '34.730'), (1, '33.580')] -[2023-10-10 13:54:57,817][76543] Updated weights for policy 0, policy_version 31593 (0.0007) -[2023-10-10 13:54:58,195][76543] Updated weights for policy 0, policy_version 31603 (0.0007) -[2023-10-10 13:54:58,332][76542] Updated weights for policy 1, policy_version 31560 (0.0009) -[2023-10-10 13:54:58,564][76543] Updated weights for policy 0, policy_version 31613 (0.0008) -[2023-10-10 13:54:58,710][76542] Updated weights for policy 1, policy_version 31570 (0.0007) -[2023-10-10 13:54:59,070][76542] Updated weights for policy 1, policy_version 31580 (0.0008) -[2023-10-10 13:55:01,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 64716800. Throughput: 0: 1815.0, 1: 1823.9. Samples: 16190550. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-10 13:55:01,076][75634] Avg episode reward: [(0, '32.630'), (1, '33.220')] -[2023-10-10 13:55:02,169][76543] Updated weights for policy 0, policy_version 31623 (0.0008) -[2023-10-10 13:55:02,542][76543] Updated weights for policy 0, policy_version 31633 (0.0008) -[2023-10-10 13:55:02,715][76542] Updated weights for policy 1, policy_version 31590 (0.0008) -[2023-10-10 13:55:02,906][76543] Updated weights for policy 0, policy_version 31643 (0.0008) -[2023-10-10 13:55:03,080][76542] Updated weights for policy 1, policy_version 31600 (0.0008) -[2023-10-10 13:55:03,455][76542] Updated weights for policy 1, policy_version 31610 (0.0007) -[2023-10-10 13:55:06,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 64782336. Throughput: 0: 1816.8, 1: 1821.0. Samples: 16200648. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-10 13:55:06,077][75634] Avg episode reward: [(0, '34.670'), (1, '36.580')] -[2023-10-10 13:55:06,498][76543] Updated weights for policy 0, policy_version 31653 (0.0009) -[2023-10-10 13:55:06,874][76543] Updated weights for policy 0, policy_version 31663 (0.0009) -[2023-10-10 13:55:07,181][76542] Updated weights for policy 1, policy_version 31620 (0.0008) -[2023-10-10 13:55:07,243][76543] Updated weights for policy 0, policy_version 31673 (0.0007) -[2023-10-10 13:55:07,559][76542] Updated weights for policy 1, policy_version 31630 (0.0008) -[2023-10-10 13:55:07,925][76542] Updated weights for policy 1, policy_version 31640 (0.0009) -[2023-10-10 13:55:10,959][76543] Updated weights for policy 0, policy_version 31683 (0.0008) -[2023-10-10 13:55:11,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 64847872. Throughput: 0: 1818.6, 1: 1816.2. Samples: 16223256. Policy #0 lag: (min: 31.0, avg: 32.6, max: 58.0) -[2023-10-10 13:55:11,077][75634] Avg episode reward: [(0, '34.580'), (1, '33.350')] -[2023-10-10 13:55:11,339][76543] Updated weights for policy 0, policy_version 31693 (0.0008) -[2023-10-10 13:55:11,550][76542] Updated weights for policy 1, policy_version 31650 (0.0010) -[2023-10-10 13:55:11,702][76543] Updated weights for policy 0, policy_version 31703 (0.0007) -[2023-10-10 13:55:11,922][76542] Updated weights for policy 1, policy_version 31660 (0.0009) -[2023-10-10 13:55:12,292][76542] Updated weights for policy 1, policy_version 31670 (0.0007) -[2023-10-10 13:55:12,653][76542] Updated weights for policy 1, policy_version 31680 (0.0010) -[2023-10-10 13:55:15,367][76543] Updated weights for policy 0, policy_version 31713 (0.0007) -[2023-10-10 13:55:15,736][76543] Updated weights for policy 0, policy_version 31723 (0.0008) -[2023-10-10 13:55:16,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 64913408. Throughput: 0: 1818.8, 1: 1810.0. Samples: 16246090. Policy #0 lag: (min: 31.0, avg: 32.6, max: 58.0) -[2023-10-10 13:55:16,076][75634] Avg episode reward: [(0, '33.860'), (1, '33.550')] -[2023-10-10 13:55:16,104][76543] Updated weights for policy 0, policy_version 31733 (0.0010) -[2023-10-10 13:55:16,322][76542] Updated weights for policy 1, policy_version 31690 (0.0011) -[2023-10-10 13:55:16,465][76543] Updated weights for policy 0, policy_version 31743 (0.0007) -[2023-10-10 13:55:16,698][76542] Updated weights for policy 1, policy_version 31700 (0.0009) -[2023-10-10 13:55:17,057][76542] Updated weights for policy 1, policy_version 31710 (0.0011) -[2023-10-10 13:55:20,085][76543] Updated weights for policy 0, policy_version 31753 (0.0008) -[2023-10-10 13:55:20,463][76543] Updated weights for policy 0, policy_version 31763 (0.0008) -[2023-10-10 13:55:20,752][76542] Updated weights for policy 1, policy_version 31720 (0.0009) -[2023-10-10 13:55:20,831][76543] Updated weights for policy 0, policy_version 31773 (0.0009) -[2023-10-10 13:55:21,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 65011712. Throughput: 0: 1820.0, 1: 1811.7. Samples: 16256136. Policy #0 lag: (min: 31.0, avg: 32.6, max: 58.0) -[2023-10-10 13:55:21,076][75634] Avg episode reward: [(0, '34.490'), (1, '29.680')] -[2023-10-10 13:55:21,117][76542] Updated weights for policy 1, policy_version 31730 (0.0007) -[2023-10-10 13:55:21,484][76542] Updated weights for policy 1, policy_version 31740 (0.0007) -[2023-10-10 13:55:24,446][76543] Updated weights for policy 0, policy_version 31783 (0.0010) -[2023-10-10 13:55:24,824][76543] Updated weights for policy 0, policy_version 31793 (0.0011) -[2023-10-10 13:55:25,190][76543] Updated weights for policy 0, policy_version 31803 (0.0009) -[2023-10-10 13:55:25,274][76542] Updated weights for policy 1, policy_version 31750 (0.0007) -[2023-10-10 13:55:25,638][76542] Updated weights for policy 1, policy_version 31760 (0.0007) -[2023-10-10 13:55:26,008][76542] Updated weights for policy 1, policy_version 31770 (0.0007) -[2023-10-10 13:55:26,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 65077248. Throughput: 0: 1819.0, 1: 1805.1. Samples: 16278458. Policy #0 lag: (min: 31.0, avg: 32.6, max: 58.0) -[2023-10-10 13:55:26,077][75634] Avg episode reward: [(0, '33.160'), (1, '29.790')] -[2023-10-10 13:55:28,962][76543] Updated weights for policy 0, policy_version 31813 (0.0008) -[2023-10-10 13:55:29,334][76543] Updated weights for policy 0, policy_version 31823 (0.0010) -[2023-10-10 13:55:29,712][76543] Updated weights for policy 0, policy_version 31833 (0.0009) -[2023-10-10 13:55:29,814][76542] Updated weights for policy 1, policy_version 31780 (0.0010) -[2023-10-10 13:55:30,179][76542] Updated weights for policy 1, policy_version 31790 (0.0008) -[2023-10-10 13:55:30,546][76542] Updated weights for policy 1, policy_version 31800 (0.0010) -[2023-10-10 13:55:31,076][75634] Fps is (10 sec: 16383.9, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 65175552. Throughput: 0: 1818.9, 1: 1803.9. Samples: 16298258. Policy #0 lag: (min: 24.0, avg: 48.5, max: 56.0) -[2023-10-10 13:55:31,077][75634] Avg episode reward: [(0, '35.340'), (1, '30.090')] -[2023-10-10 13:55:33,357][76543] Updated weights for policy 0, policy_version 31843 (0.0009) -[2023-10-10 13:55:33,722][76543] Updated weights for policy 0, policy_version 31853 (0.0009) -[2023-10-10 13:55:34,093][76543] Updated weights for policy 0, policy_version 31863 (0.0008) -[2023-10-10 13:55:34,245][76542] Updated weights for policy 1, policy_version 31810 (0.0010) -[2023-10-10 13:55:34,608][76542] Updated weights for policy 1, policy_version 31820 (0.0009) -[2023-10-10 13:55:34,979][76542] Updated weights for policy 1, policy_version 31830 (0.0008) -[2023-10-10 13:55:35,342][76542] Updated weights for policy 1, policy_version 31840 (0.0007) -[2023-10-10 13:55:36,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 65241088. Throughput: 0: 1821.7, 1: 1801.0. Samples: 16311240. Policy #0 lag: (min: 24.0, avg: 48.5, max: 56.0) -[2023-10-10 13:55:36,077][75634] Avg episode reward: [(0, '36.590'), (1, '26.560')] -[2023-10-10 13:55:37,720][76543] Updated weights for policy 0, policy_version 31873 (0.0008) -[2023-10-10 13:55:38,080][76543] Updated weights for policy 0, policy_version 31883 (0.0008) -[2023-10-10 13:55:38,454][76543] Updated weights for policy 0, policy_version 31893 (0.0008) -[2023-10-10 13:55:38,819][76543] Updated weights for policy 0, policy_version 31903 (0.0007) -[2023-10-10 13:55:38,863][76542] Updated weights for policy 1, policy_version 31850 (0.0008) -[2023-10-10 13:55:39,224][76542] Updated weights for policy 1, policy_version 31860 (0.0008) -[2023-10-10 13:55:39,593][76542] Updated weights for policy 1, policy_version 31870 (0.0010) -[2023-10-10 13:55:41,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 65306624. Throughput: 0: 1823.6, 1: 1808.9. Samples: 16331400. Policy #0 lag: (min: 24.0, avg: 48.5, max: 56.0) -[2023-10-10 13:55:41,076][75634] Avg episode reward: [(0, '34.730'), (1, '29.490')] -[2023-10-10 13:55:42,494][76543] Updated weights for policy 0, policy_version 31913 (0.0009) -[2023-10-10 13:55:42,865][76543] Updated weights for policy 0, policy_version 31923 (0.0009) -[2023-10-10 13:55:43,223][76542] Updated weights for policy 1, policy_version 31880 (0.0009) -[2023-10-10 13:55:43,234][76543] Updated weights for policy 0, policy_version 31933 (0.0008) -[2023-10-10 13:55:43,592][76542] Updated weights for policy 1, policy_version 31890 (0.0009) -[2023-10-10 13:55:43,965][76542] Updated weights for policy 1, policy_version 31900 (0.0007) -[2023-10-10 13:55:46,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 65372160. Throughput: 0: 1819.5, 1: 1810.6. Samples: 16353906. Policy #0 lag: (min: 24.0, avg: 48.5, max: 56.0) -[2023-10-10 13:55:46,077][75634] Avg episode reward: [(0, '33.660'), (1, '32.960')] -[2023-10-10 13:55:46,950][76543] Updated weights for policy 0, policy_version 31943 (0.0009) -[2023-10-10 13:55:47,315][76543] Updated weights for policy 0, policy_version 31953 (0.0008) -[2023-10-10 13:55:47,667][76542] Updated weights for policy 1, policy_version 31910 (0.0008) -[2023-10-10 13:55:47,691][76543] Updated weights for policy 0, policy_version 31963 (0.0008) -[2023-10-10 13:55:48,041][76542] Updated weights for policy 1, policy_version 31920 (0.0009) -[2023-10-10 13:55:48,407][76542] Updated weights for policy 1, policy_version 31930 (0.0009) -[2023-10-10 13:55:51,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 65437696. Throughput: 0: 1819.8, 1: 1809.1. Samples: 16363948. Policy #0 lag: (min: 24.0, avg: 48.5, max: 56.0) -[2023-10-10 13:55:51,077][75634] Avg episode reward: [(0, '33.170'), (1, '35.570')] -[2023-10-10 13:55:51,294][76543] Updated weights for policy 0, policy_version 31973 (0.0008) -[2023-10-10 13:55:51,662][76543] Updated weights for policy 0, policy_version 31983 (0.0007) -[2023-10-10 13:55:52,031][76543] Updated weights for policy 0, policy_version 31993 (0.0007) -[2023-10-10 13:55:52,051][76542] Updated weights for policy 1, policy_version 31940 (0.0008) -[2023-10-10 13:55:52,413][76542] Updated weights for policy 1, policy_version 31950 (0.0007) -[2023-10-10 13:55:52,779][76542] Updated weights for policy 1, policy_version 31960 (0.0007) -[2023-10-10 13:55:55,649][76543] Updated weights for policy 0, policy_version 32003 (0.0007) -[2023-10-10 13:55:56,014][76543] Updated weights for policy 0, policy_version 32013 (0.0007) -[2023-10-10 13:55:56,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 65503232. Throughput: 0: 1826.5, 1: 1819.0. Samples: 16387306. Policy #0 lag: (min: 18.0, avg: 44.6, max: 48.0) -[2023-10-10 13:55:56,077][75634] Avg episode reward: [(0, '30.390'), (1, '35.930')] -[2023-10-10 13:55:56,377][76543] Updated weights for policy 0, policy_version 32023 (0.0007) -[2023-10-10 13:55:56,467][76542] Updated weights for policy 1, policy_version 31970 (0.0007) -[2023-10-10 13:55:56,839][76542] Updated weights for policy 1, policy_version 31980 (0.0010) -[2023-10-10 13:55:57,207][76542] Updated weights for policy 1, policy_version 31990 (0.0010) -[2023-10-10 13:55:57,573][76542] Updated weights for policy 1, policy_version 32000 (0.0011) -[2023-10-10 13:56:00,093][76543] Updated weights for policy 0, policy_version 32033 (0.0008) -[2023-10-10 13:56:00,470][76543] Updated weights for policy 0, policy_version 32043 (0.0010) -[2023-10-10 13:56:00,839][76543] Updated weights for policy 0, policy_version 32053 (0.0011) -[2023-10-10 13:56:01,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 65568768. Throughput: 0: 1824.1, 1: 1816.0. Samples: 16409894. Policy #0 lag: (min: 18.0, avg: 44.6, max: 48.0) -[2023-10-10 13:56:01,076][75634] Avg episode reward: [(0, '30.200'), (1, '37.090')] -[2023-10-10 13:56:01,214][76543] Updated weights for policy 0, policy_version 32063 (0.0008) -[2023-10-10 13:56:01,381][76542] Updated weights for policy 1, policy_version 32010 (0.0007) -[2023-10-10 13:56:01,741][76542] Updated weights for policy 1, policy_version 32020 (0.0009) -[2023-10-10 13:56:02,107][76542] Updated weights for policy 1, policy_version 32030 (0.0009) -[2023-10-10 13:56:05,094][76543] Updated weights for policy 0, policy_version 32073 (0.0008) -[2023-10-10 13:56:05,465][76543] Updated weights for policy 0, policy_version 32083 (0.0009) -[2023-10-10 13:56:05,659][76542] Updated weights for policy 1, policy_version 32040 (0.0009) -[2023-10-10 13:56:05,836][76543] Updated weights for policy 0, policy_version 32093 (0.0008) -[2023-10-10 13:56:06,020][76542] Updated weights for policy 1, policy_version 32050 (0.0009) -[2023-10-10 13:56:06,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 65667072. Throughput: 0: 1828.8, 1: 1818.1. Samples: 16420250. Policy #0 lag: (min: 18.0, avg: 44.6, max: 48.0) -[2023-10-10 13:56:06,077][75634] Avg episode reward: [(0, '35.950'), (1, '36.390')] -[2023-10-10 13:56:06,381][76542] Updated weights for policy 1, policy_version 32060 (0.0009) -[2023-10-10 13:56:09,706][76543] Updated weights for policy 0, policy_version 32103 (0.0008) -[2023-10-10 13:56:10,089][76542] Updated weights for policy 1, policy_version 32070 (0.0010) -[2023-10-10 13:56:10,090][76543] Updated weights for policy 0, policy_version 32113 (0.0010) -[2023-10-10 13:56:10,454][76542] Updated weights for policy 1, policy_version 32080 (0.0009) -[2023-10-10 13:56:10,458][76543] Updated weights for policy 0, policy_version 32123 (0.0010) -[2023-10-10 13:56:10,828][76542] Updated weights for policy 1, policy_version 32090 (0.0008) -[2023-10-10 13:56:11,076][75634] Fps is (10 sec: 19660.8, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 65765376. Throughput: 0: 1827.9, 1: 1826.9. Samples: 16442924. Policy #0 lag: (min: 18.0, avg: 44.6, max: 48.0) -[2023-10-10 13:56:11,076][75634] Avg episode reward: [(0, '34.320'), (1, '38.570')] -[2023-10-10 13:56:14,054][76543] Updated weights for policy 0, policy_version 32133 (0.0009) -[2023-10-10 13:56:14,435][76543] Updated weights for policy 0, policy_version 32143 (0.0007) -[2023-10-10 13:56:14,461][76542] Updated weights for policy 1, policy_version 32100 (0.0008) -[2023-10-10 13:56:14,804][76543] Updated weights for policy 0, policy_version 32153 (0.0008) -[2023-10-10 13:56:14,839][76542] Updated weights for policy 1, policy_version 32110 (0.0010) -[2023-10-10 13:56:15,203][76542] Updated weights for policy 1, policy_version 32120 (0.0007) -[2023-10-10 13:56:16,076][75634] Fps is (10 sec: 16384.2, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 65830912. Throughput: 0: 1821.8, 1: 1827.4. Samples: 16462472. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-10 13:56:16,076][75634] Avg episode reward: [(0, '33.930'), (1, '37.590')] -[2023-10-10 13:56:18,446][76543] Updated weights for policy 0, policy_version 32163 (0.0009) -[2023-10-10 13:56:18,820][76543] Updated weights for policy 0, policy_version 32173 (0.0008) -[2023-10-10 13:56:18,959][76542] Updated weights for policy 1, policy_version 32130 (0.0009) -[2023-10-10 13:56:19,197][76543] Updated weights for policy 0, policy_version 32183 (0.0007) -[2023-10-10 13:56:19,325][76542] Updated weights for policy 1, policy_version 32140 (0.0008) -[2023-10-10 13:56:19,693][76542] Updated weights for policy 1, policy_version 32150 (0.0010) -[2023-10-10 13:56:20,062][76542] Updated weights for policy 1, policy_version 32160 (0.0009) -[2023-10-10 13:56:21,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 65896448. Throughput: 0: 1814.7, 1: 1832.4. Samples: 16475356. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-10 13:56:21,076][75634] Avg episode reward: [(0, '36.520'), (1, '39.330')] -[2023-10-10 13:56:23,082][76543] Updated weights for policy 0, policy_version 32193 (0.0008) -[2023-10-10 13:56:23,458][76543] Updated weights for policy 0, policy_version 32203 (0.0009) -[2023-10-10 13:56:23,679][76542] Updated weights for policy 1, policy_version 32170 (0.0007) -[2023-10-10 13:56:23,831][76543] Updated weights for policy 0, policy_version 32213 (0.0008) -[2023-10-10 13:56:24,056][76542] Updated weights for policy 1, policy_version 32180 (0.0007) -[2023-10-10 13:56:24,204][76543] Updated weights for policy 0, policy_version 32223 (0.0008) -[2023-10-10 13:56:24,415][76542] Updated weights for policy 1, policy_version 32190 (0.0007) -[2023-10-10 13:56:26,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 65961984. Throughput: 0: 1807.6, 1: 1828.7. Samples: 16495034. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-10 13:56:26,077][75634] Avg episode reward: [(0, '33.780'), (1, '35.440')] -[2023-10-10 13:56:27,924][76543] Updated weights for policy 0, policy_version 32233 (0.0007) -[2023-10-10 13:56:28,297][76543] Updated weights for policy 0, policy_version 32243 (0.0007) -[2023-10-10 13:56:28,347][76542] Updated weights for policy 1, policy_version 32200 (0.0008) -[2023-10-10 13:56:28,667][76543] Updated weights for policy 0, policy_version 32253 (0.0009) -[2023-10-10 13:56:28,720][76542] Updated weights for policy 1, policy_version 32210 (0.0008) -[2023-10-10 13:56:29,093][76542] Updated weights for policy 1, policy_version 32220 (0.0008) -[2023-10-10 13:56:31,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 66027520. Throughput: 0: 1808.9, 1: 1821.3. Samples: 16517266. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-10 13:56:31,077][75634] Avg episode reward: [(0, '33.660'), (1, '35.090')] -[2023-10-10 13:56:31,085][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000032224_32997376.pth... -[2023-10-10 13:56:31,085][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000032256_33030144.pth... -[2023-10-10 13:56:31,115][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000030528_31260672.pth -[2023-10-10 13:56:31,122][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000030560_31293440.pth -[2023-10-10 13:56:32,220][76543] Updated weights for policy 0, policy_version 32263 (0.0009) -[2023-10-10 13:56:32,603][76543] Updated weights for policy 0, policy_version 32273 (0.0010) -[2023-10-10 13:56:32,827][76542] Updated weights for policy 1, policy_version 32230 (0.0008) -[2023-10-10 13:56:32,964][76543] Updated weights for policy 0, policy_version 32283 (0.0008) -[2023-10-10 13:56:33,197][76542] Updated weights for policy 1, policy_version 32240 (0.0008) -[2023-10-10 13:56:33,563][76542] Updated weights for policy 1, policy_version 32250 (0.0009) -[2023-10-10 13:56:36,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 66093056. Throughput: 0: 1807.2, 1: 1824.4. Samples: 16527368. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-10 13:56:36,076][75634] Avg episode reward: [(0, '33.760'), (1, '35.610')] -[2023-10-10 13:56:36,546][76543] Updated weights for policy 0, policy_version 32293 (0.0008) -[2023-10-10 13:56:36,918][76543] Updated weights for policy 0, policy_version 32303 (0.0007) -[2023-10-10 13:56:37,289][76543] Updated weights for policy 0, policy_version 32313 (0.0008) -[2023-10-10 13:56:37,355][76542] Updated weights for policy 1, policy_version 32260 (0.0009) -[2023-10-10 13:56:37,724][76542] Updated weights for policy 1, policy_version 32270 (0.0009) -[2023-10-10 13:56:38,087][76542] Updated weights for policy 1, policy_version 32280 (0.0009) -[2023-10-10 13:56:41,069][76543] Updated weights for policy 0, policy_version 32323 (0.0007) -[2023-10-10 13:56:41,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 66158592. Throughput: 0: 1807.8, 1: 1809.4. Samples: 16550082. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:56:41,076][75634] Avg episode reward: [(0, '34.680'), (1, '31.510')] -[2023-10-10 13:56:41,437][76543] Updated weights for policy 0, policy_version 32333 (0.0008) -[2023-10-10 13:56:41,806][76543] Updated weights for policy 0, policy_version 32343 (0.0008) -[2023-10-10 13:56:41,988][76542] Updated weights for policy 1, policy_version 32290 (0.0008) -[2023-10-10 13:56:42,350][76542] Updated weights for policy 1, policy_version 32300 (0.0007) -[2023-10-10 13:56:42,711][76542] Updated weights for policy 1, policy_version 32310 (0.0008) -[2023-10-10 13:56:43,074][76542] Updated weights for policy 1, policy_version 32320 (0.0007) -[2023-10-10 13:56:45,592][76543] Updated weights for policy 0, policy_version 32353 (0.0008) -[2023-10-10 13:56:45,958][76543] Updated weights for policy 0, policy_version 32363 (0.0008) -[2023-10-10 13:56:46,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 66224128. Throughput: 0: 1806.1, 1: 1804.6. Samples: 16572376. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:56:46,077][75634] Avg episode reward: [(0, '35.870'), (1, '28.390')] -[2023-10-10 13:56:46,323][76543] Updated weights for policy 0, policy_version 32373 (0.0011) -[2023-10-10 13:56:46,702][76543] Updated weights for policy 0, policy_version 32383 (0.0007) -[2023-10-10 13:56:46,832][76542] Updated weights for policy 1, policy_version 32330 (0.0009) -[2023-10-10 13:56:47,205][76542] Updated weights for policy 1, policy_version 32340 (0.0010) -[2023-10-10 13:56:47,568][76542] Updated weights for policy 1, policy_version 32350 (0.0008) -[2023-10-10 13:56:50,430][76543] Updated weights for policy 0, policy_version 32393 (0.0009) -[2023-10-10 13:56:50,795][76543] Updated weights for policy 0, policy_version 32403 (0.0008) -[2023-10-10 13:56:51,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 66289664. Throughput: 0: 1799.8, 1: 1801.5. Samples: 16582308. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:56:51,076][75634] Avg episode reward: [(0, '37.020'), (1, '30.450')] -[2023-10-10 13:56:51,123][76542] Updated weights for policy 1, policy_version 32360 (0.0009) -[2023-10-10 13:56:51,165][76543] Updated weights for policy 0, policy_version 32413 (0.0007) -[2023-10-10 13:56:51,489][76542] Updated weights for policy 1, policy_version 32370 (0.0008) -[2023-10-10 13:56:51,869][76542] Updated weights for policy 1, policy_version 32380 (0.0009) -[2023-10-10 13:56:54,811][76543] Updated weights for policy 0, policy_version 32423 (0.0008) -[2023-10-10 13:56:55,180][76543] Updated weights for policy 0, policy_version 32433 (0.0008) -[2023-10-10 13:56:55,466][76542] Updated weights for policy 1, policy_version 32390 (0.0007) -[2023-10-10 13:56:55,551][76543] Updated weights for policy 0, policy_version 32443 (0.0009) -[2023-10-10 13:56:55,829][76542] Updated weights for policy 1, policy_version 32400 (0.0008) -[2023-10-10 13:56:56,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 66387968. Throughput: 0: 1806.0, 1: 1798.2. Samples: 16605110. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:56:56,076][75634] Avg episode reward: [(0, '37.410'), (1, '33.790')] -[2023-10-10 13:56:56,199][76542] Updated weights for policy 1, policy_version 32410 (0.0008) -[2023-10-10 13:56:59,091][76543] Updated weights for policy 0, policy_version 32453 (0.0008) -[2023-10-10 13:56:59,461][76543] Updated weights for policy 0, policy_version 32463 (0.0009) -[2023-10-10 13:56:59,841][76543] Updated weights for policy 0, policy_version 32473 (0.0008) -[2023-10-10 13:56:59,896][76542] Updated weights for policy 1, policy_version 32420 (0.0008) -[2023-10-10 13:57:00,259][76542] Updated weights for policy 1, policy_version 32430 (0.0008) -[2023-10-10 13:57:00,615][76542] Updated weights for policy 1, policy_version 32440 (0.0008) -[2023-10-10 13:57:01,076][75634] Fps is (10 sec: 19660.5, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 66486272. Throughput: 0: 1809.1, 1: 1804.6. Samples: 16625088. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 13:57:01,076][75634] Avg episode reward: [(0, '33.880'), (1, '34.830')] -[2023-10-10 13:57:03,521][76543] Updated weights for policy 0, policy_version 32483 (0.0009) -[2023-10-10 13:57:03,903][76543] Updated weights for policy 0, policy_version 32493 (0.0007) -[2023-10-10 13:57:04,173][76542] Updated weights for policy 1, policy_version 32450 (0.0008) -[2023-10-10 13:57:04,273][76543] Updated weights for policy 0, policy_version 32503 (0.0007) -[2023-10-10 13:57:04,540][76542] Updated weights for policy 1, policy_version 32460 (0.0008) -[2023-10-10 13:57:04,897][76542] Updated weights for policy 1, policy_version 32470 (0.0007) -[2023-10-10 13:57:05,270][76542] Updated weights for policy 1, policy_version 32480 (0.0010) -[2023-10-10 13:57:06,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 66551808. Throughput: 0: 1818.1, 1: 1800.7. Samples: 16638204. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 13:57:06,077][75634] Avg episode reward: [(0, '31.900'), (1, '34.270')] -[2023-10-10 13:57:07,838][76543] Updated weights for policy 0, policy_version 32513 (0.0008) -[2023-10-10 13:57:08,201][76543] Updated weights for policy 0, policy_version 32523 (0.0010) -[2023-10-10 13:57:08,573][76543] Updated weights for policy 0, policy_version 32533 (0.0010) -[2023-10-10 13:57:08,940][76543] Updated weights for policy 0, policy_version 32543 (0.0009) -[2023-10-10 13:57:08,962][76542] Updated weights for policy 1, policy_version 32490 (0.0007) -[2023-10-10 13:57:09,332][76542] Updated weights for policy 1, policy_version 32500 (0.0010) -[2023-10-10 13:57:09,693][76542] Updated weights for policy 1, policy_version 32510 (0.0007) -[2023-10-10 13:57:11,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 66617344. Throughput: 0: 1819.9, 1: 1804.8. Samples: 16658144. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 13:57:11,077][75634] Avg episode reward: [(0, '32.030'), (1, '35.030')] -[2023-10-10 13:57:12,717][76543] Updated weights for policy 0, policy_version 32553 (0.0008) -[2023-10-10 13:57:13,088][76543] Updated weights for policy 0, policy_version 32563 (0.0009) -[2023-10-10 13:57:13,449][76542] Updated weights for policy 1, policy_version 32520 (0.0008) -[2023-10-10 13:57:13,460][76543] Updated weights for policy 0, policy_version 32573 (0.0008) -[2023-10-10 13:57:13,830][76542] Updated weights for policy 1, policy_version 32530 (0.0008) -[2023-10-10 13:57:14,201][76542] Updated weights for policy 1, policy_version 32540 (0.0008) -[2023-10-10 13:57:16,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 66682880. Throughput: 0: 1821.5, 1: 1809.4. Samples: 16680654. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 13:57:16,076][75634] Avg episode reward: [(0, '34.020'), (1, '37.380')] -[2023-10-10 13:57:17,223][76543] Updated weights for policy 0, policy_version 32583 (0.0008) -[2023-10-10 13:57:17,592][76543] Updated weights for policy 0, policy_version 32593 (0.0007) -[2023-10-10 13:57:17,967][76543] Updated weights for policy 0, policy_version 32603 (0.0009) -[2023-10-10 13:57:17,972][76542] Updated weights for policy 1, policy_version 32550 (0.0011) -[2023-10-10 13:57:18,342][76542] Updated weights for policy 1, policy_version 32560 (0.0009) -[2023-10-10 13:57:18,703][76542] Updated weights for policy 1, policy_version 32570 (0.0008) -[2023-10-10 13:57:21,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 66748416. Throughput: 0: 1820.6, 1: 1816.2. Samples: 16691024. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 13:57:21,077][75634] Avg episode reward: [(0, '34.250'), (1, '35.570')] -[2023-10-10 13:57:21,854][76543] Updated weights for policy 0, policy_version 32613 (0.0011) -[2023-10-10 13:57:22,242][76543] Updated weights for policy 0, policy_version 32623 (0.0009) -[2023-10-10 13:57:22,451][76542] Updated weights for policy 1, policy_version 32580 (0.0008) -[2023-10-10 13:57:22,612][76543] Updated weights for policy 0, policy_version 32633 (0.0007) -[2023-10-10 13:57:22,827][76542] Updated weights for policy 1, policy_version 32590 (0.0007) -[2023-10-10 13:57:23,191][76542] Updated weights for policy 1, policy_version 32600 (0.0009) -[2023-10-10 13:57:26,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 66813952. Throughput: 0: 1812.9, 1: 1816.8. Samples: 16713418. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:57:26,077][75634] Avg episode reward: [(0, '33.430'), (1, '33.600')] -[2023-10-10 13:57:26,323][76543] Updated weights for policy 0, policy_version 32643 (0.0009) -[2023-10-10 13:57:26,697][76543] Updated weights for policy 0, policy_version 32653 (0.0007) -[2023-10-10 13:57:26,859][76542] Updated weights for policy 1, policy_version 32610 (0.0008) -[2023-10-10 13:57:27,061][76543] Updated weights for policy 0, policy_version 32663 (0.0007) -[2023-10-10 13:57:27,232][76542] Updated weights for policy 1, policy_version 32620 (0.0008) -[2023-10-10 13:57:27,593][76542] Updated weights for policy 1, policy_version 32630 (0.0008) -[2023-10-10 13:57:27,965][76542] Updated weights for policy 1, policy_version 32640 (0.0007) -[2023-10-10 13:57:30,721][76543] Updated weights for policy 0, policy_version 32673 (0.0008) -[2023-10-10 13:57:31,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 66879488. Throughput: 0: 1816.7, 1: 1823.0. Samples: 16736166. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:57:31,077][75634] Avg episode reward: [(0, '35.060'), (1, '34.310')] -[2023-10-10 13:57:31,086][76543] Updated weights for policy 0, policy_version 32683 (0.0011) -[2023-10-10 13:57:31,464][76543] Updated weights for policy 0, policy_version 32693 (0.0009) -[2023-10-10 13:57:31,655][76542] Updated weights for policy 1, policy_version 32650 (0.0007) -[2023-10-10 13:57:31,837][76543] Updated weights for policy 0, policy_version 32703 (0.0008) -[2023-10-10 13:57:32,020][76542] Updated weights for policy 1, policy_version 32660 (0.0007) -[2023-10-10 13:57:32,403][76542] Updated weights for policy 1, policy_version 32670 (0.0007) -[2023-10-10 13:57:35,463][76543] Updated weights for policy 0, policy_version 32713 (0.0007) -[2023-10-10 13:57:35,832][76543] Updated weights for policy 0, policy_version 32723 (0.0010) -[2023-10-10 13:57:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 66945024. Throughput: 0: 1815.8, 1: 1822.7. Samples: 16746038. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:57:36,077][75634] Avg episode reward: [(0, '32.320'), (1, '34.160')] -[2023-10-10 13:57:36,106][76542] Updated weights for policy 1, policy_version 32680 (0.0009) -[2023-10-10 13:57:36,203][76543] Updated weights for policy 0, policy_version 32733 (0.0007) -[2023-10-10 13:57:36,465][76542] Updated weights for policy 1, policy_version 32690 (0.0008) -[2023-10-10 13:57:36,834][76542] Updated weights for policy 1, policy_version 32700 (0.0009) -[2023-10-10 13:57:40,033][76543] Updated weights for policy 0, policy_version 32743 (0.0008) -[2023-10-10 13:57:40,405][76543] Updated weights for policy 0, policy_version 32753 (0.0008) -[2023-10-10 13:57:40,649][76542] Updated weights for policy 1, policy_version 32710 (0.0009) -[2023-10-10 13:57:40,772][76543] Updated weights for policy 0, policy_version 32763 (0.0009) -[2023-10-10 13:57:41,020][76542] Updated weights for policy 1, policy_version 32720 (0.0008) -[2023-10-10 13:57:41,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 67043328. Throughput: 0: 1820.4, 1: 1817.1. Samples: 16768800. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:57:41,077][75634] Avg episode reward: [(0, '32.240'), (1, '33.190')] -[2023-10-10 13:57:41,392][76542] Updated weights for policy 1, policy_version 32730 (0.0010) -[2023-10-10 13:57:44,557][76543] Updated weights for policy 0, policy_version 32773 (0.0008) -[2023-10-10 13:57:44,931][76543] Updated weights for policy 0, policy_version 32783 (0.0007) -[2023-10-10 13:57:45,270][76542] Updated weights for policy 1, policy_version 32740 (0.0008) -[2023-10-10 13:57:45,294][76543] Updated weights for policy 0, policy_version 32793 (0.0007) -[2023-10-10 13:57:45,636][76542] Updated weights for policy 1, policy_version 32750 (0.0007) -[2023-10-10 13:57:46,020][76542] Updated weights for policy 1, policy_version 32760 (0.0008) -[2023-10-10 13:57:46,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 67108864. Throughput: 0: 1825.6, 1: 1825.9. Samples: 16789404. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:57:46,077][75634] Avg episode reward: [(0, '34.780'), (1, '34.080')] -[2023-10-10 13:57:48,956][76543] Updated weights for policy 0, policy_version 32803 (0.0007) -[2023-10-10 13:57:49,339][76543] Updated weights for policy 0, policy_version 32813 (0.0008) -[2023-10-10 13:57:49,699][76543] Updated weights for policy 0, policy_version 32823 (0.0007) -[2023-10-10 13:57:49,774][76542] Updated weights for policy 1, policy_version 32770 (0.0010) -[2023-10-10 13:57:50,151][76542] Updated weights for policy 1, policy_version 32780 (0.0008) -[2023-10-10 13:57:50,520][76542] Updated weights for policy 1, policy_version 32790 (0.0009) -[2023-10-10 13:57:50,878][76542] Updated weights for policy 1, policy_version 32800 (0.0009) -[2023-10-10 13:57:51,076][75634] Fps is (10 sec: 16384.4, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 67207168. Throughput: 0: 1807.9, 1: 1805.5. Samples: 16800808. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:57:51,076][75634] Avg episode reward: [(0, '35.120'), (1, '29.040')] -[2023-10-10 13:57:53,238][76543] Updated weights for policy 0, policy_version 32833 (0.0008) -[2023-10-10 13:57:53,610][76543] Updated weights for policy 0, policy_version 32843 (0.0008) -[2023-10-10 13:57:53,978][76543] Updated weights for policy 0, policy_version 32853 (0.0009) -[2023-10-10 13:57:54,347][76543] Updated weights for policy 0, policy_version 32863 (0.0007) -[2023-10-10 13:57:54,397][76542] Updated weights for policy 1, policy_version 32810 (0.0007) -[2023-10-10 13:57:54,762][76542] Updated weights for policy 1, policy_version 32820 (0.0009) -[2023-10-10 13:57:55,139][76542] Updated weights for policy 1, policy_version 32830 (0.0010) -[2023-10-10 13:57:56,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 67272704. Throughput: 0: 1820.0, 1: 1819.1. Samples: 16821900. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:57:56,076][75634] Avg episode reward: [(0, '34.970'), (1, '31.070')] -[2023-10-10 13:57:58,136][76543] Updated weights for policy 0, policy_version 32873 (0.0010) -[2023-10-10 13:57:58,503][76543] Updated weights for policy 0, policy_version 32883 (0.0007) -[2023-10-10 13:57:58,872][76543] Updated weights for policy 0, policy_version 32893 (0.0008) -[2023-10-10 13:57:58,999][76542] Updated weights for policy 1, policy_version 32840 (0.0008) -[2023-10-10 13:57:59,377][76542] Updated weights for policy 1, policy_version 32850 (0.0010) -[2023-10-10 13:57:59,739][76542] Updated weights for policy 1, policy_version 32860 (0.0009) -[2023-10-10 13:58:01,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 67338240. Throughput: 0: 1816.8, 1: 1808.1. Samples: 16843774. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:58:01,076][75634] Avg episode reward: [(0, '37.150'), (1, '34.910')] -[2023-10-10 13:58:02,549][76543] Updated weights for policy 0, policy_version 32903 (0.0009) -[2023-10-10 13:58:02,927][76543] Updated weights for policy 0, policy_version 32913 (0.0008) -[2023-10-10 13:58:03,302][76543] Updated weights for policy 0, policy_version 32923 (0.0008) -[2023-10-10 13:58:03,373][76542] Updated weights for policy 1, policy_version 32870 (0.0010) -[2023-10-10 13:58:03,743][76542] Updated weights for policy 1, policy_version 32880 (0.0008) -[2023-10-10 13:58:04,113][76542] Updated weights for policy 1, policy_version 32890 (0.0007) -[2023-10-10 13:58:06,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 67403776. Throughput: 0: 1821.3, 1: 1817.4. Samples: 16854768. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:58:06,077][75634] Avg episode reward: [(0, '35.500'), (1, '34.210')] -[2023-10-10 13:58:06,921][76543] Updated weights for policy 0, policy_version 32933 (0.0008) -[2023-10-10 13:58:07,301][76543] Updated weights for policy 0, policy_version 32943 (0.0007) -[2023-10-10 13:58:07,667][76543] Updated weights for policy 0, policy_version 32953 (0.0008) -[2023-10-10 13:58:07,699][76542] Updated weights for policy 1, policy_version 32900 (0.0009) -[2023-10-10 13:58:08,069][76542] Updated weights for policy 1, policy_version 32910 (0.0007) -[2023-10-10 13:58:08,432][76542] Updated weights for policy 1, policy_version 32920 (0.0008) -[2023-10-10 13:58:11,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 67469312. Throughput: 0: 1816.8, 1: 1806.0. Samples: 16876440. Policy #0 lag: (min: 6.0, avg: 13.8, max: 38.0) -[2023-10-10 13:58:11,077][75634] Avg episode reward: [(0, '34.180'), (1, '32.800')] -[2023-10-10 13:58:11,274][76543] Updated weights for policy 0, policy_version 32963 (0.0008) -[2023-10-10 13:58:11,637][76543] Updated weights for policy 0, policy_version 32973 (0.0007) -[2023-10-10 13:58:12,010][76543] Updated weights for policy 0, policy_version 32983 (0.0007) -[2023-10-10 13:58:12,314][76542] Updated weights for policy 1, policy_version 32930 (0.0009) -[2023-10-10 13:58:12,685][76542] Updated weights for policy 1, policy_version 32940 (0.0009) -[2023-10-10 13:58:13,066][76542] Updated weights for policy 1, policy_version 32950 (0.0008) -[2023-10-10 13:58:13,432][76542] Updated weights for policy 1, policy_version 32960 (0.0008) -[2023-10-10 13:58:15,791][76543] Updated weights for policy 0, policy_version 32993 (0.0007) -[2023-10-10 13:58:16,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 67534848. Throughput: 0: 1819.3, 1: 1797.2. Samples: 16898908. Policy #0 lag: (min: 6.0, avg: 13.8, max: 38.0) -[2023-10-10 13:58:16,076][75634] Avg episode reward: [(0, '35.120'), (1, '31.410')] -[2023-10-10 13:58:16,168][76543] Updated weights for policy 0, policy_version 33003 (0.0008) -[2023-10-10 13:58:16,552][76543] Updated weights for policy 0, policy_version 33013 (0.0009) -[2023-10-10 13:58:16,919][76543] Updated weights for policy 0, policy_version 33023 (0.0008) -[2023-10-10 13:58:17,200][76542] Updated weights for policy 1, policy_version 32970 (0.0008) -[2023-10-10 13:58:17,577][76542] Updated weights for policy 1, policy_version 32980 (0.0008) -[2023-10-10 13:58:17,937][76542] Updated weights for policy 1, policy_version 32990 (0.0010) -[2023-10-10 13:58:20,416][76543] Updated weights for policy 0, policy_version 33033 (0.0007) -[2023-10-10 13:58:20,775][76543] Updated weights for policy 0, policy_version 33043 (0.0009) -[2023-10-10 13:58:21,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 67600384. Throughput: 0: 1823.3, 1: 1800.1. Samples: 16909090. Policy #0 lag: (min: 6.0, avg: 13.8, max: 38.0) -[2023-10-10 13:58:21,076][75634] Avg episode reward: [(0, '34.420'), (1, '33.250')] -[2023-10-10 13:58:21,145][76543] Updated weights for policy 0, policy_version 33053 (0.0009) -[2023-10-10 13:58:21,627][76542] Updated weights for policy 1, policy_version 33000 (0.0007) -[2023-10-10 13:58:21,996][76542] Updated weights for policy 1, policy_version 33010 (0.0007) -[2023-10-10 13:58:22,365][76542] Updated weights for policy 1, policy_version 33020 (0.0009) -[2023-10-10 13:58:24,611][76543] Updated weights for policy 0, policy_version 33063 (0.0008) -[2023-10-10 13:58:24,980][76543] Updated weights for policy 0, policy_version 33073 (0.0007) -[2023-10-10 13:58:25,342][76543] Updated weights for policy 0, policy_version 33083 (0.0007) -[2023-10-10 13:58:26,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 67698688. Throughput: 0: 1827.3, 1: 1803.7. Samples: 16932194. Policy #0 lag: (min: 6.0, avg: 13.8, max: 38.0) -[2023-10-10 13:58:26,077][75634] Avg episode reward: [(0, '37.860'), (1, '33.370')] -[2023-10-10 13:58:26,195][76542] Updated weights for policy 1, policy_version 33030 (0.0008) -[2023-10-10 13:58:26,555][76542] Updated weights for policy 1, policy_version 33040 (0.0008) -[2023-10-10 13:58:26,932][76542] Updated weights for policy 1, policy_version 33050 (0.0007) -[2023-10-10 13:58:28,957][76543] Updated weights for policy 0, policy_version 33093 (0.0009) -[2023-10-10 13:58:29,332][76543] Updated weights for policy 0, policy_version 33103 (0.0010) -[2023-10-10 13:58:29,696][76543] Updated weights for policy 0, policy_version 33113 (0.0009) -[2023-10-10 13:58:30,615][76542] Updated weights for policy 1, policy_version 33060 (0.0009) -[2023-10-10 13:58:30,983][76542] Updated weights for policy 1, policy_version 33070 (0.0010) -[2023-10-10 13:58:31,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 67764224. Throughput: 0: 1828.8, 1: 1815.9. Samples: 16953412. Policy #0 lag: (min: 1.0, avg: 6.1, max: 33.0) -[2023-10-10 13:58:31,076][75634] Avg episode reward: [(0, '35.390'), (1, '31.640')] -[2023-10-10 13:58:31,084][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000033120_33914880.pth... -[2023-10-10 13:58:31,117][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000031424_32178176.pth -[2023-10-10 13:58:31,349][76542] Updated weights for policy 1, policy_version 33080 (0.0008) -[2023-10-10 13:58:31,643][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000033088_33882112.pth... -[2023-10-10 13:58:31,673][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000031392_32145408.pth -[2023-10-10 13:58:33,449][76543] Updated weights for policy 0, policy_version 33123 (0.0008) -[2023-10-10 13:58:33,812][76543] Updated weights for policy 0, policy_version 33133 (0.0009) -[2023-10-10 13:58:34,181][76543] Updated weights for policy 0, policy_version 33143 (0.0008) -[2023-10-10 13:58:35,037][76542] Updated weights for policy 1, policy_version 33090 (0.0010) -[2023-10-10 13:58:35,414][76542] Updated weights for policy 1, policy_version 33100 (0.0010) -[2023-10-10 13:58:35,793][76542] Updated weights for policy 1, policy_version 33110 (0.0008) -[2023-10-10 13:58:36,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 67829760. Throughput: 0: 1842.9, 1: 1809.6. Samples: 16965172. Policy #0 lag: (min: 1.0, avg: 6.1, max: 33.0) -[2023-10-10 13:58:36,076][75634] Avg episode reward: [(0, '36.280'), (1, '33.860')] -[2023-10-10 13:58:36,156][76542] Updated weights for policy 1, policy_version 33120 (0.0008) -[2023-10-10 13:58:37,833][76543] Updated weights for policy 0, policy_version 33153 (0.0009) -[2023-10-10 13:58:38,200][76543] Updated weights for policy 0, policy_version 33163 (0.0008) -[2023-10-10 13:58:38,582][76543] Updated weights for policy 0, policy_version 33173 (0.0008) -[2023-10-10 13:58:38,959][76543] Updated weights for policy 0, policy_version 33183 (0.0007) -[2023-10-10 13:58:39,938][76542] Updated weights for policy 1, policy_version 33130 (0.0008) -[2023-10-10 13:58:40,301][76542] Updated weights for policy 1, policy_version 33140 (0.0009) -[2023-10-10 13:58:40,668][76542] Updated weights for policy 1, policy_version 33150 (0.0009) -[2023-10-10 13:58:41,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 67928064. Throughput: 0: 1831.3, 1: 1813.6. Samples: 16985922. Policy #0 lag: (min: 1.0, avg: 6.1, max: 33.0) -[2023-10-10 13:58:41,077][75634] Avg episode reward: [(0, '35.760'), (1, '33.890')] -[2023-10-10 13:58:42,559][76543] Updated weights for policy 0, policy_version 33193 (0.0009) -[2023-10-10 13:58:42,933][76543] Updated weights for policy 0, policy_version 33203 (0.0008) -[2023-10-10 13:58:43,294][76543] Updated weights for policy 0, policy_version 33213 (0.0008) -[2023-10-10 13:58:44,385][76542] Updated weights for policy 1, policy_version 33160 (0.0009) -[2023-10-10 13:58:44,756][76542] Updated weights for policy 1, policy_version 33170 (0.0008) -[2023-10-10 13:58:45,130][76542] Updated weights for policy 1, policy_version 33180 (0.0007) -[2023-10-10 13:58:46,076][75634] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 67993600. Throughput: 0: 1840.2, 1: 1798.8. Samples: 17007530. Policy #0 lag: (min: 1.0, avg: 6.1, max: 33.0) -[2023-10-10 13:58:46,077][75634] Avg episode reward: [(0, '36.770'), (1, '34.520')] -[2023-10-10 13:58:47,188][76543] Updated weights for policy 0, policy_version 33223 (0.0008) -[2023-10-10 13:58:47,567][76543] Updated weights for policy 0, policy_version 33233 (0.0009) -[2023-10-10 13:58:47,930][76543] Updated weights for policy 0, policy_version 33243 (0.0008) -[2023-10-10 13:58:48,823][76542] Updated weights for policy 1, policy_version 33190 (0.0008) -[2023-10-10 13:58:49,182][76542] Updated weights for policy 1, policy_version 33200 (0.0009) -[2023-10-10 13:58:49,559][76542] Updated weights for policy 1, policy_version 33210 (0.0008) -[2023-10-10 13:58:51,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 68059136. Throughput: 0: 1832.4, 1: 1809.6. Samples: 17018660. Policy #0 lag: (min: 1.0, avg: 6.1, max: 33.0) -[2023-10-10 13:58:51,076][75634] Avg episode reward: [(0, '35.600'), (1, '34.350')] -[2023-10-10 13:58:51,565][76543] Updated weights for policy 0, policy_version 33253 (0.0010) -[2023-10-10 13:58:51,948][76543] Updated weights for policy 0, policy_version 33263 (0.0009) -[2023-10-10 13:58:52,328][76543] Updated weights for policy 0, policy_version 33273 (0.0010) -[2023-10-10 13:58:53,124][76542] Updated weights for policy 1, policy_version 33220 (0.0008) -[2023-10-10 13:58:53,487][76542] Updated weights for policy 1, policy_version 33230 (0.0007) -[2023-10-10 13:58:53,857][76542] Updated weights for policy 1, policy_version 33240 (0.0008) -[2023-10-10 13:58:56,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 68124672. Throughput: 0: 1835.2, 1: 1800.0. Samples: 17040024. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-10 13:58:56,076][75634] Avg episode reward: [(0, '35.130'), (1, '34.140')] -[2023-10-10 13:58:56,099][76543] Updated weights for policy 0, policy_version 33283 (0.0007) -[2023-10-10 13:58:56,472][76543] Updated weights for policy 0, policy_version 33293 (0.0009) -[2023-10-10 13:58:56,844][76543] Updated weights for policy 0, policy_version 33303 (0.0009) -[2023-10-10 13:58:57,483][76542] Updated weights for policy 1, policy_version 33250 (0.0008) -[2023-10-10 13:58:57,851][76542] Updated weights for policy 1, policy_version 33260 (0.0007) -[2023-10-10 13:58:58,215][76542] Updated weights for policy 1, policy_version 33270 (0.0007) -[2023-10-10 13:58:58,585][76542] Updated weights for policy 1, policy_version 33280 (0.0008) -[2023-10-10 13:59:00,561][76543] Updated weights for policy 0, policy_version 33313 (0.0010) -[2023-10-10 13:59:00,924][76543] Updated weights for policy 0, policy_version 33323 (0.0007) -[2023-10-10 13:59:01,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 68190208. Throughput: 0: 1832.0, 1: 1818.2. Samples: 17063170. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-10 13:59:01,076][75634] Avg episode reward: [(0, '31.910'), (1, '34.220')] -[2023-10-10 13:59:01,291][76543] Updated weights for policy 0, policy_version 33333 (0.0010) -[2023-10-10 13:59:01,671][76543] Updated weights for policy 0, policy_version 33343 (0.0007) -[2023-10-10 13:59:02,162][76542] Updated weights for policy 1, policy_version 33290 (0.0007) -[2023-10-10 13:59:02,528][76542] Updated weights for policy 1, policy_version 33300 (0.0009) -[2023-10-10 13:59:02,904][76542] Updated weights for policy 1, policy_version 33310 (0.0008) -[2023-10-10 13:59:05,389][76543] Updated weights for policy 0, policy_version 33353 (0.0008) -[2023-10-10 13:59:05,762][76543] Updated weights for policy 0, policy_version 33363 (0.0008) -[2023-10-10 13:59:06,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 68255744. Throughput: 0: 1830.2, 1: 1819.2. Samples: 17073312. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-10 13:59:06,076][75634] Avg episode reward: [(0, '30.780'), (1, '35.370')] -[2023-10-10 13:59:06,126][76543] Updated weights for policy 0, policy_version 33373 (0.0008) -[2023-10-10 13:59:06,531][76542] Updated weights for policy 1, policy_version 33320 (0.0007) -[2023-10-10 13:59:06,904][76542] Updated weights for policy 1, policy_version 33330 (0.0007) -[2023-10-10 13:59:07,268][76542] Updated weights for policy 1, policy_version 33340 (0.0007) -[2023-10-10 13:59:09,709][76543] Updated weights for policy 0, policy_version 33383 (0.0008) -[2023-10-10 13:59:10,079][76543] Updated weights for policy 0, policy_version 33393 (0.0010) -[2023-10-10 13:59:10,449][76543] Updated weights for policy 0, policy_version 33403 (0.0010) -[2023-10-10 13:59:10,988][76542] Updated weights for policy 1, policy_version 33350 (0.0008) -[2023-10-10 13:59:11,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 68354048. Throughput: 0: 1820.3, 1: 1824.1. Samples: 17096190. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-10 13:59:11,077][75634] Avg episode reward: [(0, '32.540'), (1, '33.630')] -[2023-10-10 13:59:11,347][76542] Updated weights for policy 1, policy_version 33360 (0.0008) -[2023-10-10 13:59:11,727][76542] Updated weights for policy 1, policy_version 33370 (0.0008) -[2023-10-10 13:59:14,203][76543] Updated weights for policy 0, policy_version 33413 (0.0010) -[2023-10-10 13:59:14,564][76543] Updated weights for policy 0, policy_version 33423 (0.0009) -[2023-10-10 13:59:14,945][76543] Updated weights for policy 0, policy_version 33433 (0.0008) -[2023-10-10 13:59:15,341][76542] Updated weights for policy 1, policy_version 33380 (0.0011) -[2023-10-10 13:59:15,702][76542] Updated weights for policy 1, policy_version 33390 (0.0010) -[2023-10-10 13:59:16,073][76542] Updated weights for policy 1, policy_version 33400 (0.0008) -[2023-10-10 13:59:16,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 68419584. Throughput: 0: 1813.2, 1: 1815.5. Samples: 17116706. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:59:16,077][75634] Avg episode reward: [(0, '34.180'), (1, '36.550')] -[2023-10-10 13:59:18,604][76543] Updated weights for policy 0, policy_version 33443 (0.0010) -[2023-10-10 13:59:18,988][76543] Updated weights for policy 0, policy_version 33453 (0.0011) -[2023-10-10 13:59:19,348][76543] Updated weights for policy 0, policy_version 33463 (0.0010) -[2023-10-10 13:59:19,832][76542] Updated weights for policy 1, policy_version 33410 (0.0008) -[2023-10-10 13:59:20,194][76542] Updated weights for policy 1, policy_version 33420 (0.0008) -[2023-10-10 13:59:20,561][76542] Updated weights for policy 1, policy_version 33430 (0.0009) -[2023-10-10 13:59:20,927][76542] Updated weights for policy 1, policy_version 33440 (0.0010) -[2023-10-10 13:59:21,076][75634] Fps is (10 sec: 16383.9, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 68517888. Throughput: 0: 1812.9, 1: 1825.7. Samples: 17128910. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:59:21,077][75634] Avg episode reward: [(0, '30.750'), (1, '35.100')] -[2023-10-10 13:59:22,993][76543] Updated weights for policy 0, policy_version 33473 (0.0010) -[2023-10-10 13:59:23,356][76543] Updated weights for policy 0, policy_version 33483 (0.0008) -[2023-10-10 13:59:23,726][76543] Updated weights for policy 0, policy_version 33493 (0.0008) -[2023-10-10 13:59:24,099][76543] Updated weights for policy 0, policy_version 33503 (0.0007) -[2023-10-10 13:59:24,615][76542] Updated weights for policy 1, policy_version 33450 (0.0009) -[2023-10-10 13:59:24,988][76542] Updated weights for policy 1, policy_version 33460 (0.0007) -[2023-10-10 13:59:25,358][76542] Updated weights for policy 1, policy_version 33470 (0.0008) -[2023-10-10 13:59:26,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 68583424. Throughput: 0: 1815.4, 1: 1823.1. Samples: 17149656. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:59:26,076][75634] Avg episode reward: [(0, '31.850'), (1, '33.130')] -[2023-10-10 13:59:27,805][76543] Updated weights for policy 0, policy_version 33513 (0.0009) -[2023-10-10 13:59:28,176][76543] Updated weights for policy 0, policy_version 33523 (0.0010) -[2023-10-10 13:59:28,553][76543] Updated weights for policy 0, policy_version 33533 (0.0008) -[2023-10-10 13:59:28,947][76542] Updated weights for policy 1, policy_version 33480 (0.0009) -[2023-10-10 13:59:29,328][76542] Updated weights for policy 1, policy_version 33490 (0.0010) -[2023-10-10 13:59:29,690][76542] Updated weights for policy 1, policy_version 33500 (0.0010) -[2023-10-10 13:59:31,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 68648960. Throughput: 0: 1807.3, 1: 1840.6. Samples: 17171688. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:59:31,077][75634] Avg episode reward: [(0, '33.050'), (1, '36.450')] -[2023-10-10 13:59:32,142][76543] Updated weights for policy 0, policy_version 33543 (0.0007) -[2023-10-10 13:59:32,516][76543] Updated weights for policy 0, policy_version 33553 (0.0008) -[2023-10-10 13:59:32,891][76543] Updated weights for policy 0, policy_version 33563 (0.0008) -[2023-10-10 13:59:33,347][76542] Updated weights for policy 1, policy_version 33510 (0.0008) -[2023-10-10 13:59:33,725][76542] Updated weights for policy 1, policy_version 33520 (0.0009) -[2023-10-10 13:59:34,097][76542] Updated weights for policy 1, policy_version 33530 (0.0007) -[2023-10-10 13:59:36,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 68714496. Throughput: 0: 1809.2, 1: 1833.3. Samples: 17182572. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:59:36,077][75634] Avg episode reward: [(0, '35.640'), (1, '36.050')] -[2023-10-10 13:59:36,562][76543] Updated weights for policy 0, policy_version 33573 (0.0007) -[2023-10-10 13:59:36,931][76543] Updated weights for policy 0, policy_version 33583 (0.0009) -[2023-10-10 13:59:37,302][76543] Updated weights for policy 0, policy_version 33593 (0.0009) -[2023-10-10 13:59:37,714][76542] Updated weights for policy 1, policy_version 33540 (0.0010) -[2023-10-10 13:59:38,083][76542] Updated weights for policy 1, policy_version 33550 (0.0009) -[2023-10-10 13:59:38,453][76542] Updated weights for policy 1, policy_version 33560 (0.0008) -[2023-10-10 13:59:41,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 68780032. Throughput: 0: 1813.6, 1: 1844.5. Samples: 17204640. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 13:59:41,077][75634] Avg episode reward: [(0, '34.420'), (1, '33.420')] -[2023-10-10 13:59:41,157][76543] Updated weights for policy 0, policy_version 33603 (0.0009) -[2023-10-10 13:59:41,537][76543] Updated weights for policy 0, policy_version 33613 (0.0011) -[2023-10-10 13:59:41,898][76543] Updated weights for policy 0, policy_version 33623 (0.0009) -[2023-10-10 13:59:42,160][76542] Updated weights for policy 1, policy_version 33570 (0.0007) -[2023-10-10 13:59:42,534][76542] Updated weights for policy 1, policy_version 33580 (0.0008) -[2023-10-10 13:59:42,898][76542] Updated weights for policy 1, policy_version 33590 (0.0009) -[2023-10-10 13:59:43,276][76542] Updated weights for policy 1, policy_version 33600 (0.0009) -[2023-10-10 13:59:45,634][76543] Updated weights for policy 0, policy_version 33633 (0.0009) -[2023-10-10 13:59:46,011][76543] Updated weights for policy 0, policy_version 33643 (0.0008) -[2023-10-10 13:59:46,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 68845568. Throughput: 0: 1807.0, 1: 1832.1. Samples: 17226930. Policy #0 lag: (min: 17.0, avg: 28.0, max: 49.0) -[2023-10-10 13:59:46,076][75634] Avg episode reward: [(0, '35.860'), (1, '32.670')] -[2023-10-10 13:59:46,378][76543] Updated weights for policy 0, policy_version 33653 (0.0009) -[2023-10-10 13:59:46,743][76543] Updated weights for policy 0, policy_version 33663 (0.0007) -[2023-10-10 13:59:46,933][76542] Updated weights for policy 1, policy_version 33610 (0.0008) -[2023-10-10 13:59:47,304][76542] Updated weights for policy 1, policy_version 33620 (0.0011) -[2023-10-10 13:59:47,676][76542] Updated weights for policy 1, policy_version 33630 (0.0012) -[2023-10-10 13:59:50,460][76543] Updated weights for policy 0, policy_version 33673 (0.0007) -[2023-10-10 13:59:50,823][76543] Updated weights for policy 0, policy_version 33683 (0.0007) -[2023-10-10 13:59:51,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 68911104. Throughput: 0: 1806.0, 1: 1828.5. Samples: 17236866. Policy #0 lag: (min: 17.0, avg: 28.0, max: 49.0) -[2023-10-10 13:59:51,077][75634] Avg episode reward: [(0, '34.970'), (1, '34.590')] -[2023-10-10 13:59:51,203][76543] Updated weights for policy 0, policy_version 33693 (0.0008) -[2023-10-10 13:59:51,310][76542] Updated weights for policy 1, policy_version 33640 (0.0008) -[2023-10-10 13:59:51,676][76542] Updated weights for policy 1, policy_version 33650 (0.0007) -[2023-10-10 13:59:52,050][76542] Updated weights for policy 1, policy_version 33660 (0.0007) -[2023-10-10 13:59:54,945][76543] Updated weights for policy 0, policy_version 33703 (0.0010) -[2023-10-10 13:59:55,316][76543] Updated weights for policy 0, policy_version 33713 (0.0010) -[2023-10-10 13:59:55,692][76543] Updated weights for policy 0, policy_version 33723 (0.0010) -[2023-10-10 13:59:55,828][76542] Updated weights for policy 1, policy_version 33670 (0.0008) -[2023-10-10 13:59:56,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 69009408. Throughput: 0: 1810.1, 1: 1826.5. Samples: 17259836. Policy #0 lag: (min: 17.0, avg: 28.0, max: 49.0) -[2023-10-10 13:59:56,077][75634] Avg episode reward: [(0, '38.280'), (1, '31.770')] -[2023-10-10 13:59:56,187][76542] Updated weights for policy 1, policy_version 33680 (0.0008) -[2023-10-10 13:59:56,564][76542] Updated weights for policy 1, policy_version 33690 (0.0011) -[2023-10-10 13:59:59,372][76543] Updated weights for policy 0, policy_version 33733 (0.0008) -[2023-10-10 13:59:59,754][76543] Updated weights for policy 0, policy_version 33743 (0.0010) -[2023-10-10 14:00:00,126][76543] Updated weights for policy 0, policy_version 33753 (0.0007) -[2023-10-10 14:00:00,251][76542] Updated weights for policy 1, policy_version 33700 (0.0010) -[2023-10-10 14:00:00,614][76542] Updated weights for policy 1, policy_version 33710 (0.0011) -[2023-10-10 14:00:00,990][76542] Updated weights for policy 1, policy_version 33720 (0.0010) -[2023-10-10 14:00:01,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 69074944. Throughput: 0: 1819.0, 1: 1822.3. Samples: 17280562. Policy #0 lag: (min: 17.0, avg: 28.0, max: 49.0) -[2023-10-10 14:00:01,076][75634] Avg episode reward: [(0, '40.160'), (1, '27.780')] -[2023-10-10 14:00:01,085][76362] Saving new best policy, reward=40.160! -[2023-10-10 14:00:03,725][76543] Updated weights for policy 0, policy_version 33763 (0.0008) -[2023-10-10 14:00:04,097][76543] Updated weights for policy 0, policy_version 33773 (0.0007) -[2023-10-10 14:00:04,461][76543] Updated weights for policy 0, policy_version 33783 (0.0010) -[2023-10-10 14:00:04,772][76542] Updated weights for policy 1, policy_version 33730 (0.0009) -[2023-10-10 14:00:05,135][76542] Updated weights for policy 1, policy_version 33740 (0.0007) -[2023-10-10 14:00:05,497][76542] Updated weights for policy 1, policy_version 33750 (0.0009) -[2023-10-10 14:00:05,864][76542] Updated weights for policy 1, policy_version 33760 (0.0010) -[2023-10-10 14:00:06,076][75634] Fps is (10 sec: 16384.2, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 69173248. Throughput: 0: 1818.3, 1: 1819.6. Samples: 17292616. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-10 14:00:06,077][75634] Avg episode reward: [(0, '37.050'), (1, '29.570')] -[2023-10-10 14:00:08,270][76543] Updated weights for policy 0, policy_version 33793 (0.0010) -[2023-10-10 14:00:08,644][76543] Updated weights for policy 0, policy_version 33803 (0.0009) -[2023-10-10 14:00:09,020][76543] Updated weights for policy 0, policy_version 33813 (0.0008) -[2023-10-10 14:00:09,402][76543] Updated weights for policy 0, policy_version 33823 (0.0007) -[2023-10-10 14:00:09,490][76542] Updated weights for policy 1, policy_version 33770 (0.0008) -[2023-10-10 14:00:09,863][76542] Updated weights for policy 1, policy_version 33780 (0.0007) -[2023-10-10 14:00:10,226][76542] Updated weights for policy 1, policy_version 33790 (0.0007) -[2023-10-10 14:00:11,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 69238784. Throughput: 0: 1817.2, 1: 1823.4. Samples: 17313484. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-10 14:00:11,077][75634] Avg episode reward: [(0, '36.560'), (1, '32.140')] -[2023-10-10 14:00:13,227][76543] Updated weights for policy 0, policy_version 33833 (0.0009) -[2023-10-10 14:00:13,599][76543] Updated weights for policy 0, policy_version 33843 (0.0008) -[2023-10-10 14:00:13,884][76542] Updated weights for policy 1, policy_version 33800 (0.0007) -[2023-10-10 14:00:13,973][76543] Updated weights for policy 0, policy_version 33853 (0.0008) -[2023-10-10 14:00:14,258][76542] Updated weights for policy 1, policy_version 33810 (0.0008) -[2023-10-10 14:00:14,626][76542] Updated weights for policy 1, policy_version 33820 (0.0007) -[2023-10-10 14:00:16,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 69304320. Throughput: 0: 1807.5, 1: 1818.9. Samples: 17334880. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-10 14:00:16,077][75634] Avg episode reward: [(0, '36.660'), (1, '35.790')] -[2023-10-10 14:00:17,588][76543] Updated weights for policy 0, policy_version 33863 (0.0008) -[2023-10-10 14:00:17,963][76543] Updated weights for policy 0, policy_version 33873 (0.0007) -[2023-10-10 14:00:18,300][76542] Updated weights for policy 1, policy_version 33830 (0.0008) -[2023-10-10 14:00:18,332][76543] Updated weights for policy 0, policy_version 33883 (0.0007) -[2023-10-10 14:00:18,668][76542] Updated weights for policy 1, policy_version 33840 (0.0009) -[2023-10-10 14:00:19,048][76542] Updated weights for policy 1, policy_version 33850 (0.0010) -[2023-10-10 14:00:21,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 69369856. Throughput: 0: 1818.9, 1: 1814.0. Samples: 17346050. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-10 14:00:21,076][75634] Avg episode reward: [(0, '32.370'), (1, '36.490')] -[2023-10-10 14:00:22,131][76543] Updated weights for policy 0, policy_version 33893 (0.0009) -[2023-10-10 14:00:22,505][76543] Updated weights for policy 0, policy_version 33903 (0.0011) -[2023-10-10 14:00:22,821][76542] Updated weights for policy 1, policy_version 33860 (0.0009) -[2023-10-10 14:00:22,881][76543] Updated weights for policy 0, policy_version 33913 (0.0008) -[2023-10-10 14:00:23,188][76542] Updated weights for policy 1, policy_version 33870 (0.0008) -[2023-10-10 14:00:23,559][76542] Updated weights for policy 1, policy_version 33880 (0.0010) -[2023-10-10 14:00:26,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 69435392. Throughput: 0: 1805.5, 1: 1811.5. Samples: 17367404. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-10 14:00:26,077][75634] Avg episode reward: [(0, '29.560'), (1, '35.220')] -[2023-10-10 14:00:26,525][76543] Updated weights for policy 0, policy_version 33923 (0.0009) -[2023-10-10 14:00:26,901][76543] Updated weights for policy 0, policy_version 33933 (0.0010) -[2023-10-10 14:00:27,268][76543] Updated weights for policy 0, policy_version 33943 (0.0011) -[2023-10-10 14:00:27,318][76542] Updated weights for policy 1, policy_version 33890 (0.0009) -[2023-10-10 14:00:27,679][76542] Updated weights for policy 1, policy_version 33900 (0.0008) -[2023-10-10 14:00:28,058][76542] Updated weights for policy 1, policy_version 33910 (0.0009) -[2023-10-10 14:00:28,415][76542] Updated weights for policy 1, policy_version 33920 (0.0007) -[2023-10-10 14:00:30,869][76543] Updated weights for policy 0, policy_version 33953 (0.0007) -[2023-10-10 14:00:31,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 69500928. Throughput: 0: 1815.6, 1: 1808.8. Samples: 17390030. Policy #0 lag: (min: 17.0, avg: 31.2, max: 32.0) -[2023-10-10 14:00:31,077][75634] Avg episode reward: [(0, '30.040'), (1, '35.910')] -[2023-10-10 14:00:31,090][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000033920_34734080.pth... -[2023-10-10 14:00:31,125][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000032224_32997376.pth -[2023-10-10 14:00:31,129][76421] Saving a milestone ./train_atari/atari_defender_APPO/checkpoint_p1/milestones/checkpoint_000033920_34734080.pth -[2023-10-10 14:00:31,235][76543] Updated weights for policy 0, policy_version 33963 (0.0008) -[2023-10-10 14:00:31,611][76543] Updated weights for policy 0, policy_version 33973 (0.0007) -[2023-10-10 14:00:31,983][76543] Updated weights for policy 0, policy_version 33983 (0.0010) -[2023-10-10 14:00:32,018][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000033984_34799616.pth... -[2023-10-10 14:00:32,051][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000032256_33030144.pth -[2023-10-10 14:00:32,055][76362] Saving a milestone ./train_atari/atari_defender_APPO/checkpoint_p0/milestones/checkpoint_000033984_34799616.pth -[2023-10-10 14:00:32,255][76542] Updated weights for policy 1, policy_version 33930 (0.0008) -[2023-10-10 14:00:32,616][76542] Updated weights for policy 1, policy_version 33940 (0.0009) -[2023-10-10 14:00:32,986][76542] Updated weights for policy 1, policy_version 33950 (0.0007) -[2023-10-10 14:00:35,652][76543] Updated weights for policy 0, policy_version 33993 (0.0010) -[2023-10-10 14:00:36,018][76543] Updated weights for policy 0, policy_version 34003 (0.0009) -[2023-10-10 14:00:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 69566464. Throughput: 0: 1817.2, 1: 1805.7. Samples: 17399898. Policy #0 lag: (min: 17.0, avg: 31.2, max: 32.0) -[2023-10-10 14:00:36,076][75634] Avg episode reward: [(0, '31.550'), (1, '36.660')] -[2023-10-10 14:00:36,397][76543] Updated weights for policy 0, policy_version 34013 (0.0009) -[2023-10-10 14:00:36,620][76542] Updated weights for policy 1, policy_version 33960 (0.0008) -[2023-10-10 14:00:36,988][76542] Updated weights for policy 1, policy_version 33970 (0.0007) -[2023-10-10 14:00:37,354][76542] Updated weights for policy 1, policy_version 33980 (0.0007) -[2023-10-10 14:00:40,064][76543] Updated weights for policy 0, policy_version 34023 (0.0007) -[2023-10-10 14:00:40,450][76543] Updated weights for policy 0, policy_version 34033 (0.0009) -[2023-10-10 14:00:40,817][76543] Updated weights for policy 0, policy_version 34043 (0.0009) -[2023-10-10 14:00:41,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 69664768. Throughput: 0: 1812.7, 1: 1805.3. Samples: 17422646. Policy #0 lag: (min: 17.0, avg: 31.2, max: 32.0) -[2023-10-10 14:00:41,077][75634] Avg episode reward: [(0, '35.730'), (1, '37.630')] -[2023-10-10 14:00:41,101][76542] Updated weights for policy 1, policy_version 33990 (0.0007) -[2023-10-10 14:00:41,461][76542] Updated weights for policy 1, policy_version 34000 (0.0008) -[2023-10-10 14:00:41,832][76542] Updated weights for policy 1, policy_version 34010 (0.0007) -[2023-10-10 14:00:44,584][76543] Updated weights for policy 0, policy_version 34053 (0.0009) -[2023-10-10 14:00:44,972][76543] Updated weights for policy 0, policy_version 34063 (0.0009) -[2023-10-10 14:00:45,337][76543] Updated weights for policy 0, policy_version 34073 (0.0011) -[2023-10-10 14:00:45,659][76542] Updated weights for policy 1, policy_version 34020 (0.0008) -[2023-10-10 14:00:46,025][76542] Updated weights for policy 1, policy_version 34030 (0.0009) -[2023-10-10 14:00:46,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 69730304. Throughput: 0: 1814.2, 1: 1812.9. Samples: 17443782. Policy #0 lag: (min: 17.0, avg: 31.2, max: 32.0) -[2023-10-10 14:00:46,076][75634] Avg episode reward: [(0, '32.030'), (1, '34.360')] -[2023-10-10 14:00:46,381][76542] Updated weights for policy 1, policy_version 34040 (0.0008) -[2023-10-10 14:00:49,128][76543] Updated weights for policy 0, policy_version 34083 (0.0008) -[2023-10-10 14:00:49,510][76543] Updated weights for policy 0, policy_version 34093 (0.0008) -[2023-10-10 14:00:49,884][76543] Updated weights for policy 0, policy_version 34103 (0.0009) -[2023-10-10 14:00:50,052][76542] Updated weights for policy 1, policy_version 34050 (0.0009) -[2023-10-10 14:00:50,432][76542] Updated weights for policy 1, policy_version 34060 (0.0009) -[2023-10-10 14:00:50,804][76542] Updated weights for policy 1, policy_version 34070 (0.0008) -[2023-10-10 14:00:51,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 69795840. Throughput: 0: 1799.2, 1: 1803.8. Samples: 17454748. Policy #0 lag: (min: 10.0, avg: 15.9, max: 42.0) -[2023-10-10 14:00:51,077][75634] Avg episode reward: [(0, '31.120'), (1, '31.680')] -[2023-10-10 14:00:51,165][76542] Updated weights for policy 1, policy_version 34080 (0.0008) -[2023-10-10 14:00:53,621][76543] Updated weights for policy 0, policy_version 34113 (0.0009) -[2023-10-10 14:00:53,990][76543] Updated weights for policy 0, policy_version 34123 (0.0007) -[2023-10-10 14:00:54,363][76543] Updated weights for policy 0, policy_version 34133 (0.0007) -[2023-10-10 14:00:54,737][76543] Updated weights for policy 0, policy_version 34143 (0.0009) -[2023-10-10 14:00:54,968][76542] Updated weights for policy 1, policy_version 34090 (0.0008) -[2023-10-10 14:00:55,336][76542] Updated weights for policy 1, policy_version 34100 (0.0007) -[2023-10-10 14:00:55,695][76542] Updated weights for policy 1, policy_version 34110 (0.0008) -[2023-10-10 14:00:56,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 69894144. Throughput: 0: 1812.7, 1: 1808.3. Samples: 17476426. Policy #0 lag: (min: 10.0, avg: 15.9, max: 42.0) -[2023-10-10 14:00:56,076][75634] Avg episode reward: [(0, '36.420'), (1, '36.850')] -[2023-10-10 14:00:58,310][76543] Updated weights for policy 0, policy_version 34153 (0.0011) -[2023-10-10 14:00:58,689][76543] Updated weights for policy 0, policy_version 34163 (0.0011) -[2023-10-10 14:00:59,063][76543] Updated weights for policy 0, policy_version 34173 (0.0009) -[2023-10-10 14:00:59,407][76542] Updated weights for policy 1, policy_version 34120 (0.0011) -[2023-10-10 14:00:59,782][76542] Updated weights for policy 1, policy_version 34130 (0.0011) -[2023-10-10 14:01:00,145][76542] Updated weights for policy 1, policy_version 34140 (0.0009) -[2023-10-10 14:01:01,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 69959680. Throughput: 0: 1816.4, 1: 1796.4. Samples: 17497456. Policy #0 lag: (min: 10.0, avg: 15.9, max: 42.0) -[2023-10-10 14:01:01,077][75634] Avg episode reward: [(0, '35.790'), (1, '33.500')] -[2023-10-10 14:01:02,663][76543] Updated weights for policy 0, policy_version 34183 (0.0007) -[2023-10-10 14:01:03,025][76543] Updated weights for policy 0, policy_version 34193 (0.0007) -[2023-10-10 14:01:03,397][76543] Updated weights for policy 0, policy_version 34203 (0.0007) -[2023-10-10 14:01:03,756][76542] Updated weights for policy 1, policy_version 34150 (0.0008) -[2023-10-10 14:01:04,128][76542] Updated weights for policy 1, policy_version 34160 (0.0007) -[2023-10-10 14:01:04,501][76542] Updated weights for policy 1, policy_version 34170 (0.0010) -[2023-10-10 14:01:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 70025216. Throughput: 0: 1817.2, 1: 1809.2. Samples: 17509238. Policy #0 lag: (min: 10.0, avg: 15.9, max: 42.0) -[2023-10-10 14:01:06,076][75634] Avg episode reward: [(0, '38.780'), (1, '31.490')] -[2023-10-10 14:01:07,093][76543] Updated weights for policy 0, policy_version 34213 (0.0009) -[2023-10-10 14:01:07,463][76543] Updated weights for policy 0, policy_version 34223 (0.0010) -[2023-10-10 14:01:07,833][76543] Updated weights for policy 0, policy_version 34233 (0.0009) -[2023-10-10 14:01:08,331][76542] Updated weights for policy 1, policy_version 34180 (0.0010) -[2023-10-10 14:01:08,709][76542] Updated weights for policy 1, policy_version 34190 (0.0008) -[2023-10-10 14:01:09,076][76542] Updated weights for policy 1, policy_version 34200 (0.0008) -[2023-10-10 14:01:11,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 70090752. Throughput: 0: 1823.1, 1: 1800.7. Samples: 17530478. Policy #0 lag: (min: 10.0, avg: 15.9, max: 42.0) -[2023-10-10 14:01:11,077][75634] Avg episode reward: [(0, '36.390'), (1, '32.320')] -[2023-10-10 14:01:11,447][76543] Updated weights for policy 0, policy_version 34243 (0.0008) -[2023-10-10 14:01:11,810][76543] Updated weights for policy 0, policy_version 34253 (0.0008) -[2023-10-10 14:01:12,182][76543] Updated weights for policy 0, policy_version 34263 (0.0009) -[2023-10-10 14:01:12,746][76542] Updated weights for policy 1, policy_version 34210 (0.0008) -[2023-10-10 14:01:13,118][76542] Updated weights for policy 1, policy_version 34220 (0.0008) -[2023-10-10 14:01:13,498][76542] Updated weights for policy 1, policy_version 34230 (0.0008) -[2023-10-10 14:01:13,872][76542] Updated weights for policy 1, policy_version 34240 (0.0007) -[2023-10-10 14:01:15,801][76543] Updated weights for policy 0, policy_version 34273 (0.0008) -[2023-10-10 14:01:16,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 70156288. Throughput: 0: 1823.3, 1: 1804.4. Samples: 17553272. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:01:16,076][75634] Avg episode reward: [(0, '37.440'), (1, '33.310')] -[2023-10-10 14:01:16,171][76543] Updated weights for policy 0, policy_version 34283 (0.0009) -[2023-10-10 14:01:16,543][76543] Updated weights for policy 0, policy_version 34293 (0.0007) -[2023-10-10 14:01:16,912][76543] Updated weights for policy 0, policy_version 34303 (0.0007) -[2023-10-10 14:01:17,587][76542] Updated weights for policy 1, policy_version 34250 (0.0008) -[2023-10-10 14:01:17,955][76542] Updated weights for policy 1, policy_version 34260 (0.0008) -[2023-10-10 14:01:18,323][76542] Updated weights for policy 1, policy_version 34270 (0.0010) -[2023-10-10 14:01:20,432][76543] Updated weights for policy 0, policy_version 34313 (0.0008) -[2023-10-10 14:01:20,804][76543] Updated weights for policy 0, policy_version 34323 (0.0007) -[2023-10-10 14:01:21,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 70221824. Throughput: 0: 1823.9, 1: 1805.9. Samples: 17563238. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:01:21,076][75634] Avg episode reward: [(0, '33.720'), (1, '30.620')] -[2023-10-10 14:01:21,185][76543] Updated weights for policy 0, policy_version 34333 (0.0008) -[2023-10-10 14:01:21,997][76542] Updated weights for policy 1, policy_version 34280 (0.0008) -[2023-10-10 14:01:22,359][76542] Updated weights for policy 1, policy_version 34290 (0.0010) -[2023-10-10 14:01:22,724][76542] Updated weights for policy 1, policy_version 34300 (0.0008) -[2023-10-10 14:01:24,883][76543] Updated weights for policy 0, policy_version 34343 (0.0009) -[2023-10-10 14:01:25,256][76543] Updated weights for policy 0, policy_version 34353 (0.0009) -[2023-10-10 14:01:25,637][76543] Updated weights for policy 0, policy_version 34363 (0.0008) -[2023-10-10 14:01:26,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 70320128. Throughput: 0: 1831.5, 1: 1802.1. Samples: 17586158. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:01:26,076][75634] Avg episode reward: [(0, '34.540'), (1, '33.390')] -[2023-10-10 14:01:26,461][76542] Updated weights for policy 1, policy_version 34310 (0.0008) -[2023-10-10 14:01:26,830][76542] Updated weights for policy 1, policy_version 34320 (0.0010) -[2023-10-10 14:01:27,206][76542] Updated weights for policy 1, policy_version 34330 (0.0008) -[2023-10-10 14:01:29,450][76543] Updated weights for policy 0, policy_version 34373 (0.0008) -[2023-10-10 14:01:29,833][76543] Updated weights for policy 0, policy_version 34383 (0.0010) -[2023-10-10 14:01:30,218][76543] Updated weights for policy 0, policy_version 34393 (0.0010) -[2023-10-10 14:01:30,715][76542] Updated weights for policy 1, policy_version 34340 (0.0008) -[2023-10-10 14:01:31,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 70385664. Throughput: 0: 1824.9, 1: 1815.6. Samples: 17607602. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:01:31,076][75634] Avg episode reward: [(0, '34.840'), (1, '33.130')] -[2023-10-10 14:01:31,086][76542] Updated weights for policy 1, policy_version 34350 (0.0010) -[2023-10-10 14:01:31,462][76542] Updated weights for policy 1, policy_version 34360 (0.0007) -[2023-10-10 14:01:33,930][76543] Updated weights for policy 0, policy_version 34403 (0.0010) -[2023-10-10 14:01:34,309][76543] Updated weights for policy 0, policy_version 34413 (0.0007) -[2023-10-10 14:01:34,682][76543] Updated weights for policy 0, policy_version 34423 (0.0008) -[2023-10-10 14:01:35,208][76542] Updated weights for policy 1, policy_version 34370 (0.0007) -[2023-10-10 14:01:35,585][76542] Updated weights for policy 1, policy_version 34380 (0.0009) -[2023-10-10 14:01:35,951][76542] Updated weights for policy 1, policy_version 34390 (0.0010) -[2023-10-10 14:01:36,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 70451200. Throughput: 0: 1832.7, 1: 1815.0. Samples: 17618892. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:01:36,077][75634] Avg episode reward: [(0, '34.860'), (1, '33.780')] -[2023-10-10 14:01:36,313][76542] Updated weights for policy 1, policy_version 34400 (0.0009) -[2023-10-10 14:01:38,384][76543] Updated weights for policy 0, policy_version 34433 (0.0009) -[2023-10-10 14:01:38,754][76543] Updated weights for policy 0, policy_version 34443 (0.0007) -[2023-10-10 14:01:39,119][76543] Updated weights for policy 0, policy_version 34453 (0.0007) -[2023-10-10 14:01:39,494][76543] Updated weights for policy 0, policy_version 34463 (0.0008) -[2023-10-10 14:01:40,108][76542] Updated weights for policy 1, policy_version 34410 (0.0007) -[2023-10-10 14:01:40,470][76542] Updated weights for policy 1, policy_version 34420 (0.0007) -[2023-10-10 14:01:40,832][76542] Updated weights for policy 1, policy_version 34430 (0.0008) -[2023-10-10 14:01:41,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 70549504. Throughput: 0: 1825.9, 1: 1819.4. Samples: 17640466. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 14:01:41,077][75634] Avg episode reward: [(0, '35.690'), (1, '31.430')] -[2023-10-10 14:01:43,074][76543] Updated weights for policy 0, policy_version 34473 (0.0009) -[2023-10-10 14:01:43,444][76543] Updated weights for policy 0, policy_version 34483 (0.0007) -[2023-10-10 14:01:43,823][76543] Updated weights for policy 0, policy_version 34493 (0.0007) -[2023-10-10 14:01:44,622][76542] Updated weights for policy 1, policy_version 34440 (0.0008) -[2023-10-10 14:01:44,989][76542] Updated weights for policy 1, policy_version 34450 (0.0009) -[2023-10-10 14:01:45,364][76542] Updated weights for policy 1, policy_version 34460 (0.0008) -[2023-10-10 14:01:46,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 70615040. Throughput: 0: 1832.8, 1: 1813.8. Samples: 17661554. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 14:01:46,076][75634] Avg episode reward: [(0, '34.090'), (1, '32.210')] -[2023-10-10 14:01:47,487][76543] Updated weights for policy 0, policy_version 34503 (0.0008) -[2023-10-10 14:01:47,862][76543] Updated weights for policy 0, policy_version 34513 (0.0009) -[2023-10-10 14:01:48,239][76543] Updated weights for policy 0, policy_version 34523 (0.0008) -[2023-10-10 14:01:48,970][76542] Updated weights for policy 1, policy_version 34470 (0.0010) -[2023-10-10 14:01:49,347][76542] Updated weights for policy 1, policy_version 34480 (0.0011) -[2023-10-10 14:01:49,711][76542] Updated weights for policy 1, policy_version 34490 (0.0009) -[2023-10-10 14:01:51,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 70680576. Throughput: 0: 1823.9, 1: 1818.3. Samples: 17673140. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 14:01:51,077][75634] Avg episode reward: [(0, '34.070'), (1, '32.540')] -[2023-10-10 14:01:51,718][76543] Updated weights for policy 0, policy_version 34533 (0.0008) -[2023-10-10 14:01:52,088][76543] Updated weights for policy 0, policy_version 34543 (0.0007) -[2023-10-10 14:01:52,465][76543] Updated weights for policy 0, policy_version 34553 (0.0007) -[2023-10-10 14:01:53,309][76542] Updated weights for policy 1, policy_version 34500 (0.0007) -[2023-10-10 14:01:53,674][76542] Updated weights for policy 1, policy_version 34510 (0.0009) -[2023-10-10 14:01:54,054][76542] Updated weights for policy 1, policy_version 34520 (0.0011) -[2023-10-10 14:01:56,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 70746112. Throughput: 0: 1829.0, 1: 1817.0. Samples: 17694550. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 14:01:56,076][75634] Avg episode reward: [(0, '35.320'), (1, '33.450')] -[2023-10-10 14:01:56,111][76543] Updated weights for policy 0, policy_version 34563 (0.0007) -[2023-10-10 14:01:56,492][76543] Updated weights for policy 0, policy_version 34573 (0.0008) -[2023-10-10 14:01:56,865][76543] Updated weights for policy 0, policy_version 34583 (0.0007) -[2023-10-10 14:01:57,793][76542] Updated weights for policy 1, policy_version 34530 (0.0009) -[2023-10-10 14:01:58,162][76542] Updated weights for policy 1, policy_version 34540 (0.0008) -[2023-10-10 14:01:58,539][76542] Updated weights for policy 1, policy_version 34550 (0.0009) -[2023-10-10 14:01:58,897][76542] Updated weights for policy 1, policy_version 34560 (0.0007) -[2023-10-10 14:02:00,434][76543] Updated weights for policy 0, policy_version 34593 (0.0008) -[2023-10-10 14:02:00,798][76543] Updated weights for policy 0, policy_version 34603 (0.0009) -[2023-10-10 14:02:01,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 70811648. Throughput: 0: 1826.0, 1: 1819.0. Samples: 17717298. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 14:02:01,077][75634] Avg episode reward: [(0, '36.960'), (1, '34.550')] -[2023-10-10 14:02:01,167][76543] Updated weights for policy 0, policy_version 34613 (0.0010) -[2023-10-10 14:02:01,537][76543] Updated weights for policy 0, policy_version 34623 (0.0009) -[2023-10-10 14:02:02,623][76542] Updated weights for policy 1, policy_version 34570 (0.0008) -[2023-10-10 14:02:02,993][76542] Updated weights for policy 1, policy_version 34580 (0.0010) -[2023-10-10 14:02:03,365][76542] Updated weights for policy 1, policy_version 34590 (0.0009) -[2023-10-10 14:02:05,346][76543] Updated weights for policy 0, policy_version 34633 (0.0010) -[2023-10-10 14:02:05,719][76543] Updated weights for policy 0, policy_version 34643 (0.0009) -[2023-10-10 14:02:06,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 70877184. Throughput: 0: 1822.0, 1: 1820.6. Samples: 17727154. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 14:02:06,077][75634] Avg episode reward: [(0, '35.430'), (1, '33.890')] -[2023-10-10 14:02:06,098][76543] Updated weights for policy 0, policy_version 34653 (0.0008) -[2023-10-10 14:02:07,086][76542] Updated weights for policy 1, policy_version 34600 (0.0009) -[2023-10-10 14:02:07,452][76542] Updated weights for policy 1, policy_version 34610 (0.0009) -[2023-10-10 14:02:07,829][76542] Updated weights for policy 1, policy_version 34620 (0.0009) -[2023-10-10 14:02:09,671][76543] Updated weights for policy 0, policy_version 34663 (0.0008) -[2023-10-10 14:02:10,049][76543] Updated weights for policy 0, policy_version 34673 (0.0008) -[2023-10-10 14:02:10,423][76543] Updated weights for policy 0, policy_version 34683 (0.0007) -[2023-10-10 14:02:11,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 70975488. Throughput: 0: 1824.6, 1: 1821.9. Samples: 17750252. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:02:11,077][75634] Avg episode reward: [(0, '33.590'), (1, '36.420')] -[2023-10-10 14:02:11,470][76542] Updated weights for policy 1, policy_version 34630 (0.0009) -[2023-10-10 14:02:11,840][76542] Updated weights for policy 1, policy_version 34640 (0.0008) -[2023-10-10 14:02:12,214][76542] Updated weights for policy 1, policy_version 34650 (0.0008) -[2023-10-10 14:02:14,195][76543] Updated weights for policy 0, policy_version 34693 (0.0008) -[2023-10-10 14:02:14,564][76543] Updated weights for policy 0, policy_version 34703 (0.0009) -[2023-10-10 14:02:14,942][76543] Updated weights for policy 0, policy_version 34713 (0.0008) -[2023-10-10 14:02:15,908][76542] Updated weights for policy 1, policy_version 34660 (0.0009) -[2023-10-10 14:02:16,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 71041024. Throughput: 0: 1822.5, 1: 1820.0. Samples: 17771518. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:02:16,077][75634] Avg episode reward: [(0, '31.500'), (1, '34.880')] -[2023-10-10 14:02:16,277][76542] Updated weights for policy 1, policy_version 34670 (0.0009) -[2023-10-10 14:02:16,659][76542] Updated weights for policy 1, policy_version 34680 (0.0009) -[2023-10-10 14:02:18,693][76543] Updated weights for policy 0, policy_version 34723 (0.0008) -[2023-10-10 14:02:19,066][76543] Updated weights for policy 0, policy_version 34733 (0.0007) -[2023-10-10 14:02:19,450][76543] Updated weights for policy 0, policy_version 34743 (0.0010) -[2023-10-10 14:02:20,301][76542] Updated weights for policy 1, policy_version 34690 (0.0008) -[2023-10-10 14:02:20,673][76542] Updated weights for policy 1, policy_version 34700 (0.0007) -[2023-10-10 14:02:21,046][76542] Updated weights for policy 1, policy_version 34710 (0.0008) -[2023-10-10 14:02:21,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 71106560. Throughput: 0: 1831.2, 1: 1816.5. Samples: 17783040. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:02:21,077][75634] Avg episode reward: [(0, '30.270'), (1, '34.690')] -[2023-10-10 14:02:21,407][76542] Updated weights for policy 1, policy_version 34720 (0.0008) -[2023-10-10 14:02:23,184][76543] Updated weights for policy 0, policy_version 34753 (0.0010) -[2023-10-10 14:02:23,556][76543] Updated weights for policy 0, policy_version 34763 (0.0009) -[2023-10-10 14:02:23,925][76543] Updated weights for policy 0, policy_version 34773 (0.0007) -[2023-10-10 14:02:24,303][76543] Updated weights for policy 0, policy_version 34783 (0.0007) -[2023-10-10 14:02:24,997][76542] Updated weights for policy 1, policy_version 34730 (0.0007) -[2023-10-10 14:02:25,371][76542] Updated weights for policy 1, policy_version 34740 (0.0009) -[2023-10-10 14:02:25,743][76542] Updated weights for policy 1, policy_version 34750 (0.0008) -[2023-10-10 14:02:26,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 71204864. Throughput: 0: 1831.9, 1: 1816.6. Samples: 17804648. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:02:26,077][75634] Avg episode reward: [(0, '34.660'), (1, '34.760')] -[2023-10-10 14:02:27,819][76543] Updated weights for policy 0, policy_version 34793 (0.0009) -[2023-10-10 14:02:28,190][76543] Updated weights for policy 0, policy_version 34803 (0.0007) -[2023-10-10 14:02:28,551][76543] Updated weights for policy 0, policy_version 34813 (0.0010) -[2023-10-10 14:02:29,413][76542] Updated weights for policy 1, policy_version 34760 (0.0009) -[2023-10-10 14:02:29,786][76542] Updated weights for policy 1, policy_version 34770 (0.0010) -[2023-10-10 14:02:30,147][76542] Updated weights for policy 1, policy_version 34780 (0.0010) -[2023-10-10 14:02:31,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 71270400. Throughput: 0: 1833.8, 1: 1823.9. Samples: 17826150. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:02:31,077][75634] Avg episode reward: [(0, '34.910'), (1, '33.160')] -[2023-10-10 14:02:31,086][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000034784_35618816.pth... -[2023-10-10 14:02:31,086][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000034816_35651584.pth... -[2023-10-10 14:02:31,126][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000033088_33882112.pth -[2023-10-10 14:02:31,127][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000033120_33914880.pth -[2023-10-10 14:02:32,300][76543] Updated weights for policy 0, policy_version 34823 (0.0008) -[2023-10-10 14:02:32,675][76543] Updated weights for policy 0, policy_version 34833 (0.0007) -[2023-10-10 14:02:33,043][76543] Updated weights for policy 0, policy_version 34843 (0.0009) -[2023-10-10 14:02:33,780][76542] Updated weights for policy 1, policy_version 34790 (0.0010) -[2023-10-10 14:02:34,152][76542] Updated weights for policy 1, policy_version 34800 (0.0007) -[2023-10-10 14:02:34,514][76542] Updated weights for policy 1, policy_version 34810 (0.0008) -[2023-10-10 14:02:36,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 71335936. Throughput: 0: 1828.6, 1: 1825.6. Samples: 17837578. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-10 14:02:36,076][75634] Avg episode reward: [(0, '33.640'), (1, '30.340')] -[2023-10-10 14:02:36,533][76543] Updated weights for policy 0, policy_version 34853 (0.0007) -[2023-10-10 14:02:36,899][76543] Updated weights for policy 0, policy_version 34863 (0.0008) -[2023-10-10 14:02:37,276][76543] Updated weights for policy 0, policy_version 34873 (0.0009) -[2023-10-10 14:02:38,072][76542] Updated weights for policy 1, policy_version 34820 (0.0008) -[2023-10-10 14:02:38,434][76542] Updated weights for policy 1, policy_version 34830 (0.0008) -[2023-10-10 14:02:38,800][76542] Updated weights for policy 1, policy_version 34840 (0.0010) -[2023-10-10 14:02:40,808][76543] Updated weights for policy 0, policy_version 34883 (0.0007) -[2023-10-10 14:02:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 71401472. Throughput: 0: 1830.3, 1: 1831.9. Samples: 17859348. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-10 14:02:41,076][75634] Avg episode reward: [(0, '32.530'), (1, '33.400')] -[2023-10-10 14:02:41,174][76543] Updated weights for policy 0, policy_version 34893 (0.0007) -[2023-10-10 14:02:41,548][76543] Updated weights for policy 0, policy_version 34903 (0.0007) -[2023-10-10 14:02:42,304][76542] Updated weights for policy 1, policy_version 34850 (0.0007) -[2023-10-10 14:02:42,668][76542] Updated weights for policy 1, policy_version 34860 (0.0007) -[2023-10-10 14:02:43,041][76542] Updated weights for policy 1, policy_version 34870 (0.0007) -[2023-10-10 14:02:43,408][76542] Updated weights for policy 1, policy_version 34880 (0.0007) -[2023-10-10 14:02:45,123][76543] Updated weights for policy 0, policy_version 34913 (0.0007) -[2023-10-10 14:02:45,506][76543] Updated weights for policy 0, policy_version 34923 (0.0010) -[2023-10-10 14:02:45,872][76543] Updated weights for policy 0, policy_version 34933 (0.0011) -[2023-10-10 14:02:46,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 71467008. Throughput: 0: 1832.9, 1: 1839.2. Samples: 17882542. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-10 14:02:46,077][75634] Avg episode reward: [(0, '32.330'), (1, '34.440')] -[2023-10-10 14:02:46,245][76543] Updated weights for policy 0, policy_version 34943 (0.0009) -[2023-10-10 14:02:47,118][76542] Updated weights for policy 1, policy_version 34890 (0.0007) -[2023-10-10 14:02:47,494][76542] Updated weights for policy 1, policy_version 34900 (0.0010) -[2023-10-10 14:02:47,858][76542] Updated weights for policy 1, policy_version 34910 (0.0010) -[2023-10-10 14:02:49,903][76543] Updated weights for policy 0, policy_version 34953 (0.0008) -[2023-10-10 14:02:50,277][76543] Updated weights for policy 0, policy_version 34963 (0.0008) -[2023-10-10 14:02:50,657][76543] Updated weights for policy 0, policy_version 34973 (0.0009) -[2023-10-10 14:02:51,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 71565312. Throughput: 0: 1838.8, 1: 1838.8. Samples: 17892644. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-10 14:02:51,077][75634] Avg episode reward: [(0, '37.430'), (1, '31.660')] -[2023-10-10 14:02:51,652][76542] Updated weights for policy 1, policy_version 34920 (0.0011) -[2023-10-10 14:02:52,014][76542] Updated weights for policy 1, policy_version 34930 (0.0008) -[2023-10-10 14:02:52,389][76542] Updated weights for policy 1, policy_version 34940 (0.0007) -[2023-10-10 14:02:54,469][76543] Updated weights for policy 0, policy_version 34983 (0.0010) -[2023-10-10 14:02:54,842][76543] Updated weights for policy 0, policy_version 34993 (0.0009) -[2023-10-10 14:02:55,210][76543] Updated weights for policy 0, policy_version 35003 (0.0010) -[2023-10-10 14:02:55,872][76542] Updated weights for policy 1, policy_version 34950 (0.0009) -[2023-10-10 14:02:56,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 71630848. Throughput: 0: 1826.9, 1: 1845.8. Samples: 17915526. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-10 14:02:56,076][75634] Avg episode reward: [(0, '39.540'), (1, '31.080')] -[2023-10-10 14:02:56,240][76542] Updated weights for policy 1, policy_version 34960 (0.0011) -[2023-10-10 14:02:56,608][76542] Updated weights for policy 1, policy_version 34970 (0.0009) -[2023-10-10 14:02:58,933][76543] Updated weights for policy 0, policy_version 35013 (0.0008) -[2023-10-10 14:02:59,308][76543] Updated weights for policy 0, policy_version 35023 (0.0009) -[2023-10-10 14:02:59,680][76543] Updated weights for policy 0, policy_version 35033 (0.0008) -[2023-10-10 14:03:00,160][76542] Updated weights for policy 1, policy_version 34980 (0.0008) -[2023-10-10 14:03:00,525][76542] Updated weights for policy 1, policy_version 34990 (0.0008) -[2023-10-10 14:03:00,896][76542] Updated weights for policy 1, policy_version 35000 (0.0008) -[2023-10-10 14:03:01,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 71696384. Throughput: 0: 1828.0, 1: 1834.9. Samples: 17936348. Policy #0 lag: (min: 12.0, avg: 12.8, max: 31.0) -[2023-10-10 14:03:01,076][75634] Avg episode reward: [(0, '34.710'), (1, '29.550')] -[2023-10-10 14:03:03,315][76543] Updated weights for policy 0, policy_version 35043 (0.0010) -[2023-10-10 14:03:03,710][76543] Updated weights for policy 0, policy_version 35053 (0.0011) -[2023-10-10 14:03:04,091][76543] Updated weights for policy 0, policy_version 35063 (0.0010) -[2023-10-10 14:03:04,602][76542] Updated weights for policy 1, policy_version 35010 (0.0007) -[2023-10-10 14:03:04,962][76542] Updated weights for policy 1, policy_version 35020 (0.0008) -[2023-10-10 14:03:05,327][76542] Updated weights for policy 1, policy_version 35030 (0.0009) -[2023-10-10 14:03:05,693][76542] Updated weights for policy 1, policy_version 35040 (0.0008) -[2023-10-10 14:03:06,076][75634] Fps is (10 sec: 16383.8, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 71794688. Throughput: 0: 1827.9, 1: 1856.2. Samples: 17948826. Policy #0 lag: (min: 12.0, avg: 12.8, max: 31.0) -[2023-10-10 14:03:06,077][75634] Avg episode reward: [(0, '34.130'), (1, '34.190')] -[2023-10-10 14:03:07,848][76543] Updated weights for policy 0, policy_version 35073 (0.0008) -[2023-10-10 14:03:08,215][76543] Updated weights for policy 0, policy_version 35083 (0.0007) -[2023-10-10 14:03:08,590][76543] Updated weights for policy 0, policy_version 35093 (0.0008) -[2023-10-10 14:03:08,964][76543] Updated weights for policy 0, policy_version 35103 (0.0007) -[2023-10-10 14:03:09,387][76542] Updated weights for policy 1, policy_version 35050 (0.0010) -[2023-10-10 14:03:09,762][76542] Updated weights for policy 1, policy_version 35060 (0.0007) -[2023-10-10 14:03:10,124][76542] Updated weights for policy 1, policy_version 35070 (0.0010) -[2023-10-10 14:03:11,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 71860224. Throughput: 0: 1819.8, 1: 1837.3. Samples: 17969216. Policy #0 lag: (min: 12.0, avg: 12.8, max: 31.0) -[2023-10-10 14:03:11,077][75634] Avg episode reward: [(0, '33.750'), (1, '32.300')] -[2023-10-10 14:03:12,601][76543] Updated weights for policy 0, policy_version 35113 (0.0008) -[2023-10-10 14:03:12,980][76543] Updated weights for policy 0, policy_version 35123 (0.0009) -[2023-10-10 14:03:13,350][76543] Updated weights for policy 0, policy_version 35133 (0.0009) -[2023-10-10 14:03:13,862][76542] Updated weights for policy 1, policy_version 35080 (0.0010) -[2023-10-10 14:03:14,241][76542] Updated weights for policy 1, policy_version 35090 (0.0009) -[2023-10-10 14:03:14,605][76542] Updated weights for policy 1, policy_version 35100 (0.0009) -[2023-10-10 14:03:16,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 71925760. Throughput: 0: 1823.0, 1: 1851.7. Samples: 17991510. Policy #0 lag: (min: 12.0, avg: 12.8, max: 31.0) -[2023-10-10 14:03:16,077][75634] Avg episode reward: [(0, '35.510'), (1, '31.620')] -[2023-10-10 14:03:17,090][76543] Updated weights for policy 0, policy_version 35143 (0.0007) -[2023-10-10 14:03:17,465][76543] Updated weights for policy 0, policy_version 35153 (0.0007) -[2023-10-10 14:03:17,835][76543] Updated weights for policy 0, policy_version 35163 (0.0008) -[2023-10-10 14:03:18,398][76542] Updated weights for policy 1, policy_version 35110 (0.0008) -[2023-10-10 14:03:18,767][76542] Updated weights for policy 1, policy_version 35120 (0.0007) -[2023-10-10 14:03:19,141][76542] Updated weights for policy 1, policy_version 35130 (0.0007) -[2023-10-10 14:03:21,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 71991296. Throughput: 0: 1824.5, 1: 1832.0. Samples: 18002120. Policy #0 lag: (min: 12.0, avg: 12.8, max: 31.0) -[2023-10-10 14:03:21,076][75634] Avg episode reward: [(0, '30.690'), (1, '33.670')] -[2023-10-10 14:03:21,469][76543] Updated weights for policy 0, policy_version 35173 (0.0008) -[2023-10-10 14:03:21,833][76543] Updated weights for policy 0, policy_version 35183 (0.0010) -[2023-10-10 14:03:22,201][76543] Updated weights for policy 0, policy_version 35193 (0.0007) -[2023-10-10 14:03:22,763][76542] Updated weights for policy 1, policy_version 35140 (0.0010) -[2023-10-10 14:03:23,133][76542] Updated weights for policy 1, policy_version 35150 (0.0009) -[2023-10-10 14:03:23,505][76542] Updated weights for policy 1, policy_version 35160 (0.0009) -[2023-10-10 14:03:25,911][76543] Updated weights for policy 0, policy_version 35203 (0.0009) -[2023-10-10 14:03:26,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 72056832. Throughput: 0: 1825.6, 1: 1839.6. Samples: 18024280. Policy #0 lag: (min: 12.0, avg: 12.8, max: 31.0) -[2023-10-10 14:03:26,076][75634] Avg episode reward: [(0, '33.300'), (1, '36.200')] -[2023-10-10 14:03:26,267][76543] Updated weights for policy 0, policy_version 35213 (0.0010) -[2023-10-10 14:03:26,633][76543] Updated weights for policy 0, policy_version 35223 (0.0010) -[2023-10-10 14:03:27,100][76542] Updated weights for policy 1, policy_version 35170 (0.0009) -[2023-10-10 14:03:27,474][76542] Updated weights for policy 1, policy_version 35180 (0.0011) -[2023-10-10 14:03:27,837][76542] Updated weights for policy 1, policy_version 35190 (0.0009) -[2023-10-10 14:03:28,203][76542] Updated weights for policy 1, policy_version 35200 (0.0010) -[2023-10-10 14:03:30,326][76543] Updated weights for policy 0, policy_version 35233 (0.0010) -[2023-10-10 14:03:30,699][76543] Updated weights for policy 0, policy_version 35243 (0.0009) -[2023-10-10 14:03:31,076][75634] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 72122368. Throughput: 0: 1825.1, 1: 1834.6. Samples: 18047228. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-10-10 14:03:31,077][75634] Avg episode reward: [(0, '32.640'), (1, '37.450')] -[2023-10-10 14:03:31,081][76543] Updated weights for policy 0, policy_version 35253 (0.0009) -[2023-10-10 14:03:31,456][76543] Updated weights for policy 0, policy_version 35263 (0.0010) -[2023-10-10 14:03:31,825][76542] Updated weights for policy 1, policy_version 35210 (0.0009) -[2023-10-10 14:03:32,181][76542] Updated weights for policy 1, policy_version 35220 (0.0011) -[2023-10-10 14:03:32,556][76542] Updated weights for policy 1, policy_version 35230 (0.0008) -[2023-10-10 14:03:35,239][76543] Updated weights for policy 0, policy_version 35273 (0.0009) -[2023-10-10 14:03:35,625][76543] Updated weights for policy 0, policy_version 35283 (0.0008) -[2023-10-10 14:03:35,999][76543] Updated weights for policy 0, policy_version 35293 (0.0010) -[2023-10-10 14:03:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 72187904. Throughput: 0: 1821.8, 1: 1836.1. Samples: 18057248. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-10-10 14:03:36,077][75634] Avg episode reward: [(0, '31.320'), (1, '37.920')] -[2023-10-10 14:03:36,239][76542] Updated weights for policy 1, policy_version 35240 (0.0007) -[2023-10-10 14:03:36,618][76542] Updated weights for policy 1, policy_version 35250 (0.0008) -[2023-10-10 14:03:36,979][76542] Updated weights for policy 1, policy_version 35260 (0.0009) -[2023-10-10 14:03:39,729][76543] Updated weights for policy 0, policy_version 35303 (0.0010) -[2023-10-10 14:03:40,097][76543] Updated weights for policy 0, policy_version 35313 (0.0011) -[2023-10-10 14:03:40,476][76543] Updated weights for policy 0, policy_version 35323 (0.0009) -[2023-10-10 14:03:40,590][76542] Updated weights for policy 1, policy_version 35270 (0.0009) -[2023-10-10 14:03:40,960][76542] Updated weights for policy 1, policy_version 35280 (0.0011) -[2023-10-10 14:03:41,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 72286208. Throughput: 0: 1823.1, 1: 1832.7. Samples: 18080038. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-10-10 14:03:41,077][75634] Avg episode reward: [(0, '33.810'), (1, '35.240')] -[2023-10-10 14:03:41,336][76542] Updated weights for policy 1, policy_version 35290 (0.0008) -[2023-10-10 14:03:43,965][76543] Updated weights for policy 0, policy_version 35333 (0.0008) -[2023-10-10 14:03:44,340][76543] Updated weights for policy 0, policy_version 35343 (0.0008) -[2023-10-10 14:03:44,709][76543] Updated weights for policy 0, policy_version 35353 (0.0009) -[2023-10-10 14:03:45,006][76542] Updated weights for policy 1, policy_version 35300 (0.0009) -[2023-10-10 14:03:45,376][76542] Updated weights for policy 1, policy_version 35310 (0.0007) -[2023-10-10 14:03:45,746][76542] Updated weights for policy 1, policy_version 35320 (0.0007) -[2023-10-10 14:03:46,076][75634] Fps is (10 sec: 19660.7, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 72384512. Throughput: 0: 1827.6, 1: 1823.1. Samples: 18100630. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-10-10 14:03:46,077][75634] Avg episode reward: [(0, '37.420'), (1, '33.660')] -[2023-10-10 14:03:48,561][76543] Updated weights for policy 0, policy_version 35363 (0.0007) -[2023-10-10 14:03:48,956][76543] Updated weights for policy 0, policy_version 35373 (0.0008) -[2023-10-10 14:03:49,321][76543] Updated weights for policy 0, policy_version 35383 (0.0009) -[2023-10-10 14:03:49,470][76542] Updated weights for policy 1, policy_version 35330 (0.0008) -[2023-10-10 14:03:49,842][76542] Updated weights for policy 1, policy_version 35340 (0.0009) -[2023-10-10 14:03:50,211][76542] Updated weights for policy 1, policy_version 35350 (0.0007) -[2023-10-10 14:03:50,583][76542] Updated weights for policy 1, policy_version 35360 (0.0008) -[2023-10-10 14:03:51,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 72450048. Throughput: 0: 1822.6, 1: 1821.7. Samples: 18112818. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-10-10 14:03:51,077][75634] Avg episode reward: [(0, '35.760'), (1, '31.830')] -[2023-10-10 14:03:52,923][76543] Updated weights for policy 0, policy_version 35393 (0.0010) -[2023-10-10 14:03:53,295][76543] Updated weights for policy 0, policy_version 35403 (0.0011) -[2023-10-10 14:03:53,666][76543] Updated weights for policy 0, policy_version 35413 (0.0010) -[2023-10-10 14:03:54,038][76543] Updated weights for policy 0, policy_version 35423 (0.0009) -[2023-10-10 14:03:54,353][76542] Updated weights for policy 1, policy_version 35370 (0.0009) -[2023-10-10 14:03:54,719][76542] Updated weights for policy 1, policy_version 35380 (0.0008) -[2023-10-10 14:03:55,093][76542] Updated weights for policy 1, policy_version 35390 (0.0008) -[2023-10-10 14:03:56,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 72515584. Throughput: 0: 1818.2, 1: 1827.3. Samples: 18133266. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:03:56,077][75634] Avg episode reward: [(0, '38.690'), (1, '31.710')] -[2023-10-10 14:03:57,743][76543] Updated weights for policy 0, policy_version 35433 (0.0009) -[2023-10-10 14:03:58,107][76543] Updated weights for policy 0, policy_version 35443 (0.0008) -[2023-10-10 14:03:58,476][76543] Updated weights for policy 0, policy_version 35453 (0.0008) -[2023-10-10 14:03:58,820][76542] Updated weights for policy 1, policy_version 35400 (0.0009) -[2023-10-10 14:03:59,186][76542] Updated weights for policy 1, policy_version 35410 (0.0010) -[2023-10-10 14:03:59,551][76542] Updated weights for policy 1, policy_version 35420 (0.0009) -[2023-10-10 14:04:01,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 72581120. Throughput: 0: 1817.1, 1: 1825.1. Samples: 18155406. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:04:01,077][75634] Avg episode reward: [(0, '36.900'), (1, '29.000')] -[2023-10-10 14:04:02,161][76543] Updated weights for policy 0, policy_version 35463 (0.0010) -[2023-10-10 14:04:02,534][76543] Updated weights for policy 0, policy_version 35473 (0.0010) -[2023-10-10 14:04:02,906][76543] Updated weights for policy 0, policy_version 35483 (0.0009) -[2023-10-10 14:04:03,097][76542] Updated weights for policy 1, policy_version 35430 (0.0008) -[2023-10-10 14:04:03,472][76542] Updated weights for policy 1, policy_version 35440 (0.0007) -[2023-10-10 14:04:03,837][76542] Updated weights for policy 1, policy_version 35450 (0.0008) -[2023-10-10 14:04:06,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 72646656. Throughput: 0: 1818.8, 1: 1824.1. Samples: 18166052. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:04:06,077][75634] Avg episode reward: [(0, '37.720'), (1, '27.800')] -[2023-10-10 14:04:06,482][76543] Updated weights for policy 0, policy_version 35493 (0.0007) -[2023-10-10 14:04:06,855][76543] Updated weights for policy 0, policy_version 35503 (0.0007) -[2023-10-10 14:04:07,228][76543] Updated weights for policy 0, policy_version 35513 (0.0008) -[2023-10-10 14:04:07,397][76542] Updated weights for policy 1, policy_version 35460 (0.0008) -[2023-10-10 14:04:07,752][76542] Updated weights for policy 1, policy_version 35470 (0.0008) -[2023-10-10 14:04:08,125][76542] Updated weights for policy 1, policy_version 35480 (0.0007) -[2023-10-10 14:04:10,768][76543] Updated weights for policy 0, policy_version 35523 (0.0007) -[2023-10-10 14:04:11,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 72712192. Throughput: 0: 1821.2, 1: 1836.4. Samples: 18188872. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:04:11,076][75634] Avg episode reward: [(0, '35.650'), (1, '32.550')] -[2023-10-10 14:04:11,141][76543] Updated weights for policy 0, policy_version 35533 (0.0009) -[2023-10-10 14:04:11,519][76543] Updated weights for policy 0, policy_version 35543 (0.0008) -[2023-10-10 14:04:11,774][76542] Updated weights for policy 1, policy_version 35490 (0.0007) -[2023-10-10 14:04:12,152][76542] Updated weights for policy 1, policy_version 35500 (0.0009) -[2023-10-10 14:04:12,525][76542] Updated weights for policy 1, policy_version 35510 (0.0008) -[2023-10-10 14:04:12,887][76542] Updated weights for policy 1, policy_version 35520 (0.0008) -[2023-10-10 14:04:15,108][76543] Updated weights for policy 0, policy_version 35553 (0.0009) -[2023-10-10 14:04:15,489][76543] Updated weights for policy 0, policy_version 35563 (0.0009) -[2023-10-10 14:04:15,852][76543] Updated weights for policy 0, policy_version 35573 (0.0010) -[2023-10-10 14:04:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 72777728. Throughput: 0: 1817.2, 1: 1838.0. Samples: 18211710. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:04:16,077][75634] Avg episode reward: [(0, '33.690'), (1, '33.760')] -[2023-10-10 14:04:16,229][76543] Updated weights for policy 0, policy_version 35583 (0.0008) -[2023-10-10 14:04:16,631][76542] Updated weights for policy 1, policy_version 35530 (0.0011) -[2023-10-10 14:04:17,001][76542] Updated weights for policy 1, policy_version 35540 (0.0008) -[2023-10-10 14:04:17,371][76542] Updated weights for policy 1, policy_version 35550 (0.0008) -[2023-10-10 14:04:20,109][76543] Updated weights for policy 0, policy_version 35593 (0.0011) -[2023-10-10 14:04:20,486][76543] Updated weights for policy 0, policy_version 35603 (0.0009) -[2023-10-10 14:04:20,850][76543] Updated weights for policy 0, policy_version 35613 (0.0007) -[2023-10-10 14:04:21,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 72876032. Throughput: 0: 1819.3, 1: 1835.7. Samples: 18221726. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-10 14:04:21,077][75634] Avg episode reward: [(0, '34.160'), (1, '33.830')] -[2023-10-10 14:04:21,215][76542] Updated weights for policy 1, policy_version 35560 (0.0010) -[2023-10-10 14:04:21,596][76542] Updated weights for policy 1, policy_version 35570 (0.0008) -[2023-10-10 14:04:21,961][76542] Updated weights for policy 1, policy_version 35580 (0.0007) -[2023-10-10 14:04:24,545][76543] Updated weights for policy 0, policy_version 35623 (0.0008) -[2023-10-10 14:04:24,916][76543] Updated weights for policy 0, policy_version 35633 (0.0010) -[2023-10-10 14:04:25,282][76543] Updated weights for policy 0, policy_version 35643 (0.0009) -[2023-10-10 14:04:25,565][76542] Updated weights for policy 1, policy_version 35590 (0.0009) -[2023-10-10 14:04:25,948][76542] Updated weights for policy 1, policy_version 35600 (0.0008) -[2023-10-10 14:04:26,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 72941568. Throughput: 0: 1824.4, 1: 1833.6. Samples: 18244648. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-10 14:04:26,077][75634] Avg episode reward: [(0, '30.650'), (1, '33.540')] -[2023-10-10 14:04:26,316][76542] Updated weights for policy 1, policy_version 35610 (0.0008) -[2023-10-10 14:04:28,887][76543] Updated weights for policy 0, policy_version 35653 (0.0009) -[2023-10-10 14:04:29,260][76543] Updated weights for policy 0, policy_version 35663 (0.0011) -[2023-10-10 14:04:29,631][76543] Updated weights for policy 0, policy_version 35673 (0.0010) -[2023-10-10 14:04:30,000][76542] Updated weights for policy 1, policy_version 35620 (0.0008) -[2023-10-10 14:04:30,366][76542] Updated weights for policy 1, policy_version 35630 (0.0008) -[2023-10-10 14:04:30,730][76542] Updated weights for policy 1, policy_version 35640 (0.0007) -[2023-10-10 14:04:31,076][75634] Fps is (10 sec: 16384.3, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 73039872. Throughput: 0: 1821.3, 1: 1828.4. Samples: 18264868. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-10 14:04:31,076][75634] Avg episode reward: [(0, '31.550'), (1, '35.150')] -[2023-10-10 14:04:31,084][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000035680_36536320.pth... -[2023-10-10 14:04:31,084][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000035648_36503552.pth... -[2023-10-10 14:04:31,124][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000033984_34799616.pth -[2023-10-10 14:04:31,124][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000033920_34734080.pth -[2023-10-10 14:04:33,409][76543] Updated weights for policy 0, policy_version 35683 (0.0010) -[2023-10-10 14:04:33,798][76543] Updated weights for policy 0, policy_version 35693 (0.0010) -[2023-10-10 14:04:34,167][76543] Updated weights for policy 0, policy_version 35703 (0.0008) -[2023-10-10 14:04:34,386][76542] Updated weights for policy 1, policy_version 35650 (0.0008) -[2023-10-10 14:04:34,753][76542] Updated weights for policy 1, policy_version 35660 (0.0009) -[2023-10-10 14:04:35,120][76542] Updated weights for policy 1, policy_version 35670 (0.0009) -[2023-10-10 14:04:35,492][76542] Updated weights for policy 1, policy_version 35680 (0.0008) -[2023-10-10 14:04:36,076][75634] Fps is (10 sec: 16384.4, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 73105408. Throughput: 0: 1827.4, 1: 1833.6. Samples: 18277562. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-10 14:04:36,076][75634] Avg episode reward: [(0, '33.640'), (1, '31.110')] -[2023-10-10 14:04:37,875][76543] Updated weights for policy 0, policy_version 35713 (0.0008) -[2023-10-10 14:04:38,239][76543] Updated weights for policy 0, policy_version 35723 (0.0008) -[2023-10-10 14:04:38,609][76543] Updated weights for policy 0, policy_version 35733 (0.0007) -[2023-10-10 14:04:38,974][76543] Updated weights for policy 0, policy_version 35743 (0.0007) -[2023-10-10 14:04:39,167][76542] Updated weights for policy 1, policy_version 35690 (0.0009) -[2023-10-10 14:04:39,537][76542] Updated weights for policy 1, policy_version 35700 (0.0009) -[2023-10-10 14:04:39,907][76542] Updated weights for policy 1, policy_version 35710 (0.0007) -[2023-10-10 14:04:41,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 73170944. Throughput: 0: 1830.8, 1: 1819.2. Samples: 18297514. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-10 14:04:41,077][75634] Avg episode reward: [(0, '35.810'), (1, '29.480')] -[2023-10-10 14:04:42,483][76543] Updated weights for policy 0, policy_version 35753 (0.0009) -[2023-10-10 14:04:42,863][76543] Updated weights for policy 0, policy_version 35763 (0.0010) -[2023-10-10 14:04:43,240][76543] Updated weights for policy 0, policy_version 35773 (0.0008) -[2023-10-10 14:04:43,631][76542] Updated weights for policy 1, policy_version 35720 (0.0007) -[2023-10-10 14:04:44,002][76542] Updated weights for policy 1, policy_version 35730 (0.0007) -[2023-10-10 14:04:44,369][76542] Updated weights for policy 1, policy_version 35740 (0.0008) -[2023-10-10 14:04:46,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14662.3). Total num frames: 73236480. Throughput: 0: 1830.1, 1: 1826.8. Samples: 18319966. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-10 14:04:46,076][75634] Avg episode reward: [(0, '33.600'), (1, '33.000')] -[2023-10-10 14:04:46,909][76543] Updated weights for policy 0, policy_version 35783 (0.0008) -[2023-10-10 14:04:47,280][76543] Updated weights for policy 0, policy_version 35793 (0.0008) -[2023-10-10 14:04:47,652][76543] Updated weights for policy 0, policy_version 35803 (0.0008) -[2023-10-10 14:04:48,227][76542] Updated weights for policy 1, policy_version 35750 (0.0011) -[2023-10-10 14:04:48,618][76542] Updated weights for policy 1, policy_version 35760 (0.0009) -[2023-10-10 14:04:48,983][76542] Updated weights for policy 1, policy_version 35770 (0.0007) -[2023-10-10 14:04:51,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 73302016. Throughput: 0: 1830.2, 1: 1821.9. Samples: 18330398. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:04:51,077][75634] Avg episode reward: [(0, '34.500'), (1, '32.030')] -[2023-10-10 14:04:51,302][76543] Updated weights for policy 0, policy_version 35813 (0.0008) -[2023-10-10 14:04:51,670][76543] Updated weights for policy 0, policy_version 35823 (0.0007) -[2023-10-10 14:04:52,038][76543] Updated weights for policy 0, policy_version 35833 (0.0009) -[2023-10-10 14:04:52,659][76542] Updated weights for policy 1, policy_version 35780 (0.0009) -[2023-10-10 14:04:53,033][76542] Updated weights for policy 1, policy_version 35790 (0.0010) -[2023-10-10 14:04:53,406][76542] Updated weights for policy 1, policy_version 35800 (0.0008) -[2023-10-10 14:04:55,697][76543] Updated weights for policy 0, policy_version 35843 (0.0008) -[2023-10-10 14:04:56,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 73367552. Throughput: 0: 1822.6, 1: 1808.3. Samples: 18352262. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:04:56,077][76543] Updated weights for policy 0, policy_version 35853 (0.0008) -[2023-10-10 14:04:56,077][75634] Avg episode reward: [(0, '33.770'), (1, '33.950')] -[2023-10-10 14:04:56,452][76543] Updated weights for policy 0, policy_version 35863 (0.0008) -[2023-10-10 14:04:57,136][76542] Updated weights for policy 1, policy_version 35810 (0.0011) -[2023-10-10 14:04:57,500][76542] Updated weights for policy 1, policy_version 35820 (0.0007) -[2023-10-10 14:04:57,876][76542] Updated weights for policy 1, policy_version 35830 (0.0010) -[2023-10-10 14:04:58,243][76542] Updated weights for policy 1, policy_version 35840 (0.0008) -[2023-10-10 14:05:00,026][76543] Updated weights for policy 0, policy_version 35873 (0.0007) -[2023-10-10 14:05:00,395][76543] Updated weights for policy 0, policy_version 35883 (0.0008) -[2023-10-10 14:05:00,771][76543] Updated weights for policy 0, policy_version 35893 (0.0009) -[2023-10-10 14:05:01,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 73433088. Throughput: 0: 1824.9, 1: 1800.8. Samples: 18374868. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:05:01,076][75634] Avg episode reward: [(0, '33.910'), (1, '32.110')] -[2023-10-10 14:05:01,148][76543] Updated weights for policy 0, policy_version 35903 (0.0007) -[2023-10-10 14:05:02,062][76542] Updated weights for policy 1, policy_version 35850 (0.0009) -[2023-10-10 14:05:02,430][76542] Updated weights for policy 1, policy_version 35860 (0.0009) -[2023-10-10 14:05:02,794][76542] Updated weights for policy 1, policy_version 35870 (0.0009) -[2023-10-10 14:05:04,765][76543] Updated weights for policy 0, policy_version 35913 (0.0008) -[2023-10-10 14:05:05,135][76543] Updated weights for policy 0, policy_version 35923 (0.0007) -[2023-10-10 14:05:05,503][76543] Updated weights for policy 0, policy_version 35933 (0.0008) -[2023-10-10 14:05:06,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 73531392. Throughput: 0: 1831.5, 1: 1802.6. Samples: 18385262. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:05:06,077][75634] Avg episode reward: [(0, '33.570'), (1, '35.030')] -[2023-10-10 14:05:06,433][76542] Updated weights for policy 1, policy_version 35880 (0.0008) -[2023-10-10 14:05:06,802][76542] Updated weights for policy 1, policy_version 35890 (0.0011) -[2023-10-10 14:05:07,171][76542] Updated weights for policy 1, policy_version 35900 (0.0010) -[2023-10-10 14:05:09,185][76543] Updated weights for policy 0, policy_version 35943 (0.0009) -[2023-10-10 14:05:09,556][76543] Updated weights for policy 0, policy_version 35953 (0.0009) -[2023-10-10 14:05:09,943][76543] Updated weights for policy 0, policy_version 35963 (0.0009) -[2023-10-10 14:05:10,721][76542] Updated weights for policy 1, policy_version 35910 (0.0008) -[2023-10-10 14:05:11,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 73596928. Throughput: 0: 1821.1, 1: 1802.8. Samples: 18407722. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:05:11,077][75634] Avg episode reward: [(0, '35.550'), (1, '35.990')] -[2023-10-10 14:05:11,083][76542] Updated weights for policy 1, policy_version 35920 (0.0007) -[2023-10-10 14:05:11,454][76542] Updated weights for policy 1, policy_version 35930 (0.0007) -[2023-10-10 14:05:13,648][76543] Updated weights for policy 0, policy_version 35973 (0.0008) -[2023-10-10 14:05:14,023][76543] Updated weights for policy 0, policy_version 35983 (0.0011) -[2023-10-10 14:05:14,386][76543] Updated weights for policy 0, policy_version 35993 (0.0008) -[2023-10-10 14:05:15,158][76542] Updated weights for policy 1, policy_version 35940 (0.0008) -[2023-10-10 14:05:15,538][76542] Updated weights for policy 1, policy_version 35950 (0.0009) -[2023-10-10 14:05:15,905][76542] Updated weights for policy 1, policy_version 35960 (0.0008) -[2023-10-10 14:05:16,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 73662464. Throughput: 0: 1828.7, 1: 1807.0. Samples: 18428474. Policy #0 lag: (min: 7.0, avg: 28.2, max: 32.0) -[2023-10-10 14:05:16,076][75634] Avg episode reward: [(0, '34.140'), (1, '34.030')] -[2023-10-10 14:05:18,014][76543] Updated weights for policy 0, policy_version 36003 (0.0009) -[2023-10-10 14:05:18,386][76543] Updated weights for policy 0, policy_version 36013 (0.0009) -[2023-10-10 14:05:18,763][76543] Updated weights for policy 0, policy_version 36023 (0.0008) -[2023-10-10 14:05:19,535][76542] Updated weights for policy 1, policy_version 35970 (0.0008) -[2023-10-10 14:05:19,898][76542] Updated weights for policy 1, policy_version 35980 (0.0009) -[2023-10-10 14:05:20,260][76542] Updated weights for policy 1, policy_version 35990 (0.0011) -[2023-10-10 14:05:20,631][76542] Updated weights for policy 1, policy_version 36000 (0.0009) -[2023-10-10 14:05:21,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 73760768. Throughput: 0: 1822.5, 1: 1802.1. Samples: 18440668. Policy #0 lag: (min: 7.0, avg: 28.2, max: 32.0) -[2023-10-10 14:05:21,076][75634] Avg episode reward: [(0, '36.330'), (1, '34.860')] -[2023-10-10 14:05:22,607][76543] Updated weights for policy 0, policy_version 36033 (0.0009) -[2023-10-10 14:05:22,985][76543] Updated weights for policy 0, policy_version 36043 (0.0007) -[2023-10-10 14:05:23,361][76543] Updated weights for policy 0, policy_version 36053 (0.0009) -[2023-10-10 14:05:23,739][76543] Updated weights for policy 0, policy_version 36063 (0.0007) -[2023-10-10 14:05:24,367][76542] Updated weights for policy 1, policy_version 36010 (0.0008) -[2023-10-10 14:05:24,732][76542] Updated weights for policy 1, policy_version 36020 (0.0008) -[2023-10-10 14:05:25,099][76542] Updated weights for policy 1, policy_version 36030 (0.0010) -[2023-10-10 14:05:26,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 73826304. Throughput: 0: 1829.1, 1: 1813.0. Samples: 18461406. Policy #0 lag: (min: 7.0, avg: 28.2, max: 32.0) -[2023-10-10 14:05:26,077][75634] Avg episode reward: [(0, '32.740'), (1, '33.410')] -[2023-10-10 14:05:27,362][76543] Updated weights for policy 0, policy_version 36073 (0.0007) -[2023-10-10 14:05:27,738][76543] Updated weights for policy 0, policy_version 36083 (0.0007) -[2023-10-10 14:05:28,106][76543] Updated weights for policy 0, policy_version 36093 (0.0007) -[2023-10-10 14:05:28,873][76542] Updated weights for policy 1, policy_version 36040 (0.0009) -[2023-10-10 14:05:29,240][76542] Updated weights for policy 1, policy_version 36050 (0.0008) -[2023-10-10 14:05:29,609][76542] Updated weights for policy 1, policy_version 36060 (0.0009) -[2023-10-10 14:05:31,076][75634] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14662.3). Total num frames: 73891840. Throughput: 0: 1826.0, 1: 1805.7. Samples: 18483394. Policy #0 lag: (min: 7.0, avg: 28.2, max: 32.0) -[2023-10-10 14:05:31,077][75634] Avg episode reward: [(0, '35.880'), (1, '34.600')] -[2023-10-10 14:05:32,002][76543] Updated weights for policy 0, policy_version 36103 (0.0008) -[2023-10-10 14:05:32,381][76543] Updated weights for policy 0, policy_version 36113 (0.0010) -[2023-10-10 14:05:32,737][76543] Updated weights for policy 0, policy_version 36123 (0.0008) -[2023-10-10 14:05:33,461][76542] Updated weights for policy 1, policy_version 36070 (0.0010) -[2023-10-10 14:05:33,848][76542] Updated weights for policy 1, policy_version 36080 (0.0010) -[2023-10-10 14:05:34,209][76542] Updated weights for policy 1, policy_version 36090 (0.0007) -[2023-10-10 14:05:36,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 73957376. Throughput: 0: 1822.5, 1: 1813.1. Samples: 18493998. Policy #0 lag: (min: 7.0, avg: 28.2, max: 32.0) -[2023-10-10 14:05:36,077][75634] Avg episode reward: [(0, '40.200'), (1, '37.510')] -[2023-10-10 14:05:36,077][76362] Saving new best policy, reward=40.200! -[2023-10-10 14:05:36,431][76543] Updated weights for policy 0, policy_version 36133 (0.0010) -[2023-10-10 14:05:36,808][76543] Updated weights for policy 0, policy_version 36143 (0.0009) -[2023-10-10 14:05:37,176][76543] Updated weights for policy 0, policy_version 36153 (0.0007) -[2023-10-10 14:05:37,919][76542] Updated weights for policy 1, policy_version 36100 (0.0007) -[2023-10-10 14:05:38,291][76542] Updated weights for policy 1, policy_version 36110 (0.0008) -[2023-10-10 14:05:38,668][76542] Updated weights for policy 1, policy_version 36120 (0.0010) -[2023-10-10 14:05:40,845][76543] Updated weights for policy 0, policy_version 36163 (0.0009) -[2023-10-10 14:05:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 74022912. Throughput: 0: 1826.6, 1: 1804.9. Samples: 18515680. Policy #0 lag: (min: 7.0, avg: 28.2, max: 32.0) -[2023-10-10 14:05:41,077][75634] Avg episode reward: [(0, '36.460'), (1, '33.550')] -[2023-10-10 14:05:41,215][76543] Updated weights for policy 0, policy_version 36173 (0.0009) -[2023-10-10 14:05:41,588][76543] Updated weights for policy 0, policy_version 36183 (0.0009) -[2023-10-10 14:05:42,339][76542] Updated weights for policy 1, policy_version 36130 (0.0010) -[2023-10-10 14:05:42,721][76542] Updated weights for policy 1, policy_version 36140 (0.0009) -[2023-10-10 14:05:43,099][76542] Updated weights for policy 1, policy_version 36150 (0.0010) -[2023-10-10 14:05:43,468][76542] Updated weights for policy 1, policy_version 36160 (0.0007) -[2023-10-10 14:05:45,286][76543] Updated weights for policy 0, policy_version 36193 (0.0009) -[2023-10-10 14:05:45,664][76543] Updated weights for policy 0, policy_version 36203 (0.0007) -[2023-10-10 14:05:46,045][76543] Updated weights for policy 0, policy_version 36213 (0.0008) -[2023-10-10 14:05:46,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 74088448. Throughput: 0: 1823.9, 1: 1811.2. Samples: 18538448. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-10 14:05:46,076][75634] Avg episode reward: [(0, '33.620'), (1, '37.380')] -[2023-10-10 14:05:46,425][76543] Updated weights for policy 0, policy_version 36223 (0.0009) -[2023-10-10 14:05:47,034][76542] Updated weights for policy 1, policy_version 36170 (0.0009) -[2023-10-10 14:05:47,406][76542] Updated weights for policy 1, policy_version 36180 (0.0007) -[2023-10-10 14:05:47,770][76542] Updated weights for policy 1, policy_version 36190 (0.0007) -[2023-10-10 14:05:50,003][76543] Updated weights for policy 0, policy_version 36233 (0.0010) -[2023-10-10 14:05:50,379][76543] Updated weights for policy 0, policy_version 36243 (0.0008) -[2023-10-10 14:05:50,754][76543] Updated weights for policy 0, policy_version 36253 (0.0007) -[2023-10-10 14:05:51,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 74186752. Throughput: 0: 1813.0, 1: 1810.8. Samples: 18548336. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-10 14:05:51,078][75634] Avg episode reward: [(0, '33.210'), (1, '35.780')] -[2023-10-10 14:05:51,458][76542] Updated weights for policy 1, policy_version 36200 (0.0008) -[2023-10-10 14:05:51,815][76542] Updated weights for policy 1, policy_version 36210 (0.0009) -[2023-10-10 14:05:52,183][76542] Updated weights for policy 1, policy_version 36220 (0.0007) -[2023-10-10 14:05:54,360][76543] Updated weights for policy 0, policy_version 36263 (0.0009) -[2023-10-10 14:05:54,730][76543] Updated weights for policy 0, policy_version 36273 (0.0009) -[2023-10-10 14:05:55,098][76543] Updated weights for policy 0, policy_version 36283 (0.0007) -[2023-10-10 14:05:55,891][76542] Updated weights for policy 1, policy_version 36230 (0.0007) -[2023-10-10 14:05:56,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 74252288. Throughput: 0: 1816.9, 1: 1815.5. Samples: 18571180. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-10 14:05:56,077][75634] Avg episode reward: [(0, '37.510'), (1, '33.980')] -[2023-10-10 14:05:56,259][76542] Updated weights for policy 1, policy_version 36240 (0.0007) -[2023-10-10 14:05:56,626][76542] Updated weights for policy 1, policy_version 36250 (0.0007) -[2023-10-10 14:05:58,748][76543] Updated weights for policy 0, policy_version 36293 (0.0008) -[2023-10-10 14:05:59,127][76543] Updated weights for policy 0, policy_version 36303 (0.0007) -[2023-10-10 14:05:59,497][76543] Updated weights for policy 0, policy_version 36313 (0.0010) -[2023-10-10 14:06:00,169][76542] Updated weights for policy 1, policy_version 36260 (0.0007) -[2023-10-10 14:06:00,551][76542] Updated weights for policy 1, policy_version 36270 (0.0009) -[2023-10-10 14:06:00,911][76542] Updated weights for policy 1, policy_version 36280 (0.0012) -[2023-10-10 14:06:01,076][75634] Fps is (10 sec: 13107.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 74317824. Throughput: 0: 1817.5, 1: 1820.0. Samples: 18592162. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-10 14:06:01,076][75634] Avg episode reward: [(0, '35.930'), (1, '33.180')] -[2023-10-10 14:06:03,190][76543] Updated weights for policy 0, policy_version 36323 (0.0010) -[2023-10-10 14:06:03,571][76543] Updated weights for policy 0, policy_version 36333 (0.0009) -[2023-10-10 14:06:03,946][76543] Updated weights for policy 0, policy_version 36343 (0.0009) -[2023-10-10 14:06:04,645][76542] Updated weights for policy 1, policy_version 36290 (0.0011) -[2023-10-10 14:06:05,018][76542] Updated weights for policy 1, policy_version 36300 (0.0008) -[2023-10-10 14:06:05,373][76542] Updated weights for policy 1, policy_version 36310 (0.0009) -[2023-10-10 14:06:05,740][76542] Updated weights for policy 1, policy_version 36320 (0.0007) -[2023-10-10 14:06:06,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 74416128. Throughput: 0: 1814.1, 1: 1818.8. Samples: 18604150. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-10 14:06:06,077][75634] Avg episode reward: [(0, '32.280'), (1, '35.530')] -[2023-10-10 14:06:07,570][76543] Updated weights for policy 0, policy_version 36353 (0.0008) -[2023-10-10 14:06:07,927][76543] Updated weights for policy 0, policy_version 36363 (0.0008) -[2023-10-10 14:06:08,302][76543] Updated weights for policy 0, policy_version 36373 (0.0009) -[2023-10-10 14:06:08,681][76543] Updated weights for policy 0, policy_version 36383 (0.0011) -[2023-10-10 14:06:09,465][76542] Updated weights for policy 1, policy_version 36330 (0.0009) -[2023-10-10 14:06:09,837][76542] Updated weights for policy 1, policy_version 36340 (0.0009) -[2023-10-10 14:06:10,208][76542] Updated weights for policy 1, policy_version 36350 (0.0008) -[2023-10-10 14:06:11,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 74481664. Throughput: 0: 1815.3, 1: 1823.6. Samples: 18625152. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:06:11,076][75634] Avg episode reward: [(0, '33.150'), (1, '34.390')] -[2023-10-10 14:06:12,491][76543] Updated weights for policy 0, policy_version 36393 (0.0009) -[2023-10-10 14:06:12,856][76543] Updated weights for policy 0, policy_version 36403 (0.0008) -[2023-10-10 14:06:13,225][76543] Updated weights for policy 0, policy_version 36413 (0.0007) -[2023-10-10 14:06:13,884][76542] Updated weights for policy 1, policy_version 36360 (0.0008) -[2023-10-10 14:06:14,260][76542] Updated weights for policy 1, policy_version 36370 (0.0008) -[2023-10-10 14:06:14,620][76542] Updated weights for policy 1, policy_version 36380 (0.0009) -[2023-10-10 14:06:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 74547200. Throughput: 0: 1815.1, 1: 1828.3. Samples: 18647346. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:06:16,077][75634] Avg episode reward: [(0, '34.080'), (1, '32.790')] -[2023-10-10 14:06:16,937][76543] Updated weights for policy 0, policy_version 36423 (0.0009) -[2023-10-10 14:06:17,302][76543] Updated weights for policy 0, policy_version 36433 (0.0011) -[2023-10-10 14:06:17,676][76543] Updated weights for policy 0, policy_version 36443 (0.0008) -[2023-10-10 14:06:18,356][76542] Updated weights for policy 1, policy_version 36390 (0.0010) -[2023-10-10 14:06:18,734][76542] Updated weights for policy 1, policy_version 36400 (0.0008) -[2023-10-10 14:06:19,103][76542] Updated weights for policy 1, policy_version 36410 (0.0007) -[2023-10-10 14:06:21,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 74612736. Throughput: 0: 1814.4, 1: 1826.3. Samples: 18657826. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:06:21,077][75634] Avg episode reward: [(0, '37.500'), (1, '32.350')] -[2023-10-10 14:06:21,379][76543] Updated weights for policy 0, policy_version 36453 (0.0008) -[2023-10-10 14:06:21,746][76543] Updated weights for policy 0, policy_version 36463 (0.0008) -[2023-10-10 14:06:22,113][76543] Updated weights for policy 0, policy_version 36473 (0.0009) -[2023-10-10 14:06:22,654][76542] Updated weights for policy 1, policy_version 36420 (0.0008) -[2023-10-10 14:06:23,024][76542] Updated weights for policy 1, policy_version 36430 (0.0011) -[2023-10-10 14:06:23,389][76542] Updated weights for policy 1, policy_version 36440 (0.0009) -[2023-10-10 14:06:25,893][76543] Updated weights for policy 0, policy_version 36483 (0.0007) -[2023-10-10 14:06:26,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 74678272. Throughput: 0: 1810.8, 1: 1835.6. Samples: 18679766. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:06:26,076][75634] Avg episode reward: [(0, '37.140'), (1, '34.570')] -[2023-10-10 14:06:26,257][76543] Updated weights for policy 0, policy_version 36493 (0.0008) -[2023-10-10 14:06:26,630][76543] Updated weights for policy 0, policy_version 36503 (0.0007) -[2023-10-10 14:06:27,065][76542] Updated weights for policy 1, policy_version 36450 (0.0008) -[2023-10-10 14:06:27,431][76542] Updated weights for policy 1, policy_version 36460 (0.0008) -[2023-10-10 14:06:27,792][76542] Updated weights for policy 1, policy_version 36470 (0.0011) -[2023-10-10 14:06:28,161][76542] Updated weights for policy 1, policy_version 36480 (0.0009) -[2023-10-10 14:06:30,295][76543] Updated weights for policy 0, policy_version 36513 (0.0007) -[2023-10-10 14:06:30,665][76543] Updated weights for policy 0, policy_version 36523 (0.0010) -[2023-10-10 14:06:31,033][76543] Updated weights for policy 0, policy_version 36533 (0.0009) -[2023-10-10 14:06:31,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 74743808. Throughput: 0: 1814.0, 1: 1830.7. Samples: 18702456. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:06:31,076][75634] Avg episode reward: [(0, '37.210'), (1, '36.360')] -[2023-10-10 14:06:31,086][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000036480_37355520.pth... -[2023-10-10 14:06:31,119][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000034784_35618816.pth -[2023-10-10 14:06:31,411][76543] Updated weights for policy 0, policy_version 36543 (0.0008) -[2023-10-10 14:06:31,441][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000036544_37421056.pth... -[2023-10-10 14:06:31,470][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000034816_35651584.pth -[2023-10-10 14:06:31,985][76542] Updated weights for policy 1, policy_version 36490 (0.0007) -[2023-10-10 14:06:32,351][76542] Updated weights for policy 1, policy_version 36500 (0.0009) -[2023-10-10 14:06:32,719][76542] Updated weights for policy 1, policy_version 36510 (0.0008) -[2023-10-10 14:06:35,107][76543] Updated weights for policy 0, policy_version 36553 (0.0009) -[2023-10-10 14:06:35,477][76543] Updated weights for policy 0, policy_version 36563 (0.0010) -[2023-10-10 14:06:35,851][76543] Updated weights for policy 0, policy_version 36573 (0.0007) -[2023-10-10 14:06:36,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 74842112. Throughput: 0: 1813.3, 1: 1826.2. Samples: 18712110. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:06:36,076][75634] Avg episode reward: [(0, '36.320'), (1, '33.520')] -[2023-10-10 14:06:36,529][76542] Updated weights for policy 1, policy_version 36520 (0.0010) -[2023-10-10 14:06:36,898][76542] Updated weights for policy 1, policy_version 36530 (0.0010) -[2023-10-10 14:06:37,269][76542] Updated weights for policy 1, policy_version 36540 (0.0010) -[2023-10-10 14:06:39,485][76543] Updated weights for policy 0, policy_version 36583 (0.0008) -[2023-10-10 14:06:39,854][76543] Updated weights for policy 0, policy_version 36593 (0.0009) -[2023-10-10 14:06:40,228][76543] Updated weights for policy 0, policy_version 36603 (0.0007) -[2023-10-10 14:06:40,850][76542] Updated weights for policy 1, policy_version 36550 (0.0010) -[2023-10-10 14:06:41,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 74907648. Throughput: 0: 1820.4, 1: 1824.4. Samples: 18735200. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:06:41,077][75634] Avg episode reward: [(0, '34.560'), (1, '34.640')] -[2023-10-10 14:06:41,210][76542] Updated weights for policy 1, policy_version 36560 (0.0009) -[2023-10-10 14:06:41,582][76542] Updated weights for policy 1, policy_version 36570 (0.0010) -[2023-10-10 14:06:43,927][76543] Updated weights for policy 0, policy_version 36613 (0.0007) -[2023-10-10 14:06:44,293][76543] Updated weights for policy 0, policy_version 36623 (0.0008) -[2023-10-10 14:06:44,657][76543] Updated weights for policy 0, policy_version 36633 (0.0010) -[2023-10-10 14:06:45,308][76542] Updated weights for policy 1, policy_version 36580 (0.0009) -[2023-10-10 14:06:45,666][76542] Updated weights for policy 1, policy_version 36590 (0.0009) -[2023-10-10 14:06:46,049][76542] Updated weights for policy 1, policy_version 36600 (0.0010) -[2023-10-10 14:06:46,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 74973184. Throughput: 0: 1811.1, 1: 1826.9. Samples: 18755872. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:06:46,076][75634] Avg episode reward: [(0, '33.550'), (1, '34.680')] -[2023-10-10 14:06:48,349][76543] Updated weights for policy 0, policy_version 36643 (0.0010) -[2023-10-10 14:06:48,750][76543] Updated weights for policy 0, policy_version 36653 (0.0008) -[2023-10-10 14:06:49,112][76543] Updated weights for policy 0, policy_version 36663 (0.0007) -[2023-10-10 14:06:49,895][76542] Updated weights for policy 1, policy_version 36610 (0.0009) -[2023-10-10 14:06:50,272][76542] Updated weights for policy 1, policy_version 36620 (0.0008) -[2023-10-10 14:06:50,634][76542] Updated weights for policy 1, policy_version 36630 (0.0009) -[2023-10-10 14:06:51,008][76542] Updated weights for policy 1, policy_version 36640 (0.0008) -[2023-10-10 14:06:51,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 75071488. Throughput: 0: 1816.0, 1: 1817.9. Samples: 18767674. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:06:51,077][75634] Avg episode reward: [(0, '28.640'), (1, '36.180')] -[2023-10-10 14:06:52,829][76543] Updated weights for policy 0, policy_version 36673 (0.0009) -[2023-10-10 14:06:53,197][76543] Updated weights for policy 0, policy_version 36683 (0.0009) -[2023-10-10 14:06:53,574][76543] Updated weights for policy 0, policy_version 36693 (0.0008) -[2023-10-10 14:06:53,955][76543] Updated weights for policy 0, policy_version 36703 (0.0009) -[2023-10-10 14:06:54,621][76542] Updated weights for policy 1, policy_version 36650 (0.0011) -[2023-10-10 14:06:54,996][76542] Updated weights for policy 1, policy_version 36660 (0.0011) -[2023-10-10 14:06:55,376][76542] Updated weights for policy 1, policy_version 36670 (0.0009) -[2023-10-10 14:06:56,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 75137024. Throughput: 0: 1808.7, 1: 1817.5. Samples: 18788336. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:06:56,077][75634] Avg episode reward: [(0, '31.280'), (1, '36.110')] -[2023-10-10 14:06:57,672][76543] Updated weights for policy 0, policy_version 36713 (0.0007) -[2023-10-10 14:06:58,031][76543] Updated weights for policy 0, policy_version 36723 (0.0008) -[2023-10-10 14:06:58,404][76543] Updated weights for policy 0, policy_version 36733 (0.0008) -[2023-10-10 14:06:59,188][76542] Updated weights for policy 1, policy_version 36680 (0.0011) -[2023-10-10 14:06:59,551][76542] Updated weights for policy 1, policy_version 36690 (0.0010) -[2023-10-10 14:06:59,921][76542] Updated weights for policy 1, policy_version 36700 (0.0011) -[2023-10-10 14:07:01,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 75202560. Throughput: 0: 1813.6, 1: 1805.7. Samples: 18810212. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:07:01,076][75634] Avg episode reward: [(0, '35.230'), (1, '37.490')] -[2023-10-10 14:07:01,907][76543] Updated weights for policy 0, policy_version 36743 (0.0009) -[2023-10-10 14:07:02,282][76543] Updated weights for policy 0, policy_version 36753 (0.0007) -[2023-10-10 14:07:02,654][76543] Updated weights for policy 0, policy_version 36763 (0.0010) -[2023-10-10 14:07:03,810][76542] Updated weights for policy 1, policy_version 36710 (0.0010) -[2023-10-10 14:07:04,202][76542] Updated weights for policy 1, policy_version 36720 (0.0010) -[2023-10-10 14:07:04,568][76542] Updated weights for policy 1, policy_version 36730 (0.0008) -[2023-10-10 14:07:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 75268096. Throughput: 0: 1815.3, 1: 1814.8. Samples: 18821178. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 14:07:06,077][75634] Avg episode reward: [(0, '35.010'), (1, '33.590')] -[2023-10-10 14:07:06,498][76543] Updated weights for policy 0, policy_version 36773 (0.0009) -[2023-10-10 14:07:06,866][76543] Updated weights for policy 0, policy_version 36783 (0.0007) -[2023-10-10 14:07:07,228][76543] Updated weights for policy 0, policy_version 36793 (0.0007) -[2023-10-10 14:07:08,167][76542] Updated weights for policy 1, policy_version 36740 (0.0010) -[2023-10-10 14:07:08,538][76542] Updated weights for policy 1, policy_version 36750 (0.0010) -[2023-10-10 14:07:08,905][76542] Updated weights for policy 1, policy_version 36760 (0.0008) -[2023-10-10 14:07:10,822][76543] Updated weights for policy 0, policy_version 36803 (0.0007) -[2023-10-10 14:07:11,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 75333632. Throughput: 0: 1819.0, 1: 1795.2. Samples: 18842408. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 14:07:11,077][75634] Avg episode reward: [(0, '37.110'), (1, '31.810')] -[2023-10-10 14:07:11,187][76543] Updated weights for policy 0, policy_version 36813 (0.0008) -[2023-10-10 14:07:11,562][76543] Updated weights for policy 0, policy_version 36823 (0.0010) -[2023-10-10 14:07:12,437][76542] Updated weights for policy 1, policy_version 36770 (0.0008) -[2023-10-10 14:07:12,815][76542] Updated weights for policy 1, policy_version 36780 (0.0008) -[2023-10-10 14:07:13,189][76542] Updated weights for policy 1, policy_version 36790 (0.0009) -[2023-10-10 14:07:13,562][76542] Updated weights for policy 1, policy_version 36800 (0.0008) -[2023-10-10 14:07:15,300][76543] Updated weights for policy 0, policy_version 36833 (0.0008) -[2023-10-10 14:07:15,668][76543] Updated weights for policy 0, policy_version 36843 (0.0008) -[2023-10-10 14:07:16,040][76543] Updated weights for policy 0, policy_version 36853 (0.0007) -[2023-10-10 14:07:16,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 75399168. Throughput: 0: 1819.0, 1: 1803.7. Samples: 18865476. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 14:07:16,076][75634] Avg episode reward: [(0, '35.880'), (1, '33.560')] -[2023-10-10 14:07:16,414][76543] Updated weights for policy 0, policy_version 36863 (0.0009) -[2023-10-10 14:07:17,204][76542] Updated weights for policy 1, policy_version 36810 (0.0008) -[2023-10-10 14:07:17,568][76542] Updated weights for policy 1, policy_version 36820 (0.0010) -[2023-10-10 14:07:17,938][76542] Updated weights for policy 1, policy_version 36830 (0.0011) -[2023-10-10 14:07:20,188][76543] Updated weights for policy 0, policy_version 36873 (0.0009) -[2023-10-10 14:07:20,563][76543] Updated weights for policy 0, policy_version 36883 (0.0010) -[2023-10-10 14:07:20,934][76543] Updated weights for policy 0, policy_version 36893 (0.0010) -[2023-10-10 14:07:21,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 75497472. Throughput: 0: 1819.0, 1: 1806.7. Samples: 18875264. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 14:07:21,077][75634] Avg episode reward: [(0, '37.570'), (1, '31.450')] -[2023-10-10 14:07:21,814][76542] Updated weights for policy 1, policy_version 36840 (0.0009) -[2023-10-10 14:07:22,174][76542] Updated weights for policy 1, policy_version 36850 (0.0008) -[2023-10-10 14:07:22,541][76542] Updated weights for policy 1, policy_version 36860 (0.0008) -[2023-10-10 14:07:24,650][76543] Updated weights for policy 0, policy_version 36903 (0.0010) -[2023-10-10 14:07:25,023][76543] Updated weights for policy 0, policy_version 36913 (0.0010) -[2023-10-10 14:07:25,399][76543] Updated weights for policy 0, policy_version 36923 (0.0007) -[2023-10-10 14:07:26,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 75563008. Throughput: 0: 1817.8, 1: 1800.0. Samples: 18897998. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 14:07:26,076][75634] Avg episode reward: [(0, '36.890'), (1, '31.130')] -[2023-10-10 14:07:26,296][76542] Updated weights for policy 1, policy_version 36870 (0.0007) -[2023-10-10 14:07:26,667][76542] Updated weights for policy 1, policy_version 36880 (0.0007) -[2023-10-10 14:07:27,044][76542] Updated weights for policy 1, policy_version 36890 (0.0009) -[2023-10-10 14:07:29,053][76543] Updated weights for policy 0, policy_version 36933 (0.0007) -[2023-10-10 14:07:29,427][76543] Updated weights for policy 0, policy_version 36943 (0.0008) -[2023-10-10 14:07:29,793][76543] Updated weights for policy 0, policy_version 36953 (0.0008) -[2023-10-10 14:07:30,648][76542] Updated weights for policy 1, policy_version 36900 (0.0007) -[2023-10-10 14:07:31,023][76542] Updated weights for policy 1, policy_version 36910 (0.0008) -[2023-10-10 14:07:31,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 75628544. Throughput: 0: 1819.3, 1: 1810.4. Samples: 18919210. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-10 14:07:31,077][75634] Avg episode reward: [(0, '33.990'), (1, '29.530')] -[2023-10-10 14:07:31,387][76542] Updated weights for policy 1, policy_version 36920 (0.0010) -[2023-10-10 14:07:33,535][76543] Updated weights for policy 0, policy_version 36963 (0.0009) -[2023-10-10 14:07:33,920][76543] Updated weights for policy 0, policy_version 36973 (0.0010) -[2023-10-10 14:07:34,302][76543] Updated weights for policy 0, policy_version 36983 (0.0010) -[2023-10-10 14:07:35,186][76542] Updated weights for policy 1, policy_version 36930 (0.0010) -[2023-10-10 14:07:35,551][76542] Updated weights for policy 1, policy_version 36940 (0.0010) -[2023-10-10 14:07:35,928][76542] Updated weights for policy 1, policy_version 36950 (0.0011) -[2023-10-10 14:07:36,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 75694080. Throughput: 0: 1820.7, 1: 1802.8. Samples: 18930730. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-10 14:07:36,077][75634] Avg episode reward: [(0, '33.410'), (1, '32.360')] -[2023-10-10 14:07:36,292][76542] Updated weights for policy 1, policy_version 36960 (0.0011) -[2023-10-10 14:07:37,925][76543] Updated weights for policy 0, policy_version 36993 (0.0009) -[2023-10-10 14:07:38,289][76543] Updated weights for policy 0, policy_version 37003 (0.0007) -[2023-10-10 14:07:38,657][76543] Updated weights for policy 0, policy_version 37013 (0.0008) -[2023-10-10 14:07:39,033][76543] Updated weights for policy 0, policy_version 37023 (0.0009) -[2023-10-10 14:07:39,998][76542] Updated weights for policy 1, policy_version 36970 (0.0009) -[2023-10-10 14:07:40,370][76542] Updated weights for policy 1, policy_version 36980 (0.0009) -[2023-10-10 14:07:40,728][76542] Updated weights for policy 1, policy_version 36990 (0.0009) -[2023-10-10 14:07:41,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 75792384. Throughput: 0: 1819.3, 1: 1814.0. Samples: 18951836. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-10 14:07:41,077][75634] Avg episode reward: [(0, '33.210'), (1, '34.990')] -[2023-10-10 14:07:42,805][76543] Updated weights for policy 0, policy_version 37033 (0.0012) -[2023-10-10 14:07:43,176][76543] Updated weights for policy 0, policy_version 37043 (0.0012) -[2023-10-10 14:07:43,544][76543] Updated weights for policy 0, policy_version 37053 (0.0008) -[2023-10-10 14:07:44,274][76542] Updated weights for policy 1, policy_version 37000 (0.0010) -[2023-10-10 14:07:44,639][76542] Updated weights for policy 1, policy_version 37010 (0.0010) -[2023-10-10 14:07:45,010][76542] Updated weights for policy 1, policy_version 37020 (0.0008) -[2023-10-10 14:07:46,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 75857920. Throughput: 0: 1819.5, 1: 1811.8. Samples: 18973622. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-10 14:07:46,077][75634] Avg episode reward: [(0, '36.620'), (1, '35.520')] -[2023-10-10 14:07:47,169][76543] Updated weights for policy 0, policy_version 37063 (0.0008) -[2023-10-10 14:07:47,537][76543] Updated weights for policy 0, policy_version 37073 (0.0008) -[2023-10-10 14:07:47,903][76543] Updated weights for policy 0, policy_version 37083 (0.0009) -[2023-10-10 14:07:48,592][76542] Updated weights for policy 1, policy_version 37030 (0.0009) -[2023-10-10 14:07:48,956][76542] Updated weights for policy 1, policy_version 37040 (0.0008) -[2023-10-10 14:07:49,320][76542] Updated weights for policy 1, policy_version 37050 (0.0008) -[2023-10-10 14:07:51,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 75923456. Throughput: 0: 1820.6, 1: 1814.0. Samples: 18984732. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-10 14:07:51,077][75634] Avg episode reward: [(0, '36.410'), (1, '37.630')] -[2023-10-10 14:07:51,462][76543] Updated weights for policy 0, policy_version 37093 (0.0009) -[2023-10-10 14:07:51,836][76543] Updated weights for policy 0, policy_version 37103 (0.0009) -[2023-10-10 14:07:52,211][76543] Updated weights for policy 0, policy_version 37113 (0.0008) -[2023-10-10 14:07:52,935][76542] Updated weights for policy 1, policy_version 37060 (0.0009) -[2023-10-10 14:07:53,308][76542] Updated weights for policy 1, policy_version 37070 (0.0007) -[2023-10-10 14:07:53,673][76542] Updated weights for policy 1, policy_version 37080 (0.0007) -[2023-10-10 14:07:55,775][76543] Updated weights for policy 0, policy_version 37123 (0.0008) -[2023-10-10 14:07:56,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 75988992. Throughput: 0: 1825.2, 1: 1825.2. Samples: 19006674. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-10 14:07:56,077][75634] Avg episode reward: [(0, '38.270'), (1, '38.140')] -[2023-10-10 14:07:56,150][76543] Updated weights for policy 0, policy_version 37133 (0.0009) -[2023-10-10 14:07:56,515][76543] Updated weights for policy 0, policy_version 37143 (0.0008) -[2023-10-10 14:07:57,468][76542] Updated weights for policy 1, policy_version 37090 (0.0009) -[2023-10-10 14:07:57,831][76542] Updated weights for policy 1, policy_version 37100 (0.0010) -[2023-10-10 14:07:58,206][76542] Updated weights for policy 1, policy_version 37110 (0.0011) -[2023-10-10 14:07:58,576][76542] Updated weights for policy 1, policy_version 37120 (0.0012) -[2023-10-10 14:08:00,250][76543] Updated weights for policy 0, policy_version 37153 (0.0008) -[2023-10-10 14:08:00,619][76543] Updated weights for policy 0, policy_version 37163 (0.0009) -[2023-10-10 14:08:00,990][76543] Updated weights for policy 0, policy_version 37173 (0.0009) -[2023-10-10 14:08:01,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 76054528. Throughput: 0: 1825.2, 1: 1813.1. Samples: 19029200. Policy #0 lag: (min: 31.0, avg: 31.3, max: 42.0) -[2023-10-10 14:08:01,077][75634] Avg episode reward: [(0, '36.480'), (1, '37.140')] -[2023-10-10 14:08:01,365][76543] Updated weights for policy 0, policy_version 37183 (0.0011) -[2023-10-10 14:08:02,229][76542] Updated weights for policy 1, policy_version 37130 (0.0010) -[2023-10-10 14:08:02,596][76542] Updated weights for policy 1, policy_version 37140 (0.0010) -[2023-10-10 14:08:02,965][76542] Updated weights for policy 1, policy_version 37150 (0.0010) -[2023-10-10 14:08:05,015][76543] Updated weights for policy 0, policy_version 37193 (0.0010) -[2023-10-10 14:08:05,394][76543] Updated weights for policy 0, policy_version 37203 (0.0009) -[2023-10-10 14:08:05,763][76543] Updated weights for policy 0, policy_version 37213 (0.0008) -[2023-10-10 14:08:06,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 76152832. Throughput: 0: 1826.9, 1: 1817.6. Samples: 19039264. Policy #0 lag: (min: 31.0, avg: 31.3, max: 42.0) -[2023-10-10 14:08:06,077][75634] Avg episode reward: [(0, '35.850'), (1, '34.560')] -[2023-10-10 14:08:06,677][76542] Updated weights for policy 1, policy_version 37160 (0.0010) -[2023-10-10 14:08:07,051][76542] Updated weights for policy 1, policy_version 37170 (0.0009) -[2023-10-10 14:08:07,412][76542] Updated weights for policy 1, policy_version 37180 (0.0011) -[2023-10-10 14:08:09,454][76543] Updated weights for policy 0, policy_version 37223 (0.0007) -[2023-10-10 14:08:09,836][76543] Updated weights for policy 0, policy_version 37233 (0.0007) -[2023-10-10 14:08:10,207][76543] Updated weights for policy 0, policy_version 37243 (0.0007) -[2023-10-10 14:08:11,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 76218368. Throughput: 0: 1824.1, 1: 1819.4. Samples: 19061956. Policy #0 lag: (min: 31.0, avg: 31.3, max: 42.0) -[2023-10-10 14:08:11,076][75634] Avg episode reward: [(0, '34.420'), (1, '35.580')] -[2023-10-10 14:08:11,234][76542] Updated weights for policy 1, policy_version 37190 (0.0010) -[2023-10-10 14:08:11,609][76542] Updated weights for policy 1, policy_version 37200 (0.0010) -[2023-10-10 14:08:11,978][76542] Updated weights for policy 1, policy_version 37210 (0.0008) -[2023-10-10 14:08:13,794][76543] Updated weights for policy 0, policy_version 37253 (0.0009) -[2023-10-10 14:08:14,165][76543] Updated weights for policy 0, policy_version 37263 (0.0011) -[2023-10-10 14:08:14,529][76543] Updated weights for policy 0, policy_version 37273 (0.0008) -[2023-10-10 14:08:15,618][76542] Updated weights for policy 1, policy_version 37220 (0.0008) -[2023-10-10 14:08:15,990][76542] Updated weights for policy 1, policy_version 37230 (0.0009) -[2023-10-10 14:08:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 76283904. Throughput: 0: 1828.2, 1: 1813.1. Samples: 19083070. Policy #0 lag: (min: 31.0, avg: 31.3, max: 42.0) -[2023-10-10 14:08:16,077][75634] Avg episode reward: [(0, '30.040'), (1, '34.980')] -[2023-10-10 14:08:16,358][76542] Updated weights for policy 1, policy_version 37240 (0.0008) -[2023-10-10 14:08:18,206][76543] Updated weights for policy 0, policy_version 37283 (0.0008) -[2023-10-10 14:08:18,604][76543] Updated weights for policy 0, policy_version 37293 (0.0009) -[2023-10-10 14:08:18,976][76543] Updated weights for policy 0, policy_version 37303 (0.0009) -[2023-10-10 14:08:20,199][76542] Updated weights for policy 1, policy_version 37250 (0.0008) -[2023-10-10 14:08:20,561][76542] Updated weights for policy 1, policy_version 37260 (0.0007) -[2023-10-10 14:08:20,930][76542] Updated weights for policy 1, policy_version 37270 (0.0008) -[2023-10-10 14:08:21,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 76349440. Throughput: 0: 1825.6, 1: 1817.3. Samples: 19094658. Policy #0 lag: (min: 31.0, avg: 31.3, max: 42.0) -[2023-10-10 14:08:21,077][75634] Avg episode reward: [(0, '32.260'), (1, '31.640')] -[2023-10-10 14:08:21,304][76542] Updated weights for policy 1, policy_version 37280 (0.0009) -[2023-10-10 14:08:22,619][76543] Updated weights for policy 0, policy_version 37313 (0.0009) -[2023-10-10 14:08:22,983][76543] Updated weights for policy 0, policy_version 37323 (0.0010) -[2023-10-10 14:08:23,358][76543] Updated weights for policy 0, policy_version 37333 (0.0009) -[2023-10-10 14:08:23,725][76543] Updated weights for policy 0, policy_version 37343 (0.0010) -[2023-10-10 14:08:24,969][76542] Updated weights for policy 1, policy_version 37290 (0.0007) -[2023-10-10 14:08:25,341][76542] Updated weights for policy 1, policy_version 37300 (0.0008) -[2023-10-10 14:08:25,707][76542] Updated weights for policy 1, policy_version 37310 (0.0011) -[2023-10-10 14:08:26,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 76447744. Throughput: 0: 1828.6, 1: 1818.1. Samples: 19115936. Policy #0 lag: (min: 14.0, avg: 18.4, max: 46.0) -[2023-10-10 14:08:26,077][75634] Avg episode reward: [(0, '33.660'), (1, '32.870')] -[2023-10-10 14:08:27,384][76543] Updated weights for policy 0, policy_version 37353 (0.0007) -[2023-10-10 14:08:27,759][76543] Updated weights for policy 0, policy_version 37363 (0.0009) -[2023-10-10 14:08:28,120][76543] Updated weights for policy 0, policy_version 37373 (0.0008) -[2023-10-10 14:08:29,328][76542] Updated weights for policy 1, policy_version 37320 (0.0010) -[2023-10-10 14:08:29,696][76542] Updated weights for policy 1, policy_version 37330 (0.0008) -[2023-10-10 14:08:30,061][76542] Updated weights for policy 1, policy_version 37340 (0.0008) -[2023-10-10 14:08:31,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 76513280. Throughput: 0: 1830.2, 1: 1815.6. Samples: 19137682. Policy #0 lag: (min: 14.0, avg: 18.4, max: 46.0) -[2023-10-10 14:08:31,077][75634] Avg episode reward: [(0, '36.230'), (1, '37.050')] -[2023-10-10 14:08:31,089][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000037376_38273024.pth... -[2023-10-10 14:08:31,090][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000037344_38240256.pth... -[2023-10-10 14:08:31,128][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000035648_36503552.pth -[2023-10-10 14:08:31,129][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000035680_36536320.pth -[2023-10-10 14:08:31,897][76543] Updated weights for policy 0, policy_version 37383 (0.0009) -[2023-10-10 14:08:32,274][76543] Updated weights for policy 0, policy_version 37393 (0.0007) -[2023-10-10 14:08:32,636][76543] Updated weights for policy 0, policy_version 37403 (0.0010) -[2023-10-10 14:08:33,777][76542] Updated weights for policy 1, policy_version 37350 (0.0007) -[2023-10-10 14:08:34,164][76542] Updated weights for policy 1, policy_version 37360 (0.0008) -[2023-10-10 14:08:34,526][76542] Updated weights for policy 1, policy_version 37370 (0.0010) -[2023-10-10 14:08:36,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 76578816. Throughput: 0: 1829.3, 1: 1818.8. Samples: 19148896. Policy #0 lag: (min: 14.0, avg: 18.4, max: 46.0) -[2023-10-10 14:08:36,077][75634] Avg episode reward: [(0, '42.200'), (1, '38.130')] -[2023-10-10 14:08:36,121][76543] Updated weights for policy 0, policy_version 37413 (0.0007) -[2023-10-10 14:08:36,497][76543] Updated weights for policy 0, policy_version 37423 (0.0007) -[2023-10-10 14:08:36,862][76543] Updated weights for policy 0, policy_version 37433 (0.0011) -[2023-10-10 14:08:37,120][76362] Saving new best policy, reward=42.200! -[2023-10-10 14:08:38,224][76542] Updated weights for policy 1, policy_version 37380 (0.0009) -[2023-10-10 14:08:38,587][76542] Updated weights for policy 1, policy_version 37390 (0.0009) -[2023-10-10 14:08:38,956][76542] Updated weights for policy 1, policy_version 37400 (0.0008) -[2023-10-10 14:08:40,502][76543] Updated weights for policy 0, policy_version 37443 (0.0010) -[2023-10-10 14:08:40,876][76543] Updated weights for policy 0, policy_version 37453 (0.0010) -[2023-10-10 14:08:41,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 76644352. Throughput: 0: 1834.8, 1: 1809.0. Samples: 19170646. Policy #0 lag: (min: 14.0, avg: 18.4, max: 46.0) -[2023-10-10 14:08:41,076][75634] Avg episode reward: [(0, '37.920'), (1, '34.110')] -[2023-10-10 14:08:41,251][76543] Updated weights for policy 0, policy_version 37463 (0.0009) -[2023-10-10 14:08:42,680][76542] Updated weights for policy 1, policy_version 37410 (0.0008) -[2023-10-10 14:08:43,045][76542] Updated weights for policy 1, policy_version 37420 (0.0010) -[2023-10-10 14:08:43,416][76542] Updated weights for policy 1, policy_version 37430 (0.0011) -[2023-10-10 14:08:43,783][76542] Updated weights for policy 1, policy_version 37440 (0.0011) -[2023-10-10 14:08:45,021][76543] Updated weights for policy 0, policy_version 37473 (0.0009) -[2023-10-10 14:08:45,385][76543] Updated weights for policy 0, policy_version 37483 (0.0009) -[2023-10-10 14:08:45,763][76543] Updated weights for policy 0, policy_version 37493 (0.0008) -[2023-10-10 14:08:46,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 76709888. Throughput: 0: 1823.6, 1: 1816.7. Samples: 19193014. Policy #0 lag: (min: 14.0, avg: 18.4, max: 46.0) -[2023-10-10 14:08:46,076][75634] Avg episode reward: [(0, '40.110'), (1, '34.660')] -[2023-10-10 14:08:46,123][76543] Updated weights for policy 0, policy_version 37503 (0.0008) -[2023-10-10 14:08:47,504][76542] Updated weights for policy 1, policy_version 37450 (0.0009) -[2023-10-10 14:08:47,873][76542] Updated weights for policy 1, policy_version 37460 (0.0008) -[2023-10-10 14:08:48,241][76542] Updated weights for policy 1, policy_version 37470 (0.0009) -[2023-10-10 14:08:49,933][76543] Updated weights for policy 0, policy_version 37513 (0.0009) -[2023-10-10 14:08:50,305][76543] Updated weights for policy 0, policy_version 37523 (0.0009) -[2023-10-10 14:08:50,675][76543] Updated weights for policy 0, policy_version 37533 (0.0010) -[2023-10-10 14:08:51,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 76808192. Throughput: 0: 1827.5, 1: 1815.5. Samples: 19203200. Policy #0 lag: (min: 24.0, avg: 42.3, max: 56.0) -[2023-10-10 14:08:51,076][75634] Avg episode reward: [(0, '34.150'), (1, '33.420')] -[2023-10-10 14:08:52,134][76542] Updated weights for policy 1, policy_version 37480 (0.0009) -[2023-10-10 14:08:52,503][76542] Updated weights for policy 1, policy_version 37490 (0.0007) -[2023-10-10 14:08:52,870][76542] Updated weights for policy 1, policy_version 37500 (0.0009) -[2023-10-10 14:08:54,454][76543] Updated weights for policy 0, policy_version 37543 (0.0009) -[2023-10-10 14:08:54,823][76543] Updated weights for policy 0, policy_version 37553 (0.0007) -[2023-10-10 14:08:55,196][76543] Updated weights for policy 0, policy_version 37563 (0.0007) -[2023-10-10 14:08:56,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 76873728. Throughput: 0: 1825.7, 1: 1818.0. Samples: 19225922. Policy #0 lag: (min: 24.0, avg: 42.3, max: 56.0) -[2023-10-10 14:08:56,077][75634] Avg episode reward: [(0, '33.180'), (1, '31.050')] -[2023-10-10 14:08:56,383][76542] Updated weights for policy 1, policy_version 37510 (0.0010) -[2023-10-10 14:08:56,749][76542] Updated weights for policy 1, policy_version 37520 (0.0008) -[2023-10-10 14:08:57,116][76542] Updated weights for policy 1, policy_version 37530 (0.0007) -[2023-10-10 14:08:58,898][76543] Updated weights for policy 0, policy_version 37573 (0.0007) -[2023-10-10 14:08:59,274][76543] Updated weights for policy 0, policy_version 37583 (0.0008) -[2023-10-10 14:08:59,642][76543] Updated weights for policy 0, policy_version 37593 (0.0010) -[2023-10-10 14:09:00,775][76542] Updated weights for policy 1, policy_version 37540 (0.0009) -[2023-10-10 14:09:01,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 76939264. Throughput: 0: 1821.6, 1: 1824.8. Samples: 19247156. Policy #0 lag: (min: 24.0, avg: 42.3, max: 56.0) -[2023-10-10 14:09:01,076][75634] Avg episode reward: [(0, '31.390'), (1, '33.710')] -[2023-10-10 14:09:01,134][76542] Updated weights for policy 1, policy_version 37550 (0.0007) -[2023-10-10 14:09:01,515][76542] Updated weights for policy 1, policy_version 37560 (0.0009) -[2023-10-10 14:09:03,352][76543] Updated weights for policy 0, policy_version 37603 (0.0007) -[2023-10-10 14:09:03,742][76543] Updated weights for policy 0, policy_version 37613 (0.0007) -[2023-10-10 14:09:04,110][76543] Updated weights for policy 0, policy_version 37623 (0.0010) -[2023-10-10 14:09:05,295][76542] Updated weights for policy 1, policy_version 37570 (0.0007) -[2023-10-10 14:09:05,662][76542] Updated weights for policy 1, policy_version 37580 (0.0008) -[2023-10-10 14:09:06,027][76542] Updated weights for policy 1, policy_version 37590 (0.0009) -[2023-10-10 14:09:06,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 77004800. Throughput: 0: 1823.5, 1: 1818.4. Samples: 19258542. Policy #0 lag: (min: 24.0, avg: 42.3, max: 56.0) -[2023-10-10 14:09:06,077][75634] Avg episode reward: [(0, '31.190'), (1, '33.790')] -[2023-10-10 14:09:06,401][76542] Updated weights for policy 1, policy_version 37600 (0.0009) -[2023-10-10 14:09:07,877][76543] Updated weights for policy 0, policy_version 37633 (0.0011) -[2023-10-10 14:09:08,238][76543] Updated weights for policy 0, policy_version 37643 (0.0009) -[2023-10-10 14:09:08,613][76543] Updated weights for policy 0, policy_version 37653 (0.0010) -[2023-10-10 14:09:08,997][76543] Updated weights for policy 0, policy_version 37663 (0.0010) -[2023-10-10 14:09:10,170][76542] Updated weights for policy 1, policy_version 37610 (0.0007) -[2023-10-10 14:09:10,534][76542] Updated weights for policy 1, policy_version 37620 (0.0008) -[2023-10-10 14:09:10,904][76542] Updated weights for policy 1, policy_version 37630 (0.0010) -[2023-10-10 14:09:11,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 77103104. Throughput: 0: 1817.4, 1: 1821.6. Samples: 19279692. Policy #0 lag: (min: 24.0, avg: 42.3, max: 56.0) -[2023-10-10 14:09:11,077][75634] Avg episode reward: [(0, '33.650'), (1, '33.400')] -[2023-10-10 14:09:12,543][76543] Updated weights for policy 0, policy_version 37673 (0.0008) -[2023-10-10 14:09:12,915][76543] Updated weights for policy 0, policy_version 37683 (0.0008) -[2023-10-10 14:09:13,293][76543] Updated weights for policy 0, policy_version 37693 (0.0009) -[2023-10-10 14:09:14,430][76542] Updated weights for policy 1, policy_version 37640 (0.0011) -[2023-10-10 14:09:14,801][76542] Updated weights for policy 1, policy_version 37650 (0.0009) -[2023-10-10 14:09:15,175][76542] Updated weights for policy 1, policy_version 37660 (0.0008) -[2023-10-10 14:09:16,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 77168640. Throughput: 0: 1811.7, 1: 1817.8. Samples: 19301010. Policy #0 lag: (min: 24.0, avg: 42.3, max: 56.0) -[2023-10-10 14:09:16,077][75634] Avg episode reward: [(0, '35.180'), (1, '33.060')] -[2023-10-10 14:09:16,856][76543] Updated weights for policy 0, policy_version 37703 (0.0008) -[2023-10-10 14:09:17,221][76543] Updated weights for policy 0, policy_version 37713 (0.0009) -[2023-10-10 14:09:17,591][76543] Updated weights for policy 0, policy_version 37723 (0.0007) -[2023-10-10 14:09:19,165][76542] Updated weights for policy 1, policy_version 37670 (0.0010) -[2023-10-10 14:09:19,544][76542] Updated weights for policy 1, policy_version 37680 (0.0012) -[2023-10-10 14:09:19,908][76542] Updated weights for policy 1, policy_version 37690 (0.0011) -[2023-10-10 14:09:21,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 77234176. Throughput: 0: 1819.1, 1: 1817.5. Samples: 19312540. Policy #0 lag: (min: 7.0, avg: 14.4, max: 39.0) -[2023-10-10 14:09:21,077][75634] Avg episode reward: [(0, '38.760'), (1, '33.000')] -[2023-10-10 14:09:21,457][76543] Updated weights for policy 0, policy_version 37733 (0.0007) -[2023-10-10 14:09:21,829][76543] Updated weights for policy 0, policy_version 37743 (0.0007) -[2023-10-10 14:09:22,207][76543] Updated weights for policy 0, policy_version 37753 (0.0007) -[2023-10-10 14:09:23,510][76542] Updated weights for policy 1, policy_version 37700 (0.0008) -[2023-10-10 14:09:23,867][76542] Updated weights for policy 1, policy_version 37710 (0.0007) -[2023-10-10 14:09:24,237][76542] Updated weights for policy 1, policy_version 37720 (0.0008) -[2023-10-10 14:09:25,897][76543] Updated weights for policy 0, policy_version 37763 (0.0009) -[2023-10-10 14:09:26,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 77299712. Throughput: 0: 1804.8, 1: 1820.1. Samples: 19333764. Policy #0 lag: (min: 7.0, avg: 14.4, max: 39.0) -[2023-10-10 14:09:26,077][75634] Avg episode reward: [(0, '36.540'), (1, '35.130')] -[2023-10-10 14:09:26,272][76543] Updated weights for policy 0, policy_version 37773 (0.0007) -[2023-10-10 14:09:26,640][76543] Updated weights for policy 0, policy_version 37783 (0.0007) -[2023-10-10 14:09:27,792][76542] Updated weights for policy 1, policy_version 37730 (0.0008) -[2023-10-10 14:09:28,157][76542] Updated weights for policy 1, policy_version 37740 (0.0007) -[2023-10-10 14:09:28,524][76542] Updated weights for policy 1, policy_version 37750 (0.0008) -[2023-10-10 14:09:28,893][76542] Updated weights for policy 1, policy_version 37760 (0.0007) -[2023-10-10 14:09:30,209][76543] Updated weights for policy 0, policy_version 37793 (0.0008) -[2023-10-10 14:09:30,571][76543] Updated weights for policy 0, policy_version 37803 (0.0011) -[2023-10-10 14:09:30,947][76543] Updated weights for policy 0, policy_version 37813 (0.0010) -[2023-10-10 14:09:31,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 77365248. Throughput: 0: 1817.9, 1: 1822.8. Samples: 19356844. Policy #0 lag: (min: 7.0, avg: 14.4, max: 39.0) -[2023-10-10 14:09:31,076][75634] Avg episode reward: [(0, '34.910'), (1, '34.760')] -[2023-10-10 14:09:31,324][76543] Updated weights for policy 0, policy_version 37823 (0.0010) -[2023-10-10 14:09:32,518][76542] Updated weights for policy 1, policy_version 37770 (0.0009) -[2023-10-10 14:09:32,888][76542] Updated weights for policy 1, policy_version 37780 (0.0009) -[2023-10-10 14:09:33,253][76542] Updated weights for policy 1, policy_version 37790 (0.0008) -[2023-10-10 14:09:35,003][76543] Updated weights for policy 0, policy_version 37833 (0.0010) -[2023-10-10 14:09:35,372][76543] Updated weights for policy 0, policy_version 37843 (0.0009) -[2023-10-10 14:09:35,745][76543] Updated weights for policy 0, policy_version 37853 (0.0008) -[2023-10-10 14:09:36,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 77463552. Throughput: 0: 1814.0, 1: 1820.0. Samples: 19366734. Policy #0 lag: (min: 7.0, avg: 14.4, max: 39.0) -[2023-10-10 14:09:36,077][75634] Avg episode reward: [(0, '35.180'), (1, '32.870')] -[2023-10-10 14:09:37,120][76542] Updated weights for policy 1, policy_version 37800 (0.0010) -[2023-10-10 14:09:37,487][76542] Updated weights for policy 1, policy_version 37810 (0.0009) -[2023-10-10 14:09:37,857][76542] Updated weights for policy 1, policy_version 37820 (0.0007) -[2023-10-10 14:09:39,303][76543] Updated weights for policy 0, policy_version 37863 (0.0009) -[2023-10-10 14:09:39,672][76543] Updated weights for policy 0, policy_version 37873 (0.0010) -[2023-10-10 14:09:40,044][76543] Updated weights for policy 0, policy_version 37883 (0.0008) -[2023-10-10 14:09:41,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 77529088. Throughput: 0: 1814.0, 1: 1814.6. Samples: 19389208. Policy #0 lag: (min: 7.0, avg: 14.4, max: 39.0) -[2023-10-10 14:09:41,076][75634] Avg episode reward: [(0, '37.160'), (1, '31.630')] -[2023-10-10 14:09:41,610][76542] Updated weights for policy 1, policy_version 37830 (0.0009) -[2023-10-10 14:09:41,976][76542] Updated weights for policy 1, policy_version 37840 (0.0008) -[2023-10-10 14:09:42,347][76542] Updated weights for policy 1, policy_version 37850 (0.0008) -[2023-10-10 14:09:43,653][76543] Updated weights for policy 0, policy_version 37893 (0.0009) -[2023-10-10 14:09:44,025][76543] Updated weights for policy 0, policy_version 37903 (0.0007) -[2023-10-10 14:09:44,390][76543] Updated weights for policy 0, policy_version 37913 (0.0009) -[2023-10-10 14:09:46,034][76542] Updated weights for policy 1, policy_version 37860 (0.0007) -[2023-10-10 14:09:46,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 77594624. Throughput: 0: 1824.8, 1: 1821.2. Samples: 19411226. Policy #0 lag: (min: 31.0, avg: 31.8, max: 51.0) -[2023-10-10 14:09:46,076][75634] Avg episode reward: [(0, '36.440'), (1, '36.040')] -[2023-10-10 14:09:46,400][76542] Updated weights for policy 1, policy_version 37870 (0.0008) -[2023-10-10 14:09:46,768][76542] Updated weights for policy 1, policy_version 37880 (0.0007) -[2023-10-10 14:09:48,303][76543] Updated weights for policy 0, policy_version 37923 (0.0008) -[2023-10-10 14:09:48,711][76543] Updated weights for policy 0, policy_version 37933 (0.0008) -[2023-10-10 14:09:49,076][76543] Updated weights for policy 0, policy_version 37943 (0.0008) -[2023-10-10 14:09:50,435][76542] Updated weights for policy 1, policy_version 37890 (0.0007) -[2023-10-10 14:09:50,807][76542] Updated weights for policy 1, policy_version 37900 (0.0008) -[2023-10-10 14:09:51,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 77660160. Throughput: 0: 1822.3, 1: 1824.2. Samples: 19422634. Policy #0 lag: (min: 31.0, avg: 31.8, max: 51.0) -[2023-10-10 14:09:51,077][75634] Avg episode reward: [(0, '35.720'), (1, '36.390')] -[2023-10-10 14:09:51,176][76542] Updated weights for policy 1, policy_version 37910 (0.0010) -[2023-10-10 14:09:51,546][76542] Updated weights for policy 1, policy_version 37920 (0.0011) -[2023-10-10 14:09:52,646][76543] Updated weights for policy 0, policy_version 37953 (0.0008) -[2023-10-10 14:09:53,011][76543] Updated weights for policy 0, policy_version 37963 (0.0009) -[2023-10-10 14:09:53,378][76543] Updated weights for policy 0, policy_version 37973 (0.0010) -[2023-10-10 14:09:53,758][76543] Updated weights for policy 0, policy_version 37983 (0.0007) -[2023-10-10 14:09:55,278][76542] Updated weights for policy 1, policy_version 37930 (0.0012) -[2023-10-10 14:09:55,651][76542] Updated weights for policy 1, policy_version 37940 (0.0008) -[2023-10-10 14:09:56,020][76542] Updated weights for policy 1, policy_version 37950 (0.0007) -[2023-10-10 14:09:56,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 77725696. Throughput: 0: 1831.1, 1: 1815.6. Samples: 19443796. Policy #0 lag: (min: 31.0, avg: 31.8, max: 51.0) -[2023-10-10 14:09:56,077][75634] Avg episode reward: [(0, '35.650'), (1, '36.140')] -[2023-10-10 14:09:57,352][76543] Updated weights for policy 0, policy_version 37993 (0.0010) -[2023-10-10 14:09:57,729][76543] Updated weights for policy 0, policy_version 38003 (0.0009) -[2023-10-10 14:09:58,090][76543] Updated weights for policy 0, policy_version 38013 (0.0007) -[2023-10-10 14:09:59,617][76542] Updated weights for policy 1, policy_version 37960 (0.0009) -[2023-10-10 14:09:59,982][76542] Updated weights for policy 1, policy_version 37970 (0.0007) -[2023-10-10 14:10:00,345][76542] Updated weights for policy 1, policy_version 37980 (0.0007) -[2023-10-10 14:10:01,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 77824000. Throughput: 0: 1830.4, 1: 1816.3. Samples: 19465110. Policy #0 lag: (min: 31.0, avg: 31.8, max: 51.0) -[2023-10-10 14:10:01,076][75634] Avg episode reward: [(0, '38.740'), (1, '37.090')] -[2023-10-10 14:10:01,833][76543] Updated weights for policy 0, policy_version 38023 (0.0007) -[2023-10-10 14:10:02,199][76543] Updated weights for policy 0, policy_version 38033 (0.0008) -[2023-10-10 14:10:02,573][76543] Updated weights for policy 0, policy_version 38043 (0.0008) -[2023-10-10 14:10:04,108][76542] Updated weights for policy 1, policy_version 37990 (0.0007) -[2023-10-10 14:10:04,491][76542] Updated weights for policy 1, policy_version 38000 (0.0010) -[2023-10-10 14:10:04,853][76542] Updated weights for policy 1, policy_version 38010 (0.0010) -[2023-10-10 14:10:06,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 77889536. Throughput: 0: 1824.1, 1: 1821.0. Samples: 19476568. Policy #0 lag: (min: 31.0, avg: 31.8, max: 51.0) -[2023-10-10 14:10:06,077][75634] Avg episode reward: [(0, '34.670'), (1, '34.920')] -[2023-10-10 14:10:06,269][76543] Updated weights for policy 0, policy_version 38053 (0.0010) -[2023-10-10 14:10:06,647][76543] Updated weights for policy 0, policy_version 38063 (0.0008) -[2023-10-10 14:10:07,013][76543] Updated weights for policy 0, policy_version 38073 (0.0009) -[2023-10-10 14:10:08,629][76542] Updated weights for policy 1, policy_version 38020 (0.0009) -[2023-10-10 14:10:09,001][76542] Updated weights for policy 1, policy_version 38030 (0.0007) -[2023-10-10 14:10:09,373][76542] Updated weights for policy 1, policy_version 38040 (0.0007) -[2023-10-10 14:10:10,769][76543] Updated weights for policy 0, policy_version 38083 (0.0010) -[2023-10-10 14:10:11,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 77955072. Throughput: 0: 1828.6, 1: 1815.4. Samples: 19497742. Policy #0 lag: (min: 31.0, avg: 31.8, max: 51.0) -[2023-10-10 14:10:11,077][75634] Avg episode reward: [(0, '34.840'), (1, '36.580')] -[2023-10-10 14:10:11,148][76543] Updated weights for policy 0, policy_version 38093 (0.0009) -[2023-10-10 14:10:11,521][76543] Updated weights for policy 0, policy_version 38103 (0.0008) -[2023-10-10 14:10:13,099][76542] Updated weights for policy 1, policy_version 38050 (0.0008) -[2023-10-10 14:10:13,466][76542] Updated weights for policy 1, policy_version 38060 (0.0008) -[2023-10-10 14:10:13,834][76542] Updated weights for policy 1, policy_version 38070 (0.0009) -[2023-10-10 14:10:14,208][76542] Updated weights for policy 1, policy_version 38080 (0.0011) -[2023-10-10 14:10:15,083][76543] Updated weights for policy 0, policy_version 38113 (0.0008) -[2023-10-10 14:10:15,443][76543] Updated weights for policy 0, policy_version 38123 (0.0008) -[2023-10-10 14:10:15,820][76543] Updated weights for policy 0, policy_version 38133 (0.0011) -[2023-10-10 14:10:16,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 78020608. Throughput: 0: 1822.5, 1: 1812.7. Samples: 19520428. Policy #0 lag: (min: 2.0, avg: 9.5, max: 34.0) -[2023-10-10 14:10:16,076][75634] Avg episode reward: [(0, '32.040'), (1, '35.140')] -[2023-10-10 14:10:16,195][76543] Updated weights for policy 0, policy_version 38143 (0.0010) -[2023-10-10 14:10:17,832][76542] Updated weights for policy 1, policy_version 38090 (0.0007) -[2023-10-10 14:10:18,199][76542] Updated weights for policy 1, policy_version 38100 (0.0009) -[2023-10-10 14:10:18,566][76542] Updated weights for policy 1, policy_version 38110 (0.0008) -[2023-10-10 14:10:19,721][76543] Updated weights for policy 0, policy_version 38153 (0.0008) -[2023-10-10 14:10:20,097][76543] Updated weights for policy 0, policy_version 38163 (0.0010) -[2023-10-10 14:10:20,463][76543] Updated weights for policy 0, policy_version 38173 (0.0010) -[2023-10-10 14:10:21,076][75634] Fps is (10 sec: 16384.5, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 78118912. Throughput: 0: 1833.0, 1: 1813.6. Samples: 19530830. Policy #0 lag: (min: 2.0, avg: 9.5, max: 34.0) -[2023-10-10 14:10:21,076][75634] Avg episode reward: [(0, '34.940'), (1, '38.700')] -[2023-10-10 14:10:22,342][76542] Updated weights for policy 1, policy_version 38120 (0.0008) -[2023-10-10 14:10:22,712][76542] Updated weights for policy 1, policy_version 38130 (0.0010) -[2023-10-10 14:10:23,075][76542] Updated weights for policy 1, policy_version 38140 (0.0010) -[2023-10-10 14:10:24,046][76543] Updated weights for policy 0, policy_version 38183 (0.0012) -[2023-10-10 14:10:24,408][76543] Updated weights for policy 0, policy_version 38193 (0.0010) -[2023-10-10 14:10:24,778][76543] Updated weights for policy 0, policy_version 38203 (0.0010) -[2023-10-10 14:10:26,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 78184448. Throughput: 0: 1828.0, 1: 1818.2. Samples: 19553290. Policy #0 lag: (min: 2.0, avg: 9.5, max: 34.0) -[2023-10-10 14:10:26,076][75634] Avg episode reward: [(0, '35.310'), (1, '36.580')] -[2023-10-10 14:10:26,601][76542] Updated weights for policy 1, policy_version 38150 (0.0009) -[2023-10-10 14:10:26,972][76542] Updated weights for policy 1, policy_version 38160 (0.0008) -[2023-10-10 14:10:27,341][76542] Updated weights for policy 1, policy_version 38170 (0.0007) -[2023-10-10 14:10:28,508][76543] Updated weights for policy 0, policy_version 38213 (0.0009) -[2023-10-10 14:10:28,883][76543] Updated weights for policy 0, policy_version 38223 (0.0007) -[2023-10-10 14:10:29,253][76543] Updated weights for policy 0, policy_version 38233 (0.0007) -[2023-10-10 14:10:31,076][75634] Fps is (10 sec: 13106.7, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 78249984. Throughput: 0: 1828.7, 1: 1812.9. Samples: 19575102. Policy #0 lag: (min: 2.0, avg: 9.5, max: 34.0) -[2023-10-10 14:10:31,077][75634] Avg episode reward: [(0, '30.470'), (1, '35.430')] -[2023-10-10 14:10:31,088][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000038240_39157760.pth... -[2023-10-10 14:10:31,092][76542] Updated weights for policy 1, policy_version 38180 (0.0008) -[2023-10-10 14:10:31,124][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000036544_37421056.pth -[2023-10-10 14:10:31,461][76542] Updated weights for policy 1, policy_version 38190 (0.0009) -[2023-10-10 14:10:31,833][76542] Updated weights for policy 1, policy_version 38200 (0.0008) -[2023-10-10 14:10:32,129][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000038208_39124992.pth... -[2023-10-10 14:10:32,167][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000036480_37355520.pth -[2023-10-10 14:10:33,055][76543] Updated weights for policy 0, policy_version 38243 (0.0008) -[2023-10-10 14:10:33,447][76543] Updated weights for policy 0, policy_version 38253 (0.0010) -[2023-10-10 14:10:33,818][76543] Updated weights for policy 0, policy_version 38263 (0.0009) -[2023-10-10 14:10:35,476][76542] Updated weights for policy 1, policy_version 38210 (0.0008) -[2023-10-10 14:10:35,837][76542] Updated weights for policy 1, policy_version 38220 (0.0009) -[2023-10-10 14:10:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 78315520. Throughput: 0: 1823.0, 1: 1809.4. Samples: 19586092. Policy #0 lag: (min: 2.0, avg: 9.5, max: 34.0) -[2023-10-10 14:10:36,076][75634] Avg episode reward: [(0, '32.670'), (1, '35.510')] -[2023-10-10 14:10:36,201][76542] Updated weights for policy 1, policy_version 38230 (0.0010) -[2023-10-10 14:10:36,569][76542] Updated weights for policy 1, policy_version 38240 (0.0010) -[2023-10-10 14:10:37,595][76543] Updated weights for policy 0, policy_version 38273 (0.0008) -[2023-10-10 14:10:37,968][76543] Updated weights for policy 0, policy_version 38283 (0.0008) -[2023-10-10 14:10:38,343][76543] Updated weights for policy 0, policy_version 38293 (0.0009) -[2023-10-10 14:10:38,715][76543] Updated weights for policy 0, policy_version 38303 (0.0008) -[2023-10-10 14:10:40,295][76542] Updated weights for policy 1, policy_version 38250 (0.0009) -[2023-10-10 14:10:40,663][76542] Updated weights for policy 1, policy_version 38260 (0.0009) -[2023-10-10 14:10:41,034][76542] Updated weights for policy 1, policy_version 38270 (0.0008) -[2023-10-10 14:10:41,076][75634] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 78381056. Throughput: 0: 1820.3, 1: 1815.0. Samples: 19607384. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-10 14:10:41,076][75634] Avg episode reward: [(0, '37.460'), (1, '32.170')] -[2023-10-10 14:10:42,297][76543] Updated weights for policy 0, policy_version 38313 (0.0007) -[2023-10-10 14:10:42,673][76543] Updated weights for policy 0, policy_version 38323 (0.0010) -[2023-10-10 14:10:43,045][76543] Updated weights for policy 0, policy_version 38333 (0.0007) -[2023-10-10 14:10:44,610][76542] Updated weights for policy 1, policy_version 38280 (0.0009) -[2023-10-10 14:10:44,983][76542] Updated weights for policy 1, policy_version 38290 (0.0009) -[2023-10-10 14:10:45,356][76542] Updated weights for policy 1, policy_version 38300 (0.0009) -[2023-10-10 14:10:46,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 78479360. Throughput: 0: 1825.2, 1: 1815.4. Samples: 19628940. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-10 14:10:46,077][75634] Avg episode reward: [(0, '38.050'), (1, '28.660')] -[2023-10-10 14:10:46,687][76543] Updated weights for policy 0, policy_version 38343 (0.0007) -[2023-10-10 14:10:47,046][76543] Updated weights for policy 0, policy_version 38353 (0.0009) -[2023-10-10 14:10:47,421][76543] Updated weights for policy 0, policy_version 38363 (0.0009) -[2023-10-10 14:10:49,107][76542] Updated weights for policy 1, policy_version 38310 (0.0007) -[2023-10-10 14:10:49,486][76542] Updated weights for policy 1, policy_version 38320 (0.0008) -[2023-10-10 14:10:49,851][76542] Updated weights for policy 1, policy_version 38330 (0.0007) -[2023-10-10 14:10:51,051][76543] Updated weights for policy 0, policy_version 38373 (0.0008) -[2023-10-10 14:10:51,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 78544896. Throughput: 0: 1824.4, 1: 1815.7. Samples: 19640372. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-10 14:10:51,077][75634] Avg episode reward: [(0, '34.710'), (1, '29.230')] -[2023-10-10 14:10:51,433][76543] Updated weights for policy 0, policy_version 38383 (0.0008) -[2023-10-10 14:10:51,799][76543] Updated weights for policy 0, policy_version 38393 (0.0008) -[2023-10-10 14:10:53,430][76542] Updated weights for policy 1, policy_version 38340 (0.0007) -[2023-10-10 14:10:53,809][76542] Updated weights for policy 1, policy_version 38350 (0.0009) -[2023-10-10 14:10:54,173][76542] Updated weights for policy 1, policy_version 38360 (0.0010) -[2023-10-10 14:10:55,474][76543] Updated weights for policy 0, policy_version 38403 (0.0009) -[2023-10-10 14:10:55,840][76543] Updated weights for policy 0, policy_version 38413 (0.0009) -[2023-10-10 14:10:56,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 78610432. Throughput: 0: 1826.9, 1: 1819.0. Samples: 19661806. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-10 14:10:56,076][75634] Avg episode reward: [(0, '36.320'), (1, '32.730')] -[2023-10-10 14:10:56,207][76543] Updated weights for policy 0, policy_version 38423 (0.0009) -[2023-10-10 14:10:58,014][76542] Updated weights for policy 1, policy_version 38370 (0.0011) -[2023-10-10 14:10:58,378][76542] Updated weights for policy 1, policy_version 38380 (0.0007) -[2023-10-10 14:10:58,740][76542] Updated weights for policy 1, policy_version 38390 (0.0007) -[2023-10-10 14:10:59,109][76542] Updated weights for policy 1, policy_version 38400 (0.0008) -[2023-10-10 14:10:59,951][76543] Updated weights for policy 0, policy_version 38433 (0.0009) -[2023-10-10 14:11:00,327][76543] Updated weights for policy 0, policy_version 38443 (0.0009) -[2023-10-10 14:11:00,701][76543] Updated weights for policy 0, policy_version 38453 (0.0010) -[2023-10-10 14:11:01,066][76543] Updated weights for policy 0, policy_version 38463 (0.0009) -[2023-10-10 14:11:01,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 78675968. Throughput: 0: 1815.3, 1: 1816.3. Samples: 19683850. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-10 14:11:01,076][75634] Avg episode reward: [(0, '39.670'), (1, '32.530')] -[2023-10-10 14:11:02,814][76542] Updated weights for policy 1, policy_version 38410 (0.0008) -[2023-10-10 14:11:03,180][76542] Updated weights for policy 1, policy_version 38420 (0.0010) -[2023-10-10 14:11:03,546][76542] Updated weights for policy 1, policy_version 38430 (0.0009) -[2023-10-10 14:11:04,772][76543] Updated weights for policy 0, policy_version 38473 (0.0010) -[2023-10-10 14:11:05,146][76543] Updated weights for policy 0, policy_version 38483 (0.0009) -[2023-10-10 14:11:05,517][76543] Updated weights for policy 0, policy_version 38493 (0.0007) -[2023-10-10 14:11:06,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 78774272. Throughput: 0: 1819.0, 1: 1816.4. Samples: 19694426. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-10 14:11:06,076][75634] Avg episode reward: [(0, '31.380'), (1, '32.420')] -[2023-10-10 14:11:07,141][76542] Updated weights for policy 1, policy_version 38440 (0.0008) -[2023-10-10 14:11:07,517][76542] Updated weights for policy 1, policy_version 38450 (0.0009) -[2023-10-10 14:11:07,873][76542] Updated weights for policy 1, policy_version 38460 (0.0008) -[2023-10-10 14:11:09,305][76543] Updated weights for policy 0, policy_version 38503 (0.0011) -[2023-10-10 14:11:09,680][76543] Updated weights for policy 0, policy_version 38513 (0.0011) -[2023-10-10 14:11:10,042][76543] Updated weights for policy 0, policy_version 38523 (0.0009) -[2023-10-10 14:11:11,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 78839808. Throughput: 0: 1814.4, 1: 1821.8. Samples: 19716918. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-10 14:11:11,077][75634] Avg episode reward: [(0, '30.120'), (1, '34.670')] -[2023-10-10 14:11:11,631][76542] Updated weights for policy 1, policy_version 38470 (0.0007) -[2023-10-10 14:11:11,999][76542] Updated weights for policy 1, policy_version 38480 (0.0010) -[2023-10-10 14:11:12,353][76542] Updated weights for policy 1, policy_version 38490 (0.0008) -[2023-10-10 14:11:13,632][76543] Updated weights for policy 0, policy_version 38533 (0.0009) -[2023-10-10 14:11:14,008][76543] Updated weights for policy 0, policy_version 38543 (0.0008) -[2023-10-10 14:11:14,390][76543] Updated weights for policy 0, policy_version 38553 (0.0007) -[2023-10-10 14:11:15,949][76542] Updated weights for policy 1, policy_version 38500 (0.0009) -[2023-10-10 14:11:16,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 78905344. Throughput: 0: 1813.1, 1: 1823.7. Samples: 19738760. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-10 14:11:16,077][75634] Avg episode reward: [(0, '34.510'), (1, '37.840')] -[2023-10-10 14:11:16,326][76542] Updated weights for policy 1, policy_version 38510 (0.0008) -[2023-10-10 14:11:16,694][76542] Updated weights for policy 1, policy_version 38520 (0.0008) -[2023-10-10 14:11:17,971][76543] Updated weights for policy 0, policy_version 38563 (0.0009) -[2023-10-10 14:11:18,366][76543] Updated weights for policy 0, policy_version 38573 (0.0008) -[2023-10-10 14:11:18,729][76543] Updated weights for policy 0, policy_version 38583 (0.0008) -[2023-10-10 14:11:20,138][76542] Updated weights for policy 1, policy_version 38530 (0.0009) -[2023-10-10 14:11:20,500][76542] Updated weights for policy 1, policy_version 38540 (0.0011) -[2023-10-10 14:11:20,871][76542] Updated weights for policy 1, policy_version 38550 (0.0009) -[2023-10-10 14:11:21,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 78970880. Throughput: 0: 1817.3, 1: 1829.7. Samples: 19750210. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-10 14:11:21,076][75634] Avg episode reward: [(0, '34.520'), (1, '37.030')] -[2023-10-10 14:11:21,247][76542] Updated weights for policy 1, policy_version 38560 (0.0010) -[2023-10-10 14:11:22,495][76543] Updated weights for policy 0, policy_version 38593 (0.0008) -[2023-10-10 14:11:22,868][76543] Updated weights for policy 0, policy_version 38603 (0.0008) -[2023-10-10 14:11:23,239][76543] Updated weights for policy 0, policy_version 38613 (0.0007) -[2023-10-10 14:11:23,614][76543] Updated weights for policy 0, policy_version 38623 (0.0008) -[2023-10-10 14:11:24,843][76542] Updated weights for policy 1, policy_version 38570 (0.0008) -[2023-10-10 14:11:25,210][76542] Updated weights for policy 1, policy_version 38580 (0.0007) -[2023-10-10 14:11:25,583][76542] Updated weights for policy 1, policy_version 38590 (0.0007) -[2023-10-10 14:11:26,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 79069184. Throughput: 0: 1825.0, 1: 1825.4. Samples: 19771652. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-10 14:11:26,077][75634] Avg episode reward: [(0, '35.290'), (1, '32.340')] -[2023-10-10 14:11:27,315][76543] Updated weights for policy 0, policy_version 38633 (0.0008) -[2023-10-10 14:11:27,685][76543] Updated weights for policy 0, policy_version 38643 (0.0008) -[2023-10-10 14:11:28,063][76543] Updated weights for policy 0, policy_version 38653 (0.0008) -[2023-10-10 14:11:29,303][76542] Updated weights for policy 1, policy_version 38600 (0.0009) -[2023-10-10 14:11:29,668][76542] Updated weights for policy 1, policy_version 38610 (0.0008) -[2023-10-10 14:11:30,037][76542] Updated weights for policy 1, policy_version 38620 (0.0010) -[2023-10-10 14:11:31,076][75634] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 79134720. Throughput: 0: 1814.4, 1: 1829.1. Samples: 19792896. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-10 14:11:31,077][75634] Avg episode reward: [(0, '32.240'), (1, '33.550')] -[2023-10-10 14:11:31,870][76543] Updated weights for policy 0, policy_version 38663 (0.0007) -[2023-10-10 14:11:32,231][76543] Updated weights for policy 0, policy_version 38673 (0.0007) -[2023-10-10 14:11:32,600][76543] Updated weights for policy 0, policy_version 38683 (0.0007) -[2023-10-10 14:11:33,730][76542] Updated weights for policy 1, policy_version 38630 (0.0010) -[2023-10-10 14:11:34,087][76542] Updated weights for policy 1, policy_version 38640 (0.0008) -[2023-10-10 14:11:34,465][76542] Updated weights for policy 1, policy_version 38650 (0.0011) -[2023-10-10 14:11:36,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 79200256. Throughput: 0: 1814.4, 1: 1828.9. Samples: 19804316. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:11:36,076][75634] Avg episode reward: [(0, '34.440'), (1, '30.750')] -[2023-10-10 14:11:36,349][76543] Updated weights for policy 0, policy_version 38693 (0.0008) -[2023-10-10 14:11:36,723][76543] Updated weights for policy 0, policy_version 38703 (0.0008) -[2023-10-10 14:11:37,095][76543] Updated weights for policy 0, policy_version 38713 (0.0009) -[2023-10-10 14:11:38,198][76542] Updated weights for policy 1, policy_version 38660 (0.0009) -[2023-10-10 14:11:38,567][76542] Updated weights for policy 1, policy_version 38670 (0.0009) -[2023-10-10 14:11:38,939][76542] Updated weights for policy 1, policy_version 38680 (0.0008) -[2023-10-10 14:11:40,664][76543] Updated weights for policy 0, policy_version 38723 (0.0009) -[2023-10-10 14:11:41,037][76543] Updated weights for policy 0, policy_version 38733 (0.0008) -[2023-10-10 14:11:41,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 79265792. Throughput: 0: 1812.7, 1: 1836.2. Samples: 19826006. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:11:41,077][75634] Avg episode reward: [(0, '36.250'), (1, '33.010')] -[2023-10-10 14:11:41,413][76543] Updated weights for policy 0, policy_version 38743 (0.0008) -[2023-10-10 14:11:42,664][76542] Updated weights for policy 1, policy_version 38690 (0.0008) -[2023-10-10 14:11:43,033][76542] Updated weights for policy 1, policy_version 38700 (0.0007) -[2023-10-10 14:11:43,400][76542] Updated weights for policy 1, policy_version 38710 (0.0008) -[2023-10-10 14:11:43,758][76542] Updated weights for policy 1, policy_version 38720 (0.0007) -[2023-10-10 14:11:44,993][76543] Updated weights for policy 0, policy_version 38753 (0.0008) -[2023-10-10 14:11:45,360][76543] Updated weights for policy 0, policy_version 38763 (0.0008) -[2023-10-10 14:11:45,739][76543] Updated weights for policy 0, policy_version 38773 (0.0008) -[2023-10-10 14:11:46,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 79331328. Throughput: 0: 1824.6, 1: 1835.5. Samples: 19848554. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:11:46,077][75634] Avg episode reward: [(0, '36.240'), (1, '32.410')] -[2023-10-10 14:11:46,099][76543] Updated weights for policy 0, policy_version 38783 (0.0007) -[2023-10-10 14:11:47,414][76542] Updated weights for policy 1, policy_version 38730 (0.0008) -[2023-10-10 14:11:47,783][76542] Updated weights for policy 1, policy_version 38740 (0.0009) -[2023-10-10 14:11:48,159][76542] Updated weights for policy 1, policy_version 38750 (0.0009) -[2023-10-10 14:11:49,711][76543] Updated weights for policy 0, policy_version 38793 (0.0009) -[2023-10-10 14:11:50,078][76543] Updated weights for policy 0, policy_version 38803 (0.0010) -[2023-10-10 14:11:50,445][76543] Updated weights for policy 0, policy_version 38813 (0.0010) -[2023-10-10 14:11:51,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 79429632. Throughput: 0: 1820.4, 1: 1834.7. Samples: 19858904. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:11:51,077][75634] Avg episode reward: [(0, '35.670'), (1, '32.920')] -[2023-10-10 14:11:51,830][76542] Updated weights for policy 1, policy_version 38760 (0.0008) -[2023-10-10 14:11:52,201][76542] Updated weights for policy 1, policy_version 38770 (0.0007) -[2023-10-10 14:11:52,575][76542] Updated weights for policy 1, policy_version 38780 (0.0007) -[2023-10-10 14:11:54,046][76543] Updated weights for policy 0, policy_version 38823 (0.0007) -[2023-10-10 14:11:54,422][76543] Updated weights for policy 0, policy_version 38833 (0.0009) -[2023-10-10 14:11:54,802][76543] Updated weights for policy 0, policy_version 38843 (0.0010) -[2023-10-10 14:11:56,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 79495168. Throughput: 0: 1826.3, 1: 1826.8. Samples: 19881308. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:11:56,077][75634] Avg episode reward: [(0, '33.450'), (1, '35.710')] -[2023-10-10 14:11:56,193][76542] Updated weights for policy 1, policy_version 38790 (0.0007) -[2023-10-10 14:11:56,558][76542] Updated weights for policy 1, policy_version 38800 (0.0009) -[2023-10-10 14:11:56,933][76542] Updated weights for policy 1, policy_version 38810 (0.0008) -[2023-10-10 14:11:58,380][76543] Updated weights for policy 0, policy_version 38853 (0.0008) -[2023-10-10 14:11:58,759][76543] Updated weights for policy 0, policy_version 38863 (0.0008) -[2023-10-10 14:11:59,130][76543] Updated weights for policy 0, policy_version 38873 (0.0009) -[2023-10-10 14:12:00,601][76542] Updated weights for policy 1, policy_version 38820 (0.0008) -[2023-10-10 14:12:00,974][76542] Updated weights for policy 1, policy_version 38830 (0.0009) -[2023-10-10 14:12:01,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 79560704. Throughput: 0: 1827.3, 1: 1827.9. Samples: 19903242. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 14:12:01,077][75634] Avg episode reward: [(0, '32.750'), (1, '32.330')] -[2023-10-10 14:12:01,353][76542] Updated weights for policy 1, policy_version 38840 (0.0010) -[2023-10-10 14:12:02,744][76543] Updated weights for policy 0, policy_version 38883 (0.0008) -[2023-10-10 14:12:03,125][76543] Updated weights for policy 0, policy_version 38893 (0.0008) -[2023-10-10 14:12:03,493][76543] Updated weights for policy 0, policy_version 38903 (0.0008) -[2023-10-10 14:12:05,076][76542] Updated weights for policy 1, policy_version 38850 (0.0009) -[2023-10-10 14:12:05,441][76542] Updated weights for policy 1, policy_version 38860 (0.0011) -[2023-10-10 14:12:05,807][76542] Updated weights for policy 1, policy_version 38870 (0.0009) -[2023-10-10 14:12:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 79626240. Throughput: 0: 1818.6, 1: 1829.1. Samples: 19914356. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 14:12:06,077][75634] Avg episode reward: [(0, '34.380'), (1, '35.290')] -[2023-10-10 14:12:06,171][76542] Updated weights for policy 1, policy_version 38880 (0.0010) -[2023-10-10 14:12:07,260][76543] Updated weights for policy 0, policy_version 38913 (0.0008) -[2023-10-10 14:12:07,630][76543] Updated weights for policy 0, policy_version 38923 (0.0007) -[2023-10-10 14:12:08,009][76543] Updated weights for policy 0, policy_version 38933 (0.0009) -[2023-10-10 14:12:08,383][76543] Updated weights for policy 0, policy_version 38943 (0.0010) -[2023-10-10 14:12:09,920][76542] Updated weights for policy 1, policy_version 38890 (0.0008) -[2023-10-10 14:12:10,286][76542] Updated weights for policy 1, policy_version 38900 (0.0007) -[2023-10-10 14:12:10,661][76542] Updated weights for policy 1, policy_version 38910 (0.0009) -[2023-10-10 14:12:11,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 79724544. Throughput: 0: 1823.6, 1: 1822.8. Samples: 19935738. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 14:12:11,076][75634] Avg episode reward: [(0, '33.400'), (1, '33.680')] -[2023-10-10 14:12:12,262][76543] Updated weights for policy 0, policy_version 38953 (0.0009) -[2023-10-10 14:12:12,641][76543] Updated weights for policy 0, policy_version 38963 (0.0007) -[2023-10-10 14:12:13,014][76543] Updated weights for policy 0, policy_version 38973 (0.0008) -[2023-10-10 14:12:14,451][76542] Updated weights for policy 1, policy_version 38920 (0.0009) -[2023-10-10 14:12:14,812][76542] Updated weights for policy 1, policy_version 38930 (0.0007) -[2023-10-10 14:12:15,178][76542] Updated weights for policy 1, policy_version 38940 (0.0007) -[2023-10-10 14:12:16,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 79790080. Throughput: 0: 1825.6, 1: 1821.3. Samples: 19957008. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 14:12:16,077][75634] Avg episode reward: [(0, '36.630'), (1, '31.780')] -[2023-10-10 14:12:16,601][76543] Updated weights for policy 0, policy_version 38983 (0.0008) -[2023-10-10 14:12:16,973][76543] Updated weights for policy 0, policy_version 38993 (0.0008) -[2023-10-10 14:12:17,358][76543] Updated weights for policy 0, policy_version 39003 (0.0011) -[2023-10-10 14:12:18,771][76542] Updated weights for policy 1, policy_version 38950 (0.0008) -[2023-10-10 14:12:19,145][76542] Updated weights for policy 1, policy_version 38960 (0.0009) -[2023-10-10 14:12:19,504][76542] Updated weights for policy 1, policy_version 38970 (0.0009) -[2023-10-10 14:12:21,002][76543] Updated weights for policy 0, policy_version 39013 (0.0008) -[2023-10-10 14:12:21,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 79855616. Throughput: 0: 1826.8, 1: 1820.5. Samples: 19968446. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 14:12:21,076][75634] Avg episode reward: [(0, '34.400'), (1, '34.100')] -[2023-10-10 14:12:21,367][76543] Updated weights for policy 0, policy_version 39023 (0.0008) -[2023-10-10 14:12:21,746][76543] Updated weights for policy 0, policy_version 39033 (0.0010) -[2023-10-10 14:12:23,074][76542] Updated weights for policy 1, policy_version 38980 (0.0007) -[2023-10-10 14:12:23,452][76542] Updated weights for policy 1, policy_version 38990 (0.0007) -[2023-10-10 14:12:23,807][76542] Updated weights for policy 1, policy_version 39000 (0.0007) -[2023-10-10 14:12:25,384][76543] Updated weights for policy 0, policy_version 39043 (0.0010) -[2023-10-10 14:12:25,763][76543] Updated weights for policy 0, policy_version 39053 (0.0007) -[2023-10-10 14:12:26,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 79921152. Throughput: 0: 1831.4, 1: 1820.0. Samples: 19990318. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 14:12:26,076][75634] Avg episode reward: [(0, '32.950'), (1, '33.420')] -[2023-10-10 14:12:26,133][76543] Updated weights for policy 0, policy_version 39063 (0.0007) -[2023-10-10 14:12:27,607][76542] Updated weights for policy 1, policy_version 39010 (0.0007) -[2023-10-10 14:12:27,976][76542] Updated weights for policy 1, policy_version 39020 (0.0007) -[2023-10-10 14:12:28,353][76542] Updated weights for policy 1, policy_version 39030 (0.0008) -[2023-10-10 14:12:28,719][76542] Updated weights for policy 1, policy_version 39040 (0.0008) -[2023-10-10 14:12:29,741][76543] Updated weights for policy 0, policy_version 39073 (0.0009) -[2023-10-10 14:12:30,108][76543] Updated weights for policy 0, policy_version 39083 (0.0008) -[2023-10-10 14:12:30,474][76543] Updated weights for policy 0, policy_version 39093 (0.0007) -[2023-10-10 14:12:30,846][76543] Updated weights for policy 0, policy_version 39103 (0.0008) -[2023-10-10 14:12:31,076][75634] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 80019456. Throughput: 0: 1820.3, 1: 1819.8. Samples: 20012358. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 14:12:31,077][75634] Avg episode reward: [(0, '33.920'), (1, '37.070')] -[2023-10-10 14:12:31,090][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000039040_39976960.pth... -[2023-10-10 14:12:31,090][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000039104_40042496.pth... -[2023-10-10 14:12:31,120][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000037376_38273024.pth -[2023-10-10 14:12:31,125][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000037344_38240256.pth -[2023-10-10 14:12:32,552][76542] Updated weights for policy 1, policy_version 39050 (0.0007) -[2023-10-10 14:12:32,912][76542] Updated weights for policy 1, policy_version 39060 (0.0008) -[2023-10-10 14:12:33,282][76542] Updated weights for policy 1, policy_version 39070 (0.0009) -[2023-10-10 14:12:34,476][76543] Updated weights for policy 0, policy_version 39113 (0.0009) -[2023-10-10 14:12:34,854][76543] Updated weights for policy 0, policy_version 39123 (0.0010) -[2023-10-10 14:12:35,221][76543] Updated weights for policy 0, policy_version 39133 (0.0009) -[2023-10-10 14:12:36,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 80084992. Throughput: 0: 1828.4, 1: 1817.2. Samples: 20022954. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 14:12:36,077][75634] Avg episode reward: [(0, '34.870'), (1, '35.210')] -[2023-10-10 14:12:36,990][76542] Updated weights for policy 1, policy_version 39080 (0.0009) -[2023-10-10 14:12:37,355][76542] Updated weights for policy 1, policy_version 39090 (0.0007) -[2023-10-10 14:12:37,733][76542] Updated weights for policy 1, policy_version 39100 (0.0008) -[2023-10-10 14:12:38,987][76543] Updated weights for policy 0, policy_version 39143 (0.0009) -[2023-10-10 14:12:39,364][76543] Updated weights for policy 0, policy_version 39153 (0.0010) -[2023-10-10 14:12:39,724][76543] Updated weights for policy 0, policy_version 39163 (0.0008) -[2023-10-10 14:12:41,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 80150528. Throughput: 0: 1817.0, 1: 1817.5. Samples: 20044858. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 14:12:41,078][75634] Avg episode reward: [(0, '37.070'), (1, '37.180')] -[2023-10-10 14:12:41,479][76542] Updated weights for policy 1, policy_version 39110 (0.0008) -[2023-10-10 14:12:41,859][76542] Updated weights for policy 1, policy_version 39120 (0.0008) -[2023-10-10 14:12:42,216][76542] Updated weights for policy 1, policy_version 39130 (0.0009) -[2023-10-10 14:12:43,618][76543] Updated weights for policy 0, policy_version 39173 (0.0008) -[2023-10-10 14:12:43,987][76543] Updated weights for policy 0, policy_version 39183 (0.0009) -[2023-10-10 14:12:44,354][76543] Updated weights for policy 0, policy_version 39193 (0.0008) -[2023-10-10 14:12:45,850][76542] Updated weights for policy 1, policy_version 39140 (0.0009) -[2023-10-10 14:12:46,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 80216064. Throughput: 0: 1820.6, 1: 1814.9. Samples: 20066840. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 14:12:46,076][75634] Avg episode reward: [(0, '37.860'), (1, '40.080')] -[2023-10-10 14:12:46,227][76542] Updated weights for policy 1, policy_version 39150 (0.0008) -[2023-10-10 14:12:46,594][76542] Updated weights for policy 1, policy_version 39160 (0.0007) -[2023-10-10 14:12:46,889][76421] Saving new best policy, reward=40.080! -[2023-10-10 14:12:47,992][76543] Updated weights for policy 0, policy_version 39203 (0.0008) -[2023-10-10 14:12:48,371][76543] Updated weights for policy 0, policy_version 39213 (0.0008) -[2023-10-10 14:12:48,740][76543] Updated weights for policy 0, policy_version 39223 (0.0010) -[2023-10-10 14:12:50,188][76542] Updated weights for policy 1, policy_version 39170 (0.0007) -[2023-10-10 14:12:50,559][76542] Updated weights for policy 1, policy_version 39180 (0.0008) -[2023-10-10 14:12:50,919][76542] Updated weights for policy 1, policy_version 39190 (0.0009) -[2023-10-10 14:12:51,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 80281600. Throughput: 0: 1824.8, 1: 1807.6. Samples: 20077814. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 14:12:51,077][75634] Avg episode reward: [(0, '32.260'), (1, '37.410')] -[2023-10-10 14:12:51,285][76542] Updated weights for policy 1, policy_version 39200 (0.0007) -[2023-10-10 14:12:52,310][76543] Updated weights for policy 0, policy_version 39233 (0.0007) -[2023-10-10 14:12:52,687][76543] Updated weights for policy 0, policy_version 39243 (0.0008) -[2023-10-10 14:12:53,051][76543] Updated weights for policy 0, policy_version 39253 (0.0007) -[2023-10-10 14:12:53,422][76543] Updated weights for policy 0, policy_version 39263 (0.0009) -[2023-10-10 14:12:55,064][76542] Updated weights for policy 1, policy_version 39210 (0.0009) -[2023-10-10 14:12:55,433][76542] Updated weights for policy 1, policy_version 39220 (0.0009) -[2023-10-10 14:12:55,809][76542] Updated weights for policy 1, policy_version 39230 (0.0008) -[2023-10-10 14:12:56,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 80379904. Throughput: 0: 1823.4, 1: 1815.8. Samples: 20099500. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-10 14:12:56,077][75634] Avg episode reward: [(0, '31.830'), (1, '34.370')] -[2023-10-10 14:12:57,095][76543] Updated weights for policy 0, policy_version 39273 (0.0008) -[2023-10-10 14:12:57,471][76543] Updated weights for policy 0, policy_version 39283 (0.0008) -[2023-10-10 14:12:57,854][76543] Updated weights for policy 0, policy_version 39293 (0.0009) -[2023-10-10 14:12:59,518][76542] Updated weights for policy 1, policy_version 39240 (0.0007) -[2023-10-10 14:12:59,881][76542] Updated weights for policy 1, policy_version 39250 (0.0009) -[2023-10-10 14:13:00,256][76542] Updated weights for policy 1, policy_version 39260 (0.0008) -[2023-10-10 14:13:01,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 80445440. Throughput: 0: 1830.9, 1: 1815.4. Samples: 20121092. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-10 14:13:01,076][75634] Avg episode reward: [(0, '34.510'), (1, '34.650')] -[2023-10-10 14:13:01,278][76543] Updated weights for policy 0, policy_version 39303 (0.0007) -[2023-10-10 14:13:01,652][76543] Updated weights for policy 0, policy_version 39313 (0.0007) -[2023-10-10 14:13:02,020][76543] Updated weights for policy 0, policy_version 39323 (0.0007) -[2023-10-10 14:13:03,866][76542] Updated weights for policy 1, policy_version 39270 (0.0007) -[2023-10-10 14:13:04,240][76542] Updated weights for policy 1, policy_version 39280 (0.0008) -[2023-10-10 14:13:04,611][76542] Updated weights for policy 1, policy_version 39290 (0.0008) -[2023-10-10 14:13:05,621][76543] Updated weights for policy 0, policy_version 39333 (0.0008) -[2023-10-10 14:13:05,990][76543] Updated weights for policy 0, policy_version 39343 (0.0007) -[2023-10-10 14:13:06,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 80510976. Throughput: 0: 1831.8, 1: 1821.4. Samples: 20132840. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-10 14:13:06,076][75634] Avg episode reward: [(0, '34.470'), (1, '35.940')] -[2023-10-10 14:13:06,367][76543] Updated weights for policy 0, policy_version 39353 (0.0007) -[2023-10-10 14:13:08,343][76542] Updated weights for policy 1, policy_version 39300 (0.0009) -[2023-10-10 14:13:08,702][76542] Updated weights for policy 1, policy_version 39310 (0.0008) -[2023-10-10 14:13:09,068][76542] Updated weights for policy 1, policy_version 39320 (0.0009) -[2023-10-10 14:13:10,118][76543] Updated weights for policy 0, policy_version 39363 (0.0009) -[2023-10-10 14:13:10,489][76543] Updated weights for policy 0, policy_version 39373 (0.0007) -[2023-10-10 14:13:10,867][76543] Updated weights for policy 0, policy_version 39383 (0.0010) -[2023-10-10 14:13:11,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 80576512. Throughput: 0: 1830.6, 1: 1816.3. Samples: 20154426. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-10 14:13:11,076][75634] Avg episode reward: [(0, '36.510'), (1, '34.400')] -[2023-10-10 14:13:12,859][76542] Updated weights for policy 1, policy_version 39330 (0.0009) -[2023-10-10 14:13:13,222][76542] Updated weights for policy 1, policy_version 39340 (0.0008) -[2023-10-10 14:13:13,601][76542] Updated weights for policy 1, policy_version 39350 (0.0009) -[2023-10-10 14:13:13,969][76542] Updated weights for policy 1, policy_version 39360 (0.0007) -[2023-10-10 14:13:14,415][76543] Updated weights for policy 0, policy_version 39393 (0.0008) -[2023-10-10 14:13:14,792][76543] Updated weights for policy 0, policy_version 39403 (0.0010) -[2023-10-10 14:13:15,163][76543] Updated weights for policy 0, policy_version 39413 (0.0009) -[2023-10-10 14:13:15,533][76543] Updated weights for policy 0, policy_version 39423 (0.0009) -[2023-10-10 14:13:16,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 80674816. Throughput: 0: 1830.8, 1: 1816.7. Samples: 20176496. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-10 14:13:16,077][75634] Avg episode reward: [(0, '36.570'), (1, '31.870')] -[2023-10-10 14:13:17,633][76542] Updated weights for policy 1, policy_version 39370 (0.0010) -[2023-10-10 14:13:18,005][76542] Updated weights for policy 1, policy_version 39380 (0.0007) -[2023-10-10 14:13:18,366][76542] Updated weights for policy 1, policy_version 39390 (0.0009) -[2023-10-10 14:13:19,212][76543] Updated weights for policy 0, policy_version 39433 (0.0007) -[2023-10-10 14:13:19,587][76543] Updated weights for policy 0, policy_version 39443 (0.0009) -[2023-10-10 14:13:19,961][76543] Updated weights for policy 0, policy_version 39453 (0.0009) -[2023-10-10 14:13:21,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 80740352. Throughput: 0: 1834.0, 1: 1816.4. Samples: 20187220. Policy #0 lag: (min: 3.0, avg: 3.0, max: 4.0) -[2023-10-10 14:13:21,076][75634] Avg episode reward: [(0, '34.660'), (1, '33.490')] -[2023-10-10 14:13:22,070][76542] Updated weights for policy 1, policy_version 39400 (0.0008) -[2023-10-10 14:13:22,444][76542] Updated weights for policy 1, policy_version 39410 (0.0008) -[2023-10-10 14:13:22,817][76542] Updated weights for policy 1, policy_version 39420 (0.0008) -[2023-10-10 14:13:23,534][76543] Updated weights for policy 0, policy_version 39463 (0.0009) -[2023-10-10 14:13:23,905][76543] Updated weights for policy 0, policy_version 39473 (0.0007) -[2023-10-10 14:13:24,284][76543] Updated weights for policy 0, policy_version 39483 (0.0008) -[2023-10-10 14:13:26,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 80805888. Throughput: 0: 1831.4, 1: 1820.6. Samples: 20209198. Policy #0 lag: (min: 3.0, avg: 3.0, max: 4.0) -[2023-10-10 14:13:26,076][75634] Avg episode reward: [(0, '36.590'), (1, '35.550')] -[2023-10-10 14:13:26,417][76542] Updated weights for policy 1, policy_version 39430 (0.0008) -[2023-10-10 14:13:26,784][76542] Updated weights for policy 1, policy_version 39440 (0.0009) -[2023-10-10 14:13:27,151][76542] Updated weights for policy 1, policy_version 39450 (0.0012) -[2023-10-10 14:13:28,025][76543] Updated weights for policy 0, policy_version 39493 (0.0008) -[2023-10-10 14:13:28,397][76543] Updated weights for policy 0, policy_version 39503 (0.0011) -[2023-10-10 14:13:28,768][76543] Updated weights for policy 0, policy_version 39513 (0.0008) -[2023-10-10 14:13:30,836][76542] Updated weights for policy 1, policy_version 39460 (0.0010) -[2023-10-10 14:13:31,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 80871424. Throughput: 0: 1840.5, 1: 1823.3. Samples: 20231714. Policy #0 lag: (min: 3.0, avg: 3.0, max: 4.0) -[2023-10-10 14:13:31,076][75634] Avg episode reward: [(0, '36.440'), (1, '35.980')] -[2023-10-10 14:13:31,214][76542] Updated weights for policy 1, policy_version 39470 (0.0009) -[2023-10-10 14:13:31,574][76542] Updated weights for policy 1, policy_version 39480 (0.0010) -[2023-10-10 14:13:32,510][76543] Updated weights for policy 0, policy_version 39523 (0.0007) -[2023-10-10 14:13:32,875][76543] Updated weights for policy 0, policy_version 39533 (0.0008) -[2023-10-10 14:13:33,248][76543] Updated weights for policy 0, policy_version 39543 (0.0009) -[2023-10-10 14:13:35,150][76542] Updated weights for policy 1, policy_version 39490 (0.0009) -[2023-10-10 14:13:35,519][76542] Updated weights for policy 1, policy_version 39500 (0.0009) -[2023-10-10 14:13:35,893][76542] Updated weights for policy 1, policy_version 39510 (0.0009) -[2023-10-10 14:13:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 80936960. Throughput: 0: 1825.5, 1: 1829.8. Samples: 20242302. Policy #0 lag: (min: 3.0, avg: 3.0, max: 4.0) -[2023-10-10 14:13:36,076][75634] Avg episode reward: [(0, '36.570'), (1, '35.270')] -[2023-10-10 14:13:36,259][76542] Updated weights for policy 1, policy_version 39520 (0.0007) -[2023-10-10 14:13:36,953][76543] Updated weights for policy 0, policy_version 39553 (0.0009) -[2023-10-10 14:13:37,324][76543] Updated weights for policy 0, policy_version 39563 (0.0011) -[2023-10-10 14:13:37,697][76543] Updated weights for policy 0, policy_version 39573 (0.0007) -[2023-10-10 14:13:38,062][76543] Updated weights for policy 0, policy_version 39583 (0.0008) -[2023-10-10 14:13:40,045][76542] Updated weights for policy 1, policy_version 39530 (0.0010) -[2023-10-10 14:13:40,423][76542] Updated weights for policy 1, policy_version 39540 (0.0011) -[2023-10-10 14:13:40,782][76542] Updated weights for policy 1, policy_version 39550 (0.0009) -[2023-10-10 14:13:41,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 81035264. Throughput: 0: 1838.0, 1: 1830.9. Samples: 20264600. Policy #0 lag: (min: 3.0, avg: 3.0, max: 4.0) -[2023-10-10 14:13:41,077][75634] Avg episode reward: [(0, '33.940'), (1, '33.970')] -[2023-10-10 14:13:41,748][76543] Updated weights for policy 0, policy_version 39593 (0.0009) -[2023-10-10 14:13:42,117][76543] Updated weights for policy 0, policy_version 39603 (0.0009) -[2023-10-10 14:13:42,495][76543] Updated weights for policy 0, policy_version 39613 (0.0008) -[2023-10-10 14:13:44,362][76542] Updated weights for policy 1, policy_version 39560 (0.0010) -[2023-10-10 14:13:44,737][76542] Updated weights for policy 1, policy_version 39570 (0.0011) -[2023-10-10 14:13:45,117][76542] Updated weights for policy 1, policy_version 39580 (0.0007) -[2023-10-10 14:13:46,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 81100800. Throughput: 0: 1836.1, 1: 1832.0. Samples: 20286158. Policy #0 lag: (min: 3.0, avg: 3.0, max: 4.0) -[2023-10-10 14:13:46,076][75634] Avg episode reward: [(0, '34.450'), (1, '34.380')] -[2023-10-10 14:13:46,270][76543] Updated weights for policy 0, policy_version 39623 (0.0011) -[2023-10-10 14:13:46,656][76543] Updated weights for policy 0, policy_version 39633 (0.0011) -[2023-10-10 14:13:47,022][76543] Updated weights for policy 0, policy_version 39643 (0.0010) -[2023-10-10 14:13:48,785][76542] Updated weights for policy 1, policy_version 39590 (0.0008) -[2023-10-10 14:13:49,149][76542] Updated weights for policy 1, policy_version 39600 (0.0011) -[2023-10-10 14:13:49,518][76542] Updated weights for policy 1, policy_version 39610 (0.0008) -[2023-10-10 14:13:50,736][76543] Updated weights for policy 0, policy_version 39653 (0.0010) -[2023-10-10 14:13:51,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 81166336. Throughput: 0: 1832.7, 1: 1820.4. Samples: 20297232. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-10 14:13:51,077][75634] Avg episode reward: [(0, '35.310'), (1, '35.490')] -[2023-10-10 14:13:51,115][76543] Updated weights for policy 0, policy_version 39663 (0.0012) -[2023-10-10 14:13:51,497][76543] Updated weights for policy 0, policy_version 39673 (0.0010) -[2023-10-10 14:13:53,193][76542] Updated weights for policy 1, policy_version 39620 (0.0009) -[2023-10-10 14:13:53,557][76542] Updated weights for policy 1, policy_version 39630 (0.0009) -[2023-10-10 14:13:53,921][76542] Updated weights for policy 1, policy_version 39640 (0.0007) -[2023-10-10 14:13:55,155][76543] Updated weights for policy 0, policy_version 39683 (0.0008) -[2023-10-10 14:13:55,516][76543] Updated weights for policy 0, policy_version 39693 (0.0010) -[2023-10-10 14:13:55,884][76543] Updated weights for policy 0, policy_version 39703 (0.0007) -[2023-10-10 14:13:56,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 81231872. Throughput: 0: 1828.2, 1: 1826.0. Samples: 20318862. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-10 14:13:56,076][75634] Avg episode reward: [(0, '34.090'), (1, '35.710')] -[2023-10-10 14:13:57,673][76542] Updated weights for policy 1, policy_version 39650 (0.0008) -[2023-10-10 14:13:58,035][76542] Updated weights for policy 1, policy_version 39660 (0.0010) -[2023-10-10 14:13:58,411][76542] Updated weights for policy 1, policy_version 39670 (0.0009) -[2023-10-10 14:13:58,776][76542] Updated weights for policy 1, policy_version 39680 (0.0009) -[2023-10-10 14:13:59,579][76543] Updated weights for policy 0, policy_version 39713 (0.0008) -[2023-10-10 14:13:59,949][76543] Updated weights for policy 0, policy_version 39723 (0.0008) -[2023-10-10 14:14:00,322][76543] Updated weights for policy 0, policy_version 39733 (0.0007) -[2023-10-10 14:14:00,686][76543] Updated weights for policy 0, policy_version 39743 (0.0010) -[2023-10-10 14:14:01,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 81330176. Throughput: 0: 1825.0, 1: 1829.0. Samples: 20340926. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-10 14:14:01,076][75634] Avg episode reward: [(0, '36.080'), (1, '37.490')] -[2023-10-10 14:14:02,580][76542] Updated weights for policy 1, policy_version 39690 (0.0010) -[2023-10-10 14:14:02,952][76542] Updated weights for policy 1, policy_version 39700 (0.0009) -[2023-10-10 14:14:03,323][76542] Updated weights for policy 1, policy_version 39710 (0.0008) -[2023-10-10 14:14:04,205][76543] Updated weights for policy 0, policy_version 39753 (0.0008) -[2023-10-10 14:14:04,573][76543] Updated weights for policy 0, policy_version 39763 (0.0009) -[2023-10-10 14:14:04,944][76543] Updated weights for policy 0, policy_version 39773 (0.0010) -[2023-10-10 14:14:06,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 81395712. Throughput: 0: 1827.4, 1: 1826.6. Samples: 20351650. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-10 14:14:06,076][75634] Avg episode reward: [(0, '35.210'), (1, '35.350')] -[2023-10-10 14:14:06,988][76542] Updated weights for policy 1, policy_version 39720 (0.0009) -[2023-10-10 14:14:07,348][76542] Updated weights for policy 1, policy_version 39730 (0.0009) -[2023-10-10 14:14:07,721][76542] Updated weights for policy 1, policy_version 39740 (0.0007) -[2023-10-10 14:14:08,728][76543] Updated weights for policy 0, policy_version 39783 (0.0009) -[2023-10-10 14:14:09,087][76543] Updated weights for policy 0, policy_version 39793 (0.0010) -[2023-10-10 14:14:09,453][76543] Updated weights for policy 0, policy_version 39803 (0.0010) -[2023-10-10 14:14:11,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 81461248. Throughput: 0: 1827.5, 1: 1826.4. Samples: 20373624. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-10 14:14:11,076][75634] Avg episode reward: [(0, '35.890'), (1, '35.200')] -[2023-10-10 14:14:11,374][76542] Updated weights for policy 1, policy_version 39750 (0.0008) -[2023-10-10 14:14:11,750][76542] Updated weights for policy 1, policy_version 39760 (0.0010) -[2023-10-10 14:14:12,118][76542] Updated weights for policy 1, policy_version 39770 (0.0009) -[2023-10-10 14:14:13,086][76543] Updated weights for policy 0, policy_version 39813 (0.0009) -[2023-10-10 14:14:13,457][76543] Updated weights for policy 0, policy_version 39823 (0.0010) -[2023-10-10 14:14:13,825][76543] Updated weights for policy 0, policy_version 39833 (0.0008) -[2023-10-10 14:14:15,714][76542] Updated weights for policy 1, policy_version 39780 (0.0010) -[2023-10-10 14:14:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 81526784. Throughput: 0: 1822.3, 1: 1824.8. Samples: 20395836. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:14:16,077][75634] Avg episode reward: [(0, '34.960'), (1, '31.780')] -[2023-10-10 14:14:16,081][76542] Updated weights for policy 1, policy_version 39790 (0.0009) -[2023-10-10 14:14:16,445][76542] Updated weights for policy 1, policy_version 39800 (0.0008) -[2023-10-10 14:14:17,538][76543] Updated weights for policy 0, policy_version 39843 (0.0009) -[2023-10-10 14:14:17,901][76543] Updated weights for policy 0, policy_version 39853 (0.0008) -[2023-10-10 14:14:18,282][76543] Updated weights for policy 0, policy_version 39863 (0.0008) -[2023-10-10 14:14:20,175][76542] Updated weights for policy 1, policy_version 39810 (0.0009) -[2023-10-10 14:14:20,546][76542] Updated weights for policy 1, policy_version 39820 (0.0007) -[2023-10-10 14:14:20,910][76542] Updated weights for policy 1, policy_version 39830 (0.0008) -[2023-10-10 14:14:21,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 81592320. Throughput: 0: 1827.3, 1: 1824.1. Samples: 20406618. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:14:21,076][75634] Avg episode reward: [(0, '37.310'), (1, '32.910')] -[2023-10-10 14:14:21,271][76542] Updated weights for policy 1, policy_version 39840 (0.0007) -[2023-10-10 14:14:21,985][76543] Updated weights for policy 0, policy_version 39873 (0.0008) -[2023-10-10 14:14:22,359][76543] Updated weights for policy 0, policy_version 39883 (0.0007) -[2023-10-10 14:14:22,732][76543] Updated weights for policy 0, policy_version 39893 (0.0008) -[2023-10-10 14:14:23,101][76543] Updated weights for policy 0, policy_version 39903 (0.0009) -[2023-10-10 14:14:24,959][76542] Updated weights for policy 1, policy_version 39850 (0.0009) -[2023-10-10 14:14:25,326][76542] Updated weights for policy 1, policy_version 39860 (0.0010) -[2023-10-10 14:14:25,690][76542] Updated weights for policy 1, policy_version 39870 (0.0010) -[2023-10-10 14:14:26,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 81690624. Throughput: 0: 1827.2, 1: 1821.8. Samples: 20428802. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:14:26,076][75634] Avg episode reward: [(0, '35.950'), (1, '33.240')] -[2023-10-10 14:14:26,628][76543] Updated weights for policy 0, policy_version 39913 (0.0008) -[2023-10-10 14:14:27,003][76543] Updated weights for policy 0, policy_version 39923 (0.0008) -[2023-10-10 14:14:27,372][76543] Updated weights for policy 0, policy_version 39933 (0.0007) -[2023-10-10 14:14:29,356][76542] Updated weights for policy 1, policy_version 39880 (0.0008) -[2023-10-10 14:14:29,712][76542] Updated weights for policy 1, policy_version 39890 (0.0009) -[2023-10-10 14:14:30,086][76542] Updated weights for policy 1, policy_version 39900 (0.0008) -[2023-10-10 14:14:30,904][76543] Updated weights for policy 0, policy_version 39943 (0.0009) -[2023-10-10 14:14:31,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 81756160. Throughput: 0: 1830.6, 1: 1817.6. Samples: 20450328. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:14:31,076][75634] Avg episode reward: [(0, '38.130'), (1, '32.520')] -[2023-10-10 14:14:31,086][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000039904_40861696.pth... -[2023-10-10 14:14:31,124][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000038208_39124992.pth -[2023-10-10 14:14:31,280][76543] Updated weights for policy 0, policy_version 39953 (0.0010) -[2023-10-10 14:14:31,653][76543] Updated weights for policy 0, policy_version 39963 (0.0008) -[2023-10-10 14:14:31,842][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000039968_40927232.pth... -[2023-10-10 14:14:31,871][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000038240_39157760.pth -[2023-10-10 14:14:33,816][76542] Updated weights for policy 1, policy_version 39910 (0.0007) -[2023-10-10 14:14:34,173][76542] Updated weights for policy 1, policy_version 39920 (0.0008) -[2023-10-10 14:14:34,536][76542] Updated weights for policy 1, policy_version 39930 (0.0009) -[2023-10-10 14:14:35,357][76543] Updated weights for policy 0, policy_version 39973 (0.0009) -[2023-10-10 14:14:35,741][76543] Updated weights for policy 0, policy_version 39983 (0.0009) -[2023-10-10 14:14:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 81821696. Throughput: 0: 1830.5, 1: 1820.2. Samples: 20461514. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:14:36,076][75634] Avg episode reward: [(0, '37.400'), (1, '33.510')] -[2023-10-10 14:14:36,112][76543] Updated weights for policy 0, policy_version 39993 (0.0009) -[2023-10-10 14:14:38,195][76542] Updated weights for policy 1, policy_version 39940 (0.0009) -[2023-10-10 14:14:38,570][76542] Updated weights for policy 1, policy_version 39950 (0.0010) -[2023-10-10 14:14:38,934][76542] Updated weights for policy 1, policy_version 39960 (0.0008) -[2023-10-10 14:14:39,843][76543] Updated weights for policy 0, policy_version 40003 (0.0009) -[2023-10-10 14:14:40,223][76543] Updated weights for policy 0, policy_version 40013 (0.0009) -[2023-10-10 14:14:40,588][76543] Updated weights for policy 0, policy_version 40023 (0.0010) -[2023-10-10 14:14:41,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 81920000. Throughput: 0: 1825.4, 1: 1816.9. Samples: 20482764. Policy #0 lag: (min: 20.0, avg: 26.6, max: 52.0) -[2023-10-10 14:14:41,077][75634] Avg episode reward: [(0, '36.430'), (1, '32.640')] -[2023-10-10 14:14:42,837][76542] Updated weights for policy 1, policy_version 39970 (0.0009) -[2023-10-10 14:14:43,196][76542] Updated weights for policy 1, policy_version 39980 (0.0010) -[2023-10-10 14:14:43,567][76542] Updated weights for policy 1, policy_version 39990 (0.0010) -[2023-10-10 14:14:43,932][76542] Updated weights for policy 1, policy_version 40000 (0.0011) -[2023-10-10 14:14:44,170][76543] Updated weights for policy 0, policy_version 40033 (0.0009) -[2023-10-10 14:14:44,537][76543] Updated weights for policy 0, policy_version 40043 (0.0008) -[2023-10-10 14:14:44,909][76543] Updated weights for policy 0, policy_version 40053 (0.0008) -[2023-10-10 14:14:45,283][76543] Updated weights for policy 0, policy_version 40063 (0.0009) -[2023-10-10 14:14:46,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 81985536. Throughput: 0: 1817.0, 1: 1811.6. Samples: 20504212. Policy #0 lag: (min: 20.0, avg: 26.6, max: 52.0) -[2023-10-10 14:14:46,076][75634] Avg episode reward: [(0, '39.840'), (1, '34.210')] -[2023-10-10 14:14:47,756][76542] Updated weights for policy 1, policy_version 40010 (0.0009) -[2023-10-10 14:14:48,127][76542] Updated weights for policy 1, policy_version 40020 (0.0007) -[2023-10-10 14:14:48,494][76542] Updated weights for policy 1, policy_version 40030 (0.0008) -[2023-10-10 14:14:49,093][76543] Updated weights for policy 0, policy_version 40073 (0.0008) -[2023-10-10 14:14:49,456][76543] Updated weights for policy 0, policy_version 40083 (0.0008) -[2023-10-10 14:14:49,838][76543] Updated weights for policy 0, policy_version 40093 (0.0010) -[2023-10-10 14:14:51,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 82051072. Throughput: 0: 1824.7, 1: 1809.2. Samples: 20515174. Policy #0 lag: (min: 20.0, avg: 26.6, max: 52.0) -[2023-10-10 14:14:51,076][75634] Avg episode reward: [(0, '33.040'), (1, '31.870')] -[2023-10-10 14:14:51,977][76542] Updated weights for policy 1, policy_version 40040 (0.0008) -[2023-10-10 14:14:52,352][76542] Updated weights for policy 1, policy_version 40050 (0.0007) -[2023-10-10 14:14:52,722][76542] Updated weights for policy 1, policy_version 40060 (0.0009) -[2023-10-10 14:14:53,609][76543] Updated weights for policy 0, policy_version 40103 (0.0008) -[2023-10-10 14:14:53,991][76543] Updated weights for policy 0, policy_version 40113 (0.0008) -[2023-10-10 14:14:54,362][76543] Updated weights for policy 0, policy_version 40123 (0.0010) -[2023-10-10 14:14:56,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 82116608. Throughput: 0: 1819.7, 1: 1813.6. Samples: 20537122. Policy #0 lag: (min: 20.0, avg: 26.6, max: 52.0) -[2023-10-10 14:14:56,077][75634] Avg episode reward: [(0, '34.420'), (1, '31.830')] -[2023-10-10 14:14:56,374][76542] Updated weights for policy 1, policy_version 40070 (0.0007) -[2023-10-10 14:14:56,741][76542] Updated weights for policy 1, policy_version 40080 (0.0008) -[2023-10-10 14:14:57,118][76542] Updated weights for policy 1, policy_version 40090 (0.0008) -[2023-10-10 14:14:57,914][76543] Updated weights for policy 0, policy_version 40133 (0.0008) -[2023-10-10 14:14:58,303][76543] Updated weights for policy 0, policy_version 40143 (0.0008) -[2023-10-10 14:14:58,682][76543] Updated weights for policy 0, policy_version 40153 (0.0009) -[2023-10-10 14:15:00,729][76542] Updated weights for policy 1, policy_version 40100 (0.0008) -[2023-10-10 14:15:01,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 82182144. Throughput: 0: 1828.3, 1: 1813.0. Samples: 20559696. Policy #0 lag: (min: 20.0, avg: 26.6, max: 52.0) -[2023-10-10 14:15:01,076][75634] Avg episode reward: [(0, '32.350'), (1, '34.740')] -[2023-10-10 14:15:01,100][76542] Updated weights for policy 1, policy_version 40110 (0.0008) -[2023-10-10 14:15:01,463][76542] Updated weights for policy 1, policy_version 40120 (0.0008) -[2023-10-10 14:15:02,244][76543] Updated weights for policy 0, policy_version 40163 (0.0008) -[2023-10-10 14:15:02,620][76543] Updated weights for policy 0, policy_version 40173 (0.0007) -[2023-10-10 14:15:02,991][76543] Updated weights for policy 0, policy_version 40183 (0.0007) -[2023-10-10 14:15:05,309][76542] Updated weights for policy 1, policy_version 40130 (0.0009) -[2023-10-10 14:15:05,675][76542] Updated weights for policy 1, policy_version 40140 (0.0008) -[2023-10-10 14:15:06,041][76542] Updated weights for policy 1, policy_version 40150 (0.0007) -[2023-10-10 14:15:06,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 82247680. Throughput: 0: 1821.3, 1: 1810.0. Samples: 20570028. Policy #0 lag: (min: 20.0, avg: 26.6, max: 52.0) -[2023-10-10 14:15:06,076][75634] Avg episode reward: [(0, '28.550'), (1, '34.290')] -[2023-10-10 14:15:06,409][76542] Updated weights for policy 1, policy_version 40160 (0.0008) -[2023-10-10 14:15:06,619][76543] Updated weights for policy 0, policy_version 40193 (0.0008) -[2023-10-10 14:15:06,988][76543] Updated weights for policy 0, policy_version 40203 (0.0009) -[2023-10-10 14:15:07,362][76543] Updated weights for policy 0, policy_version 40213 (0.0009) -[2023-10-10 14:15:07,734][76543] Updated weights for policy 0, policy_version 40223 (0.0009) -[2023-10-10 14:15:10,009][76542] Updated weights for policy 1, policy_version 40170 (0.0009) -[2023-10-10 14:15:10,380][76542] Updated weights for policy 1, policy_version 40180 (0.0008) -[2023-10-10 14:15:10,745][76542] Updated weights for policy 1, policy_version 40190 (0.0007) -[2023-10-10 14:15:11,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 82345984. Throughput: 0: 1828.3, 1: 1809.5. Samples: 20592504. Policy #0 lag: (min: 9.0, avg: 19.9, max: 41.0) -[2023-10-10 14:15:11,077][75634] Avg episode reward: [(0, '33.830'), (1, '33.400')] -[2023-10-10 14:15:11,305][76543] Updated weights for policy 0, policy_version 40233 (0.0008) -[2023-10-10 14:15:11,680][76543] Updated weights for policy 0, policy_version 40243 (0.0007) -[2023-10-10 14:15:12,050][76543] Updated weights for policy 0, policy_version 40253 (0.0007) -[2023-10-10 14:15:14,298][76542] Updated weights for policy 1, policy_version 40200 (0.0010) -[2023-10-10 14:15:14,666][76542] Updated weights for policy 1, policy_version 40210 (0.0011) -[2023-10-10 14:15:15,035][76542] Updated weights for policy 1, policy_version 40220 (0.0010) -[2023-10-10 14:15:15,939][76543] Updated weights for policy 0, policy_version 40263 (0.0010) -[2023-10-10 14:15:16,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 82411520. Throughput: 0: 1822.6, 1: 1819.3. Samples: 20614216. Policy #0 lag: (min: 9.0, avg: 19.9, max: 41.0) -[2023-10-10 14:15:16,077][75634] Avg episode reward: [(0, '28.700'), (1, '35.800')] -[2023-10-10 14:15:16,307][76543] Updated weights for policy 0, policy_version 40273 (0.0008) -[2023-10-10 14:15:16,684][76543] Updated weights for policy 0, policy_version 40283 (0.0011) -[2023-10-10 14:15:18,641][76542] Updated weights for policy 1, policy_version 40230 (0.0008) -[2023-10-10 14:15:19,014][76542] Updated weights for policy 1, policy_version 40240 (0.0007) -[2023-10-10 14:15:19,375][76542] Updated weights for policy 1, policy_version 40250 (0.0010) -[2023-10-10 14:15:20,483][76543] Updated weights for policy 0, policy_version 40293 (0.0007) -[2023-10-10 14:15:20,860][76543] Updated weights for policy 0, policy_version 40303 (0.0008) -[2023-10-10 14:15:21,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 82477056. Throughput: 0: 1820.9, 1: 1817.5. Samples: 20625240. Policy #0 lag: (min: 9.0, avg: 19.9, max: 41.0) -[2023-10-10 14:15:21,076][75634] Avg episode reward: [(0, '35.010'), (1, '38.730')] -[2023-10-10 14:15:21,232][76543] Updated weights for policy 0, policy_version 40313 (0.0011) -[2023-10-10 14:15:23,051][76542] Updated weights for policy 1, policy_version 40260 (0.0009) -[2023-10-10 14:15:23,423][76542] Updated weights for policy 1, policy_version 40270 (0.0009) -[2023-10-10 14:15:23,794][76542] Updated weights for policy 1, policy_version 40280 (0.0007) -[2023-10-10 14:15:24,853][76543] Updated weights for policy 0, policy_version 40323 (0.0007) -[2023-10-10 14:15:25,216][76543] Updated weights for policy 0, policy_version 40333 (0.0008) -[2023-10-10 14:15:25,601][76543] Updated weights for policy 0, policy_version 40343 (0.0009) -[2023-10-10 14:15:26,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 82575360. Throughput: 0: 1824.0, 1: 1821.6. Samples: 20646820. Policy #0 lag: (min: 9.0, avg: 19.9, max: 41.0) -[2023-10-10 14:15:26,077][75634] Avg episode reward: [(0, '37.830'), (1, '38.590')] -[2023-10-10 14:15:27,521][76542] Updated weights for policy 1, policy_version 40290 (0.0008) -[2023-10-10 14:15:27,880][76542] Updated weights for policy 1, policy_version 40300 (0.0009) -[2023-10-10 14:15:28,264][76542] Updated weights for policy 1, policy_version 40310 (0.0009) -[2023-10-10 14:15:28,630][76542] Updated weights for policy 1, policy_version 40320 (0.0007) -[2023-10-10 14:15:29,311][76543] Updated weights for policy 0, policy_version 40353 (0.0009) -[2023-10-10 14:15:29,683][76543] Updated weights for policy 0, policy_version 40363 (0.0009) -[2023-10-10 14:15:30,061][76543] Updated weights for policy 0, policy_version 40373 (0.0007) -[2023-10-10 14:15:30,439][76543] Updated weights for policy 0, policy_version 40383 (0.0007) -[2023-10-10 14:15:31,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 82640896. Throughput: 0: 1824.1, 1: 1833.1. Samples: 20668784. Policy #0 lag: (min: 9.0, avg: 19.9, max: 41.0) -[2023-10-10 14:15:31,077][75634] Avg episode reward: [(0, '35.350'), (1, '35.070')] -[2023-10-10 14:15:32,296][76542] Updated weights for policy 1, policy_version 40330 (0.0007) -[2023-10-10 14:15:32,672][76542] Updated weights for policy 1, policy_version 40340 (0.0007) -[2023-10-10 14:15:33,037][76542] Updated weights for policy 1, policy_version 40350 (0.0008) -[2023-10-10 14:15:34,173][76543] Updated weights for policy 0, policy_version 40393 (0.0007) -[2023-10-10 14:15:34,545][76543] Updated weights for policy 0, policy_version 40403 (0.0008) -[2023-10-10 14:15:34,913][76543] Updated weights for policy 0, policy_version 40413 (0.0009) -[2023-10-10 14:15:36,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 82706432. Throughput: 0: 1818.5, 1: 1838.5. Samples: 20679738. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-10 14:15:36,076][75634] Avg episode reward: [(0, '36.380'), (1, '38.180')] -[2023-10-10 14:15:36,663][76542] Updated weights for policy 1, policy_version 40360 (0.0007) -[2023-10-10 14:15:37,023][76542] Updated weights for policy 1, policy_version 40370 (0.0009) -[2023-10-10 14:15:37,387][76542] Updated weights for policy 1, policy_version 40380 (0.0009) -[2023-10-10 14:15:38,602][76543] Updated weights for policy 0, policy_version 40423 (0.0008) -[2023-10-10 14:15:38,983][76543] Updated weights for policy 0, policy_version 40433 (0.0008) -[2023-10-10 14:15:39,349][76543] Updated weights for policy 0, policy_version 40443 (0.0008) -[2023-10-10 14:15:41,062][76542] Updated weights for policy 1, policy_version 40390 (0.0011) -[2023-10-10 14:15:41,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 82771968. Throughput: 0: 1823.0, 1: 1834.2. Samples: 20701698. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-10 14:15:41,076][75634] Avg episode reward: [(0, '34.600'), (1, '35.240')] -[2023-10-10 14:15:41,431][76542] Updated weights for policy 1, policy_version 40400 (0.0008) -[2023-10-10 14:15:41,805][76542] Updated weights for policy 1, policy_version 40410 (0.0010) -[2023-10-10 14:15:43,015][76543] Updated weights for policy 0, policy_version 40453 (0.0009) -[2023-10-10 14:15:43,386][76543] Updated weights for policy 0, policy_version 40463 (0.0009) -[2023-10-10 14:15:43,759][76543] Updated weights for policy 0, policy_version 40473 (0.0007) -[2023-10-10 14:15:45,664][76542] Updated weights for policy 1, policy_version 40420 (0.0010) -[2023-10-10 14:15:46,041][76542] Updated weights for policy 1, policy_version 40430 (0.0008) -[2023-10-10 14:15:46,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 82837504. Throughput: 0: 1816.3, 1: 1827.6. Samples: 20723674. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-10 14:15:46,077][75634] Avg episode reward: [(0, '34.060'), (1, '36.500')] -[2023-10-10 14:15:46,414][76542] Updated weights for policy 1, policy_version 40440 (0.0007) -[2023-10-10 14:15:47,542][76543] Updated weights for policy 0, policy_version 40483 (0.0008) -[2023-10-10 14:15:47,902][76543] Updated weights for policy 0, policy_version 40493 (0.0011) -[2023-10-10 14:15:48,278][76543] Updated weights for policy 0, policy_version 40503 (0.0009) -[2023-10-10 14:15:50,030][76542] Updated weights for policy 1, policy_version 40450 (0.0008) -[2023-10-10 14:15:50,397][76542] Updated weights for policy 1, policy_version 40460 (0.0008) -[2023-10-10 14:15:50,759][76542] Updated weights for policy 1, policy_version 40470 (0.0008) -[2023-10-10 14:15:51,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 82903040. Throughput: 0: 1820.4, 1: 1831.7. Samples: 20734376. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-10 14:15:51,077][75634] Avg episode reward: [(0, '35.340'), (1, '36.550')] -[2023-10-10 14:15:51,122][76542] Updated weights for policy 1, policy_version 40480 (0.0009) -[2023-10-10 14:15:51,862][76543] Updated weights for policy 0, policy_version 40513 (0.0008) -[2023-10-10 14:15:52,232][76543] Updated weights for policy 0, policy_version 40523 (0.0007) -[2023-10-10 14:15:52,601][76543] Updated weights for policy 0, policy_version 40533 (0.0008) -[2023-10-10 14:15:52,974][76543] Updated weights for policy 0, policy_version 40543 (0.0009) -[2023-10-10 14:15:54,794][76542] Updated weights for policy 1, policy_version 40490 (0.0007) -[2023-10-10 14:15:55,160][76542] Updated weights for policy 1, policy_version 40500 (0.0008) -[2023-10-10 14:15:55,539][76542] Updated weights for policy 1, policy_version 40510 (0.0010) -[2023-10-10 14:15:56,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 83001344. Throughput: 0: 1818.0, 1: 1830.6. Samples: 20756694. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-10 14:15:56,077][75634] Avg episode reward: [(0, '32.490'), (1, '33.900')] -[2023-10-10 14:15:56,530][76543] Updated weights for policy 0, policy_version 40553 (0.0007) -[2023-10-10 14:15:56,899][76543] Updated weights for policy 0, policy_version 40563 (0.0007) -[2023-10-10 14:15:57,272][76543] Updated weights for policy 0, policy_version 40573 (0.0008) -[2023-10-10 14:15:59,351][76542] Updated weights for policy 1, policy_version 40520 (0.0010) -[2023-10-10 14:15:59,723][76542] Updated weights for policy 1, policy_version 40530 (0.0011) -[2023-10-10 14:16:00,086][76542] Updated weights for policy 1, policy_version 40540 (0.0010) -[2023-10-10 14:16:00,999][76543] Updated weights for policy 0, policy_version 40583 (0.0008) -[2023-10-10 14:16:01,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 83066880. Throughput: 0: 1820.5, 1: 1823.1. Samples: 20778174. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-10 14:16:01,076][75634] Avg episode reward: [(0, '32.720'), (1, '33.570')] -[2023-10-10 14:16:01,382][76543] Updated weights for policy 0, policy_version 40593 (0.0009) -[2023-10-10 14:16:01,753][76543] Updated weights for policy 0, policy_version 40603 (0.0009) -[2023-10-10 14:16:03,883][76542] Updated weights for policy 1, policy_version 40550 (0.0007) -[2023-10-10 14:16:04,251][76542] Updated weights for policy 1, policy_version 40560 (0.0007) -[2023-10-10 14:16:04,621][76542] Updated weights for policy 1, policy_version 40570 (0.0008) -[2023-10-10 14:16:05,321][76543] Updated weights for policy 0, policy_version 40613 (0.0009) -[2023-10-10 14:16:05,710][76543] Updated weights for policy 0, policy_version 40623 (0.0008) -[2023-10-10 14:16:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 83132416. Throughput: 0: 1823.1, 1: 1824.7. Samples: 20789390. Policy #0 lag: (min: 14.0, avg: 15.7, max: 42.0) -[2023-10-10 14:16:06,077][75634] Avg episode reward: [(0, '37.330'), (1, '31.780')] -[2023-10-10 14:16:06,080][76543] Updated weights for policy 0, policy_version 40633 (0.0008) -[2023-10-10 14:16:08,465][76542] Updated weights for policy 1, policy_version 40580 (0.0010) -[2023-10-10 14:16:08,835][76542] Updated weights for policy 1, policy_version 40590 (0.0007) -[2023-10-10 14:16:09,209][76542] Updated weights for policy 1, policy_version 40600 (0.0007) -[2023-10-10 14:16:09,553][76543] Updated weights for policy 0, policy_version 40643 (0.0008) -[2023-10-10 14:16:09,924][76543] Updated weights for policy 0, policy_version 40653 (0.0009) -[2023-10-10 14:16:10,295][76543] Updated weights for policy 0, policy_version 40663 (0.0008) -[2023-10-10 14:16:11,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 83230720. Throughput: 0: 1832.4, 1: 1817.1. Samples: 20811046. Policy #0 lag: (min: 14.0, avg: 15.7, max: 42.0) -[2023-10-10 14:16:11,077][75634] Avg episode reward: [(0, '39.280'), (1, '34.820')] -[2023-10-10 14:16:12,706][76542] Updated weights for policy 1, policy_version 40610 (0.0008) -[2023-10-10 14:16:13,081][76542] Updated weights for policy 1, policy_version 40620 (0.0009) -[2023-10-10 14:16:13,442][76542] Updated weights for policy 1, policy_version 40630 (0.0009) -[2023-10-10 14:16:13,810][76542] Updated weights for policy 1, policy_version 40640 (0.0007) -[2023-10-10 14:16:13,890][76543] Updated weights for policy 0, policy_version 40673 (0.0009) -[2023-10-10 14:16:14,260][76543] Updated weights for policy 0, policy_version 40683 (0.0007) -[2023-10-10 14:16:14,638][76543] Updated weights for policy 0, policy_version 40693 (0.0011) -[2023-10-10 14:16:15,006][76543] Updated weights for policy 0, policy_version 40703 (0.0010) -[2023-10-10 14:16:16,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 83296256. Throughput: 0: 1830.1, 1: 1812.1. Samples: 20832682. Policy #0 lag: (min: 14.0, avg: 15.7, max: 42.0) -[2023-10-10 14:16:16,076][75634] Avg episode reward: [(0, '40.730'), (1, '31.670')] -[2023-10-10 14:16:17,640][76542] Updated weights for policy 1, policy_version 40650 (0.0009) -[2023-10-10 14:16:18,011][76542] Updated weights for policy 1, policy_version 40660 (0.0008) -[2023-10-10 14:16:18,379][76542] Updated weights for policy 1, policy_version 40670 (0.0008) -[2023-10-10 14:16:18,654][76543] Updated weights for policy 0, policy_version 40713 (0.0008) -[2023-10-10 14:16:19,026][76543] Updated weights for policy 0, policy_version 40723 (0.0007) -[2023-10-10 14:16:19,389][76543] Updated weights for policy 0, policy_version 40733 (0.0009) -[2023-10-10 14:16:21,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 83361792. Throughput: 0: 1838.6, 1: 1811.2. Samples: 20843978. Policy #0 lag: (min: 14.0, avg: 15.7, max: 42.0) -[2023-10-10 14:16:21,076][75634] Avg episode reward: [(0, '37.900'), (1, '33.100')] -[2023-10-10 14:16:22,047][76542] Updated weights for policy 1, policy_version 40680 (0.0008) -[2023-10-10 14:16:22,424][76542] Updated weights for policy 1, policy_version 40690 (0.0009) -[2023-10-10 14:16:22,788][76542] Updated weights for policy 1, policy_version 40700 (0.0008) -[2023-10-10 14:16:23,007][76543] Updated weights for policy 0, policy_version 40743 (0.0008) -[2023-10-10 14:16:23,382][76543] Updated weights for policy 0, policy_version 40753 (0.0008) -[2023-10-10 14:16:23,757][76543] Updated weights for policy 0, policy_version 40763 (0.0008) -[2023-10-10 14:16:26,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 83427328. Throughput: 0: 1825.3, 1: 1804.0. Samples: 20865018. Policy #0 lag: (min: 14.0, avg: 15.7, max: 42.0) -[2023-10-10 14:16:26,077][75634] Avg episode reward: [(0, '37.490'), (1, '36.710')] -[2023-10-10 14:16:26,504][76542] Updated weights for policy 1, policy_version 40710 (0.0008) -[2023-10-10 14:16:26,869][76542] Updated weights for policy 1, policy_version 40720 (0.0007) -[2023-10-10 14:16:27,242][76542] Updated weights for policy 1, policy_version 40730 (0.0010) -[2023-10-10 14:16:27,561][76543] Updated weights for policy 0, policy_version 40773 (0.0008) -[2023-10-10 14:16:27,937][76543] Updated weights for policy 0, policy_version 40783 (0.0008) -[2023-10-10 14:16:28,314][76543] Updated weights for policy 0, policy_version 40793 (0.0009) -[2023-10-10 14:16:30,954][76542] Updated weights for policy 1, policy_version 40740 (0.0009) -[2023-10-10 14:16:31,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 83492864. Throughput: 0: 1835.2, 1: 1807.5. Samples: 20887594. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:16:31,076][75634] Avg episode reward: [(0, '34.190'), (1, '32.780')] -[2023-10-10 14:16:31,086][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000040800_41779200.pth... -[2023-10-10 14:16:31,119][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000039104_40042496.pth -[2023-10-10 14:16:31,310][76542] Updated weights for policy 1, policy_version 40750 (0.0008) -[2023-10-10 14:16:31,691][76542] Updated weights for policy 1, policy_version 40760 (0.0008) -[2023-10-10 14:16:31,937][76543] Updated weights for policy 0, policy_version 40803 (0.0008) -[2023-10-10 14:16:31,980][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000040768_41746432.pth... -[2023-10-10 14:16:32,012][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000039040_39976960.pth -[2023-10-10 14:16:32,319][76543] Updated weights for policy 0, policy_version 40813 (0.0009) -[2023-10-10 14:16:32,691][76543] Updated weights for policy 0, policy_version 40823 (0.0011) -[2023-10-10 14:16:35,312][76542] Updated weights for policy 1, policy_version 40770 (0.0009) -[2023-10-10 14:16:35,668][76542] Updated weights for policy 1, policy_version 40780 (0.0008) -[2023-10-10 14:16:36,041][76542] Updated weights for policy 1, policy_version 40790 (0.0007) -[2023-10-10 14:16:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 83558400. Throughput: 0: 1823.3, 1: 1798.2. Samples: 20897342. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:16:36,076][75634] Avg episode reward: [(0, '31.010'), (1, '32.330')] -[2023-10-10 14:16:36,349][76543] Updated weights for policy 0, policy_version 40833 (0.0011) -[2023-10-10 14:16:36,403][76542] Updated weights for policy 1, policy_version 40800 (0.0011) -[2023-10-10 14:16:36,710][76543] Updated weights for policy 0, policy_version 40843 (0.0008) -[2023-10-10 14:16:37,090][76543] Updated weights for policy 0, policy_version 40853 (0.0009) -[2023-10-10 14:16:37,466][76543] Updated weights for policy 0, policy_version 40863 (0.0009) -[2023-10-10 14:16:40,053][76542] Updated weights for policy 1, policy_version 40810 (0.0011) -[2023-10-10 14:16:40,428][76542] Updated weights for policy 1, policy_version 40820 (0.0009) -[2023-10-10 14:16:40,792][76542] Updated weights for policy 1, policy_version 40830 (0.0009) -[2023-10-10 14:16:41,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 83656704. Throughput: 0: 1826.6, 1: 1803.7. Samples: 20920056. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:16:41,076][75634] Avg episode reward: [(0, '30.880'), (1, '29.910')] -[2023-10-10 14:16:41,224][76543] Updated weights for policy 0, policy_version 40873 (0.0008) -[2023-10-10 14:16:41,588][76543] Updated weights for policy 0, policy_version 40883 (0.0010) -[2023-10-10 14:16:41,955][76543] Updated weights for policy 0, policy_version 40893 (0.0007) -[2023-10-10 14:16:44,652][76542] Updated weights for policy 1, policy_version 40840 (0.0007) -[2023-10-10 14:16:45,012][76542] Updated weights for policy 1, policy_version 40850 (0.0011) -[2023-10-10 14:16:45,382][76542] Updated weights for policy 1, policy_version 40860 (0.0010) -[2023-10-10 14:16:45,804][76543] Updated weights for policy 0, policy_version 40903 (0.0008) -[2023-10-10 14:16:46,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 83722240. Throughput: 0: 1825.8, 1: 1802.2. Samples: 20941434. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:16:46,077][75634] Avg episode reward: [(0, '29.730'), (1, '32.850')] -[2023-10-10 14:16:46,174][76543] Updated weights for policy 0, policy_version 40913 (0.0009) -[2023-10-10 14:16:46,554][76543] Updated weights for policy 0, policy_version 40923 (0.0008) -[2023-10-10 14:16:49,170][76542] Updated weights for policy 1, policy_version 40870 (0.0010) -[2023-10-10 14:16:49,541][76542] Updated weights for policy 1, policy_version 40880 (0.0010) -[2023-10-10 14:16:49,909][76542] Updated weights for policy 1, policy_version 40890 (0.0007) -[2023-10-10 14:16:50,408][76543] Updated weights for policy 0, policy_version 40933 (0.0009) -[2023-10-10 14:16:50,784][76543] Updated weights for policy 0, policy_version 40943 (0.0007) -[2023-10-10 14:16:51,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 83787776. Throughput: 0: 1826.8, 1: 1801.9. Samples: 20952682. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:16:51,077][75634] Avg episode reward: [(0, '30.190'), (1, '34.250')] -[2023-10-10 14:16:51,154][76543] Updated weights for policy 0, policy_version 40953 (0.0009) -[2023-10-10 14:16:53,495][76542] Updated weights for policy 1, policy_version 40900 (0.0008) -[2023-10-10 14:16:53,867][76542] Updated weights for policy 1, policy_version 40910 (0.0009) -[2023-10-10 14:16:54,234][76542] Updated weights for policy 1, policy_version 40920 (0.0008) -[2023-10-10 14:16:54,758][76543] Updated weights for policy 0, policy_version 40963 (0.0008) -[2023-10-10 14:16:55,128][76543] Updated weights for policy 0, policy_version 40973 (0.0010) -[2023-10-10 14:16:55,494][76543] Updated weights for policy 0, policy_version 40983 (0.0008) -[2023-10-10 14:16:56,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 83886080. Throughput: 0: 1816.5, 1: 1810.0. Samples: 20974240. Policy #0 lag: (min: 3.0, avg: 11.0, max: 35.0) -[2023-10-10 14:16:56,076][75634] Avg episode reward: [(0, '33.870'), (1, '32.730')] -[2023-10-10 14:16:58,085][76542] Updated weights for policy 1, policy_version 40930 (0.0009) -[2023-10-10 14:16:58,454][76542] Updated weights for policy 1, policy_version 40940 (0.0008) -[2023-10-10 14:16:58,825][76542] Updated weights for policy 1, policy_version 40950 (0.0008) -[2023-10-10 14:16:59,048][76543] Updated weights for policy 0, policy_version 40993 (0.0007) -[2023-10-10 14:16:59,186][76542] Updated weights for policy 1, policy_version 40960 (0.0009) -[2023-10-10 14:16:59,416][76543] Updated weights for policy 0, policy_version 41003 (0.0009) -[2023-10-10 14:16:59,789][76543] Updated weights for policy 0, policy_version 41013 (0.0008) -[2023-10-10 14:17:00,156][76543] Updated weights for policy 0, policy_version 41023 (0.0008) -[2023-10-10 14:17:01,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 83951616. Throughput: 0: 1816.3, 1: 1802.3. Samples: 20995524. Policy #0 lag: (min: 3.0, avg: 11.0, max: 35.0) -[2023-10-10 14:17:01,077][75634] Avg episode reward: [(0, '35.320'), (1, '35.570')] -[2023-10-10 14:17:02,947][76542] Updated weights for policy 1, policy_version 40970 (0.0009) -[2023-10-10 14:17:03,322][76542] Updated weights for policy 1, policy_version 40980 (0.0011) -[2023-10-10 14:17:03,692][76542] Updated weights for policy 1, policy_version 40990 (0.0008) -[2023-10-10 14:17:03,753][76543] Updated weights for policy 0, policy_version 41033 (0.0007) -[2023-10-10 14:17:04,126][76543] Updated weights for policy 0, policy_version 41043 (0.0007) -[2023-10-10 14:17:04,501][76543] Updated weights for policy 0, policy_version 41053 (0.0010) -[2023-10-10 14:17:06,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 84017152. Throughput: 0: 1817.5, 1: 1806.8. Samples: 21007072. Policy #0 lag: (min: 3.0, avg: 11.0, max: 35.0) -[2023-10-10 14:17:06,077][75634] Avg episode reward: [(0, '36.340'), (1, '37.770')] -[2023-10-10 14:17:07,026][76542] Updated weights for policy 1, policy_version 41000 (0.0007) -[2023-10-10 14:17:07,395][76542] Updated weights for policy 1, policy_version 41010 (0.0010) -[2023-10-10 14:17:07,767][76542] Updated weights for policy 1, policy_version 41020 (0.0009) -[2023-10-10 14:17:08,367][76543] Updated weights for policy 0, policy_version 41063 (0.0010) -[2023-10-10 14:17:08,743][76543] Updated weights for policy 0, policy_version 41073 (0.0009) -[2023-10-10 14:17:09,120][76543] Updated weights for policy 0, policy_version 41083 (0.0009) -[2023-10-10 14:17:11,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 84082688. Throughput: 0: 1815.1, 1: 1814.5. Samples: 21028350. Policy #0 lag: (min: 3.0, avg: 11.0, max: 35.0) -[2023-10-10 14:17:11,077][75634] Avg episode reward: [(0, '39.380'), (1, '36.460')] -[2023-10-10 14:17:11,471][76542] Updated weights for policy 1, policy_version 41030 (0.0008) -[2023-10-10 14:17:11,836][76542] Updated weights for policy 1, policy_version 41040 (0.0008) -[2023-10-10 14:17:12,221][76542] Updated weights for policy 1, policy_version 41050 (0.0008) -[2023-10-10 14:17:12,857][76543] Updated weights for policy 0, policy_version 41093 (0.0010) -[2023-10-10 14:17:13,229][76543] Updated weights for policy 0, policy_version 41103 (0.0010) -[2023-10-10 14:17:13,605][76543] Updated weights for policy 0, policy_version 41113 (0.0009) -[2023-10-10 14:17:16,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 84148224. Throughput: 0: 1814.0, 1: 1811.9. Samples: 21050760. Policy #0 lag: (min: 3.0, avg: 11.0, max: 35.0) -[2023-10-10 14:17:16,077][75634] Avg episode reward: [(0, '37.770'), (1, '32.810')] -[2023-10-10 14:17:16,174][76542] Updated weights for policy 1, policy_version 41060 (0.0008) -[2023-10-10 14:17:16,548][76542] Updated weights for policy 1, policy_version 41070 (0.0009) -[2023-10-10 14:17:16,913][76542] Updated weights for policy 1, policy_version 41080 (0.0011) -[2023-10-10 14:17:17,285][76543] Updated weights for policy 0, policy_version 41123 (0.0008) -[2023-10-10 14:17:17,647][76543] Updated weights for policy 0, policy_version 41133 (0.0007) -[2023-10-10 14:17:18,016][76543] Updated weights for policy 0, policy_version 41143 (0.0008) -[2023-10-10 14:17:20,751][76542] Updated weights for policy 1, policy_version 41090 (0.0008) -[2023-10-10 14:17:21,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 84213760. Throughput: 0: 1817.1, 1: 1816.7. Samples: 21060864. Policy #0 lag: (min: 3.0, avg: 11.0, max: 35.0) -[2023-10-10 14:17:21,076][75634] Avg episode reward: [(0, '32.090'), (1, '31.610')] -[2023-10-10 14:17:21,121][76542] Updated weights for policy 1, policy_version 41100 (0.0010) -[2023-10-10 14:17:21,501][76542] Updated weights for policy 1, policy_version 41110 (0.0010) -[2023-10-10 14:17:21,759][76543] Updated weights for policy 0, policy_version 41153 (0.0007) -[2023-10-10 14:17:21,862][76542] Updated weights for policy 1, policy_version 41120 (0.0008) -[2023-10-10 14:17:22,145][76543] Updated weights for policy 0, policy_version 41163 (0.0009) -[2023-10-10 14:17:22,510][76543] Updated weights for policy 0, policy_version 41173 (0.0009) -[2023-10-10 14:17:22,876][76543] Updated weights for policy 0, policy_version 41183 (0.0008) -[2023-10-10 14:17:25,506][76542] Updated weights for policy 1, policy_version 41130 (0.0009) -[2023-10-10 14:17:25,872][76542] Updated weights for policy 1, policy_version 41140 (0.0009) -[2023-10-10 14:17:26,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.2). Total num frames: 84279296. Throughput: 0: 1813.8, 1: 1816.3. Samples: 21083410. Policy #0 lag: (min: 15.0, avg: 23.0, max: 47.0) -[2023-10-10 14:17:26,076][75634] Avg episode reward: [(0, '28.110'), (1, '32.220')] -[2023-10-10 14:17:26,233][76542] Updated weights for policy 1, policy_version 41150 (0.0007) -[2023-10-10 14:17:26,467][76543] Updated weights for policy 0, policy_version 41193 (0.0008) -[2023-10-10 14:17:26,839][76543] Updated weights for policy 0, policy_version 41203 (0.0009) -[2023-10-10 14:17:27,212][76543] Updated weights for policy 0, policy_version 41213 (0.0011) -[2023-10-10 14:17:29,954][76542] Updated weights for policy 1, policy_version 41160 (0.0009) -[2023-10-10 14:17:30,327][76542] Updated weights for policy 1, policy_version 41170 (0.0008) -[2023-10-10 14:17:30,687][76542] Updated weights for policy 1, policy_version 41180 (0.0007) -[2023-10-10 14:17:31,019][76543] Updated weights for policy 0, policy_version 41223 (0.0009) -[2023-10-10 14:17:31,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 84377600. Throughput: 0: 1814.3, 1: 1816.6. Samples: 21104826. Policy #0 lag: (min: 15.0, avg: 23.0, max: 47.0) -[2023-10-10 14:17:31,077][75634] Avg episode reward: [(0, '32.050'), (1, '33.950')] -[2023-10-10 14:17:31,393][76543] Updated weights for policy 0, policy_version 41233 (0.0010) -[2023-10-10 14:17:31,763][76543] Updated weights for policy 0, policy_version 41243 (0.0008) -[2023-10-10 14:17:34,345][76542] Updated weights for policy 1, policy_version 41190 (0.0011) -[2023-10-10 14:17:34,711][76542] Updated weights for policy 1, policy_version 41200 (0.0009) -[2023-10-10 14:17:35,087][76542] Updated weights for policy 1, policy_version 41210 (0.0012) -[2023-10-10 14:17:35,427][76543] Updated weights for policy 0, policy_version 41253 (0.0009) -[2023-10-10 14:17:35,806][76543] Updated weights for policy 0, policy_version 41263 (0.0007) -[2023-10-10 14:17:36,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 84443136. Throughput: 0: 1816.2, 1: 1811.7. Samples: 21115940. Policy #0 lag: (min: 15.0, avg: 23.0, max: 47.0) -[2023-10-10 14:17:36,076][75634] Avg episode reward: [(0, '32.550'), (1, '33.740')] -[2023-10-10 14:17:36,183][76543] Updated weights for policy 0, policy_version 41273 (0.0008) -[2023-10-10 14:17:38,823][76542] Updated weights for policy 1, policy_version 41220 (0.0009) -[2023-10-10 14:17:39,190][76542] Updated weights for policy 1, policy_version 41230 (0.0008) -[2023-10-10 14:17:39,560][76542] Updated weights for policy 1, policy_version 41240 (0.0008) -[2023-10-10 14:17:39,802][76543] Updated weights for policy 0, policy_version 41283 (0.0008) -[2023-10-10 14:17:40,174][76543] Updated weights for policy 0, policy_version 41293 (0.0010) -[2023-10-10 14:17:40,546][76543] Updated weights for policy 0, policy_version 41303 (0.0008) -[2023-10-10 14:17:41,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 84541440. Throughput: 0: 1817.6, 1: 1808.8. Samples: 21137426. Policy #0 lag: (min: 15.0, avg: 23.0, max: 47.0) -[2023-10-10 14:17:41,077][75634] Avg episode reward: [(0, '33.160'), (1, '36.810')] -[2023-10-10 14:17:43,068][76542] Updated weights for policy 1, policy_version 41250 (0.0009) -[2023-10-10 14:17:43,440][76542] Updated weights for policy 1, policy_version 41260 (0.0009) -[2023-10-10 14:17:43,809][76542] Updated weights for policy 1, policy_version 41270 (0.0010) -[2023-10-10 14:17:44,089][76543] Updated weights for policy 0, policy_version 41313 (0.0008) -[2023-10-10 14:17:44,172][76542] Updated weights for policy 1, policy_version 41280 (0.0010) -[2023-10-10 14:17:44,465][76543] Updated weights for policy 0, policy_version 41323 (0.0008) -[2023-10-10 14:17:44,831][76543] Updated weights for policy 0, policy_version 41333 (0.0007) -[2023-10-10 14:17:45,201][76543] Updated weights for policy 0, policy_version 41343 (0.0009) -[2023-10-10 14:17:46,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 84606976. Throughput: 0: 1822.3, 1: 1811.0. Samples: 21159020. Policy #0 lag: (min: 15.0, avg: 23.0, max: 47.0) -[2023-10-10 14:17:46,077][75634] Avg episode reward: [(0, '33.690'), (1, '37.130')] -[2023-10-10 14:17:48,131][76542] Updated weights for policy 1, policy_version 41290 (0.0011) -[2023-10-10 14:17:48,502][76542] Updated weights for policy 1, policy_version 41300 (0.0012) -[2023-10-10 14:17:48,871][76542] Updated weights for policy 1, policy_version 41310 (0.0008) -[2023-10-10 14:17:48,985][76543] Updated weights for policy 0, policy_version 41353 (0.0009) -[2023-10-10 14:17:49,360][76543] Updated weights for policy 0, policy_version 41363 (0.0009) -[2023-10-10 14:17:49,730][76543] Updated weights for policy 0, policy_version 41373 (0.0007) -[2023-10-10 14:17:51,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 84672512. Throughput: 0: 1816.4, 1: 1810.2. Samples: 21170270. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) -[2023-10-10 14:17:51,077][75634] Avg episode reward: [(0, '35.780'), (1, '39.210')] -[2023-10-10 14:17:52,573][76542] Updated weights for policy 1, policy_version 41320 (0.0008) -[2023-10-10 14:17:52,940][76542] Updated weights for policy 1, policy_version 41330 (0.0008) -[2023-10-10 14:17:53,304][76542] Updated weights for policy 1, policy_version 41340 (0.0008) -[2023-10-10 14:17:53,495][76543] Updated weights for policy 0, policy_version 41383 (0.0008) -[2023-10-10 14:17:53,866][76543] Updated weights for policy 0, policy_version 41393 (0.0012) -[2023-10-10 14:17:54,232][76543] Updated weights for policy 0, policy_version 41403 (0.0010) -[2023-10-10 14:17:56,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 84738048. Throughput: 0: 1824.5, 1: 1800.5. Samples: 21191474. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) -[2023-10-10 14:17:56,077][75634] Avg episode reward: [(0, '37.990'), (1, '37.950')] -[2023-10-10 14:17:57,045][76542] Updated weights for policy 1, policy_version 41350 (0.0008) -[2023-10-10 14:17:57,410][76542] Updated weights for policy 1, policy_version 41360 (0.0009) -[2023-10-10 14:17:57,788][76542] Updated weights for policy 1, policy_version 41370 (0.0008) -[2023-10-10 14:17:57,867][76543] Updated weights for policy 0, policy_version 41413 (0.0009) -[2023-10-10 14:17:58,234][76543] Updated weights for policy 0, policy_version 41423 (0.0009) -[2023-10-10 14:17:58,605][76543] Updated weights for policy 0, policy_version 41433 (0.0009) -[2023-10-10 14:18:01,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 84803584. Throughput: 0: 1815.6, 1: 1810.1. Samples: 21213912. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) -[2023-10-10 14:18:01,077][75634] Avg episode reward: [(0, '39.750'), (1, '34.780')] -[2023-10-10 14:18:01,480][76542] Updated weights for policy 1, policy_version 41380 (0.0009) -[2023-10-10 14:18:01,844][76542] Updated weights for policy 1, policy_version 41390 (0.0010) -[2023-10-10 14:18:02,225][76542] Updated weights for policy 1, policy_version 41400 (0.0008) -[2023-10-10 14:18:02,407][76543] Updated weights for policy 0, policy_version 41443 (0.0010) -[2023-10-10 14:18:02,771][76543] Updated weights for policy 0, policy_version 41453 (0.0009) -[2023-10-10 14:18:03,143][76543] Updated weights for policy 0, policy_version 41463 (0.0008) -[2023-10-10 14:18:05,879][76542] Updated weights for policy 1, policy_version 41410 (0.0009) -[2023-10-10 14:18:06,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 84869120. Throughput: 0: 1820.3, 1: 1810.2. Samples: 21224240. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) -[2023-10-10 14:18:06,077][75634] Avg episode reward: [(0, '38.770'), (1, '34.050')] -[2023-10-10 14:18:06,247][76542] Updated weights for policy 1, policy_version 41420 (0.0011) -[2023-10-10 14:18:06,625][76542] Updated weights for policy 1, policy_version 41430 (0.0009) -[2023-10-10 14:18:06,886][76543] Updated weights for policy 0, policy_version 41473 (0.0008) -[2023-10-10 14:18:06,984][76542] Updated weights for policy 1, policy_version 41440 (0.0009) -[2023-10-10 14:18:07,258][76543] Updated weights for policy 0, policy_version 41483 (0.0008) -[2023-10-10 14:18:07,641][76543] Updated weights for policy 0, policy_version 41493 (0.0009) -[2023-10-10 14:18:08,014][76543] Updated weights for policy 0, policy_version 41503 (0.0009) -[2023-10-10 14:18:10,776][76542] Updated weights for policy 1, policy_version 41450 (0.0011) -[2023-10-10 14:18:11,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 84934656. Throughput: 0: 1817.2, 1: 1807.3. Samples: 21246512. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) -[2023-10-10 14:18:11,077][75634] Avg episode reward: [(0, '33.870'), (1, '34.940')] -[2023-10-10 14:18:11,142][76542] Updated weights for policy 1, policy_version 41460 (0.0007) -[2023-10-10 14:18:11,512][76542] Updated weights for policy 1, policy_version 41470 (0.0008) -[2023-10-10 14:18:11,650][76543] Updated weights for policy 0, policy_version 41513 (0.0009) -[2023-10-10 14:18:12,020][76543] Updated weights for policy 0, policy_version 41523 (0.0009) -[2023-10-10 14:18:12,390][76543] Updated weights for policy 0, policy_version 41533 (0.0011) -[2023-10-10 14:18:15,214][76542] Updated weights for policy 1, policy_version 41480 (0.0008) -[2023-10-10 14:18:15,572][76542] Updated weights for policy 1, policy_version 41490 (0.0007) -[2023-10-10 14:18:15,940][76542] Updated weights for policy 1, policy_version 41500 (0.0007) -[2023-10-10 14:18:16,075][76543] Updated weights for policy 0, policy_version 41543 (0.0008) -[2023-10-10 14:18:16,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 85000192. Throughput: 0: 1818.4, 1: 1815.6. Samples: 21268358. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) -[2023-10-10 14:18:16,076][75634] Avg episode reward: [(0, '36.020'), (1, '37.780')] -[2023-10-10 14:18:16,453][76543] Updated weights for policy 0, policy_version 41553 (0.0010) -[2023-10-10 14:18:16,818][76543] Updated weights for policy 0, policy_version 41563 (0.0011) -[2023-10-10 14:18:19,497][76542] Updated weights for policy 1, policy_version 41510 (0.0009) -[2023-10-10 14:18:19,873][76542] Updated weights for policy 1, policy_version 41520 (0.0009) -[2023-10-10 14:18:20,247][76542] Updated weights for policy 1, policy_version 41530 (0.0007) -[2023-10-10 14:18:20,708][76543] Updated weights for policy 0, policy_version 41573 (0.0010) -[2023-10-10 14:18:21,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 85098496. Throughput: 0: 1816.0, 1: 1815.3. Samples: 21279348. Policy #0 lag: (min: 8.0, avg: 35.6, max: 40.0) -[2023-10-10 14:18:21,077][75634] Avg episode reward: [(0, '34.070'), (1, '33.810')] -[2023-10-10 14:18:21,095][76543] Updated weights for policy 0, policy_version 41583 (0.0008) -[2023-10-10 14:18:21,448][76543] Updated weights for policy 0, policy_version 41593 (0.0007) -[2023-10-10 14:18:23,853][76542] Updated weights for policy 1, policy_version 41540 (0.0007) -[2023-10-10 14:18:24,223][76542] Updated weights for policy 1, policy_version 41550 (0.0008) -[2023-10-10 14:18:24,585][76542] Updated weights for policy 1, policy_version 41560 (0.0008) -[2023-10-10 14:18:25,132][76543] Updated weights for policy 0, policy_version 41603 (0.0008) -[2023-10-10 14:18:25,507][76543] Updated weights for policy 0, policy_version 41613 (0.0009) -[2023-10-10 14:18:25,877][76543] Updated weights for policy 0, policy_version 41623 (0.0008) -[2023-10-10 14:18:26,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 85164032. Throughput: 0: 1809.6, 1: 1825.1. Samples: 21300990. Policy #0 lag: (min: 8.0, avg: 35.6, max: 40.0) -[2023-10-10 14:18:26,076][75634] Avg episode reward: [(0, '37.640'), (1, '31.650')] -[2023-10-10 14:18:28,296][76542] Updated weights for policy 1, policy_version 41570 (0.0007) -[2023-10-10 14:18:28,673][76542] Updated weights for policy 1, policy_version 41580 (0.0008) -[2023-10-10 14:18:29,034][76542] Updated weights for policy 1, policy_version 41590 (0.0008) -[2023-10-10 14:18:29,404][76542] Updated weights for policy 1, policy_version 41600 (0.0008) -[2023-10-10 14:18:29,410][76543] Updated weights for policy 0, policy_version 41633 (0.0009) -[2023-10-10 14:18:29,788][76543] Updated weights for policy 0, policy_version 41643 (0.0007) -[2023-10-10 14:18:30,158][76543] Updated weights for policy 0, policy_version 41653 (0.0007) -[2023-10-10 14:18:30,525][76543] Updated weights for policy 0, policy_version 41663 (0.0009) -[2023-10-10 14:18:31,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 85262336. Throughput: 0: 1816.6, 1: 1822.4. Samples: 21322778. Policy #0 lag: (min: 8.0, avg: 35.6, max: 40.0) -[2023-10-10 14:18:31,076][75634] Avg episode reward: [(0, '35.000'), (1, '34.310')] -[2023-10-10 14:18:31,083][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000041664_42663936.pth... -[2023-10-10 14:18:31,083][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000041600_42598400.pth... -[2023-10-10 14:18:31,115][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000039904_40861696.pth -[2023-10-10 14:18:31,115][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000039968_40927232.pth -[2023-10-10 14:18:33,184][76542] Updated weights for policy 1, policy_version 41610 (0.0009) -[2023-10-10 14:18:33,564][76542] Updated weights for policy 1, policy_version 41620 (0.0007) -[2023-10-10 14:18:33,926][76542] Updated weights for policy 1, policy_version 41630 (0.0009) -[2023-10-10 14:18:34,084][76543] Updated weights for policy 0, policy_version 41673 (0.0007) -[2023-10-10 14:18:34,447][76543] Updated weights for policy 0, policy_version 41683 (0.0009) -[2023-10-10 14:18:34,820][76543] Updated weights for policy 0, policy_version 41693 (0.0010) -[2023-10-10 14:18:36,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 85327872. Throughput: 0: 1814.7, 1: 1825.1. Samples: 21334058. Policy #0 lag: (min: 8.0, avg: 35.6, max: 40.0) -[2023-10-10 14:18:36,076][75634] Avg episode reward: [(0, '34.880'), (1, '34.500')] -[2023-10-10 14:18:37,619][76542] Updated weights for policy 1, policy_version 41640 (0.0009) -[2023-10-10 14:18:37,977][76542] Updated weights for policy 1, policy_version 41650 (0.0008) -[2023-10-10 14:18:38,345][76542] Updated weights for policy 1, policy_version 41660 (0.0007) -[2023-10-10 14:18:38,525][76543] Updated weights for policy 0, policy_version 41703 (0.0007) -[2023-10-10 14:18:38,902][76543] Updated weights for policy 0, policy_version 41713 (0.0007) -[2023-10-10 14:18:39,274][76543] Updated weights for policy 0, policy_version 41723 (0.0008) -[2023-10-10 14:18:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 85393408. Throughput: 0: 1820.6, 1: 1823.6. Samples: 21355464. Policy #0 lag: (min: 8.0, avg: 35.6, max: 40.0) -[2023-10-10 14:18:41,076][75634] Avg episode reward: [(0, '36.590'), (1, '34.430')] -[2023-10-10 14:18:42,070][76542] Updated weights for policy 1, policy_version 41670 (0.0008) -[2023-10-10 14:18:42,447][76542] Updated weights for policy 1, policy_version 41680 (0.0008) -[2023-10-10 14:18:42,811][76542] Updated weights for policy 1, policy_version 41690 (0.0009) -[2023-10-10 14:18:42,837][76543] Updated weights for policy 0, policy_version 41733 (0.0009) -[2023-10-10 14:18:43,211][76543] Updated weights for policy 0, policy_version 41743 (0.0011) -[2023-10-10 14:18:43,571][76543] Updated weights for policy 0, policy_version 41753 (0.0009) -[2023-10-10 14:18:46,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 85458944. Throughput: 0: 1825.0, 1: 1821.4. Samples: 21378000. Policy #0 lag: (min: 25.0, avg: 42.7, max: 57.0) -[2023-10-10 14:18:46,077][75634] Avg episode reward: [(0, '32.590'), (1, '36.650')] -[2023-10-10 14:18:46,569][76542] Updated weights for policy 1, policy_version 41700 (0.0008) -[2023-10-10 14:18:46,947][76542] Updated weights for policy 1, policy_version 41710 (0.0007) -[2023-10-10 14:18:47,307][76542] Updated weights for policy 1, policy_version 41720 (0.0009) -[2023-10-10 14:18:47,421][76543] Updated weights for policy 0, policy_version 41763 (0.0007) -[2023-10-10 14:18:47,788][76543] Updated weights for policy 0, policy_version 41773 (0.0008) -[2023-10-10 14:18:48,148][76543] Updated weights for policy 0, policy_version 41783 (0.0010) -[2023-10-10 14:18:51,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 85524480. Throughput: 0: 1821.9, 1: 1815.7. Samples: 21387930. Policy #0 lag: (min: 25.0, avg: 42.7, max: 57.0) -[2023-10-10 14:18:51,076][75634] Avg episode reward: [(0, '35.950'), (1, '37.750')] -[2023-10-10 14:18:51,093][76542] Updated weights for policy 1, policy_version 41730 (0.0007) -[2023-10-10 14:18:51,463][76542] Updated weights for policy 1, policy_version 41740 (0.0009) -[2023-10-10 14:18:51,822][76543] Updated weights for policy 0, policy_version 41793 (0.0007) -[2023-10-10 14:18:51,839][76542] Updated weights for policy 1, policy_version 41750 (0.0008) -[2023-10-10 14:18:52,194][76543] Updated weights for policy 0, policy_version 41803 (0.0007) -[2023-10-10 14:18:52,204][76542] Updated weights for policy 1, policy_version 41760 (0.0007) -[2023-10-10 14:18:52,569][76543] Updated weights for policy 0, policy_version 41813 (0.0007) -[2023-10-10 14:18:52,943][76543] Updated weights for policy 0, policy_version 41823 (0.0008) -[2023-10-10 14:18:55,760][76542] Updated weights for policy 1, policy_version 41770 (0.0007) -[2023-10-10 14:18:56,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 85590016. Throughput: 0: 1823.4, 1: 1818.0. Samples: 21410374. Policy #0 lag: (min: 25.0, avg: 42.7, max: 57.0) -[2023-10-10 14:18:56,077][75634] Avg episode reward: [(0, '33.600'), (1, '34.270')] -[2023-10-10 14:18:56,133][76542] Updated weights for policy 1, policy_version 41780 (0.0007) -[2023-10-10 14:18:56,500][76542] Updated weights for policy 1, policy_version 41790 (0.0007) -[2023-10-10 14:18:56,600][76543] Updated weights for policy 0, policy_version 41833 (0.0007) -[2023-10-10 14:18:56,973][76543] Updated weights for policy 0, policy_version 41843 (0.0008) -[2023-10-10 14:18:57,349][76543] Updated weights for policy 0, policy_version 41853 (0.0007) -[2023-10-10 14:19:00,111][76542] Updated weights for policy 1, policy_version 41800 (0.0010) -[2023-10-10 14:19:00,488][76542] Updated weights for policy 1, policy_version 41810 (0.0009) -[2023-10-10 14:19:00,852][76542] Updated weights for policy 1, policy_version 41820 (0.0007) -[2023-10-10 14:19:00,990][76543] Updated weights for policy 0, policy_version 41863 (0.0008) -[2023-10-10 14:19:01,076][75634] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 85688320. Throughput: 0: 1819.6, 1: 1819.1. Samples: 21432102. Policy #0 lag: (min: 25.0, avg: 42.7, max: 57.0) -[2023-10-10 14:19:01,077][75634] Avg episode reward: [(0, '30.960'), (1, '31.520')] -[2023-10-10 14:19:01,357][76543] Updated weights for policy 0, policy_version 41873 (0.0011) -[2023-10-10 14:19:01,737][76543] Updated weights for policy 0, policy_version 41883 (0.0009) -[2023-10-10 14:19:04,568][76542] Updated weights for policy 1, policy_version 41830 (0.0008) -[2023-10-10 14:19:04,935][76542] Updated weights for policy 1, policy_version 41840 (0.0008) -[2023-10-10 14:19:05,305][76542] Updated weights for policy 1, policy_version 41850 (0.0007) -[2023-10-10 14:19:05,472][76543] Updated weights for policy 0, policy_version 41893 (0.0009) -[2023-10-10 14:19:05,865][76543] Updated weights for policy 0, policy_version 41903 (0.0010) -[2023-10-10 14:19:06,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 85753856. Throughput: 0: 1820.6, 1: 1817.2. Samples: 21443046. Policy #0 lag: (min: 25.0, avg: 42.7, max: 57.0) -[2023-10-10 14:19:06,076][75634] Avg episode reward: [(0, '37.380'), (1, '28.500')] -[2023-10-10 14:19:06,240][76543] Updated weights for policy 0, policy_version 41913 (0.0008) -[2023-10-10 14:19:09,144][76542] Updated weights for policy 1, policy_version 41860 (0.0008) -[2023-10-10 14:19:09,506][76542] Updated weights for policy 1, policy_version 41870 (0.0010) -[2023-10-10 14:19:09,764][76543] Updated weights for policy 0, policy_version 41923 (0.0008) -[2023-10-10 14:19:09,887][76542] Updated weights for policy 1, policy_version 41880 (0.0008) -[2023-10-10 14:19:10,143][76543] Updated weights for policy 0, policy_version 41933 (0.0007) -[2023-10-10 14:19:10,504][76543] Updated weights for policy 0, policy_version 41943 (0.0008) -[2023-10-10 14:19:11,076][75634] Fps is (10 sec: 16384.1, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 85852160. Throughput: 0: 1827.4, 1: 1810.8. Samples: 21464712. Policy #0 lag: (min: 25.0, avg: 42.7, max: 57.0) -[2023-10-10 14:19:11,077][75634] Avg episode reward: [(0, '38.800'), (1, '28.020')] -[2023-10-10 14:19:13,535][76542] Updated weights for policy 1, policy_version 41890 (0.0008) -[2023-10-10 14:19:13,906][76542] Updated weights for policy 1, policy_version 41900 (0.0007) -[2023-10-10 14:19:14,280][76542] Updated weights for policy 1, policy_version 41910 (0.0008) -[2023-10-10 14:19:14,358][76543] Updated weights for policy 0, policy_version 41953 (0.0011) -[2023-10-10 14:19:14,644][76542] Updated weights for policy 1, policy_version 41920 (0.0011) -[2023-10-10 14:19:14,732][76543] Updated weights for policy 0, policy_version 41963 (0.0008) -[2023-10-10 14:19:15,099][76543] Updated weights for policy 0, policy_version 41973 (0.0010) -[2023-10-10 14:19:15,462][76543] Updated weights for policy 0, policy_version 41983 (0.0011) -[2023-10-10 14:19:16,076][75634] Fps is (10 sec: 16383.7, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 85917696. Throughput: 0: 1815.5, 1: 1802.5. Samples: 21485590. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 14:19:16,077][75634] Avg episode reward: [(0, '38.770'), (1, '31.520')] -[2023-10-10 14:19:18,389][76542] Updated weights for policy 1, policy_version 41930 (0.0009) -[2023-10-10 14:19:18,765][76542] Updated weights for policy 1, policy_version 41940 (0.0009) -[2023-10-10 14:19:19,133][76542] Updated weights for policy 1, policy_version 41950 (0.0009) -[2023-10-10 14:19:19,222][76543] Updated weights for policy 0, policy_version 41993 (0.0009) -[2023-10-10 14:19:19,596][76543] Updated weights for policy 0, policy_version 42003 (0.0010) -[2023-10-10 14:19:19,958][76543] Updated weights for policy 0, policy_version 42013 (0.0010) -[2023-10-10 14:19:21,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 85983232. Throughput: 0: 1807.3, 1: 1813.5. Samples: 21496994. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 14:19:21,077][75634] Avg episode reward: [(0, '38.010'), (1, '32.970')] -[2023-10-10 14:19:22,763][76542] Updated weights for policy 1, policy_version 41960 (0.0010) -[2023-10-10 14:19:23,134][76542] Updated weights for policy 1, policy_version 41970 (0.0010) -[2023-10-10 14:19:23,502][76542] Updated weights for policy 1, policy_version 41980 (0.0009) -[2023-10-10 14:19:23,502][76543] Updated weights for policy 0, policy_version 42023 (0.0008) -[2023-10-10 14:19:23,877][76543] Updated weights for policy 0, policy_version 42033 (0.0007) -[2023-10-10 14:19:24,246][76543] Updated weights for policy 0, policy_version 42043 (0.0007) -[2023-10-10 14:19:26,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 86048768. Throughput: 0: 1806.0, 1: 1807.4. Samples: 21518068. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 14:19:26,077][75634] Avg episode reward: [(0, '35.190'), (1, '35.060')] -[2023-10-10 14:19:27,204][76542] Updated weights for policy 1, policy_version 41990 (0.0007) -[2023-10-10 14:19:27,582][76542] Updated weights for policy 1, policy_version 42000 (0.0008) -[2023-10-10 14:19:27,950][76542] Updated weights for policy 1, policy_version 42010 (0.0009) -[2023-10-10 14:19:28,014][76543] Updated weights for policy 0, policy_version 42053 (0.0008) -[2023-10-10 14:19:28,384][76543] Updated weights for policy 0, policy_version 42063 (0.0009) -[2023-10-10 14:19:28,750][76543] Updated weights for policy 0, policy_version 42073 (0.0007) -[2023-10-10 14:19:31,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 86114304. Throughput: 0: 1804.2, 1: 1804.8. Samples: 21540404. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 14:19:31,076][75634] Avg episode reward: [(0, '34.880'), (1, '37.450')] -[2023-10-10 14:19:31,727][76542] Updated weights for policy 1, policy_version 42020 (0.0009) -[2023-10-10 14:19:32,099][76542] Updated weights for policy 1, policy_version 42030 (0.0009) -[2023-10-10 14:19:32,477][76542] Updated weights for policy 1, policy_version 42040 (0.0009) -[2023-10-10 14:19:32,502][76543] Updated weights for policy 0, policy_version 42083 (0.0007) -[2023-10-10 14:19:32,878][76543] Updated weights for policy 0, policy_version 42093 (0.0009) -[2023-10-10 14:19:33,256][76543] Updated weights for policy 0, policy_version 42103 (0.0009) -[2023-10-10 14:19:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 86179840. Throughput: 0: 1812.1, 1: 1804.8. Samples: 21550692. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 14:19:36,076][75634] Avg episode reward: [(0, '30.940'), (1, '36.100')] -[2023-10-10 14:19:36,224][76542] Updated weights for policy 1, policy_version 42050 (0.0008) -[2023-10-10 14:19:36,599][76542] Updated weights for policy 1, policy_version 42060 (0.0010) -[2023-10-10 14:19:36,960][76542] Updated weights for policy 1, policy_version 42070 (0.0011) -[2023-10-10 14:19:37,107][76543] Updated weights for policy 0, policy_version 42113 (0.0008) -[2023-10-10 14:19:37,326][76542] Updated weights for policy 1, policy_version 42080 (0.0008) -[2023-10-10 14:19:37,475][76543] Updated weights for policy 0, policy_version 42123 (0.0010) -[2023-10-10 14:19:37,841][76543] Updated weights for policy 0, policy_version 42133 (0.0009) -[2023-10-10 14:19:38,221][76543] Updated weights for policy 0, policy_version 42143 (0.0008) -[2023-10-10 14:19:41,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 86245376. Throughput: 0: 1807.8, 1: 1803.9. Samples: 21572900. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 14:19:41,076][75634] Avg episode reward: [(0, '33.740'), (1, '35.390')] -[2023-10-10 14:19:41,082][76542] Updated weights for policy 1, policy_version 42090 (0.0009) -[2023-10-10 14:19:41,446][76542] Updated weights for policy 1, policy_version 42100 (0.0009) -[2023-10-10 14:19:41,810][76542] Updated weights for policy 1, policy_version 42110 (0.0007) -[2023-10-10 14:19:41,884][76543] Updated weights for policy 0, policy_version 42153 (0.0008) -[2023-10-10 14:19:42,264][76543] Updated weights for policy 0, policy_version 42163 (0.0010) -[2023-10-10 14:19:42,630][76543] Updated weights for policy 0, policy_version 42173 (0.0008) -[2023-10-10 14:19:45,482][76542] Updated weights for policy 1, policy_version 42120 (0.0007) -[2023-10-10 14:19:45,863][76542] Updated weights for policy 1, policy_version 42130 (0.0007) -[2023-10-10 14:19:46,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 86310912. Throughput: 0: 1809.2, 1: 1813.9. Samples: 21595142. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 14:19:46,077][75634] Avg episode reward: [(0, '32.000'), (1, '28.860')] -[2023-10-10 14:19:46,229][76542] Updated weights for policy 1, policy_version 42140 (0.0008) -[2023-10-10 14:19:46,248][76543] Updated weights for policy 0, policy_version 42183 (0.0007) -[2023-10-10 14:19:46,621][76543] Updated weights for policy 0, policy_version 42193 (0.0008) -[2023-10-10 14:19:46,992][76543] Updated weights for policy 0, policy_version 42203 (0.0010) -[2023-10-10 14:19:49,869][76542] Updated weights for policy 1, policy_version 42150 (0.0008) -[2023-10-10 14:19:50,243][76542] Updated weights for policy 1, policy_version 42160 (0.0008) -[2023-10-10 14:19:50,610][76542] Updated weights for policy 1, policy_version 42170 (0.0007) -[2023-10-10 14:19:50,877][76543] Updated weights for policy 0, policy_version 42213 (0.0010) -[2023-10-10 14:19:51,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 86409216. Throughput: 0: 1806.9, 1: 1806.8. Samples: 21605664. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:19:51,077][75634] Avg episode reward: [(0, '35.020'), (1, '32.580')] -[2023-10-10 14:19:51,247][76543] Updated weights for policy 0, policy_version 42223 (0.0008) -[2023-10-10 14:19:51,629][76543] Updated weights for policy 0, policy_version 42233 (0.0009) -[2023-10-10 14:19:54,198][76542] Updated weights for policy 1, policy_version 42180 (0.0008) -[2023-10-10 14:19:54,570][76542] Updated weights for policy 1, policy_version 42190 (0.0010) -[2023-10-10 14:19:54,942][76542] Updated weights for policy 1, policy_version 42200 (0.0009) -[2023-10-10 14:19:55,282][76543] Updated weights for policy 0, policy_version 42243 (0.0009) -[2023-10-10 14:19:55,665][76543] Updated weights for policy 0, policy_version 42253 (0.0010) -[2023-10-10 14:19:56,037][76543] Updated weights for policy 0, policy_version 42263 (0.0007) -[2023-10-10 14:19:56,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 86474752. Throughput: 0: 1803.6, 1: 1821.0. Samples: 21627818. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:19:56,077][75634] Avg episode reward: [(0, '37.290'), (1, '31.490')] -[2023-10-10 14:19:58,515][76542] Updated weights for policy 1, policy_version 42210 (0.0009) -[2023-10-10 14:19:58,880][76542] Updated weights for policy 1, policy_version 42220 (0.0008) -[2023-10-10 14:19:59,248][76542] Updated weights for policy 1, policy_version 42230 (0.0009) -[2023-10-10 14:19:59,606][76542] Updated weights for policy 1, policy_version 42240 (0.0008) -[2023-10-10 14:19:59,686][76543] Updated weights for policy 0, policy_version 42273 (0.0010) -[2023-10-10 14:20:00,061][76543] Updated weights for policy 0, policy_version 42283 (0.0010) -[2023-10-10 14:20:00,435][76543] Updated weights for policy 0, policy_version 42293 (0.0009) -[2023-10-10 14:20:00,803][76543] Updated weights for policy 0, policy_version 42303 (0.0007) -[2023-10-10 14:20:01,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 86573056. Throughput: 0: 1817.0, 1: 1817.5. Samples: 21649142. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:20:01,076][75634] Avg episode reward: [(0, '33.830'), (1, '33.050')] -[2023-10-10 14:20:03,341][76542] Updated weights for policy 1, policy_version 42250 (0.0008) -[2023-10-10 14:20:03,714][76542] Updated weights for policy 1, policy_version 42260 (0.0007) -[2023-10-10 14:20:04,077][76542] Updated weights for policy 1, policy_version 42270 (0.0007) -[2023-10-10 14:20:04,570][76543] Updated weights for policy 0, policy_version 42313 (0.0010) -[2023-10-10 14:20:04,935][76543] Updated weights for policy 0, policy_version 42323 (0.0008) -[2023-10-10 14:20:05,311][76543] Updated weights for policy 0, policy_version 42333 (0.0008) -[2023-10-10 14:20:06,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 86638592. Throughput: 0: 1817.6, 1: 1821.5. Samples: 21660752. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:20:06,077][75634] Avg episode reward: [(0, '34.310'), (1, '32.630')] -[2023-10-10 14:20:07,780][76542] Updated weights for policy 1, policy_version 42280 (0.0009) -[2023-10-10 14:20:08,149][76542] Updated weights for policy 1, policy_version 42290 (0.0011) -[2023-10-10 14:20:08,504][76542] Updated weights for policy 1, policy_version 42300 (0.0012) -[2023-10-10 14:20:08,853][76543] Updated weights for policy 0, policy_version 42343 (0.0010) -[2023-10-10 14:20:09,218][76543] Updated weights for policy 0, policy_version 42353 (0.0007) -[2023-10-10 14:20:09,603][76543] Updated weights for policy 0, policy_version 42363 (0.0008) -[2023-10-10 14:20:11,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 86704128. Throughput: 0: 1828.3, 1: 1821.2. Samples: 21682292. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:20:11,076][75634] Avg episode reward: [(0, '33.150'), (1, '33.940')] -[2023-10-10 14:20:12,241][76542] Updated weights for policy 1, policy_version 42310 (0.0008) -[2023-10-10 14:20:12,599][76542] Updated weights for policy 1, policy_version 42320 (0.0008) -[2023-10-10 14:20:12,975][76542] Updated weights for policy 1, policy_version 42330 (0.0010) -[2023-10-10 14:20:13,265][76543] Updated weights for policy 0, policy_version 42373 (0.0008) -[2023-10-10 14:20:13,643][76543] Updated weights for policy 0, policy_version 42383 (0.0007) -[2023-10-10 14:20:14,007][76543] Updated weights for policy 0, policy_version 42393 (0.0007) -[2023-10-10 14:20:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 86769664. Throughput: 0: 1821.4, 1: 1822.9. Samples: 21704396. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:20:16,076][75634] Avg episode reward: [(0, '33.250'), (1, '37.180')] -[2023-10-10 14:20:16,725][76542] Updated weights for policy 1, policy_version 42340 (0.0010) -[2023-10-10 14:20:17,092][76542] Updated weights for policy 1, policy_version 42350 (0.0008) -[2023-10-10 14:20:17,455][76542] Updated weights for policy 1, policy_version 42360 (0.0008) -[2023-10-10 14:20:17,610][76543] Updated weights for policy 0, policy_version 42403 (0.0009) -[2023-10-10 14:20:17,978][76543] Updated weights for policy 0, policy_version 42413 (0.0010) -[2023-10-10 14:20:18,352][76543] Updated weights for policy 0, policy_version 42423 (0.0008) -[2023-10-10 14:20:21,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 86835200. Throughput: 0: 1825.6, 1: 1826.8. Samples: 21715046. Policy #0 lag: (min: 35.0, avg: 53.6, max: 56.0) -[2023-10-10 14:20:21,076][75634] Avg episode reward: [(0, '33.970'), (1, '33.370')] -[2023-10-10 14:20:21,116][76542] Updated weights for policy 1, policy_version 42370 (0.0009) -[2023-10-10 14:20:21,486][76542] Updated weights for policy 1, policy_version 42380 (0.0008) -[2023-10-10 14:20:21,850][76542] Updated weights for policy 1, policy_version 42390 (0.0008) -[2023-10-10 14:20:22,017][76543] Updated weights for policy 0, policy_version 42433 (0.0007) -[2023-10-10 14:20:22,224][76542] Updated weights for policy 1, policy_version 42400 (0.0009) -[2023-10-10 14:20:22,383][76543] Updated weights for policy 0, policy_version 42443 (0.0010) -[2023-10-10 14:20:22,754][76543] Updated weights for policy 0, policy_version 42453 (0.0010) -[2023-10-10 14:20:23,118][76543] Updated weights for policy 0, policy_version 42463 (0.0007) -[2023-10-10 14:20:25,653][76542] Updated weights for policy 1, policy_version 42410 (0.0010) -[2023-10-10 14:20:26,028][76542] Updated weights for policy 1, policy_version 42420 (0.0008) -[2023-10-10 14:20:26,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 86900736. Throughput: 0: 1818.7, 1: 1834.6. Samples: 21737300. Policy #0 lag: (min: 35.0, avg: 53.6, max: 56.0) -[2023-10-10 14:20:26,077][75634] Avg episode reward: [(0, '37.200'), (1, '31.920')] -[2023-10-10 14:20:26,397][76542] Updated weights for policy 1, policy_version 42430 (0.0009) -[2023-10-10 14:20:27,021][76543] Updated weights for policy 0, policy_version 42473 (0.0008) -[2023-10-10 14:20:27,395][76543] Updated weights for policy 0, policy_version 42483 (0.0009) -[2023-10-10 14:20:27,776][76543] Updated weights for policy 0, policy_version 42493 (0.0009) -[2023-10-10 14:20:30,206][76542] Updated weights for policy 1, policy_version 42440 (0.0009) -[2023-10-10 14:20:30,565][76542] Updated weights for policy 1, policy_version 42450 (0.0007) -[2023-10-10 14:20:30,933][76542] Updated weights for policy 1, policy_version 42460 (0.0009) -[2023-10-10 14:20:31,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 86999040. Throughput: 0: 1813.4, 1: 1824.9. Samples: 21758866. Policy #0 lag: (min: 35.0, avg: 53.6, max: 56.0) -[2023-10-10 14:20:31,077][75634] Avg episode reward: [(0, '40.070'), (1, '31.710')] -[2023-10-10 14:20:31,085][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000042464_43483136.pth... -[2023-10-10 14:20:31,085][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000042496_43515904.pth... -[2023-10-10 14:20:31,118][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000040800_41779200.pth -[2023-10-10 14:20:31,122][76362] Saving a milestone ./train_atari/atari_defender_APPO/checkpoint_p0/milestones/checkpoint_000042496_43515904.pth -[2023-10-10 14:20:31,124][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000040768_41746432.pth -[2023-10-10 14:20:31,130][76421] Saving a milestone ./train_atari/atari_defender_APPO/checkpoint_p1/milestones/checkpoint_000042464_43483136.pth -[2023-10-10 14:20:31,560][76543] Updated weights for policy 0, policy_version 42503 (0.0008) -[2023-10-10 14:20:31,931][76543] Updated weights for policy 0, policy_version 42513 (0.0009) -[2023-10-10 14:20:32,308][76543] Updated weights for policy 0, policy_version 42523 (0.0008) -[2023-10-10 14:20:34,691][76542] Updated weights for policy 1, policy_version 42470 (0.0010) -[2023-10-10 14:20:35,063][76542] Updated weights for policy 1, policy_version 42480 (0.0008) -[2023-10-10 14:20:35,427][76542] Updated weights for policy 1, policy_version 42490 (0.0009) -[2023-10-10 14:20:36,017][76543] Updated weights for policy 0, policy_version 42533 (0.0008) -[2023-10-10 14:20:36,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 87064576. Throughput: 0: 1816.0, 1: 1831.0. Samples: 21769778. Policy #0 lag: (min: 35.0, avg: 53.6, max: 56.0) -[2023-10-10 14:20:36,077][75634] Avg episode reward: [(0, '40.080'), (1, '36.100')] -[2023-10-10 14:20:36,389][76543] Updated weights for policy 0, policy_version 42543 (0.0007) -[2023-10-10 14:20:36,761][76543] Updated weights for policy 0, policy_version 42553 (0.0008) -[2023-10-10 14:20:38,999][76542] Updated weights for policy 1, policy_version 42500 (0.0008) -[2023-10-10 14:20:39,362][76542] Updated weights for policy 1, policy_version 42510 (0.0008) -[2023-10-10 14:20:39,739][76542] Updated weights for policy 1, policy_version 42520 (0.0009) -[2023-10-10 14:20:40,331][76543] Updated weights for policy 0, policy_version 42563 (0.0008) -[2023-10-10 14:20:40,707][76543] Updated weights for policy 0, policy_version 42573 (0.0010) -[2023-10-10 14:20:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 87130112. Throughput: 0: 1818.0, 1: 1820.6. Samples: 21791556. Policy #0 lag: (min: 35.0, avg: 53.6, max: 56.0) -[2023-10-10 14:20:41,077][75634] Avg episode reward: [(0, '40.060'), (1, '35.130')] -[2023-10-10 14:20:41,077][76543] Updated weights for policy 0, policy_version 42583 (0.0008) -[2023-10-10 14:20:43,377][76542] Updated weights for policy 1, policy_version 42530 (0.0009) -[2023-10-10 14:20:43,750][76542] Updated weights for policy 1, policy_version 42540 (0.0008) -[2023-10-10 14:20:44,115][76542] Updated weights for policy 1, policy_version 42550 (0.0009) -[2023-10-10 14:20:44,482][76542] Updated weights for policy 1, policy_version 42560 (0.0009) -[2023-10-10 14:20:44,608][76543] Updated weights for policy 0, policy_version 42593 (0.0008) -[2023-10-10 14:20:44,987][76543] Updated weights for policy 0, policy_version 42603 (0.0010) -[2023-10-10 14:20:45,368][76543] Updated weights for policy 0, policy_version 42613 (0.0009) -[2023-10-10 14:20:45,749][76543] Updated weights for policy 0, policy_version 42623 (0.0010) -[2023-10-10 14:20:46,076][75634] Fps is (10 sec: 16384.1, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 87228416. Throughput: 0: 1819.8, 1: 1831.6. Samples: 21813458. Policy #0 lag: (min: 35.0, avg: 53.6, max: 56.0) -[2023-10-10 14:20:46,077][75634] Avg episode reward: [(0, '41.560'), (1, '34.600')] -[2023-10-10 14:20:48,283][76542] Updated weights for policy 1, policy_version 42570 (0.0009) -[2023-10-10 14:20:48,650][76542] Updated weights for policy 1, policy_version 42580 (0.0008) -[2023-10-10 14:20:49,028][76542] Updated weights for policy 1, policy_version 42590 (0.0009) -[2023-10-10 14:20:49,472][76543] Updated weights for policy 0, policy_version 42633 (0.0010) -[2023-10-10 14:20:49,839][76543] Updated weights for policy 0, policy_version 42643 (0.0011) -[2023-10-10 14:20:50,203][76543] Updated weights for policy 0, policy_version 42653 (0.0008) -[2023-10-10 14:20:51,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 87293952. Throughput: 0: 1814.1, 1: 1821.7. Samples: 21824364. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-10-10 14:20:51,076][75634] Avg episode reward: [(0, '38.210'), (1, '32.550')] -[2023-10-10 14:20:52,423][76542] Updated weights for policy 1, policy_version 42600 (0.0009) -[2023-10-10 14:20:52,796][76542] Updated weights for policy 1, policy_version 42610 (0.0010) -[2023-10-10 14:20:53,170][76542] Updated weights for policy 1, policy_version 42620 (0.0009) -[2023-10-10 14:20:53,942][76543] Updated weights for policy 0, policy_version 42663 (0.0008) -[2023-10-10 14:20:54,306][76543] Updated weights for policy 0, policy_version 42673 (0.0008) -[2023-10-10 14:20:54,682][76543] Updated weights for policy 0, policy_version 42683 (0.0009) -[2023-10-10 14:20:56,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 87359488. Throughput: 0: 1813.8, 1: 1832.8. Samples: 21846388. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-10-10 14:20:56,077][75634] Avg episode reward: [(0, '32.700'), (1, '33.870')] -[2023-10-10 14:20:56,770][76542] Updated weights for policy 1, policy_version 42630 (0.0008) -[2023-10-10 14:20:57,137][76542] Updated weights for policy 1, policy_version 42640 (0.0010) -[2023-10-10 14:20:57,522][76542] Updated weights for policy 1, policy_version 42650 (0.0010) -[2023-10-10 14:20:58,460][76543] Updated weights for policy 0, policy_version 42693 (0.0009) -[2023-10-10 14:20:58,839][76543] Updated weights for policy 0, policy_version 42703 (0.0008) -[2023-10-10 14:20:59,215][76543] Updated weights for policy 0, policy_version 42713 (0.0009) -[2023-10-10 14:21:01,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 87425024. Throughput: 0: 1810.6, 1: 1831.1. Samples: 21868272. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-10-10 14:21:01,076][75634] Avg episode reward: [(0, '29.380'), (1, '36.250')] -[2023-10-10 14:21:01,219][76542] Updated weights for policy 1, policy_version 42660 (0.0010) -[2023-10-10 14:21:01,585][76542] Updated weights for policy 1, policy_version 42670 (0.0008) -[2023-10-10 14:21:01,952][76542] Updated weights for policy 1, policy_version 42680 (0.0007) -[2023-10-10 14:21:02,758][76543] Updated weights for policy 0, policy_version 42723 (0.0008) -[2023-10-10 14:21:03,134][76543] Updated weights for policy 0, policy_version 42733 (0.0010) -[2023-10-10 14:21:03,506][76543] Updated weights for policy 0, policy_version 42743 (0.0007) -[2023-10-10 14:21:05,644][76542] Updated weights for policy 1, policy_version 42690 (0.0007) -[2023-10-10 14:21:06,012][76542] Updated weights for policy 1, policy_version 42700 (0.0007) -[2023-10-10 14:21:06,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 87490560. Throughput: 0: 1815.2, 1: 1832.6. Samples: 21879198. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-10-10 14:21:06,076][75634] Avg episode reward: [(0, '33.740'), (1, '31.870')] -[2023-10-10 14:21:06,368][76542] Updated weights for policy 1, policy_version 42710 (0.0010) -[2023-10-10 14:21:06,736][76542] Updated weights for policy 1, policy_version 42720 (0.0007) -[2023-10-10 14:21:07,068][76543] Updated weights for policy 0, policy_version 42753 (0.0007) -[2023-10-10 14:21:07,448][76543] Updated weights for policy 0, policy_version 42763 (0.0008) -[2023-10-10 14:21:07,819][76543] Updated weights for policy 0, policy_version 42773 (0.0009) -[2023-10-10 14:21:08,191][76543] Updated weights for policy 0, policy_version 42783 (0.0008) -[2023-10-10 14:21:10,607][76542] Updated weights for policy 1, policy_version 42730 (0.0008) -[2023-10-10 14:21:10,976][76542] Updated weights for policy 1, policy_version 42740 (0.0007) -[2023-10-10 14:21:11,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 87556096. Throughput: 0: 1817.3, 1: 1823.2. Samples: 21901122. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-10-10 14:21:11,076][75634] Avg episode reward: [(0, '35.430'), (1, '32.240')] -[2023-10-10 14:21:11,343][76542] Updated weights for policy 1, policy_version 42750 (0.0007) -[2023-10-10 14:21:11,711][76543] Updated weights for policy 0, policy_version 42793 (0.0009) -[2023-10-10 14:21:12,091][76543] Updated weights for policy 0, policy_version 42803 (0.0007) -[2023-10-10 14:21:12,473][76543] Updated weights for policy 0, policy_version 42813 (0.0007) -[2023-10-10 14:21:15,026][76542] Updated weights for policy 1, policy_version 42760 (0.0008) -[2023-10-10 14:21:15,386][76542] Updated weights for policy 1, policy_version 42770 (0.0008) -[2023-10-10 14:21:15,755][76542] Updated weights for policy 1, policy_version 42780 (0.0009) -[2023-10-10 14:21:16,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 87654400. Throughput: 0: 1830.0, 1: 1822.6. Samples: 21923234. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-10-10 14:21:16,076][75634] Avg episode reward: [(0, '35.820'), (1, '37.020')] -[2023-10-10 14:21:16,113][76543] Updated weights for policy 0, policy_version 42823 (0.0007) -[2023-10-10 14:21:16,496][76543] Updated weights for policy 0, policy_version 42833 (0.0008) -[2023-10-10 14:21:16,868][76543] Updated weights for policy 0, policy_version 42843 (0.0009) -[2023-10-10 14:21:19,440][76542] Updated weights for policy 1, policy_version 42790 (0.0008) -[2023-10-10 14:21:19,807][76542] Updated weights for policy 1, policy_version 42800 (0.0009) -[2023-10-10 14:21:20,178][76542] Updated weights for policy 1, policy_version 42810 (0.0008) -[2023-10-10 14:21:20,644][76543] Updated weights for policy 0, policy_version 42853 (0.0008) -[2023-10-10 14:21:21,023][76543] Updated weights for policy 0, policy_version 42863 (0.0009) -[2023-10-10 14:21:21,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 87719936. Throughput: 0: 1827.8, 1: 1826.0. Samples: 21934200. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-10-10 14:21:21,077][75634] Avg episode reward: [(0, '36.110'), (1, '37.930')] -[2023-10-10 14:21:21,406][76543] Updated weights for policy 0, policy_version 42873 (0.0009) -[2023-10-10 14:21:23,944][76542] Updated weights for policy 1, policy_version 42820 (0.0007) -[2023-10-10 14:21:24,315][76542] Updated weights for policy 1, policy_version 42830 (0.0009) -[2023-10-10 14:21:24,676][76542] Updated weights for policy 1, policy_version 42840 (0.0010) -[2023-10-10 14:21:24,913][76543] Updated weights for policy 0, policy_version 42883 (0.0008) -[2023-10-10 14:21:25,282][76543] Updated weights for policy 0, policy_version 42893 (0.0009) -[2023-10-10 14:21:25,664][76543] Updated weights for policy 0, policy_version 42903 (0.0011) -[2023-10-10 14:21:26,076][75634] Fps is (10 sec: 16383.7, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 87818240. Throughput: 0: 1831.1, 1: 1823.0. Samples: 21955990. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:21:26,077][75634] Avg episode reward: [(0, '36.020'), (1, '33.340')] -[2023-10-10 14:21:28,615][76542] Updated weights for policy 1, policy_version 42850 (0.0009) -[2023-10-10 14:21:28,979][76542] Updated weights for policy 1, policy_version 42860 (0.0011) -[2023-10-10 14:21:29,289][76543] Updated weights for policy 0, policy_version 42913 (0.0010) -[2023-10-10 14:21:29,350][76542] Updated weights for policy 1, policy_version 42870 (0.0010) -[2023-10-10 14:21:29,658][76543] Updated weights for policy 0, policy_version 42923 (0.0009) -[2023-10-10 14:21:29,718][76542] Updated weights for policy 1, policy_version 42880 (0.0008) -[2023-10-10 14:21:30,022][76543] Updated weights for policy 0, policy_version 42933 (0.0007) -[2023-10-10 14:21:30,396][76543] Updated weights for policy 0, policy_version 42943 (0.0009) -[2023-10-10 14:21:31,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 87883776. Throughput: 0: 1817.7, 1: 1818.9. Samples: 21977108. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:21:31,077][75634] Avg episode reward: [(0, '34.520'), (1, '34.740')] -[2023-10-10 14:21:33,474][76542] Updated weights for policy 1, policy_version 42890 (0.0009) -[2023-10-10 14:21:33,848][76542] Updated weights for policy 1, policy_version 42900 (0.0009) -[2023-10-10 14:21:34,215][76542] Updated weights for policy 1, policy_version 42910 (0.0008) -[2023-10-10 14:21:34,265][76543] Updated weights for policy 0, policy_version 42953 (0.0008) -[2023-10-10 14:21:34,636][76543] Updated weights for policy 0, policy_version 42963 (0.0009) -[2023-10-10 14:21:35,013][76543] Updated weights for policy 0, policy_version 42973 (0.0008) -[2023-10-10 14:21:36,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 87949312. Throughput: 0: 1827.5, 1: 1826.0. Samples: 21988770. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:21:36,076][75634] Avg episode reward: [(0, '30.360'), (1, '33.520')] -[2023-10-10 14:21:37,804][76542] Updated weights for policy 1, policy_version 42920 (0.0007) -[2023-10-10 14:21:38,172][76542] Updated weights for policy 1, policy_version 42930 (0.0010) -[2023-10-10 14:21:38,557][76542] Updated weights for policy 1, policy_version 42940 (0.0010) -[2023-10-10 14:21:38,792][76543] Updated weights for policy 0, policy_version 42983 (0.0008) -[2023-10-10 14:21:39,161][76543] Updated weights for policy 0, policy_version 42993 (0.0008) -[2023-10-10 14:21:39,531][76543] Updated weights for policy 0, policy_version 43003 (0.0008) -[2023-10-10 14:21:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 88014848. Throughput: 0: 1821.0, 1: 1814.2. Samples: 22009972. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:21:41,077][75634] Avg episode reward: [(0, '30.510'), (1, '31.230')] -[2023-10-10 14:21:42,177][76542] Updated weights for policy 1, policy_version 42950 (0.0007) -[2023-10-10 14:21:42,546][76542] Updated weights for policy 1, policy_version 42960 (0.0008) -[2023-10-10 14:21:42,917][76542] Updated weights for policy 1, policy_version 42970 (0.0009) -[2023-10-10 14:21:43,121][76543] Updated weights for policy 0, policy_version 43013 (0.0009) -[2023-10-10 14:21:43,486][76543] Updated weights for policy 0, policy_version 43023 (0.0008) -[2023-10-10 14:21:43,858][76543] Updated weights for policy 0, policy_version 43033 (0.0008) -[2023-10-10 14:21:46,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 88080384. Throughput: 0: 1831.9, 1: 1816.0. Samples: 22032430. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:21:46,077][75634] Avg episode reward: [(0, '32.150'), (1, '32.230')] -[2023-10-10 14:21:46,558][76542] Updated weights for policy 1, policy_version 42980 (0.0008) -[2023-10-10 14:21:46,927][76542] Updated weights for policy 1, policy_version 42990 (0.0008) -[2023-10-10 14:21:47,307][76542] Updated weights for policy 1, policy_version 43000 (0.0009) -[2023-10-10 14:21:47,616][76543] Updated weights for policy 0, policy_version 43043 (0.0007) -[2023-10-10 14:21:47,996][76543] Updated weights for policy 0, policy_version 43053 (0.0009) -[2023-10-10 14:21:48,362][76543] Updated weights for policy 0, policy_version 43063 (0.0010) -[2023-10-10 14:21:50,836][76542] Updated weights for policy 1, policy_version 43010 (0.0008) -[2023-10-10 14:21:51,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 88145920. Throughput: 0: 1826.3, 1: 1814.5. Samples: 22043036. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:21:51,076][75634] Avg episode reward: [(0, '35.670'), (1, '30.820')] -[2023-10-10 14:21:51,192][76542] Updated weights for policy 1, policy_version 43020 (0.0009) -[2023-10-10 14:21:51,561][76542] Updated weights for policy 1, policy_version 43030 (0.0007) -[2023-10-10 14:21:51,924][76542] Updated weights for policy 1, policy_version 43040 (0.0008) -[2023-10-10 14:21:51,991][76543] Updated weights for policy 0, policy_version 43073 (0.0007) -[2023-10-10 14:21:52,365][76543] Updated weights for policy 0, policy_version 43083 (0.0011) -[2023-10-10 14:21:52,741][76543] Updated weights for policy 0, policy_version 43093 (0.0008) -[2023-10-10 14:21:53,113][76543] Updated weights for policy 0, policy_version 43103 (0.0008) -[2023-10-10 14:21:55,545][76542] Updated weights for policy 1, policy_version 43050 (0.0007) -[2023-10-10 14:21:55,921][76542] Updated weights for policy 1, policy_version 43060 (0.0008) -[2023-10-10 14:21:56,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 88211456. Throughput: 0: 1829.4, 1: 1825.1. Samples: 22065572. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-10-10 14:21:56,077][75634] Avg episode reward: [(0, '36.020'), (1, '34.440')] -[2023-10-10 14:21:56,286][76542] Updated weights for policy 1, policy_version 43070 (0.0009) -[2023-10-10 14:21:56,771][76543] Updated weights for policy 0, policy_version 43113 (0.0008) -[2023-10-10 14:21:57,137][76543] Updated weights for policy 0, policy_version 43123 (0.0008) -[2023-10-10 14:21:57,512][76543] Updated weights for policy 0, policy_version 43133 (0.0009) -[2023-10-10 14:22:00,024][76542] Updated weights for policy 1, policy_version 43080 (0.0008) -[2023-10-10 14:22:00,398][76542] Updated weights for policy 1, policy_version 43090 (0.0007) -[2023-10-10 14:22:00,761][76542] Updated weights for policy 1, policy_version 43100 (0.0009) -[2023-10-10 14:22:01,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 88309760. Throughput: 0: 1824.0, 1: 1819.5. Samples: 22087192. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-10-10 14:22:01,076][75634] Avg episode reward: [(0, '35.190'), (1, '37.280')] -[2023-10-10 14:22:01,184][76543] Updated weights for policy 0, policy_version 43143 (0.0010) -[2023-10-10 14:22:01,559][76543] Updated weights for policy 0, policy_version 43153 (0.0011) -[2023-10-10 14:22:01,938][76543] Updated weights for policy 0, policy_version 43163 (0.0011) -[2023-10-10 14:22:04,533][76542] Updated weights for policy 1, policy_version 43110 (0.0010) -[2023-10-10 14:22:04,908][76542] Updated weights for policy 1, policy_version 43120 (0.0009) -[2023-10-10 14:22:05,266][76542] Updated weights for policy 1, policy_version 43130 (0.0009) -[2023-10-10 14:22:05,708][76543] Updated weights for policy 0, policy_version 43173 (0.0009) -[2023-10-10 14:22:06,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 88375296. Throughput: 0: 1825.4, 1: 1818.0. Samples: 22098152. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-10-10 14:22:06,076][75634] Avg episode reward: [(0, '35.480'), (1, '33.590')] -[2023-10-10 14:22:06,078][76543] Updated weights for policy 0, policy_version 43183 (0.0008) -[2023-10-10 14:22:06,433][76543] Updated weights for policy 0, policy_version 43193 (0.0011) -[2023-10-10 14:22:08,879][76542] Updated weights for policy 1, policy_version 43140 (0.0008) -[2023-10-10 14:22:09,248][76542] Updated weights for policy 1, policy_version 43150 (0.0008) -[2023-10-10 14:22:09,627][76542] Updated weights for policy 1, policy_version 43160 (0.0009) -[2023-10-10 14:22:10,136][76543] Updated weights for policy 0, policy_version 43203 (0.0010) -[2023-10-10 14:22:10,506][76543] Updated weights for policy 0, policy_version 43213 (0.0010) -[2023-10-10 14:22:10,886][76543] Updated weights for policy 0, policy_version 43223 (0.0009) -[2023-10-10 14:22:11,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 88440832. Throughput: 0: 1816.9, 1: 1820.8. Samples: 22119686. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-10-10 14:22:11,076][75634] Avg episode reward: [(0, '36.260'), (1, '35.970')] -[2023-10-10 14:22:13,358][76542] Updated weights for policy 1, policy_version 43170 (0.0010) -[2023-10-10 14:22:13,726][76542] Updated weights for policy 1, policy_version 43180 (0.0009) -[2023-10-10 14:22:14,099][76542] Updated weights for policy 1, policy_version 43190 (0.0008) -[2023-10-10 14:22:14,467][76542] Updated weights for policy 1, policy_version 43200 (0.0009) -[2023-10-10 14:22:14,497][76543] Updated weights for policy 0, policy_version 43233 (0.0009) -[2023-10-10 14:22:14,862][76543] Updated weights for policy 0, policy_version 43243 (0.0010) -[2023-10-10 14:22:15,234][76543] Updated weights for policy 0, policy_version 43253 (0.0007) -[2023-10-10 14:22:15,601][76543] Updated weights for policy 0, policy_version 43263 (0.0009) -[2023-10-10 14:22:16,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 88539136. Throughput: 0: 1826.0, 1: 1821.3. Samples: 22141232. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-10-10 14:22:16,076][75634] Avg episode reward: [(0, '36.920'), (1, '34.430')] -[2023-10-10 14:22:18,391][76542] Updated weights for policy 1, policy_version 43210 (0.0007) -[2023-10-10 14:22:18,765][76542] Updated weights for policy 1, policy_version 43220 (0.0009) -[2023-10-10 14:22:19,137][76542] Updated weights for policy 1, policy_version 43230 (0.0009) -[2023-10-10 14:22:19,387][76543] Updated weights for policy 0, policy_version 43273 (0.0009) -[2023-10-10 14:22:19,765][76543] Updated weights for policy 0, policy_version 43283 (0.0008) -[2023-10-10 14:22:20,136][76543] Updated weights for policy 0, policy_version 43293 (0.0007) -[2023-10-10 14:22:21,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 88604672. Throughput: 0: 1821.0, 1: 1816.8. Samples: 22152470. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-10-10 14:22:21,076][75634] Avg episode reward: [(0, '35.020'), (1, '35.720')] -[2023-10-10 14:22:22,797][76542] Updated weights for policy 1, policy_version 43240 (0.0009) -[2023-10-10 14:22:23,159][76542] Updated weights for policy 1, policy_version 43250 (0.0007) -[2023-10-10 14:22:23,529][76542] Updated weights for policy 1, policy_version 43260 (0.0007) -[2023-10-10 14:22:23,815][76543] Updated weights for policy 0, policy_version 43303 (0.0008) -[2023-10-10 14:22:24,186][76543] Updated weights for policy 0, policy_version 43313 (0.0009) -[2023-10-10 14:22:24,552][76543] Updated weights for policy 0, policy_version 43323 (0.0008) -[2023-10-10 14:22:26,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 88670208. Throughput: 0: 1821.7, 1: 1817.0. Samples: 22173714. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-10 14:22:26,076][75634] Avg episode reward: [(0, '36.820'), (1, '36.820')] -[2023-10-10 14:22:27,238][76542] Updated weights for policy 1, policy_version 43270 (0.0009) -[2023-10-10 14:22:27,609][76542] Updated weights for policy 1, policy_version 43280 (0.0011) -[2023-10-10 14:22:27,981][76542] Updated weights for policy 1, policy_version 43290 (0.0010) -[2023-10-10 14:22:28,176][76543] Updated weights for policy 0, policy_version 43333 (0.0009) -[2023-10-10 14:22:28,548][76543] Updated weights for policy 0, policy_version 43343 (0.0010) -[2023-10-10 14:22:28,920][76543] Updated weights for policy 0, policy_version 43353 (0.0011) -[2023-10-10 14:22:31,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 88735744. Throughput: 0: 1816.4, 1: 1818.1. Samples: 22195980. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-10 14:22:31,076][75634] Avg episode reward: [(0, '36.010'), (1, '33.840')] -[2023-10-10 14:22:31,086][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000043360_44400640.pth... -[2023-10-10 14:22:31,087][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000043296_44335104.pth... -[2023-10-10 14:22:31,123][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000041600_42598400.pth -[2023-10-10 14:22:31,124][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000041664_42663936.pth -[2023-10-10 14:22:31,669][76542] Updated weights for policy 1, policy_version 43300 (0.0008) -[2023-10-10 14:22:32,048][76542] Updated weights for policy 1, policy_version 43310 (0.0010) -[2023-10-10 14:22:32,409][76542] Updated weights for policy 1, policy_version 43320 (0.0011) -[2023-10-10 14:22:32,672][76543] Updated weights for policy 0, policy_version 43363 (0.0008) -[2023-10-10 14:22:33,046][76543] Updated weights for policy 0, policy_version 43373 (0.0008) -[2023-10-10 14:22:33,411][76543] Updated weights for policy 0, policy_version 43383 (0.0008) -[2023-10-10 14:22:36,002][76542] Updated weights for policy 1, policy_version 43330 (0.0009) -[2023-10-10 14:22:36,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 88801280. Throughput: 0: 1815.5, 1: 1821.1. Samples: 22206688. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-10 14:22:36,077][75634] Avg episode reward: [(0, '34.790'), (1, '37.320')] -[2023-10-10 14:22:36,371][76542] Updated weights for policy 1, policy_version 43340 (0.0012) -[2023-10-10 14:22:36,739][76542] Updated weights for policy 1, policy_version 43350 (0.0010) -[2023-10-10 14:22:36,940][76543] Updated weights for policy 0, policy_version 43393 (0.0008) -[2023-10-10 14:22:37,104][76542] Updated weights for policy 1, policy_version 43360 (0.0008) -[2023-10-10 14:22:37,304][76543] Updated weights for policy 0, policy_version 43403 (0.0009) -[2023-10-10 14:22:37,675][76543] Updated weights for policy 0, policy_version 43413 (0.0009) -[2023-10-10 14:22:38,045][76543] Updated weights for policy 0, policy_version 43423 (0.0010) -[2023-10-10 14:22:40,840][76542] Updated weights for policy 1, policy_version 43370 (0.0011) -[2023-10-10 14:22:41,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 88866816. Throughput: 0: 1819.9, 1: 1811.9. Samples: 22229006. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-10 14:22:41,077][75634] Avg episode reward: [(0, '35.750'), (1, '38.610')] -[2023-10-10 14:22:41,204][76542] Updated weights for policy 1, policy_version 43380 (0.0010) -[2023-10-10 14:22:41,573][76542] Updated weights for policy 1, policy_version 43390 (0.0008) -[2023-10-10 14:22:41,737][76543] Updated weights for policy 0, policy_version 43433 (0.0010) -[2023-10-10 14:22:42,112][76543] Updated weights for policy 0, policy_version 43443 (0.0007) -[2023-10-10 14:22:42,480][76543] Updated weights for policy 0, policy_version 43453 (0.0008) -[2023-10-10 14:22:45,219][76542] Updated weights for policy 1, policy_version 43400 (0.0007) -[2023-10-10 14:22:45,588][76542] Updated weights for policy 1, policy_version 43410 (0.0008) -[2023-10-10 14:22:45,953][76542] Updated weights for policy 1, policy_version 43420 (0.0008) -[2023-10-10 14:22:46,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 88932352. Throughput: 0: 1820.3, 1: 1821.2. Samples: 22251060. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-10 14:22:46,077][75634] Avg episode reward: [(0, '35.710'), (1, '35.320')] -[2023-10-10 14:22:46,088][76543] Updated weights for policy 0, policy_version 43463 (0.0009) -[2023-10-10 14:22:46,450][76543] Updated weights for policy 0, policy_version 43473 (0.0008) -[2023-10-10 14:22:46,829][76543] Updated weights for policy 0, policy_version 43483 (0.0008) -[2023-10-10 14:22:49,732][76542] Updated weights for policy 1, policy_version 43430 (0.0008) -[2023-10-10 14:22:50,107][76542] Updated weights for policy 1, policy_version 43440 (0.0007) -[2023-10-10 14:22:50,474][76542] Updated weights for policy 1, policy_version 43450 (0.0008) -[2023-10-10 14:22:50,580][76543] Updated weights for policy 0, policy_version 43493 (0.0008) -[2023-10-10 14:22:50,956][76543] Updated weights for policy 0, policy_version 43503 (0.0009) -[2023-10-10 14:22:51,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 89030656. Throughput: 0: 1821.1, 1: 1816.7. Samples: 22261854. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-10 14:22:51,077][75634] Avg episode reward: [(0, '33.250'), (1, '35.170')] -[2023-10-10 14:22:51,320][76543] Updated weights for policy 0, policy_version 43513 (0.0009) -[2023-10-10 14:22:54,154][76542] Updated weights for policy 1, policy_version 43460 (0.0007) -[2023-10-10 14:22:54,523][76542] Updated weights for policy 1, policy_version 43470 (0.0009) -[2023-10-10 14:22:54,885][76542] Updated weights for policy 1, policy_version 43480 (0.0009) -[2023-10-10 14:22:54,943][76543] Updated weights for policy 0, policy_version 43523 (0.0010) -[2023-10-10 14:22:55,307][76543] Updated weights for policy 0, policy_version 43533 (0.0009) -[2023-10-10 14:22:55,678][76543] Updated weights for policy 0, policy_version 43543 (0.0009) -[2023-10-10 14:22:56,076][75634] Fps is (10 sec: 19661.4, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 89128960. Throughput: 0: 1829.3, 1: 1819.6. Samples: 22283886. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-10 14:22:56,076][75634] Avg episode reward: [(0, '31.810'), (1, '34.610')] -[2023-10-10 14:22:58,499][76542] Updated weights for policy 1, policy_version 43490 (0.0008) -[2023-10-10 14:22:58,858][76542] Updated weights for policy 1, policy_version 43500 (0.0008) -[2023-10-10 14:22:59,232][76542] Updated weights for policy 1, policy_version 43510 (0.0008) -[2023-10-10 14:22:59,234][76543] Updated weights for policy 0, policy_version 43553 (0.0009) -[2023-10-10 14:22:59,604][76543] Updated weights for policy 0, policy_version 43563 (0.0008) -[2023-10-10 14:22:59,604][76542] Updated weights for policy 1, policy_version 43520 (0.0009) -[2023-10-10 14:22:59,977][76543] Updated weights for policy 0, policy_version 43573 (0.0009) -[2023-10-10 14:23:00,349][76543] Updated weights for policy 0, policy_version 43583 (0.0008) -[2023-10-10 14:23:01,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 89194496. Throughput: 0: 1822.4, 1: 1819.3. Samples: 22305108. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-10 14:23:01,077][75634] Avg episode reward: [(0, '37.070'), (1, '36.650')] -[2023-10-10 14:23:03,106][76542] Updated weights for policy 1, policy_version 43530 (0.0007) -[2023-10-10 14:23:03,479][76542] Updated weights for policy 1, policy_version 43540 (0.0008) -[2023-10-10 14:23:03,852][76542] Updated weights for policy 1, policy_version 43550 (0.0008) -[2023-10-10 14:23:03,961][76543] Updated weights for policy 0, policy_version 43593 (0.0009) -[2023-10-10 14:23:04,342][76543] Updated weights for policy 0, policy_version 43603 (0.0007) -[2023-10-10 14:23:04,705][76543] Updated weights for policy 0, policy_version 43613 (0.0008) -[2023-10-10 14:23:06,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 89260032. Throughput: 0: 1831.4, 1: 1819.0. Samples: 22316736. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-10 14:23:06,077][75634] Avg episode reward: [(0, '35.680'), (1, '33.170')] -[2023-10-10 14:23:07,547][76542] Updated weights for policy 1, policy_version 43560 (0.0009) -[2023-10-10 14:23:07,925][76542] Updated weights for policy 1, policy_version 43570 (0.0008) -[2023-10-10 14:23:08,284][76542] Updated weights for policy 1, policy_version 43580 (0.0010) -[2023-10-10 14:23:08,448][76543] Updated weights for policy 0, policy_version 43623 (0.0007) -[2023-10-10 14:23:08,823][76543] Updated weights for policy 0, policy_version 43633 (0.0007) -[2023-10-10 14:23:09,198][76543] Updated weights for policy 0, policy_version 43643 (0.0008) -[2023-10-10 14:23:11,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 89325568. Throughput: 0: 1823.1, 1: 1825.4. Samples: 22337898. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-10 14:23:11,077][75634] Avg episode reward: [(0, '36.920'), (1, '34.800')] -[2023-10-10 14:23:12,244][76542] Updated weights for policy 1, policy_version 43590 (0.0008) -[2023-10-10 14:23:12,624][76542] Updated weights for policy 1, policy_version 43600 (0.0008) -[2023-10-10 14:23:12,770][76543] Updated weights for policy 0, policy_version 43653 (0.0008) -[2023-10-10 14:23:12,993][76542] Updated weights for policy 1, policy_version 43610 (0.0008) -[2023-10-10 14:23:13,129][76543] Updated weights for policy 0, policy_version 43663 (0.0007) -[2023-10-10 14:23:13,506][76543] Updated weights for policy 0, policy_version 43673 (0.0007) -[2023-10-10 14:23:16,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 89391104. Throughput: 0: 1831.3, 1: 1818.9. Samples: 22360240. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-10 14:23:16,076][75634] Avg episode reward: [(0, '35.150'), (1, '34.090')] -[2023-10-10 14:23:16,744][76542] Updated weights for policy 1, policy_version 43620 (0.0008) -[2023-10-10 14:23:17,104][76542] Updated weights for policy 1, policy_version 43630 (0.0009) -[2023-10-10 14:23:17,321][76543] Updated weights for policy 0, policy_version 43683 (0.0007) -[2023-10-10 14:23:17,468][76542] Updated weights for policy 1, policy_version 43640 (0.0007) -[2023-10-10 14:23:17,691][76543] Updated weights for policy 0, policy_version 43693 (0.0007) -[2023-10-10 14:23:18,073][76543] Updated weights for policy 0, policy_version 43703 (0.0009) -[2023-10-10 14:23:21,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 89456640. Throughput: 0: 1822.1, 1: 1815.4. Samples: 22370376. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-10 14:23:21,077][75634] Avg episode reward: [(0, '34.550'), (1, '33.030')] -[2023-10-10 14:23:21,158][76542] Updated weights for policy 1, policy_version 43650 (0.0007) -[2023-10-10 14:23:21,525][76542] Updated weights for policy 1, policy_version 43660 (0.0009) -[2023-10-10 14:23:21,720][76543] Updated weights for policy 0, policy_version 43713 (0.0009) -[2023-10-10 14:23:21,886][76542] Updated weights for policy 1, policy_version 43670 (0.0008) -[2023-10-10 14:23:22,097][76543] Updated weights for policy 0, policy_version 43723 (0.0008) -[2023-10-10 14:23:22,257][76542] Updated weights for policy 1, policy_version 43680 (0.0008) -[2023-10-10 14:23:22,465][76543] Updated weights for policy 0, policy_version 43733 (0.0008) -[2023-10-10 14:23:22,843][76543] Updated weights for policy 0, policy_version 43743 (0.0009) -[2023-10-10 14:23:25,941][76542] Updated weights for policy 1, policy_version 43690 (0.0010) -[2023-10-10 14:23:26,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 89522176. Throughput: 0: 1824.6, 1: 1816.4. Samples: 22392850. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-10 14:23:26,077][75634] Avg episode reward: [(0, '39.510'), (1, '34.070')] -[2023-10-10 14:23:26,308][76542] Updated weights for policy 1, policy_version 43700 (0.0011) -[2023-10-10 14:23:26,514][76543] Updated weights for policy 0, policy_version 43753 (0.0009) -[2023-10-10 14:23:26,681][76542] Updated weights for policy 1, policy_version 43710 (0.0008) -[2023-10-10 14:23:26,878][76543] Updated weights for policy 0, policy_version 43763 (0.0008) -[2023-10-10 14:23:27,247][76543] Updated weights for policy 0, policy_version 43773 (0.0010) -[2023-10-10 14:23:30,494][76542] Updated weights for policy 1, policy_version 43720 (0.0008) -[2023-10-10 14:23:30,871][76542] Updated weights for policy 1, policy_version 43730 (0.0008) -[2023-10-10 14:23:31,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 89587712. Throughput: 0: 1812.7, 1: 1813.4. Samples: 22414234. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 14:23:31,077][75634] Avg episode reward: [(0, '39.910'), (1, '33.140')] -[2023-10-10 14:23:31,167][76543] Updated weights for policy 0, policy_version 43783 (0.0009) -[2023-10-10 14:23:31,227][76542] Updated weights for policy 1, policy_version 43740 (0.0008) -[2023-10-10 14:23:31,536][76543] Updated weights for policy 0, policy_version 43793 (0.0009) -[2023-10-10 14:23:31,919][76543] Updated weights for policy 0, policy_version 43803 (0.0009) -[2023-10-10 14:23:35,019][76542] Updated weights for policy 1, policy_version 43750 (0.0007) -[2023-10-10 14:23:35,391][76542] Updated weights for policy 1, policy_version 43760 (0.0007) -[2023-10-10 14:23:35,637][76543] Updated weights for policy 0, policy_version 43813 (0.0008) -[2023-10-10 14:23:35,748][76542] Updated weights for policy 1, policy_version 43770 (0.0007) -[2023-10-10 14:23:36,014][76543] Updated weights for policy 0, policy_version 43823 (0.0007) -[2023-10-10 14:23:36,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 89686016. Throughput: 0: 1810.4, 1: 1807.5. Samples: 22424660. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 14:23:36,077][75634] Avg episode reward: [(0, '35.490'), (1, '32.530')] -[2023-10-10 14:23:36,382][76543] Updated weights for policy 0, policy_version 43833 (0.0009) -[2023-10-10 14:23:39,367][76542] Updated weights for policy 1, policy_version 43780 (0.0008) -[2023-10-10 14:23:39,738][76542] Updated weights for policy 1, policy_version 43790 (0.0009) -[2023-10-10 14:23:40,114][76542] Updated weights for policy 1, policy_version 43800 (0.0008) -[2023-10-10 14:23:40,187][76543] Updated weights for policy 0, policy_version 43843 (0.0008) -[2023-10-10 14:23:40,562][76543] Updated weights for policy 0, policy_version 43853 (0.0007) -[2023-10-10 14:23:40,931][76543] Updated weights for policy 0, policy_version 43863 (0.0008) -[2023-10-10 14:23:41,076][75634] Fps is (10 sec: 16384.6, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 89751552. Throughput: 0: 1806.7, 1: 1809.4. Samples: 22446610. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 14:23:41,076][75634] Avg episode reward: [(0, '37.560'), (1, '33.200')] -[2023-10-10 14:23:43,864][76542] Updated weights for policy 1, policy_version 43810 (0.0007) -[2023-10-10 14:23:44,232][76542] Updated weights for policy 1, policy_version 43820 (0.0008) -[2023-10-10 14:23:44,597][76542] Updated weights for policy 1, policy_version 43830 (0.0008) -[2023-10-10 14:23:44,634][76543] Updated weights for policy 0, policy_version 43873 (0.0009) -[2023-10-10 14:23:44,968][76542] Updated weights for policy 1, policy_version 43840 (0.0010) -[2023-10-10 14:23:45,000][76543] Updated weights for policy 0, policy_version 43883 (0.0009) -[2023-10-10 14:23:45,363][76543] Updated weights for policy 0, policy_version 43893 (0.0008) -[2023-10-10 14:23:45,739][76543] Updated weights for policy 0, policy_version 43903 (0.0009) -[2023-10-10 14:23:46,076][75634] Fps is (10 sec: 16384.2, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 89849856. Throughput: 0: 1814.8, 1: 1796.4. Samples: 22467610. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 14:23:46,077][75634] Avg episode reward: [(0, '36.120'), (1, '33.900')] -[2023-10-10 14:23:48,935][76542] Updated weights for policy 1, policy_version 43850 (0.0009) -[2023-10-10 14:23:49,311][76542] Updated weights for policy 1, policy_version 43860 (0.0008) -[2023-10-10 14:23:49,378][76543] Updated weights for policy 0, policy_version 43913 (0.0007) -[2023-10-10 14:23:49,679][76542] Updated weights for policy 1, policy_version 43870 (0.0008) -[2023-10-10 14:23:49,757][76543] Updated weights for policy 0, policy_version 43923 (0.0008) -[2023-10-10 14:23:50,117][76543] Updated weights for policy 0, policy_version 43933 (0.0007) -[2023-10-10 14:23:51,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 89915392. Throughput: 0: 1806.0, 1: 1812.4. Samples: 22479560. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 14:23:51,076][75634] Avg episode reward: [(0, '35.540'), (1, '33.130')] -[2023-10-10 14:23:53,410][76542] Updated weights for policy 1, policy_version 43880 (0.0007) -[2023-10-10 14:23:53,772][76542] Updated weights for policy 1, policy_version 43890 (0.0007) -[2023-10-10 14:23:53,873][76543] Updated weights for policy 0, policy_version 43943 (0.0008) -[2023-10-10 14:23:54,123][76542] Updated weights for policy 1, policy_version 43900 (0.0007) -[2023-10-10 14:23:54,244][76543] Updated weights for policy 0, policy_version 43953 (0.0008) -[2023-10-10 14:23:54,619][76543] Updated weights for policy 0, policy_version 43963 (0.0010) -[2023-10-10 14:23:56,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 89980928. Throughput: 0: 1817.2, 1: 1784.8. Samples: 22499986. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 14:23:56,077][75634] Avg episode reward: [(0, '34.540'), (1, '35.690')] -[2023-10-10 14:23:57,899][76542] Updated weights for policy 1, policy_version 43910 (0.0008) -[2023-10-10 14:23:58,263][76542] Updated weights for policy 1, policy_version 43920 (0.0009) -[2023-10-10 14:23:58,403][76543] Updated weights for policy 0, policy_version 43973 (0.0009) -[2023-10-10 14:23:58,622][76542] Updated weights for policy 1, policy_version 43930 (0.0007) -[2023-10-10 14:23:58,776][76543] Updated weights for policy 0, policy_version 43983 (0.0008) -[2023-10-10 14:23:59,154][76543] Updated weights for policy 0, policy_version 43993 (0.0009) -[2023-10-10 14:24:01,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 90046464. Throughput: 0: 1804.2, 1: 1792.4. Samples: 22522088. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:24:01,076][75634] Avg episode reward: [(0, '36.140'), (1, '33.700')] -[2023-10-10 14:24:02,421][76542] Updated weights for policy 1, policy_version 43940 (0.0009) -[2023-10-10 14:24:02,792][76542] Updated weights for policy 1, policy_version 43950 (0.0010) -[2023-10-10 14:24:02,830][76543] Updated weights for policy 0, policy_version 44003 (0.0010) -[2023-10-10 14:24:03,164][76542] Updated weights for policy 1, policy_version 43960 (0.0007) -[2023-10-10 14:24:03,202][76543] Updated weights for policy 0, policy_version 44013 (0.0008) -[2023-10-10 14:24:03,573][76543] Updated weights for policy 0, policy_version 44023 (0.0009) -[2023-10-10 14:24:06,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 90112000. Throughput: 0: 1818.0, 1: 1790.7. Samples: 22532764. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:24:06,076][75634] Avg episode reward: [(0, '36.880'), (1, '34.230')] -[2023-10-10 14:24:06,837][76542] Updated weights for policy 1, policy_version 43970 (0.0007) -[2023-10-10 14:24:07,130][76543] Updated weights for policy 0, policy_version 44033 (0.0007) -[2023-10-10 14:24:07,216][76542] Updated weights for policy 1, policy_version 43980 (0.0009) -[2023-10-10 14:24:07,499][76543] Updated weights for policy 0, policy_version 44043 (0.0007) -[2023-10-10 14:24:07,590][76542] Updated weights for policy 1, policy_version 43990 (0.0009) -[2023-10-10 14:24:07,868][76543] Updated weights for policy 0, policy_version 44053 (0.0008) -[2023-10-10 14:24:07,953][76542] Updated weights for policy 1, policy_version 44000 (0.0010) -[2023-10-10 14:24:08,251][76543] Updated weights for policy 0, policy_version 44063 (0.0010) -[2023-10-10 14:24:11,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 90177536. Throughput: 0: 1803.3, 1: 1792.6. Samples: 22554666. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:24:11,077][75634] Avg episode reward: [(0, '36.750'), (1, '36.140')] -[2023-10-10 14:24:11,707][76542] Updated weights for policy 1, policy_version 44010 (0.0008) -[2023-10-10 14:24:12,064][76543] Updated weights for policy 0, policy_version 44073 (0.0009) -[2023-10-10 14:24:12,065][76542] Updated weights for policy 1, policy_version 44020 (0.0008) -[2023-10-10 14:24:12,436][76542] Updated weights for policy 1, policy_version 44030 (0.0010) -[2023-10-10 14:24:12,441][76543] Updated weights for policy 0, policy_version 44083 (0.0009) -[2023-10-10 14:24:12,800][76543] Updated weights for policy 0, policy_version 44093 (0.0008) -[2023-10-10 14:24:16,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 90243072. Throughput: 0: 1808.7, 1: 1807.4. Samples: 22576960. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:24:16,077][75634] Avg episode reward: [(0, '36.690'), (1, '36.180')] -[2023-10-10 14:24:16,220][76542] Updated weights for policy 1, policy_version 44040 (0.0008) -[2023-10-10 14:24:16,492][76543] Updated weights for policy 0, policy_version 44103 (0.0009) -[2023-10-10 14:24:16,595][76542] Updated weights for policy 1, policy_version 44050 (0.0009) -[2023-10-10 14:24:16,861][76543] Updated weights for policy 0, policy_version 44113 (0.0008) -[2023-10-10 14:24:16,958][76542] Updated weights for policy 1, policy_version 44060 (0.0008) -[2023-10-10 14:24:17,227][76543] Updated weights for policy 0, policy_version 44123 (0.0011) -[2023-10-10 14:24:20,678][76542] Updated weights for policy 1, policy_version 44070 (0.0009) -[2023-10-10 14:24:21,047][76542] Updated weights for policy 1, policy_version 44080 (0.0008) -[2023-10-10 14:24:21,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 90308608. Throughput: 0: 1810.1, 1: 1788.4. Samples: 22586590. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:24:21,076][75634] Avg episode reward: [(0, '36.410'), (1, '36.120')] -[2023-10-10 14:24:21,132][76543] Updated weights for policy 0, policy_version 44133 (0.0009) -[2023-10-10 14:24:21,409][76542] Updated weights for policy 1, policy_version 44090 (0.0008) -[2023-10-10 14:24:21,528][76543] Updated weights for policy 0, policy_version 44143 (0.0007) -[2023-10-10 14:24:21,890][76543] Updated weights for policy 0, policy_version 44153 (0.0009) -[2023-10-10 14:24:25,030][76542] Updated weights for policy 1, policy_version 44100 (0.0007) -[2023-10-10 14:24:25,402][76542] Updated weights for policy 1, policy_version 44110 (0.0008) -[2023-10-10 14:24:25,544][76543] Updated weights for policy 0, policy_version 44163 (0.0008) -[2023-10-10 14:24:25,770][76542] Updated weights for policy 1, policy_version 44120 (0.0007) -[2023-10-10 14:24:25,912][76543] Updated weights for policy 0, policy_version 44173 (0.0008) -[2023-10-10 14:24:26,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 90406912. Throughput: 0: 1805.5, 1: 1807.1. Samples: 22609176. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:24:26,077][75634] Avg episode reward: [(0, '35.750'), (1, '32.740')] -[2023-10-10 14:24:26,288][76543] Updated weights for policy 0, policy_version 44183 (0.0009) -[2023-10-10 14:24:29,447][76542] Updated weights for policy 1, policy_version 44130 (0.0009) -[2023-10-10 14:24:29,815][76542] Updated weights for policy 1, policy_version 44140 (0.0009) -[2023-10-10 14:24:30,179][76543] Updated weights for policy 0, policy_version 44193 (0.0007) -[2023-10-10 14:24:30,182][76542] Updated weights for policy 1, policy_version 44150 (0.0009) -[2023-10-10 14:24:30,544][76542] Updated weights for policy 1, policy_version 44160 (0.0007) -[2023-10-10 14:24:30,554][76543] Updated weights for policy 0, policy_version 44203 (0.0009) -[2023-10-10 14:24:30,923][76543] Updated weights for policy 0, policy_version 44213 (0.0011) -[2023-10-10 14:24:31,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 90472448. Throughput: 0: 1811.6, 1: 1795.2. Samples: 22629912. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:24:31,076][75634] Avg episode reward: [(0, '34.970'), (1, '34.380')] -[2023-10-10 14:24:31,084][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000044160_45219840.pth... -[2023-10-10 14:24:31,116][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000042464_43483136.pth -[2023-10-10 14:24:31,291][76543] Updated weights for policy 0, policy_version 44223 (0.0008) -[2023-10-10 14:24:31,328][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000044224_45285376.pth... -[2023-10-10 14:24:31,367][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000042496_43515904.pth -[2023-10-10 14:24:34,437][76542] Updated weights for policy 1, policy_version 44170 (0.0008) -[2023-10-10 14:24:34,811][76542] Updated weights for policy 1, policy_version 44180 (0.0009) -[2023-10-10 14:24:34,972][76543] Updated weights for policy 0, policy_version 44233 (0.0010) -[2023-10-10 14:24:35,178][76542] Updated weights for policy 1, policy_version 44190 (0.0008) -[2023-10-10 14:24:35,346][76543] Updated weights for policy 0, policy_version 44243 (0.0008) -[2023-10-10 14:24:35,713][76543] Updated weights for policy 0, policy_version 44253 (0.0009) -[2023-10-10 14:24:36,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 90570752. Throughput: 0: 1793.3, 1: 1802.4. Samples: 22641368. Policy #0 lag: (min: 1.0, avg: 10.0, max: 33.0) -[2023-10-10 14:24:36,077][75634] Avg episode reward: [(0, '34.730'), (1, '34.650')] -[2023-10-10 14:24:38,830][76542] Updated weights for policy 1, policy_version 44200 (0.0008) -[2023-10-10 14:24:39,213][76542] Updated weights for policy 1, policy_version 44210 (0.0008) -[2023-10-10 14:24:39,378][76543] Updated weights for policy 0, policy_version 44263 (0.0008) -[2023-10-10 14:24:39,574][76542] Updated weights for policy 1, policy_version 44220 (0.0008) -[2023-10-10 14:24:39,743][76543] Updated weights for policy 0, policy_version 44273 (0.0009) -[2023-10-10 14:24:40,113][76543] Updated weights for policy 0, policy_version 44283 (0.0011) -[2023-10-10 14:24:41,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 90636288. Throughput: 0: 1808.2, 1: 1802.2. Samples: 22662454. Policy #0 lag: (min: 1.0, avg: 10.0, max: 33.0) -[2023-10-10 14:24:41,077][75634] Avg episode reward: [(0, '33.740'), (1, '34.180')] -[2023-10-10 14:24:43,252][76542] Updated weights for policy 1, policy_version 44230 (0.0010) -[2023-10-10 14:24:43,622][76542] Updated weights for policy 1, policy_version 44240 (0.0011) -[2023-10-10 14:24:43,831][76543] Updated weights for policy 0, policy_version 44293 (0.0008) -[2023-10-10 14:24:43,988][76542] Updated weights for policy 1, policy_version 44250 (0.0007) -[2023-10-10 14:24:44,197][76543] Updated weights for policy 0, policy_version 44303 (0.0008) -[2023-10-10 14:24:44,560][76543] Updated weights for policy 0, policy_version 44313 (0.0009) -[2023-10-10 14:24:46,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 90701824. Throughput: 0: 1792.0, 1: 1798.2. Samples: 22683644. Policy #0 lag: (min: 1.0, avg: 10.0, max: 33.0) -[2023-10-10 14:24:46,076][75634] Avg episode reward: [(0, '34.890'), (1, '34.950')] -[2023-10-10 14:24:47,486][76542] Updated weights for policy 1, policy_version 44260 (0.0008) -[2023-10-10 14:24:47,849][76542] Updated weights for policy 1, policy_version 44270 (0.0008) -[2023-10-10 14:24:48,223][76542] Updated weights for policy 1, policy_version 44280 (0.0007) -[2023-10-10 14:24:48,317][76543] Updated weights for policy 0, policy_version 44323 (0.0009) -[2023-10-10 14:24:48,692][76543] Updated weights for policy 0, policy_version 44333 (0.0007) -[2023-10-10 14:24:49,059][76543] Updated weights for policy 0, policy_version 44343 (0.0009) -[2023-10-10 14:24:51,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 90767360. Throughput: 0: 1801.9, 1: 1801.2. Samples: 22694900. Policy #0 lag: (min: 1.0, avg: 10.0, max: 33.0) -[2023-10-10 14:24:51,076][75634] Avg episode reward: [(0, '36.060'), (1, '35.780')] -[2023-10-10 14:24:51,945][76542] Updated weights for policy 1, policy_version 44290 (0.0009) -[2023-10-10 14:24:52,316][76542] Updated weights for policy 1, policy_version 44300 (0.0010) -[2023-10-10 14:24:52,680][76542] Updated weights for policy 1, policy_version 44310 (0.0008) -[2023-10-10 14:24:52,748][76543] Updated weights for policy 0, policy_version 44353 (0.0009) -[2023-10-10 14:24:53,042][76542] Updated weights for policy 1, policy_version 44320 (0.0007) -[2023-10-10 14:24:53,121][76543] Updated weights for policy 0, policy_version 44363 (0.0010) -[2023-10-10 14:24:53,496][76543] Updated weights for policy 0, policy_version 44373 (0.0008) -[2023-10-10 14:24:53,869][76543] Updated weights for policy 0, policy_version 44383 (0.0007) -[2023-10-10 14:24:56,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 90832896. Throughput: 0: 1793.0, 1: 1801.9. Samples: 22716438. Policy #0 lag: (min: 1.0, avg: 10.0, max: 33.0) -[2023-10-10 14:24:56,076][75634] Avg episode reward: [(0, '37.930'), (1, '33.100')] -[2023-10-10 14:24:56,582][76542] Updated weights for policy 1, policy_version 44330 (0.0007) -[2023-10-10 14:24:56,945][76542] Updated weights for policy 1, policy_version 44340 (0.0008) -[2023-10-10 14:24:57,312][76542] Updated weights for policy 1, policy_version 44350 (0.0009) -[2023-10-10 14:24:57,687][76543] Updated weights for policy 0, policy_version 44393 (0.0008) -[2023-10-10 14:24:58,070][76543] Updated weights for policy 0, policy_version 44403 (0.0008) -[2023-10-10 14:24:58,435][76543] Updated weights for policy 0, policy_version 44413 (0.0009) -[2023-10-10 14:25:00,969][76542] Updated weights for policy 1, policy_version 44360 (0.0007) -[2023-10-10 14:25:01,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 90898432. Throughput: 0: 1792.9, 1: 1814.2. Samples: 22739280. Policy #0 lag: (min: 1.0, avg: 10.0, max: 33.0) -[2023-10-10 14:25:01,077][75634] Avg episode reward: [(0, '35.230'), (1, '33.640')] -[2023-10-10 14:25:01,344][76542] Updated weights for policy 1, policy_version 44370 (0.0009) -[2023-10-10 14:25:01,714][76542] Updated weights for policy 1, policy_version 44380 (0.0010) -[2023-10-10 14:25:02,034][76543] Updated weights for policy 0, policy_version 44423 (0.0009) -[2023-10-10 14:25:02,411][76543] Updated weights for policy 0, policy_version 44433 (0.0008) -[2023-10-10 14:25:02,791][76543] Updated weights for policy 0, policy_version 44443 (0.0008) -[2023-10-10 14:25:05,325][76542] Updated weights for policy 1, policy_version 44390 (0.0008) -[2023-10-10 14:25:05,685][76542] Updated weights for policy 1, policy_version 44400 (0.0010) -[2023-10-10 14:25:06,063][76542] Updated weights for policy 1, policy_version 44410 (0.0012) -[2023-10-10 14:25:06,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 90963968. Throughput: 0: 1794.5, 1: 1826.2. Samples: 22749522. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:25:06,077][75634] Avg episode reward: [(0, '35.410'), (1, '32.690')] -[2023-10-10 14:25:06,428][76543] Updated weights for policy 0, policy_version 44453 (0.0007) -[2023-10-10 14:25:06,807][76543] Updated weights for policy 0, policy_version 44463 (0.0009) -[2023-10-10 14:25:07,175][76543] Updated weights for policy 0, policy_version 44473 (0.0007) -[2023-10-10 14:25:09,930][76542] Updated weights for policy 1, policy_version 44420 (0.0009) -[2023-10-10 14:25:10,291][76542] Updated weights for policy 1, policy_version 44430 (0.0008) -[2023-10-10 14:25:10,664][76542] Updated weights for policy 1, policy_version 44440 (0.0007) -[2023-10-10 14:25:10,819][76543] Updated weights for policy 0, policy_version 44483 (0.0008) -[2023-10-10 14:25:11,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 91062272. Throughput: 0: 1806.8, 1: 1816.6. Samples: 22772228. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:25:11,077][75634] Avg episode reward: [(0, '35.130'), (1, '33.570')] -[2023-10-10 14:25:11,183][76543] Updated weights for policy 0, policy_version 44493 (0.0009) -[2023-10-10 14:25:11,561][76543] Updated weights for policy 0, policy_version 44503 (0.0009) -[2023-10-10 14:25:14,297][76542] Updated weights for policy 1, policy_version 44450 (0.0008) -[2023-10-10 14:25:14,664][76542] Updated weights for policy 1, policy_version 44460 (0.0008) -[2023-10-10 14:25:15,031][76542] Updated weights for policy 1, policy_version 44470 (0.0009) -[2023-10-10 14:25:15,275][76543] Updated weights for policy 0, policy_version 44513 (0.0008) -[2023-10-10 14:25:15,401][76542] Updated weights for policy 1, policy_version 44480 (0.0007) -[2023-10-10 14:25:15,644][76543] Updated weights for policy 0, policy_version 44523 (0.0009) -[2023-10-10 14:25:16,023][76543] Updated weights for policy 0, policy_version 44533 (0.0008) -[2023-10-10 14:25:16,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 91127808. Throughput: 0: 1814.9, 1: 1816.1. Samples: 22793308. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:25:16,077][75634] Avg episode reward: [(0, '37.620'), (1, '32.590')] -[2023-10-10 14:25:16,402][76543] Updated weights for policy 0, policy_version 44543 (0.0007) -[2023-10-10 14:25:19,150][76542] Updated weights for policy 1, policy_version 44490 (0.0009) -[2023-10-10 14:25:19,518][76542] Updated weights for policy 1, policy_version 44500 (0.0009) -[2023-10-10 14:25:19,888][76542] Updated weights for policy 1, policy_version 44510 (0.0008) -[2023-10-10 14:25:20,138][76543] Updated weights for policy 0, policy_version 44553 (0.0009) -[2023-10-10 14:25:20,520][76543] Updated weights for policy 0, policy_version 44563 (0.0010) -[2023-10-10 14:25:20,891][76543] Updated weights for policy 0, policy_version 44573 (0.0009) -[2023-10-10 14:25:21,076][75634] Fps is (10 sec: 16384.0, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 91226112. Throughput: 0: 1810.2, 1: 1816.8. Samples: 22804584. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:25:21,077][75634] Avg episode reward: [(0, '40.600'), (1, '32.870')] -[2023-10-10 14:25:23,573][76542] Updated weights for policy 1, policy_version 44520 (0.0007) -[2023-10-10 14:25:23,949][76542] Updated weights for policy 1, policy_version 44530 (0.0007) -[2023-10-10 14:25:24,317][76542] Updated weights for policy 1, policy_version 44540 (0.0008) -[2023-10-10 14:25:24,531][76543] Updated weights for policy 0, policy_version 44583 (0.0010) -[2023-10-10 14:25:24,905][76543] Updated weights for policy 0, policy_version 44593 (0.0009) -[2023-10-10 14:25:25,269][76543] Updated weights for policy 0, policy_version 44603 (0.0008) -[2023-10-10 14:25:26,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 91291648. Throughput: 0: 1813.3, 1: 1817.4. Samples: 22825838. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:25:26,076][75634] Avg episode reward: [(0, '38.840'), (1, '33.800')] -[2023-10-10 14:25:28,203][76542] Updated weights for policy 1, policy_version 44550 (0.0008) -[2023-10-10 14:25:28,570][76542] Updated weights for policy 1, policy_version 44560 (0.0012) -[2023-10-10 14:25:28,871][76543] Updated weights for policy 0, policy_version 44613 (0.0008) -[2023-10-10 14:25:28,937][76542] Updated weights for policy 1, policy_version 44570 (0.0010) -[2023-10-10 14:25:29,249][76543] Updated weights for policy 0, policy_version 44623 (0.0008) -[2023-10-10 14:25:29,621][76543] Updated weights for policy 0, policy_version 44633 (0.0010) -[2023-10-10 14:25:31,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 91357184. Throughput: 0: 1815.4, 1: 1815.4. Samples: 22847028. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:25:31,077][75634] Avg episode reward: [(0, '36.960'), (1, '34.160')] -[2023-10-10 14:25:32,635][76542] Updated weights for policy 1, policy_version 44580 (0.0007) -[2023-10-10 14:25:33,004][76542] Updated weights for policy 1, policy_version 44590 (0.0008) -[2023-10-10 14:25:33,372][76542] Updated weights for policy 1, policy_version 44600 (0.0008) -[2023-10-10 14:25:33,432][76543] Updated weights for policy 0, policy_version 44643 (0.0008) -[2023-10-10 14:25:33,801][76543] Updated weights for policy 0, policy_version 44653 (0.0008) -[2023-10-10 14:25:34,168][76543] Updated weights for policy 0, policy_version 44663 (0.0007) -[2023-10-10 14:25:36,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 91422720. Throughput: 0: 1820.0, 1: 1816.5. Samples: 22858546. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-10 14:25:36,077][75634] Avg episode reward: [(0, '39.910'), (1, '34.490')] -[2023-10-10 14:25:37,230][76542] Updated weights for policy 1, policy_version 44610 (0.0008) -[2023-10-10 14:25:37,600][76542] Updated weights for policy 1, policy_version 44620 (0.0008) -[2023-10-10 14:25:37,919][76543] Updated weights for policy 0, policy_version 44673 (0.0010) -[2023-10-10 14:25:37,970][76542] Updated weights for policy 1, policy_version 44630 (0.0008) -[2023-10-10 14:25:38,294][76543] Updated weights for policy 0, policy_version 44683 (0.0008) -[2023-10-10 14:25:38,336][76542] Updated weights for policy 1, policy_version 44640 (0.0008) -[2023-10-10 14:25:38,659][76543] Updated weights for policy 0, policy_version 44693 (0.0011) -[2023-10-10 14:25:39,028][76543] Updated weights for policy 0, policy_version 44703 (0.0009) -[2023-10-10 14:25:41,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 91488256. Throughput: 0: 1820.5, 1: 1810.7. Samples: 22879844. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-10 14:25:41,077][75634] Avg episode reward: [(0, '38.860'), (1, '32.340')] -[2023-10-10 14:25:42,184][76542] Updated weights for policy 1, policy_version 44650 (0.0008) -[2023-10-10 14:25:42,554][76542] Updated weights for policy 1, policy_version 44660 (0.0007) -[2023-10-10 14:25:42,703][76543] Updated weights for policy 0, policy_version 44713 (0.0009) -[2023-10-10 14:25:42,915][76542] Updated weights for policy 1, policy_version 44670 (0.0008) -[2023-10-10 14:25:43,070][76543] Updated weights for policy 0, policy_version 44723 (0.0009) -[2023-10-10 14:25:43,441][76543] Updated weights for policy 0, policy_version 44733 (0.0007) -[2023-10-10 14:25:46,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 91553792. Throughput: 0: 1825.2, 1: 1807.6. Samples: 22902754. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-10 14:25:46,076][75634] Avg episode reward: [(0, '37.120'), (1, '35.260')] -[2023-10-10 14:25:46,379][76542] Updated weights for policy 1, policy_version 44680 (0.0008) -[2023-10-10 14:25:46,746][76542] Updated weights for policy 1, policy_version 44690 (0.0008) -[2023-10-10 14:25:47,087][76543] Updated weights for policy 0, policy_version 44743 (0.0007) -[2023-10-10 14:25:47,121][76542] Updated weights for policy 1, policy_version 44700 (0.0007) -[2023-10-10 14:25:47,465][76543] Updated weights for policy 0, policy_version 44753 (0.0008) -[2023-10-10 14:25:47,831][76543] Updated weights for policy 0, policy_version 44763 (0.0009) -[2023-10-10 14:25:50,898][76542] Updated weights for policy 1, policy_version 44710 (0.0008) -[2023-10-10 14:25:51,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 91619328. Throughput: 0: 1824.7, 1: 1798.1. Samples: 22912550. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-10 14:25:51,076][75634] Avg episode reward: [(0, '29.840'), (1, '35.710')] -[2023-10-10 14:25:51,271][76542] Updated weights for policy 1, policy_version 44720 (0.0008) -[2023-10-10 14:25:51,543][76543] Updated weights for policy 0, policy_version 44773 (0.0009) -[2023-10-10 14:25:51,633][76542] Updated weights for policy 1, policy_version 44730 (0.0007) -[2023-10-10 14:25:51,907][76543] Updated weights for policy 0, policy_version 44783 (0.0008) -[2023-10-10 14:25:52,281][76543] Updated weights for policy 0, policy_version 44793 (0.0008) -[2023-10-10 14:25:55,350][76542] Updated weights for policy 1, policy_version 44740 (0.0007) -[2023-10-10 14:25:55,721][76542] Updated weights for policy 1, policy_version 44750 (0.0007) -[2023-10-10 14:25:55,996][76543] Updated weights for policy 0, policy_version 44803 (0.0008) -[2023-10-10 14:25:56,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 91684864. Throughput: 0: 1820.1, 1: 1803.1. Samples: 22935272. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-10 14:25:56,076][75634] Avg episode reward: [(0, '36.680'), (1, '33.170')] -[2023-10-10 14:25:56,081][76542] Updated weights for policy 1, policy_version 44760 (0.0007) -[2023-10-10 14:25:56,375][76543] Updated weights for policy 0, policy_version 44813 (0.0009) -[2023-10-10 14:25:56,749][76543] Updated weights for policy 0, policy_version 44823 (0.0008) -[2023-10-10 14:25:59,735][76542] Updated weights for policy 1, policy_version 44770 (0.0007) -[2023-10-10 14:26:00,101][76542] Updated weights for policy 1, policy_version 44780 (0.0008) -[2023-10-10 14:26:00,461][76542] Updated weights for policy 1, policy_version 44790 (0.0009) -[2023-10-10 14:26:00,534][76543] Updated weights for policy 0, policy_version 44833 (0.0009) -[2023-10-10 14:26:00,826][76542] Updated weights for policy 1, policy_version 44800 (0.0008) -[2023-10-10 14:26:00,899][76543] Updated weights for policy 0, policy_version 44843 (0.0009) -[2023-10-10 14:26:01,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 91783168. Throughput: 0: 1817.4, 1: 1813.1. Samples: 22956682. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-10 14:26:01,077][75634] Avg episode reward: [(0, '36.050'), (1, '35.330')] -[2023-10-10 14:26:01,278][76543] Updated weights for policy 0, policy_version 44853 (0.0008) -[2023-10-10 14:26:01,648][76543] Updated weights for policy 0, policy_version 44863 (0.0009) -[2023-10-10 14:26:04,559][76542] Updated weights for policy 1, policy_version 44810 (0.0007) -[2023-10-10 14:26:04,942][76542] Updated weights for policy 1, policy_version 44820 (0.0008) -[2023-10-10 14:26:05,284][76543] Updated weights for policy 0, policy_version 44873 (0.0009) -[2023-10-10 14:26:05,307][76542] Updated weights for policy 1, policy_version 44830 (0.0009) -[2023-10-10 14:26:05,659][76543] Updated weights for policy 0, policy_version 44883 (0.0007) -[2023-10-10 14:26:06,039][76543] Updated weights for policy 0, policy_version 44893 (0.0008) -[2023-10-10 14:26:06,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 91848704. Throughput: 0: 1819.7, 1: 1812.4. Samples: 22968030. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-10 14:26:06,076][75634] Avg episode reward: [(0, '33.240'), (1, '36.720')] -[2023-10-10 14:26:08,919][76542] Updated weights for policy 1, policy_version 44840 (0.0010) -[2023-10-10 14:26:09,292][76542] Updated weights for policy 1, policy_version 44850 (0.0008) -[2023-10-10 14:26:09,623][76543] Updated weights for policy 0, policy_version 44903 (0.0008) -[2023-10-10 14:26:09,654][76542] Updated weights for policy 1, policy_version 44860 (0.0007) -[2023-10-10 14:26:09,985][76543] Updated weights for policy 0, policy_version 44913 (0.0007) -[2023-10-10 14:26:10,358][76543] Updated weights for policy 0, policy_version 44923 (0.0007) -[2023-10-10 14:26:11,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 91947008. Throughput: 0: 1822.0, 1: 1819.5. Samples: 22989706. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 14:26:11,076][75634] Avg episode reward: [(0, '34.220'), (1, '35.560')] -[2023-10-10 14:26:13,407][76542] Updated weights for policy 1, policy_version 44870 (0.0007) -[2023-10-10 14:26:13,775][76542] Updated weights for policy 1, policy_version 44880 (0.0008) -[2023-10-10 14:26:13,964][76543] Updated weights for policy 0, policy_version 44933 (0.0009) -[2023-10-10 14:26:14,149][76542] Updated weights for policy 1, policy_version 44890 (0.0007) -[2023-10-10 14:26:14,343][76543] Updated weights for policy 0, policy_version 44943 (0.0008) -[2023-10-10 14:26:14,703][76543] Updated weights for policy 0, policy_version 44953 (0.0009) -[2023-10-10 14:26:16,076][75634] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 92012544. Throughput: 0: 1820.0, 1: 1820.7. Samples: 23010860. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 14:26:16,077][75634] Avg episode reward: [(0, '35.270'), (1, '29.830')] -[2023-10-10 14:26:17,886][76542] Updated weights for policy 1, policy_version 44900 (0.0008) -[2023-10-10 14:26:18,248][76542] Updated weights for policy 1, policy_version 44910 (0.0009) -[2023-10-10 14:26:18,400][76543] Updated weights for policy 0, policy_version 44963 (0.0007) -[2023-10-10 14:26:18,617][76542] Updated weights for policy 1, policy_version 44920 (0.0007) -[2023-10-10 14:26:18,765][76543] Updated weights for policy 0, policy_version 44973 (0.0007) -[2023-10-10 14:26:19,134][76543] Updated weights for policy 0, policy_version 44983 (0.0007) -[2023-10-10 14:26:21,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 92078080. Throughput: 0: 1822.6, 1: 1825.5. Samples: 23022708. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 14:26:21,077][75634] Avg episode reward: [(0, '36.700'), (1, '30.040')] -[2023-10-10 14:26:22,355][76542] Updated weights for policy 1, policy_version 44930 (0.0009) -[2023-10-10 14:26:22,716][76542] Updated weights for policy 1, policy_version 44940 (0.0008) -[2023-10-10 14:26:22,873][76543] Updated weights for policy 0, policy_version 44993 (0.0010) -[2023-10-10 14:26:23,080][76542] Updated weights for policy 1, policy_version 44950 (0.0007) -[2023-10-10 14:26:23,244][76543] Updated weights for policy 0, policy_version 45003 (0.0007) -[2023-10-10 14:26:23,452][76542] Updated weights for policy 1, policy_version 44960 (0.0007) -[2023-10-10 14:26:23,608][76543] Updated weights for policy 0, policy_version 45013 (0.0007) -[2023-10-10 14:26:23,979][76543] Updated weights for policy 0, policy_version 45023 (0.0007) -[2023-10-10 14:26:26,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 92143616. Throughput: 0: 1816.0, 1: 1822.3. Samples: 23043566. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 14:26:26,077][75634] Avg episode reward: [(0, '36.910'), (1, '31.850')] -[2023-10-10 14:26:27,129][76542] Updated weights for policy 1, policy_version 44970 (0.0009) -[2023-10-10 14:26:27,496][76542] Updated weights for policy 1, policy_version 44980 (0.0007) -[2023-10-10 14:26:27,806][76543] Updated weights for policy 0, policy_version 45033 (0.0007) -[2023-10-10 14:26:27,870][76542] Updated weights for policy 1, policy_version 44990 (0.0007) -[2023-10-10 14:26:28,180][76543] Updated weights for policy 0, policy_version 45043 (0.0009) -[2023-10-10 14:26:28,559][76543] Updated weights for policy 0, policy_version 45053 (0.0008) -[2023-10-10 14:26:31,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 92209152. Throughput: 0: 1811.7, 1: 1823.0. Samples: 23066318. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 14:26:31,077][75634] Avg episode reward: [(0, '38.960'), (1, '30.960')] -[2023-10-10 14:26:31,090][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000045056_46137344.pth... -[2023-10-10 14:26:31,091][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000044992_46071808.pth... -[2023-10-10 14:26:31,125][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000043296_44335104.pth -[2023-10-10 14:26:31,130][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000043360_44400640.pth -[2023-10-10 14:26:31,535][76542] Updated weights for policy 1, policy_version 45000 (0.0008) -[2023-10-10 14:26:31,898][76542] Updated weights for policy 1, policy_version 45010 (0.0008) -[2023-10-10 14:26:32,189][76543] Updated weights for policy 0, policy_version 45063 (0.0009) -[2023-10-10 14:26:32,268][76542] Updated weights for policy 1, policy_version 45020 (0.0007) -[2023-10-10 14:26:32,561][76543] Updated weights for policy 0, policy_version 45073 (0.0011) -[2023-10-10 14:26:32,925][76543] Updated weights for policy 0, policy_version 45083 (0.0009) -[2023-10-10 14:26:36,017][76542] Updated weights for policy 1, policy_version 45030 (0.0008) -[2023-10-10 14:26:36,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 92274688. Throughput: 0: 1808.0, 1: 1826.0. Samples: 23076082. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 14:26:36,076][75634] Avg episode reward: [(0, '36.970'), (1, '32.470')] -[2023-10-10 14:26:36,385][76542] Updated weights for policy 1, policy_version 45040 (0.0008) -[2023-10-10 14:26:36,671][76543] Updated weights for policy 0, policy_version 45093 (0.0007) -[2023-10-10 14:26:36,761][76542] Updated weights for policy 1, policy_version 45050 (0.0009) -[2023-10-10 14:26:37,045][76543] Updated weights for policy 0, policy_version 45103 (0.0007) -[2023-10-10 14:26:37,415][76543] Updated weights for policy 0, policy_version 45113 (0.0009) -[2023-10-10 14:26:40,386][76542] Updated weights for policy 1, policy_version 45060 (0.0009) -[2023-10-10 14:26:40,752][76542] Updated weights for policy 1, policy_version 45070 (0.0010) -[2023-10-10 14:26:41,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 92340224. Throughput: 0: 1806.1, 1: 1826.7. Samples: 23098746. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:26:41,076][75634] Avg episode reward: [(0, '36.450'), (1, '35.180')] -[2023-10-10 14:26:41,121][76542] Updated weights for policy 1, policy_version 45080 (0.0008) -[2023-10-10 14:26:41,223][76543] Updated weights for policy 0, policy_version 45123 (0.0010) -[2023-10-10 14:26:41,616][76543] Updated weights for policy 0, policy_version 45133 (0.0009) -[2023-10-10 14:26:41,990][76543] Updated weights for policy 0, policy_version 45143 (0.0007) -[2023-10-10 14:26:44,814][76542] Updated weights for policy 1, policy_version 45090 (0.0008) -[2023-10-10 14:26:45,176][76542] Updated weights for policy 1, policy_version 45100 (0.0010) -[2023-10-10 14:26:45,552][76542] Updated weights for policy 1, policy_version 45110 (0.0008) -[2023-10-10 14:26:45,651][76543] Updated weights for policy 0, policy_version 45153 (0.0009) -[2023-10-10 14:26:45,916][76542] Updated weights for policy 1, policy_version 45120 (0.0008) -[2023-10-10 14:26:46,024][76543] Updated weights for policy 0, policy_version 45163 (0.0007) -[2023-10-10 14:26:46,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 92438528. Throughput: 0: 1806.3, 1: 1820.1. Samples: 23119870. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:26:46,077][75634] Avg episode reward: [(0, '36.390'), (1, '36.040')] -[2023-10-10 14:26:46,389][76543] Updated weights for policy 0, policy_version 45173 (0.0007) -[2023-10-10 14:26:46,767][76543] Updated weights for policy 0, policy_version 45183 (0.0008) -[2023-10-10 14:26:49,725][76542] Updated weights for policy 1, policy_version 45130 (0.0011) -[2023-10-10 14:26:50,100][76542] Updated weights for policy 1, policy_version 45140 (0.0009) -[2023-10-10 14:26:50,448][76543] Updated weights for policy 0, policy_version 45193 (0.0008) -[2023-10-10 14:26:50,470][76542] Updated weights for policy 1, policy_version 45150 (0.0007) -[2023-10-10 14:26:50,824][76543] Updated weights for policy 0, policy_version 45203 (0.0010) -[2023-10-10 14:26:51,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 92504064. Throughput: 0: 1804.8, 1: 1811.0. Samples: 23130738. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:26:51,076][75634] Avg episode reward: [(0, '34.930'), (1, '35.090')] -[2023-10-10 14:26:51,194][76543] Updated weights for policy 0, policy_version 45213 (0.0011) -[2023-10-10 14:26:54,178][76542] Updated weights for policy 1, policy_version 45160 (0.0009) -[2023-10-10 14:26:54,539][76542] Updated weights for policy 1, policy_version 45170 (0.0008) -[2023-10-10 14:26:54,872][76543] Updated weights for policy 0, policy_version 45223 (0.0008) -[2023-10-10 14:26:54,910][76542] Updated weights for policy 1, policy_version 45180 (0.0007) -[2023-10-10 14:26:55,243][76543] Updated weights for policy 0, policy_version 45233 (0.0007) -[2023-10-10 14:26:55,616][76543] Updated weights for policy 0, policy_version 45243 (0.0009) -[2023-10-10 14:26:56,076][75634] Fps is (10 sec: 16383.8, 60 sec: 15291.7, 300 sec: 14551.2). Total num frames: 92602368. Throughput: 0: 1803.5, 1: 1817.2. Samples: 23152636. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:26:56,077][75634] Avg episode reward: [(0, '33.220'), (1, '32.460')] -[2023-10-10 14:26:58,581][76542] Updated weights for policy 1, policy_version 45190 (0.0007) -[2023-10-10 14:26:58,953][76542] Updated weights for policy 1, policy_version 45200 (0.0011) -[2023-10-10 14:26:59,297][76543] Updated weights for policy 0, policy_version 45253 (0.0008) -[2023-10-10 14:26:59,326][76542] Updated weights for policy 1, policy_version 45210 (0.0009) -[2023-10-10 14:26:59,666][76543] Updated weights for policy 0, policy_version 45263 (0.0008) -[2023-10-10 14:27:00,032][76543] Updated weights for policy 0, policy_version 45273 (0.0010) -[2023-10-10 14:27:01,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 92667904. Throughput: 0: 1805.6, 1: 1805.7. Samples: 23173364. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:27:01,077][75634] Avg episode reward: [(0, '31.950'), (1, '35.250')] -[2023-10-10 14:27:03,060][76542] Updated weights for policy 1, policy_version 45220 (0.0008) -[2023-10-10 14:27:03,425][76542] Updated weights for policy 1, policy_version 45230 (0.0008) -[2023-10-10 14:27:03,788][76542] Updated weights for policy 1, policy_version 45240 (0.0008) -[2023-10-10 14:27:03,860][76543] Updated weights for policy 0, policy_version 45283 (0.0010) -[2023-10-10 14:27:04,225][76543] Updated weights for policy 0, policy_version 45293 (0.0007) -[2023-10-10 14:27:04,598][76543] Updated weights for policy 0, policy_version 45303 (0.0009) -[2023-10-10 14:27:06,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 92733440. Throughput: 0: 1795.2, 1: 1808.6. Samples: 23184882. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:27:06,077][75634] Avg episode reward: [(0, '33.420'), (1, '34.130')] -[2023-10-10 14:27:07,567][76542] Updated weights for policy 1, policy_version 45250 (0.0008) -[2023-10-10 14:27:07,934][76542] Updated weights for policy 1, policy_version 45260 (0.0009) -[2023-10-10 14:27:08,305][76542] Updated weights for policy 1, policy_version 45270 (0.0009) -[2023-10-10 14:27:08,315][76543] Updated weights for policy 0, policy_version 45313 (0.0007) -[2023-10-10 14:27:08,666][76542] Updated weights for policy 1, policy_version 45280 (0.0008) -[2023-10-10 14:27:08,685][76543] Updated weights for policy 0, policy_version 45323 (0.0007) -[2023-10-10 14:27:09,051][76543] Updated weights for policy 0, policy_version 45333 (0.0009) -[2023-10-10 14:27:09,412][76543] Updated weights for policy 0, policy_version 45343 (0.0008) -[2023-10-10 14:27:11,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 92798976. Throughput: 0: 1805.9, 1: 1801.5. Samples: 23205900. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-10 14:27:11,077][75634] Avg episode reward: [(0, '35.790'), (1, '40.050')] -[2023-10-10 14:27:12,267][76542] Updated weights for policy 1, policy_version 45290 (0.0008) -[2023-10-10 14:27:12,634][76542] Updated weights for policy 1, policy_version 45300 (0.0007) -[2023-10-10 14:27:13,003][76542] Updated weights for policy 1, policy_version 45310 (0.0007) -[2023-10-10 14:27:13,201][76543] Updated weights for policy 0, policy_version 45353 (0.0008) -[2023-10-10 14:27:13,570][76543] Updated weights for policy 0, policy_version 45363 (0.0007) -[2023-10-10 14:27:13,942][76543] Updated weights for policy 0, policy_version 45373 (0.0007) -[2023-10-10 14:27:16,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 92864512. Throughput: 0: 1803.1, 1: 1798.1. Samples: 23228370. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-10 14:27:16,077][75634] Avg episode reward: [(0, '36.790'), (1, '38.320')] -[2023-10-10 14:27:16,719][76542] Updated weights for policy 1, policy_version 45320 (0.0007) -[2023-10-10 14:27:17,098][76542] Updated weights for policy 1, policy_version 45330 (0.0008) -[2023-10-10 14:27:17,461][76542] Updated weights for policy 1, policy_version 45340 (0.0008) -[2023-10-10 14:27:17,490][76543] Updated weights for policy 0, policy_version 45383 (0.0007) -[2023-10-10 14:27:17,869][76543] Updated weights for policy 0, policy_version 45393 (0.0008) -[2023-10-10 14:27:18,229][76543] Updated weights for policy 0, policy_version 45403 (0.0007) -[2023-10-10 14:27:21,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 92930048. Throughput: 0: 1814.9, 1: 1799.2. Samples: 23238714. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-10 14:27:21,076][75634] Avg episode reward: [(0, '34.510'), (1, '36.350')] -[2023-10-10 14:27:21,261][76542] Updated weights for policy 1, policy_version 45350 (0.0008) -[2023-10-10 14:27:21,626][76542] Updated weights for policy 1, policy_version 45360 (0.0008) -[2023-10-10 14:27:21,827][76543] Updated weights for policy 0, policy_version 45413 (0.0007) -[2023-10-10 14:27:21,990][76542] Updated weights for policy 1, policy_version 45370 (0.0008) -[2023-10-10 14:27:22,194][76543] Updated weights for policy 0, policy_version 45423 (0.0008) -[2023-10-10 14:27:22,562][76543] Updated weights for policy 0, policy_version 45433 (0.0008) -[2023-10-10 14:27:25,636][76542] Updated weights for policy 1, policy_version 45380 (0.0008) -[2023-10-10 14:27:26,008][76542] Updated weights for policy 1, policy_version 45390 (0.0008) -[2023-10-10 14:27:26,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 92995584. Throughput: 0: 1811.7, 1: 1803.8. Samples: 23261442. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-10 14:27:26,076][75634] Avg episode reward: [(0, '37.710'), (1, '35.380')] -[2023-10-10 14:27:26,372][76542] Updated weights for policy 1, policy_version 45400 (0.0009) -[2023-10-10 14:27:26,381][76543] Updated weights for policy 0, policy_version 45443 (0.0008) -[2023-10-10 14:27:26,772][76543] Updated weights for policy 0, policy_version 45453 (0.0007) -[2023-10-10 14:27:27,136][76543] Updated weights for policy 0, policy_version 45463 (0.0009) -[2023-10-10 14:27:29,888][76542] Updated weights for policy 1, policy_version 45410 (0.0008) -[2023-10-10 14:27:30,255][76542] Updated weights for policy 1, policy_version 45420 (0.0009) -[2023-10-10 14:27:30,623][76542] Updated weights for policy 1, policy_version 45430 (0.0008) -[2023-10-10 14:27:30,945][76543] Updated weights for policy 0, policy_version 45473 (0.0009) -[2023-10-10 14:27:30,994][76542] Updated weights for policy 1, policy_version 45440 (0.0009) -[2023-10-10 14:27:31,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 93093888. Throughput: 0: 1813.6, 1: 1815.6. Samples: 23283186. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-10 14:27:31,076][75634] Avg episode reward: [(0, '38.250'), (1, '33.500')] -[2023-10-10 14:27:31,312][76543] Updated weights for policy 0, policy_version 45483 (0.0010) -[2023-10-10 14:27:31,686][76543] Updated weights for policy 0, policy_version 45493 (0.0010) -[2023-10-10 14:27:32,059][76543] Updated weights for policy 0, policy_version 45503 (0.0010) -[2023-10-10 14:27:34,859][76542] Updated weights for policy 1, policy_version 45450 (0.0007) -[2023-10-10 14:27:35,230][76542] Updated weights for policy 1, policy_version 45460 (0.0009) -[2023-10-10 14:27:35,598][76542] Updated weights for policy 1, policy_version 45470 (0.0009) -[2023-10-10 14:27:35,692][76543] Updated weights for policy 0, policy_version 45513 (0.0009) -[2023-10-10 14:27:36,067][76543] Updated weights for policy 0, policy_version 45523 (0.0009) -[2023-10-10 14:27:36,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 93159424. Throughput: 0: 1815.8, 1: 1816.6. Samples: 23294196. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-10 14:27:36,076][75634] Avg episode reward: [(0, '36.700'), (1, '34.300')] -[2023-10-10 14:27:36,443][76543] Updated weights for policy 0, policy_version 45533 (0.0009) -[2023-10-10 14:27:39,165][76542] Updated weights for policy 1, policy_version 45480 (0.0008) -[2023-10-10 14:27:39,546][76542] Updated weights for policy 1, policy_version 45490 (0.0009) -[2023-10-10 14:27:39,906][76542] Updated weights for policy 1, policy_version 45500 (0.0009) -[2023-10-10 14:27:40,124][76543] Updated weights for policy 0, policy_version 45543 (0.0009) -[2023-10-10 14:27:40,503][76543] Updated weights for policy 0, policy_version 45553 (0.0009) -[2023-10-10 14:27:40,871][76543] Updated weights for policy 0, policy_version 45563 (0.0008) -[2023-10-10 14:27:41,076][75634] Fps is (10 sec: 16383.8, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 93257728. Throughput: 0: 1818.9, 1: 1818.5. Samples: 23316322. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:27:41,077][75634] Avg episode reward: [(0, '38.560'), (1, '28.660')] -[2023-10-10 14:27:43,526][76542] Updated weights for policy 1, policy_version 45510 (0.0010) -[2023-10-10 14:27:43,891][76542] Updated weights for policy 1, policy_version 45520 (0.0010) -[2023-10-10 14:27:44,257][76542] Updated weights for policy 1, policy_version 45530 (0.0008) -[2023-10-10 14:27:44,773][76543] Updated weights for policy 0, policy_version 45573 (0.0012) -[2023-10-10 14:27:45,137][76543] Updated weights for policy 0, policy_version 45583 (0.0010) -[2023-10-10 14:27:45,513][76543] Updated weights for policy 0, policy_version 45593 (0.0011) -[2023-10-10 14:27:46,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 93323264. Throughput: 0: 1824.8, 1: 1825.2. Samples: 23337612. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:27:46,076][75634] Avg episode reward: [(0, '35.190'), (1, '29.710')] -[2023-10-10 14:27:47,978][76542] Updated weights for policy 1, policy_version 45540 (0.0010) -[2023-10-10 14:27:48,350][76542] Updated weights for policy 1, policy_version 45550 (0.0010) -[2023-10-10 14:27:48,717][76542] Updated weights for policy 1, policy_version 45560 (0.0008) -[2023-10-10 14:27:49,103][76543] Updated weights for policy 0, policy_version 45603 (0.0010) -[2023-10-10 14:27:49,471][76543] Updated weights for policy 0, policy_version 45613 (0.0008) -[2023-10-10 14:27:49,852][76543] Updated weights for policy 0, policy_version 45623 (0.0011) -[2023-10-10 14:27:51,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 93388800. Throughput: 0: 1818.6, 1: 1822.5. Samples: 23348730. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:27:51,076][75634] Avg episode reward: [(0, '34.230'), (1, '32.920')] -[2023-10-10 14:27:52,453][76542] Updated weights for policy 1, policy_version 45570 (0.0009) -[2023-10-10 14:27:52,822][76542] Updated weights for policy 1, policy_version 45580 (0.0011) -[2023-10-10 14:27:53,205][76542] Updated weights for policy 1, policy_version 45590 (0.0008) -[2023-10-10 14:27:53,419][76543] Updated weights for policy 0, policy_version 45633 (0.0008) -[2023-10-10 14:27:53,580][76542] Updated weights for policy 1, policy_version 45600 (0.0009) -[2023-10-10 14:27:53,783][76543] Updated weights for policy 0, policy_version 45643 (0.0008) -[2023-10-10 14:27:54,164][76543] Updated weights for policy 0, policy_version 45653 (0.0009) -[2023-10-10 14:27:54,526][76543] Updated weights for policy 0, policy_version 45663 (0.0011) -[2023-10-10 14:27:56,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 93454336. Throughput: 0: 1825.2, 1: 1827.5. Samples: 23370274. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:27:56,077][75634] Avg episode reward: [(0, '36.800'), (1, '37.320')] -[2023-10-10 14:27:57,268][76542] Updated weights for policy 1, policy_version 45610 (0.0009) -[2023-10-10 14:27:57,637][76542] Updated weights for policy 1, policy_version 45620 (0.0008) -[2023-10-10 14:27:57,994][76542] Updated weights for policy 1, policy_version 45630 (0.0010) -[2023-10-10 14:27:58,015][76543] Updated weights for policy 0, policy_version 45673 (0.0010) -[2023-10-10 14:27:58,389][76543] Updated weights for policy 0, policy_version 45683 (0.0009) -[2023-10-10 14:27:58,761][76543] Updated weights for policy 0, policy_version 45693 (0.0007) -[2023-10-10 14:28:01,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 93519872. Throughput: 0: 1828.2, 1: 1827.7. Samples: 23392888. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:28:01,077][75634] Avg episode reward: [(0, '34.200'), (1, '36.020')] -[2023-10-10 14:28:01,732][76542] Updated weights for policy 1, policy_version 45640 (0.0009) -[2023-10-10 14:28:02,101][76542] Updated weights for policy 1, policy_version 45650 (0.0009) -[2023-10-10 14:28:02,465][76542] Updated weights for policy 1, policy_version 45660 (0.0009) -[2023-10-10 14:28:02,551][76543] Updated weights for policy 0, policy_version 45703 (0.0008) -[2023-10-10 14:28:02,919][76543] Updated weights for policy 0, policy_version 45713 (0.0008) -[2023-10-10 14:28:03,286][76543] Updated weights for policy 0, policy_version 45723 (0.0012) -[2023-10-10 14:28:06,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 93585408. Throughput: 0: 1826.3, 1: 1824.8. Samples: 23403010. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:28:06,077][75634] Avg episode reward: [(0, '33.730'), (1, '36.840')] -[2023-10-10 14:28:06,235][76542] Updated weights for policy 1, policy_version 45670 (0.0008) -[2023-10-10 14:28:06,608][76542] Updated weights for policy 1, policy_version 45680 (0.0008) -[2023-10-10 14:28:06,909][76543] Updated weights for policy 0, policy_version 45733 (0.0010) -[2023-10-10 14:28:06,985][76542] Updated weights for policy 1, policy_version 45690 (0.0009) -[2023-10-10 14:28:07,279][76543] Updated weights for policy 0, policy_version 45743 (0.0009) -[2023-10-10 14:28:07,657][76543] Updated weights for policy 0, policy_version 45753 (0.0010) -[2023-10-10 14:28:10,749][76542] Updated weights for policy 1, policy_version 45700 (0.0009) -[2023-10-10 14:28:11,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 93650944. Throughput: 0: 1825.6, 1: 1818.4. Samples: 23425426. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:28:11,077][75634] Avg episode reward: [(0, '40.160'), (1, '37.210')] -[2023-10-10 14:28:11,124][76542] Updated weights for policy 1, policy_version 45710 (0.0009) -[2023-10-10 14:28:11,348][76543] Updated weights for policy 0, policy_version 45763 (0.0009) -[2023-10-10 14:28:11,490][76542] Updated weights for policy 1, policy_version 45720 (0.0009) -[2023-10-10 14:28:11,753][76543] Updated weights for policy 0, policy_version 45773 (0.0009) -[2023-10-10 14:28:12,130][76543] Updated weights for policy 0, policy_version 45783 (0.0008) -[2023-10-10 14:28:15,167][76542] Updated weights for policy 1, policy_version 45730 (0.0007) -[2023-10-10 14:28:15,539][76542] Updated weights for policy 1, policy_version 45740 (0.0008) -[2023-10-10 14:28:15,870][76543] Updated weights for policy 0, policy_version 45793 (0.0008) -[2023-10-10 14:28:15,903][76542] Updated weights for policy 1, policy_version 45750 (0.0008) -[2023-10-10 14:28:16,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 93716480. Throughput: 0: 1822.3, 1: 1824.8. Samples: 23447306. Policy #0 lag: (min: 5.0, avg: 12.4, max: 37.0) -[2023-10-10 14:28:16,077][75634] Avg episode reward: [(0, '37.740'), (1, '38.570')] -[2023-10-10 14:28:16,238][76543] Updated weights for policy 0, policy_version 45803 (0.0007) -[2023-10-10 14:28:16,269][76542] Updated weights for policy 1, policy_version 45760 (0.0009) -[2023-10-10 14:28:16,607][76543] Updated weights for policy 0, policy_version 45813 (0.0007) -[2023-10-10 14:28:16,971][76543] Updated weights for policy 0, policy_version 45823 (0.0007) -[2023-10-10 14:28:20,012][76542] Updated weights for policy 1, policy_version 45770 (0.0010) -[2023-10-10 14:28:20,375][76542] Updated weights for policy 1, policy_version 45780 (0.0010) -[2023-10-10 14:28:20,742][76542] Updated weights for policy 1, policy_version 45790 (0.0009) -[2023-10-10 14:28:20,780][76543] Updated weights for policy 0, policy_version 45833 (0.0009) -[2023-10-10 14:28:21,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 93814784. Throughput: 0: 1823.7, 1: 1819.8. Samples: 23458154. Policy #0 lag: (min: 5.0, avg: 12.4, max: 37.0) -[2023-10-10 14:28:21,077][75634] Avg episode reward: [(0, '32.730'), (1, '36.960')] -[2023-10-10 14:28:21,159][76543] Updated weights for policy 0, policy_version 45843 (0.0010) -[2023-10-10 14:28:21,529][76543] Updated weights for policy 0, policy_version 45853 (0.0007) -[2023-10-10 14:28:24,349][76542] Updated weights for policy 1, policy_version 45800 (0.0008) -[2023-10-10 14:28:24,712][76542] Updated weights for policy 1, policy_version 45810 (0.0009) -[2023-10-10 14:28:25,085][76542] Updated weights for policy 1, policy_version 45820 (0.0011) -[2023-10-10 14:28:25,233][76543] Updated weights for policy 0, policy_version 45863 (0.0009) -[2023-10-10 14:28:25,605][76543] Updated weights for policy 0, policy_version 45873 (0.0007) -[2023-10-10 14:28:25,984][76543] Updated weights for policy 0, policy_version 45883 (0.0010) -[2023-10-10 14:28:26,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 93880320. Throughput: 0: 1812.9, 1: 1823.7. Samples: 23479968. Policy #0 lag: (min: 5.0, avg: 12.4, max: 37.0) -[2023-10-10 14:28:26,076][75634] Avg episode reward: [(0, '33.370'), (1, '34.080')] -[2023-10-10 14:28:28,692][76542] Updated weights for policy 1, policy_version 45830 (0.0009) -[2023-10-10 14:28:29,065][76542] Updated weights for policy 1, policy_version 45840 (0.0008) -[2023-10-10 14:28:29,433][76542] Updated weights for policy 1, policy_version 45850 (0.0008) -[2023-10-10 14:28:29,590][76543] Updated weights for policy 0, policy_version 45893 (0.0009) -[2023-10-10 14:28:29,961][76543] Updated weights for policy 0, policy_version 45903 (0.0009) -[2023-10-10 14:28:30,328][76543] Updated weights for policy 0, policy_version 45913 (0.0009) -[2023-10-10 14:28:31,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 93978624. Throughput: 0: 1816.7, 1: 1818.0. Samples: 23501172. Policy #0 lag: (min: 5.0, avg: 12.4, max: 37.0) -[2023-10-10 14:28:31,077][75634] Avg episode reward: [(0, '35.140'), (1, '32.490')] -[2023-10-10 14:28:31,086][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000045856_46956544.pth... -[2023-10-10 14:28:31,087][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000045920_47022080.pth... -[2023-10-10 14:28:31,117][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000044160_45219840.pth -[2023-10-10 14:28:31,124][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000044224_45285376.pth -[2023-10-10 14:28:32,955][76542] Updated weights for policy 1, policy_version 45860 (0.0009) -[2023-10-10 14:28:33,319][76542] Updated weights for policy 1, policy_version 45870 (0.0010) -[2023-10-10 14:28:33,697][76542] Updated weights for policy 1, policy_version 45880 (0.0008) -[2023-10-10 14:28:34,044][76543] Updated weights for policy 0, policy_version 45923 (0.0008) -[2023-10-10 14:28:34,427][76543] Updated weights for policy 0, policy_version 45933 (0.0009) -[2023-10-10 14:28:34,794][76543] Updated weights for policy 0, policy_version 45943 (0.0008) -[2023-10-10 14:28:36,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 94044160. Throughput: 0: 1816.8, 1: 1825.3. Samples: 23512624. Policy #0 lag: (min: 5.0, avg: 12.4, max: 37.0) -[2023-10-10 14:28:36,076][75634] Avg episode reward: [(0, '34.470'), (1, '31.530')] -[2023-10-10 14:28:37,484][76542] Updated weights for policy 1, policy_version 45890 (0.0009) -[2023-10-10 14:28:37,854][76542] Updated weights for policy 1, policy_version 45900 (0.0007) -[2023-10-10 14:28:38,223][76542] Updated weights for policy 1, policy_version 45910 (0.0009) -[2023-10-10 14:28:38,505][76543] Updated weights for policy 0, policy_version 45953 (0.0007) -[2023-10-10 14:28:38,592][76542] Updated weights for policy 1, policy_version 45920 (0.0008) -[2023-10-10 14:28:38,869][76543] Updated weights for policy 0, policy_version 45963 (0.0009) -[2023-10-10 14:28:39,244][76543] Updated weights for policy 0, policy_version 45973 (0.0011) -[2023-10-10 14:28:39,631][76543] Updated weights for policy 0, policy_version 45983 (0.0011) -[2023-10-10 14:28:41,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 94109696. Throughput: 0: 1814.5, 1: 1822.5. Samples: 23533942. Policy #0 lag: (min: 5.0, avg: 12.4, max: 37.0) -[2023-10-10 14:28:41,077][75634] Avg episode reward: [(0, '36.700'), (1, '34.130')] -[2023-10-10 14:28:42,226][76542] Updated weights for policy 1, policy_version 45930 (0.0009) -[2023-10-10 14:28:42,594][76542] Updated weights for policy 1, policy_version 45940 (0.0009) -[2023-10-10 14:28:42,968][76542] Updated weights for policy 1, policy_version 45950 (0.0008) -[2023-10-10 14:28:43,213][76543] Updated weights for policy 0, policy_version 45993 (0.0008) -[2023-10-10 14:28:43,595][76543] Updated weights for policy 0, policy_version 46003 (0.0008) -[2023-10-10 14:28:43,962][76543] Updated weights for policy 0, policy_version 46013 (0.0010) -[2023-10-10 14:28:46,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 94175232. Throughput: 0: 1803.8, 1: 1827.0. Samples: 23556274. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-10 14:28:46,077][75634] Avg episode reward: [(0, '35.970'), (1, '35.360')] -[2023-10-10 14:28:46,598][76542] Updated weights for policy 1, policy_version 45960 (0.0008) -[2023-10-10 14:28:46,975][76542] Updated weights for policy 1, policy_version 45970 (0.0008) -[2023-10-10 14:28:47,342][76542] Updated weights for policy 1, policy_version 45980 (0.0008) -[2023-10-10 14:28:47,806][76543] Updated weights for policy 0, policy_version 46023 (0.0009) -[2023-10-10 14:28:48,189][76543] Updated weights for policy 0, policy_version 46033 (0.0010) -[2023-10-10 14:28:48,550][76543] Updated weights for policy 0, policy_version 46043 (0.0010) -[2023-10-10 14:28:51,029][76542] Updated weights for policy 1, policy_version 45990 (0.0009) -[2023-10-10 14:28:51,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 94240768. Throughput: 0: 1810.9, 1: 1829.8. Samples: 23566842. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-10 14:28:51,076][75634] Avg episode reward: [(0, '34.310'), (1, '35.470')] -[2023-10-10 14:28:51,397][76542] Updated weights for policy 1, policy_version 46000 (0.0007) -[2023-10-10 14:28:51,761][76542] Updated weights for policy 1, policy_version 46010 (0.0007) -[2023-10-10 14:28:52,261][76543] Updated weights for policy 0, policy_version 46053 (0.0010) -[2023-10-10 14:28:52,628][76543] Updated weights for policy 0, policy_version 46063 (0.0007) -[2023-10-10 14:28:52,995][76543] Updated weights for policy 0, policy_version 46073 (0.0009) -[2023-10-10 14:28:55,529][76542] Updated weights for policy 1, policy_version 46020 (0.0008) -[2023-10-10 14:28:55,888][76542] Updated weights for policy 1, policy_version 46030 (0.0008) -[2023-10-10 14:28:56,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 94306304. Throughput: 0: 1807.7, 1: 1829.5. Samples: 23589100. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-10 14:28:56,076][75634] Avg episode reward: [(0, '38.970'), (1, '36.420')] -[2023-10-10 14:28:56,257][76542] Updated weights for policy 1, policy_version 46040 (0.0008) -[2023-10-10 14:28:56,631][76543] Updated weights for policy 0, policy_version 46083 (0.0007) -[2023-10-10 14:28:57,017][76543] Updated weights for policy 0, policy_version 46093 (0.0008) -[2023-10-10 14:28:57,391][76543] Updated weights for policy 0, policy_version 46103 (0.0008) -[2023-10-10 14:29:00,035][76542] Updated weights for policy 1, policy_version 46050 (0.0009) -[2023-10-10 14:29:00,400][76542] Updated weights for policy 1, policy_version 46060 (0.0008) -[2023-10-10 14:29:00,759][76542] Updated weights for policy 1, policy_version 46070 (0.0007) -[2023-10-10 14:29:01,066][76543] Updated weights for policy 0, policy_version 46113 (0.0007) -[2023-10-10 14:29:01,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 94371840. Throughput: 0: 1814.4, 1: 1822.5. Samples: 23610964. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-10 14:29:01,077][75634] Avg episode reward: [(0, '39.260'), (1, '36.920')] -[2023-10-10 14:29:01,119][76542] Updated weights for policy 1, policy_version 46080 (0.0010) -[2023-10-10 14:29:01,430][76543] Updated weights for policy 0, policy_version 46123 (0.0007) -[2023-10-10 14:29:01,796][76543] Updated weights for policy 0, policy_version 46133 (0.0007) -[2023-10-10 14:29:02,166][76543] Updated weights for policy 0, policy_version 46143 (0.0008) -[2023-10-10 14:29:04,786][76542] Updated weights for policy 1, policy_version 46090 (0.0010) -[2023-10-10 14:29:05,161][76542] Updated weights for policy 1, policy_version 46100 (0.0009) -[2023-10-10 14:29:05,529][76542] Updated weights for policy 1, policy_version 46110 (0.0008) -[2023-10-10 14:29:05,866][76543] Updated weights for policy 0, policy_version 46153 (0.0010) -[2023-10-10 14:29:06,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 94470144. Throughput: 0: 1812.2, 1: 1824.5. Samples: 23621804. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-10 14:29:06,076][75634] Avg episode reward: [(0, '37.890'), (1, '35.070')] -[2023-10-10 14:29:06,235][76543] Updated weights for policy 0, policy_version 46163 (0.0007) -[2023-10-10 14:29:06,615][76543] Updated weights for policy 0, policy_version 46173 (0.0009) -[2023-10-10 14:29:09,311][76542] Updated weights for policy 1, policy_version 46120 (0.0008) -[2023-10-10 14:29:09,680][76542] Updated weights for policy 1, policy_version 46130 (0.0007) -[2023-10-10 14:29:10,055][76542] Updated weights for policy 1, policy_version 46140 (0.0009) -[2023-10-10 14:29:10,245][76543] Updated weights for policy 0, policy_version 46183 (0.0009) -[2023-10-10 14:29:10,622][76543] Updated weights for policy 0, policy_version 46193 (0.0007) -[2023-10-10 14:29:10,994][76543] Updated weights for policy 0, policy_version 46203 (0.0008) -[2023-10-10 14:29:11,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 94535680. Throughput: 0: 1814.5, 1: 1823.2. Samples: 23643666. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-10 14:29:11,077][75634] Avg episode reward: [(0, '34.200'), (1, '38.130')] -[2023-10-10 14:29:13,622][76542] Updated weights for policy 1, policy_version 46150 (0.0007) -[2023-10-10 14:29:13,990][76542] Updated weights for policy 1, policy_version 46160 (0.0007) -[2023-10-10 14:29:14,353][76542] Updated weights for policy 1, policy_version 46170 (0.0009) -[2023-10-10 14:29:14,564][76543] Updated weights for policy 0, policy_version 46213 (0.0010) -[2023-10-10 14:29:14,940][76543] Updated weights for policy 0, policy_version 46223 (0.0009) -[2023-10-10 14:29:15,315][76543] Updated weights for policy 0, policy_version 46233 (0.0007) -[2023-10-10 14:29:16,076][75634] Fps is (10 sec: 16383.9, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 94633984. Throughput: 0: 1811.7, 1: 1826.9. Samples: 23664908. Policy #0 lag: (min: 23.0, avg: 37.8, max: 55.0) -[2023-10-10 14:29:16,076][75634] Avg episode reward: [(0, '35.180'), (1, '38.230')] -[2023-10-10 14:29:17,943][76542] Updated weights for policy 1, policy_version 46180 (0.0008) -[2023-10-10 14:29:18,312][76542] Updated weights for policy 1, policy_version 46190 (0.0007) -[2023-10-10 14:29:18,683][76542] Updated weights for policy 1, policy_version 46200 (0.0007) -[2023-10-10 14:29:19,065][76543] Updated weights for policy 0, policy_version 46243 (0.0007) -[2023-10-10 14:29:19,427][76543] Updated weights for policy 0, policy_version 46253 (0.0007) -[2023-10-10 14:29:19,789][76543] Updated weights for policy 0, policy_version 46263 (0.0007) -[2023-10-10 14:29:21,076][75634] Fps is (10 sec: 16384.6, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 94699520. Throughput: 0: 1817.3, 1: 1823.0. Samples: 23676438. Policy #0 lag: (min: 23.0, avg: 37.8, max: 55.0) -[2023-10-10 14:29:21,076][75634] Avg episode reward: [(0, '32.630'), (1, '35.320')] -[2023-10-10 14:29:22,448][76542] Updated weights for policy 1, policy_version 46210 (0.0008) -[2023-10-10 14:29:22,810][76542] Updated weights for policy 1, policy_version 46220 (0.0008) -[2023-10-10 14:29:23,177][76542] Updated weights for policy 1, policy_version 46230 (0.0007) -[2023-10-10 14:29:23,460][76543] Updated weights for policy 0, policy_version 46273 (0.0007) -[2023-10-10 14:29:23,541][76542] Updated weights for policy 1, policy_version 46240 (0.0007) -[2023-10-10 14:29:23,844][76543] Updated weights for policy 0, policy_version 46283 (0.0008) -[2023-10-10 14:29:24,228][76543] Updated weights for policy 0, policy_version 46293 (0.0007) -[2023-10-10 14:29:24,602][76543] Updated weights for policy 0, policy_version 46303 (0.0010) -[2023-10-10 14:29:26,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 94765056. Throughput: 0: 1819.1, 1: 1830.6. Samples: 23698176. Policy #0 lag: (min: 23.0, avg: 37.8, max: 55.0) -[2023-10-10 14:29:26,077][75634] Avg episode reward: [(0, '33.390'), (1, '33.300')] -[2023-10-10 14:29:27,149][76542] Updated weights for policy 1, policy_version 46250 (0.0007) -[2023-10-10 14:29:27,519][76542] Updated weights for policy 1, policy_version 46260 (0.0007) -[2023-10-10 14:29:27,892][76542] Updated weights for policy 1, policy_version 46270 (0.0007) -[2023-10-10 14:29:28,388][76543] Updated weights for policy 0, policy_version 46313 (0.0011) -[2023-10-10 14:29:28,756][76543] Updated weights for policy 0, policy_version 46323 (0.0007) -[2023-10-10 14:29:29,126][76543] Updated weights for policy 0, policy_version 46333 (0.0007) -[2023-10-10 14:29:31,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 94830592. Throughput: 0: 1818.2, 1: 1830.8. Samples: 23720482. Policy #0 lag: (min: 23.0, avg: 37.8, max: 55.0) -[2023-10-10 14:29:31,077][75634] Avg episode reward: [(0, '33.150'), (1, '35.000')] -[2023-10-10 14:29:31,516][76542] Updated weights for policy 1, policy_version 46280 (0.0012) -[2023-10-10 14:29:31,876][76542] Updated weights for policy 1, policy_version 46290 (0.0011) -[2023-10-10 14:29:32,249][76542] Updated weights for policy 1, policy_version 46300 (0.0008) -[2023-10-10 14:29:32,728][76543] Updated weights for policy 0, policy_version 46343 (0.0008) -[2023-10-10 14:29:33,105][76543] Updated weights for policy 0, policy_version 46353 (0.0008) -[2023-10-10 14:29:33,488][76543] Updated weights for policy 0, policy_version 46363 (0.0010) -[2023-10-10 14:29:35,889][76542] Updated weights for policy 1, policy_version 46310 (0.0007) -[2023-10-10 14:29:36,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 94896128. Throughput: 0: 1817.3, 1: 1829.9. Samples: 23730966. Policy #0 lag: (min: 23.0, avg: 37.8, max: 55.0) -[2023-10-10 14:29:36,076][75634] Avg episode reward: [(0, '34.260'), (1, '32.220')] -[2023-10-10 14:29:36,262][76542] Updated weights for policy 1, policy_version 46320 (0.0007) -[2023-10-10 14:29:36,617][76542] Updated weights for policy 1, policy_version 46330 (0.0007) -[2023-10-10 14:29:37,246][76543] Updated weights for policy 0, policy_version 46373 (0.0008) -[2023-10-10 14:29:37,614][76543] Updated weights for policy 0, policy_version 46383 (0.0008) -[2023-10-10 14:29:37,982][76543] Updated weights for policy 0, policy_version 46393 (0.0008) -[2023-10-10 14:29:40,330][76542] Updated weights for policy 1, policy_version 46340 (0.0008) -[2023-10-10 14:29:40,694][76542] Updated weights for policy 1, policy_version 46350 (0.0011) -[2023-10-10 14:29:41,063][76542] Updated weights for policy 1, policy_version 46360 (0.0010) -[2023-10-10 14:29:41,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 94961664. Throughput: 0: 1809.8, 1: 1832.7. Samples: 23753014. Policy #0 lag: (min: 23.0, avg: 37.8, max: 55.0) -[2023-10-10 14:29:41,076][75634] Avg episode reward: [(0, '36.350'), (1, '31.450')] -[2023-10-10 14:29:41,856][76543] Updated weights for policy 0, policy_version 46403 (0.0008) -[2023-10-10 14:29:42,251][76543] Updated weights for policy 0, policy_version 46413 (0.0009) -[2023-10-10 14:29:42,624][76543] Updated weights for policy 0, policy_version 46423 (0.0010) -[2023-10-10 14:29:44,664][76542] Updated weights for policy 1, policy_version 46370 (0.0007) -[2023-10-10 14:29:45,033][76542] Updated weights for policy 1, policy_version 46380 (0.0009) -[2023-10-10 14:29:45,397][76542] Updated weights for policy 1, policy_version 46390 (0.0011) -[2023-10-10 14:29:45,765][76542] Updated weights for policy 1, policy_version 46400 (0.0008) -[2023-10-10 14:29:46,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 95059968. Throughput: 0: 1805.4, 1: 1827.7. Samples: 23774450. Policy #0 lag: (min: 23.0, avg: 37.8, max: 55.0) -[2023-10-10 14:29:46,077][75634] Avg episode reward: [(0, '37.320'), (1, '28.800')] -[2023-10-10 14:29:46,242][76543] Updated weights for policy 0, policy_version 46433 (0.0009) -[2023-10-10 14:29:46,614][76543] Updated weights for policy 0, policy_version 46443 (0.0008) -[2023-10-10 14:29:46,984][76543] Updated weights for policy 0, policy_version 46453 (0.0007) -[2023-10-10 14:29:47,356][76543] Updated weights for policy 0, policy_version 46463 (0.0009) -[2023-10-10 14:29:49,515][76542] Updated weights for policy 1, policy_version 46410 (0.0011) -[2023-10-10 14:29:49,880][76542] Updated weights for policy 1, policy_version 46420 (0.0009) -[2023-10-10 14:29:50,264][76542] Updated weights for policy 1, policy_version 46430 (0.0008) -[2023-10-10 14:29:51,001][76543] Updated weights for policy 0, policy_version 46473 (0.0010) -[2023-10-10 14:29:51,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 95125504. Throughput: 0: 1807.5, 1: 1833.9. Samples: 23785668. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 14:29:51,077][75634] Avg episode reward: [(0, '34.650'), (1, '32.520')] -[2023-10-10 14:29:51,377][76543] Updated weights for policy 0, policy_version 46483 (0.0010) -[2023-10-10 14:29:51,742][76543] Updated weights for policy 0, policy_version 46493 (0.0011) -[2023-10-10 14:29:54,007][76542] Updated weights for policy 1, policy_version 46440 (0.0008) -[2023-10-10 14:29:54,384][76542] Updated weights for policy 1, policy_version 46450 (0.0008) -[2023-10-10 14:29:54,742][76542] Updated weights for policy 1, policy_version 46460 (0.0009) -[2023-10-10 14:29:55,445][76543] Updated weights for policy 0, policy_version 46503 (0.0011) -[2023-10-10 14:29:55,812][76543] Updated weights for policy 0, policy_version 46513 (0.0010) -[2023-10-10 14:29:56,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 95191040. Throughput: 0: 1807.7, 1: 1819.3. Samples: 23806882. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 14:29:56,076][75634] Avg episode reward: [(0, '34.000'), (1, '35.190')] -[2023-10-10 14:29:56,177][76543] Updated weights for policy 0, policy_version 46523 (0.0010) -[2023-10-10 14:29:58,261][76542] Updated weights for policy 1, policy_version 46470 (0.0009) -[2023-10-10 14:29:58,625][76542] Updated weights for policy 1, policy_version 46480 (0.0009) -[2023-10-10 14:29:59,000][76542] Updated weights for policy 1, policy_version 46490 (0.0007) -[2023-10-10 14:29:59,897][76543] Updated weights for policy 0, policy_version 46533 (0.0008) -[2023-10-10 14:30:00,264][76543] Updated weights for policy 0, policy_version 46543 (0.0009) -[2023-10-10 14:30:00,638][76543] Updated weights for policy 0, policy_version 46553 (0.0008) -[2023-10-10 14:30:01,076][75634] Fps is (10 sec: 16383.9, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 95289344. Throughput: 0: 1820.4, 1: 1827.1. Samples: 23829050. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 14:30:01,077][75634] Avg episode reward: [(0, '35.020'), (1, '32.890')] -[2023-10-10 14:30:02,649][76542] Updated weights for policy 1, policy_version 46500 (0.0007) -[2023-10-10 14:30:03,015][76542] Updated weights for policy 1, policy_version 46510 (0.0010) -[2023-10-10 14:30:03,389][76542] Updated weights for policy 1, policy_version 46520 (0.0009) -[2023-10-10 14:30:04,278][76543] Updated weights for policy 0, policy_version 46563 (0.0010) -[2023-10-10 14:30:04,653][76543] Updated weights for policy 0, policy_version 46573 (0.0010) -[2023-10-10 14:30:05,026][76543] Updated weights for policy 0, policy_version 46583 (0.0007) -[2023-10-10 14:30:06,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 95354880. Throughput: 0: 1811.6, 1: 1816.7. Samples: 23839712. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 14:30:06,076][75634] Avg episode reward: [(0, '38.000'), (1, '33.870')] -[2023-10-10 14:30:07,127][76542] Updated weights for policy 1, policy_version 46530 (0.0008) -[2023-10-10 14:30:07,499][76542] Updated weights for policy 1, policy_version 46540 (0.0011) -[2023-10-10 14:30:07,861][76542] Updated weights for policy 1, policy_version 46550 (0.0008) -[2023-10-10 14:30:08,237][76542] Updated weights for policy 1, policy_version 46560 (0.0009) -[2023-10-10 14:30:08,711][76543] Updated weights for policy 0, policy_version 46593 (0.0007) -[2023-10-10 14:30:09,090][76543] Updated weights for policy 0, policy_version 46603 (0.0007) -[2023-10-10 14:30:09,471][76543] Updated weights for policy 0, policy_version 46613 (0.0008) -[2023-10-10 14:30:09,832][76543] Updated weights for policy 0, policy_version 46623 (0.0009) -[2023-10-10 14:30:11,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 95420416. Throughput: 0: 1815.5, 1: 1818.7. Samples: 23861714. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 14:30:11,076][75634] Avg episode reward: [(0, '38.760'), (1, '35.330')] -[2023-10-10 14:30:11,974][76542] Updated weights for policy 1, policy_version 46570 (0.0007) -[2023-10-10 14:30:12,340][76542] Updated weights for policy 1, policy_version 46580 (0.0010) -[2023-10-10 14:30:12,711][76542] Updated weights for policy 1, policy_version 46590 (0.0010) -[2023-10-10 14:30:13,326][76543] Updated weights for policy 0, policy_version 46633 (0.0010) -[2023-10-10 14:30:13,697][76543] Updated weights for policy 0, policy_version 46643 (0.0009) -[2023-10-10 14:30:14,070][76543] Updated weights for policy 0, policy_version 46653 (0.0011) -[2023-10-10 14:30:16,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 95485952. Throughput: 0: 1814.9, 1: 1815.9. Samples: 23883866. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 14:30:16,076][75634] Avg episode reward: [(0, '35.980'), (1, '34.050')] -[2023-10-10 14:30:16,534][76542] Updated weights for policy 1, policy_version 46600 (0.0010) -[2023-10-10 14:30:16,909][76542] Updated weights for policy 1, policy_version 46610 (0.0009) -[2023-10-10 14:30:17,284][76542] Updated weights for policy 1, policy_version 46620 (0.0011) -[2023-10-10 14:30:17,867][76543] Updated weights for policy 0, policy_version 46663 (0.0009) -[2023-10-10 14:30:18,233][76543] Updated weights for policy 0, policy_version 46673 (0.0009) -[2023-10-10 14:30:18,611][76543] Updated weights for policy 0, policy_version 46683 (0.0008) -[2023-10-10 14:30:20,957][76542] Updated weights for policy 1, policy_version 46630 (0.0010) -[2023-10-10 14:30:21,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 95551488. Throughput: 0: 1816.2, 1: 1815.2. Samples: 23894378. Policy #0 lag: (min: 18.0, avg: 21.0, max: 50.0) -[2023-10-10 14:30:21,076][75634] Avg episode reward: [(0, '37.820'), (1, '32.990')] -[2023-10-10 14:30:21,331][76542] Updated weights for policy 1, policy_version 46640 (0.0009) -[2023-10-10 14:30:21,704][76542] Updated weights for policy 1, policy_version 46650 (0.0009) -[2023-10-10 14:30:22,242][76543] Updated weights for policy 0, policy_version 46693 (0.0008) -[2023-10-10 14:30:22,612][76543] Updated weights for policy 0, policy_version 46703 (0.0009) -[2023-10-10 14:30:22,988][76543] Updated weights for policy 0, policy_version 46713 (0.0011) -[2023-10-10 14:30:25,392][76542] Updated weights for policy 1, policy_version 46660 (0.0009) -[2023-10-10 14:30:25,763][76542] Updated weights for policy 1, policy_version 46670 (0.0009) -[2023-10-10 14:30:26,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 95617024. Throughput: 0: 1813.7, 1: 1817.4. Samples: 23916416. Policy #0 lag: (min: 18.0, avg: 21.0, max: 50.0) -[2023-10-10 14:30:26,077][75634] Avg episode reward: [(0, '37.200'), (1, '34.340')] -[2023-10-10 14:30:26,136][76542] Updated weights for policy 1, policy_version 46680 (0.0010) -[2023-10-10 14:30:26,722][76543] Updated weights for policy 0, policy_version 46723 (0.0007) -[2023-10-10 14:30:27,114][76543] Updated weights for policy 0, policy_version 46733 (0.0007) -[2023-10-10 14:30:27,491][76543] Updated weights for policy 0, policy_version 46743 (0.0008) -[2023-10-10 14:30:29,760][76542] Updated weights for policy 1, policy_version 46690 (0.0008) -[2023-10-10 14:30:30,127][76542] Updated weights for policy 1, policy_version 46700 (0.0008) -[2023-10-10 14:30:30,507][76542] Updated weights for policy 1, policy_version 46710 (0.0009) -[2023-10-10 14:30:30,871][76542] Updated weights for policy 1, policy_version 46720 (0.0008) -[2023-10-10 14:30:31,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 95715328. Throughput: 0: 1817.0, 1: 1815.8. Samples: 23937928. Policy #0 lag: (min: 18.0, avg: 21.0, max: 50.0) -[2023-10-10 14:30:31,077][75634] Avg episode reward: [(0, '31.980'), (1, '35.810')] -[2023-10-10 14:30:31,085][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000046720_47841280.pth... -[2023-10-10 14:30:31,119][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000044992_46071808.pth -[2023-10-10 14:30:31,148][76543] Updated weights for policy 0, policy_version 46753 (0.0008) -[2023-10-10 14:30:31,530][76543] Updated weights for policy 0, policy_version 46763 (0.0007) -[2023-10-10 14:30:31,897][76543] Updated weights for policy 0, policy_version 46773 (0.0007) -[2023-10-10 14:30:32,281][76543] Updated weights for policy 0, policy_version 46783 (0.0007) -[2023-10-10 14:30:32,310][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000046784_47906816.pth... -[2023-10-10 14:30:32,339][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000045056_46137344.pth -[2023-10-10 14:30:34,637][76542] Updated weights for policy 1, policy_version 46730 (0.0008) -[2023-10-10 14:30:35,015][76542] Updated weights for policy 1, policy_version 46740 (0.0009) -[2023-10-10 14:30:35,380][76542] Updated weights for policy 1, policy_version 46750 (0.0009) -[2023-10-10 14:30:36,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 95780864. Throughput: 0: 1814.5, 1: 1813.2. Samples: 23948912. Policy #0 lag: (min: 18.0, avg: 21.0, max: 50.0) -[2023-10-10 14:30:36,076][75634] Avg episode reward: [(0, '31.860'), (1, '37.500')] -[2023-10-10 14:30:36,098][76543] Updated weights for policy 0, policy_version 46793 (0.0011) -[2023-10-10 14:30:36,474][76543] Updated weights for policy 0, policy_version 46803 (0.0010) -[2023-10-10 14:30:36,834][76543] Updated weights for policy 0, policy_version 46813 (0.0010) -[2023-10-10 14:30:39,112][76542] Updated weights for policy 1, policy_version 46760 (0.0008) -[2023-10-10 14:30:39,491][76542] Updated weights for policy 1, policy_version 46770 (0.0008) -[2023-10-10 14:30:39,855][76542] Updated weights for policy 1, policy_version 46780 (0.0009) -[2023-10-10 14:30:40,537][76543] Updated weights for policy 0, policy_version 46823 (0.0008) -[2023-10-10 14:30:40,913][76543] Updated weights for policy 0, policy_version 46833 (0.0008) -[2023-10-10 14:30:41,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 95846400. Throughput: 0: 1817.2, 1: 1819.7. Samples: 23970542. Policy #0 lag: (min: 18.0, avg: 21.0, max: 50.0) -[2023-10-10 14:30:41,076][75634] Avg episode reward: [(0, '28.960'), (1, '37.790')] -[2023-10-10 14:30:41,289][76543] Updated weights for policy 0, policy_version 46843 (0.0008) -[2023-10-10 14:30:43,413][76542] Updated weights for policy 1, policy_version 46790 (0.0010) -[2023-10-10 14:30:43,785][76542] Updated weights for policy 1, policy_version 46800 (0.0011) -[2023-10-10 14:30:44,151][76542] Updated weights for policy 1, policy_version 46810 (0.0010) -[2023-10-10 14:30:44,965][76543] Updated weights for policy 0, policy_version 46853 (0.0009) -[2023-10-10 14:30:45,348][76543] Updated weights for policy 0, policy_version 46863 (0.0009) -[2023-10-10 14:30:45,716][76543] Updated weights for policy 0, policy_version 46873 (0.0009) -[2023-10-10 14:30:46,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 95944704. Throughput: 0: 1819.2, 1: 1810.5. Samples: 23992384. Policy #0 lag: (min: 18.0, avg: 21.0, max: 50.0) -[2023-10-10 14:30:46,077][75634] Avg episode reward: [(0, '32.260'), (1, '35.390')] -[2023-10-10 14:30:47,908][76542] Updated weights for policy 1, policy_version 46820 (0.0011) -[2023-10-10 14:30:48,281][76542] Updated weights for policy 1, policy_version 46830 (0.0008) -[2023-10-10 14:30:48,645][76542] Updated weights for policy 1, policy_version 46840 (0.0010) -[2023-10-10 14:30:49,420][76543] Updated weights for policy 0, policy_version 46883 (0.0009) -[2023-10-10 14:30:49,788][76543] Updated weights for policy 0, policy_version 46893 (0.0008) -[2023-10-10 14:30:50,148][76543] Updated weights for policy 0, policy_version 46903 (0.0008) -[2023-10-10 14:30:51,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 96010240. Throughput: 0: 1817.1, 1: 1814.4. Samples: 24003128. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 14:30:51,077][75634] Avg episode reward: [(0, '32.020'), (1, '34.460')] -[2023-10-10 14:30:52,480][76542] Updated weights for policy 1, policy_version 46850 (0.0007) -[2023-10-10 14:30:52,848][76542] Updated weights for policy 1, policy_version 46860 (0.0009) -[2023-10-10 14:30:53,212][76542] Updated weights for policy 1, policy_version 46870 (0.0009) -[2023-10-10 14:30:53,583][76542] Updated weights for policy 1, policy_version 46880 (0.0009) -[2023-10-10 14:30:53,819][76543] Updated weights for policy 0, policy_version 46913 (0.0008) -[2023-10-10 14:30:54,201][76543] Updated weights for policy 0, policy_version 46923 (0.0008) -[2023-10-10 14:30:54,571][76543] Updated weights for policy 0, policy_version 46933 (0.0007) -[2023-10-10 14:30:54,943][76543] Updated weights for policy 0, policy_version 46943 (0.0007) -[2023-10-10 14:30:56,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 96075776. Throughput: 0: 1824.1, 1: 1810.8. Samples: 24025282. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 14:30:56,076][75634] Avg episode reward: [(0, '37.430'), (1, '31.110')] -[2023-10-10 14:30:57,067][76542] Updated weights for policy 1, policy_version 46890 (0.0009) -[2023-10-10 14:30:57,430][76542] Updated weights for policy 1, policy_version 46900 (0.0008) -[2023-10-10 14:30:57,811][76542] Updated weights for policy 1, policy_version 46910 (0.0007) -[2023-10-10 14:30:58,379][76543] Updated weights for policy 0, policy_version 46953 (0.0008) -[2023-10-10 14:30:58,743][76543] Updated weights for policy 0, policy_version 46963 (0.0007) -[2023-10-10 14:30:59,113][76543] Updated weights for policy 0, policy_version 46973 (0.0009) -[2023-10-10 14:31:01,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 96141312. Throughput: 0: 1824.5, 1: 1817.6. Samples: 24047760. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 14:31:01,076][75634] Avg episode reward: [(0, '35.320'), (1, '32.030')] -[2023-10-10 14:31:01,587][76542] Updated weights for policy 1, policy_version 46920 (0.0008) -[2023-10-10 14:31:01,965][76542] Updated weights for policy 1, policy_version 46930 (0.0008) -[2023-10-10 14:31:02,331][76542] Updated weights for policy 1, policy_version 46940 (0.0009) -[2023-10-10 14:31:02,797][76543] Updated weights for policy 0, policy_version 46983 (0.0010) -[2023-10-10 14:31:03,178][76543] Updated weights for policy 0, policy_version 46993 (0.0010) -[2023-10-10 14:31:03,550][76543] Updated weights for policy 0, policy_version 47003 (0.0008) -[2023-10-10 14:31:05,884][76542] Updated weights for policy 1, policy_version 46950 (0.0009) -[2023-10-10 14:31:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 96206848. Throughput: 0: 1826.4, 1: 1818.4. Samples: 24058394. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 14:31:06,076][75634] Avg episode reward: [(0, '35.220'), (1, '34.210')] -[2023-10-10 14:31:06,250][76542] Updated weights for policy 1, policy_version 46960 (0.0010) -[2023-10-10 14:31:06,631][76542] Updated weights for policy 1, policy_version 46970 (0.0009) -[2023-10-10 14:31:07,188][76543] Updated weights for policy 0, policy_version 47013 (0.0007) -[2023-10-10 14:31:07,560][76543] Updated weights for policy 0, policy_version 47023 (0.0009) -[2023-10-10 14:31:07,932][76543] Updated weights for policy 0, policy_version 47033 (0.0008) -[2023-10-10 14:31:10,331][76542] Updated weights for policy 1, policy_version 46980 (0.0009) -[2023-10-10 14:31:10,703][76542] Updated weights for policy 1, policy_version 46990 (0.0009) -[2023-10-10 14:31:11,062][76542] Updated weights for policy 1, policy_version 47000 (0.0009) -[2023-10-10 14:31:11,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 96272384. Throughput: 0: 1825.9, 1: 1822.5. Samples: 24080592. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 14:31:11,076][75634] Avg episode reward: [(0, '35.890'), (1, '34.900')] -[2023-10-10 14:31:11,816][76543] Updated weights for policy 0, policy_version 47043 (0.0008) -[2023-10-10 14:31:12,220][76543] Updated weights for policy 0, policy_version 47053 (0.0008) -[2023-10-10 14:31:12,589][76543] Updated weights for policy 0, policy_version 47063 (0.0009) -[2023-10-10 14:31:14,759][76542] Updated weights for policy 1, policy_version 47010 (0.0007) -[2023-10-10 14:31:15,120][76542] Updated weights for policy 1, policy_version 47020 (0.0007) -[2023-10-10 14:31:15,486][76542] Updated weights for policy 1, policy_version 47030 (0.0011) -[2023-10-10 14:31:15,850][76542] Updated weights for policy 1, policy_version 47040 (0.0010) -[2023-10-10 14:31:16,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 96370688. Throughput: 0: 1825.7, 1: 1818.9. Samples: 24101936. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 14:31:16,077][75634] Avg episode reward: [(0, '34.540'), (1, '33.450')] -[2023-10-10 14:31:16,157][76543] Updated weights for policy 0, policy_version 47073 (0.0008) -[2023-10-10 14:31:16,534][76543] Updated weights for policy 0, policy_version 47083 (0.0008) -[2023-10-10 14:31:16,902][76543] Updated weights for policy 0, policy_version 47093 (0.0007) -[2023-10-10 14:31:17,274][76543] Updated weights for policy 0, policy_version 47103 (0.0009) -[2023-10-10 14:31:19,451][76542] Updated weights for policy 1, policy_version 47050 (0.0010) -[2023-10-10 14:31:19,827][76542] Updated weights for policy 1, policy_version 47060 (0.0009) -[2023-10-10 14:31:20,194][76542] Updated weights for policy 1, policy_version 47070 (0.0010) -[2023-10-10 14:31:20,952][76543] Updated weights for policy 0, policy_version 47113 (0.0011) -[2023-10-10 14:31:21,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 96436224. Throughput: 0: 1825.8, 1: 1822.0. Samples: 24113062. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 14:31:21,076][75634] Avg episode reward: [(0, '36.990'), (1, '35.910')] -[2023-10-10 14:31:21,311][76543] Updated weights for policy 0, policy_version 47123 (0.0011) -[2023-10-10 14:31:21,684][76543] Updated weights for policy 0, policy_version 47133 (0.0009) -[2023-10-10 14:31:24,008][76542] Updated weights for policy 1, policy_version 47080 (0.0010) -[2023-10-10 14:31:24,380][76542] Updated weights for policy 1, policy_version 47090 (0.0010) -[2023-10-10 14:31:24,750][76542] Updated weights for policy 1, policy_version 47100 (0.0010) -[2023-10-10 14:31:25,288][76543] Updated weights for policy 0, policy_version 47143 (0.0008) -[2023-10-10 14:31:25,657][76543] Updated weights for policy 0, policy_version 47153 (0.0010) -[2023-10-10 14:31:26,023][76543] Updated weights for policy 0, policy_version 47163 (0.0009) -[2023-10-10 14:31:26,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 96501760. Throughput: 0: 1830.0, 1: 1818.1. Samples: 24134710. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-10 14:31:26,076][75634] Avg episode reward: [(0, '34.210'), (1, '37.530')] -[2023-10-10 14:31:28,304][76542] Updated weights for policy 1, policy_version 47110 (0.0008) -[2023-10-10 14:31:28,694][76542] Updated weights for policy 1, policy_version 47120 (0.0009) -[2023-10-10 14:31:29,052][76542] Updated weights for policy 1, policy_version 47130 (0.0010) -[2023-10-10 14:31:29,720][76543] Updated weights for policy 0, policy_version 47173 (0.0010) -[2023-10-10 14:31:30,083][76543] Updated weights for policy 0, policy_version 47183 (0.0011) -[2023-10-10 14:31:30,459][76543] Updated weights for policy 0, policy_version 47193 (0.0009) -[2023-10-10 14:31:31,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 96600064. Throughput: 0: 1818.9, 1: 1828.4. Samples: 24156516. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-10 14:31:31,077][75634] Avg episode reward: [(0, '34.210'), (1, '37.980')] -[2023-10-10 14:31:32,982][76542] Updated weights for policy 1, policy_version 47140 (0.0009) -[2023-10-10 14:31:33,346][76542] Updated weights for policy 1, policy_version 47150 (0.0009) -[2023-10-10 14:31:33,716][76542] Updated weights for policy 1, policy_version 47160 (0.0009) -[2023-10-10 14:31:34,181][76543] Updated weights for policy 0, policy_version 47203 (0.0011) -[2023-10-10 14:31:34,546][76543] Updated weights for policy 0, policy_version 47213 (0.0009) -[2023-10-10 14:31:34,919][76543] Updated weights for policy 0, policy_version 47223 (0.0010) -[2023-10-10 14:31:36,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 96665600. Throughput: 0: 1822.2, 1: 1832.0. Samples: 24167568. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-10 14:31:36,076][75634] Avg episode reward: [(0, '33.930'), (1, '33.790')] -[2023-10-10 14:31:37,461][76542] Updated weights for policy 1, policy_version 47170 (0.0010) -[2023-10-10 14:31:37,827][76542] Updated weights for policy 1, policy_version 47180 (0.0008) -[2023-10-10 14:31:38,195][76542] Updated weights for policy 1, policy_version 47190 (0.0010) -[2023-10-10 14:31:38,477][76543] Updated weights for policy 0, policy_version 47233 (0.0009) -[2023-10-10 14:31:38,562][76542] Updated weights for policy 1, policy_version 47200 (0.0009) -[2023-10-10 14:31:38,851][76543] Updated weights for policy 0, policy_version 47243 (0.0010) -[2023-10-10 14:31:39,225][76543] Updated weights for policy 0, policy_version 47253 (0.0011) -[2023-10-10 14:31:39,599][76543] Updated weights for policy 0, policy_version 47263 (0.0010) -[2023-10-10 14:31:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 96731136. Throughput: 0: 1812.8, 1: 1831.4. Samples: 24189272. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-10 14:31:41,077][75634] Avg episode reward: [(0, '36.310'), (1, '33.510')] -[2023-10-10 14:31:42,254][76542] Updated weights for policy 1, policy_version 47210 (0.0010) -[2023-10-10 14:31:42,617][76542] Updated weights for policy 1, policy_version 47220 (0.0009) -[2023-10-10 14:31:42,986][76542] Updated weights for policy 1, policy_version 47230 (0.0008) -[2023-10-10 14:31:43,380][76543] Updated weights for policy 0, policy_version 47273 (0.0010) -[2023-10-10 14:31:43,746][76543] Updated weights for policy 0, policy_version 47283 (0.0009) -[2023-10-10 14:31:44,121][76543] Updated weights for policy 0, policy_version 47293 (0.0010) -[2023-10-10 14:31:46,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 96796672. Throughput: 0: 1812.1, 1: 1823.5. Samples: 24211364. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-10 14:31:46,077][75634] Avg episode reward: [(0, '38.210'), (1, '33.630')] -[2023-10-10 14:31:46,667][76542] Updated weights for policy 1, policy_version 47240 (0.0007) -[2023-10-10 14:31:47,030][76542] Updated weights for policy 1, policy_version 47250 (0.0007) -[2023-10-10 14:31:47,406][76542] Updated weights for policy 1, policy_version 47260 (0.0008) -[2023-10-10 14:31:47,848][76543] Updated weights for policy 0, policy_version 47303 (0.0009) -[2023-10-10 14:31:48,220][76543] Updated weights for policy 0, policy_version 47313 (0.0007) -[2023-10-10 14:31:48,601][76543] Updated weights for policy 0, policy_version 47323 (0.0007) -[2023-10-10 14:31:50,993][76542] Updated weights for policy 1, policy_version 47270 (0.0011) -[2023-10-10 14:31:51,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 96862208. Throughput: 0: 1814.3, 1: 1821.6. Samples: 24222010. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-10 14:31:51,076][75634] Avg episode reward: [(0, '34.140'), (1, '27.870')] -[2023-10-10 14:31:51,368][76542] Updated weights for policy 1, policy_version 47280 (0.0010) -[2023-10-10 14:31:51,734][76542] Updated weights for policy 1, policy_version 47290 (0.0010) -[2023-10-10 14:31:52,328][76543] Updated weights for policy 0, policy_version 47333 (0.0007) -[2023-10-10 14:31:52,695][76543] Updated weights for policy 0, policy_version 47343 (0.0007) -[2023-10-10 14:31:53,064][76543] Updated weights for policy 0, policy_version 47353 (0.0007) -[2023-10-10 14:31:55,562][76542] Updated weights for policy 1, policy_version 47300 (0.0010) -[2023-10-10 14:31:55,935][76542] Updated weights for policy 1, policy_version 47310 (0.0010) -[2023-10-10 14:31:56,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 96927744. Throughput: 0: 1819.8, 1: 1813.2. Samples: 24244078. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:31:56,077][75634] Avg episode reward: [(0, '34.550'), (1, '30.120')] -[2023-10-10 14:31:56,315][76542] Updated weights for policy 1, policy_version 47320 (0.0011) -[2023-10-10 14:31:56,716][76543] Updated weights for policy 0, policy_version 47363 (0.0009) -[2023-10-10 14:31:57,119][76543] Updated weights for policy 0, policy_version 47373 (0.0009) -[2023-10-10 14:31:57,492][76543] Updated weights for policy 0, policy_version 47383 (0.0007) -[2023-10-10 14:31:59,765][76542] Updated weights for policy 1, policy_version 47330 (0.0008) -[2023-10-10 14:32:00,144][76542] Updated weights for policy 1, policy_version 47340 (0.0008) -[2023-10-10 14:32:00,510][76542] Updated weights for policy 1, policy_version 47350 (0.0010) -[2023-10-10 14:32:00,879][76542] Updated weights for policy 1, policy_version 47360 (0.0009) -[2023-10-10 14:32:01,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 97026048. Throughput: 0: 1823.5, 1: 1822.6. Samples: 24266010. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:32:01,076][75634] Avg episode reward: [(0, '37.630'), (1, '31.360')] -[2023-10-10 14:32:01,127][76543] Updated weights for policy 0, policy_version 47393 (0.0008) -[2023-10-10 14:32:01,495][76543] Updated weights for policy 0, policy_version 47403 (0.0008) -[2023-10-10 14:32:01,869][76543] Updated weights for policy 0, policy_version 47413 (0.0008) -[2023-10-10 14:32:02,239][76543] Updated weights for policy 0, policy_version 47423 (0.0007) -[2023-10-10 14:32:04,419][76542] Updated weights for policy 1, policy_version 47370 (0.0007) -[2023-10-10 14:32:04,787][76542] Updated weights for policy 1, policy_version 47380 (0.0008) -[2023-10-10 14:32:05,155][76542] Updated weights for policy 1, policy_version 47390 (0.0009) -[2023-10-10 14:32:05,894][76543] Updated weights for policy 0, policy_version 47433 (0.0008) -[2023-10-10 14:32:06,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 97091584. Throughput: 0: 1825.3, 1: 1826.1. Samples: 24277376. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:32:06,076][75634] Avg episode reward: [(0, '41.390'), (1, '34.890')] -[2023-10-10 14:32:06,266][76543] Updated weights for policy 0, policy_version 47443 (0.0010) -[2023-10-10 14:32:06,630][76543] Updated weights for policy 0, policy_version 47453 (0.0007) -[2023-10-10 14:32:08,796][76542] Updated weights for policy 1, policy_version 47400 (0.0008) -[2023-10-10 14:32:09,156][76542] Updated weights for policy 1, policy_version 47410 (0.0009) -[2023-10-10 14:32:09,528][76542] Updated weights for policy 1, policy_version 47420 (0.0008) -[2023-10-10 14:32:10,180][76543] Updated weights for policy 0, policy_version 47463 (0.0010) -[2023-10-10 14:32:10,553][76543] Updated weights for policy 0, policy_version 47473 (0.0009) -[2023-10-10 14:32:10,921][76543] Updated weights for policy 0, policy_version 47483 (0.0009) -[2023-10-10 14:32:11,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 97157120. Throughput: 0: 1824.0, 1: 1826.8. Samples: 24299000. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:32:11,077][75634] Avg episode reward: [(0, '40.610'), (1, '34.120')] -[2023-10-10 14:32:13,248][76542] Updated weights for policy 1, policy_version 47430 (0.0008) -[2023-10-10 14:32:13,621][76542] Updated weights for policy 1, policy_version 47440 (0.0008) -[2023-10-10 14:32:13,992][76542] Updated weights for policy 1, policy_version 47450 (0.0009) -[2023-10-10 14:32:14,419][76543] Updated weights for policy 0, policy_version 47493 (0.0009) -[2023-10-10 14:32:14,785][76543] Updated weights for policy 0, policy_version 47503 (0.0010) -[2023-10-10 14:32:15,162][76543] Updated weights for policy 0, policy_version 47513 (0.0010) -[2023-10-10 14:32:16,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 97255424. Throughput: 0: 1827.7, 1: 1829.8. Samples: 24321102. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:32:16,076][75634] Avg episode reward: [(0, '36.660'), (1, '32.740')] -[2023-10-10 14:32:17,564][76542] Updated weights for policy 1, policy_version 47460 (0.0008) -[2023-10-10 14:32:17,932][76542] Updated weights for policy 1, policy_version 47470 (0.0008) -[2023-10-10 14:32:18,303][76542] Updated weights for policy 1, policy_version 47480 (0.0007) -[2023-10-10 14:32:18,858][76543] Updated weights for policy 0, policy_version 47523 (0.0009) -[2023-10-10 14:32:19,232][76543] Updated weights for policy 0, policy_version 47533 (0.0008) -[2023-10-10 14:32:19,608][76543] Updated weights for policy 0, policy_version 47543 (0.0010) -[2023-10-10 14:32:21,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 97320960. Throughput: 0: 1837.7, 1: 1823.8. Samples: 24332338. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:32:21,077][75634] Avg episode reward: [(0, '38.090'), (1, '33.490')] -[2023-10-10 14:32:22,297][76542] Updated weights for policy 1, policy_version 47490 (0.0008) -[2023-10-10 14:32:22,660][76542] Updated weights for policy 1, policy_version 47500 (0.0009) -[2023-10-10 14:32:23,030][76542] Updated weights for policy 1, policy_version 47510 (0.0009) -[2023-10-10 14:32:23,142][76543] Updated weights for policy 0, policy_version 47553 (0.0010) -[2023-10-10 14:32:23,403][76542] Updated weights for policy 1, policy_version 47520 (0.0008) -[2023-10-10 14:32:23,501][76543] Updated weights for policy 0, policy_version 47563 (0.0009) -[2023-10-10 14:32:23,886][76543] Updated weights for policy 0, policy_version 47573 (0.0007) -[2023-10-10 14:32:24,248][76543] Updated weights for policy 0, policy_version 47583 (0.0007) -[2023-10-10 14:32:26,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 97386496. Throughput: 0: 1827.2, 1: 1825.0. Samples: 24353618. Policy #0 lag: (min: 25.0, avg: 38.2, max: 57.0) -[2023-10-10 14:32:26,077][75634] Avg episode reward: [(0, '37.880'), (1, '36.160')] -[2023-10-10 14:32:27,015][76542] Updated weights for policy 1, policy_version 47530 (0.0008) -[2023-10-10 14:32:27,377][76542] Updated weights for policy 1, policy_version 47540 (0.0008) -[2023-10-10 14:32:27,742][76542] Updated weights for policy 1, policy_version 47550 (0.0007) -[2023-10-10 14:32:27,890][76543] Updated weights for policy 0, policy_version 47593 (0.0009) -[2023-10-10 14:32:28,276][76543] Updated weights for policy 0, policy_version 47603 (0.0011) -[2023-10-10 14:32:28,646][76543] Updated weights for policy 0, policy_version 47613 (0.0011) -[2023-10-10 14:32:31,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 97452032. Throughput: 0: 1838.8, 1: 1825.8. Samples: 24376272. Policy #0 lag: (min: 25.0, avg: 38.2, max: 57.0) -[2023-10-10 14:32:31,076][75634] Avg episode reward: [(0, '32.590'), (1, '32.320')] -[2023-10-10 14:32:31,083][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000047616_48758784.pth... -[2023-10-10 14:32:31,118][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000045920_47022080.pth -[2023-10-10 14:32:31,326][76542] Updated weights for policy 1, policy_version 47560 (0.0008) -[2023-10-10 14:32:31,690][76542] Updated weights for policy 1, policy_version 47570 (0.0011) -[2023-10-10 14:32:32,065][76542] Updated weights for policy 1, policy_version 47580 (0.0009) -[2023-10-10 14:32:32,212][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000047584_48726016.pth... -[2023-10-10 14:32:32,249][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000045856_46956544.pth -[2023-10-10 14:32:32,351][76543] Updated weights for policy 0, policy_version 47623 (0.0010) -[2023-10-10 14:32:32,722][76543] Updated weights for policy 0, policy_version 47633 (0.0010) -[2023-10-10 14:32:33,095][76543] Updated weights for policy 0, policy_version 47643 (0.0011) -[2023-10-10 14:32:35,731][76542] Updated weights for policy 1, policy_version 47590 (0.0007) -[2023-10-10 14:32:36,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 97517568. Throughput: 0: 1822.3, 1: 1826.7. Samples: 24386216. Policy #0 lag: (min: 25.0, avg: 38.2, max: 57.0) -[2023-10-10 14:32:36,077][75634] Avg episode reward: [(0, '31.210'), (1, '34.300')] -[2023-10-10 14:32:36,095][76542] Updated weights for policy 1, policy_version 47600 (0.0007) -[2023-10-10 14:32:36,458][76542] Updated weights for policy 1, policy_version 47610 (0.0007) -[2023-10-10 14:32:36,803][76543] Updated weights for policy 0, policy_version 47653 (0.0008) -[2023-10-10 14:32:37,182][76543] Updated weights for policy 0, policy_version 47663 (0.0007) -[2023-10-10 14:32:37,551][76543] Updated weights for policy 0, policy_version 47673 (0.0010) -[2023-10-10 14:32:40,133][76542] Updated weights for policy 1, policy_version 47620 (0.0007) -[2023-10-10 14:32:40,503][76542] Updated weights for policy 1, policy_version 47630 (0.0009) -[2023-10-10 14:32:40,870][76542] Updated weights for policy 1, policy_version 47640 (0.0008) -[2023-10-10 14:32:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 97583104. Throughput: 0: 1832.9, 1: 1830.5. Samples: 24408930. Policy #0 lag: (min: 25.0, avg: 38.2, max: 57.0) -[2023-10-10 14:32:41,076][75634] Avg episode reward: [(0, '34.350'), (1, '33.910')] -[2023-10-10 14:32:41,490][76543] Updated weights for policy 0, policy_version 47683 (0.0010) -[2023-10-10 14:32:41,884][76543] Updated weights for policy 0, policy_version 47693 (0.0009) -[2023-10-10 14:32:42,245][76543] Updated weights for policy 0, policy_version 47703 (0.0007) -[2023-10-10 14:32:44,458][76542] Updated weights for policy 1, policy_version 47650 (0.0007) -[2023-10-10 14:32:44,828][76542] Updated weights for policy 1, policy_version 47660 (0.0009) -[2023-10-10 14:32:45,195][76542] Updated weights for policy 1, policy_version 47670 (0.0007) -[2023-10-10 14:32:45,555][76542] Updated weights for policy 1, policy_version 47680 (0.0009) -[2023-10-10 14:32:45,987][76543] Updated weights for policy 0, policy_version 47713 (0.0007) -[2023-10-10 14:32:46,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 97681408. Throughput: 0: 1833.2, 1: 1820.7. Samples: 24430434. Policy #0 lag: (min: 25.0, avg: 38.2, max: 57.0) -[2023-10-10 14:32:46,077][75634] Avg episode reward: [(0, '35.780'), (1, '36.430')] -[2023-10-10 14:32:46,359][76543] Updated weights for policy 0, policy_version 47723 (0.0008) -[2023-10-10 14:32:46,727][76543] Updated weights for policy 0, policy_version 47733 (0.0008) -[2023-10-10 14:32:47,101][76543] Updated weights for policy 0, policy_version 47743 (0.0009) -[2023-10-10 14:32:49,313][76542] Updated weights for policy 1, policy_version 47690 (0.0008) -[2023-10-10 14:32:49,689][76542] Updated weights for policy 1, policy_version 47700 (0.0007) -[2023-10-10 14:32:50,053][76542] Updated weights for policy 1, policy_version 47710 (0.0009) -[2023-10-10 14:32:50,718][76543] Updated weights for policy 0, policy_version 47753 (0.0008) -[2023-10-10 14:32:51,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 97746944. Throughput: 0: 1830.2, 1: 1822.0. Samples: 24441726. Policy #0 lag: (min: 25.0, avg: 38.2, max: 57.0) -[2023-10-10 14:32:51,077][75634] Avg episode reward: [(0, '34.660'), (1, '39.710')] -[2023-10-10 14:32:51,091][76543] Updated weights for policy 0, policy_version 47763 (0.0008) -[2023-10-10 14:32:51,453][76543] Updated weights for policy 0, policy_version 47773 (0.0008) -[2023-10-10 14:32:53,768][76542] Updated weights for policy 1, policy_version 47720 (0.0009) -[2023-10-10 14:32:54,127][76542] Updated weights for policy 1, policy_version 47730 (0.0007) -[2023-10-10 14:32:54,506][76542] Updated weights for policy 1, policy_version 47740 (0.0009) -[2023-10-10 14:32:55,238][76543] Updated weights for policy 0, policy_version 47783 (0.0008) -[2023-10-10 14:32:55,607][76543] Updated weights for policy 0, policy_version 47793 (0.0009) -[2023-10-10 14:32:55,978][76543] Updated weights for policy 0, policy_version 47803 (0.0012) -[2023-10-10 14:32:56,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 97812480. Throughput: 0: 1831.6, 1: 1817.3. Samples: 24463202. Policy #0 lag: (min: 25.0, avg: 38.2, max: 57.0) -[2023-10-10 14:32:56,076][75634] Avg episode reward: [(0, '34.260'), (1, '37.380')] -[2023-10-10 14:32:58,098][76542] Updated weights for policy 1, policy_version 47750 (0.0009) -[2023-10-10 14:32:58,478][76542] Updated weights for policy 1, policy_version 47760 (0.0010) -[2023-10-10 14:32:58,849][76542] Updated weights for policy 1, policy_version 47770 (0.0008) -[2023-10-10 14:32:59,561][76543] Updated weights for policy 0, policy_version 47813 (0.0008) -[2023-10-10 14:32:59,931][76543] Updated weights for policy 0, policy_version 47823 (0.0009) -[2023-10-10 14:33:00,311][76543] Updated weights for policy 0, policy_version 47833 (0.0009) -[2023-10-10 14:33:01,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 97910784. Throughput: 0: 1828.8, 1: 1817.9. Samples: 24485204. Policy #0 lag: (min: 24.0, avg: 45.6, max: 56.0) -[2023-10-10 14:33:01,077][75634] Avg episode reward: [(0, '34.810'), (1, '36.280')] -[2023-10-10 14:33:02,591][76542] Updated weights for policy 1, policy_version 47780 (0.0007) -[2023-10-10 14:33:02,956][76542] Updated weights for policy 1, policy_version 47790 (0.0008) -[2023-10-10 14:33:03,328][76542] Updated weights for policy 1, policy_version 47800 (0.0007) -[2023-10-10 14:33:03,956][76543] Updated weights for policy 0, policy_version 47843 (0.0008) -[2023-10-10 14:33:04,329][76543] Updated weights for policy 0, policy_version 47853 (0.0007) -[2023-10-10 14:33:04,689][76543] Updated weights for policy 0, policy_version 47863 (0.0010) -[2023-10-10 14:33:06,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 97976320. Throughput: 0: 1828.1, 1: 1814.6. Samples: 24496260. Policy #0 lag: (min: 24.0, avg: 45.6, max: 56.0) -[2023-10-10 14:33:06,077][75634] Avg episode reward: [(0, '37.080'), (1, '34.280')] -[2023-10-10 14:33:07,062][76542] Updated weights for policy 1, policy_version 47810 (0.0010) -[2023-10-10 14:33:07,436][76542] Updated weights for policy 1, policy_version 47820 (0.0008) -[2023-10-10 14:33:07,802][76542] Updated weights for policy 1, policy_version 47830 (0.0009) -[2023-10-10 14:33:08,166][76542] Updated weights for policy 1, policy_version 47840 (0.0010) -[2023-10-10 14:33:08,265][76543] Updated weights for policy 0, policy_version 47873 (0.0007) -[2023-10-10 14:33:08,636][76543] Updated weights for policy 0, policy_version 47883 (0.0007) -[2023-10-10 14:33:09,007][76543] Updated weights for policy 0, policy_version 47893 (0.0007) -[2023-10-10 14:33:09,383][76543] Updated weights for policy 0, policy_version 47903 (0.0007) -[2023-10-10 14:33:11,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 98041856. Throughput: 0: 1833.8, 1: 1823.4. Samples: 24518190. Policy #0 lag: (min: 24.0, avg: 45.6, max: 56.0) -[2023-10-10 14:33:11,077][75634] Avg episode reward: [(0, '38.320'), (1, '35.400')] -[2023-10-10 14:33:11,837][76542] Updated weights for policy 1, policy_version 47850 (0.0010) -[2023-10-10 14:33:12,210][76542] Updated weights for policy 1, policy_version 47860 (0.0007) -[2023-10-10 14:33:12,585][76542] Updated weights for policy 1, policy_version 47870 (0.0008) -[2023-10-10 14:33:12,991][76543] Updated weights for policy 0, policy_version 47913 (0.0008) -[2023-10-10 14:33:13,365][76543] Updated weights for policy 0, policy_version 47923 (0.0008) -[2023-10-10 14:33:13,726][76543] Updated weights for policy 0, policy_version 47933 (0.0009) -[2023-10-10 14:33:16,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 98107392. Throughput: 0: 1830.5, 1: 1826.0. Samples: 24540812. Policy #0 lag: (min: 24.0, avg: 45.6, max: 56.0) -[2023-10-10 14:33:16,077][75634] Avg episode reward: [(0, '36.910'), (1, '34.450')] -[2023-10-10 14:33:16,223][76542] Updated weights for policy 1, policy_version 47880 (0.0008) -[2023-10-10 14:33:16,607][76542] Updated weights for policy 1, policy_version 47890 (0.0007) -[2023-10-10 14:33:16,973][76542] Updated weights for policy 1, policy_version 47900 (0.0008) -[2023-10-10 14:33:17,484][76543] Updated weights for policy 0, policy_version 47943 (0.0009) -[2023-10-10 14:33:17,853][76543] Updated weights for policy 0, policy_version 47953 (0.0008) -[2023-10-10 14:33:18,225][76543] Updated weights for policy 0, policy_version 47963 (0.0008) -[2023-10-10 14:33:20,517][76542] Updated weights for policy 1, policy_version 47910 (0.0009) -[2023-10-10 14:33:20,885][76542] Updated weights for policy 1, policy_version 47920 (0.0007) -[2023-10-10 14:33:21,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 98172928. Throughput: 0: 1832.7, 1: 1827.9. Samples: 24550944. Policy #0 lag: (min: 24.0, avg: 45.6, max: 56.0) -[2023-10-10 14:33:21,076][75634] Avg episode reward: [(0, '38.500'), (1, '31.790')] -[2023-10-10 14:33:21,251][76542] Updated weights for policy 1, policy_version 47930 (0.0007) -[2023-10-10 14:33:22,005][76543] Updated weights for policy 0, policy_version 47973 (0.0008) -[2023-10-10 14:33:22,376][76543] Updated weights for policy 0, policy_version 47983 (0.0007) -[2023-10-10 14:33:22,743][76543] Updated weights for policy 0, policy_version 47993 (0.0008) -[2023-10-10 14:33:24,939][76542] Updated weights for policy 1, policy_version 47940 (0.0007) -[2023-10-10 14:33:25,313][76542] Updated weights for policy 1, policy_version 47950 (0.0009) -[2023-10-10 14:33:25,683][76542] Updated weights for policy 1, policy_version 47960 (0.0008) -[2023-10-10 14:33:26,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 98271232. Throughput: 0: 1828.7, 1: 1830.8. Samples: 24573610. Policy #0 lag: (min: 24.0, avg: 45.6, max: 56.0) -[2023-10-10 14:33:26,077][75634] Avg episode reward: [(0, '37.490'), (1, '33.970')] -[2023-10-10 14:33:26,403][76543] Updated weights for policy 0, policy_version 48003 (0.0010) -[2023-10-10 14:33:26,793][76543] Updated weights for policy 0, policy_version 48013 (0.0008) -[2023-10-10 14:33:27,164][76543] Updated weights for policy 0, policy_version 48023 (0.0008) -[2023-10-10 14:33:29,353][76542] Updated weights for policy 1, policy_version 47970 (0.0009) -[2023-10-10 14:33:29,714][76542] Updated weights for policy 1, policy_version 47980 (0.0008) -[2023-10-10 14:33:30,093][76542] Updated weights for policy 1, policy_version 47990 (0.0010) -[2023-10-10 14:33:30,456][76542] Updated weights for policy 1, policy_version 48000 (0.0011) -[2023-10-10 14:33:30,741][76543] Updated weights for policy 0, policy_version 48033 (0.0008) -[2023-10-10 14:33:31,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 98336768. Throughput: 0: 1832.7, 1: 1827.0. Samples: 24595120. Policy #0 lag: (min: 11.0, avg: 11.9, max: 32.0) -[2023-10-10 14:33:31,077][75634] Avg episode reward: [(0, '38.620'), (1, '37.650')] -[2023-10-10 14:33:31,112][76543] Updated weights for policy 0, policy_version 48043 (0.0007) -[2023-10-10 14:33:31,482][76543] Updated weights for policy 0, policy_version 48053 (0.0008) -[2023-10-10 14:33:31,857][76543] Updated weights for policy 0, policy_version 48063 (0.0007) -[2023-10-10 14:33:34,300][76542] Updated weights for policy 1, policy_version 48010 (0.0009) -[2023-10-10 14:33:34,671][76542] Updated weights for policy 1, policy_version 48020 (0.0008) -[2023-10-10 14:33:35,047][76542] Updated weights for policy 1, policy_version 48030 (0.0008) -[2023-10-10 14:33:35,456][76543] Updated weights for policy 0, policy_version 48073 (0.0009) -[2023-10-10 14:33:35,831][76543] Updated weights for policy 0, policy_version 48083 (0.0008) -[2023-10-10 14:33:36,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 98402304. Throughput: 0: 1835.7, 1: 1824.0. Samples: 24606410. Policy #0 lag: (min: 11.0, avg: 11.9, max: 32.0) -[2023-10-10 14:33:36,076][75634] Avg episode reward: [(0, '35.540'), (1, '36.420')] -[2023-10-10 14:33:36,201][76543] Updated weights for policy 0, policy_version 48093 (0.0008) -[2023-10-10 14:33:38,531][76542] Updated weights for policy 1, policy_version 48040 (0.0010) -[2023-10-10 14:33:38,895][76542] Updated weights for policy 1, policy_version 48050 (0.0010) -[2023-10-10 14:33:39,264][76542] Updated weights for policy 1, policy_version 48060 (0.0011) -[2023-10-10 14:33:39,772][76543] Updated weights for policy 0, policy_version 48103 (0.0007) -[2023-10-10 14:33:40,142][76543] Updated weights for policy 0, policy_version 48113 (0.0007) -[2023-10-10 14:33:40,509][76543] Updated weights for policy 0, policy_version 48123 (0.0007) -[2023-10-10 14:33:41,076][75634] Fps is (10 sec: 16384.3, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 98500608. Throughput: 0: 1837.6, 1: 1831.6. Samples: 24628316. Policy #0 lag: (min: 11.0, avg: 11.9, max: 32.0) -[2023-10-10 14:33:41,076][75634] Avg episode reward: [(0, '36.030'), (1, '33.980')] -[2023-10-10 14:33:43,122][76542] Updated weights for policy 1, policy_version 48070 (0.0009) -[2023-10-10 14:33:43,511][76542] Updated weights for policy 1, policy_version 48080 (0.0009) -[2023-10-10 14:33:43,888][76542] Updated weights for policy 1, policy_version 48090 (0.0011) -[2023-10-10 14:33:44,164][76543] Updated weights for policy 0, policy_version 48133 (0.0009) -[2023-10-10 14:33:44,543][76543] Updated weights for policy 0, policy_version 48143 (0.0009) -[2023-10-10 14:33:44,904][76543] Updated weights for policy 0, policy_version 48153 (0.0010) -[2023-10-10 14:33:46,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 98566144. Throughput: 0: 1824.8, 1: 1820.0. Samples: 24649222. Policy #0 lag: (min: 11.0, avg: 11.9, max: 32.0) -[2023-10-10 14:33:46,077][75634] Avg episode reward: [(0, '32.390'), (1, '34.200')] -[2023-10-10 14:33:47,535][76542] Updated weights for policy 1, policy_version 48100 (0.0007) -[2023-10-10 14:33:47,910][76542] Updated weights for policy 1, policy_version 48110 (0.0008) -[2023-10-10 14:33:48,280][76542] Updated weights for policy 1, policy_version 48120 (0.0010) -[2023-10-10 14:33:48,548][76543] Updated weights for policy 0, policy_version 48163 (0.0008) -[2023-10-10 14:33:48,923][76543] Updated weights for policy 0, policy_version 48173 (0.0008) -[2023-10-10 14:33:49,289][76543] Updated weights for policy 0, policy_version 48183 (0.0009) -[2023-10-10 14:33:51,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 98631680. Throughput: 0: 1833.2, 1: 1821.7. Samples: 24660728. Policy #0 lag: (min: 11.0, avg: 11.9, max: 32.0) -[2023-10-10 14:33:51,076][75634] Avg episode reward: [(0, '32.310'), (1, '34.410')] -[2023-10-10 14:33:52,122][76542] Updated weights for policy 1, policy_version 48130 (0.0011) -[2023-10-10 14:33:52,492][76542] Updated weights for policy 1, policy_version 48140 (0.0008) -[2023-10-10 14:33:52,853][76542] Updated weights for policy 1, policy_version 48150 (0.0007) -[2023-10-10 14:33:52,951][76543] Updated weights for policy 0, policy_version 48193 (0.0008) -[2023-10-10 14:33:53,222][76542] Updated weights for policy 1, policy_version 48160 (0.0009) -[2023-10-10 14:33:53,331][76543] Updated weights for policy 0, policy_version 48203 (0.0007) -[2023-10-10 14:33:53,702][76543] Updated weights for policy 0, policy_version 48213 (0.0010) -[2023-10-10 14:33:54,071][76543] Updated weights for policy 0, policy_version 48223 (0.0008) -[2023-10-10 14:33:56,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 98697216. Throughput: 0: 1817.3, 1: 1819.5. Samples: 24681844. Policy #0 lag: (min: 11.0, avg: 11.9, max: 32.0) -[2023-10-10 14:33:56,077][75634] Avg episode reward: [(0, '33.430'), (1, '34.530')] -[2023-10-10 14:33:56,922][76542] Updated weights for policy 1, policy_version 48170 (0.0010) -[2023-10-10 14:33:57,298][76542] Updated weights for policy 1, policy_version 48180 (0.0008) -[2023-10-10 14:33:57,659][76542] Updated weights for policy 1, policy_version 48190 (0.0007) -[2023-10-10 14:33:57,801][76543] Updated weights for policy 0, policy_version 48233 (0.0008) -[2023-10-10 14:33:58,168][76543] Updated weights for policy 0, policy_version 48243 (0.0009) -[2023-10-10 14:33:58,538][76543] Updated weights for policy 0, policy_version 48253 (0.0007) -[2023-10-10 14:34:01,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 98762752. Throughput: 0: 1824.4, 1: 1816.7. Samples: 24704662. Policy #0 lag: (min: 18.0, avg: 21.4, max: 50.0) -[2023-10-10 14:34:01,076][75634] Avg episode reward: [(0, '33.680'), (1, '34.860')] -[2023-10-10 14:34:01,460][76542] Updated weights for policy 1, policy_version 48200 (0.0007) -[2023-10-10 14:34:01,832][76542] Updated weights for policy 1, policy_version 48210 (0.0007) -[2023-10-10 14:34:02,180][76543] Updated weights for policy 0, policy_version 48263 (0.0007) -[2023-10-10 14:34:02,199][76542] Updated weights for policy 1, policy_version 48220 (0.0008) -[2023-10-10 14:34:02,553][76543] Updated weights for policy 0, policy_version 48273 (0.0007) -[2023-10-10 14:34:02,916][76543] Updated weights for policy 0, policy_version 48283 (0.0008) -[2023-10-10 14:34:06,034][76542] Updated weights for policy 1, policy_version 48230 (0.0009) -[2023-10-10 14:34:06,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 98828288. Throughput: 0: 1821.9, 1: 1812.3. Samples: 24714484. Policy #0 lag: (min: 18.0, avg: 21.4, max: 50.0) -[2023-10-10 14:34:06,077][75634] Avg episode reward: [(0, '37.290'), (1, '33.670')] -[2023-10-10 14:34:06,404][76542] Updated weights for policy 1, policy_version 48240 (0.0007) -[2023-10-10 14:34:06,546][76543] Updated weights for policy 0, policy_version 48293 (0.0009) -[2023-10-10 14:34:06,770][76542] Updated weights for policy 1, policy_version 48250 (0.0008) -[2023-10-10 14:34:06,914][76543] Updated weights for policy 0, policy_version 48303 (0.0008) -[2023-10-10 14:34:07,289][76543] Updated weights for policy 0, policy_version 48313 (0.0008) -[2023-10-10 14:34:10,436][76542] Updated weights for policy 1, policy_version 48260 (0.0009) -[2023-10-10 14:34:10,815][76542] Updated weights for policy 1, policy_version 48270 (0.0008) -[2023-10-10 14:34:10,972][76543] Updated weights for policy 0, policy_version 48323 (0.0008) -[2023-10-10 14:34:11,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 98893824. Throughput: 0: 1827.9, 1: 1807.5. Samples: 24737200. Policy #0 lag: (min: 18.0, avg: 21.4, max: 50.0) -[2023-10-10 14:34:11,076][75634] Avg episode reward: [(0, '33.370'), (1, '36.480')] -[2023-10-10 14:34:11,176][76542] Updated weights for policy 1, policy_version 48280 (0.0008) -[2023-10-10 14:34:11,344][76543] Updated weights for policy 0, policy_version 48333 (0.0007) -[2023-10-10 14:34:11,714][76543] Updated weights for policy 0, policy_version 48343 (0.0007) -[2023-10-10 14:34:14,861][76542] Updated weights for policy 1, policy_version 48290 (0.0007) -[2023-10-10 14:34:15,233][76542] Updated weights for policy 1, policy_version 48300 (0.0010) -[2023-10-10 14:34:15,600][76542] Updated weights for policy 1, policy_version 48310 (0.0009) -[2023-10-10 14:34:15,642][76543] Updated weights for policy 0, policy_version 48353 (0.0007) -[2023-10-10 14:34:15,963][76542] Updated weights for policy 1, policy_version 48320 (0.0009) -[2023-10-10 14:34:16,041][76543] Updated weights for policy 0, policy_version 48363 (0.0007) -[2023-10-10 14:34:16,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 98992128. Throughput: 0: 1818.4, 1: 1812.0. Samples: 24758488. Policy #0 lag: (min: 18.0, avg: 21.4, max: 50.0) -[2023-10-10 14:34:16,076][75634] Avg episode reward: [(0, '35.290'), (1, '36.240')] -[2023-10-10 14:34:16,418][76543] Updated weights for policy 0, policy_version 48373 (0.0007) -[2023-10-10 14:34:16,791][76543] Updated weights for policy 0, policy_version 48383 (0.0008) -[2023-10-10 14:34:19,715][76542] Updated weights for policy 1, policy_version 48330 (0.0009) -[2023-10-10 14:34:20,082][76542] Updated weights for policy 1, policy_version 48340 (0.0009) -[2023-10-10 14:34:20,453][76542] Updated weights for policy 1, policy_version 48350 (0.0009) -[2023-10-10 14:34:20,499][76543] Updated weights for policy 0, policy_version 48393 (0.0009) -[2023-10-10 14:34:20,870][76543] Updated weights for policy 0, policy_version 48403 (0.0009) -[2023-10-10 14:34:21,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 99057664. Throughput: 0: 1815.5, 1: 1804.4. Samples: 24769306. Policy #0 lag: (min: 18.0, avg: 21.4, max: 50.0) -[2023-10-10 14:34:21,076][75634] Avg episode reward: [(0, '35.970'), (1, '34.670')] -[2023-10-10 14:34:21,241][76543] Updated weights for policy 0, policy_version 48413 (0.0008) -[2023-10-10 14:34:24,042][76542] Updated weights for policy 1, policy_version 48360 (0.0009) -[2023-10-10 14:34:24,406][76542] Updated weights for policy 1, policy_version 48370 (0.0009) -[2023-10-10 14:34:24,779][76542] Updated weights for policy 1, policy_version 48380 (0.0007) -[2023-10-10 14:34:24,990][76543] Updated weights for policy 0, policy_version 48423 (0.0010) -[2023-10-10 14:34:25,372][76543] Updated weights for policy 0, policy_version 48433 (0.0009) -[2023-10-10 14:34:25,731][76543] Updated weights for policy 0, policy_version 48443 (0.0009) -[2023-10-10 14:34:26,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 99155968. Throughput: 0: 1806.1, 1: 1808.3. Samples: 24790964. Policy #0 lag: (min: 18.0, avg: 21.4, max: 50.0) -[2023-10-10 14:34:26,077][75634] Avg episode reward: [(0, '34.830'), (1, '32.990')] -[2023-10-10 14:34:28,483][76542] Updated weights for policy 1, policy_version 48390 (0.0007) -[2023-10-10 14:34:28,851][76542] Updated weights for policy 1, policy_version 48400 (0.0007) -[2023-10-10 14:34:29,210][76542] Updated weights for policy 1, policy_version 48410 (0.0009) -[2023-10-10 14:34:29,434][76543] Updated weights for policy 0, policy_version 48453 (0.0008) -[2023-10-10 14:34:29,799][76543] Updated weights for policy 0, policy_version 48463 (0.0010) -[2023-10-10 14:34:30,184][76543] Updated weights for policy 0, policy_version 48473 (0.0008) -[2023-10-10 14:34:31,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 99221504. Throughput: 0: 1814.5, 1: 1813.8. Samples: 24812496. Policy #0 lag: (min: 25.0, avg: 33.5, max: 57.0) -[2023-10-10 14:34:31,076][75634] Avg episode reward: [(0, '33.770'), (1, '36.050')] -[2023-10-10 14:34:31,083][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000048480_49643520.pth... -[2023-10-10 14:34:31,083][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000048416_49577984.pth... -[2023-10-10 14:34:31,116][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000046720_47841280.pth -[2023-10-10 14:34:31,121][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000046784_47906816.pth -[2023-10-10 14:34:32,758][76542] Updated weights for policy 1, policy_version 48420 (0.0008) -[2023-10-10 14:34:33,124][76542] Updated weights for policy 1, policy_version 48430 (0.0009) -[2023-10-10 14:34:33,507][76542] Updated weights for policy 1, policy_version 48440 (0.0009) -[2023-10-10 14:34:33,756][76543] Updated weights for policy 0, policy_version 48483 (0.0008) -[2023-10-10 14:34:34,114][76543] Updated weights for policy 0, policy_version 48493 (0.0009) -[2023-10-10 14:34:34,488][76543] Updated weights for policy 0, policy_version 48503 (0.0011) -[2023-10-10 14:34:36,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 99287040. Throughput: 0: 1807.3, 1: 1817.7. Samples: 24823854. Policy #0 lag: (min: 25.0, avg: 33.5, max: 57.0) -[2023-10-10 14:34:36,077][75634] Avg episode reward: [(0, '36.630'), (1, '36.680')] -[2023-10-10 14:34:37,147][76542] Updated weights for policy 1, policy_version 48450 (0.0009) -[2023-10-10 14:34:37,501][76542] Updated weights for policy 1, policy_version 48460 (0.0007) -[2023-10-10 14:34:37,877][76542] Updated weights for policy 1, policy_version 48470 (0.0008) -[2023-10-10 14:34:38,170][76543] Updated weights for policy 0, policy_version 48513 (0.0010) -[2023-10-10 14:34:38,245][76542] Updated weights for policy 1, policy_version 48480 (0.0007) -[2023-10-10 14:34:38,550][76543] Updated weights for policy 0, policy_version 48523 (0.0009) -[2023-10-10 14:34:38,922][76543] Updated weights for policy 0, policy_version 48533 (0.0009) -[2023-10-10 14:34:39,289][76543] Updated weights for policy 0, policy_version 48543 (0.0007) -[2023-10-10 14:34:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 99352576. Throughput: 0: 1815.6, 1: 1819.3. Samples: 24845410. Policy #0 lag: (min: 25.0, avg: 33.5, max: 57.0) -[2023-10-10 14:34:41,076][75634] Avg episode reward: [(0, '37.360'), (1, '34.250')] -[2023-10-10 14:34:41,902][76542] Updated weights for policy 1, policy_version 48490 (0.0008) -[2023-10-10 14:34:42,273][76542] Updated weights for policy 1, policy_version 48500 (0.0009) -[2023-10-10 14:34:42,644][76542] Updated weights for policy 1, policy_version 48510 (0.0008) -[2023-10-10 14:34:42,985][76543] Updated weights for policy 0, policy_version 48553 (0.0008) -[2023-10-10 14:34:43,360][76543] Updated weights for policy 0, policy_version 48563 (0.0007) -[2023-10-10 14:34:43,729][76543] Updated weights for policy 0, policy_version 48573 (0.0007) -[2023-10-10 14:34:46,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 99418112. Throughput: 0: 1817.9, 1: 1816.6. Samples: 24868212. Policy #0 lag: (min: 25.0, avg: 33.5, max: 57.0) -[2023-10-10 14:34:46,077][75634] Avg episode reward: [(0, '34.660'), (1, '35.230')] -[2023-10-10 14:34:46,365][76542] Updated weights for policy 1, policy_version 48520 (0.0008) -[2023-10-10 14:34:46,731][76542] Updated weights for policy 1, policy_version 48530 (0.0008) -[2023-10-10 14:34:47,097][76542] Updated weights for policy 1, policy_version 48540 (0.0009) -[2023-10-10 14:34:47,208][76543] Updated weights for policy 0, policy_version 48583 (0.0009) -[2023-10-10 14:34:47,575][76543] Updated weights for policy 0, policy_version 48593 (0.0009) -[2023-10-10 14:34:47,949][76543] Updated weights for policy 0, policy_version 48603 (0.0011) -[2023-10-10 14:34:50,701][76542] Updated weights for policy 1, policy_version 48550 (0.0009) -[2023-10-10 14:34:51,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 99483648. Throughput: 0: 1819.0, 1: 1821.4. Samples: 24878302. Policy #0 lag: (min: 25.0, avg: 33.5, max: 57.0) -[2023-10-10 14:34:51,077][75634] Avg episode reward: [(0, '34.530'), (1, '39.650')] -[2023-10-10 14:34:51,080][76542] Updated weights for policy 1, policy_version 48560 (0.0011) -[2023-10-10 14:34:51,437][76542] Updated weights for policy 1, policy_version 48570 (0.0009) -[2023-10-10 14:34:51,692][76543] Updated weights for policy 0, policy_version 48613 (0.0009) -[2023-10-10 14:34:52,062][76543] Updated weights for policy 0, policy_version 48623 (0.0007) -[2023-10-10 14:34:52,425][76543] Updated weights for policy 0, policy_version 48633 (0.0008) -[2023-10-10 14:34:55,103][76542] Updated weights for policy 1, policy_version 48580 (0.0008) -[2023-10-10 14:34:55,481][76542] Updated weights for policy 1, policy_version 48590 (0.0009) -[2023-10-10 14:34:55,853][76542] Updated weights for policy 1, policy_version 48600 (0.0009) -[2023-10-10 14:34:56,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 99549184. Throughput: 0: 1813.7, 1: 1828.8. Samples: 24901114. Policy #0 lag: (min: 25.0, avg: 33.5, max: 57.0) -[2023-10-10 14:34:56,077][75634] Avg episode reward: [(0, '38.960'), (1, '34.750')] -[2023-10-10 14:34:56,129][76543] Updated weights for policy 0, policy_version 48643 (0.0008) -[2023-10-10 14:34:56,490][76543] Updated weights for policy 0, policy_version 48653 (0.0010) -[2023-10-10 14:34:56,859][76543] Updated weights for policy 0, policy_version 48663 (0.0009) -[2023-10-10 14:34:59,619][76542] Updated weights for policy 1, policy_version 48610 (0.0007) -[2023-10-10 14:34:59,977][76542] Updated weights for policy 1, policy_version 48620 (0.0009) -[2023-10-10 14:35:00,347][76542] Updated weights for policy 1, policy_version 48630 (0.0008) -[2023-10-10 14:35:00,580][76543] Updated weights for policy 0, policy_version 48673 (0.0008) -[2023-10-10 14:35:00,718][76542] Updated weights for policy 1, policy_version 48640 (0.0008) -[2023-10-10 14:35:00,974][76543] Updated weights for policy 0, policy_version 48683 (0.0008) -[2023-10-10 14:35:01,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 99647488. Throughput: 0: 1818.8, 1: 1825.9. Samples: 24922500. Policy #0 lag: (min: 25.0, avg: 33.5, max: 57.0) -[2023-10-10 14:35:01,076][75634] Avg episode reward: [(0, '37.550'), (1, '35.080')] -[2023-10-10 14:35:01,347][76543] Updated weights for policy 0, policy_version 48693 (0.0010) -[2023-10-10 14:35:01,721][76543] Updated weights for policy 0, policy_version 48703 (0.0010) -[2023-10-10 14:35:04,392][76542] Updated weights for policy 1, policy_version 48650 (0.0008) -[2023-10-10 14:35:04,760][76542] Updated weights for policy 1, policy_version 48660 (0.0008) -[2023-10-10 14:35:05,123][76542] Updated weights for policy 1, policy_version 48670 (0.0008) -[2023-10-10 14:35:05,440][76543] Updated weights for policy 0, policy_version 48713 (0.0009) -[2023-10-10 14:35:05,816][76543] Updated weights for policy 0, policy_version 48723 (0.0008) -[2023-10-10 14:35:06,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 99713024. Throughput: 0: 1817.6, 1: 1834.9. Samples: 24933670. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:35:06,080][75634] Avg episode reward: [(0, '36.620'), (1, '33.320')] -[2023-10-10 14:35:06,188][76543] Updated weights for policy 0, policy_version 48733 (0.0009) -[2023-10-10 14:35:08,916][76542] Updated weights for policy 1, policy_version 48680 (0.0011) -[2023-10-10 14:35:09,283][76542] Updated weights for policy 1, policy_version 48690 (0.0009) -[2023-10-10 14:35:09,663][76542] Updated weights for policy 1, policy_version 48700 (0.0010) -[2023-10-10 14:35:09,868][76543] Updated weights for policy 0, policy_version 48743 (0.0007) -[2023-10-10 14:35:10,238][76543] Updated weights for policy 0, policy_version 48753 (0.0009) -[2023-10-10 14:35:10,612][76543] Updated weights for policy 0, policy_version 48763 (0.0009) -[2023-10-10 14:35:11,076][75634] Fps is (10 sec: 16383.9, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 99811328. Throughput: 0: 1819.6, 1: 1828.0. Samples: 24955108. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:35:11,077][75634] Avg episode reward: [(0, '34.170'), (1, '39.000')] -[2023-10-10 14:35:13,395][76542] Updated weights for policy 1, policy_version 48710 (0.0008) -[2023-10-10 14:35:13,759][76542] Updated weights for policy 1, policy_version 48720 (0.0009) -[2023-10-10 14:35:14,130][76542] Updated weights for policy 1, policy_version 48730 (0.0010) -[2023-10-10 14:35:14,407][76543] Updated weights for policy 0, policy_version 48773 (0.0009) -[2023-10-10 14:35:14,773][76543] Updated weights for policy 0, policy_version 48783 (0.0011) -[2023-10-10 14:35:15,148][76543] Updated weights for policy 0, policy_version 48793 (0.0010) -[2023-10-10 14:35:16,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 99876864. Throughput: 0: 1816.1, 1: 1824.5. Samples: 24976324. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:35:16,077][75634] Avg episode reward: [(0, '33.860'), (1, '38.310')] -[2023-10-10 14:35:17,804][76542] Updated weights for policy 1, policy_version 48740 (0.0008) -[2023-10-10 14:35:18,185][76542] Updated weights for policy 1, policy_version 48750 (0.0011) -[2023-10-10 14:35:18,552][76542] Updated weights for policy 1, policy_version 48760 (0.0010) -[2023-10-10 14:35:18,887][76543] Updated weights for policy 0, policy_version 48803 (0.0009) -[2023-10-10 14:35:19,262][76543] Updated weights for policy 0, policy_version 48813 (0.0008) -[2023-10-10 14:35:19,633][76543] Updated weights for policy 0, policy_version 48823 (0.0008) -[2023-10-10 14:35:21,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 99942400. Throughput: 0: 1813.4, 1: 1825.3. Samples: 24987592. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:35:21,076][75634] Avg episode reward: [(0, '37.490'), (1, '34.780')] -[2023-10-10 14:35:22,138][76542] Updated weights for policy 1, policy_version 48770 (0.0008) -[2023-10-10 14:35:22,501][76542] Updated weights for policy 1, policy_version 48780 (0.0008) -[2023-10-10 14:35:22,865][76542] Updated weights for policy 1, policy_version 48790 (0.0008) -[2023-10-10 14:35:23,233][76542] Updated weights for policy 1, policy_version 48800 (0.0008) -[2023-10-10 14:35:23,248][76543] Updated weights for policy 0, policy_version 48833 (0.0009) -[2023-10-10 14:35:23,615][76543] Updated weights for policy 0, policy_version 48843 (0.0007) -[2023-10-10 14:35:23,992][76543] Updated weights for policy 0, policy_version 48853 (0.0011) -[2023-10-10 14:35:24,354][76543] Updated weights for policy 0, policy_version 48863 (0.0007) -[2023-10-10 14:35:26,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 100007936. Throughput: 0: 1817.1, 1: 1819.7. Samples: 25009064. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:35:26,077][75634] Avg episode reward: [(0, '32.450'), (1, '35.710')] -[2023-10-10 14:35:26,921][76542] Updated weights for policy 1, policy_version 48810 (0.0009) -[2023-10-10 14:35:27,300][76542] Updated weights for policy 1, policy_version 48820 (0.0011) -[2023-10-10 14:35:27,664][76542] Updated weights for policy 1, policy_version 48830 (0.0010) -[2023-10-10 14:35:28,099][76543] Updated weights for policy 0, policy_version 48873 (0.0010) -[2023-10-10 14:35:28,467][76543] Updated weights for policy 0, policy_version 48883 (0.0009) -[2023-10-10 14:35:28,845][76543] Updated weights for policy 0, policy_version 48893 (0.0009) -[2023-10-10 14:35:31,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 100073472. Throughput: 0: 1812.0, 1: 1821.1. Samples: 25031698. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:35:31,077][75634] Avg episode reward: [(0, '33.090'), (1, '38.200')] -[2023-10-10 14:35:31,430][76542] Updated weights for policy 1, policy_version 48840 (0.0008) -[2023-10-10 14:35:31,802][76542] Updated weights for policy 1, policy_version 48850 (0.0010) -[2023-10-10 14:35:32,169][76542] Updated weights for policy 1, policy_version 48860 (0.0008) -[2023-10-10 14:35:32,511][76543] Updated weights for policy 0, policy_version 48903 (0.0008) -[2023-10-10 14:35:32,889][76543] Updated weights for policy 0, policy_version 48913 (0.0009) -[2023-10-10 14:35:33,260][76543] Updated weights for policy 0, policy_version 48923 (0.0010) -[2023-10-10 14:35:35,787][76542] Updated weights for policy 1, policy_version 48870 (0.0007) -[2023-10-10 14:35:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 100139008. Throughput: 0: 1823.9, 1: 1820.0. Samples: 25042276. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 14:35:36,077][75634] Avg episode reward: [(0, '31.930'), (1, '36.220')] -[2023-10-10 14:35:36,149][76542] Updated weights for policy 1, policy_version 48880 (0.0007) -[2023-10-10 14:35:36,510][76542] Updated weights for policy 1, policy_version 48890 (0.0007) -[2023-10-10 14:35:36,926][76543] Updated weights for policy 0, policy_version 48933 (0.0010) -[2023-10-10 14:35:37,294][76543] Updated weights for policy 0, policy_version 48943 (0.0010) -[2023-10-10 14:35:37,668][76543] Updated weights for policy 0, policy_version 48953 (0.0010) -[2023-10-10 14:35:40,263][76542] Updated weights for policy 1, policy_version 48900 (0.0009) -[2023-10-10 14:35:40,629][76542] Updated weights for policy 1, policy_version 48910 (0.0008) -[2023-10-10 14:35:40,995][76542] Updated weights for policy 1, policy_version 48920 (0.0009) -[2023-10-10 14:35:41,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 100204544. Throughput: 0: 1825.0, 1: 1814.3. Samples: 25064884. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 14:35:41,076][75634] Avg episode reward: [(0, '36.220'), (1, '33.150')] -[2023-10-10 14:35:41,260][76543] Updated weights for policy 0, policy_version 48963 (0.0007) -[2023-10-10 14:35:41,628][76543] Updated weights for policy 0, policy_version 48973 (0.0008) -[2023-10-10 14:35:42,008][76543] Updated weights for policy 0, policy_version 48983 (0.0008) -[2023-10-10 14:35:44,732][76542] Updated weights for policy 1, policy_version 48930 (0.0009) -[2023-10-10 14:35:45,099][76542] Updated weights for policy 1, policy_version 48940 (0.0008) -[2023-10-10 14:35:45,465][76542] Updated weights for policy 1, policy_version 48950 (0.0009) -[2023-10-10 14:35:45,660][76543] Updated weights for policy 0, policy_version 48993 (0.0010) -[2023-10-10 14:35:45,830][76542] Updated weights for policy 1, policy_version 48960 (0.0008) -[2023-10-10 14:35:46,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 100302848. Throughput: 0: 1828.1, 1: 1815.2. Samples: 25086446. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 14:35:46,076][75634] Avg episode reward: [(0, '35.230'), (1, '32.440')] -[2023-10-10 14:35:46,089][76543] Updated weights for policy 0, policy_version 49003 (0.0007) -[2023-10-10 14:35:46,452][76543] Updated weights for policy 0, policy_version 49013 (0.0009) -[2023-10-10 14:35:46,827][76543] Updated weights for policy 0, policy_version 49023 (0.0010) -[2023-10-10 14:35:49,542][76542] Updated weights for policy 1, policy_version 48970 (0.0007) -[2023-10-10 14:35:49,907][76542] Updated weights for policy 1, policy_version 48980 (0.0007) -[2023-10-10 14:35:50,280][76542] Updated weights for policy 1, policy_version 48990 (0.0008) -[2023-10-10 14:35:50,498][76543] Updated weights for policy 0, policy_version 49033 (0.0009) -[2023-10-10 14:35:50,857][76543] Updated weights for policy 0, policy_version 49043 (0.0009) -[2023-10-10 14:35:51,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 100368384. Throughput: 0: 1823.1, 1: 1813.1. Samples: 25097300. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 14:35:51,077][75634] Avg episode reward: [(0, '35.380'), (1, '33.770')] -[2023-10-10 14:35:51,227][76543] Updated weights for policy 0, policy_version 49053 (0.0007) -[2023-10-10 14:35:53,987][76542] Updated weights for policy 1, policy_version 49000 (0.0007) -[2023-10-10 14:35:54,361][76542] Updated weights for policy 1, policy_version 49010 (0.0008) -[2023-10-10 14:35:54,723][76542] Updated weights for policy 1, policy_version 49020 (0.0008) -[2023-10-10 14:35:54,777][76543] Updated weights for policy 0, policy_version 49063 (0.0007) -[2023-10-10 14:35:55,146][76543] Updated weights for policy 0, policy_version 49073 (0.0010) -[2023-10-10 14:35:55,513][76543] Updated weights for policy 0, policy_version 49083 (0.0008) -[2023-10-10 14:35:56,076][75634] Fps is (10 sec: 16383.9, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 100466688. Throughput: 0: 1828.4, 1: 1814.3. Samples: 25119028. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 14:35:56,077][75634] Avg episode reward: [(0, '37.060'), (1, '33.900')] -[2023-10-10 14:35:58,386][76542] Updated weights for policy 1, policy_version 49030 (0.0008) -[2023-10-10 14:35:58,770][76542] Updated weights for policy 1, policy_version 49040 (0.0007) -[2023-10-10 14:35:58,968][76543] Updated weights for policy 0, policy_version 49093 (0.0007) -[2023-10-10 14:35:59,146][76542] Updated weights for policy 1, policy_version 49050 (0.0007) -[2023-10-10 14:35:59,325][76543] Updated weights for policy 0, policy_version 49103 (0.0007) -[2023-10-10 14:35:59,696][76543] Updated weights for policy 0, policy_version 49113 (0.0008) -[2023-10-10 14:36:01,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 100532224. Throughput: 0: 1830.4, 1: 1819.1. Samples: 25140550. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 14:36:01,077][75634] Avg episode reward: [(0, '38.450'), (1, '34.880')] -[2023-10-10 14:36:02,813][76542] Updated weights for policy 1, policy_version 49060 (0.0009) -[2023-10-10 14:36:03,169][76542] Updated weights for policy 1, policy_version 49070 (0.0009) -[2023-10-10 14:36:03,488][76543] Updated weights for policy 0, policy_version 49123 (0.0009) -[2023-10-10 14:36:03,537][76542] Updated weights for policy 1, policy_version 49080 (0.0008) -[2023-10-10 14:36:03,858][76543] Updated weights for policy 0, policy_version 49133 (0.0008) -[2023-10-10 14:36:04,230][76543] Updated weights for policy 0, policy_version 49143 (0.0010) -[2023-10-10 14:36:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 100597760. Throughput: 0: 1844.4, 1: 1816.1. Samples: 25152314. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:36:06,077][75634] Avg episode reward: [(0, '39.540'), (1, '35.700')] -[2023-10-10 14:36:07,295][76542] Updated weights for policy 1, policy_version 49090 (0.0008) -[2023-10-10 14:36:07,661][76542] Updated weights for policy 1, policy_version 49100 (0.0007) -[2023-10-10 14:36:08,009][76543] Updated weights for policy 0, policy_version 49153 (0.0010) -[2023-10-10 14:36:08,026][76542] Updated weights for policy 1, policy_version 49110 (0.0008) -[2023-10-10 14:36:08,377][76543] Updated weights for policy 0, policy_version 49163 (0.0008) -[2023-10-10 14:36:08,392][76542] Updated weights for policy 1, policy_version 49120 (0.0008) -[2023-10-10 14:36:08,753][76543] Updated weights for policy 0, policy_version 49173 (0.0008) -[2023-10-10 14:36:09,120][76543] Updated weights for policy 0, policy_version 49183 (0.0007) -[2023-10-10 14:36:11,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 100663296. Throughput: 0: 1836.7, 1: 1811.1. Samples: 25173212. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:36:11,076][75634] Avg episode reward: [(0, '37.290'), (1, '33.360')] -[2023-10-10 14:36:12,123][76542] Updated weights for policy 1, policy_version 49130 (0.0008) -[2023-10-10 14:36:12,490][76542] Updated weights for policy 1, policy_version 49140 (0.0009) -[2023-10-10 14:36:12,593][76543] Updated weights for policy 0, policy_version 49193 (0.0009) -[2023-10-10 14:36:12,856][76542] Updated weights for policy 1, policy_version 49150 (0.0007) -[2023-10-10 14:36:12,965][76543] Updated weights for policy 0, policy_version 49203 (0.0008) -[2023-10-10 14:36:13,338][76543] Updated weights for policy 0, policy_version 49213 (0.0008) -[2023-10-10 14:36:16,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 100728832. Throughput: 0: 1846.5, 1: 1813.0. Samples: 25196378. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:36:16,077][75634] Avg episode reward: [(0, '37.940'), (1, '29.460')] -[2023-10-10 14:36:16,573][76542] Updated weights for policy 1, policy_version 49160 (0.0010) -[2023-10-10 14:36:16,938][76542] Updated weights for policy 1, policy_version 49170 (0.0008) -[2023-10-10 14:36:16,947][76543] Updated weights for policy 0, policy_version 49223 (0.0009) -[2023-10-10 14:36:17,307][76542] Updated weights for policy 1, policy_version 49180 (0.0009) -[2023-10-10 14:36:17,312][76543] Updated weights for policy 0, policy_version 49233 (0.0007) -[2023-10-10 14:36:17,700][76543] Updated weights for policy 0, policy_version 49243 (0.0010) -[2023-10-10 14:36:21,014][76542] Updated weights for policy 1, policy_version 49190 (0.0008) -[2023-10-10 14:36:21,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 100794368. Throughput: 0: 1831.5, 1: 1808.5. Samples: 25206074. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:36:21,076][75634] Avg episode reward: [(0, '35.460'), (1, '33.260')] -[2023-10-10 14:36:21,380][76542] Updated weights for policy 1, policy_version 49200 (0.0008) -[2023-10-10 14:36:21,385][76543] Updated weights for policy 0, policy_version 49253 (0.0009) -[2023-10-10 14:36:21,752][76543] Updated weights for policy 0, policy_version 49263 (0.0008) -[2023-10-10 14:36:21,755][76542] Updated weights for policy 1, policy_version 49210 (0.0008) -[2023-10-10 14:36:22,118][76543] Updated weights for policy 0, policy_version 49273 (0.0010) -[2023-10-10 14:36:25,569][76542] Updated weights for policy 1, policy_version 49220 (0.0009) -[2023-10-10 14:36:25,718][76543] Updated weights for policy 0, policy_version 49283 (0.0010) -[2023-10-10 14:36:25,934][76542] Updated weights for policy 1, policy_version 49230 (0.0010) -[2023-10-10 14:36:26,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 100859904. Throughput: 0: 1838.7, 1: 1803.2. Samples: 25228768. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:36:26,076][75634] Avg episode reward: [(0, '35.020'), (1, '32.560')] -[2023-10-10 14:36:26,096][76543] Updated weights for policy 0, policy_version 49293 (0.0008) -[2023-10-10 14:36:26,298][76542] Updated weights for policy 1, policy_version 49240 (0.0010) -[2023-10-10 14:36:26,464][76543] Updated weights for policy 0, policy_version 49303 (0.0008) -[2023-10-10 14:36:30,100][76543] Updated weights for policy 0, policy_version 49313 (0.0009) -[2023-10-10 14:36:30,104][76542] Updated weights for policy 1, policy_version 49250 (0.0007) -[2023-10-10 14:36:30,478][76542] Updated weights for policy 1, policy_version 49260 (0.0008) -[2023-10-10 14:36:30,511][76543] Updated weights for policy 0, policy_version 49323 (0.0007) -[2023-10-10 14:36:30,842][76542] Updated weights for policy 1, policy_version 49270 (0.0009) -[2023-10-10 14:36:30,870][76543] Updated weights for policy 0, policy_version 49333 (0.0010) -[2023-10-10 14:36:31,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 100925440. Throughput: 0: 1829.0, 1: 1816.6. Samples: 25250500. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:36:31,077][75634] Avg episode reward: [(0, '31.840'), (1, '33.220')] -[2023-10-10 14:36:31,201][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000049280_50462720.pth... -[2023-10-10 14:36:31,205][76542] Updated weights for policy 1, policy_version 49280 (0.0009) -[2023-10-10 14:36:31,233][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000047584_48726016.pth -[2023-10-10 14:36:31,235][76543] Updated weights for policy 0, policy_version 49343 (0.0008) -[2023-10-10 14:36:31,271][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000049344_50528256.pth... -[2023-10-10 14:36:31,307][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000047616_48758784.pth -[2023-10-10 14:36:34,829][76542] Updated weights for policy 1, policy_version 49290 (0.0009) -[2023-10-10 14:36:34,849][76543] Updated weights for policy 0, policy_version 49353 (0.0008) -[2023-10-10 14:36:35,199][76542] Updated weights for policy 1, policy_version 49300 (0.0008) -[2023-10-10 14:36:35,217][76543] Updated weights for policy 0, policy_version 49363 (0.0008) -[2023-10-10 14:36:35,561][76542] Updated weights for policy 1, policy_version 49310 (0.0010) -[2023-10-10 14:36:35,585][76543] Updated weights for policy 0, policy_version 49373 (0.0007) -[2023-10-10 14:36:36,076][75634] Fps is (10 sec: 19660.9, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 101056512. Throughput: 0: 1843.7, 1: 1805.5. Samples: 25261512. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:36:36,076][75634] Avg episode reward: [(0, '34.140'), (1, '32.990')] -[2023-10-10 14:36:39,117][76542] Updated weights for policy 1, policy_version 49320 (0.0009) -[2023-10-10 14:36:39,219][76543] Updated weights for policy 0, policy_version 49383 (0.0008) -[2023-10-10 14:36:39,492][76542] Updated weights for policy 1, policy_version 49330 (0.0008) -[2023-10-10 14:36:39,594][76543] Updated weights for policy 0, policy_version 49393 (0.0008) -[2023-10-10 14:36:39,861][76542] Updated weights for policy 1, policy_version 49340 (0.0009) -[2023-10-10 14:36:39,963][76543] Updated weights for policy 0, policy_version 49403 (0.0009) -[2023-10-10 14:36:41,076][75634] Fps is (10 sec: 19660.6, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 101122048. Throughput: 0: 1834.4, 1: 1809.5. Samples: 25283002. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:36:41,077][75634] Avg episode reward: [(0, '35.460'), (1, '35.090')] -[2023-10-10 14:36:43,618][76542] Updated weights for policy 1, policy_version 49350 (0.0009) -[2023-10-10 14:36:43,804][76543] Updated weights for policy 0, policy_version 49413 (0.0009) -[2023-10-10 14:36:44,007][76542] Updated weights for policy 1, policy_version 49360 (0.0010) -[2023-10-10 14:36:44,178][76543] Updated weights for policy 0, policy_version 49423 (0.0008) -[2023-10-10 14:36:44,365][76542] Updated weights for policy 1, policy_version 49370 (0.0008) -[2023-10-10 14:36:44,550][76543] Updated weights for policy 0, policy_version 49433 (0.0007) -[2023-10-10 14:36:46,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 101187584. Throughput: 0: 1831.6, 1: 1798.5. Samples: 25303906. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:36:46,077][75634] Avg episode reward: [(0, '33.510'), (1, '37.640')] -[2023-10-10 14:36:48,128][76542] Updated weights for policy 1, policy_version 49380 (0.0010) -[2023-10-10 14:36:48,393][76543] Updated weights for policy 0, policy_version 49443 (0.0007) -[2023-10-10 14:36:48,493][76542] Updated weights for policy 1, policy_version 49390 (0.0008) -[2023-10-10 14:36:48,770][76543] Updated weights for policy 0, policy_version 49453 (0.0008) -[2023-10-10 14:36:48,861][76542] Updated weights for policy 1, policy_version 49400 (0.0009) -[2023-10-10 14:36:49,141][76543] Updated weights for policy 0, policy_version 49463 (0.0008) -[2023-10-10 14:36:51,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 101253120. Throughput: 0: 1822.7, 1: 1808.6. Samples: 25315724. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:36:51,077][75634] Avg episode reward: [(0, '35.730'), (1, '35.140')] -[2023-10-10 14:36:52,615][76542] Updated weights for policy 1, policy_version 49410 (0.0008) -[2023-10-10 14:36:52,747][76543] Updated weights for policy 0, policy_version 49473 (0.0011) -[2023-10-10 14:36:52,987][76542] Updated weights for policy 1, policy_version 49420 (0.0008) -[2023-10-10 14:36:53,118][76543] Updated weights for policy 0, policy_version 49483 (0.0010) -[2023-10-10 14:36:53,351][76542] Updated weights for policy 1, policy_version 49430 (0.0008) -[2023-10-10 14:36:53,489][76543] Updated weights for policy 0, policy_version 49493 (0.0007) -[2023-10-10 14:36:53,727][76542] Updated weights for policy 1, policy_version 49440 (0.0008) -[2023-10-10 14:36:53,855][76543] Updated weights for policy 0, policy_version 49503 (0.0007) -[2023-10-10 14:36:56,076][75634] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 101318656. Throughput: 0: 1825.0, 1: 1800.2. Samples: 25336346. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:36:56,076][75634] Avg episode reward: [(0, '37.720'), (1, '37.160')] -[2023-10-10 14:36:57,441][76542] Updated weights for policy 1, policy_version 49450 (0.0007) -[2023-10-10 14:36:57,549][76543] Updated weights for policy 0, policy_version 49513 (0.0009) -[2023-10-10 14:36:57,802][76542] Updated weights for policy 1, policy_version 49460 (0.0007) -[2023-10-10 14:36:57,923][76543] Updated weights for policy 0, policy_version 49523 (0.0008) -[2023-10-10 14:36:58,163][76542] Updated weights for policy 1, policy_version 49470 (0.0008) -[2023-10-10 14:36:58,305][76543] Updated weights for policy 0, policy_version 49533 (0.0009) -[2023-10-10 14:37:01,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 101384192. Throughput: 0: 1819.7, 1: 1797.5. Samples: 25359152. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:37:01,076][75634] Avg episode reward: [(0, '34.500'), (1, '37.100')] -[2023-10-10 14:37:01,910][76543] Updated weights for policy 0, policy_version 49543 (0.0008) -[2023-10-10 14:37:02,108][76542] Updated weights for policy 1, policy_version 49480 (0.0008) -[2023-10-10 14:37:02,274][76543] Updated weights for policy 0, policy_version 49553 (0.0008) -[2023-10-10 14:37:02,487][76542] Updated weights for policy 1, policy_version 49490 (0.0008) -[2023-10-10 14:37:02,634][76543] Updated weights for policy 0, policy_version 49563 (0.0007) -[2023-10-10 14:37:02,853][76542] Updated weights for policy 1, policy_version 49500 (0.0007) -[2023-10-10 14:37:06,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 101449728. Throughput: 0: 1821.6, 1: 1799.9. Samples: 25369038. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:37:06,077][75634] Avg episode reward: [(0, '34.130'), (1, '37.960')] -[2023-10-10 14:37:06,480][76543] Updated weights for policy 0, policy_version 49573 (0.0008) -[2023-10-10 14:37:06,695][76542] Updated weights for policy 1, policy_version 49510 (0.0010) -[2023-10-10 14:37:06,851][76543] Updated weights for policy 0, policy_version 49583 (0.0008) -[2023-10-10 14:37:07,061][76542] Updated weights for policy 1, policy_version 49520 (0.0007) -[2023-10-10 14:37:07,218][76543] Updated weights for policy 0, policy_version 49593 (0.0009) -[2023-10-10 14:37:07,426][76542] Updated weights for policy 1, policy_version 49530 (0.0008) -[2023-10-10 14:37:10,938][76543] Updated weights for policy 0, policy_version 49603 (0.0009) -[2023-10-10 14:37:11,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 101515264. Throughput: 0: 1812.0, 1: 1804.1. Samples: 25391496. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:37:11,076][75634] Avg episode reward: [(0, '32.180'), (1, '36.090')] -[2023-10-10 14:37:11,109][76542] Updated weights for policy 1, policy_version 49540 (0.0007) -[2023-10-10 14:37:11,307][76543] Updated weights for policy 0, policy_version 49613 (0.0007) -[2023-10-10 14:37:11,482][76542] Updated weights for policy 1, policy_version 49550 (0.0009) -[2023-10-10 14:37:11,676][76543] Updated weights for policy 0, policy_version 49623 (0.0008) -[2023-10-10 14:37:11,842][76542] Updated weights for policy 1, policy_version 49560 (0.0008) -[2023-10-10 14:37:15,346][76543] Updated weights for policy 0, policy_version 49633 (0.0008) -[2023-10-10 14:37:15,698][76542] Updated weights for policy 1, policy_version 49570 (0.0009) -[2023-10-10 14:37:15,750][76543] Updated weights for policy 0, policy_version 49643 (0.0009) -[2023-10-10 14:37:16,063][76542] Updated weights for policy 1, policy_version 49580 (0.0008) -[2023-10-10 14:37:16,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.2). Total num frames: 101580800. Throughput: 0: 1818.7, 1: 1815.2. Samples: 25414026. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:37:16,076][75634] Avg episode reward: [(0, '33.990'), (1, '35.200')] -[2023-10-10 14:37:16,133][76543] Updated weights for policy 0, policy_version 49653 (0.0007) -[2023-10-10 14:37:16,430][76542] Updated weights for policy 1, policy_version 49590 (0.0008) -[2023-10-10 14:37:16,498][76543] Updated weights for policy 0, policy_version 49663 (0.0009) -[2023-10-10 14:37:16,798][76542] Updated weights for policy 1, policy_version 49600 (0.0008) -[2023-10-10 14:37:20,285][76543] Updated weights for policy 0, policy_version 49673 (0.0009) -[2023-10-10 14:37:20,517][76542] Updated weights for policy 1, policy_version 49610 (0.0009) -[2023-10-10 14:37:20,644][76543] Updated weights for policy 0, policy_version 49683 (0.0009) -[2023-10-10 14:37:20,885][76542] Updated weights for policy 1, policy_version 49620 (0.0009) -[2023-10-10 14:37:21,025][76543] Updated weights for policy 0, policy_version 49693 (0.0008) -[2023-10-10 14:37:21,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 101646336. Throughput: 0: 1808.1, 1: 1799.9. Samples: 25423872. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:37:21,076][75634] Avg episode reward: [(0, '34.580'), (1, '36.780')] -[2023-10-10 14:37:21,256][76542] Updated weights for policy 1, policy_version 49630 (0.0009) -[2023-10-10 14:37:24,626][76543] Updated weights for policy 0, policy_version 49703 (0.0008) -[2023-10-10 14:37:24,785][76542] Updated weights for policy 1, policy_version 49640 (0.0010) -[2023-10-10 14:37:24,986][76543] Updated weights for policy 0, policy_version 49713 (0.0007) -[2023-10-10 14:37:25,163][76542] Updated weights for policy 1, policy_version 49650 (0.0009) -[2023-10-10 14:37:25,364][76543] Updated weights for policy 0, policy_version 49723 (0.0008) -[2023-10-10 14:37:25,528][76542] Updated weights for policy 1, policy_version 49660 (0.0009) -[2023-10-10 14:37:26,076][75634] Fps is (10 sec: 19660.7, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 101777408. Throughput: 0: 1814.5, 1: 1822.4. Samples: 25446660. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:37:26,076][75634] Avg episode reward: [(0, '35.670'), (1, '31.090')] -[2023-10-10 14:37:28,969][76543] Updated weights for policy 0, policy_version 49733 (0.0009) -[2023-10-10 14:37:29,322][76542] Updated weights for policy 1, policy_version 49670 (0.0009) -[2023-10-10 14:37:29,335][76543] Updated weights for policy 0, policy_version 49743 (0.0008) -[2023-10-10 14:37:29,705][76542] Updated weights for policy 1, policy_version 49680 (0.0008) -[2023-10-10 14:37:29,713][76543] Updated weights for policy 0, policy_version 49753 (0.0007) -[2023-10-10 14:37:30,077][76542] Updated weights for policy 1, policy_version 49690 (0.0010) -[2023-10-10 14:37:31,076][75634] Fps is (10 sec: 19660.5, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 101842944. Throughput: 0: 1811.2, 1: 1802.1. Samples: 25466506. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:37:31,077][75634] Avg episode reward: [(0, '32.000'), (1, '31.990')] -[2023-10-10 14:37:33,332][76543] Updated weights for policy 0, policy_version 49763 (0.0008) -[2023-10-10 14:37:33,700][76543] Updated weights for policy 0, policy_version 49773 (0.0010) -[2023-10-10 14:37:33,722][76542] Updated weights for policy 1, policy_version 49700 (0.0008) -[2023-10-10 14:37:34,069][76543] Updated weights for policy 0, policy_version 49783 (0.0009) -[2023-10-10 14:37:34,095][76542] Updated weights for policy 1, policy_version 49710 (0.0008) -[2023-10-10 14:37:34,455][76542] Updated weights for policy 1, policy_version 49720 (0.0007) -[2023-10-10 14:37:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14662.3). Total num frames: 101908480. Throughput: 0: 1816.9, 1: 1817.1. Samples: 25479252. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:37:36,076][75634] Avg episode reward: [(0, '33.200'), (1, '34.630')] -[2023-10-10 14:37:37,638][76543] Updated weights for policy 0, policy_version 49793 (0.0008) -[2023-10-10 14:37:38,019][76543] Updated weights for policy 0, policy_version 49803 (0.0008) -[2023-10-10 14:37:38,115][76542] Updated weights for policy 1, policy_version 49730 (0.0008) -[2023-10-10 14:37:38,386][76543] Updated weights for policy 0, policy_version 49813 (0.0008) -[2023-10-10 14:37:38,493][76542] Updated weights for policy 1, policy_version 49740 (0.0009) -[2023-10-10 14:37:38,754][76543] Updated weights for policy 0, policy_version 49823 (0.0009) -[2023-10-10 14:37:38,860][76542] Updated weights for policy 1, policy_version 49750 (0.0008) -[2023-10-10 14:37:39,228][76542] Updated weights for policy 1, policy_version 49760 (0.0008) -[2023-10-10 14:37:41,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 101974016. Throughput: 0: 1816.3, 1: 1801.8. Samples: 25499158. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:37:41,077][75634] Avg episode reward: [(0, '34.950'), (1, '34.940')] -[2023-10-10 14:37:42,549][76543] Updated weights for policy 0, policy_version 49833 (0.0010) -[2023-10-10 14:37:42,924][76543] Updated weights for policy 0, policy_version 49843 (0.0008) -[2023-10-10 14:37:42,998][76542] Updated weights for policy 1, policy_version 49770 (0.0009) -[2023-10-10 14:37:43,292][76543] Updated weights for policy 0, policy_version 49853 (0.0009) -[2023-10-10 14:37:43,372][76542] Updated weights for policy 1, policy_version 49780 (0.0007) -[2023-10-10 14:37:43,740][76542] Updated weights for policy 1, policy_version 49790 (0.0007) -[2023-10-10 14:37:46,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 102039552. Throughput: 0: 1810.7, 1: 1800.1. Samples: 25521640. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:37:46,077][75634] Avg episode reward: [(0, '37.080'), (1, '35.260')] -[2023-10-10 14:37:47,151][76543] Updated weights for policy 0, policy_version 49863 (0.0008) -[2023-10-10 14:37:47,413][76542] Updated weights for policy 1, policy_version 49800 (0.0009) -[2023-10-10 14:37:47,522][76543] Updated weights for policy 0, policy_version 49873 (0.0007) -[2023-10-10 14:37:47,771][76542] Updated weights for policy 1, policy_version 49810 (0.0007) -[2023-10-10 14:37:47,890][76543] Updated weights for policy 0, policy_version 49883 (0.0009) -[2023-10-10 14:37:48,137][76542] Updated weights for policy 1, policy_version 49820 (0.0008) -[2023-10-10 14:37:51,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 102105088. Throughput: 0: 1807.5, 1: 1802.3. Samples: 25531478. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:37:51,077][75634] Avg episode reward: [(0, '39.980'), (1, '36.960')] -[2023-10-10 14:37:51,672][76542] Updated weights for policy 1, policy_version 49830 (0.0008) -[2023-10-10 14:37:51,674][76543] Updated weights for policy 0, policy_version 49893 (0.0008) -[2023-10-10 14:37:52,040][76542] Updated weights for policy 1, policy_version 49840 (0.0008) -[2023-10-10 14:37:52,042][76543] Updated weights for policy 0, policy_version 49903 (0.0007) -[2023-10-10 14:37:52,411][76542] Updated weights for policy 1, policy_version 49850 (0.0007) -[2023-10-10 14:37:52,416][76543] Updated weights for policy 0, policy_version 49913 (0.0007) -[2023-10-10 14:37:55,983][76543] Updated weights for policy 0, policy_version 49923 (0.0008) -[2023-10-10 14:37:56,036][76542] Updated weights for policy 1, policy_version 49860 (0.0008) -[2023-10-10 14:37:56,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 102170624. Throughput: 0: 1814.5, 1: 1808.1. Samples: 25554514. Policy #0 lag: (min: 1.0, avg: 9.4, max: 33.0) -[2023-10-10 14:37:56,077][75634] Avg episode reward: [(0, '37.070'), (1, '41.650')] -[2023-10-10 14:37:56,355][76543] Updated weights for policy 0, policy_version 49933 (0.0007) -[2023-10-10 14:37:56,412][76542] Updated weights for policy 1, policy_version 49870 (0.0008) -[2023-10-10 14:37:56,727][76543] Updated weights for policy 0, policy_version 49943 (0.0008) -[2023-10-10 14:37:56,769][76542] Updated weights for policy 1, policy_version 49880 (0.0008) -[2023-10-10 14:37:57,058][76421] Saving new best policy, reward=41.650! -[2023-10-10 14:38:00,356][76542] Updated weights for policy 1, policy_version 49890 (0.0009) -[2023-10-10 14:38:00,676][76543] Updated weights for policy 0, policy_version 49953 (0.0008) -[2023-10-10 14:38:00,724][76542] Updated weights for policy 1, policy_version 49900 (0.0008) -[2023-10-10 14:38:01,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 102236160. Throughput: 0: 1810.8, 1: 1809.2. Samples: 25576922. Policy #0 lag: (min: 1.0, avg: 9.4, max: 33.0) -[2023-10-10 14:38:01,076][75634] Avg episode reward: [(0, '36.040'), (1, '34.890')] -[2023-10-10 14:38:01,088][76542] Updated weights for policy 1, policy_version 49910 (0.0007) -[2023-10-10 14:38:01,093][76543] Updated weights for policy 0, policy_version 49963 (0.0008) -[2023-10-10 14:38:01,450][76542] Updated weights for policy 1, policy_version 49920 (0.0007) -[2023-10-10 14:38:01,459][76543] Updated weights for policy 0, policy_version 49973 (0.0008) -[2023-10-10 14:38:01,835][76543] Updated weights for policy 0, policy_version 49983 (0.0008) -[2023-10-10 14:38:05,122][76542] Updated weights for policy 1, policy_version 49930 (0.0011) -[2023-10-10 14:38:05,491][76542] Updated weights for policy 1, policy_version 49940 (0.0007) -[2023-10-10 14:38:05,501][76543] Updated weights for policy 0, policy_version 49993 (0.0008) -[2023-10-10 14:38:05,855][76542] Updated weights for policy 1, policy_version 49950 (0.0008) -[2023-10-10 14:38:05,872][76543] Updated weights for policy 0, policy_version 50003 (0.0009) -[2023-10-10 14:38:06,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 102334464. Throughput: 0: 1812.3, 1: 1820.3. Samples: 25587338. Policy #0 lag: (min: 1.0, avg: 9.4, max: 33.0) -[2023-10-10 14:38:06,076][75634] Avg episode reward: [(0, '36.180'), (1, '32.530')] -[2023-10-10 14:38:06,236][76543] Updated weights for policy 0, policy_version 50013 (0.0008) -[2023-10-10 14:38:09,448][76542] Updated weights for policy 1, policy_version 49960 (0.0011) -[2023-10-10 14:38:09,813][76542] Updated weights for policy 1, policy_version 49970 (0.0010) -[2023-10-10 14:38:09,945][76543] Updated weights for policy 0, policy_version 50023 (0.0009) -[2023-10-10 14:38:10,174][76542] Updated weights for policy 1, policy_version 49980 (0.0009) -[2023-10-10 14:38:10,313][76543] Updated weights for policy 0, policy_version 50033 (0.0008) -[2023-10-10 14:38:10,685][76543] Updated weights for policy 0, policy_version 50043 (0.0009) -[2023-10-10 14:38:11,076][75634] Fps is (10 sec: 19660.6, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 102432768. Throughput: 0: 1813.2, 1: 1808.3. Samples: 25609628. Policy #0 lag: (min: 1.0, avg: 9.4, max: 33.0) -[2023-10-10 14:38:11,077][75634] Avg episode reward: [(0, '35.150'), (1, '34.420')] -[2023-10-10 14:38:14,014][76542] Updated weights for policy 1, policy_version 49990 (0.0010) -[2023-10-10 14:38:14,349][76543] Updated weights for policy 0, policy_version 50053 (0.0010) -[2023-10-10 14:38:14,399][76542] Updated weights for policy 1, policy_version 50000 (0.0010) -[2023-10-10 14:38:14,710][76543] Updated weights for policy 0, policy_version 50063 (0.0007) -[2023-10-10 14:38:14,769][76542] Updated weights for policy 1, policy_version 50010 (0.0009) -[2023-10-10 14:38:15,083][76543] Updated weights for policy 0, policy_version 50073 (0.0008) -[2023-10-10 14:38:16,076][75634] Fps is (10 sec: 16383.7, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 102498304. Throughput: 0: 1822.0, 1: 1816.5. Samples: 25630240. Policy #0 lag: (min: 1.0, avg: 9.4, max: 33.0) -[2023-10-10 14:38:16,077][75634] Avg episode reward: [(0, '31.720'), (1, '35.070')] -[2023-10-10 14:38:18,609][76542] Updated weights for policy 1, policy_version 50020 (0.0011) -[2023-10-10 14:38:18,764][76543] Updated weights for policy 0, policy_version 50083 (0.0008) -[2023-10-10 14:38:18,976][76542] Updated weights for policy 1, policy_version 50030 (0.0009) -[2023-10-10 14:38:19,133][76543] Updated weights for policy 0, policy_version 50093 (0.0008) -[2023-10-10 14:38:19,352][76542] Updated weights for policy 1, policy_version 50040 (0.0009) -[2023-10-10 14:38:19,495][76543] Updated weights for policy 0, policy_version 50103 (0.0007) -[2023-10-10 14:38:21,076][75634] Fps is (10 sec: 13107.3, 60 sec: 15291.7, 300 sec: 14551.2). Total num frames: 102563840. Throughput: 0: 1814.7, 1: 1814.7. Samples: 25642576. Policy #0 lag: (min: 1.0, avg: 9.4, max: 33.0) -[2023-10-10 14:38:21,076][75634] Avg episode reward: [(0, '33.580'), (1, '30.030')] -[2023-10-10 14:38:23,076][76542] Updated weights for policy 1, policy_version 50050 (0.0009) -[2023-10-10 14:38:23,133][76543] Updated weights for policy 0, policy_version 50113 (0.0010) -[2023-10-10 14:38:23,446][76542] Updated weights for policy 1, policy_version 50060 (0.0008) -[2023-10-10 14:38:23,489][76543] Updated weights for policy 0, policy_version 50123 (0.0008) -[2023-10-10 14:38:23,823][76542] Updated weights for policy 1, policy_version 50070 (0.0007) -[2023-10-10 14:38:23,864][76543] Updated weights for policy 0, policy_version 50133 (0.0008) -[2023-10-10 14:38:24,187][76542] Updated weights for policy 1, policy_version 50080 (0.0007) -[2023-10-10 14:38:24,241][76543] Updated weights for policy 0, policy_version 50143 (0.0007) -[2023-10-10 14:38:26,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 102629376. Throughput: 0: 1815.2, 1: 1822.7. Samples: 25662860. Policy #0 lag: (min: 15.0, avg: 17.0, max: 45.0) -[2023-10-10 14:38:26,077][75634] Avg episode reward: [(0, '34.010'), (1, '32.380')] -[2023-10-10 14:38:27,830][76543] Updated weights for policy 0, policy_version 50153 (0.0007) -[2023-10-10 14:38:28,019][76542] Updated weights for policy 1, policy_version 50090 (0.0010) -[2023-10-10 14:38:28,202][76543] Updated weights for policy 0, policy_version 50163 (0.0008) -[2023-10-10 14:38:28,384][76542] Updated weights for policy 1, policy_version 50100 (0.0011) -[2023-10-10 14:38:28,566][76543] Updated weights for policy 0, policy_version 50173 (0.0010) -[2023-10-10 14:38:28,758][76542] Updated weights for policy 1, policy_version 50110 (0.0008) -[2023-10-10 14:38:31,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 102694912. Throughput: 0: 1816.9, 1: 1826.4. Samples: 25685586. Policy #0 lag: (min: 15.0, avg: 17.0, max: 45.0) -[2023-10-10 14:38:31,077][75634] Avg episode reward: [(0, '35.930'), (1, '34.600')] -[2023-10-10 14:38:31,087][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000050112_51314688.pth... -[2023-10-10 14:38:31,087][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000050176_51380224.pth... -[2023-10-10 14:38:31,121][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000048416_49577984.pth -[2023-10-10 14:38:31,122][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000048480_49643520.pth -[2023-10-10 14:38:32,366][76542] Updated weights for policy 1, policy_version 50120 (0.0008) -[2023-10-10 14:38:32,433][76543] Updated weights for policy 0, policy_version 50183 (0.0008) -[2023-10-10 14:38:32,738][76542] Updated weights for policy 1, policy_version 50130 (0.0008) -[2023-10-10 14:38:32,798][76543] Updated weights for policy 0, policy_version 50193 (0.0007) -[2023-10-10 14:38:33,103][76542] Updated weights for policy 1, policy_version 50140 (0.0009) -[2023-10-10 14:38:33,172][76543] Updated weights for policy 0, policy_version 50203 (0.0009) -[2023-10-10 14:38:36,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 102760448. Throughput: 0: 1823.6, 1: 1825.1. Samples: 25695668. Policy #0 lag: (min: 15.0, avg: 17.0, max: 45.0) -[2023-10-10 14:38:36,076][75634] Avg episode reward: [(0, '35.350'), (1, '37.010')] -[2023-10-10 14:38:36,830][76542] Updated weights for policy 1, policy_version 50150 (0.0010) -[2023-10-10 14:38:36,857][76543] Updated weights for policy 0, policy_version 50213 (0.0009) -[2023-10-10 14:38:37,208][76542] Updated weights for policy 1, policy_version 50160 (0.0008) -[2023-10-10 14:38:37,233][76543] Updated weights for policy 0, policy_version 50223 (0.0009) -[2023-10-10 14:38:37,576][76542] Updated weights for policy 1, policy_version 50170 (0.0008) -[2023-10-10 14:38:37,604][76543] Updated weights for policy 0, policy_version 50233 (0.0007) -[2023-10-10 14:38:41,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 102825984. Throughput: 0: 1813.7, 1: 1821.3. Samples: 25718090. Policy #0 lag: (min: 15.0, avg: 17.0, max: 45.0) -[2023-10-10 14:38:41,076][75634] Avg episode reward: [(0, '38.580'), (1, '37.170')] -[2023-10-10 14:38:41,085][76542] Updated weights for policy 1, policy_version 50180 (0.0008) -[2023-10-10 14:38:41,172][76543] Updated weights for policy 0, policy_version 50243 (0.0008) -[2023-10-10 14:38:41,448][76542] Updated weights for policy 1, policy_version 50190 (0.0009) -[2023-10-10 14:38:41,540][76543] Updated weights for policy 0, policy_version 50253 (0.0007) -[2023-10-10 14:38:41,825][76542] Updated weights for policy 1, policy_version 50200 (0.0008) -[2023-10-10 14:38:41,917][76543] Updated weights for policy 0, policy_version 50263 (0.0007) -[2023-10-10 14:38:45,587][76542] Updated weights for policy 1, policy_version 50210 (0.0008) -[2023-10-10 14:38:45,688][76543] Updated weights for policy 0, policy_version 50273 (0.0009) -[2023-10-10 14:38:45,953][76542] Updated weights for policy 1, policy_version 50220 (0.0007) -[2023-10-10 14:38:46,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 102891520. Throughput: 0: 1816.4, 1: 1822.3. Samples: 25740660. Policy #0 lag: (min: 15.0, avg: 17.0, max: 45.0) -[2023-10-10 14:38:46,076][75634] Avg episode reward: [(0, '38.780'), (1, '34.330')] -[2023-10-10 14:38:46,103][76543] Updated weights for policy 0, policy_version 50283 (0.0007) -[2023-10-10 14:38:46,326][76542] Updated weights for policy 1, policy_version 50230 (0.0007) -[2023-10-10 14:38:46,469][76543] Updated weights for policy 0, policy_version 50293 (0.0007) -[2023-10-10 14:38:46,686][76542] Updated weights for policy 1, policy_version 50240 (0.0009) -[2023-10-10 14:38:46,837][76543] Updated weights for policy 0, policy_version 50303 (0.0007) -[2023-10-10 14:38:50,482][76543] Updated weights for policy 0, policy_version 50313 (0.0008) -[2023-10-10 14:38:50,519][76542] Updated weights for policy 1, policy_version 50250 (0.0008) -[2023-10-10 14:38:50,858][76543] Updated weights for policy 0, policy_version 50323 (0.0008) -[2023-10-10 14:38:50,887][76542] Updated weights for policy 1, policy_version 50260 (0.0010) -[2023-10-10 14:38:51,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 102957056. Throughput: 0: 1817.2, 1: 1808.7. Samples: 25750504. Policy #0 lag: (min: 15.0, avg: 17.0, max: 45.0) -[2023-10-10 14:38:51,076][75634] Avg episode reward: [(0, '37.890'), (1, '33.440')] -[2023-10-10 14:38:51,215][76543] Updated weights for policy 0, policy_version 50333 (0.0010) -[2023-10-10 14:38:51,254][76542] Updated weights for policy 1, policy_version 50270 (0.0009) -[2023-10-10 14:38:55,001][76543] Updated weights for policy 0, policy_version 50343 (0.0009) -[2023-10-10 14:38:55,015][76542] Updated weights for policy 1, policy_version 50280 (0.0009) -[2023-10-10 14:38:55,375][76543] Updated weights for policy 0, policy_version 50353 (0.0008) -[2023-10-10 14:38:55,384][76542] Updated weights for policy 1, policy_version 50290 (0.0008) -[2023-10-10 14:38:55,746][76542] Updated weights for policy 1, policy_version 50300 (0.0007) -[2023-10-10 14:38:55,757][76543] Updated weights for policy 0, policy_version 50363 (0.0008) -[2023-10-10 14:38:56,076][75634] Fps is (10 sec: 19660.4, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 103088128. Throughput: 0: 1813.2, 1: 1820.5. Samples: 25773144. Policy #0 lag: (min: 15.0, avg: 17.0, max: 45.0) -[2023-10-10 14:38:56,077][75634] Avg episode reward: [(0, '33.690'), (1, '34.100')] -[2023-10-10 14:38:59,164][76543] Updated weights for policy 0, policy_version 50373 (0.0007) -[2023-10-10 14:38:59,521][76542] Updated weights for policy 1, policy_version 50310 (0.0008) -[2023-10-10 14:38:59,533][76543] Updated weights for policy 0, policy_version 50383 (0.0007) -[2023-10-10 14:38:59,896][76542] Updated weights for policy 1, policy_version 50320 (0.0008) -[2023-10-10 14:38:59,912][76543] Updated weights for policy 0, policy_version 50393 (0.0007) -[2023-10-10 14:39:00,263][76542] Updated weights for policy 1, policy_version 50330 (0.0008) -[2023-10-10 14:39:01,076][75634] Fps is (10 sec: 19660.4, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 103153664. Throughput: 0: 1810.7, 1: 1806.8. Samples: 25793028. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-10 14:39:01,077][75634] Avg episode reward: [(0, '36.130'), (1, '35.550')] -[2023-10-10 14:39:03,578][76543] Updated weights for policy 0, policy_version 50403 (0.0008) -[2023-10-10 14:39:03,949][76543] Updated weights for policy 0, policy_version 50413 (0.0008) -[2023-10-10 14:39:04,111][76542] Updated weights for policy 1, policy_version 50340 (0.0008) -[2023-10-10 14:39:04,315][76543] Updated weights for policy 0, policy_version 50423 (0.0007) -[2023-10-10 14:39:04,477][76542] Updated weights for policy 1, policy_version 50350 (0.0010) -[2023-10-10 14:39:04,846][76542] Updated weights for policy 1, policy_version 50360 (0.0007) -[2023-10-10 14:39:06,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 103219200. Throughput: 0: 1819.9, 1: 1814.1. Samples: 25806110. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-10 14:39:06,077][75634] Avg episode reward: [(0, '37.550'), (1, '33.840')] -[2023-10-10 14:39:07,988][76543] Updated weights for policy 0, policy_version 50433 (0.0009) -[2023-10-10 14:39:08,362][76543] Updated weights for policy 0, policy_version 50443 (0.0008) -[2023-10-10 14:39:08,518][76542] Updated weights for policy 1, policy_version 50370 (0.0009) -[2023-10-10 14:39:08,731][76543] Updated weights for policy 0, policy_version 50453 (0.0007) -[2023-10-10 14:39:08,887][76542] Updated weights for policy 1, policy_version 50380 (0.0009) -[2023-10-10 14:39:09,105][76543] Updated weights for policy 0, policy_version 50463 (0.0008) -[2023-10-10 14:39:09,254][76542] Updated weights for policy 1, policy_version 50390 (0.0008) -[2023-10-10 14:39:09,613][76542] Updated weights for policy 1, policy_version 50400 (0.0008) -[2023-10-10 14:39:11,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 103284736. Throughput: 0: 1817.0, 1: 1805.9. Samples: 25825890. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-10 14:39:11,076][75634] Avg episode reward: [(0, '35.560'), (1, '34.710')] -[2023-10-10 14:39:12,876][76543] Updated weights for policy 0, policy_version 50473 (0.0009) -[2023-10-10 14:39:13,221][76542] Updated weights for policy 1, policy_version 50410 (0.0008) -[2023-10-10 14:39:13,247][76543] Updated weights for policy 0, policy_version 50483 (0.0007) -[2023-10-10 14:39:13,593][76542] Updated weights for policy 1, policy_version 50420 (0.0008) -[2023-10-10 14:39:13,612][76543] Updated weights for policy 0, policy_version 50493 (0.0008) -[2023-10-10 14:39:13,957][76542] Updated weights for policy 1, policy_version 50430 (0.0007) -[2023-10-10 14:39:16,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 103350272. Throughput: 0: 1820.9, 1: 1809.2. Samples: 25848938. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-10 14:39:16,076][75634] Avg episode reward: [(0, '36.630'), (1, '36.550')] -[2023-10-10 14:39:17,385][76543] Updated weights for policy 0, policy_version 50503 (0.0010) -[2023-10-10 14:39:17,472][76542] Updated weights for policy 1, policy_version 50440 (0.0007) -[2023-10-10 14:39:17,743][76543] Updated weights for policy 0, policy_version 50513 (0.0008) -[2023-10-10 14:39:17,842][76542] Updated weights for policy 1, policy_version 50450 (0.0008) -[2023-10-10 14:39:18,119][76543] Updated weights for policy 0, policy_version 50523 (0.0008) -[2023-10-10 14:39:18,216][76542] Updated weights for policy 1, policy_version 50460 (0.0008) -[2023-10-10 14:39:21,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 103415808. Throughput: 0: 1817.2, 1: 1813.4. Samples: 25859044. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-10 14:39:21,076][75634] Avg episode reward: [(0, '37.750'), (1, '38.480')] -[2023-10-10 14:39:21,737][76543] Updated weights for policy 0, policy_version 50533 (0.0008) -[2023-10-10 14:39:21,896][76542] Updated weights for policy 1, policy_version 50470 (0.0008) -[2023-10-10 14:39:22,107][76543] Updated weights for policy 0, policy_version 50543 (0.0008) -[2023-10-10 14:39:22,257][76542] Updated weights for policy 1, policy_version 50480 (0.0007) -[2023-10-10 14:39:22,475][76543] Updated weights for policy 0, policy_version 50553 (0.0007) -[2023-10-10 14:39:22,622][76542] Updated weights for policy 1, policy_version 50490 (0.0007) -[2023-10-10 14:39:26,035][76543] Updated weights for policy 0, policy_version 50563 (0.0008) -[2023-10-10 14:39:26,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 103481344. Throughput: 0: 1826.4, 1: 1809.1. Samples: 25881688. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-10 14:39:26,076][75634] Avg episode reward: [(0, '39.640'), (1, '32.150')] -[2023-10-10 14:39:26,347][76542] Updated weights for policy 1, policy_version 50500 (0.0008) -[2023-10-10 14:39:26,398][76543] Updated weights for policy 0, policy_version 50573 (0.0008) -[2023-10-10 14:39:26,712][76542] Updated weights for policy 1, policy_version 50510 (0.0007) -[2023-10-10 14:39:26,773][76543] Updated weights for policy 0, policy_version 50583 (0.0007) -[2023-10-10 14:39:27,076][76542] Updated weights for policy 1, policy_version 50520 (0.0007) -[2023-10-10 14:39:30,471][76543] Updated weights for policy 0, policy_version 50593 (0.0007) -[2023-10-10 14:39:30,856][76542] Updated weights for policy 1, policy_version 50530 (0.0007) -[2023-10-10 14:39:30,866][76543] Updated weights for policy 0, policy_version 50603 (0.0007) -[2023-10-10 14:39:31,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 103546880. Throughput: 0: 1827.2, 1: 1818.1. Samples: 25904696. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-10 14:39:31,076][75634] Avg episode reward: [(0, '33.030'), (1, '31.970')] -[2023-10-10 14:39:31,227][76542] Updated weights for policy 1, policy_version 50540 (0.0007) -[2023-10-10 14:39:31,231][76543] Updated weights for policy 0, policy_version 50613 (0.0008) -[2023-10-10 14:39:31,587][76542] Updated weights for policy 1, policy_version 50550 (0.0008) -[2023-10-10 14:39:31,596][76543] Updated weights for policy 0, policy_version 50623 (0.0007) -[2023-10-10 14:39:31,968][76542] Updated weights for policy 1, policy_version 50560 (0.0008) -[2023-10-10 14:39:35,284][76543] Updated weights for policy 0, policy_version 50633 (0.0009) -[2023-10-10 14:39:35,654][76543] Updated weights for policy 0, policy_version 50643 (0.0008) -[2023-10-10 14:39:35,802][76542] Updated weights for policy 1, policy_version 50570 (0.0007) -[2023-10-10 14:39:36,028][76543] Updated weights for policy 0, policy_version 50653 (0.0010) -[2023-10-10 14:39:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 103612416. Throughput: 0: 1830.6, 1: 1815.5. Samples: 25914580. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-10 14:39:36,076][75634] Avg episode reward: [(0, '34.010'), (1, '34.630')] -[2023-10-10 14:39:36,180][76542] Updated weights for policy 1, policy_version 50580 (0.0008) -[2023-10-10 14:39:36,551][76542] Updated weights for policy 1, policy_version 50590 (0.0008) -[2023-10-10 14:39:39,721][76543] Updated weights for policy 0, policy_version 50663 (0.0009) -[2023-10-10 14:39:40,093][76543] Updated weights for policy 0, policy_version 50673 (0.0009) -[2023-10-10 14:39:40,259][76542] Updated weights for policy 1, policy_version 50600 (0.0008) -[2023-10-10 14:39:40,460][76543] Updated weights for policy 0, policy_version 50683 (0.0007) -[2023-10-10 14:39:40,628][76542] Updated weights for policy 1, policy_version 50610 (0.0008) -[2023-10-10 14:39:41,002][76542] Updated weights for policy 1, policy_version 50620 (0.0008) -[2023-10-10 14:39:41,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 103710720. Throughput: 0: 1828.5, 1: 1813.1. Samples: 25937012. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:39:41,076][75634] Avg episode reward: [(0, '34.020'), (1, '36.330')] -[2023-10-10 14:39:44,146][76543] Updated weights for policy 0, policy_version 50693 (0.0010) -[2023-10-10 14:39:44,510][76543] Updated weights for policy 0, policy_version 50703 (0.0010) -[2023-10-10 14:39:44,802][76542] Updated weights for policy 1, policy_version 50630 (0.0008) -[2023-10-10 14:39:44,874][76543] Updated weights for policy 0, policy_version 50713 (0.0008) -[2023-10-10 14:39:45,187][76542] Updated weights for policy 1, policy_version 50640 (0.0008) -[2023-10-10 14:39:45,556][76542] Updated weights for policy 1, policy_version 50650 (0.0009) -[2023-10-10 14:39:46,076][75634] Fps is (10 sec: 19660.6, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 103809024. Throughput: 0: 1820.1, 1: 1818.1. Samples: 25956748. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:39:46,077][75634] Avg episode reward: [(0, '30.740'), (1, '35.560')] -[2023-10-10 14:39:48,757][76543] Updated weights for policy 0, policy_version 50723 (0.0007) -[2023-10-10 14:39:49,124][76543] Updated weights for policy 0, policy_version 50733 (0.0008) -[2023-10-10 14:39:49,134][76542] Updated weights for policy 1, policy_version 50660 (0.0007) -[2023-10-10 14:39:49,496][76542] Updated weights for policy 1, policy_version 50670 (0.0007) -[2023-10-10 14:39:49,498][76543] Updated weights for policy 0, policy_version 50743 (0.0009) -[2023-10-10 14:39:49,866][76542] Updated weights for policy 1, policy_version 50680 (0.0007) -[2023-10-10 14:39:51,076][75634] Fps is (10 sec: 16383.8, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 103874560. Throughput: 0: 1810.9, 1: 1816.5. Samples: 25969342. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:39:51,077][75634] Avg episode reward: [(0, '31.980'), (1, '36.630')] -[2023-10-10 14:39:53,298][76543] Updated weights for policy 0, policy_version 50753 (0.0010) -[2023-10-10 14:39:53,597][76542] Updated weights for policy 1, policy_version 50690 (0.0007) -[2023-10-10 14:39:53,662][76543] Updated weights for policy 0, policy_version 50763 (0.0009) -[2023-10-10 14:39:53,968][76542] Updated weights for policy 1, policy_version 50700 (0.0008) -[2023-10-10 14:39:54,035][76543] Updated weights for policy 0, policy_version 50773 (0.0007) -[2023-10-10 14:39:54,331][76542] Updated weights for policy 1, policy_version 50710 (0.0008) -[2023-10-10 14:39:54,396][76543] Updated weights for policy 0, policy_version 50783 (0.0009) -[2023-10-10 14:39:54,687][76542] Updated weights for policy 1, policy_version 50720 (0.0010) -[2023-10-10 14:39:56,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 103940096. Throughput: 0: 1814.7, 1: 1818.7. Samples: 25989394. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:39:56,077][75634] Avg episode reward: [(0, '34.410'), (1, '37.010')] -[2023-10-10 14:39:58,172][76543] Updated weights for policy 0, policy_version 50793 (0.0008) -[2023-10-10 14:39:58,350][76542] Updated weights for policy 1, policy_version 50730 (0.0007) -[2023-10-10 14:39:58,543][76543] Updated weights for policy 0, policy_version 50803 (0.0007) -[2023-10-10 14:39:58,707][76542] Updated weights for policy 1, policy_version 50740 (0.0007) -[2023-10-10 14:39:58,910][76543] Updated weights for policy 0, policy_version 50813 (0.0007) -[2023-10-10 14:39:59,079][76542] Updated weights for policy 1, policy_version 50750 (0.0009) -[2023-10-10 14:40:01,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 104005632. Throughput: 0: 1804.7, 1: 1809.1. Samples: 26011562. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:40:01,077][75634] Avg episode reward: [(0, '36.520'), (1, '33.840')] -[2023-10-10 14:40:02,669][76543] Updated weights for policy 0, policy_version 50823 (0.0007) -[2023-10-10 14:40:02,822][76542] Updated weights for policy 1, policy_version 50760 (0.0008) -[2023-10-10 14:40:03,040][76543] Updated weights for policy 0, policy_version 50833 (0.0008) -[2023-10-10 14:40:03,189][76542] Updated weights for policy 1, policy_version 50770 (0.0007) -[2023-10-10 14:40:03,406][76543] Updated weights for policy 0, policy_version 50843 (0.0008) -[2023-10-10 14:40:03,561][76542] Updated weights for policy 1, policy_version 50780 (0.0008) -[2023-10-10 14:40:06,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 104071168. Throughput: 0: 1817.0, 1: 1806.8. Samples: 26022114. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:40:06,076][75634] Avg episode reward: [(0, '37.720'), (1, '33.830')] -[2023-10-10 14:40:07,119][76543] Updated weights for policy 0, policy_version 50853 (0.0009) -[2023-10-10 14:40:07,345][76542] Updated weights for policy 1, policy_version 50790 (0.0009) -[2023-10-10 14:40:07,490][76543] Updated weights for policy 0, policy_version 50863 (0.0008) -[2023-10-10 14:40:07,711][76542] Updated weights for policy 1, policy_version 50800 (0.0007) -[2023-10-10 14:40:07,848][76543] Updated weights for policy 0, policy_version 50873 (0.0009) -[2023-10-10 14:40:08,082][76542] Updated weights for policy 1, policy_version 50810 (0.0010) -[2023-10-10 14:40:11,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 104136704. Throughput: 0: 1802.4, 1: 1802.7. Samples: 26043914. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:40:11,076][75634] Avg episode reward: [(0, '39.110'), (1, '34.110')] -[2023-10-10 14:40:11,470][76543] Updated weights for policy 0, policy_version 50883 (0.0008) -[2023-10-10 14:40:11,791][76542] Updated weights for policy 1, policy_version 50820 (0.0009) -[2023-10-10 14:40:11,835][76543] Updated weights for policy 0, policy_version 50893 (0.0009) -[2023-10-10 14:40:12,150][76542] Updated weights for policy 1, policy_version 50830 (0.0008) -[2023-10-10 14:40:12,205][76543] Updated weights for policy 0, policy_version 50903 (0.0007) -[2023-10-10 14:40:12,529][76542] Updated weights for policy 1, policy_version 50840 (0.0008) -[2023-10-10 14:40:15,839][76543] Updated weights for policy 0, policy_version 50913 (0.0007) -[2023-10-10 14:40:16,058][76542] Updated weights for policy 1, policy_version 50850 (0.0008) -[2023-10-10 14:40:16,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 104202240. Throughput: 0: 1802.9, 1: 1802.6. Samples: 26066944. Policy #0 lag: (min: 17.0, avg: 27.6, max: 49.0) -[2023-10-10 14:40:16,076][75634] Avg episode reward: [(0, '35.000'), (1, '36.150')] -[2023-10-10 14:40:16,236][76543] Updated weights for policy 0, policy_version 50923 (0.0009) -[2023-10-10 14:40:16,425][76542] Updated weights for policy 1, policy_version 50860 (0.0008) -[2023-10-10 14:40:16,608][76543] Updated weights for policy 0, policy_version 50933 (0.0009) -[2023-10-10 14:40:16,804][76542] Updated weights for policy 1, policy_version 50870 (0.0008) -[2023-10-10 14:40:16,975][76543] Updated weights for policy 0, policy_version 50943 (0.0010) -[2023-10-10 14:40:17,164][76542] Updated weights for policy 1, policy_version 50880 (0.0009) -[2023-10-10 14:40:20,811][76543] Updated weights for policy 0, policy_version 50953 (0.0007) -[2023-10-10 14:40:20,943][76542] Updated weights for policy 1, policy_version 50890 (0.0008) -[2023-10-10 14:40:21,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 104267776. Throughput: 0: 1797.3, 1: 1806.0. Samples: 26076728. Policy #0 lag: (min: 17.0, avg: 27.6, max: 49.0) -[2023-10-10 14:40:21,076][75634] Avg episode reward: [(0, '32.670'), (1, '34.340')] -[2023-10-10 14:40:21,188][76543] Updated weights for policy 0, policy_version 50963 (0.0008) -[2023-10-10 14:40:21,302][76542] Updated weights for policy 1, policy_version 50900 (0.0009) -[2023-10-10 14:40:21,559][76543] Updated weights for policy 0, policy_version 50973 (0.0008) -[2023-10-10 14:40:21,665][76542] Updated weights for policy 1, policy_version 50910 (0.0007) -[2023-10-10 14:40:25,183][76543] Updated weights for policy 0, policy_version 50983 (0.0008) -[2023-10-10 14:40:25,352][76542] Updated weights for policy 1, policy_version 50920 (0.0008) -[2023-10-10 14:40:25,556][76543] Updated weights for policy 0, policy_version 50993 (0.0008) -[2023-10-10 14:40:25,723][76542] Updated weights for policy 1, policy_version 50930 (0.0007) -[2023-10-10 14:40:25,918][76543] Updated weights for policy 0, policy_version 51003 (0.0007) -[2023-10-10 14:40:26,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.2). Total num frames: 104333312. Throughput: 0: 1800.8, 1: 1808.4. Samples: 26099426. Policy #0 lag: (min: 17.0, avg: 27.6, max: 49.0) -[2023-10-10 14:40:26,076][75634] Avg episode reward: [(0, '32.960'), (1, '34.410')] -[2023-10-10 14:40:26,092][76542] Updated weights for policy 1, policy_version 50940 (0.0008) -[2023-10-10 14:40:29,666][76543] Updated weights for policy 0, policy_version 51013 (0.0010) -[2023-10-10 14:40:29,907][76542] Updated weights for policy 1, policy_version 50950 (0.0009) -[2023-10-10 14:40:30,041][76543] Updated weights for policy 0, policy_version 51023 (0.0009) -[2023-10-10 14:40:30,284][76542] Updated weights for policy 1, policy_version 50960 (0.0008) -[2023-10-10 14:40:30,413][76543] Updated weights for policy 0, policy_version 51033 (0.0007) -[2023-10-10 14:40:30,654][76542] Updated weights for policy 1, policy_version 50970 (0.0008) -[2023-10-10 14:40:31,076][75634] Fps is (10 sec: 19660.5, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 104464384. Throughput: 0: 1816.7, 1: 1812.1. Samples: 26120042. Policy #0 lag: (min: 17.0, avg: 27.6, max: 49.0) -[2023-10-10 14:40:31,077][75634] Avg episode reward: [(0, '31.480'), (1, '36.620')] -[2023-10-10 14:40:31,089][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000050976_52199424.pth... -[2023-10-10 14:40:31,089][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000051040_52264960.pth... -[2023-10-10 14:40:31,127][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000049280_50462720.pth -[2023-10-10 14:40:31,129][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000049344_50528256.pth -[2023-10-10 14:40:31,132][76421] Saving a milestone ./train_atari/atari_defender_APPO/checkpoint_p1/milestones/checkpoint_000050976_52199424.pth -[2023-10-10 14:40:31,135][76362] Saving a milestone ./train_atari/atari_defender_APPO/checkpoint_p0/milestones/checkpoint_000051040_52264960.pth -[2023-10-10 14:40:34,080][76543] Updated weights for policy 0, policy_version 51043 (0.0007) -[2023-10-10 14:40:34,194][76542] Updated weights for policy 1, policy_version 50980 (0.0007) -[2023-10-10 14:40:34,455][76543] Updated weights for policy 0, policy_version 51053 (0.0008) -[2023-10-10 14:40:34,553][76542] Updated weights for policy 1, policy_version 50990 (0.0009) -[2023-10-10 14:40:34,816][76543] Updated weights for policy 0, policy_version 51063 (0.0007) -[2023-10-10 14:40:34,923][76542] Updated weights for policy 1, policy_version 51000 (0.0007) -[2023-10-10 14:40:36,076][75634] Fps is (10 sec: 19660.8, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 104529920. Throughput: 0: 1808.9, 1: 1810.5. Samples: 26132216. Policy #0 lag: (min: 17.0, avg: 27.6, max: 49.0) -[2023-10-10 14:40:36,076][75634] Avg episode reward: [(0, '33.070'), (1, '33.240')] -[2023-10-10 14:40:38,508][76543] Updated weights for policy 0, policy_version 51073 (0.0009) -[2023-10-10 14:40:38,639][76542] Updated weights for policy 1, policy_version 51010 (0.0007) -[2023-10-10 14:40:38,878][76543] Updated weights for policy 0, policy_version 51083 (0.0008) -[2023-10-10 14:40:39,005][76542] Updated weights for policy 1, policy_version 51020 (0.0009) -[2023-10-10 14:40:39,256][76543] Updated weights for policy 0, policy_version 51093 (0.0009) -[2023-10-10 14:40:39,374][76542] Updated weights for policy 1, policy_version 51030 (0.0009) -[2023-10-10 14:40:39,611][76543] Updated weights for policy 0, policy_version 51103 (0.0009) -[2023-10-10 14:40:39,734][76542] Updated weights for policy 1, policy_version 51040 (0.0010) -[2023-10-10 14:40:41,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 104595456. Throughput: 0: 1818.5, 1: 1807.6. Samples: 26152572. Policy #0 lag: (min: 17.0, avg: 27.6, max: 49.0) -[2023-10-10 14:40:41,077][75634] Avg episode reward: [(0, '35.790'), (1, '32.390')] -[2023-10-10 14:40:43,347][76542] Updated weights for policy 1, policy_version 51050 (0.0008) -[2023-10-10 14:40:43,376][76543] Updated weights for policy 0, policy_version 51113 (0.0009) -[2023-10-10 14:40:43,720][76542] Updated weights for policy 1, policy_version 51060 (0.0007) -[2023-10-10 14:40:43,749][76543] Updated weights for policy 0, policy_version 51123 (0.0007) -[2023-10-10 14:40:44,091][76542] Updated weights for policy 1, policy_version 51070 (0.0008) -[2023-10-10 14:40:44,128][76543] Updated weights for policy 0, policy_version 51133 (0.0007) -[2023-10-10 14:40:46,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 104660992. Throughput: 0: 1812.9, 1: 1816.0. Samples: 26174860. Policy #0 lag: (min: 17.0, avg: 27.6, max: 49.0) -[2023-10-10 14:40:46,076][75634] Avg episode reward: [(0, '36.180'), (1, '34.160')] -[2023-10-10 14:40:47,890][76543] Updated weights for policy 0, policy_version 51143 (0.0008) -[2023-10-10 14:40:47,926][76542] Updated weights for policy 1, policy_version 51080 (0.0009) -[2023-10-10 14:40:48,260][76543] Updated weights for policy 0, policy_version 51153 (0.0007) -[2023-10-10 14:40:48,297][76542] Updated weights for policy 1, policy_version 51090 (0.0009) -[2023-10-10 14:40:48,639][76543] Updated weights for policy 0, policy_version 51163 (0.0008) -[2023-10-10 14:40:48,660][76542] Updated weights for policy 1, policy_version 51100 (0.0008) -[2023-10-10 14:40:51,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 104726528. Throughput: 0: 1814.3, 1: 1821.3. Samples: 26185718. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:40:51,077][75634] Avg episode reward: [(0, '35.950'), (1, '34.860')] -[2023-10-10 14:40:52,348][76543] Updated weights for policy 0, policy_version 51173 (0.0009) -[2023-10-10 14:40:52,416][76542] Updated weights for policy 1, policy_version 51110 (0.0009) -[2023-10-10 14:40:52,716][76543] Updated weights for policy 0, policy_version 51183 (0.0008) -[2023-10-10 14:40:52,784][76542] Updated weights for policy 1, policy_version 51120 (0.0008) -[2023-10-10 14:40:53,074][76543] Updated weights for policy 0, policy_version 51193 (0.0009) -[2023-10-10 14:40:53,162][76542] Updated weights for policy 1, policy_version 51130 (0.0009) -[2023-10-10 14:40:56,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 104792064. Throughput: 0: 1813.8, 1: 1818.3. Samples: 26207356. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:40:56,077][75634] Avg episode reward: [(0, '36.170'), (1, '35.770')] -[2023-10-10 14:40:56,688][76543] Updated weights for policy 0, policy_version 51203 (0.0008) -[2023-10-10 14:40:57,035][76542] Updated weights for policy 1, policy_version 51140 (0.0008) -[2023-10-10 14:40:57,054][76543] Updated weights for policy 0, policy_version 51213 (0.0009) -[2023-10-10 14:40:57,404][76542] Updated weights for policy 1, policy_version 51150 (0.0008) -[2023-10-10 14:40:57,422][76543] Updated weights for policy 0, policy_version 51223 (0.0008) -[2023-10-10 14:40:57,766][76542] Updated weights for policy 1, policy_version 51160 (0.0008) -[2023-10-10 14:41:01,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 104857600. Throughput: 0: 1809.4, 1: 1816.2. Samples: 26230096. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:41:01,076][75634] Avg episode reward: [(0, '37.850'), (1, '35.580')] -[2023-10-10 14:41:01,191][76543] Updated weights for policy 0, policy_version 51233 (0.0009) -[2023-10-10 14:41:01,386][76542] Updated weights for policy 1, policy_version 51170 (0.0008) -[2023-10-10 14:41:01,596][76543] Updated weights for policy 0, policy_version 51243 (0.0008) -[2023-10-10 14:41:01,751][76542] Updated weights for policy 1, policy_version 51180 (0.0008) -[2023-10-10 14:41:01,971][76543] Updated weights for policy 0, policy_version 51253 (0.0007) -[2023-10-10 14:41:02,117][76542] Updated weights for policy 1, policy_version 51190 (0.0009) -[2023-10-10 14:41:02,341][76543] Updated weights for policy 0, policy_version 51263 (0.0007) -[2023-10-10 14:41:02,483][76542] Updated weights for policy 1, policy_version 51200 (0.0010) -[2023-10-10 14:41:05,741][76543] Updated weights for policy 0, policy_version 51273 (0.0007) -[2023-10-10 14:41:06,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 104923136. Throughput: 0: 1813.2, 1: 1814.3. Samples: 26239966. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:41:06,076][75634] Avg episode reward: [(0, '39.980'), (1, '36.390')] -[2023-10-10 14:41:06,098][76543] Updated weights for policy 0, policy_version 51283 (0.0007) -[2023-10-10 14:41:06,283][76542] Updated weights for policy 1, policy_version 51210 (0.0007) -[2023-10-10 14:41:06,468][76543] Updated weights for policy 0, policy_version 51293 (0.0007) -[2023-10-10 14:41:06,644][76542] Updated weights for policy 1, policy_version 51220 (0.0008) -[2023-10-10 14:41:07,019][76542] Updated weights for policy 1, policy_version 51230 (0.0008) -[2023-10-10 14:41:10,273][76543] Updated weights for policy 0, policy_version 51303 (0.0009) -[2023-10-10 14:41:10,644][76543] Updated weights for policy 0, policy_version 51313 (0.0008) -[2023-10-10 14:41:10,705][76542] Updated weights for policy 1, policy_version 51240 (0.0009) -[2023-10-10 14:41:11,016][76543] Updated weights for policy 0, policy_version 51323 (0.0007) -[2023-10-10 14:41:11,076][76542] Updated weights for policy 1, policy_version 51250 (0.0008) -[2023-10-10 14:41:11,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 104988672. Throughput: 0: 1819.9, 1: 1811.8. Samples: 26262850. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:41:11,077][75634] Avg episode reward: [(0, '39.300'), (1, '39.510')] -[2023-10-10 14:41:11,438][76542] Updated weights for policy 1, policy_version 51260 (0.0007) -[2023-10-10 14:41:14,794][76543] Updated weights for policy 0, policy_version 51333 (0.0010) -[2023-10-10 14:41:15,170][76543] Updated weights for policy 0, policy_version 51343 (0.0008) -[2023-10-10 14:41:15,262][76542] Updated weights for policy 1, policy_version 51270 (0.0008) -[2023-10-10 14:41:15,538][76543] Updated weights for policy 0, policy_version 51353 (0.0008) -[2023-10-10 14:41:15,630][76542] Updated weights for policy 1, policy_version 51280 (0.0008) -[2023-10-10 14:41:15,995][76542] Updated weights for policy 1, policy_version 51290 (0.0008) -[2023-10-10 14:41:16,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 105086976. Throughput: 0: 1817.6, 1: 1818.7. Samples: 26283674. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:41:16,076][75634] Avg episode reward: [(0, '37.520'), (1, '35.130')] -[2023-10-10 14:41:19,175][76543] Updated weights for policy 0, policy_version 51363 (0.0007) -[2023-10-10 14:41:19,556][76543] Updated weights for policy 0, policy_version 51373 (0.0008) -[2023-10-10 14:41:19,708][76542] Updated weights for policy 1, policy_version 51300 (0.0007) -[2023-10-10 14:41:19,926][76543] Updated weights for policy 0, policy_version 51383 (0.0008) -[2023-10-10 14:41:20,064][76542] Updated weights for policy 1, policy_version 51310 (0.0010) -[2023-10-10 14:41:20,437][76542] Updated weights for policy 1, policy_version 51320 (0.0009) -[2023-10-10 14:41:21,076][75634] Fps is (10 sec: 19661.3, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 105185280. Throughput: 0: 1811.8, 1: 1803.9. Samples: 26294922. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:41:21,076][75634] Avg episode reward: [(0, '39.460'), (1, '36.740')] -[2023-10-10 14:41:23,510][76543] Updated weights for policy 0, policy_version 51393 (0.0007) -[2023-10-10 14:41:23,867][76543] Updated weights for policy 0, policy_version 51403 (0.0008) -[2023-10-10 14:41:24,136][76542] Updated weights for policy 1, policy_version 51330 (0.0009) -[2023-10-10 14:41:24,241][76543] Updated weights for policy 0, policy_version 51413 (0.0009) -[2023-10-10 14:41:24,497][76542] Updated weights for policy 1, policy_version 51340 (0.0009) -[2023-10-10 14:41:24,609][76543] Updated weights for policy 0, policy_version 51423 (0.0009) -[2023-10-10 14:41:24,872][76542] Updated weights for policy 1, policy_version 51350 (0.0009) -[2023-10-10 14:41:25,237][76542] Updated weights for policy 1, policy_version 51360 (0.0008) -[2023-10-10 14:41:26,076][75634] Fps is (10 sec: 16384.0, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 105250816. Throughput: 0: 1816.1, 1: 1817.6. Samples: 26316088. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:41:26,077][75634] Avg episode reward: [(0, '34.670'), (1, '37.620')] -[2023-10-10 14:41:28,264][76543] Updated weights for policy 0, policy_version 51433 (0.0007) -[2023-10-10 14:41:28,624][76543] Updated weights for policy 0, policy_version 51443 (0.0008) -[2023-10-10 14:41:28,850][76542] Updated weights for policy 1, policy_version 51370 (0.0008) -[2023-10-10 14:41:28,987][76543] Updated weights for policy 0, policy_version 51453 (0.0010) -[2023-10-10 14:41:29,211][76542] Updated weights for policy 1, policy_version 51380 (0.0008) -[2023-10-10 14:41:29,578][76542] Updated weights for policy 1, policy_version 51390 (0.0009) -[2023-10-10 14:41:31,076][75634] Fps is (10 sec: 13106.5, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 105316352. Throughput: 0: 1823.3, 1: 1802.4. Samples: 26338020. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:41:31,078][75634] Avg episode reward: [(0, '33.840'), (1, '35.000')] -[2023-10-10 14:41:32,630][76543] Updated weights for policy 0, policy_version 51463 (0.0007) -[2023-10-10 14:41:33,003][76543] Updated weights for policy 0, policy_version 51473 (0.0009) -[2023-10-10 14:41:33,163][76542] Updated weights for policy 1, policy_version 51400 (0.0008) -[2023-10-10 14:41:33,371][76543] Updated weights for policy 0, policy_version 51483 (0.0007) -[2023-10-10 14:41:33,527][76542] Updated weights for policy 1, policy_version 51410 (0.0008) -[2023-10-10 14:41:33,895][76542] Updated weights for policy 1, policy_version 51420 (0.0011) -[2023-10-10 14:41:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 105381888. Throughput: 0: 1819.0, 1: 1808.9. Samples: 26348974. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:41:36,076][75634] Avg episode reward: [(0, '32.430'), (1, '35.200')] -[2023-10-10 14:41:37,010][76543] Updated weights for policy 0, policy_version 51493 (0.0010) -[2023-10-10 14:41:37,379][76543] Updated weights for policy 0, policy_version 51503 (0.0009) -[2023-10-10 14:41:37,621][76542] Updated weights for policy 1, policy_version 51430 (0.0009) -[2023-10-10 14:41:37,756][76543] Updated weights for policy 0, policy_version 51513 (0.0009) -[2023-10-10 14:41:37,979][76542] Updated weights for policy 1, policy_version 51440 (0.0008) -[2023-10-10 14:41:38,355][76542] Updated weights for policy 1, policy_version 51450 (0.0007) -[2023-10-10 14:41:41,076][75634] Fps is (10 sec: 13107.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 105447424. Throughput: 0: 1829.7, 1: 1810.0. Samples: 26371138. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:41:41,076][75634] Avg episode reward: [(0, '32.850'), (1, '34.880')] -[2023-10-10 14:41:41,333][76543] Updated weights for policy 0, policy_version 51523 (0.0009) -[2023-10-10 14:41:41,695][76543] Updated weights for policy 0, policy_version 51533 (0.0008) -[2023-10-10 14:41:42,009][76542] Updated weights for policy 1, policy_version 51460 (0.0007) -[2023-10-10 14:41:42,069][76543] Updated weights for policy 0, policy_version 51543 (0.0008) -[2023-10-10 14:41:42,373][76542] Updated weights for policy 1, policy_version 51470 (0.0008) -[2023-10-10 14:41:42,748][76542] Updated weights for policy 1, policy_version 51480 (0.0010) -[2023-10-10 14:41:45,822][76543] Updated weights for policy 0, policy_version 51553 (0.0008) -[2023-10-10 14:41:46,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 105512960. Throughput: 0: 1835.6, 1: 1810.1. Samples: 26394152. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:41:46,077][75634] Avg episode reward: [(0, '30.480'), (1, '33.750')] -[2023-10-10 14:41:46,184][76543] Updated weights for policy 0, policy_version 51563 (0.0008) -[2023-10-10 14:41:46,538][76542] Updated weights for policy 1, policy_version 51490 (0.0010) -[2023-10-10 14:41:46,561][76543] Updated weights for policy 0, policy_version 51573 (0.0007) -[2023-10-10 14:41:46,895][76542] Updated weights for policy 1, policy_version 51500 (0.0008) -[2023-10-10 14:41:46,937][76543] Updated weights for policy 0, policy_version 51583 (0.0008) -[2023-10-10 14:41:47,273][76542] Updated weights for policy 1, policy_version 51510 (0.0008) -[2023-10-10 14:41:47,639][76542] Updated weights for policy 1, policy_version 51520 (0.0010) -[2023-10-10 14:41:50,690][76543] Updated weights for policy 0, policy_version 51593 (0.0008) -[2023-10-10 14:41:51,065][76543] Updated weights for policy 0, policy_version 51603 (0.0008) -[2023-10-10 14:41:51,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 105578496. Throughput: 0: 1836.4, 1: 1809.4. Samples: 26404026. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:41:51,076][75634] Avg episode reward: [(0, '33.770'), (1, '34.710')] -[2023-10-10 14:41:51,221][76542] Updated weights for policy 1, policy_version 51530 (0.0009) -[2023-10-10 14:41:51,429][76543] Updated weights for policy 0, policy_version 51613 (0.0007) -[2023-10-10 14:41:51,591][76542] Updated weights for policy 1, policy_version 51540 (0.0007) -[2023-10-10 14:41:51,968][76542] Updated weights for policy 1, policy_version 51550 (0.0008) -[2023-10-10 14:41:54,992][76543] Updated weights for policy 0, policy_version 51623 (0.0008) -[2023-10-10 14:41:55,371][76543] Updated weights for policy 0, policy_version 51633 (0.0007) -[2023-10-10 14:41:55,674][76542] Updated weights for policy 1, policy_version 51560 (0.0009) -[2023-10-10 14:41:55,738][76543] Updated weights for policy 0, policy_version 51643 (0.0007) -[2023-10-10 14:41:56,040][76542] Updated weights for policy 1, policy_version 51570 (0.0009) -[2023-10-10 14:41:56,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 105676800. Throughput: 0: 1831.2, 1: 1816.3. Samples: 26426988. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:41:56,076][75634] Avg episode reward: [(0, '30.800'), (1, '32.220')] -[2023-10-10 14:41:56,414][76542] Updated weights for policy 1, policy_version 51580 (0.0010) -[2023-10-10 14:41:59,305][76543] Updated weights for policy 0, policy_version 51653 (0.0008) -[2023-10-10 14:41:59,671][76543] Updated weights for policy 0, policy_version 51663 (0.0010) -[2023-10-10 14:42:00,042][76543] Updated weights for policy 0, policy_version 51673 (0.0010) -[2023-10-10 14:42:00,287][76542] Updated weights for policy 1, policy_version 51590 (0.0009) -[2023-10-10 14:42:00,656][76542] Updated weights for policy 1, policy_version 51600 (0.0008) -[2023-10-10 14:42:01,027][76542] Updated weights for policy 1, policy_version 51610 (0.0008) -[2023-10-10 14:42:01,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 105742336. Throughput: 0: 1826.6, 1: 1817.2. Samples: 26447644. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-10 14:42:01,076][75634] Avg episode reward: [(0, '37.840'), (1, '33.020')] -[2023-10-10 14:42:03,837][76543] Updated weights for policy 0, policy_version 51683 (0.0007) -[2023-10-10 14:42:04,214][76543] Updated weights for policy 0, policy_version 51693 (0.0008) -[2023-10-10 14:42:04,588][76543] Updated weights for policy 0, policy_version 51703 (0.0009) -[2023-10-10 14:42:04,648][76542] Updated weights for policy 1, policy_version 51620 (0.0009) -[2023-10-10 14:42:05,024][76542] Updated weights for policy 1, policy_version 51630 (0.0009) -[2023-10-10 14:42:05,386][76542] Updated weights for policy 1, policy_version 51640 (0.0010) -[2023-10-10 14:42:06,076][75634] Fps is (10 sec: 16383.7, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 105840640. Throughput: 0: 1841.2, 1: 1819.8. Samples: 26459670. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-10 14:42:06,077][75634] Avg episode reward: [(0, '42.120'), (1, '34.770')] -[2023-10-10 14:42:08,249][76543] Updated weights for policy 0, policy_version 51713 (0.0007) -[2023-10-10 14:42:08,611][76543] Updated weights for policy 0, policy_version 51723 (0.0009) -[2023-10-10 14:42:08,980][76543] Updated weights for policy 0, policy_version 51733 (0.0008) -[2023-10-10 14:42:09,165][76542] Updated weights for policy 1, policy_version 51650 (0.0010) -[2023-10-10 14:42:09,353][76543] Updated weights for policy 0, policy_version 51743 (0.0010) -[2023-10-10 14:42:09,536][76542] Updated weights for policy 1, policy_version 51660 (0.0008) -[2023-10-10 14:42:09,900][76542] Updated weights for policy 1, policy_version 51670 (0.0007) -[2023-10-10 14:42:10,270][76542] Updated weights for policy 1, policy_version 51680 (0.0008) -[2023-10-10 14:42:11,076][75634] Fps is (10 sec: 16383.8, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 105906176. Throughput: 0: 1828.5, 1: 1819.4. Samples: 26480244. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-10 14:42:11,077][75634] Avg episode reward: [(0, '40.760'), (1, '33.370')] -[2023-10-10 14:42:12,985][76543] Updated weights for policy 0, policy_version 51753 (0.0011) -[2023-10-10 14:42:13,352][76543] Updated weights for policy 0, policy_version 51763 (0.0010) -[2023-10-10 14:42:13,724][76543] Updated weights for policy 0, policy_version 51773 (0.0009) -[2023-10-10 14:42:13,982][76542] Updated weights for policy 1, policy_version 51690 (0.0008) -[2023-10-10 14:42:14,353][76542] Updated weights for policy 1, policy_version 51700 (0.0007) -[2023-10-10 14:42:14,715][76542] Updated weights for policy 1, policy_version 51710 (0.0010) -[2023-10-10 14:42:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 105971712. Throughput: 0: 1837.0, 1: 1810.8. Samples: 26502172. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-10 14:42:16,077][75634] Avg episode reward: [(0, '40.000'), (1, '32.840')] -[2023-10-10 14:42:17,424][76543] Updated weights for policy 0, policy_version 51783 (0.0007) -[2023-10-10 14:42:17,790][76543] Updated weights for policy 0, policy_version 51793 (0.0008) -[2023-10-10 14:42:18,156][76543] Updated weights for policy 0, policy_version 51803 (0.0008) -[2023-10-10 14:42:18,449][76542] Updated weights for policy 1, policy_version 51720 (0.0007) -[2023-10-10 14:42:18,813][76542] Updated weights for policy 1, policy_version 51730 (0.0008) -[2023-10-10 14:42:19,179][76542] Updated weights for policy 1, policy_version 51740 (0.0009) -[2023-10-10 14:42:21,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 106037248. Throughput: 0: 1831.4, 1: 1812.4. Samples: 26512946. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-10 14:42:21,077][75634] Avg episode reward: [(0, '43.190'), (1, '33.750')] -[2023-10-10 14:42:21,077][76362] Saving new best policy, reward=43.190! -[2023-10-10 14:42:21,783][76543] Updated weights for policy 0, policy_version 51813 (0.0009) -[2023-10-10 14:42:22,159][76543] Updated weights for policy 0, policy_version 51823 (0.0008) -[2023-10-10 14:42:22,521][76543] Updated weights for policy 0, policy_version 51833 (0.0007) -[2023-10-10 14:42:22,762][76542] Updated weights for policy 1, policy_version 51750 (0.0008) -[2023-10-10 14:42:23,133][76542] Updated weights for policy 1, policy_version 51760 (0.0011) -[2023-10-10 14:42:23,504][76542] Updated weights for policy 1, policy_version 51770 (0.0010) -[2023-10-10 14:42:26,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 106102784. Throughput: 0: 1829.2, 1: 1807.0. Samples: 26534768. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-10 14:42:26,077][75634] Avg episode reward: [(0, '40.680'), (1, '35.450')] -[2023-10-10 14:42:26,121][76543] Updated weights for policy 0, policy_version 51843 (0.0009) -[2023-10-10 14:42:26,491][76543] Updated weights for policy 0, policy_version 51853 (0.0009) -[2023-10-10 14:42:26,855][76543] Updated weights for policy 0, policy_version 51863 (0.0008) -[2023-10-10 14:42:27,291][76542] Updated weights for policy 1, policy_version 51780 (0.0010) -[2023-10-10 14:42:27,660][76542] Updated weights for policy 1, policy_version 51790 (0.0011) -[2023-10-10 14:42:28,035][76542] Updated weights for policy 1, policy_version 51800 (0.0010) -[2023-10-10 14:42:30,497][76543] Updated weights for policy 0, policy_version 51873 (0.0008) -[2023-10-10 14:42:30,859][76543] Updated weights for policy 0, policy_version 51883 (0.0010) -[2023-10-10 14:42:31,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.6, 300 sec: 14440.1). Total num frames: 106168320. Throughput: 0: 1827.9, 1: 1802.0. Samples: 26557496. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-10 14:42:31,076][75634] Avg episode reward: [(0, '39.050'), (1, '35.980')] -[2023-10-10 14:42:31,086][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000051808_53051392.pth... -[2023-10-10 14:42:31,117][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000050112_51314688.pth -[2023-10-10 14:42:31,234][76543] Updated weights for policy 0, policy_version 51893 (0.0011) -[2023-10-10 14:42:31,599][76543] Updated weights for policy 0, policy_version 51903 (0.0011) -[2023-10-10 14:42:31,635][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000051904_53149696.pth... -[2023-10-10 14:42:31,673][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000050176_51380224.pth -[2023-10-10 14:42:31,914][76542] Updated weights for policy 1, policy_version 51810 (0.0007) -[2023-10-10 14:42:32,288][76542] Updated weights for policy 1, policy_version 51820 (0.0008) -[2023-10-10 14:42:32,660][76542] Updated weights for policy 1, policy_version 51830 (0.0008) -[2023-10-10 14:42:33,015][76542] Updated weights for policy 1, policy_version 51840 (0.0008) -[2023-10-10 14:42:35,328][76543] Updated weights for policy 0, policy_version 51913 (0.0009) -[2023-10-10 14:42:35,705][76543] Updated weights for policy 0, policy_version 51923 (0.0010) -[2023-10-10 14:42:36,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 106233856. Throughput: 0: 1826.6, 1: 1802.2. Samples: 26567322. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-10 14:42:36,076][75634] Avg episode reward: [(0, '32.380'), (1, '34.360')] -[2023-10-10 14:42:36,085][76543] Updated weights for policy 0, policy_version 51933 (0.0008) -[2023-10-10 14:42:36,741][76542] Updated weights for policy 1, policy_version 51850 (0.0010) -[2023-10-10 14:42:37,115][76542] Updated weights for policy 1, policy_version 51860 (0.0009) -[2023-10-10 14:42:37,488][76542] Updated weights for policy 1, policy_version 51870 (0.0008) -[2023-10-10 14:42:39,825][76543] Updated weights for policy 0, policy_version 51943 (0.0010) -[2023-10-10 14:42:40,193][76543] Updated weights for policy 0, policy_version 51953 (0.0008) -[2023-10-10 14:42:40,560][76543] Updated weights for policy 0, policy_version 51963 (0.0009) -[2023-10-10 14:42:41,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 106332160. Throughput: 0: 1824.9, 1: 1798.1. Samples: 26590024. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-10 14:42:41,076][75634] Avg episode reward: [(0, '29.860'), (1, '35.450')] -[2023-10-10 14:42:41,161][76542] Updated weights for policy 1, policy_version 51880 (0.0009) -[2023-10-10 14:42:41,519][76542] Updated weights for policy 1, policy_version 51890 (0.0007) -[2023-10-10 14:42:41,883][76542] Updated weights for policy 1, policy_version 51900 (0.0007) -[2023-10-10 14:42:44,205][76543] Updated weights for policy 0, policy_version 51973 (0.0008) -[2023-10-10 14:42:44,571][76543] Updated weights for policy 0, policy_version 51983 (0.0007) -[2023-10-10 14:42:44,939][76543] Updated weights for policy 0, policy_version 51993 (0.0007) -[2023-10-10 14:42:45,681][76542] Updated weights for policy 1, policy_version 51910 (0.0007) -[2023-10-10 14:42:46,052][76542] Updated weights for policy 1, policy_version 51920 (0.0007) -[2023-10-10 14:42:46,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 106397696. Throughput: 0: 1825.7, 1: 1813.0. Samples: 26611388. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-10 14:42:46,076][75634] Avg episode reward: [(0, '33.960'), (1, '32.670')] -[2023-10-10 14:42:46,416][76542] Updated weights for policy 1, policy_version 51930 (0.0009) -[2023-10-10 14:42:48,632][76543] Updated weights for policy 0, policy_version 52003 (0.0007) -[2023-10-10 14:42:48,997][76543] Updated weights for policy 0, policy_version 52013 (0.0007) -[2023-10-10 14:42:49,377][76543] Updated weights for policy 0, policy_version 52023 (0.0009) -[2023-10-10 14:42:50,069][76542] Updated weights for policy 1, policy_version 51940 (0.0008) -[2023-10-10 14:42:50,433][76542] Updated weights for policy 1, policy_version 51950 (0.0009) -[2023-10-10 14:42:50,799][76542] Updated weights for policy 1, policy_version 51960 (0.0008) -[2023-10-10 14:42:51,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 106463232. Throughput: 0: 1829.8, 1: 1802.5. Samples: 26623126. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-10 14:42:51,076][75634] Avg episode reward: [(0, '35.690'), (1, '35.260')] -[2023-10-10 14:42:53,017][76543] Updated weights for policy 0, policy_version 52033 (0.0009) -[2023-10-10 14:42:53,381][76543] Updated weights for policy 0, policy_version 52043 (0.0007) -[2023-10-10 14:42:53,752][76543] Updated weights for policy 0, policy_version 52053 (0.0008) -[2023-10-10 14:42:54,117][76543] Updated weights for policy 0, policy_version 52063 (0.0007) -[2023-10-10 14:42:54,535][76542] Updated weights for policy 1, policy_version 51970 (0.0009) -[2023-10-10 14:42:54,893][76542] Updated weights for policy 1, policy_version 51980 (0.0011) -[2023-10-10 14:42:55,259][76542] Updated weights for policy 1, policy_version 51990 (0.0010) -[2023-10-10 14:42:55,628][76542] Updated weights for policy 1, policy_version 52000 (0.0007) -[2023-10-10 14:42:56,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 106561536. Throughput: 0: 1829.8, 1: 1817.0. Samples: 26644352. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-10 14:42:56,076][75634] Avg episode reward: [(0, '34.000'), (1, '36.020')] -[2023-10-10 14:42:57,594][76543] Updated weights for policy 0, policy_version 52073 (0.0009) -[2023-10-10 14:42:57,967][76543] Updated weights for policy 0, policy_version 52083 (0.0009) -[2023-10-10 14:42:58,328][76543] Updated weights for policy 0, policy_version 52093 (0.0007) -[2023-10-10 14:42:59,089][76542] Updated weights for policy 1, policy_version 52010 (0.0010) -[2023-10-10 14:42:59,459][76542] Updated weights for policy 1, policy_version 52020 (0.0007) -[2023-10-10 14:42:59,824][76542] Updated weights for policy 1, policy_version 52030 (0.0008) -[2023-10-10 14:43:01,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 106627072. Throughput: 0: 1839.0, 1: 1816.9. Samples: 26666686. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-10 14:43:01,077][75634] Avg episode reward: [(0, '40.520'), (1, '34.710')] -[2023-10-10 14:43:01,914][76543] Updated weights for policy 0, policy_version 52103 (0.0009) -[2023-10-10 14:43:02,290][76543] Updated weights for policy 0, policy_version 52113 (0.0009) -[2023-10-10 14:43:02,666][76543] Updated weights for policy 0, policy_version 52123 (0.0007) -[2023-10-10 14:43:03,384][76542] Updated weights for policy 1, policy_version 52040 (0.0007) -[2023-10-10 14:43:03,755][76542] Updated weights for policy 1, policy_version 52050 (0.0008) -[2023-10-10 14:43:04,127][76542] Updated weights for policy 1, policy_version 52060 (0.0007) -[2023-10-10 14:43:06,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 106692608. Throughput: 0: 1836.0, 1: 1823.9. Samples: 26677644. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-10 14:43:06,077][75634] Avg episode reward: [(0, '40.580'), (1, '34.230')] -[2023-10-10 14:43:06,301][76543] Updated weights for policy 0, policy_version 52133 (0.0009) -[2023-10-10 14:43:06,671][76543] Updated weights for policy 0, policy_version 52143 (0.0007) -[2023-10-10 14:43:07,049][76543] Updated weights for policy 0, policy_version 52153 (0.0007) -[2023-10-10 14:43:07,800][76542] Updated weights for policy 1, policy_version 52070 (0.0009) -[2023-10-10 14:43:08,170][76542] Updated weights for policy 1, policy_version 52080 (0.0011) -[2023-10-10 14:43:08,532][76542] Updated weights for policy 1, policy_version 52090 (0.0012) -[2023-10-10 14:43:10,654][76543] Updated weights for policy 0, policy_version 52163 (0.0009) -[2023-10-10 14:43:11,024][76543] Updated weights for policy 0, policy_version 52173 (0.0011) -[2023-10-10 14:43:11,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 106758144. Throughput: 0: 1848.1, 1: 1820.3. Samples: 26699844. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-10 14:43:11,076][75634] Avg episode reward: [(0, '40.470'), (1, '35.170')] -[2023-10-10 14:43:11,395][76543] Updated weights for policy 0, policy_version 52183 (0.0008) -[2023-10-10 14:43:12,370][76542] Updated weights for policy 1, policy_version 52100 (0.0010) -[2023-10-10 14:43:12,744][76542] Updated weights for policy 1, policy_version 52110 (0.0008) -[2023-10-10 14:43:13,111][76542] Updated weights for policy 1, policy_version 52120 (0.0009) -[2023-10-10 14:43:14,893][76543] Updated weights for policy 0, policy_version 52193 (0.0009) -[2023-10-10 14:43:15,258][76543] Updated weights for policy 0, policy_version 52203 (0.0011) -[2023-10-10 14:43:15,629][76543] Updated weights for policy 0, policy_version 52213 (0.0010) -[2023-10-10 14:43:16,000][76543] Updated weights for policy 0, policy_version 52223 (0.0008) -[2023-10-10 14:43:16,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 106856448. Throughput: 0: 1844.9, 1: 1822.9. Samples: 26722548. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:43:16,076][75634] Avg episode reward: [(0, '39.120'), (1, '36.390')] -[2023-10-10 14:43:16,741][76542] Updated weights for policy 1, policy_version 52130 (0.0007) -[2023-10-10 14:43:17,108][76542] Updated weights for policy 1, policy_version 52140 (0.0008) -[2023-10-10 14:43:17,479][76542] Updated weights for policy 1, policy_version 52150 (0.0009) -[2023-10-10 14:43:17,856][76542] Updated weights for policy 1, policy_version 52160 (0.0008) -[2023-10-10 14:43:19,829][76543] Updated weights for policy 0, policy_version 52233 (0.0009) -[2023-10-10 14:43:20,199][76543] Updated weights for policy 0, policy_version 52243 (0.0007) -[2023-10-10 14:43:20,567][76543] Updated weights for policy 0, policy_version 52253 (0.0009) -[2023-10-10 14:43:21,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 106921984. Throughput: 0: 1854.7, 1: 1827.5. Samples: 26733022. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:43:21,077][75634] Avg episode reward: [(0, '37.730'), (1, '33.490')] -[2023-10-10 14:43:21,372][76542] Updated weights for policy 1, policy_version 52170 (0.0008) -[2023-10-10 14:43:21,750][76542] Updated weights for policy 1, policy_version 52180 (0.0009) -[2023-10-10 14:43:22,111][76542] Updated weights for policy 1, policy_version 52190 (0.0008) -[2023-10-10 14:43:24,203][76543] Updated weights for policy 0, policy_version 52263 (0.0009) -[2023-10-10 14:43:24,580][76543] Updated weights for policy 0, policy_version 52273 (0.0007) -[2023-10-10 14:43:24,957][76543] Updated weights for policy 0, policy_version 52283 (0.0009) -[2023-10-10 14:43:25,779][76542] Updated weights for policy 1, policy_version 52200 (0.0010) -[2023-10-10 14:43:26,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 106987520. Throughput: 0: 1849.3, 1: 1832.0. Samples: 26755682. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:43:26,076][75634] Avg episode reward: [(0, '36.440'), (1, '33.180')] -[2023-10-10 14:43:26,141][76542] Updated weights for policy 1, policy_version 52210 (0.0010) -[2023-10-10 14:43:26,519][76542] Updated weights for policy 1, policy_version 52220 (0.0007) -[2023-10-10 14:43:28,477][76543] Updated weights for policy 0, policy_version 52293 (0.0011) -[2023-10-10 14:43:28,843][76543] Updated weights for policy 0, policy_version 52303 (0.0011) -[2023-10-10 14:43:29,219][76543] Updated weights for policy 0, policy_version 52313 (0.0008) -[2023-10-10 14:43:30,366][76542] Updated weights for policy 1, policy_version 52230 (0.0008) -[2023-10-10 14:43:30,744][76542] Updated weights for policy 1, policy_version 52240 (0.0009) -[2023-10-10 14:43:31,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 107053056. Throughput: 0: 1850.8, 1: 1818.2. Samples: 26776492. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:43:31,077][75634] Avg episode reward: [(0, '35.110'), (1, '36.110')] -[2023-10-10 14:43:31,113][76542] Updated weights for policy 1, policy_version 52250 (0.0009) -[2023-10-10 14:43:32,924][76543] Updated weights for policy 0, policy_version 52323 (0.0011) -[2023-10-10 14:43:33,295][76543] Updated weights for policy 0, policy_version 52333 (0.0012) -[2023-10-10 14:43:33,674][76543] Updated weights for policy 0, policy_version 52343 (0.0008) -[2023-10-10 14:43:34,803][76542] Updated weights for policy 1, policy_version 52260 (0.0008) -[2023-10-10 14:43:35,167][76542] Updated weights for policy 1, policy_version 52270 (0.0011) -[2023-10-10 14:43:35,527][76542] Updated weights for policy 1, policy_version 52280 (0.0010) -[2023-10-10 14:43:36,076][75634] Fps is (10 sec: 16384.1, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 107151360. Throughput: 0: 1841.1, 1: 1826.2. Samples: 26788154. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:43:36,076][75634] Avg episode reward: [(0, '30.150'), (1, '36.260')] -[2023-10-10 14:43:37,442][76543] Updated weights for policy 0, policy_version 52353 (0.0007) -[2023-10-10 14:43:37,825][76543] Updated weights for policy 0, policy_version 52363 (0.0010) -[2023-10-10 14:43:38,183][76543] Updated weights for policy 0, policy_version 52373 (0.0010) -[2023-10-10 14:43:38,554][76543] Updated weights for policy 0, policy_version 52383 (0.0011) -[2023-10-10 14:43:39,097][76542] Updated weights for policy 1, policy_version 52290 (0.0010) -[2023-10-10 14:43:39,461][76542] Updated weights for policy 1, policy_version 52300 (0.0009) -[2023-10-10 14:43:39,821][76542] Updated weights for policy 1, policy_version 52310 (0.0009) -[2023-10-10 14:43:40,195][76542] Updated weights for policy 1, policy_version 52320 (0.0007) -[2023-10-10 14:43:41,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 107216896. Throughput: 0: 1846.2, 1: 1821.6. Samples: 26809402. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:43:41,077][75634] Avg episode reward: [(0, '31.850'), (1, '34.980')] -[2023-10-10 14:43:42,313][76543] Updated weights for policy 0, policy_version 52393 (0.0011) -[2023-10-10 14:43:42,693][76543] Updated weights for policy 0, policy_version 52403 (0.0010) -[2023-10-10 14:43:43,068][76543] Updated weights for policy 0, policy_version 52413 (0.0007) -[2023-10-10 14:43:43,909][76542] Updated weights for policy 1, policy_version 52330 (0.0012) -[2023-10-10 14:43:44,274][76542] Updated weights for policy 1, policy_version 52340 (0.0011) -[2023-10-10 14:43:44,644][76542] Updated weights for policy 1, policy_version 52350 (0.0009) -[2023-10-10 14:43:46,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 107282432. Throughput: 0: 1832.8, 1: 1825.2. Samples: 26831296. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:43:46,076][75634] Avg episode reward: [(0, '36.310'), (1, '36.450')] -[2023-10-10 14:43:46,820][76543] Updated weights for policy 0, policy_version 52423 (0.0009) -[2023-10-10 14:43:47,186][76543] Updated weights for policy 0, policy_version 52433 (0.0010) -[2023-10-10 14:43:47,564][76543] Updated weights for policy 0, policy_version 52443 (0.0010) -[2023-10-10 14:43:48,364][76542] Updated weights for policy 1, policy_version 52360 (0.0008) -[2023-10-10 14:43:48,719][76542] Updated weights for policy 1, policy_version 52370 (0.0010) -[2023-10-10 14:43:49,088][76542] Updated weights for policy 1, policy_version 52380 (0.0009) -[2023-10-10 14:43:51,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 107347968. Throughput: 0: 1825.9, 1: 1818.5. Samples: 26841640. Policy #0 lag: (min: 32.0, avg: 54.4, max: 56.0) -[2023-10-10 14:43:51,077][75634] Avg episode reward: [(0, '36.560'), (1, '31.240')] -[2023-10-10 14:43:51,134][76543] Updated weights for policy 0, policy_version 52453 (0.0009) -[2023-10-10 14:43:51,499][76543] Updated weights for policy 0, policy_version 52463 (0.0008) -[2023-10-10 14:43:51,867][76543] Updated weights for policy 0, policy_version 52473 (0.0009) -[2023-10-10 14:43:52,743][76542] Updated weights for policy 1, policy_version 52390 (0.0010) -[2023-10-10 14:43:53,112][76542] Updated weights for policy 1, policy_version 52400 (0.0010) -[2023-10-10 14:43:53,490][76542] Updated weights for policy 1, policy_version 52410 (0.0008) -[2023-10-10 14:43:55,570][76543] Updated weights for policy 0, policy_version 52483 (0.0011) -[2023-10-10 14:43:55,938][76543] Updated weights for policy 0, policy_version 52493 (0.0009) -[2023-10-10 14:43:56,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 107413504. Throughput: 0: 1828.2, 1: 1821.6. Samples: 26864086. Policy #0 lag: (min: 32.0, avg: 54.4, max: 56.0) -[2023-10-10 14:43:56,076][75634] Avg episode reward: [(0, '35.100'), (1, '32.190')] -[2023-10-10 14:43:56,305][76543] Updated weights for policy 0, policy_version 52503 (0.0008) -[2023-10-10 14:43:57,111][76542] Updated weights for policy 1, policy_version 52420 (0.0009) -[2023-10-10 14:43:57,476][76542] Updated weights for policy 1, policy_version 52430 (0.0009) -[2023-10-10 14:43:57,850][76542] Updated weights for policy 1, policy_version 52440 (0.0008) -[2023-10-10 14:43:59,939][76543] Updated weights for policy 0, policy_version 52513 (0.0010) -[2023-10-10 14:44:00,310][76543] Updated weights for policy 0, policy_version 52523 (0.0010) -[2023-10-10 14:44:00,669][76543] Updated weights for policy 0, policy_version 52533 (0.0010) -[2023-10-10 14:44:01,050][76543] Updated weights for policy 0, policy_version 52543 (0.0010) -[2023-10-10 14:44:01,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 107479040. Throughput: 0: 1820.1, 1: 1830.2. Samples: 26886812. Policy #0 lag: (min: 32.0, avg: 54.4, max: 56.0) -[2023-10-10 14:44:01,076][75634] Avg episode reward: [(0, '36.540'), (1, '33.360')] -[2023-10-10 14:44:01,449][76542] Updated weights for policy 1, policy_version 52450 (0.0011) -[2023-10-10 14:44:01,807][76542] Updated weights for policy 1, policy_version 52460 (0.0007) -[2023-10-10 14:44:02,187][76542] Updated weights for policy 1, policy_version 52470 (0.0008) -[2023-10-10 14:44:02,546][76542] Updated weights for policy 1, policy_version 52480 (0.0009) -[2023-10-10 14:44:04,574][76543] Updated weights for policy 0, policy_version 52553 (0.0010) -[2023-10-10 14:44:04,947][76543] Updated weights for policy 0, policy_version 52563 (0.0007) -[2023-10-10 14:44:05,327][76543] Updated weights for policy 0, policy_version 52573 (0.0007) -[2023-10-10 14:44:06,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 107577344. Throughput: 0: 1824.2, 1: 1825.9. Samples: 26897278. Policy #0 lag: (min: 32.0, avg: 54.4, max: 56.0) -[2023-10-10 14:44:06,077][75634] Avg episode reward: [(0, '35.810'), (1, '33.990')] -[2023-10-10 14:44:06,173][76542] Updated weights for policy 1, policy_version 52490 (0.0010) -[2023-10-10 14:44:06,541][76542] Updated weights for policy 1, policy_version 52500 (0.0011) -[2023-10-10 14:44:06,915][76542] Updated weights for policy 1, policy_version 52510 (0.0010) -[2023-10-10 14:44:09,105][76543] Updated weights for policy 0, policy_version 52583 (0.0007) -[2023-10-10 14:44:09,487][76543] Updated weights for policy 0, policy_version 52593 (0.0007) -[2023-10-10 14:44:09,868][76543] Updated weights for policy 0, policy_version 52603 (0.0009) -[2023-10-10 14:44:10,739][76542] Updated weights for policy 1, policy_version 52520 (0.0008) -[2023-10-10 14:44:11,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 107642880. Throughput: 0: 1814.6, 1: 1825.1. Samples: 26919468. Policy #0 lag: (min: 32.0, avg: 54.4, max: 56.0) -[2023-10-10 14:44:11,077][75634] Avg episode reward: [(0, '38.340'), (1, '34.090')] -[2023-10-10 14:44:11,101][76542] Updated weights for policy 1, policy_version 52530 (0.0009) -[2023-10-10 14:44:11,469][76542] Updated weights for policy 1, policy_version 52540 (0.0007) -[2023-10-10 14:44:13,504][76543] Updated weights for policy 0, policy_version 52613 (0.0009) -[2023-10-10 14:44:13,872][76543] Updated weights for policy 0, policy_version 52623 (0.0010) -[2023-10-10 14:44:14,248][76543] Updated weights for policy 0, policy_version 52633 (0.0009) -[2023-10-10 14:44:15,181][76542] Updated weights for policy 1, policy_version 52550 (0.0008) -[2023-10-10 14:44:15,559][76542] Updated weights for policy 1, policy_version 52560 (0.0009) -[2023-10-10 14:44:15,926][76542] Updated weights for policy 1, policy_version 52570 (0.0007) -[2023-10-10 14:44:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 107708416. Throughput: 0: 1818.0, 1: 1829.3. Samples: 26940620. Policy #0 lag: (min: 32.0, avg: 54.4, max: 56.0) -[2023-10-10 14:44:16,077][75634] Avg episode reward: [(0, '32.910'), (1, '30.640')] -[2023-10-10 14:44:17,812][76543] Updated weights for policy 0, policy_version 52643 (0.0009) -[2023-10-10 14:44:18,192][76543] Updated weights for policy 0, policy_version 52653 (0.0009) -[2023-10-10 14:44:18,571][76543] Updated weights for policy 0, policy_version 52663 (0.0009) -[2023-10-10 14:44:19,537][76542] Updated weights for policy 1, policy_version 52580 (0.0007) -[2023-10-10 14:44:19,907][76542] Updated weights for policy 1, policy_version 52590 (0.0009) -[2023-10-10 14:44:20,283][76542] Updated weights for policy 1, policy_version 52600 (0.0007) -[2023-10-10 14:44:21,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 107806720. Throughput: 0: 1816.7, 1: 1836.6. Samples: 26952556. Policy #0 lag: (min: 32.0, avg: 54.4, max: 56.0) -[2023-10-10 14:44:21,077][75634] Avg episode reward: [(0, '35.340'), (1, '31.980')] -[2023-10-10 14:44:22,439][76543] Updated weights for policy 0, policy_version 52673 (0.0007) -[2023-10-10 14:44:22,803][76543] Updated weights for policy 0, policy_version 52683 (0.0009) -[2023-10-10 14:44:23,175][76543] Updated weights for policy 0, policy_version 52693 (0.0007) -[2023-10-10 14:44:23,551][76543] Updated weights for policy 0, policy_version 52703 (0.0007) -[2023-10-10 14:44:23,957][76542] Updated weights for policy 1, policy_version 52610 (0.0007) -[2023-10-10 14:44:24,328][76542] Updated weights for policy 1, policy_version 52620 (0.0008) -[2023-10-10 14:44:24,694][76542] Updated weights for policy 1, policy_version 52630 (0.0008) -[2023-10-10 14:44:25,060][76542] Updated weights for policy 1, policy_version 52640 (0.0008) -[2023-10-10 14:44:26,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 107872256. Throughput: 0: 1821.0, 1: 1826.0. Samples: 26973516. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:44:26,077][75634] Avg episode reward: [(0, '37.130'), (1, '35.060')] -[2023-10-10 14:44:27,240][76543] Updated weights for policy 0, policy_version 52713 (0.0010) -[2023-10-10 14:44:27,618][76543] Updated weights for policy 0, policy_version 52723 (0.0009) -[2023-10-10 14:44:27,977][76543] Updated weights for policy 0, policy_version 52733 (0.0009) -[2023-10-10 14:44:28,692][76542] Updated weights for policy 1, policy_version 52650 (0.0007) -[2023-10-10 14:44:29,061][76542] Updated weights for policy 1, policy_version 52660 (0.0007) -[2023-10-10 14:44:29,426][76542] Updated weights for policy 1, policy_version 52670 (0.0011) -[2023-10-10 14:44:31,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 107937792. Throughput: 0: 1829.2, 1: 1831.1. Samples: 26996008. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:44:31,077][75634] Avg episode reward: [(0, '38.390'), (1, '32.600')] -[2023-10-10 14:44:31,091][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000052672_53936128.pth... -[2023-10-10 14:44:31,091][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000052736_54001664.pth... -[2023-10-10 14:44:31,129][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000051040_52264960.pth -[2023-10-10 14:44:31,129][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000050976_52199424.pth -[2023-10-10 14:44:31,547][76543] Updated weights for policy 0, policy_version 52743 (0.0010) -[2023-10-10 14:44:31,913][76543] Updated weights for policy 0, policy_version 52753 (0.0008) -[2023-10-10 14:44:32,287][76543] Updated weights for policy 0, policy_version 52763 (0.0008) -[2023-10-10 14:44:33,134][76542] Updated weights for policy 1, policy_version 52680 (0.0010) -[2023-10-10 14:44:33,505][76542] Updated weights for policy 1, policy_version 52690 (0.0009) -[2023-10-10 14:44:33,861][76542] Updated weights for policy 1, policy_version 52700 (0.0010) -[2023-10-10 14:44:35,996][76543] Updated weights for policy 0, policy_version 52773 (0.0009) -[2023-10-10 14:44:36,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 108003328. Throughput: 0: 1831.7, 1: 1827.3. Samples: 27006298. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:44:36,077][75634] Avg episode reward: [(0, '38.100'), (1, '31.320')] -[2023-10-10 14:44:36,379][76543] Updated weights for policy 0, policy_version 52783 (0.0007) -[2023-10-10 14:44:36,746][76543] Updated weights for policy 0, policy_version 52793 (0.0007) -[2023-10-10 14:44:37,400][76542] Updated weights for policy 1, policy_version 52710 (0.0011) -[2023-10-10 14:44:37,765][76542] Updated weights for policy 1, policy_version 52720 (0.0009) -[2023-10-10 14:44:38,126][76542] Updated weights for policy 1, policy_version 52730 (0.0008) -[2023-10-10 14:44:40,370][76543] Updated weights for policy 0, policy_version 52803 (0.0008) -[2023-10-10 14:44:40,744][76543] Updated weights for policy 0, policy_version 52813 (0.0008) -[2023-10-10 14:44:41,076][75634] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 108068864. Throughput: 0: 1828.0, 1: 1836.2. Samples: 27028976. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:44:41,076][75634] Avg episode reward: [(0, '34.830'), (1, '32.380')] -[2023-10-10 14:44:41,122][76543] Updated weights for policy 0, policy_version 52823 (0.0007) -[2023-10-10 14:44:41,825][76542] Updated weights for policy 1, policy_version 52740 (0.0009) -[2023-10-10 14:44:42,194][76542] Updated weights for policy 1, policy_version 52750 (0.0009) -[2023-10-10 14:44:42,564][76542] Updated weights for policy 1, policy_version 52760 (0.0008) -[2023-10-10 14:44:44,782][76543] Updated weights for policy 0, policy_version 52833 (0.0007) -[2023-10-10 14:44:45,147][76543] Updated weights for policy 0, policy_version 52843 (0.0009) -[2023-10-10 14:44:45,516][76543] Updated weights for policy 0, policy_version 52853 (0.0009) -[2023-10-10 14:44:45,889][76543] Updated weights for policy 0, policy_version 52863 (0.0007) -[2023-10-10 14:44:46,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 108167168. Throughput: 0: 1824.7, 1: 1829.3. Samples: 27051242. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:44:46,076][75634] Avg episode reward: [(0, '34.410'), (1, '35.180')] -[2023-10-10 14:44:46,226][76542] Updated weights for policy 1, policy_version 52770 (0.0008) -[2023-10-10 14:44:46,586][76542] Updated weights for policy 1, policy_version 52780 (0.0009) -[2023-10-10 14:44:46,968][76542] Updated weights for policy 1, policy_version 52790 (0.0012) -[2023-10-10 14:44:47,331][76542] Updated weights for policy 1, policy_version 52800 (0.0010) -[2023-10-10 14:44:49,524][76543] Updated weights for policy 0, policy_version 52873 (0.0009) -[2023-10-10 14:44:49,891][76543] Updated weights for policy 0, policy_version 52883 (0.0009) -[2023-10-10 14:44:50,267][76543] Updated weights for policy 0, policy_version 52893 (0.0007) -[2023-10-10 14:44:50,960][76542] Updated weights for policy 1, policy_version 52810 (0.0008) -[2023-10-10 14:44:51,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 108232704. Throughput: 0: 1824.4, 1: 1830.1. Samples: 27061732. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:44:51,077][75634] Avg episode reward: [(0, '33.950'), (1, '37.500')] -[2023-10-10 14:44:51,325][76542] Updated weights for policy 1, policy_version 52820 (0.0008) -[2023-10-10 14:44:51,695][76542] Updated weights for policy 1, policy_version 52830 (0.0007) -[2023-10-10 14:44:53,897][76543] Updated weights for policy 0, policy_version 52903 (0.0009) -[2023-10-10 14:44:54,265][76543] Updated weights for policy 0, policy_version 52913 (0.0007) -[2023-10-10 14:44:54,632][76543] Updated weights for policy 0, policy_version 52923 (0.0009) -[2023-10-10 14:44:55,508][76542] Updated weights for policy 1, policy_version 52840 (0.0011) -[2023-10-10 14:44:55,886][76542] Updated weights for policy 1, policy_version 52850 (0.0008) -[2023-10-10 14:44:56,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 108298240. Throughput: 0: 1828.1, 1: 1832.6. Samples: 27084198. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:44:56,077][75634] Avg episode reward: [(0, '38.010'), (1, '35.190')] -[2023-10-10 14:44:56,256][76542] Updated weights for policy 1, policy_version 52860 (0.0009) -[2023-10-10 14:44:58,461][76543] Updated weights for policy 0, policy_version 52933 (0.0010) -[2023-10-10 14:44:58,852][76543] Updated weights for policy 0, policy_version 52943 (0.0007) -[2023-10-10 14:44:59,228][76543] Updated weights for policy 0, policy_version 52953 (0.0008) -[2023-10-10 14:45:00,142][76542] Updated weights for policy 1, policy_version 52870 (0.0007) -[2023-10-10 14:45:00,513][76542] Updated weights for policy 1, policy_version 52880 (0.0008) -[2023-10-10 14:45:00,877][76542] Updated weights for policy 1, policy_version 52890 (0.0008) -[2023-10-10 14:45:01,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 108363776. Throughput: 0: 1829.9, 1: 1821.3. Samples: 27104922. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:45:01,077][75634] Avg episode reward: [(0, '35.860'), (1, '38.230')] -[2023-10-10 14:45:02,727][76543] Updated weights for policy 0, policy_version 52963 (0.0011) -[2023-10-10 14:45:03,105][76543] Updated weights for policy 0, policy_version 52973 (0.0010) -[2023-10-10 14:45:03,478][76543] Updated weights for policy 0, policy_version 52983 (0.0009) -[2023-10-10 14:45:04,465][76542] Updated weights for policy 1, policy_version 52900 (0.0012) -[2023-10-10 14:45:04,831][76542] Updated weights for policy 1, policy_version 52910 (0.0009) -[2023-10-10 14:45:05,201][76542] Updated weights for policy 1, policy_version 52920 (0.0009) -[2023-10-10 14:45:06,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 108462080. Throughput: 0: 1825.7, 1: 1823.8. Samples: 27116782. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:45:06,076][75634] Avg episode reward: [(0, '38.780'), (1, '39.540')] -[2023-10-10 14:45:07,234][76543] Updated weights for policy 0, policy_version 52993 (0.0009) -[2023-10-10 14:45:07,607][76543] Updated weights for policy 0, policy_version 53003 (0.0010) -[2023-10-10 14:45:07,983][76543] Updated weights for policy 0, policy_version 53013 (0.0009) -[2023-10-10 14:45:08,357][76543] Updated weights for policy 0, policy_version 53023 (0.0007) -[2023-10-10 14:45:08,847][76542] Updated weights for policy 1, policy_version 52930 (0.0007) -[2023-10-10 14:45:09,212][76542] Updated weights for policy 1, policy_version 52940 (0.0007) -[2023-10-10 14:45:09,571][76542] Updated weights for policy 1, policy_version 52950 (0.0007) -[2023-10-10 14:45:09,935][76542] Updated weights for policy 1, policy_version 52960 (0.0008) -[2023-10-10 14:45:11,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 108527616. Throughput: 0: 1830.8, 1: 1825.2. Samples: 27138034. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:45:11,077][75634] Avg episode reward: [(0, '35.090'), (1, '37.200')] -[2023-10-10 14:45:11,856][76543] Updated weights for policy 0, policy_version 53033 (0.0010) -[2023-10-10 14:45:12,222][76543] Updated weights for policy 0, policy_version 53043 (0.0009) -[2023-10-10 14:45:12,599][76543] Updated weights for policy 0, policy_version 53053 (0.0010) -[2023-10-10 14:45:13,582][76542] Updated weights for policy 1, policy_version 52970 (0.0009) -[2023-10-10 14:45:13,947][76542] Updated weights for policy 1, policy_version 52980 (0.0010) -[2023-10-10 14:45:14,314][76542] Updated weights for policy 1, policy_version 52990 (0.0010) -[2023-10-10 14:45:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 108593152. Throughput: 0: 1827.4, 1: 1834.0. Samples: 27160770. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:45:16,077][75634] Avg episode reward: [(0, '32.630'), (1, '34.720')] -[2023-10-10 14:45:16,465][76543] Updated weights for policy 0, policy_version 53063 (0.0009) -[2023-10-10 14:45:16,845][76543] Updated weights for policy 0, policy_version 53073 (0.0009) -[2023-10-10 14:45:17,217][76543] Updated weights for policy 0, policy_version 53083 (0.0007) -[2023-10-10 14:45:17,842][76542] Updated weights for policy 1, policy_version 53000 (0.0010) -[2023-10-10 14:45:18,211][76542] Updated weights for policy 1, policy_version 53010 (0.0008) -[2023-10-10 14:45:18,580][76542] Updated weights for policy 1, policy_version 53020 (0.0007) -[2023-10-10 14:45:20,929][76543] Updated weights for policy 0, policy_version 53093 (0.0009) -[2023-10-10 14:45:21,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14662.3). Total num frames: 108658688. Throughput: 0: 1829.9, 1: 1824.6. Samples: 27170752. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:45:21,076][75634] Avg episode reward: [(0, '35.580'), (1, '35.350')] -[2023-10-10 14:45:21,298][76543] Updated weights for policy 0, policy_version 53103 (0.0009) -[2023-10-10 14:45:21,674][76543] Updated weights for policy 0, policy_version 53113 (0.0009) -[2023-10-10 14:45:22,168][76542] Updated weights for policy 1, policy_version 53030 (0.0009) -[2023-10-10 14:45:22,541][76542] Updated weights for policy 1, policy_version 53040 (0.0011) -[2023-10-10 14:45:22,910][76542] Updated weights for policy 1, policy_version 53050 (0.0010) -[2023-10-10 14:45:25,341][76543] Updated weights for policy 0, policy_version 53123 (0.0009) -[2023-10-10 14:45:25,707][76543] Updated weights for policy 0, policy_version 53133 (0.0010) -[2023-10-10 14:45:26,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 108724224. Throughput: 0: 1826.0, 1: 1836.3. Samples: 27193782. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:45:26,077][75634] Avg episode reward: [(0, '36.880'), (1, '36.050')] -[2023-10-10 14:45:26,082][76543] Updated weights for policy 0, policy_version 53143 (0.0010) -[2023-10-10 14:45:26,464][76542] Updated weights for policy 1, policy_version 53060 (0.0007) -[2023-10-10 14:45:26,817][76542] Updated weights for policy 1, policy_version 53070 (0.0009) -[2023-10-10 14:45:27,189][76542] Updated weights for policy 1, policy_version 53080 (0.0009) -[2023-10-10 14:45:29,775][76543] Updated weights for policy 0, policy_version 53153 (0.0008) -[2023-10-10 14:45:30,150][76543] Updated weights for policy 0, policy_version 53163 (0.0007) -[2023-10-10 14:45:30,523][76543] Updated weights for policy 0, policy_version 53173 (0.0008) -[2023-10-10 14:45:30,817][76542] Updated weights for policy 1, policy_version 53090 (0.0010) -[2023-10-10 14:45:30,886][76543] Updated weights for policy 0, policy_version 53183 (0.0008) -[2023-10-10 14:45:31,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 108822528. Throughput: 0: 1823.3, 1: 1836.7. Samples: 27215940. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:45:31,077][75634] Avg episode reward: [(0, '32.770'), (1, '33.790')] -[2023-10-10 14:45:31,168][76542] Updated weights for policy 1, policy_version 53100 (0.0009) -[2023-10-10 14:45:31,544][76542] Updated weights for policy 1, policy_version 53110 (0.0009) -[2023-10-10 14:45:31,910][76542] Updated weights for policy 1, policy_version 53120 (0.0008) -[2023-10-10 14:45:34,430][76543] Updated weights for policy 0, policy_version 53193 (0.0009) -[2023-10-10 14:45:34,790][76543] Updated weights for policy 0, policy_version 53203 (0.0011) -[2023-10-10 14:45:35,170][76543] Updated weights for policy 0, policy_version 53213 (0.0009) -[2023-10-10 14:45:35,582][76542] Updated weights for policy 1, policy_version 53130 (0.0010) -[2023-10-10 14:45:35,952][76542] Updated weights for policy 1, policy_version 53140 (0.0009) -[2023-10-10 14:45:36,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 108888064. Throughput: 0: 1829.6, 1: 1834.9. Samples: 27226636. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:45:36,077][75634] Avg episode reward: [(0, '35.310'), (1, '34.680')] -[2023-10-10 14:45:36,315][76542] Updated weights for policy 1, policy_version 53150 (0.0007) -[2023-10-10 14:45:38,871][76543] Updated weights for policy 0, policy_version 53223 (0.0007) -[2023-10-10 14:45:39,243][76543] Updated weights for policy 0, policy_version 53233 (0.0007) -[2023-10-10 14:45:39,615][76543] Updated weights for policy 0, policy_version 53243 (0.0010) -[2023-10-10 14:45:39,995][76542] Updated weights for policy 1, policy_version 53160 (0.0008) -[2023-10-10 14:45:40,358][76542] Updated weights for policy 1, policy_version 53170 (0.0008) -[2023-10-10 14:45:40,732][76542] Updated weights for policy 1, policy_version 53180 (0.0008) -[2023-10-10 14:45:41,076][75634] Fps is (10 sec: 16384.2, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 108986368. Throughput: 0: 1823.0, 1: 1835.6. Samples: 27248834. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:45:41,076][75634] Avg episode reward: [(0, '31.450'), (1, '32.640')] -[2023-10-10 14:45:43,184][76543] Updated weights for policy 0, policy_version 53253 (0.0008) -[2023-10-10 14:45:43,558][76543] Updated weights for policy 0, policy_version 53263 (0.0008) -[2023-10-10 14:45:43,935][76543] Updated weights for policy 0, policy_version 53273 (0.0009) -[2023-10-10 14:45:44,505][76542] Updated weights for policy 1, policy_version 53190 (0.0009) -[2023-10-10 14:45:44,879][76542] Updated weights for policy 1, policy_version 53200 (0.0008) -[2023-10-10 14:45:45,247][76542] Updated weights for policy 1, policy_version 53210 (0.0011) -[2023-10-10 14:45:46,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 109051904. Throughput: 0: 1832.0, 1: 1828.7. Samples: 27269652. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:45:46,077][75634] Avg episode reward: [(0, '34.810'), (1, '33.960')] -[2023-10-10 14:45:47,674][76543] Updated weights for policy 0, policy_version 53283 (0.0008) -[2023-10-10 14:45:48,045][76543] Updated weights for policy 0, policy_version 53293 (0.0010) -[2023-10-10 14:45:48,423][76543] Updated weights for policy 0, policy_version 53303 (0.0012) -[2023-10-10 14:45:49,128][76542] Updated weights for policy 1, policy_version 53220 (0.0011) -[2023-10-10 14:45:49,507][76542] Updated weights for policy 1, policy_version 53230 (0.0009) -[2023-10-10 14:45:49,878][76542] Updated weights for policy 1, policy_version 53240 (0.0009) -[2023-10-10 14:45:51,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 109117440. Throughput: 0: 1828.8, 1: 1833.7. Samples: 27281598. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:45:51,077][75634] Avg episode reward: [(0, '37.780'), (1, '35.450')] -[2023-10-10 14:45:51,971][76543] Updated weights for policy 0, policy_version 53313 (0.0010) -[2023-10-10 14:45:52,348][76543] Updated weights for policy 0, policy_version 53323 (0.0008) -[2023-10-10 14:45:52,726][76543] Updated weights for policy 0, policy_version 53333 (0.0008) -[2023-10-10 14:45:53,094][76543] Updated weights for policy 0, policy_version 53343 (0.0009) -[2023-10-10 14:45:53,672][76542] Updated weights for policy 1, policy_version 53250 (0.0010) -[2023-10-10 14:45:54,042][76542] Updated weights for policy 1, policy_version 53260 (0.0011) -[2023-10-10 14:45:54,425][76542] Updated weights for policy 1, policy_version 53270 (0.0012) -[2023-10-10 14:45:54,786][76542] Updated weights for policy 1, policy_version 53280 (0.0011) -[2023-10-10 14:45:56,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 109182976. Throughput: 0: 1827.2, 1: 1818.5. Samples: 27302090. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:45:56,077][75634] Avg episode reward: [(0, '36.310'), (1, '33.400')] -[2023-10-10 14:45:56,624][76543] Updated weights for policy 0, policy_version 53353 (0.0007) -[2023-10-10 14:45:56,994][76543] Updated weights for policy 0, policy_version 53363 (0.0008) -[2023-10-10 14:45:57,362][76543] Updated weights for policy 0, policy_version 53373 (0.0009) -[2023-10-10 14:45:58,679][76542] Updated weights for policy 1, policy_version 53290 (0.0009) -[2023-10-10 14:45:59,055][76542] Updated weights for policy 1, policy_version 53300 (0.0008) -[2023-10-10 14:45:59,412][76542] Updated weights for policy 1, policy_version 53310 (0.0010) -[2023-10-10 14:46:01,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 109248512. Throughput: 0: 1825.4, 1: 1813.6. Samples: 27324524. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:46:01,076][75634] Avg episode reward: [(0, '36.030'), (1, '33.210')] -[2023-10-10 14:46:01,186][76543] Updated weights for policy 0, policy_version 53383 (0.0008) -[2023-10-10 14:46:01,563][76543] Updated weights for policy 0, policy_version 53393 (0.0008) -[2023-10-10 14:46:01,928][76543] Updated weights for policy 0, policy_version 53403 (0.0007) -[2023-10-10 14:46:03,021][76542] Updated weights for policy 1, policy_version 53320 (0.0007) -[2023-10-10 14:46:03,391][76542] Updated weights for policy 1, policy_version 53330 (0.0008) -[2023-10-10 14:46:03,760][76542] Updated weights for policy 1, policy_version 53340 (0.0010) -[2023-10-10 14:46:05,566][76543] Updated weights for policy 0, policy_version 53413 (0.0008) -[2023-10-10 14:46:05,931][76543] Updated weights for policy 0, policy_version 53423 (0.0010) -[2023-10-10 14:46:06,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14662.3). Total num frames: 109314048. Throughput: 0: 1827.2, 1: 1818.5. Samples: 27334808. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:46:06,076][75634] Avg episode reward: [(0, '32.420'), (1, '34.430')] -[2023-10-10 14:46:06,305][76543] Updated weights for policy 0, policy_version 53433 (0.0007) -[2023-10-10 14:46:07,588][76542] Updated weights for policy 1, policy_version 53350 (0.0007) -[2023-10-10 14:46:07,958][76542] Updated weights for policy 1, policy_version 53360 (0.0007) -[2023-10-10 14:46:08,319][76542] Updated weights for policy 1, policy_version 53370 (0.0007) -[2023-10-10 14:46:10,025][76543] Updated weights for policy 0, policy_version 53443 (0.0007) -[2023-10-10 14:46:10,404][76543] Updated weights for policy 0, policy_version 53453 (0.0008) -[2023-10-10 14:46:10,775][76543] Updated weights for policy 0, policy_version 53463 (0.0009) -[2023-10-10 14:46:11,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 109379584. Throughput: 0: 1824.9, 1: 1806.3. Samples: 27357188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:46:11,077][75634] Avg episode reward: [(0, '33.600'), (1, '34.070')] -[2023-10-10 14:46:11,978][76542] Updated weights for policy 1, policy_version 53380 (0.0008) -[2023-10-10 14:46:12,349][76542] Updated weights for policy 1, policy_version 53390 (0.0008) -[2023-10-10 14:46:12,722][76542] Updated weights for policy 1, policy_version 53400 (0.0009) -[2023-10-10 14:46:14,330][76543] Updated weights for policy 0, policy_version 53473 (0.0009) -[2023-10-10 14:46:14,701][76543] Updated weights for policy 0, policy_version 53483 (0.0008) -[2023-10-10 14:46:15,070][76543] Updated weights for policy 0, policy_version 53493 (0.0008) -[2023-10-10 14:46:15,438][76543] Updated weights for policy 0, policy_version 53503 (0.0008) -[2023-10-10 14:46:16,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 109477888. Throughput: 0: 1812.9, 1: 1807.6. Samples: 27378866. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-10-10 14:46:16,077][75634] Avg episode reward: [(0, '34.960'), (1, '33.280')] -[2023-10-10 14:46:16,446][76542] Updated weights for policy 1, policy_version 53410 (0.0008) -[2023-10-10 14:46:16,815][76542] Updated weights for policy 1, policy_version 53420 (0.0009) -[2023-10-10 14:46:17,188][76542] Updated weights for policy 1, policy_version 53430 (0.0008) -[2023-10-10 14:46:17,554][76542] Updated weights for policy 1, policy_version 53440 (0.0010) -[2023-10-10 14:46:19,230][76543] Updated weights for policy 0, policy_version 53513 (0.0008) -[2023-10-10 14:46:19,599][76543] Updated weights for policy 0, policy_version 53523 (0.0009) -[2023-10-10 14:46:19,962][76543] Updated weights for policy 0, policy_version 53533 (0.0011) -[2023-10-10 14:46:21,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 109543424. Throughput: 0: 1822.4, 1: 1807.3. Samples: 27389976. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-10-10 14:46:21,076][75634] Avg episode reward: [(0, '34.740'), (1, '32.700')] -[2023-10-10 14:46:21,194][76542] Updated weights for policy 1, policy_version 53450 (0.0008) -[2023-10-10 14:46:21,563][76542] Updated weights for policy 1, policy_version 53460 (0.0010) -[2023-10-10 14:46:21,932][76542] Updated weights for policy 1, policy_version 53470 (0.0007) -[2023-10-10 14:46:23,872][76543] Updated weights for policy 0, policy_version 53543 (0.0011) -[2023-10-10 14:46:24,256][76543] Updated weights for policy 0, policy_version 53553 (0.0010) -[2023-10-10 14:46:24,620][76543] Updated weights for policy 0, policy_version 53563 (0.0008) -[2023-10-10 14:46:25,858][76542] Updated weights for policy 1, policy_version 53480 (0.0007) -[2023-10-10 14:46:26,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 109608960. Throughput: 0: 1819.6, 1: 1797.3. Samples: 27411594. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-10-10 14:46:26,076][75634] Avg episode reward: [(0, '33.830'), (1, '39.020')] -[2023-10-10 14:46:26,224][76542] Updated weights for policy 1, policy_version 53490 (0.0009) -[2023-10-10 14:46:26,595][76542] Updated weights for policy 1, policy_version 53500 (0.0010) -[2023-10-10 14:46:28,595][76543] Updated weights for policy 0, policy_version 53573 (0.0008) -[2023-10-10 14:46:28,975][76543] Updated weights for policy 0, policy_version 53583 (0.0008) -[2023-10-10 14:46:29,356][76543] Updated weights for policy 0, policy_version 53593 (0.0007) -[2023-10-10 14:46:30,300][76542] Updated weights for policy 1, policy_version 53510 (0.0008) -[2023-10-10 14:46:30,659][76542] Updated weights for policy 1, policy_version 53520 (0.0008) -[2023-10-10 14:46:31,032][76542] Updated weights for policy 1, policy_version 53530 (0.0008) -[2023-10-10 14:46:31,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 109674496. Throughput: 0: 1802.7, 1: 1811.2. Samples: 27432278. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-10-10 14:46:31,077][75634] Avg episode reward: [(0, '36.300'), (1, '39.080')] -[2023-10-10 14:46:31,085][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000053600_54886400.pth... -[2023-10-10 14:46:31,121][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000051904_53149696.pth -[2023-10-10 14:46:31,245][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000053536_54820864.pth... -[2023-10-10 14:46:31,284][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000051808_53051392.pth -[2023-10-10 14:46:33,074][76543] Updated weights for policy 0, policy_version 53603 (0.0008) -[2023-10-10 14:46:33,437][76543] Updated weights for policy 0, policy_version 53613 (0.0007) -[2023-10-10 14:46:33,815][76543] Updated weights for policy 0, policy_version 53623 (0.0008) -[2023-10-10 14:46:34,722][76542] Updated weights for policy 1, policy_version 53540 (0.0008) -[2023-10-10 14:46:35,121][76542] Updated weights for policy 1, policy_version 53550 (0.0009) -[2023-10-10 14:46:35,495][76542] Updated weights for policy 1, policy_version 53560 (0.0008) -[2023-10-10 14:46:36,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 109772800. Throughput: 0: 1812.2, 1: 1800.5. Samples: 27444168. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-10-10 14:46:36,076][75634] Avg episode reward: [(0, '35.010'), (1, '36.110')] -[2023-10-10 14:46:37,580][76543] Updated weights for policy 0, policy_version 53633 (0.0008) -[2023-10-10 14:46:37,943][76543] Updated weights for policy 0, policy_version 53643 (0.0009) -[2023-10-10 14:46:38,326][76543] Updated weights for policy 0, policy_version 53653 (0.0007) -[2023-10-10 14:46:38,688][76543] Updated weights for policy 0, policy_version 53663 (0.0009) -[2023-10-10 14:46:39,205][76542] Updated weights for policy 1, policy_version 53570 (0.0009) -[2023-10-10 14:46:39,581][76542] Updated weights for policy 1, policy_version 53580 (0.0007) -[2023-10-10 14:46:39,948][76542] Updated weights for policy 1, policy_version 53590 (0.0009) -[2023-10-10 14:46:40,315][76542] Updated weights for policy 1, policy_version 53600 (0.0009) -[2023-10-10 14:46:41,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 14662.3). Total num frames: 109838336. Throughput: 0: 1798.8, 1: 1811.9. Samples: 27464572. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-10-10 14:46:41,077][75634] Avg episode reward: [(0, '33.900'), (1, '36.280')] -[2023-10-10 14:46:42,255][76543] Updated weights for policy 0, policy_version 53673 (0.0007) -[2023-10-10 14:46:42,630][76543] Updated weights for policy 0, policy_version 53683 (0.0007) -[2023-10-10 14:46:43,000][76543] Updated weights for policy 0, policy_version 53693 (0.0008) -[2023-10-10 14:46:44,053][76542] Updated weights for policy 1, policy_version 53610 (0.0008) -[2023-10-10 14:46:44,421][76542] Updated weights for policy 1, policy_version 53620 (0.0008) -[2023-10-10 14:46:44,793][76542] Updated weights for policy 1, policy_version 53630 (0.0008) -[2023-10-10 14:46:46,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14662.3). Total num frames: 109903872. Throughput: 0: 1796.0, 1: 1800.4. Samples: 27486362. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-10-10 14:46:46,077][75634] Avg episode reward: [(0, '34.050'), (1, '33.660')] -[2023-10-10 14:46:46,849][76543] Updated weights for policy 0, policy_version 53703 (0.0008) -[2023-10-10 14:46:47,228][76543] Updated weights for policy 0, policy_version 53713 (0.0007) -[2023-10-10 14:46:47,595][76543] Updated weights for policy 0, policy_version 53723 (0.0007) -[2023-10-10 14:46:48,417][76542] Updated weights for policy 1, policy_version 53640 (0.0010) -[2023-10-10 14:46:48,790][76542] Updated weights for policy 1, policy_version 53650 (0.0008) -[2023-10-10 14:46:49,157][76542] Updated weights for policy 1, policy_version 53660 (0.0010) -[2023-10-10 14:46:51,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 109969408. Throughput: 0: 1794.7, 1: 1811.1. Samples: 27497068. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-10 14:46:51,076][75634] Avg episode reward: [(0, '35.820'), (1, '29.120')] -[2023-10-10 14:46:51,348][76543] Updated weights for policy 0, policy_version 53733 (0.0009) -[2023-10-10 14:46:51,713][76543] Updated weights for policy 0, policy_version 53743 (0.0009) -[2023-10-10 14:46:52,081][76543] Updated weights for policy 0, policy_version 53753 (0.0009) -[2023-10-10 14:46:52,772][76542] Updated weights for policy 1, policy_version 53670 (0.0008) -[2023-10-10 14:46:53,141][76542] Updated weights for policy 1, policy_version 53680 (0.0008) -[2023-10-10 14:46:53,506][76542] Updated weights for policy 1, policy_version 53690 (0.0007) -[2023-10-10 14:46:55,788][76543] Updated weights for policy 0, policy_version 53763 (0.0008) -[2023-10-10 14:46:56,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 110034944. Throughput: 0: 1797.7, 1: 1803.5. Samples: 27519238. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-10 14:46:56,076][75634] Avg episode reward: [(0, '36.680'), (1, '30.870')] -[2023-10-10 14:46:56,163][76543] Updated weights for policy 0, policy_version 53773 (0.0008) -[2023-10-10 14:46:56,541][76543] Updated weights for policy 0, policy_version 53783 (0.0008) -[2023-10-10 14:46:57,170][76542] Updated weights for policy 1, policy_version 53700 (0.0007) -[2023-10-10 14:46:57,539][76542] Updated weights for policy 1, policy_version 53710 (0.0009) -[2023-10-10 14:46:57,908][76542] Updated weights for policy 1, policy_version 53720 (0.0009) -[2023-10-10 14:47:00,114][76543] Updated weights for policy 0, policy_version 53793 (0.0009) -[2023-10-10 14:47:00,487][76543] Updated weights for policy 0, policy_version 53803 (0.0008) -[2023-10-10 14:47:00,857][76543] Updated weights for policy 0, policy_version 53813 (0.0008) -[2023-10-10 14:47:01,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 110100480. Throughput: 0: 1817.7, 1: 1802.4. Samples: 27541770. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-10 14:47:01,077][75634] Avg episode reward: [(0, '34.090'), (1, '29.880')] -[2023-10-10 14:47:01,231][76543] Updated weights for policy 0, policy_version 53823 (0.0009) -[2023-10-10 14:47:01,497][76542] Updated weights for policy 1, policy_version 53730 (0.0008) -[2023-10-10 14:47:01,863][76542] Updated weights for policy 1, policy_version 53740 (0.0008) -[2023-10-10 14:47:02,238][76542] Updated weights for policy 1, policy_version 53750 (0.0007) -[2023-10-10 14:47:02,613][76542] Updated weights for policy 1, policy_version 53760 (0.0008) -[2023-10-10 14:47:04,697][76543] Updated weights for policy 0, policy_version 53833 (0.0009) -[2023-10-10 14:47:05,073][76543] Updated weights for policy 0, policy_version 53843 (0.0008) -[2023-10-10 14:47:05,450][76543] Updated weights for policy 0, policy_version 53853 (0.0009) -[2023-10-10 14:47:06,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 110198784. Throughput: 0: 1799.3, 1: 1803.4. Samples: 27552096. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-10 14:47:06,077][75634] Avg episode reward: [(0, '30.810'), (1, '29.680')] -[2023-10-10 14:47:06,327][76542] Updated weights for policy 1, policy_version 53770 (0.0007) -[2023-10-10 14:47:06,697][76542] Updated weights for policy 1, policy_version 53780 (0.0007) -[2023-10-10 14:47:07,074][76542] Updated weights for policy 1, policy_version 53790 (0.0007) -[2023-10-10 14:47:09,282][76543] Updated weights for policy 0, policy_version 53863 (0.0010) -[2023-10-10 14:47:09,648][76543] Updated weights for policy 0, policy_version 53873 (0.0010) -[2023-10-10 14:47:10,029][76543] Updated weights for policy 0, policy_version 53883 (0.0008) -[2023-10-10 14:47:10,918][76542] Updated weights for policy 1, policy_version 53800 (0.0008) -[2023-10-10 14:47:11,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 110264320. Throughput: 0: 1817.1, 1: 1808.7. Samples: 27574754. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-10 14:47:11,077][75634] Avg episode reward: [(0, '33.910'), (1, '31.140')] -[2023-10-10 14:47:11,291][76542] Updated weights for policy 1, policy_version 53810 (0.0007) -[2023-10-10 14:47:11,663][76542] Updated weights for policy 1, policy_version 53820 (0.0008) -[2023-10-10 14:47:13,905][76543] Updated weights for policy 0, policy_version 53893 (0.0008) -[2023-10-10 14:47:14,293][76543] Updated weights for policy 0, policy_version 53903 (0.0009) -[2023-10-10 14:47:14,660][76543] Updated weights for policy 0, policy_version 53913 (0.0010) -[2023-10-10 14:47:15,343][76542] Updated weights for policy 1, policy_version 53830 (0.0008) -[2023-10-10 14:47:15,712][76542] Updated weights for policy 1, policy_version 53840 (0.0007) -[2023-10-10 14:47:16,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 110329856. Throughput: 0: 1810.0, 1: 1809.6. Samples: 27595158. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-10 14:47:16,076][75634] Avg episode reward: [(0, '36.110'), (1, '33.710')] -[2023-10-10 14:47:16,081][76542] Updated weights for policy 1, policy_version 53850 (0.0007) -[2023-10-10 14:47:18,223][76543] Updated weights for policy 0, policy_version 53923 (0.0010) -[2023-10-10 14:47:18,601][76543] Updated weights for policy 0, policy_version 53933 (0.0009) -[2023-10-10 14:47:18,973][76543] Updated weights for policy 0, policy_version 53943 (0.0009) -[2023-10-10 14:47:19,887][76542] Updated weights for policy 1, policy_version 53860 (0.0010) -[2023-10-10 14:47:20,272][76542] Updated weights for policy 1, policy_version 53870 (0.0009) -[2023-10-10 14:47:20,639][76542] Updated weights for policy 1, policy_version 53880 (0.0008) -[2023-10-10 14:47:21,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 110428160. Throughput: 0: 1816.6, 1: 1802.0. Samples: 27607006. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-10 14:47:21,076][75634] Avg episode reward: [(0, '36.370'), (1, '34.950')] -[2023-10-10 14:47:22,582][76543] Updated weights for policy 0, policy_version 53953 (0.0007) -[2023-10-10 14:47:22,944][76543] Updated weights for policy 0, policy_version 53963 (0.0008) -[2023-10-10 14:47:23,324][76543] Updated weights for policy 0, policy_version 53973 (0.0007) -[2023-10-10 14:47:23,695][76543] Updated weights for policy 0, policy_version 53983 (0.0009) -[2023-10-10 14:47:24,398][76542] Updated weights for policy 1, policy_version 53890 (0.0010) -[2023-10-10 14:47:24,768][76542] Updated weights for policy 1, policy_version 53900 (0.0011) -[2023-10-10 14:47:25,137][76542] Updated weights for policy 1, policy_version 53910 (0.0007) -[2023-10-10 14:47:25,504][76542] Updated weights for policy 1, policy_version 53920 (0.0007) -[2023-10-10 14:47:26,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 110493696. Throughput: 0: 1819.2, 1: 1815.0. Samples: 27628112. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:47:26,077][75634] Avg episode reward: [(0, '36.440'), (1, '32.610')] -[2023-10-10 14:47:27,443][76543] Updated weights for policy 0, policy_version 53993 (0.0008) -[2023-10-10 14:47:27,813][76543] Updated weights for policy 0, policy_version 54003 (0.0009) -[2023-10-10 14:47:28,184][76543] Updated weights for policy 0, policy_version 54013 (0.0009) -[2023-10-10 14:47:29,112][76542] Updated weights for policy 1, policy_version 53930 (0.0008) -[2023-10-10 14:47:29,476][76542] Updated weights for policy 1, policy_version 53940 (0.0007) -[2023-10-10 14:47:29,848][76542] Updated weights for policy 1, policy_version 53950 (0.0012) -[2023-10-10 14:47:31,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 110559232. Throughput: 0: 1818.8, 1: 1816.4. Samples: 27649944. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:47:31,076][75634] Avg episode reward: [(0, '38.080'), (1, '39.480')] -[2023-10-10 14:47:32,074][76543] Updated weights for policy 0, policy_version 54023 (0.0009) -[2023-10-10 14:47:32,443][76543] Updated weights for policy 0, policy_version 54033 (0.0008) -[2023-10-10 14:47:32,811][76543] Updated weights for policy 0, policy_version 54043 (0.0008) -[2023-10-10 14:47:33,549][76542] Updated weights for policy 1, policy_version 53960 (0.0009) -[2023-10-10 14:47:33,922][76542] Updated weights for policy 1, policy_version 53970 (0.0007) -[2023-10-10 14:47:34,288][76542] Updated weights for policy 1, policy_version 53980 (0.0010) -[2023-10-10 14:47:36,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 110624768. Throughput: 0: 1814.0, 1: 1821.6. Samples: 27660670. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:47:36,077][75634] Avg episode reward: [(0, '40.660'), (1, '38.820')] -[2023-10-10 14:47:36,489][76543] Updated weights for policy 0, policy_version 54053 (0.0007) -[2023-10-10 14:47:36,866][76543] Updated weights for policy 0, policy_version 54063 (0.0010) -[2023-10-10 14:47:37,237][76543] Updated weights for policy 0, policy_version 54073 (0.0009) -[2023-10-10 14:47:37,920][76542] Updated weights for policy 1, policy_version 53990 (0.0011) -[2023-10-10 14:47:38,289][76542] Updated weights for policy 1, policy_version 54000 (0.0009) -[2023-10-10 14:47:38,660][76542] Updated weights for policy 1, policy_version 54010 (0.0010) -[2023-10-10 14:47:40,959][76543] Updated weights for policy 0, policy_version 54083 (0.0010) -[2023-10-10 14:47:41,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 110690304. Throughput: 0: 1811.2, 1: 1817.4. Samples: 27682528. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:47:41,077][75634] Avg episode reward: [(0, '39.840'), (1, '34.300')] -[2023-10-10 14:47:41,327][76543] Updated weights for policy 0, policy_version 54093 (0.0007) -[2023-10-10 14:47:41,705][76543] Updated weights for policy 0, policy_version 54103 (0.0008) -[2023-10-10 14:47:42,407][76542] Updated weights for policy 1, policy_version 54020 (0.0009) -[2023-10-10 14:47:42,774][76542] Updated weights for policy 1, policy_version 54030 (0.0008) -[2023-10-10 14:47:43,153][76542] Updated weights for policy 1, policy_version 54040 (0.0008) -[2023-10-10 14:47:45,178][76543] Updated weights for policy 0, policy_version 54113 (0.0008) -[2023-10-10 14:47:45,545][76543] Updated weights for policy 0, policy_version 54123 (0.0007) -[2023-10-10 14:47:45,910][76543] Updated weights for policy 0, policy_version 54133 (0.0007) -[2023-10-10 14:47:46,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 110755840. Throughput: 0: 1821.4, 1: 1817.6. Samples: 27705524. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:47:46,077][75634] Avg episode reward: [(0, '35.740'), (1, '34.310')] -[2023-10-10 14:47:46,281][76543] Updated weights for policy 0, policy_version 54143 (0.0008) -[2023-10-10 14:47:46,772][76542] Updated weights for policy 1, policy_version 54050 (0.0007) -[2023-10-10 14:47:47,146][76542] Updated weights for policy 1, policy_version 54060 (0.0007) -[2023-10-10 14:47:47,523][76542] Updated weights for policy 1, policy_version 54070 (0.0009) -[2023-10-10 14:47:47,884][76542] Updated weights for policy 1, policy_version 54080 (0.0011) -[2023-10-10 14:47:49,792][76543] Updated weights for policy 0, policy_version 54153 (0.0008) -[2023-10-10 14:47:50,159][76543] Updated weights for policy 0, policy_version 54163 (0.0008) -[2023-10-10 14:47:50,531][76543] Updated weights for policy 0, policy_version 54173 (0.0010) -[2023-10-10 14:47:51,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 110854144. Throughput: 0: 1816.9, 1: 1820.7. Samples: 27715788. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:47:51,077][75634] Avg episode reward: [(0, '35.760'), (1, '32.070')] -[2023-10-10 14:47:51,502][76542] Updated weights for policy 1, policy_version 54090 (0.0009) -[2023-10-10 14:47:51,867][76542] Updated weights for policy 1, policy_version 54100 (0.0007) -[2023-10-10 14:47:52,227][76542] Updated weights for policy 1, policy_version 54110 (0.0007) -[2023-10-10 14:47:54,188][76543] Updated weights for policy 0, policy_version 54183 (0.0009) -[2023-10-10 14:47:54,570][76543] Updated weights for policy 0, policy_version 54193 (0.0011) -[2023-10-10 14:47:54,939][76543] Updated weights for policy 0, policy_version 54203 (0.0008) -[2023-10-10 14:47:55,814][76542] Updated weights for policy 1, policy_version 54120 (0.0009) -[2023-10-10 14:47:56,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 110919680. Throughput: 0: 1816.9, 1: 1826.8. Samples: 27738724. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:47:56,076][75634] Avg episode reward: [(0, '35.880'), (1, '30.040')] -[2023-10-10 14:47:56,178][76542] Updated weights for policy 1, policy_version 54130 (0.0010) -[2023-10-10 14:47:56,551][76542] Updated weights for policy 1, policy_version 54140 (0.0007) -[2023-10-10 14:47:58,661][76543] Updated weights for policy 0, policy_version 54213 (0.0009) -[2023-10-10 14:47:59,046][76543] Updated weights for policy 0, policy_version 54223 (0.0010) -[2023-10-10 14:47:59,416][76543] Updated weights for policy 0, policy_version 54233 (0.0008) -[2023-10-10 14:48:00,303][76542] Updated weights for policy 1, policy_version 54150 (0.0008) -[2023-10-10 14:48:00,666][76542] Updated weights for policy 1, policy_version 54160 (0.0009) -[2023-10-10 14:48:01,035][76542] Updated weights for policy 1, policy_version 54170 (0.0007) -[2023-10-10 14:48:01,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 110985216. Throughput: 0: 1820.8, 1: 1828.1. Samples: 27759360. Policy #0 lag: (min: 31.0, avg: 31.7, max: 49.0) -[2023-10-10 14:48:01,076][75634] Avg episode reward: [(0, '36.130'), (1, '31.700')] -[2023-10-10 14:48:03,196][76543] Updated weights for policy 0, policy_version 54243 (0.0009) -[2023-10-10 14:48:03,564][76543] Updated weights for policy 0, policy_version 54253 (0.0009) -[2023-10-10 14:48:03,942][76543] Updated weights for policy 0, policy_version 54263 (0.0010) -[2023-10-10 14:48:04,870][76542] Updated weights for policy 1, policy_version 54180 (0.0008) -[2023-10-10 14:48:05,264][76542] Updated weights for policy 1, policy_version 54190 (0.0010) -[2023-10-10 14:48:05,628][76542] Updated weights for policy 1, policy_version 54200 (0.0010) -[2023-10-10 14:48:06,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 111083520. Throughput: 0: 1814.7, 1: 1833.9. Samples: 27771192. Policy #0 lag: (min: 31.0, avg: 31.7, max: 49.0) -[2023-10-10 14:48:06,077][75634] Avg episode reward: [(0, '34.430'), (1, '32.960')] -[2023-10-10 14:48:07,689][76543] Updated weights for policy 0, policy_version 54273 (0.0009) -[2023-10-10 14:48:08,063][76543] Updated weights for policy 0, policy_version 54283 (0.0009) -[2023-10-10 14:48:08,438][76543] Updated weights for policy 0, policy_version 54293 (0.0007) -[2023-10-10 14:48:08,812][76543] Updated weights for policy 0, policy_version 54303 (0.0007) -[2023-10-10 14:48:09,289][76542] Updated weights for policy 1, policy_version 54210 (0.0010) -[2023-10-10 14:48:09,664][76542] Updated weights for policy 1, policy_version 54220 (0.0008) -[2023-10-10 14:48:10,030][76542] Updated weights for policy 1, policy_version 54230 (0.0008) -[2023-10-10 14:48:10,397][76542] Updated weights for policy 1, policy_version 54240 (0.0009) -[2023-10-10 14:48:11,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 111149056. Throughput: 0: 1811.8, 1: 1828.0. Samples: 27791902. Policy #0 lag: (min: 31.0, avg: 31.7, max: 49.0) -[2023-10-10 14:48:11,077][75634] Avg episode reward: [(0, '34.500'), (1, '34.110')] -[2023-10-10 14:48:12,444][76543] Updated weights for policy 0, policy_version 54313 (0.0011) -[2023-10-10 14:48:12,813][76543] Updated weights for policy 0, policy_version 54323 (0.0011) -[2023-10-10 14:48:13,184][76543] Updated weights for policy 0, policy_version 54333 (0.0009) -[2023-10-10 14:48:14,053][76542] Updated weights for policy 1, policy_version 54250 (0.0009) -[2023-10-10 14:48:14,415][76542] Updated weights for policy 1, policy_version 54260 (0.0009) -[2023-10-10 14:48:14,787][76542] Updated weights for policy 1, policy_version 54270 (0.0011) -[2023-10-10 14:48:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 111214592. Throughput: 0: 1816.0, 1: 1830.2. Samples: 27814026. Policy #0 lag: (min: 31.0, avg: 31.7, max: 49.0) -[2023-10-10 14:48:16,077][75634] Avg episode reward: [(0, '34.190'), (1, '36.460')] -[2023-10-10 14:48:16,888][76543] Updated weights for policy 0, policy_version 54343 (0.0007) -[2023-10-10 14:48:17,259][76543] Updated weights for policy 0, policy_version 54353 (0.0010) -[2023-10-10 14:48:17,628][76543] Updated weights for policy 0, policy_version 54363 (0.0008) -[2023-10-10 14:48:18,403][76542] Updated weights for policy 1, policy_version 54280 (0.0007) -[2023-10-10 14:48:18,767][76542] Updated weights for policy 1, policy_version 54290 (0.0009) -[2023-10-10 14:48:19,133][76542] Updated weights for policy 1, policy_version 54300 (0.0007) -[2023-10-10 14:48:21,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 111280128. Throughput: 0: 1821.2, 1: 1826.1. Samples: 27824796. Policy #0 lag: (min: 31.0, avg: 31.7, max: 49.0) -[2023-10-10 14:48:21,077][75634] Avg episode reward: [(0, '37.070'), (1, '37.570')] -[2023-10-10 14:48:21,379][76543] Updated weights for policy 0, policy_version 54373 (0.0007) -[2023-10-10 14:48:21,755][76543] Updated weights for policy 0, policy_version 54383 (0.0007) -[2023-10-10 14:48:22,123][76543] Updated weights for policy 0, policy_version 54393 (0.0007) -[2023-10-10 14:48:22,813][76542] Updated weights for policy 1, policy_version 54310 (0.0008) -[2023-10-10 14:48:23,175][76542] Updated weights for policy 1, policy_version 54320 (0.0009) -[2023-10-10 14:48:23,550][76542] Updated weights for policy 1, policy_version 54330 (0.0011) -[2023-10-10 14:48:25,752][76543] Updated weights for policy 0, policy_version 54403 (0.0009) -[2023-10-10 14:48:26,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 111345664. Throughput: 0: 1828.1, 1: 1828.0. Samples: 27847054. Policy #0 lag: (min: 31.0, avg: 31.7, max: 49.0) -[2023-10-10 14:48:26,077][75634] Avg episode reward: [(0, '35.410'), (1, '38.900')] -[2023-10-10 14:48:26,114][76543] Updated weights for policy 0, policy_version 54413 (0.0008) -[2023-10-10 14:48:26,485][76543] Updated weights for policy 0, policy_version 54423 (0.0008) -[2023-10-10 14:48:27,245][76542] Updated weights for policy 1, policy_version 54340 (0.0010) -[2023-10-10 14:48:27,616][76542] Updated weights for policy 1, policy_version 54350 (0.0008) -[2023-10-10 14:48:27,990][76542] Updated weights for policy 1, policy_version 54360 (0.0008) -[2023-10-10 14:48:29,992][76543] Updated weights for policy 0, policy_version 54433 (0.0008) -[2023-10-10 14:48:30,367][76543] Updated weights for policy 0, policy_version 54443 (0.0007) -[2023-10-10 14:48:30,743][76543] Updated weights for policy 0, policy_version 54453 (0.0010) -[2023-10-10 14:48:31,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 111411200. Throughput: 0: 1820.9, 1: 1830.9. Samples: 27869850. Policy #0 lag: (min: 31.0, avg: 31.7, max: 49.0) -[2023-10-10 14:48:31,076][75634] Avg episode reward: [(0, '34.060'), (1, '38.510')] -[2023-10-10 14:48:31,085][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000054368_55672832.pth... -[2023-10-10 14:48:31,114][76543] Updated weights for policy 0, policy_version 54463 (0.0008) -[2023-10-10 14:48:31,116][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000052672_53936128.pth -[2023-10-10 14:48:31,142][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000054464_55771136.pth... -[2023-10-10 14:48:31,172][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000052736_54001664.pth -[2023-10-10 14:48:31,729][76542] Updated weights for policy 1, policy_version 54370 (0.0011) -[2023-10-10 14:48:32,101][76542] Updated weights for policy 1, policy_version 54380 (0.0009) -[2023-10-10 14:48:32,471][76542] Updated weights for policy 1, policy_version 54390 (0.0007) -[2023-10-10 14:48:32,840][76542] Updated weights for policy 1, policy_version 54400 (0.0008) -[2023-10-10 14:48:34,765][76543] Updated weights for policy 0, policy_version 54473 (0.0009) -[2023-10-10 14:48:35,133][76543] Updated weights for policy 0, policy_version 54483 (0.0008) -[2023-10-10 14:48:35,499][76543] Updated weights for policy 0, policy_version 54493 (0.0007) -[2023-10-10 14:48:36,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 111509504. Throughput: 0: 1828.1, 1: 1824.4. Samples: 27880150. Policy #0 lag: (min: 30.0, avg: 32.2, max: 61.0) -[2023-10-10 14:48:36,076][75634] Avg episode reward: [(0, '36.030'), (1, '36.060')] -[2023-10-10 14:48:36,488][76542] Updated weights for policy 1, policy_version 54410 (0.0007) -[2023-10-10 14:48:36,868][76542] Updated weights for policy 1, policy_version 54420 (0.0007) -[2023-10-10 14:48:37,237][76542] Updated weights for policy 1, policy_version 54430 (0.0011) -[2023-10-10 14:48:39,303][76543] Updated weights for policy 0, policy_version 54503 (0.0007) -[2023-10-10 14:48:39,670][76543] Updated weights for policy 0, policy_version 54513 (0.0008) -[2023-10-10 14:48:40,044][76543] Updated weights for policy 0, policy_version 54523 (0.0008) -[2023-10-10 14:48:40,927][76542] Updated weights for policy 1, policy_version 54440 (0.0011) -[2023-10-10 14:48:41,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 111575040. Throughput: 0: 1825.2, 1: 1819.5. Samples: 27902734. Policy #0 lag: (min: 30.0, avg: 32.2, max: 61.0) -[2023-10-10 14:48:41,076][75634] Avg episode reward: [(0, '39.220'), (1, '36.700')] -[2023-10-10 14:48:41,292][76542] Updated weights for policy 1, policy_version 54450 (0.0008) -[2023-10-10 14:48:41,665][76542] Updated weights for policy 1, policy_version 54460 (0.0009) -[2023-10-10 14:48:43,651][76543] Updated weights for policy 0, policy_version 54533 (0.0009) -[2023-10-10 14:48:44,039][76543] Updated weights for policy 0, policy_version 54543 (0.0009) -[2023-10-10 14:48:44,409][76543] Updated weights for policy 0, policy_version 54553 (0.0008) -[2023-10-10 14:48:45,166][76542] Updated weights for policy 1, policy_version 54470 (0.0012) -[2023-10-10 14:48:45,533][76542] Updated weights for policy 1, policy_version 54480 (0.0010) -[2023-10-10 14:48:45,898][76542] Updated weights for policy 1, policy_version 54490 (0.0007) -[2023-10-10 14:48:46,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 111640576. Throughput: 0: 1825.8, 1: 1823.2. Samples: 27923566. Policy #0 lag: (min: 30.0, avg: 32.2, max: 61.0) -[2023-10-10 14:48:46,077][75634] Avg episode reward: [(0, '34.930'), (1, '36.820')] -[2023-10-10 14:48:47,972][76543] Updated weights for policy 0, policy_version 54563 (0.0009) -[2023-10-10 14:48:48,337][76543] Updated weights for policy 0, policy_version 54573 (0.0009) -[2023-10-10 14:48:48,694][76543] Updated weights for policy 0, policy_version 54583 (0.0009) -[2023-10-10 14:48:49,507][76542] Updated weights for policy 1, policy_version 54500 (0.0008) -[2023-10-10 14:48:49,904][76542] Updated weights for policy 1, policy_version 54510 (0.0010) -[2023-10-10 14:48:50,273][76542] Updated weights for policy 1, policy_version 54520 (0.0008) -[2023-10-10 14:48:51,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 111738880. Throughput: 0: 1825.7, 1: 1829.2. Samples: 27935662. Policy #0 lag: (min: 30.0, avg: 32.2, max: 61.0) -[2023-10-10 14:48:51,077][75634] Avg episode reward: [(0, '34.150'), (1, '34.110')] -[2023-10-10 14:48:52,328][76543] Updated weights for policy 0, policy_version 54593 (0.0010) -[2023-10-10 14:48:52,697][76543] Updated weights for policy 0, policy_version 54603 (0.0010) -[2023-10-10 14:48:53,070][76543] Updated weights for policy 0, policy_version 54613 (0.0010) -[2023-10-10 14:48:53,446][76543] Updated weights for policy 0, policy_version 54623 (0.0009) -[2023-10-10 14:48:54,019][76542] Updated weights for policy 1, policy_version 54530 (0.0009) -[2023-10-10 14:48:54,384][76542] Updated weights for policy 1, policy_version 54540 (0.0009) -[2023-10-10 14:48:54,750][76542] Updated weights for policy 1, policy_version 54550 (0.0008) -[2023-10-10 14:48:55,115][76542] Updated weights for policy 1, policy_version 54560 (0.0007) -[2023-10-10 14:48:56,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 111804416. Throughput: 0: 1833.9, 1: 1819.9. Samples: 27956320. Policy #0 lag: (min: 30.0, avg: 32.2, max: 61.0) -[2023-10-10 14:48:56,077][75634] Avg episode reward: [(0, '35.540'), (1, '30.110')] -[2023-10-10 14:48:57,191][76543] Updated weights for policy 0, policy_version 54633 (0.0009) -[2023-10-10 14:48:57,559][76543] Updated weights for policy 0, policy_version 54643 (0.0007) -[2023-10-10 14:48:57,928][76543] Updated weights for policy 0, policy_version 54653 (0.0007) -[2023-10-10 14:48:58,750][76542] Updated weights for policy 1, policy_version 54570 (0.0008) -[2023-10-10 14:48:59,123][76542] Updated weights for policy 1, policy_version 54580 (0.0008) -[2023-10-10 14:48:59,488][76542] Updated weights for policy 1, policy_version 54590 (0.0008) -[2023-10-10 14:49:01,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 111869952. Throughput: 0: 1833.2, 1: 1830.6. Samples: 27978896. Policy #0 lag: (min: 30.0, avg: 32.2, max: 61.0) -[2023-10-10 14:49:01,076][75634] Avg episode reward: [(0, '35.380'), (1, '26.940')] -[2023-10-10 14:49:01,608][76543] Updated weights for policy 0, policy_version 54663 (0.0008) -[2023-10-10 14:49:01,978][76543] Updated weights for policy 0, policy_version 54673 (0.0007) -[2023-10-10 14:49:02,356][76543] Updated weights for policy 0, policy_version 54683 (0.0011) -[2023-10-10 14:49:03,019][76542] Updated weights for policy 1, policy_version 54600 (0.0008) -[2023-10-10 14:49:03,379][76542] Updated weights for policy 1, policy_version 54610 (0.0010) -[2023-10-10 14:49:03,752][76542] Updated weights for policy 1, policy_version 54620 (0.0008) -[2023-10-10 14:49:06,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 111935488. Throughput: 0: 1833.2, 1: 1821.3. Samples: 27989248. Policy #0 lag: (min: 30.0, avg: 32.2, max: 61.0) -[2023-10-10 14:49:06,076][75634] Avg episode reward: [(0, '33.750'), (1, '30.290')] -[2023-10-10 14:49:06,110][76543] Updated weights for policy 0, policy_version 54693 (0.0008) -[2023-10-10 14:49:06,480][76543] Updated weights for policy 0, policy_version 54703 (0.0008) -[2023-10-10 14:49:06,854][76543] Updated weights for policy 0, policy_version 54713 (0.0008) -[2023-10-10 14:49:07,476][76542] Updated weights for policy 1, policy_version 54630 (0.0008) -[2023-10-10 14:49:07,843][76542] Updated weights for policy 1, policy_version 54640 (0.0009) -[2023-10-10 14:49:08,216][76542] Updated weights for policy 1, policy_version 54650 (0.0009) -[2023-10-10 14:49:10,573][76543] Updated weights for policy 0, policy_version 54723 (0.0009) -[2023-10-10 14:49:10,940][76543] Updated weights for policy 0, policy_version 54733 (0.0007) -[2023-10-10 14:49:11,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 112001024. Throughput: 0: 1829.4, 1: 1827.3. Samples: 28011606. Policy #0 lag: (min: 30.0, avg: 32.2, max: 61.0) -[2023-10-10 14:49:11,077][75634] Avg episode reward: [(0, '36.880'), (1, '35.330')] -[2023-10-10 14:49:11,318][76543] Updated weights for policy 0, policy_version 54743 (0.0009) -[2023-10-10 14:49:11,879][76542] Updated weights for policy 1, policy_version 54660 (0.0008) -[2023-10-10 14:49:12,250][76542] Updated weights for policy 1, policy_version 54670 (0.0007) -[2023-10-10 14:49:12,620][76542] Updated weights for policy 1, policy_version 54680 (0.0008) -[2023-10-10 14:49:15,074][76543] Updated weights for policy 0, policy_version 54753 (0.0010) -[2023-10-10 14:49:15,447][76543] Updated weights for policy 0, policy_version 54763 (0.0007) -[2023-10-10 14:49:15,815][76543] Updated weights for policy 0, policy_version 54773 (0.0008) -[2023-10-10 14:49:16,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 112066560. Throughput: 0: 1825.8, 1: 1829.8. Samples: 28034354. Policy #0 lag: (min: 13.0, avg: 14.4, max: 40.0) -[2023-10-10 14:49:16,076][75634] Avg episode reward: [(0, '31.430'), (1, '37.770')] -[2023-10-10 14:49:16,192][76543] Updated weights for policy 0, policy_version 54783 (0.0008) -[2023-10-10 14:49:16,204][76542] Updated weights for policy 1, policy_version 54690 (0.0007) -[2023-10-10 14:49:16,571][76542] Updated weights for policy 1, policy_version 54700 (0.0008) -[2023-10-10 14:49:16,949][76542] Updated weights for policy 1, policy_version 54710 (0.0010) -[2023-10-10 14:49:17,312][76542] Updated weights for policy 1, policy_version 54720 (0.0008) -[2023-10-10 14:49:19,832][76543] Updated weights for policy 0, policy_version 54793 (0.0008) -[2023-10-10 14:49:20,192][76543] Updated weights for policy 0, policy_version 54803 (0.0008) -[2023-10-10 14:49:20,570][76543] Updated weights for policy 0, policy_version 54813 (0.0009) -[2023-10-10 14:49:21,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 112164864. Throughput: 0: 1824.7, 1: 1830.9. Samples: 28044652. Policy #0 lag: (min: 13.0, avg: 14.4, max: 40.0) -[2023-10-10 14:49:21,076][75634] Avg episode reward: [(0, '33.060'), (1, '38.430')] -[2023-10-10 14:49:21,105][76542] Updated weights for policy 1, policy_version 54730 (0.0010) -[2023-10-10 14:49:21,471][76542] Updated weights for policy 1, policy_version 54740 (0.0007) -[2023-10-10 14:49:21,844][76542] Updated weights for policy 1, policy_version 54750 (0.0007) -[2023-10-10 14:49:24,214][76543] Updated weights for policy 0, policy_version 54823 (0.0008) -[2023-10-10 14:49:24,584][76543] Updated weights for policy 0, policy_version 54833 (0.0008) -[2023-10-10 14:49:24,951][76543] Updated weights for policy 0, policy_version 54843 (0.0008) -[2023-10-10 14:49:25,385][76542] Updated weights for policy 1, policy_version 54760 (0.0008) -[2023-10-10 14:49:25,759][76542] Updated weights for policy 1, policy_version 54770 (0.0007) -[2023-10-10 14:49:26,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 112230400. Throughput: 0: 1824.7, 1: 1835.5. Samples: 28067444. Policy #0 lag: (min: 13.0, avg: 14.4, max: 40.0) -[2023-10-10 14:49:26,077][75634] Avg episode reward: [(0, '35.890'), (1, '41.620')] -[2023-10-10 14:49:26,127][76542] Updated weights for policy 1, policy_version 54780 (0.0011) -[2023-10-10 14:49:28,561][76543] Updated weights for policy 0, policy_version 54853 (0.0008) -[2023-10-10 14:49:28,943][76543] Updated weights for policy 0, policy_version 54863 (0.0009) -[2023-10-10 14:49:29,302][76543] Updated weights for policy 0, policy_version 54873 (0.0008) -[2023-10-10 14:49:29,873][76542] Updated weights for policy 1, policy_version 54790 (0.0010) -[2023-10-10 14:49:30,239][76542] Updated weights for policy 1, policy_version 54800 (0.0010) -[2023-10-10 14:49:30,613][76542] Updated weights for policy 1, policy_version 54810 (0.0009) -[2023-10-10 14:49:31,076][75634] Fps is (10 sec: 16383.7, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 112328704. Throughput: 0: 1830.0, 1: 1821.1. Samples: 28087862. Policy #0 lag: (min: 13.0, avg: 14.4, max: 40.0) -[2023-10-10 14:49:31,077][75634] Avg episode reward: [(0, '37.170'), (1, '36.880')] -[2023-10-10 14:49:32,972][76543] Updated weights for policy 0, policy_version 54883 (0.0009) -[2023-10-10 14:49:33,338][76543] Updated weights for policy 0, policy_version 54893 (0.0009) -[2023-10-10 14:49:33,720][76543] Updated weights for policy 0, policy_version 54903 (0.0009) -[2023-10-10 14:49:34,366][76542] Updated weights for policy 1, policy_version 54820 (0.0009) -[2023-10-10 14:49:34,759][76542] Updated weights for policy 1, policy_version 54830 (0.0010) -[2023-10-10 14:49:35,121][76542] Updated weights for policy 1, policy_version 54840 (0.0008) -[2023-10-10 14:49:36,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 112394240. Throughput: 0: 1825.8, 1: 1831.1. Samples: 28100222. Policy #0 lag: (min: 13.0, avg: 14.4, max: 40.0) -[2023-10-10 14:49:36,076][75634] Avg episode reward: [(0, '36.060'), (1, '32.480')] -[2023-10-10 14:49:37,370][76543] Updated weights for policy 0, policy_version 54913 (0.0008) -[2023-10-10 14:49:37,743][76543] Updated weights for policy 0, policy_version 54923 (0.0009) -[2023-10-10 14:49:38,105][76543] Updated weights for policy 0, policy_version 54933 (0.0008) -[2023-10-10 14:49:38,477][76543] Updated weights for policy 0, policy_version 54943 (0.0007) -[2023-10-10 14:49:38,841][76542] Updated weights for policy 1, policy_version 54850 (0.0007) -[2023-10-10 14:49:39,216][76542] Updated weights for policy 1, policy_version 54860 (0.0007) -[2023-10-10 14:49:39,581][76542] Updated weights for policy 1, policy_version 54870 (0.0008) -[2023-10-10 14:49:39,947][76542] Updated weights for policy 1, policy_version 54880 (0.0008) -[2023-10-10 14:49:41,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 112459776. Throughput: 0: 1826.9, 1: 1826.9. Samples: 28120744. Policy #0 lag: (min: 13.0, avg: 14.4, max: 40.0) -[2023-10-10 14:49:41,076][75634] Avg episode reward: [(0, '36.980'), (1, '31.790')] -[2023-10-10 14:49:42,091][76543] Updated weights for policy 0, policy_version 54953 (0.0010) -[2023-10-10 14:49:42,458][76543] Updated weights for policy 0, policy_version 54963 (0.0007) -[2023-10-10 14:49:42,825][76543] Updated weights for policy 0, policy_version 54973 (0.0009) -[2023-10-10 14:49:43,850][76542] Updated weights for policy 1, policy_version 54890 (0.0009) -[2023-10-10 14:49:44,217][76542] Updated weights for policy 1, policy_version 54900 (0.0008) -[2023-10-10 14:49:44,584][76542] Updated weights for policy 1, policy_version 54910 (0.0007) -[2023-10-10 14:49:46,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 112525312. Throughput: 0: 1829.6, 1: 1817.8. Samples: 28143030. Policy #0 lag: (min: 13.0, avg: 14.4, max: 40.0) -[2023-10-10 14:49:46,076][75634] Avg episode reward: [(0, '34.940'), (1, '26.360')] -[2023-10-10 14:49:46,330][76543] Updated weights for policy 0, policy_version 54983 (0.0008) -[2023-10-10 14:49:46,709][76543] Updated weights for policy 0, policy_version 54993 (0.0010) -[2023-10-10 14:49:47,079][76543] Updated weights for policy 0, policy_version 55003 (0.0010) -[2023-10-10 14:49:48,211][76542] Updated weights for policy 1, policy_version 54920 (0.0009) -[2023-10-10 14:49:48,570][76542] Updated weights for policy 1, policy_version 54930 (0.0007) -[2023-10-10 14:49:48,931][76542] Updated weights for policy 1, policy_version 54940 (0.0007) -[2023-10-10 14:49:50,772][76543] Updated weights for policy 0, policy_version 55013 (0.0009) -[2023-10-10 14:49:51,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 112590848. Throughput: 0: 1829.6, 1: 1822.1. Samples: 28153572. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:49:51,077][75634] Avg episode reward: [(0, '36.610'), (1, '29.330')] -[2023-10-10 14:49:51,148][76543] Updated weights for policy 0, policy_version 55023 (0.0009) -[2023-10-10 14:49:51,516][76543] Updated weights for policy 0, policy_version 55033 (0.0011) -[2023-10-10 14:49:52,861][76542] Updated weights for policy 1, policy_version 54950 (0.0008) -[2023-10-10 14:49:53,235][76542] Updated weights for policy 1, policy_version 54960 (0.0008) -[2023-10-10 14:49:53,603][76542] Updated weights for policy 1, policy_version 54970 (0.0010) -[2023-10-10 14:49:55,456][76543] Updated weights for policy 0, policy_version 55043 (0.0008) -[2023-10-10 14:49:55,818][76543] Updated weights for policy 0, policy_version 55053 (0.0010) -[2023-10-10 14:49:56,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 112656384. Throughput: 0: 1834.5, 1: 1815.2. Samples: 28175842. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:49:56,077][75634] Avg episode reward: [(0, '40.540'), (1, '29.400')] -[2023-10-10 14:49:56,182][76543] Updated weights for policy 0, policy_version 55063 (0.0010) -[2023-10-10 14:49:57,134][76542] Updated weights for policy 1, policy_version 54980 (0.0009) -[2023-10-10 14:49:57,501][76542] Updated weights for policy 1, policy_version 54990 (0.0008) -[2023-10-10 14:49:57,868][76542] Updated weights for policy 1, policy_version 55000 (0.0007) -[2023-10-10 14:49:59,859][76543] Updated weights for policy 0, policy_version 55073 (0.0010) -[2023-10-10 14:50:00,224][76543] Updated weights for policy 0, policy_version 55083 (0.0009) -[2023-10-10 14:50:00,597][76543] Updated weights for policy 0, policy_version 55093 (0.0011) -[2023-10-10 14:50:00,962][76543] Updated weights for policy 0, policy_version 55103 (0.0010) -[2023-10-10 14:50:01,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 112754688. Throughput: 0: 1828.4, 1: 1823.2. Samples: 28198678. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:50:01,077][75634] Avg episode reward: [(0, '37.730'), (1, '33.650')] -[2023-10-10 14:50:01,321][76542] Updated weights for policy 1, policy_version 55010 (0.0009) -[2023-10-10 14:50:01,697][76542] Updated weights for policy 1, policy_version 55020 (0.0010) -[2023-10-10 14:50:02,064][76542] Updated weights for policy 1, policy_version 55030 (0.0010) -[2023-10-10 14:50:02,425][76542] Updated weights for policy 1, policy_version 55040 (0.0007) -[2023-10-10 14:50:04,594][76543] Updated weights for policy 0, policy_version 55113 (0.0008) -[2023-10-10 14:50:04,960][76543] Updated weights for policy 0, policy_version 55123 (0.0007) -[2023-10-10 14:50:05,338][76543] Updated weights for policy 0, policy_version 55133 (0.0007) -[2023-10-10 14:50:06,047][76542] Updated weights for policy 1, policy_version 55050 (0.0009) -[2023-10-10 14:50:06,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 112820224. Throughput: 0: 1829.8, 1: 1825.9. Samples: 28209160. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:50:06,077][75634] Avg episode reward: [(0, '36.430'), (1, '37.240')] -[2023-10-10 14:50:06,415][76542] Updated weights for policy 1, policy_version 55060 (0.0009) -[2023-10-10 14:50:06,789][76542] Updated weights for policy 1, policy_version 55070 (0.0009) -[2023-10-10 14:50:09,138][76543] Updated weights for policy 0, policy_version 55143 (0.0007) -[2023-10-10 14:50:09,507][76543] Updated weights for policy 0, policy_version 55153 (0.0009) -[2023-10-10 14:50:09,873][76543] Updated weights for policy 0, policy_version 55163 (0.0008) -[2023-10-10 14:50:10,356][76542] Updated weights for policy 1, policy_version 55080 (0.0007) -[2023-10-10 14:50:10,723][76542] Updated weights for policy 1, policy_version 55090 (0.0007) -[2023-10-10 14:50:11,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 112885760. Throughput: 0: 1823.2, 1: 1823.9. Samples: 28231562. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:50:11,076][75634] Avg episode reward: [(0, '34.380'), (1, '34.580')] -[2023-10-10 14:50:11,086][76542] Updated weights for policy 1, policy_version 55100 (0.0009) -[2023-10-10 14:50:13,562][76543] Updated weights for policy 0, policy_version 55173 (0.0009) -[2023-10-10 14:50:13,948][76543] Updated weights for policy 0, policy_version 55183 (0.0008) -[2023-10-10 14:50:14,324][76543] Updated weights for policy 0, policy_version 55193 (0.0007) -[2023-10-10 14:50:14,702][76542] Updated weights for policy 1, policy_version 55110 (0.0011) -[2023-10-10 14:50:15,076][76542] Updated weights for policy 1, policy_version 55120 (0.0009) -[2023-10-10 14:50:15,443][76542] Updated weights for policy 1, policy_version 55130 (0.0008) -[2023-10-10 14:50:16,076][75634] Fps is (10 sec: 16383.9, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 112984064. Throughput: 0: 1824.4, 1: 1821.7. Samples: 28251936. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:50:16,077][75634] Avg episode reward: [(0, '36.630'), (1, '31.430')] -[2023-10-10 14:50:17,924][76543] Updated weights for policy 0, policy_version 55203 (0.0008) -[2023-10-10 14:50:18,291][76543] Updated weights for policy 0, policy_version 55213 (0.0008) -[2023-10-10 14:50:18,670][76543] Updated weights for policy 0, policy_version 55223 (0.0008) -[2023-10-10 14:50:19,202][76542] Updated weights for policy 1, policy_version 55140 (0.0009) -[2023-10-10 14:50:19,591][76542] Updated weights for policy 1, policy_version 55150 (0.0009) -[2023-10-10 14:50:19,966][76542] Updated weights for policy 1, policy_version 55160 (0.0008) -[2023-10-10 14:50:21,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 113049600. Throughput: 0: 1825.1, 1: 1823.4. Samples: 28264402. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:50:21,076][75634] Avg episode reward: [(0, '38.790'), (1, '32.660')] -[2023-10-10 14:50:22,215][76543] Updated weights for policy 0, policy_version 55233 (0.0008) -[2023-10-10 14:50:22,590][76543] Updated weights for policy 0, policy_version 55243 (0.0007) -[2023-10-10 14:50:22,957][76543] Updated weights for policy 0, policy_version 55253 (0.0008) -[2023-10-10 14:50:23,323][76543] Updated weights for policy 0, policy_version 55263 (0.0008) -[2023-10-10 14:50:23,694][76542] Updated weights for policy 1, policy_version 55170 (0.0007) -[2023-10-10 14:50:24,063][76542] Updated weights for policy 1, policy_version 55180 (0.0008) -[2023-10-10 14:50:24,445][76542] Updated weights for policy 1, policy_version 55190 (0.0010) -[2023-10-10 14:50:24,811][76542] Updated weights for policy 1, policy_version 55200 (0.0010) -[2023-10-10 14:50:26,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 113115136. Throughput: 0: 1831.1, 1: 1819.7. Samples: 28285028. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:50:26,076][75634] Avg episode reward: [(0, '36.630'), (1, '35.630')] -[2023-10-10 14:50:27,099][76543] Updated weights for policy 0, policy_version 55273 (0.0009) -[2023-10-10 14:50:27,474][76543] Updated weights for policy 0, policy_version 55283 (0.0010) -[2023-10-10 14:50:27,842][76543] Updated weights for policy 0, policy_version 55293 (0.0008) -[2023-10-10 14:50:28,547][76542] Updated weights for policy 1, policy_version 55210 (0.0009) -[2023-10-10 14:50:28,914][76542] Updated weights for policy 1, policy_version 55220 (0.0007) -[2023-10-10 14:50:29,281][76542] Updated weights for policy 1, policy_version 55230 (0.0008) -[2023-10-10 14:50:31,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 113180672. Throughput: 0: 1825.4, 1: 1826.5. Samples: 28307366. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:50:31,077][75634] Avg episode reward: [(0, '38.220'), (1, '37.110')] -[2023-10-10 14:50:31,087][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000055232_56557568.pth... -[2023-10-10 14:50:31,087][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000055296_56623104.pth... -[2023-10-10 14:50:31,116][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000053536_54820864.pth -[2023-10-10 14:50:31,122][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000053600_54886400.pth -[2023-10-10 14:50:31,506][76543] Updated weights for policy 0, policy_version 55303 (0.0008) -[2023-10-10 14:50:31,882][76543] Updated weights for policy 0, policy_version 55313 (0.0007) -[2023-10-10 14:50:32,245][76543] Updated weights for policy 0, policy_version 55323 (0.0007) -[2023-10-10 14:50:33,026][76542] Updated weights for policy 1, policy_version 55240 (0.0007) -[2023-10-10 14:50:33,396][76542] Updated weights for policy 1, policy_version 55250 (0.0009) -[2023-10-10 14:50:33,773][76542] Updated weights for policy 1, policy_version 55260 (0.0010) -[2023-10-10 14:50:35,969][76543] Updated weights for policy 0, policy_version 55333 (0.0010) -[2023-10-10 14:50:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 113246208. Throughput: 0: 1823.6, 1: 1817.5. Samples: 28317424. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:50:36,076][75634] Avg episode reward: [(0, '39.280'), (1, '34.720')] -[2023-10-10 14:50:36,336][76543] Updated weights for policy 0, policy_version 55343 (0.0008) -[2023-10-10 14:50:36,707][76543] Updated weights for policy 0, policy_version 55353 (0.0007) -[2023-10-10 14:50:37,361][76542] Updated weights for policy 1, policy_version 55270 (0.0007) -[2023-10-10 14:50:37,718][76542] Updated weights for policy 1, policy_version 55280 (0.0007) -[2023-10-10 14:50:38,081][76542] Updated weights for policy 1, policy_version 55290 (0.0009) -[2023-10-10 14:50:40,419][76543] Updated weights for policy 0, policy_version 55363 (0.0007) -[2023-10-10 14:50:40,784][76543] Updated weights for policy 0, policy_version 55373 (0.0008) -[2023-10-10 14:50:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 113311744. Throughput: 0: 1818.0, 1: 1830.8. Samples: 28340038. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:50:41,076][75634] Avg episode reward: [(0, '37.220'), (1, '38.130')] -[2023-10-10 14:50:41,157][76543] Updated weights for policy 0, policy_version 55383 (0.0010) -[2023-10-10 14:50:41,784][76542] Updated weights for policy 1, policy_version 55300 (0.0009) -[2023-10-10 14:50:42,151][76542] Updated weights for policy 1, policy_version 55310 (0.0011) -[2023-10-10 14:50:42,517][76542] Updated weights for policy 1, policy_version 55320 (0.0008) -[2023-10-10 14:50:44,840][76543] Updated weights for policy 0, policy_version 55393 (0.0011) -[2023-10-10 14:50:45,209][76543] Updated weights for policy 0, policy_version 55403 (0.0009) -[2023-10-10 14:50:45,574][76543] Updated weights for policy 0, policy_version 55413 (0.0011) -[2023-10-10 14:50:45,951][76543] Updated weights for policy 0, policy_version 55423 (0.0010) -[2023-10-10 14:50:46,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 113410048. Throughput: 0: 1817.6, 1: 1816.3. Samples: 28362204. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:50:46,077][75634] Avg episode reward: [(0, '37.650'), (1, '39.010')] -[2023-10-10 14:50:46,300][76542] Updated weights for policy 1, policy_version 55330 (0.0008) -[2023-10-10 14:50:46,667][76542] Updated weights for policy 1, policy_version 55340 (0.0010) -[2023-10-10 14:50:47,041][76542] Updated weights for policy 1, policy_version 55350 (0.0010) -[2023-10-10 14:50:47,411][76542] Updated weights for policy 1, policy_version 55360 (0.0009) -[2023-10-10 14:50:49,499][76543] Updated weights for policy 0, policy_version 55433 (0.0007) -[2023-10-10 14:50:49,868][76543] Updated weights for policy 0, policy_version 55443 (0.0010) -[2023-10-10 14:50:50,251][76543] Updated weights for policy 0, policy_version 55453 (0.0011) -[2023-10-10 14:50:51,001][76542] Updated weights for policy 1, policy_version 55370 (0.0007) -[2023-10-10 14:50:51,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 113475584. Throughput: 0: 1823.0, 1: 1816.8. Samples: 28372950. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:50:51,076][75634] Avg episode reward: [(0, '36.570'), (1, '34.290')] -[2023-10-10 14:50:51,370][76542] Updated weights for policy 1, policy_version 55380 (0.0007) -[2023-10-10 14:50:51,741][76542] Updated weights for policy 1, policy_version 55390 (0.0008) -[2023-10-10 14:50:53,794][76543] Updated weights for policy 0, policy_version 55463 (0.0007) -[2023-10-10 14:50:54,155][76543] Updated weights for policy 0, policy_version 55473 (0.0007) -[2023-10-10 14:50:54,521][76543] Updated weights for policy 0, policy_version 55483 (0.0010) -[2023-10-10 14:50:55,362][76542] Updated weights for policy 1, policy_version 55400 (0.0009) -[2023-10-10 14:50:55,726][76542] Updated weights for policy 1, policy_version 55410 (0.0008) -[2023-10-10 14:50:56,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 113541120. Throughput: 0: 1819.9, 1: 1819.2. Samples: 28395320. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:50:56,076][75634] Avg episode reward: [(0, '37.540'), (1, '35.040')] -[2023-10-10 14:50:56,104][76542] Updated weights for policy 1, policy_version 55420 (0.0007) -[2023-10-10 14:50:58,097][76543] Updated weights for policy 0, policy_version 55493 (0.0009) -[2023-10-10 14:50:58,476][76543] Updated weights for policy 0, policy_version 55503 (0.0008) -[2023-10-10 14:50:58,857][76543] Updated weights for policy 0, policy_version 55513 (0.0008) -[2023-10-10 14:50:59,715][76542] Updated weights for policy 1, policy_version 55430 (0.0008) -[2023-10-10 14:51:00,084][76542] Updated weights for policy 1, policy_version 55440 (0.0008) -[2023-10-10 14:51:00,448][76542] Updated weights for policy 1, policy_version 55450 (0.0009) -[2023-10-10 14:51:01,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 113639424. Throughput: 0: 1827.6, 1: 1821.3. Samples: 28416138. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 14:51:01,076][75634] Avg episode reward: [(0, '36.630'), (1, '30.160')] -[2023-10-10 14:51:02,564][76543] Updated weights for policy 0, policy_version 55523 (0.0008) -[2023-10-10 14:51:02,956][76543] Updated weights for policy 0, policy_version 55533 (0.0007) -[2023-10-10 14:51:03,323][76543] Updated weights for policy 0, policy_version 55543 (0.0009) -[2023-10-10 14:51:04,104][76542] Updated weights for policy 1, policy_version 55460 (0.0008) -[2023-10-10 14:51:04,504][76542] Updated weights for policy 1, policy_version 55470 (0.0009) -[2023-10-10 14:51:04,867][76542] Updated weights for policy 1, policy_version 55480 (0.0010) -[2023-10-10 14:51:06,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 113704960. Throughput: 0: 1819.9, 1: 1826.3. Samples: 28428484. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 14:51:06,077][75634] Avg episode reward: [(0, '35.130'), (1, '29.840')] -[2023-10-10 14:51:06,855][76543] Updated weights for policy 0, policy_version 55553 (0.0009) -[2023-10-10 14:51:07,218][76543] Updated weights for policy 0, policy_version 55563 (0.0009) -[2023-10-10 14:51:07,590][76543] Updated weights for policy 0, policy_version 55573 (0.0008) -[2023-10-10 14:51:07,967][76543] Updated weights for policy 0, policy_version 55583 (0.0008) -[2023-10-10 14:51:08,577][76542] Updated weights for policy 1, policy_version 55490 (0.0010) -[2023-10-10 14:51:08,950][76542] Updated weights for policy 1, policy_version 55500 (0.0007) -[2023-10-10 14:51:09,312][76542] Updated weights for policy 1, policy_version 55510 (0.0008) -[2023-10-10 14:51:09,674][76542] Updated weights for policy 1, policy_version 55520 (0.0009) -[2023-10-10 14:51:11,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 113770496. Throughput: 0: 1826.1, 1: 1820.0. Samples: 28449100. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 14:51:11,076][75634] Avg episode reward: [(0, '36.290'), (1, '32.450')] -[2023-10-10 14:51:11,706][76543] Updated weights for policy 0, policy_version 55593 (0.0008) -[2023-10-10 14:51:12,076][76543] Updated weights for policy 0, policy_version 55603 (0.0007) -[2023-10-10 14:51:12,444][76543] Updated weights for policy 0, policy_version 55613 (0.0007) -[2023-10-10 14:51:13,583][76542] Updated weights for policy 1, policy_version 55530 (0.0009) -[2023-10-10 14:51:13,951][76542] Updated weights for policy 1, policy_version 55540 (0.0007) -[2023-10-10 14:51:14,320][76542] Updated weights for policy 1, policy_version 55550 (0.0010) -[2023-10-10 14:51:16,019][76543] Updated weights for policy 0, policy_version 55623 (0.0007) -[2023-10-10 14:51:16,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 113836032. Throughput: 0: 1828.5, 1: 1820.8. Samples: 28471584. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 14:51:16,076][75634] Avg episode reward: [(0, '38.510'), (1, '34.860')] -[2023-10-10 14:51:16,393][76543] Updated weights for policy 0, policy_version 55633 (0.0009) -[2023-10-10 14:51:16,770][76543] Updated weights for policy 0, policy_version 55643 (0.0008) -[2023-10-10 14:51:18,052][76542] Updated weights for policy 1, policy_version 55560 (0.0008) -[2023-10-10 14:51:18,435][76542] Updated weights for policy 1, policy_version 55570 (0.0008) -[2023-10-10 14:51:18,794][76542] Updated weights for policy 1, policy_version 55580 (0.0009) -[2023-10-10 14:51:20,349][76543] Updated weights for policy 0, policy_version 55653 (0.0007) -[2023-10-10 14:51:20,717][76543] Updated weights for policy 0, policy_version 55663 (0.0010) -[2023-10-10 14:51:21,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 113901568. Throughput: 0: 1831.4, 1: 1825.2. Samples: 28481974. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 14:51:21,076][75634] Avg episode reward: [(0, '39.930'), (1, '37.480')] -[2023-10-10 14:51:21,088][76543] Updated weights for policy 0, policy_version 55673 (0.0007) -[2023-10-10 14:51:22,556][76542] Updated weights for policy 1, policy_version 55590 (0.0009) -[2023-10-10 14:51:22,921][76542] Updated weights for policy 1, policy_version 55600 (0.0009) -[2023-10-10 14:51:23,286][76542] Updated weights for policy 1, policy_version 55610 (0.0008) -[2023-10-10 14:51:24,672][76543] Updated weights for policy 0, policy_version 55683 (0.0007) -[2023-10-10 14:51:25,052][76543] Updated weights for policy 0, policy_version 55693 (0.0009) -[2023-10-10 14:51:25,419][76543] Updated weights for policy 0, policy_version 55703 (0.0007) -[2023-10-10 14:51:26,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 113999872. Throughput: 0: 1844.9, 1: 1822.2. Samples: 28505056. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 14:51:26,076][75634] Avg episode reward: [(0, '36.620'), (1, '37.970')] -[2023-10-10 14:51:26,882][76542] Updated weights for policy 1, policy_version 55620 (0.0008) -[2023-10-10 14:51:27,248][76542] Updated weights for policy 1, policy_version 55630 (0.0010) -[2023-10-10 14:51:27,608][76542] Updated weights for policy 1, policy_version 55640 (0.0008) -[2023-10-10 14:51:29,105][76543] Updated weights for policy 0, policy_version 55713 (0.0007) -[2023-10-10 14:51:29,464][76543] Updated weights for policy 0, policy_version 55723 (0.0009) -[2023-10-10 14:51:29,831][76543] Updated weights for policy 0, policy_version 55733 (0.0009) -[2023-10-10 14:51:30,203][76543] Updated weights for policy 0, policy_version 55743 (0.0007) -[2023-10-10 14:51:31,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 114065408. Throughput: 0: 1828.0, 1: 1819.2. Samples: 28526326. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 14:51:31,077][75634] Avg episode reward: [(0, '35.480'), (1, '36.270')] -[2023-10-10 14:51:31,398][76542] Updated weights for policy 1, policy_version 55650 (0.0008) -[2023-10-10 14:51:31,754][76542] Updated weights for policy 1, policy_version 55660 (0.0009) -[2023-10-10 14:51:32,130][76542] Updated weights for policy 1, policy_version 55670 (0.0010) -[2023-10-10 14:51:32,489][76542] Updated weights for policy 1, policy_version 55680 (0.0010) -[2023-10-10 14:51:33,930][76543] Updated weights for policy 0, policy_version 55753 (0.0007) -[2023-10-10 14:51:34,291][76543] Updated weights for policy 0, policy_version 55763 (0.0009) -[2023-10-10 14:51:34,662][76543] Updated weights for policy 0, policy_version 55773 (0.0009) -[2023-10-10 14:51:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 114130944. Throughput: 0: 1844.8, 1: 1816.7. Samples: 28537718. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 14:51:36,076][75634] Avg episode reward: [(0, '38.230'), (1, '34.120')] -[2023-10-10 14:51:36,339][76542] Updated weights for policy 1, policy_version 55690 (0.0009) -[2023-10-10 14:51:36,699][76542] Updated weights for policy 1, policy_version 55700 (0.0007) -[2023-10-10 14:51:37,066][76542] Updated weights for policy 1, policy_version 55710 (0.0009) -[2023-10-10 14:51:38,233][76543] Updated weights for policy 0, policy_version 55783 (0.0007) -[2023-10-10 14:51:38,593][76543] Updated weights for policy 0, policy_version 55793 (0.0011) -[2023-10-10 14:51:38,964][76543] Updated weights for policy 0, policy_version 55803 (0.0011) -[2023-10-10 14:51:40,729][76542] Updated weights for policy 1, policy_version 55720 (0.0011) -[2023-10-10 14:51:41,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 114196480. Throughput: 0: 1833.3, 1: 1809.4. Samples: 28559244. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 14:51:41,076][75634] Avg episode reward: [(0, '38.720'), (1, '32.800')] -[2023-10-10 14:51:41,100][76542] Updated weights for policy 1, policy_version 55730 (0.0008) -[2023-10-10 14:51:41,476][76542] Updated weights for policy 1, policy_version 55740 (0.0010) -[2023-10-10 14:51:42,568][76543] Updated weights for policy 0, policy_version 55813 (0.0009) -[2023-10-10 14:51:42,940][76543] Updated weights for policy 0, policy_version 55823 (0.0010) -[2023-10-10 14:51:43,308][76543] Updated weights for policy 0, policy_version 55833 (0.0011) -[2023-10-10 14:51:44,908][76542] Updated weights for policy 1, policy_version 55750 (0.0009) -[2023-10-10 14:51:45,270][76542] Updated weights for policy 1, policy_version 55760 (0.0007) -[2023-10-10 14:51:45,635][76542] Updated weights for policy 1, policy_version 55770 (0.0009) -[2023-10-10 14:51:46,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 114294784. Throughput: 0: 1851.7, 1: 1811.3. Samples: 28580974. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 14:51:46,076][75634] Avg episode reward: [(0, '38.620'), (1, '31.140')] -[2023-10-10 14:51:46,992][76543] Updated weights for policy 0, policy_version 55843 (0.0010) -[2023-10-10 14:51:47,353][76543] Updated weights for policy 0, policy_version 55853 (0.0007) -[2023-10-10 14:51:47,726][76543] Updated weights for policy 0, policy_version 55863 (0.0011) -[2023-10-10 14:51:49,483][76542] Updated weights for policy 1, policy_version 55780 (0.0008) -[2023-10-10 14:51:49,848][76542] Updated weights for policy 1, policy_version 55790 (0.0010) -[2023-10-10 14:51:50,218][76542] Updated weights for policy 1, policy_version 55800 (0.0008) -[2023-10-10 14:51:51,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 114360320. Throughput: 0: 1840.8, 1: 1797.9. Samples: 28592224. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 14:51:51,077][75634] Avg episode reward: [(0, '38.340'), (1, '33.510')] -[2023-10-10 14:51:51,378][76543] Updated weights for policy 0, policy_version 55873 (0.0010) -[2023-10-10 14:51:51,790][76543] Updated weights for policy 0, policy_version 55883 (0.0009) -[2023-10-10 14:51:52,162][76543] Updated weights for policy 0, policy_version 55893 (0.0008) -[2023-10-10 14:51:52,519][76543] Updated weights for policy 0, policy_version 55903 (0.0007) -[2023-10-10 14:51:53,932][76542] Updated weights for policy 1, policy_version 55810 (0.0008) -[2023-10-10 14:51:54,311][76542] Updated weights for policy 1, policy_version 55820 (0.0007) -[2023-10-10 14:51:54,676][76542] Updated weights for policy 1, policy_version 55830 (0.0008) -[2023-10-10 14:51:55,041][76542] Updated weights for policy 1, policy_version 55840 (0.0007) -[2023-10-10 14:51:56,042][76543] Updated weights for policy 0, policy_version 55913 (0.0008) -[2023-10-10 14:51:56,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 114425856. Throughput: 0: 1859.7, 1: 1813.2. Samples: 28614384. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 14:51:56,076][75634] Avg episode reward: [(0, '38.280'), (1, '35.420')] -[2023-10-10 14:51:56,403][76543] Updated weights for policy 0, policy_version 55923 (0.0009) -[2023-10-10 14:51:56,779][76543] Updated weights for policy 0, policy_version 55933 (0.0008) -[2023-10-10 14:51:58,926][76542] Updated weights for policy 1, policy_version 55850 (0.0009) -[2023-10-10 14:51:59,297][76542] Updated weights for policy 1, policy_version 55860 (0.0010) -[2023-10-10 14:51:59,662][76542] Updated weights for policy 1, policy_version 55870 (0.0007) -[2023-10-10 14:52:00,400][76543] Updated weights for policy 0, policy_version 55943 (0.0009) -[2023-10-10 14:52:00,779][76543] Updated weights for policy 0, policy_version 55953 (0.0007) -[2023-10-10 14:52:01,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 114491392. Throughput: 0: 1861.9, 1: 1809.9. Samples: 28636816. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 14:52:01,077][75634] Avg episode reward: [(0, '41.160'), (1, '35.030')] -[2023-10-10 14:52:01,149][76543] Updated weights for policy 0, policy_version 55963 (0.0008) -[2023-10-10 14:52:03,361][76542] Updated weights for policy 1, policy_version 55880 (0.0008) -[2023-10-10 14:52:03,726][76542] Updated weights for policy 1, policy_version 55890 (0.0008) -[2023-10-10 14:52:04,092][76542] Updated weights for policy 1, policy_version 55900 (0.0008) -[2023-10-10 14:52:04,679][76543] Updated weights for policy 0, policy_version 55973 (0.0008) -[2023-10-10 14:52:05,047][76543] Updated weights for policy 0, policy_version 55983 (0.0007) -[2023-10-10 14:52:05,431][76543] Updated weights for policy 0, policy_version 55993 (0.0009) -[2023-10-10 14:52:06,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 114589696. Throughput: 0: 1863.8, 1: 1816.6. Samples: 28647594. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 14:52:06,076][75634] Avg episode reward: [(0, '34.630'), (1, '37.910')] -[2023-10-10 14:52:07,894][76542] Updated weights for policy 1, policy_version 55910 (0.0008) -[2023-10-10 14:52:08,270][76542] Updated weights for policy 1, policy_version 55920 (0.0010) -[2023-10-10 14:52:08,633][76542] Updated weights for policy 1, policy_version 55930 (0.0007) -[2023-10-10 14:52:09,011][76543] Updated weights for policy 0, policy_version 56003 (0.0007) -[2023-10-10 14:52:09,382][76543] Updated weights for policy 0, policy_version 56013 (0.0008) -[2023-10-10 14:52:09,750][76543] Updated weights for policy 0, policy_version 56023 (0.0007) -[2023-10-10 14:52:11,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 114655232. Throughput: 0: 1843.1, 1: 1807.0. Samples: 28669310. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-10 14:52:11,076][75634] Avg episode reward: [(0, '32.980'), (1, '33.930')] -[2023-10-10 14:52:12,348][76542] Updated weights for policy 1, policy_version 55940 (0.0009) -[2023-10-10 14:52:12,719][76542] Updated weights for policy 1, policy_version 55950 (0.0008) -[2023-10-10 14:52:13,081][76542] Updated weights for policy 1, policy_version 55960 (0.0010) -[2023-10-10 14:52:13,451][76543] Updated weights for policy 0, policy_version 56033 (0.0009) -[2023-10-10 14:52:13,808][76543] Updated weights for policy 0, policy_version 56043 (0.0007) -[2023-10-10 14:52:14,175][76543] Updated weights for policy 0, policy_version 56053 (0.0007) -[2023-10-10 14:52:14,549][76543] Updated weights for policy 0, policy_version 56063 (0.0009) -[2023-10-10 14:52:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 114720768. Throughput: 0: 1852.4, 1: 1811.7. Samples: 28691214. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:52:16,076][75634] Avg episode reward: [(0, '32.710'), (1, '31.560')] -[2023-10-10 14:52:16,626][76542] Updated weights for policy 1, policy_version 55970 (0.0008) -[2023-10-10 14:52:16,996][76542] Updated weights for policy 1, policy_version 55980 (0.0009) -[2023-10-10 14:52:17,371][76542] Updated weights for policy 1, policy_version 55990 (0.0010) -[2023-10-10 14:52:17,737][76542] Updated weights for policy 1, policy_version 56000 (0.0009) -[2023-10-10 14:52:18,339][76543] Updated weights for policy 0, policy_version 56073 (0.0007) -[2023-10-10 14:52:18,706][76543] Updated weights for policy 0, policy_version 56083 (0.0010) -[2023-10-10 14:52:19,078][76543] Updated weights for policy 0, policy_version 56093 (0.0008) -[2023-10-10 14:52:21,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 114786304. Throughput: 0: 1841.5, 1: 1813.2. Samples: 28702176. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:52:21,076][75634] Avg episode reward: [(0, '33.250'), (1, '31.780')] -[2023-10-10 14:52:21,461][76542] Updated weights for policy 1, policy_version 56010 (0.0007) -[2023-10-10 14:52:21,825][76542] Updated weights for policy 1, policy_version 56020 (0.0010) -[2023-10-10 14:52:22,192][76542] Updated weights for policy 1, policy_version 56030 (0.0011) -[2023-10-10 14:52:22,648][76543] Updated weights for policy 0, policy_version 56103 (0.0009) -[2023-10-10 14:52:23,008][76543] Updated weights for policy 0, policy_version 56113 (0.0009) -[2023-10-10 14:52:23,378][76543] Updated weights for policy 0, policy_version 56123 (0.0009) -[2023-10-10 14:52:25,736][76542] Updated weights for policy 1, policy_version 56040 (0.0008) -[2023-10-10 14:52:26,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 114851840. Throughput: 0: 1843.8, 1: 1822.0. Samples: 28724204. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:52:26,076][75634] Avg episode reward: [(0, '32.870'), (1, '35.720')] -[2023-10-10 14:52:26,102][76542] Updated weights for policy 1, policy_version 56050 (0.0008) -[2023-10-10 14:52:26,478][76542] Updated weights for policy 1, policy_version 56060 (0.0007) -[2023-10-10 14:52:27,007][76543] Updated weights for policy 0, policy_version 56133 (0.0007) -[2023-10-10 14:52:27,382][76543] Updated weights for policy 0, policy_version 56143 (0.0009) -[2023-10-10 14:52:27,755][76543] Updated weights for policy 0, policy_version 56153 (0.0009) -[2023-10-10 14:52:30,137][76542] Updated weights for policy 1, policy_version 56070 (0.0007) -[2023-10-10 14:52:30,505][76542] Updated weights for policy 1, policy_version 56080 (0.0007) -[2023-10-10 14:52:30,880][76542] Updated weights for policy 1, policy_version 56090 (0.0011) -[2023-10-10 14:52:31,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 114917376. Throughput: 0: 1846.2, 1: 1828.0. Samples: 28746312. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:52:31,077][75634] Avg episode reward: [(0, '32.190'), (1, '32.410')] -[2023-10-10 14:52:31,086][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000056160_57507840.pth... -[2023-10-10 14:52:31,101][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000056096_57442304.pth... -[2023-10-10 14:52:31,123][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000054464_55771136.pth -[2023-10-10 14:52:31,141][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000054368_55672832.pth -[2023-10-10 14:52:31,364][76543] Updated weights for policy 0, policy_version 56163 (0.0009) -[2023-10-10 14:52:31,744][76543] Updated weights for policy 0, policy_version 56173 (0.0008) -[2023-10-10 14:52:32,122][76543] Updated weights for policy 0, policy_version 56183 (0.0009) -[2023-10-10 14:52:34,557][76542] Updated weights for policy 1, policy_version 56100 (0.0009) -[2023-10-10 14:52:34,942][76542] Updated weights for policy 1, policy_version 56110 (0.0007) -[2023-10-10 14:52:35,308][76542] Updated weights for policy 1, policy_version 56120 (0.0010) -[2023-10-10 14:52:35,858][76543] Updated weights for policy 0, policy_version 56193 (0.0009) -[2023-10-10 14:52:36,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 115015680. Throughput: 0: 1842.5, 1: 1823.6. Samples: 28757198. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:52:36,076][75634] Avg episode reward: [(0, '32.050'), (1, '34.420')] -[2023-10-10 14:52:36,230][76543] Updated weights for policy 0, policy_version 56203 (0.0007) -[2023-10-10 14:52:36,603][76543] Updated weights for policy 0, policy_version 56213 (0.0009) -[2023-10-10 14:52:36,969][76543] Updated weights for policy 0, policy_version 56223 (0.0008) -[2023-10-10 14:52:39,007][76542] Updated weights for policy 1, policy_version 56130 (0.0008) -[2023-10-10 14:52:39,385][76542] Updated weights for policy 1, policy_version 56140 (0.0009) -[2023-10-10 14:52:39,747][76542] Updated weights for policy 1, policy_version 56150 (0.0010) -[2023-10-10 14:52:40,111][76542] Updated weights for policy 1, policy_version 56160 (0.0011) -[2023-10-10 14:52:40,831][76543] Updated weights for policy 0, policy_version 56233 (0.0010) -[2023-10-10 14:52:41,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 115081216. Throughput: 0: 1832.7, 1: 1826.4. Samples: 28779044. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:52:41,077][75634] Avg episode reward: [(0, '31.070'), (1, '37.460')] -[2023-10-10 14:52:41,209][76543] Updated weights for policy 0, policy_version 56243 (0.0010) -[2023-10-10 14:52:41,575][76543] Updated weights for policy 0, policy_version 56253 (0.0009) -[2023-10-10 14:52:43,733][76542] Updated weights for policy 1, policy_version 56170 (0.0007) -[2023-10-10 14:52:44,101][76542] Updated weights for policy 1, policy_version 56180 (0.0007) -[2023-10-10 14:52:44,470][76542] Updated weights for policy 1, policy_version 56190 (0.0007) -[2023-10-10 14:52:45,201][76543] Updated weights for policy 0, policy_version 56263 (0.0008) -[2023-10-10 14:52:45,577][76543] Updated weights for policy 0, policy_version 56273 (0.0007) -[2023-10-10 14:52:45,949][76543] Updated weights for policy 0, policy_version 56283 (0.0008) -[2023-10-10 14:52:46,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 115146752. Throughput: 0: 1819.9, 1: 1827.0. Samples: 28800926. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:52:46,076][75634] Avg episode reward: [(0, '31.230'), (1, '35.930')] -[2023-10-10 14:52:48,112][76542] Updated weights for policy 1, policy_version 56200 (0.0007) -[2023-10-10 14:52:48,478][76542] Updated weights for policy 1, policy_version 56210 (0.0008) -[2023-10-10 14:52:48,850][76542] Updated weights for policy 1, policy_version 56220 (0.0008) -[2023-10-10 14:52:49,561][76543] Updated weights for policy 0, policy_version 56293 (0.0009) -[2023-10-10 14:52:49,931][76543] Updated weights for policy 0, policy_version 56303 (0.0010) -[2023-10-10 14:52:50,311][76543] Updated weights for policy 0, policy_version 56313 (0.0008) -[2023-10-10 14:52:51,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 115245056. Throughput: 0: 1824.6, 1: 1819.6. Samples: 28811584. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:52:51,076][75634] Avg episode reward: [(0, '30.490'), (1, '33.620')] -[2023-10-10 14:52:52,609][76542] Updated weights for policy 1, policy_version 56230 (0.0009) -[2023-10-10 14:52:52,979][76542] Updated weights for policy 1, policy_version 56240 (0.0009) -[2023-10-10 14:52:53,360][76542] Updated weights for policy 1, policy_version 56250 (0.0009) -[2023-10-10 14:52:54,041][76543] Updated weights for policy 0, policy_version 56323 (0.0009) -[2023-10-10 14:52:54,417][76543] Updated weights for policy 0, policy_version 56333 (0.0009) -[2023-10-10 14:52:54,794][76543] Updated weights for policy 0, policy_version 56343 (0.0009) -[2023-10-10 14:52:56,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 115310592. Throughput: 0: 1825.2, 1: 1832.7. Samples: 28833916. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:52:56,076][75634] Avg episode reward: [(0, '30.090'), (1, '32.520')] -[2023-10-10 14:52:56,892][76542] Updated weights for policy 1, policy_version 56260 (0.0010) -[2023-10-10 14:52:57,265][76542] Updated weights for policy 1, policy_version 56270 (0.0009) -[2023-10-10 14:52:57,626][76542] Updated weights for policy 1, policy_version 56280 (0.0007) -[2023-10-10 14:52:58,465][76543] Updated weights for policy 0, policy_version 56353 (0.0009) -[2023-10-10 14:52:58,829][76543] Updated weights for policy 0, policy_version 56363 (0.0007) -[2023-10-10 14:52:59,197][76543] Updated weights for policy 0, policy_version 56373 (0.0010) -[2023-10-10 14:52:59,570][76543] Updated weights for policy 0, policy_version 56383 (0.0010) -[2023-10-10 14:53:01,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 115376128. Throughput: 0: 1818.1, 1: 1833.4. Samples: 28855530. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:53:01,076][75634] Avg episode reward: [(0, '33.350'), (1, '36.720')] -[2023-10-10 14:53:01,323][76542] Updated weights for policy 1, policy_version 56290 (0.0009) -[2023-10-10 14:53:01,703][76542] Updated weights for policy 1, policy_version 56300 (0.0010) -[2023-10-10 14:53:02,069][76542] Updated weights for policy 1, policy_version 56310 (0.0008) -[2023-10-10 14:53:02,434][76542] Updated weights for policy 1, policy_version 56320 (0.0008) -[2023-10-10 14:53:03,395][76543] Updated weights for policy 0, policy_version 56393 (0.0008) -[2023-10-10 14:53:03,769][76543] Updated weights for policy 0, policy_version 56403 (0.0007) -[2023-10-10 14:53:04,145][76543] Updated weights for policy 0, policy_version 56413 (0.0009) -[2023-10-10 14:53:06,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 115441664. Throughput: 0: 1819.7, 1: 1829.9. Samples: 28866412. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:53:06,077][75634] Avg episode reward: [(0, '33.940'), (1, '31.490')] -[2023-10-10 14:53:06,251][76542] Updated weights for policy 1, policy_version 56330 (0.0008) -[2023-10-10 14:53:06,619][76542] Updated weights for policy 1, policy_version 56340 (0.0007) -[2023-10-10 14:53:06,991][76542] Updated weights for policy 1, policy_version 56350 (0.0008) -[2023-10-10 14:53:07,858][76543] Updated weights for policy 0, policy_version 56423 (0.0008) -[2023-10-10 14:53:08,243][76543] Updated weights for policy 0, policy_version 56433 (0.0010) -[2023-10-10 14:53:08,612][76543] Updated weights for policy 0, policy_version 56443 (0.0007) -[2023-10-10 14:53:10,485][76542] Updated weights for policy 1, policy_version 56360 (0.0009) -[2023-10-10 14:53:10,847][76542] Updated weights for policy 1, policy_version 56370 (0.0010) -[2023-10-10 14:53:11,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 115507200. Throughput: 0: 1814.9, 1: 1827.7. Samples: 28888122. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:53:11,076][75634] Avg episode reward: [(0, '34.790'), (1, '32.930')] -[2023-10-10 14:53:11,221][76542] Updated weights for policy 1, policy_version 56380 (0.0007) -[2023-10-10 14:53:12,303][76543] Updated weights for policy 0, policy_version 56453 (0.0008) -[2023-10-10 14:53:12,674][76543] Updated weights for policy 0, policy_version 56463 (0.0008) -[2023-10-10 14:53:13,036][76543] Updated weights for policy 0, policy_version 56473 (0.0007) -[2023-10-10 14:53:14,929][76542] Updated weights for policy 1, policy_version 56390 (0.0009) -[2023-10-10 14:53:15,310][76542] Updated weights for policy 1, policy_version 56400 (0.0009) -[2023-10-10 14:53:15,679][76542] Updated weights for policy 1, policy_version 56410 (0.0008) -[2023-10-10 14:53:16,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 115605504. Throughput: 0: 1811.9, 1: 1818.7. Samples: 28909688. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:53:16,078][75634] Avg episode reward: [(0, '38.000'), (1, '31.910')] -[2023-10-10 14:53:16,751][76543] Updated weights for policy 0, policy_version 56483 (0.0010) -[2023-10-10 14:53:17,115][76543] Updated weights for policy 0, policy_version 56493 (0.0010) -[2023-10-10 14:53:17,482][76543] Updated weights for policy 0, policy_version 56503 (0.0010) -[2023-10-10 14:53:19,433][76542] Updated weights for policy 1, policy_version 56420 (0.0009) -[2023-10-10 14:53:19,807][76542] Updated weights for policy 1, policy_version 56430 (0.0008) -[2023-10-10 14:53:20,178][76542] Updated weights for policy 1, policy_version 56440 (0.0010) -[2023-10-10 14:53:21,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 115671040. Throughput: 0: 1809.3, 1: 1825.4. Samples: 28920760. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:53:21,076][75634] Avg episode reward: [(0, '36.880'), (1, '33.470')] -[2023-10-10 14:53:21,242][76543] Updated weights for policy 0, policy_version 56513 (0.0010) -[2023-10-10 14:53:21,610][76543] Updated weights for policy 0, policy_version 56523 (0.0008) -[2023-10-10 14:53:21,994][76543] Updated weights for policy 0, policy_version 56533 (0.0009) -[2023-10-10 14:53:22,364][76543] Updated weights for policy 0, policy_version 56543 (0.0007) -[2023-10-10 14:53:23,803][76542] Updated weights for policy 1, policy_version 56450 (0.0009) -[2023-10-10 14:53:24,168][76542] Updated weights for policy 1, policy_version 56460 (0.0008) -[2023-10-10 14:53:24,532][76542] Updated weights for policy 1, policy_version 56470 (0.0011) -[2023-10-10 14:53:24,896][76542] Updated weights for policy 1, policy_version 56480 (0.0010) -[2023-10-10 14:53:26,076][75634] Fps is (10 sec: 13107.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 115736576. Throughput: 0: 1809.0, 1: 1815.3. Samples: 28942138. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:53:26,076][75634] Avg episode reward: [(0, '36.600'), (1, '35.390')] -[2023-10-10 14:53:26,161][76543] Updated weights for policy 0, policy_version 56553 (0.0010) -[2023-10-10 14:53:26,543][76543] Updated weights for policy 0, policy_version 56563 (0.0010) -[2023-10-10 14:53:26,906][76543] Updated weights for policy 0, policy_version 56573 (0.0010) -[2023-10-10 14:53:28,656][76542] Updated weights for policy 1, policy_version 56490 (0.0007) -[2023-10-10 14:53:29,035][76542] Updated weights for policy 1, policy_version 56500 (0.0011) -[2023-10-10 14:53:29,394][76542] Updated weights for policy 1, policy_version 56510 (0.0008) -[2023-10-10 14:53:30,585][76543] Updated weights for policy 0, policy_version 56583 (0.0008) -[2023-10-10 14:53:30,950][76543] Updated weights for policy 0, policy_version 56593 (0.0009) -[2023-10-10 14:53:31,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 115802112. Throughput: 0: 1815.8, 1: 1818.8. Samples: 28964482. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-10 14:53:31,077][75634] Avg episode reward: [(0, '38.160'), (1, '35.680')] -[2023-10-10 14:53:31,336][76543] Updated weights for policy 0, policy_version 56603 (0.0008) -[2023-10-10 14:53:33,039][76542] Updated weights for policy 1, policy_version 56520 (0.0008) -[2023-10-10 14:53:33,405][76542] Updated weights for policy 1, policy_version 56530 (0.0008) -[2023-10-10 14:53:33,773][76542] Updated weights for policy 1, policy_version 56540 (0.0009) -[2023-10-10 14:53:35,024][76543] Updated weights for policy 0, policy_version 56613 (0.0007) -[2023-10-10 14:53:35,398][76543] Updated weights for policy 0, policy_version 56623 (0.0007) -[2023-10-10 14:53:35,772][76543] Updated weights for policy 0, policy_version 56633 (0.0009) -[2023-10-10 14:53:36,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 115900416. Throughput: 0: 1808.7, 1: 1819.5. Samples: 28974854. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-10 14:53:36,076][75634] Avg episode reward: [(0, '36.780'), (1, '37.130')] -[2023-10-10 14:53:37,451][76542] Updated weights for policy 1, policy_version 56550 (0.0009) -[2023-10-10 14:53:37,822][76542] Updated weights for policy 1, policy_version 56560 (0.0010) -[2023-10-10 14:53:38,197][76542] Updated weights for policy 1, policy_version 56570 (0.0007) -[2023-10-10 14:53:39,269][76543] Updated weights for policy 0, policy_version 56643 (0.0010) -[2023-10-10 14:53:39,649][76543] Updated weights for policy 0, policy_version 56653 (0.0011) -[2023-10-10 14:53:40,021][76543] Updated weights for policy 0, policy_version 56663 (0.0011) -[2023-10-10 14:53:41,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 115965952. Throughput: 0: 1815.7, 1: 1814.0. Samples: 28997254. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-10 14:53:41,076][75634] Avg episode reward: [(0, '39.830'), (1, '34.580')] -[2023-10-10 14:53:41,834][76542] Updated weights for policy 1, policy_version 56580 (0.0007) -[2023-10-10 14:53:42,203][76542] Updated weights for policy 1, policy_version 56590 (0.0008) -[2023-10-10 14:53:42,563][76542] Updated weights for policy 1, policy_version 56600 (0.0008) -[2023-10-10 14:53:43,641][76543] Updated weights for policy 0, policy_version 56673 (0.0008) -[2023-10-10 14:53:44,007][76543] Updated weights for policy 0, policy_version 56683 (0.0007) -[2023-10-10 14:53:44,384][76543] Updated weights for policy 0, policy_version 56693 (0.0008) -[2023-10-10 14:53:44,760][76543] Updated weights for policy 0, policy_version 56703 (0.0011) -[2023-10-10 14:53:46,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 116031488. Throughput: 0: 1818.2, 1: 1819.3. Samples: 29019218. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-10 14:53:46,076][75634] Avg episode reward: [(0, '39.210'), (1, '38.460')] -[2023-10-10 14:53:46,294][76542] Updated weights for policy 1, policy_version 56610 (0.0008) -[2023-10-10 14:53:46,664][76542] Updated weights for policy 1, policy_version 56620 (0.0007) -[2023-10-10 14:53:47,029][76542] Updated weights for policy 1, policy_version 56630 (0.0008) -[2023-10-10 14:53:47,397][76542] Updated weights for policy 1, policy_version 56640 (0.0008) -[2023-10-10 14:53:48,415][76543] Updated weights for policy 0, policy_version 56713 (0.0008) -[2023-10-10 14:53:48,789][76543] Updated weights for policy 0, policy_version 56723 (0.0007) -[2023-10-10 14:53:49,155][76543] Updated weights for policy 0, policy_version 56733 (0.0008) -[2023-10-10 14:53:50,949][76542] Updated weights for policy 1, policy_version 56650 (0.0008) -[2023-10-10 14:53:51,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 116097024. Throughput: 0: 1821.9, 1: 1823.3. Samples: 29030446. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-10 14:53:51,076][75634] Avg episode reward: [(0, '38.010'), (1, '34.390')] -[2023-10-10 14:53:51,315][76542] Updated weights for policy 1, policy_version 56660 (0.0008) -[2023-10-10 14:53:51,680][76542] Updated weights for policy 1, policy_version 56670 (0.0007) -[2023-10-10 14:53:52,772][76543] Updated weights for policy 0, policy_version 56743 (0.0008) -[2023-10-10 14:53:53,151][76543] Updated weights for policy 0, policy_version 56753 (0.0007) -[2023-10-10 14:53:53,521][76543] Updated weights for policy 0, policy_version 56763 (0.0008) -[2023-10-10 14:53:55,359][76542] Updated weights for policy 1, policy_version 56680 (0.0008) -[2023-10-10 14:53:55,735][76542] Updated weights for policy 1, policy_version 56690 (0.0007) -[2023-10-10 14:53:56,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 116162560. Throughput: 0: 1824.3, 1: 1826.0. Samples: 29052388. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-10 14:53:56,076][75634] Avg episode reward: [(0, '36.540'), (1, '34.250')] -[2023-10-10 14:53:56,101][76542] Updated weights for policy 1, policy_version 56700 (0.0008) -[2023-10-10 14:53:56,997][76543] Updated weights for policy 0, policy_version 56773 (0.0009) -[2023-10-10 14:53:57,362][76543] Updated weights for policy 0, policy_version 56783 (0.0011) -[2023-10-10 14:53:57,735][76543] Updated weights for policy 0, policy_version 56793 (0.0007) -[2023-10-10 14:53:59,881][76542] Updated weights for policy 1, policy_version 56710 (0.0009) -[2023-10-10 14:54:00,253][76542] Updated weights for policy 1, policy_version 56720 (0.0007) -[2023-10-10 14:54:00,626][76542] Updated weights for policy 1, policy_version 56730 (0.0009) -[2023-10-10 14:54:01,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 116260864. Throughput: 0: 1829.9, 1: 1826.4. Samples: 29074222. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-10 14:54:01,077][75634] Avg episode reward: [(0, '32.210'), (1, '35.540')] -[2023-10-10 14:54:01,348][76543] Updated weights for policy 0, policy_version 56803 (0.0008) -[2023-10-10 14:54:01,720][76543] Updated weights for policy 0, policy_version 56813 (0.0009) -[2023-10-10 14:54:02,087][76543] Updated weights for policy 0, policy_version 56823 (0.0009) -[2023-10-10 14:54:04,269][76542] Updated weights for policy 1, policy_version 56740 (0.0011) -[2023-10-10 14:54:04,663][76542] Updated weights for policy 1, policy_version 56750 (0.0009) -[2023-10-10 14:54:05,030][76542] Updated weights for policy 1, policy_version 56760 (0.0008) -[2023-10-10 14:54:05,829][76543] Updated weights for policy 0, policy_version 56833 (0.0011) -[2023-10-10 14:54:06,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 116326400. Throughput: 0: 1834.7, 1: 1829.3. Samples: 29085642. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-10 14:54:06,077][75634] Avg episode reward: [(0, '33.440'), (1, '40.150')] -[2023-10-10 14:54:06,203][76543] Updated weights for policy 0, policy_version 56843 (0.0011) -[2023-10-10 14:54:06,573][76543] Updated weights for policy 0, policy_version 56853 (0.0007) -[2023-10-10 14:54:06,950][76543] Updated weights for policy 0, policy_version 56863 (0.0008) -[2023-10-10 14:54:08,739][76542] Updated weights for policy 1, policy_version 56770 (0.0010) -[2023-10-10 14:54:09,113][76542] Updated weights for policy 1, policy_version 56780 (0.0009) -[2023-10-10 14:54:09,476][76542] Updated weights for policy 1, policy_version 56790 (0.0008) -[2023-10-10 14:54:09,848][76542] Updated weights for policy 1, policy_version 56800 (0.0009) -[2023-10-10 14:54:10,678][76543] Updated weights for policy 0, policy_version 56873 (0.0010) -[2023-10-10 14:54:11,040][76543] Updated weights for policy 0, policy_version 56883 (0.0010) -[2023-10-10 14:54:11,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 116391936. Throughput: 0: 1836.7, 1: 1829.8. Samples: 29107134. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-10 14:54:11,077][75634] Avg episode reward: [(0, '35.340'), (1, '39.770')] -[2023-10-10 14:54:11,410][76543] Updated weights for policy 0, policy_version 56893 (0.0007) -[2023-10-10 14:54:13,611][76542] Updated weights for policy 1, policy_version 56810 (0.0010) -[2023-10-10 14:54:13,983][76542] Updated weights for policy 1, policy_version 56820 (0.0007) -[2023-10-10 14:54:14,348][76542] Updated weights for policy 1, policy_version 56830 (0.0008) -[2023-10-10 14:54:15,152][76543] Updated weights for policy 0, policy_version 56903 (0.0010) -[2023-10-10 14:54:15,526][76543] Updated weights for policy 0, policy_version 56913 (0.0011) -[2023-10-10 14:54:15,894][76543] Updated weights for policy 0, policy_version 56923 (0.0008) -[2023-10-10 14:54:16,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 116490240. Throughput: 0: 1826.9, 1: 1829.8. Samples: 29129034. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-10 14:54:16,077][75634] Avg episode reward: [(0, '34.410'), (1, '37.280')] -[2023-10-10 14:54:18,280][76542] Updated weights for policy 1, policy_version 56840 (0.0008) -[2023-10-10 14:54:18,651][76542] Updated weights for policy 1, policy_version 56850 (0.0008) -[2023-10-10 14:54:19,030][76542] Updated weights for policy 1, policy_version 56860 (0.0008) -[2023-10-10 14:54:19,549][76543] Updated weights for policy 0, policy_version 56933 (0.0008) -[2023-10-10 14:54:19,909][76543] Updated weights for policy 0, policy_version 56943 (0.0008) -[2023-10-10 14:54:20,284][76543] Updated weights for policy 0, policy_version 56953 (0.0010) -[2023-10-10 14:54:21,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 116555776. Throughput: 0: 1834.4, 1: 1830.1. Samples: 29139760. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-10 14:54:21,077][75634] Avg episode reward: [(0, '35.950'), (1, '35.570')] -[2023-10-10 14:54:22,597][76542] Updated weights for policy 1, policy_version 56870 (0.0007) -[2023-10-10 14:54:22,955][76542] Updated weights for policy 1, policy_version 56880 (0.0008) -[2023-10-10 14:54:23,322][76542] Updated weights for policy 1, policy_version 56890 (0.0010) -[2023-10-10 14:54:23,930][76543] Updated weights for policy 0, policy_version 56963 (0.0010) -[2023-10-10 14:54:24,314][76543] Updated weights for policy 0, policy_version 56973 (0.0011) -[2023-10-10 14:54:24,678][76543] Updated weights for policy 0, policy_version 56983 (0.0011) -[2023-10-10 14:54:26,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 116621312. Throughput: 0: 1823.4, 1: 1827.5. Samples: 29161544. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-10 14:54:26,076][75634] Avg episode reward: [(0, '36.980'), (1, '36.130')] -[2023-10-10 14:54:26,913][76542] Updated weights for policy 1, policy_version 56900 (0.0009) -[2023-10-10 14:54:27,282][76542] Updated weights for policy 1, policy_version 56910 (0.0007) -[2023-10-10 14:54:27,642][76542] Updated weights for policy 1, policy_version 56920 (0.0009) -[2023-10-10 14:54:28,416][76543] Updated weights for policy 0, policy_version 56993 (0.0008) -[2023-10-10 14:54:28,786][76543] Updated weights for policy 0, policy_version 57003 (0.0010) -[2023-10-10 14:54:29,152][76543] Updated weights for policy 0, policy_version 57013 (0.0008) -[2023-10-10 14:54:29,516][76543] Updated weights for policy 0, policy_version 57023 (0.0008) -[2023-10-10 14:54:31,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 116686848. Throughput: 0: 1826.7, 1: 1826.7. Samples: 29183626. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-10 14:54:31,077][75634] Avg episode reward: [(0, '34.470'), (1, '33.080')] -[2023-10-10 14:54:31,088][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000057024_58392576.pth... -[2023-10-10 14:54:31,089][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000056928_58294272.pth... -[2023-10-10 14:54:31,124][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000055232_56557568.pth -[2023-10-10 14:54:31,130][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000055296_56623104.pth -[2023-10-10 14:54:31,337][76542] Updated weights for policy 1, policy_version 56930 (0.0008) -[2023-10-10 14:54:31,705][76542] Updated weights for policy 1, policy_version 56940 (0.0007) -[2023-10-10 14:54:32,087][76542] Updated weights for policy 1, policy_version 56950 (0.0007) -[2023-10-10 14:54:32,456][76542] Updated weights for policy 1, policy_version 56960 (0.0008) -[2023-10-10 14:54:33,212][76543] Updated weights for policy 0, policy_version 57033 (0.0007) -[2023-10-10 14:54:33,588][76543] Updated weights for policy 0, policy_version 57043 (0.0009) -[2023-10-10 14:54:33,960][76543] Updated weights for policy 0, policy_version 57053 (0.0010) -[2023-10-10 14:54:36,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 116752384. Throughput: 0: 1823.9, 1: 1824.5. Samples: 29194624. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-10 14:54:36,077][75634] Avg episode reward: [(0, '36.250'), (1, '35.890')] -[2023-10-10 14:54:36,159][76542] Updated weights for policy 1, policy_version 56970 (0.0010) -[2023-10-10 14:54:36,539][76542] Updated weights for policy 1, policy_version 56980 (0.0010) -[2023-10-10 14:54:36,903][76542] Updated weights for policy 1, policy_version 56990 (0.0011) -[2023-10-10 14:54:37,526][76543] Updated weights for policy 0, policy_version 57063 (0.0011) -[2023-10-10 14:54:37,895][76543] Updated weights for policy 0, policy_version 57073 (0.0009) -[2023-10-10 14:54:38,272][76543] Updated weights for policy 0, policy_version 57083 (0.0009) -[2023-10-10 14:54:40,621][76542] Updated weights for policy 1, policy_version 57000 (0.0008) -[2023-10-10 14:54:40,991][76542] Updated weights for policy 1, policy_version 57010 (0.0007) -[2023-10-10 14:54:41,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 116817920. Throughput: 0: 1825.2, 1: 1815.5. Samples: 29216218. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-10 14:54:41,076][75634] Avg episode reward: [(0, '34.490'), (1, '35.430')] -[2023-10-10 14:54:41,364][76542] Updated weights for policy 1, policy_version 57020 (0.0009) -[2023-10-10 14:54:41,985][76543] Updated weights for policy 0, policy_version 57093 (0.0009) -[2023-10-10 14:54:42,351][76543] Updated weights for policy 0, policy_version 57103 (0.0010) -[2023-10-10 14:54:42,723][76543] Updated weights for policy 0, policy_version 57113 (0.0010) -[2023-10-10 14:54:45,213][76542] Updated weights for policy 1, policy_version 57030 (0.0010) -[2023-10-10 14:54:45,585][76542] Updated weights for policy 1, policy_version 57040 (0.0011) -[2023-10-10 14:54:45,958][76542] Updated weights for policy 1, policy_version 57050 (0.0009) -[2023-10-10 14:54:46,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 116883456. Throughput: 0: 1819.4, 1: 1819.4. Samples: 29237966. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-10 14:54:46,076][75634] Avg episode reward: [(0, '38.090'), (1, '36.130')] -[2023-10-10 14:54:46,407][76543] Updated weights for policy 0, policy_version 57123 (0.0009) -[2023-10-10 14:54:46,776][76543] Updated weights for policy 0, policy_version 57133 (0.0007) -[2023-10-10 14:54:47,140][76543] Updated weights for policy 0, policy_version 57143 (0.0009) -[2023-10-10 14:54:49,759][76542] Updated weights for policy 1, policy_version 57060 (0.0010) -[2023-10-10 14:54:50,156][76542] Updated weights for policy 1, policy_version 57070 (0.0008) -[2023-10-10 14:54:50,529][76542] Updated weights for policy 1, policy_version 57080 (0.0008) -[2023-10-10 14:54:50,848][76543] Updated weights for policy 0, policy_version 57153 (0.0009) -[2023-10-10 14:54:51,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 116981760. Throughput: 0: 1821.8, 1: 1808.4. Samples: 29248998. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-10 14:54:51,077][75634] Avg episode reward: [(0, '37.520'), (1, '35.770')] -[2023-10-10 14:54:51,216][76543] Updated weights for policy 0, policy_version 57163 (0.0008) -[2023-10-10 14:54:51,601][76543] Updated weights for policy 0, policy_version 57173 (0.0007) -[2023-10-10 14:54:51,975][76543] Updated weights for policy 0, policy_version 57183 (0.0008) -[2023-10-10 14:54:54,102][76542] Updated weights for policy 1, policy_version 57090 (0.0010) -[2023-10-10 14:54:54,470][76542] Updated weights for policy 1, policy_version 57100 (0.0008) -[2023-10-10 14:54:54,849][76542] Updated weights for policy 1, policy_version 57110 (0.0011) -[2023-10-10 14:54:55,223][76542] Updated weights for policy 1, policy_version 57120 (0.0010) -[2023-10-10 14:54:55,737][76543] Updated weights for policy 0, policy_version 57193 (0.0007) -[2023-10-10 14:54:56,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 117047296. Throughput: 0: 1823.0, 1: 1815.9. Samples: 29270886. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-10 14:54:56,076][75634] Avg episode reward: [(0, '36.160'), (1, '36.040')] -[2023-10-10 14:54:56,112][76543] Updated weights for policy 0, policy_version 57203 (0.0009) -[2023-10-10 14:54:56,484][76543] Updated weights for policy 0, policy_version 57213 (0.0010) -[2023-10-10 14:54:58,792][76542] Updated weights for policy 1, policy_version 57130 (0.0009) -[2023-10-10 14:54:59,150][76542] Updated weights for policy 1, policy_version 57140 (0.0011) -[2023-10-10 14:54:59,512][76542] Updated weights for policy 1, policy_version 57150 (0.0011) -[2023-10-10 14:54:59,992][76543] Updated weights for policy 0, policy_version 57223 (0.0008) -[2023-10-10 14:55:00,360][76543] Updated weights for policy 0, policy_version 57233 (0.0008) -[2023-10-10 14:55:00,724][76543] Updated weights for policy 0, policy_version 57243 (0.0008) -[2023-10-10 14:55:01,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 117145600. Throughput: 0: 1820.1, 1: 1807.6. Samples: 29292282. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-10 14:55:01,076][75634] Avg episode reward: [(0, '33.010'), (1, '34.330')] -[2023-10-10 14:55:03,213][76542] Updated weights for policy 1, policy_version 57160 (0.0009) -[2023-10-10 14:55:03,589][76542] Updated weights for policy 1, policy_version 57170 (0.0009) -[2023-10-10 14:55:03,964][76542] Updated weights for policy 1, policy_version 57180 (0.0008) -[2023-10-10 14:55:04,324][76543] Updated weights for policy 0, policy_version 57253 (0.0009) -[2023-10-10 14:55:04,689][76543] Updated weights for policy 0, policy_version 57263 (0.0008) -[2023-10-10 14:55:05,064][76543] Updated weights for policy 0, policy_version 57273 (0.0008) -[2023-10-10 14:55:06,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 117211136. Throughput: 0: 1827.9, 1: 1811.9. Samples: 29303548. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-10 14:55:06,077][75634] Avg episode reward: [(0, '31.490'), (1, '31.400')] -[2023-10-10 14:55:07,703][76542] Updated weights for policy 1, policy_version 57190 (0.0009) -[2023-10-10 14:55:08,057][76542] Updated weights for policy 1, policy_version 57200 (0.0008) -[2023-10-10 14:55:08,437][76542] Updated weights for policy 1, policy_version 57210 (0.0011) -[2023-10-10 14:55:08,596][76543] Updated weights for policy 0, policy_version 57283 (0.0009) -[2023-10-10 14:55:08,957][76543] Updated weights for policy 0, policy_version 57293 (0.0008) -[2023-10-10 14:55:09,330][76543] Updated weights for policy 0, policy_version 57303 (0.0007) -[2023-10-10 14:55:11,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 117276672. Throughput: 0: 1825.3, 1: 1809.9. Samples: 29325130. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-10 14:55:11,077][75634] Avg episode reward: [(0, '32.290'), (1, '33.210')] -[2023-10-10 14:55:12,106][76542] Updated weights for policy 1, policy_version 57220 (0.0008) -[2023-10-10 14:55:12,476][76542] Updated weights for policy 1, policy_version 57230 (0.0010) -[2023-10-10 14:55:12,838][76542] Updated weights for policy 1, policy_version 57240 (0.0007) -[2023-10-10 14:55:12,926][76543] Updated weights for policy 0, policy_version 57313 (0.0007) -[2023-10-10 14:55:13,288][76543] Updated weights for policy 0, policy_version 57323 (0.0009) -[2023-10-10 14:55:13,657][76543] Updated weights for policy 0, policy_version 57333 (0.0007) -[2023-10-10 14:55:14,037][76543] Updated weights for policy 0, policy_version 57343 (0.0008) -[2023-10-10 14:55:16,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 117342208. Throughput: 0: 1841.6, 1: 1803.6. Samples: 29347658. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-10 14:55:16,077][75634] Avg episode reward: [(0, '33.900'), (1, '34.440')] -[2023-10-10 14:55:16,562][76542] Updated weights for policy 1, policy_version 57250 (0.0008) -[2023-10-10 14:55:16,931][76542] Updated weights for policy 1, policy_version 57260 (0.0011) -[2023-10-10 14:55:17,295][76542] Updated weights for policy 1, policy_version 57270 (0.0009) -[2023-10-10 14:55:17,622][76543] Updated weights for policy 0, policy_version 57353 (0.0008) -[2023-10-10 14:55:17,665][76542] Updated weights for policy 1, policy_version 57280 (0.0008) -[2023-10-10 14:55:17,995][76543] Updated weights for policy 0, policy_version 57363 (0.0007) -[2023-10-10 14:55:18,360][76543] Updated weights for policy 0, policy_version 57373 (0.0009) -[2023-10-10 14:55:21,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 117407744. Throughput: 0: 1824.6, 1: 1804.7. Samples: 29357942. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-10 14:55:21,076][75634] Avg episode reward: [(0, '35.190'), (1, '35.590')] -[2023-10-10 14:55:21,353][76542] Updated weights for policy 1, policy_version 57290 (0.0010) -[2023-10-10 14:55:21,720][76542] Updated weights for policy 1, policy_version 57300 (0.0010) -[2023-10-10 14:55:22,013][76543] Updated weights for policy 0, policy_version 57383 (0.0008) -[2023-10-10 14:55:22,085][76542] Updated weights for policy 1, policy_version 57310 (0.0007) -[2023-10-10 14:55:22,381][76543] Updated weights for policy 0, policy_version 57393 (0.0009) -[2023-10-10 14:55:22,758][76543] Updated weights for policy 0, policy_version 57403 (0.0008) -[2023-10-10 14:55:25,901][76542] Updated weights for policy 1, policy_version 57320 (0.0010) -[2023-10-10 14:55:26,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 117473280. Throughput: 0: 1848.5, 1: 1798.8. Samples: 29380348. Policy #0 lag: (min: 9.0, avg: 14.1, max: 41.0) -[2023-10-10 14:55:26,076][75634] Avg episode reward: [(0, '37.480'), (1, '35.110')] -[2023-10-10 14:55:26,272][76542] Updated weights for policy 1, policy_version 57330 (0.0009) -[2023-10-10 14:55:26,307][76543] Updated weights for policy 0, policy_version 57413 (0.0009) -[2023-10-10 14:55:26,635][76542] Updated weights for policy 1, policy_version 57340 (0.0007) -[2023-10-10 14:55:26,674][76543] Updated weights for policy 0, policy_version 57423 (0.0008) -[2023-10-10 14:55:27,035][76543] Updated weights for policy 0, policy_version 57433 (0.0008) -[2023-10-10 14:55:30,385][76542] Updated weights for policy 1, policy_version 57350 (0.0009) -[2023-10-10 14:55:30,753][76542] Updated weights for policy 1, policy_version 57360 (0.0010) -[2023-10-10 14:55:30,845][76543] Updated weights for policy 0, policy_version 57443 (0.0009) -[2023-10-10 14:55:31,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 117538816. Throughput: 0: 1845.9, 1: 1805.8. Samples: 29402296. Policy #0 lag: (min: 9.0, avg: 14.1, max: 41.0) -[2023-10-10 14:55:31,077][75634] Avg episode reward: [(0, '38.450'), (1, '34.780')] -[2023-10-10 14:55:31,121][76542] Updated weights for policy 1, policy_version 57370 (0.0008) -[2023-10-10 14:55:31,206][76543] Updated weights for policy 0, policy_version 57453 (0.0008) -[2023-10-10 14:55:31,580][76543] Updated weights for policy 0, policy_version 57463 (0.0010) -[2023-10-10 14:55:35,065][76542] Updated weights for policy 1, policy_version 57380 (0.0008) -[2023-10-10 14:55:35,288][76543] Updated weights for policy 0, policy_version 57473 (0.0009) -[2023-10-10 14:55:35,432][76542] Updated weights for policy 1, policy_version 57390 (0.0008) -[2023-10-10 14:55:35,650][76543] Updated weights for policy 0, policy_version 57483 (0.0007) -[2023-10-10 14:55:35,804][76542] Updated weights for policy 1, policy_version 57400 (0.0008) -[2023-10-10 14:55:36,019][76543] Updated weights for policy 0, policy_version 57493 (0.0007) -[2023-10-10 14:55:36,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 117604352. Throughput: 0: 1842.2, 1: 1798.3. Samples: 29412822. Policy #0 lag: (min: 9.0, avg: 14.1, max: 41.0) -[2023-10-10 14:55:36,076][75634] Avg episode reward: [(0, '39.070'), (1, '37.270')] -[2023-10-10 14:55:36,392][76543] Updated weights for policy 0, policy_version 57503 (0.0008) -[2023-10-10 14:55:39,446][76542] Updated weights for policy 1, policy_version 57410 (0.0008) -[2023-10-10 14:55:39,816][76542] Updated weights for policy 1, policy_version 57420 (0.0009) -[2023-10-10 14:55:40,128][76543] Updated weights for policy 0, policy_version 57513 (0.0008) -[2023-10-10 14:55:40,179][76542] Updated weights for policy 1, policy_version 57430 (0.0007) -[2023-10-10 14:55:40,486][76543] Updated weights for policy 0, policy_version 57523 (0.0008) -[2023-10-10 14:55:40,544][76542] Updated weights for policy 1, policy_version 57440 (0.0008) -[2023-10-10 14:55:40,856][76543] Updated weights for policy 0, policy_version 57533 (0.0008) -[2023-10-10 14:55:41,076][75634] Fps is (10 sec: 19661.0, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 117735424. Throughput: 0: 1837.8, 1: 1808.7. Samples: 29434978. Policy #0 lag: (min: 9.0, avg: 14.1, max: 41.0) -[2023-10-10 14:55:41,077][75634] Avg episode reward: [(0, '37.350'), (1, '36.520')] -[2023-10-10 14:55:44,273][76542] Updated weights for policy 1, policy_version 57450 (0.0008) -[2023-10-10 14:55:44,652][76542] Updated weights for policy 1, policy_version 57460 (0.0010) -[2023-10-10 14:55:44,723][76543] Updated weights for policy 0, policy_version 57543 (0.0007) -[2023-10-10 14:55:45,023][76542] Updated weights for policy 1, policy_version 57470 (0.0007) -[2023-10-10 14:55:45,095][76543] Updated weights for policy 0, policy_version 57553 (0.0010) -[2023-10-10 14:55:45,473][76543] Updated weights for policy 0, policy_version 57563 (0.0010) -[2023-10-10 14:55:46,076][75634] Fps is (10 sec: 19660.3, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 117800960. Throughput: 0: 1826.0, 1: 1797.5. Samples: 29455342. Policy #0 lag: (min: 9.0, avg: 14.1, max: 41.0) -[2023-10-10 14:55:46,077][75634] Avg episode reward: [(0, '37.970'), (1, '32.470')] -[2023-10-10 14:55:48,828][76542] Updated weights for policy 1, policy_version 57480 (0.0007) -[2023-10-10 14:55:49,189][76542] Updated weights for policy 1, policy_version 57490 (0.0008) -[2023-10-10 14:55:49,250][76543] Updated weights for policy 0, policy_version 57573 (0.0010) -[2023-10-10 14:55:49,558][76542] Updated weights for policy 1, policy_version 57500 (0.0008) -[2023-10-10 14:55:49,625][76543] Updated weights for policy 0, policy_version 57583 (0.0008) -[2023-10-10 14:55:49,990][76543] Updated weights for policy 0, policy_version 57593 (0.0007) -[2023-10-10 14:55:51,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 117866496. Throughput: 0: 1827.5, 1: 1809.6. Samples: 29467214. Policy #0 lag: (min: 9.0, avg: 14.1, max: 41.0) -[2023-10-10 14:55:51,077][75634] Avg episode reward: [(0, '33.950'), (1, '34.520')] -[2023-10-10 14:55:53,181][76542] Updated weights for policy 1, policy_version 57510 (0.0009) -[2023-10-10 14:55:53,529][76543] Updated weights for policy 0, policy_version 57603 (0.0007) -[2023-10-10 14:55:53,549][76542] Updated weights for policy 1, policy_version 57520 (0.0009) -[2023-10-10 14:55:53,900][76543] Updated weights for policy 0, policy_version 57613 (0.0008) -[2023-10-10 14:55:53,916][76542] Updated weights for policy 1, policy_version 57530 (0.0008) -[2023-10-10 14:55:54,270][76543] Updated weights for policy 0, policy_version 57623 (0.0009) -[2023-10-10 14:55:56,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 117932032. Throughput: 0: 1823.6, 1: 1792.8. Samples: 29487868. Policy #0 lag: (min: 9.0, avg: 14.1, max: 41.0) -[2023-10-10 14:55:56,076][75634] Avg episode reward: [(0, '36.700'), (1, '37.140')] -[2023-10-10 14:55:57,568][76542] Updated weights for policy 1, policy_version 57540 (0.0009) -[2023-10-10 14:55:57,807][76543] Updated weights for policy 0, policy_version 57633 (0.0011) -[2023-10-10 14:55:57,931][76542] Updated weights for policy 1, policy_version 57550 (0.0010) -[2023-10-10 14:55:58,173][76543] Updated weights for policy 0, policy_version 57643 (0.0007) -[2023-10-10 14:55:58,301][76542] Updated weights for policy 1, policy_version 57560 (0.0008) -[2023-10-10 14:55:58,536][76543] Updated weights for policy 0, policy_version 57653 (0.0007) -[2023-10-10 14:55:58,913][76543] Updated weights for policy 0, policy_version 57663 (0.0008) -[2023-10-10 14:56:01,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 117997568. Throughput: 0: 1822.3, 1: 1795.2. Samples: 29510442. Policy #0 lag: (min: 16.0, avg: 37.5, max: 40.0) -[2023-10-10 14:56:01,076][75634] Avg episode reward: [(0, '37.860'), (1, '36.650')] -[2023-10-10 14:56:02,103][76542] Updated weights for policy 1, policy_version 57570 (0.0009) -[2023-10-10 14:56:02,475][76542] Updated weights for policy 1, policy_version 57580 (0.0010) -[2023-10-10 14:56:02,750][76543] Updated weights for policy 0, policy_version 57673 (0.0007) -[2023-10-10 14:56:02,846][76542] Updated weights for policy 1, policy_version 57590 (0.0008) -[2023-10-10 14:56:03,126][76543] Updated weights for policy 0, policy_version 57683 (0.0007) -[2023-10-10 14:56:03,212][76542] Updated weights for policy 1, policy_version 57600 (0.0008) -[2023-10-10 14:56:03,487][76543] Updated weights for policy 0, policy_version 57693 (0.0009) -[2023-10-10 14:56:06,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 118063104. Throughput: 0: 1823.5, 1: 1794.4. Samples: 29520746. Policy #0 lag: (min: 16.0, avg: 37.5, max: 40.0) -[2023-10-10 14:56:06,077][75634] Avg episode reward: [(0, '33.660'), (1, '35.700')] -[2023-10-10 14:56:06,892][76542] Updated weights for policy 1, policy_version 57610 (0.0010) -[2023-10-10 14:56:07,190][76543] Updated weights for policy 0, policy_version 57703 (0.0008) -[2023-10-10 14:56:07,255][76542] Updated weights for policy 1, policy_version 57620 (0.0008) -[2023-10-10 14:56:07,564][76543] Updated weights for policy 0, policy_version 57713 (0.0008) -[2023-10-10 14:56:07,628][76542] Updated weights for policy 1, policy_version 57630 (0.0008) -[2023-10-10 14:56:07,927][76543] Updated weights for policy 0, policy_version 57723 (0.0008) -[2023-10-10 14:56:11,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 118128640. Throughput: 0: 1819.0, 1: 1799.5. Samples: 29543182. Policy #0 lag: (min: 16.0, avg: 37.5, max: 40.0) -[2023-10-10 14:56:11,077][75634] Avg episode reward: [(0, '34.480'), (1, '37.910')] -[2023-10-10 14:56:11,384][76542] Updated weights for policy 1, policy_version 57640 (0.0007) -[2023-10-10 14:56:11,505][76543] Updated weights for policy 0, policy_version 57733 (0.0007) -[2023-10-10 14:56:11,741][76542] Updated weights for policy 1, policy_version 57650 (0.0007) -[2023-10-10 14:56:11,866][76543] Updated weights for policy 0, policy_version 57743 (0.0008) -[2023-10-10 14:56:12,114][76542] Updated weights for policy 1, policy_version 57660 (0.0007) -[2023-10-10 14:56:12,239][76543] Updated weights for policy 0, policy_version 57753 (0.0007) -[2023-10-10 14:56:15,682][76542] Updated weights for policy 1, policy_version 57670 (0.0009) -[2023-10-10 14:56:16,041][76542] Updated weights for policy 1, policy_version 57680 (0.0010) -[2023-10-10 14:56:16,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 118194176. Throughput: 0: 1815.6, 1: 1813.2. Samples: 29565592. Policy #0 lag: (min: 16.0, avg: 37.5, max: 40.0) -[2023-10-10 14:56:16,077][75634] Avg episode reward: [(0, '35.550'), (1, '39.130')] -[2023-10-10 14:56:16,156][76543] Updated weights for policy 0, policy_version 57763 (0.0008) -[2023-10-10 14:56:16,406][76542] Updated weights for policy 1, policy_version 57690 (0.0008) -[2023-10-10 14:56:16,533][76543] Updated weights for policy 0, policy_version 57773 (0.0007) -[2023-10-10 14:56:16,916][76543] Updated weights for policy 0, policy_version 57783 (0.0009) -[2023-10-10 14:56:20,098][76542] Updated weights for policy 1, policy_version 57700 (0.0009) -[2023-10-10 14:56:20,477][76543] Updated weights for policy 0, policy_version 57793 (0.0010) -[2023-10-10 14:56:20,485][76542] Updated weights for policy 1, policy_version 57710 (0.0009) -[2023-10-10 14:56:20,842][76543] Updated weights for policy 0, policy_version 57803 (0.0008) -[2023-10-10 14:56:20,864][76542] Updated weights for policy 1, policy_version 57720 (0.0008) -[2023-10-10 14:56:21,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 118259712. Throughput: 0: 1809.5, 1: 1810.2. Samples: 29575710. Policy #0 lag: (min: 16.0, avg: 37.5, max: 40.0) -[2023-10-10 14:56:21,076][75634] Avg episode reward: [(0, '32.620'), (1, '37.840')] -[2023-10-10 14:56:21,215][76543] Updated weights for policy 0, policy_version 57813 (0.0007) -[2023-10-10 14:56:21,585][76543] Updated weights for policy 0, policy_version 57823 (0.0007) -[2023-10-10 14:56:24,484][76542] Updated weights for policy 1, policy_version 57730 (0.0008) -[2023-10-10 14:56:24,868][76542] Updated weights for policy 1, policy_version 57740 (0.0011) -[2023-10-10 14:56:25,228][76542] Updated weights for policy 1, policy_version 57750 (0.0007) -[2023-10-10 14:56:25,284][76543] Updated weights for policy 0, policy_version 57833 (0.0007) -[2023-10-10 14:56:25,599][76542] Updated weights for policy 1, policy_version 57760 (0.0007) -[2023-10-10 14:56:25,659][76543] Updated weights for policy 0, policy_version 57843 (0.0007) -[2023-10-10 14:56:26,021][76543] Updated weights for policy 0, policy_version 57853 (0.0008) -[2023-10-10 14:56:26,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 118358016. Throughput: 0: 1816.9, 1: 1812.5. Samples: 29598302. Policy #0 lag: (min: 16.0, avg: 37.5, max: 40.0) -[2023-10-10 14:56:26,076][75634] Avg episode reward: [(0, '36.460'), (1, '36.970')] -[2023-10-10 14:56:29,406][76542] Updated weights for policy 1, policy_version 57770 (0.0008) -[2023-10-10 14:56:29,769][76543] Updated weights for policy 0, policy_version 57863 (0.0009) -[2023-10-10 14:56:29,777][76542] Updated weights for policy 1, policy_version 57780 (0.0008) -[2023-10-10 14:56:30,145][76543] Updated weights for policy 0, policy_version 57873 (0.0009) -[2023-10-10 14:56:30,150][76542] Updated weights for policy 1, policy_version 57790 (0.0007) -[2023-10-10 14:56:30,521][76543] Updated weights for policy 0, policy_version 57883 (0.0011) -[2023-10-10 14:56:31,076][75634] Fps is (10 sec: 19660.5, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 118456320. Throughput: 0: 1826.4, 1: 1815.4. Samples: 29619224. Policy #0 lag: (min: 16.0, avg: 37.5, max: 40.0) -[2023-10-10 14:56:31,077][75634] Avg episode reward: [(0, '36.410'), (1, '37.540')] -[2023-10-10 14:56:31,085][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000057888_59277312.pth... -[2023-10-10 14:56:31,085][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000057792_59179008.pth... -[2023-10-10 14:56:31,118][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000056096_57442304.pth -[2023-10-10 14:56:31,126][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000056160_57507840.pth -[2023-10-10 14:56:33,766][76542] Updated weights for policy 1, policy_version 57800 (0.0007) -[2023-10-10 14:56:34,132][76542] Updated weights for policy 1, policy_version 57810 (0.0007) -[2023-10-10 14:56:34,176][76543] Updated weights for policy 0, policy_version 57893 (0.0008) -[2023-10-10 14:56:34,491][76542] Updated weights for policy 1, policy_version 57820 (0.0008) -[2023-10-10 14:56:34,540][76543] Updated weights for policy 0, policy_version 57903 (0.0008) -[2023-10-10 14:56:34,908][76543] Updated weights for policy 0, policy_version 57913 (0.0009) -[2023-10-10 14:56:36,076][75634] Fps is (10 sec: 16383.8, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 118521856. Throughput: 0: 1828.8, 1: 1819.9. Samples: 29631406. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-10 14:56:36,077][75634] Avg episode reward: [(0, '36.740'), (1, '31.780')] -[2023-10-10 14:56:38,112][76542] Updated weights for policy 1, policy_version 57830 (0.0009) -[2023-10-10 14:56:38,472][76543] Updated weights for policy 0, policy_version 57923 (0.0008) -[2023-10-10 14:56:38,485][76542] Updated weights for policy 1, policy_version 57840 (0.0007) -[2023-10-10 14:56:38,831][76543] Updated weights for policy 0, policy_version 57933 (0.0007) -[2023-10-10 14:56:38,859][76542] Updated weights for policy 1, policy_version 57850 (0.0007) -[2023-10-10 14:56:39,206][76543] Updated weights for policy 0, policy_version 57943 (0.0008) -[2023-10-10 14:56:41,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 118587392. Throughput: 0: 1826.1, 1: 1824.4. Samples: 29652144. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-10 14:56:41,077][75634] Avg episode reward: [(0, '39.640'), (1, '32.680')] -[2023-10-10 14:56:42,529][76542] Updated weights for policy 1, policy_version 57860 (0.0007) -[2023-10-10 14:56:42,812][76543] Updated weights for policy 0, policy_version 57953 (0.0008) -[2023-10-10 14:56:42,888][76542] Updated weights for policy 1, policy_version 57870 (0.0007) -[2023-10-10 14:56:43,187][76543] Updated weights for policy 0, policy_version 57963 (0.0007) -[2023-10-10 14:56:43,253][76542] Updated weights for policy 1, policy_version 57880 (0.0007) -[2023-10-10 14:56:43,559][76543] Updated weights for policy 0, policy_version 57973 (0.0009) -[2023-10-10 14:56:43,924][76543] Updated weights for policy 0, policy_version 57983 (0.0009) -[2023-10-10 14:56:46,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 118652928. Throughput: 0: 1826.3, 1: 1824.2. Samples: 29674712. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-10 14:56:46,076][75634] Avg episode reward: [(0, '39.090'), (1, '33.020')] -[2023-10-10 14:56:46,906][76542] Updated weights for policy 1, policy_version 57890 (0.0008) -[2023-10-10 14:56:47,270][76542] Updated weights for policy 1, policy_version 57900 (0.0008) -[2023-10-10 14:56:47,639][76542] Updated weights for policy 1, policy_version 57910 (0.0009) -[2023-10-10 14:56:47,666][76543] Updated weights for policy 0, policy_version 57993 (0.0008) -[2023-10-10 14:56:48,006][76542] Updated weights for policy 1, policy_version 57920 (0.0008) -[2023-10-10 14:56:48,031][76543] Updated weights for policy 0, policy_version 58003 (0.0009) -[2023-10-10 14:56:48,399][76543] Updated weights for policy 0, policy_version 58013 (0.0008) -[2023-10-10 14:56:51,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 118718464. Throughput: 0: 1824.8, 1: 1827.6. Samples: 29685106. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-10 14:56:51,077][75634] Avg episode reward: [(0, '37.920'), (1, '33.480')] -[2023-10-10 14:56:51,596][76542] Updated weights for policy 1, policy_version 57930 (0.0007) -[2023-10-10 14:56:51,960][76542] Updated weights for policy 1, policy_version 57940 (0.0008) -[2023-10-10 14:56:52,169][76543] Updated weights for policy 0, policy_version 58023 (0.0007) -[2023-10-10 14:56:52,330][76542] Updated weights for policy 1, policy_version 57950 (0.0008) -[2023-10-10 14:56:52,544][76543] Updated weights for policy 0, policy_version 58033 (0.0007) -[2023-10-10 14:56:52,921][76543] Updated weights for policy 0, policy_version 58043 (0.0007) -[2023-10-10 14:56:55,963][76542] Updated weights for policy 1, policy_version 57960 (0.0009) -[2023-10-10 14:56:56,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 118784000. Throughput: 0: 1827.3, 1: 1830.1. Samples: 29707760. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-10 14:56:56,076][75634] Avg episode reward: [(0, '38.810'), (1, '34.630')] -[2023-10-10 14:56:56,298][76543] Updated weights for policy 0, policy_version 58053 (0.0007) -[2023-10-10 14:56:56,339][76542] Updated weights for policy 1, policy_version 57970 (0.0009) -[2023-10-10 14:56:56,675][76543] Updated weights for policy 0, policy_version 58063 (0.0008) -[2023-10-10 14:56:56,708][76542] Updated weights for policy 1, policy_version 57980 (0.0008) -[2023-10-10 14:56:57,035][76543] Updated weights for policy 0, policy_version 58073 (0.0010) -[2023-10-10 14:57:00,459][76542] Updated weights for policy 1, policy_version 57990 (0.0007) -[2023-10-10 14:57:00,802][76543] Updated weights for policy 0, policy_version 58083 (0.0010) -[2023-10-10 14:57:00,831][76542] Updated weights for policy 1, policy_version 58000 (0.0007) -[2023-10-10 14:57:01,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 118849536. Throughput: 0: 1827.1, 1: 1825.2. Samples: 29729948. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-10 14:57:01,076][75634] Avg episode reward: [(0, '35.790'), (1, '34.920')] -[2023-10-10 14:57:01,170][76543] Updated weights for policy 0, policy_version 58093 (0.0008) -[2023-10-10 14:57:01,201][76542] Updated weights for policy 1, policy_version 58010 (0.0008) -[2023-10-10 14:57:01,544][76543] Updated weights for policy 0, policy_version 58103 (0.0008) -[2023-10-10 14:57:05,041][76542] Updated weights for policy 1, policy_version 58020 (0.0009) -[2023-10-10 14:57:05,229][76543] Updated weights for policy 0, policy_version 58113 (0.0008) -[2023-10-10 14:57:05,406][76542] Updated weights for policy 1, policy_version 58030 (0.0008) -[2023-10-10 14:57:05,597][76543] Updated weights for policy 0, policy_version 58123 (0.0008) -[2023-10-10 14:57:05,767][76542] Updated weights for policy 1, policy_version 58040 (0.0008) -[2023-10-10 14:57:05,955][76543] Updated weights for policy 0, policy_version 58133 (0.0009) -[2023-10-10 14:57:06,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 118947840. Throughput: 0: 1832.8, 1: 1826.1. Samples: 29740360. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-10 14:57:06,076][75634] Avg episode reward: [(0, '36.170'), (1, '37.320')] -[2023-10-10 14:57:06,325][76543] Updated weights for policy 0, policy_version 58143 (0.0010) -[2023-10-10 14:57:09,463][76542] Updated weights for policy 1, policy_version 58050 (0.0008) -[2023-10-10 14:57:09,825][76542] Updated weights for policy 1, policy_version 58060 (0.0009) -[2023-10-10 14:57:10,033][76543] Updated weights for policy 0, policy_version 58153 (0.0009) -[2023-10-10 14:57:10,195][76542] Updated weights for policy 1, policy_version 58070 (0.0007) -[2023-10-10 14:57:10,405][76543] Updated weights for policy 0, policy_version 58163 (0.0007) -[2023-10-10 14:57:10,569][76542] Updated weights for policy 1, policy_version 58080 (0.0007) -[2023-10-10 14:57:10,782][76543] Updated weights for policy 0, policy_version 58173 (0.0007) -[2023-10-10 14:57:11,076][75634] Fps is (10 sec: 19660.4, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 119046144. Throughput: 0: 1828.2, 1: 1820.5. Samples: 29762496. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-10 14:57:11,077][75634] Avg episode reward: [(0, '32.570'), (1, '36.420')] -[2023-10-10 14:57:14,147][76542] Updated weights for policy 1, policy_version 58090 (0.0007) -[2023-10-10 14:57:14,511][76542] Updated weights for policy 1, policy_version 58100 (0.0009) -[2023-10-10 14:57:14,548][76543] Updated weights for policy 0, policy_version 58183 (0.0009) -[2023-10-10 14:57:14,881][76542] Updated weights for policy 1, policy_version 58110 (0.0009) -[2023-10-10 14:57:14,919][76543] Updated weights for policy 0, policy_version 58193 (0.0010) -[2023-10-10 14:57:15,284][76543] Updated weights for policy 0, policy_version 58203 (0.0008) -[2023-10-10 14:57:16,076][75634] Fps is (10 sec: 16383.7, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 119111680. Throughput: 0: 1814.4, 1: 1827.7. Samples: 29783118. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) -[2023-10-10 14:57:16,077][75634] Avg episode reward: [(0, '34.430'), (1, '35.050')] -[2023-10-10 14:57:18,599][76542] Updated weights for policy 1, policy_version 58120 (0.0008) -[2023-10-10 14:57:18,893][76543] Updated weights for policy 0, policy_version 58213 (0.0008) -[2023-10-10 14:57:18,963][76542] Updated weights for policy 1, policy_version 58130 (0.0007) -[2023-10-10 14:57:19,265][76543] Updated weights for policy 0, policy_version 58223 (0.0009) -[2023-10-10 14:57:19,327][76542] Updated weights for policy 1, policy_version 58140 (0.0007) -[2023-10-10 14:57:19,634][76543] Updated weights for policy 0, policy_version 58233 (0.0007) -[2023-10-10 14:57:21,076][75634] Fps is (10 sec: 13107.2, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 119177216. Throughput: 0: 1821.4, 1: 1824.5. Samples: 29795472. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) -[2023-10-10 14:57:21,077][75634] Avg episode reward: [(0, '34.770'), (1, '31.670')] -[2023-10-10 14:57:22,925][76542] Updated weights for policy 1, policy_version 58150 (0.0009) -[2023-10-10 14:57:23,298][76542] Updated weights for policy 1, policy_version 58160 (0.0009) -[2023-10-10 14:57:23,420][76543] Updated weights for policy 0, policy_version 58243 (0.0007) -[2023-10-10 14:57:23,663][76542] Updated weights for policy 1, policy_version 58170 (0.0007) -[2023-10-10 14:57:23,800][76543] Updated weights for policy 0, policy_version 58253 (0.0008) -[2023-10-10 14:57:24,184][76543] Updated weights for policy 0, policy_version 58263 (0.0010) -[2023-10-10 14:57:26,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 119242752. Throughput: 0: 1819.0, 1: 1831.3. Samples: 29816406. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) -[2023-10-10 14:57:26,076][75634] Avg episode reward: [(0, '36.300'), (1, '31.840')] -[2023-10-10 14:57:27,346][76542] Updated weights for policy 1, policy_version 58180 (0.0007) -[2023-10-10 14:57:27,715][76542] Updated weights for policy 1, policy_version 58190 (0.0009) -[2023-10-10 14:57:27,776][76543] Updated weights for policy 0, policy_version 58273 (0.0010) -[2023-10-10 14:57:28,086][76542] Updated weights for policy 1, policy_version 58200 (0.0009) -[2023-10-10 14:57:28,145][76543] Updated weights for policy 0, policy_version 58283 (0.0009) -[2023-10-10 14:57:28,514][76543] Updated weights for policy 0, policy_version 58293 (0.0010) -[2023-10-10 14:57:28,885][76543] Updated weights for policy 0, policy_version 58303 (0.0010) -[2023-10-10 14:57:31,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 119308288. Throughput: 0: 1819.5, 1: 1828.8. Samples: 29838888. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) -[2023-10-10 14:57:31,076][75634] Avg episode reward: [(0, '37.770'), (1, '34.080')] -[2023-10-10 14:57:31,794][76542] Updated weights for policy 1, policy_version 58210 (0.0009) -[2023-10-10 14:57:32,159][76542] Updated weights for policy 1, policy_version 58220 (0.0011) -[2023-10-10 14:57:32,522][76542] Updated weights for policy 1, policy_version 58230 (0.0010) -[2023-10-10 14:57:32,691][76543] Updated weights for policy 0, policy_version 58313 (0.0008) -[2023-10-10 14:57:32,888][76542] Updated weights for policy 1, policy_version 58240 (0.0008) -[2023-10-10 14:57:33,057][76543] Updated weights for policy 0, policy_version 58323 (0.0008) -[2023-10-10 14:57:33,434][76543] Updated weights for policy 0, policy_version 58333 (0.0007) -[2023-10-10 14:57:36,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 119373824. Throughput: 0: 1820.7, 1: 1827.7. Samples: 29849284. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) -[2023-10-10 14:57:36,077][75634] Avg episode reward: [(0, '39.470'), (1, '35.130')] -[2023-10-10 14:57:36,510][76542] Updated weights for policy 1, policy_version 58250 (0.0007) -[2023-10-10 14:57:36,876][76542] Updated weights for policy 1, policy_version 58260 (0.0008) -[2023-10-10 14:57:36,984][76543] Updated weights for policy 0, policy_version 58343 (0.0007) -[2023-10-10 14:57:37,235][76542] Updated weights for policy 1, policy_version 58270 (0.0009) -[2023-10-10 14:57:37,355][76543] Updated weights for policy 0, policy_version 58353 (0.0007) -[2023-10-10 14:57:37,720][76543] Updated weights for policy 0, policy_version 58363 (0.0007) -[2023-10-10 14:57:41,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 119439360. Throughput: 0: 1820.7, 1: 1822.5. Samples: 29871704. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) -[2023-10-10 14:57:41,076][75634] Avg episode reward: [(0, '36.380'), (1, '40.320')] -[2023-10-10 14:57:41,131][76542] Updated weights for policy 1, policy_version 58280 (0.0007) -[2023-10-10 14:57:41,473][76543] Updated weights for policy 0, policy_version 58373 (0.0009) -[2023-10-10 14:57:41,496][76542] Updated weights for policy 1, policy_version 58290 (0.0007) -[2023-10-10 14:57:41,845][76543] Updated weights for policy 0, policy_version 58383 (0.0008) -[2023-10-10 14:57:41,869][76542] Updated weights for policy 1, policy_version 58300 (0.0008) -[2023-10-10 14:57:42,219][76543] Updated weights for policy 0, policy_version 58393 (0.0007) -[2023-10-10 14:57:45,605][76542] Updated weights for policy 1, policy_version 58310 (0.0008) -[2023-10-10 14:57:45,847][76543] Updated weights for policy 0, policy_version 58403 (0.0008) -[2023-10-10 14:57:45,968][76542] Updated weights for policy 1, policy_version 58320 (0.0007) -[2023-10-10 14:57:46,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 119504896. Throughput: 0: 1822.9, 1: 1817.7. Samples: 29893774. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) -[2023-10-10 14:57:46,076][75634] Avg episode reward: [(0, '38.720'), (1, '39.670')] -[2023-10-10 14:57:46,216][76543] Updated weights for policy 0, policy_version 58413 (0.0007) -[2023-10-10 14:57:46,335][76542] Updated weights for policy 1, policy_version 58330 (0.0007) -[2023-10-10 14:57:46,588][76543] Updated weights for policy 0, policy_version 58423 (0.0009) -[2023-10-10 14:57:50,152][76542] Updated weights for policy 1, policy_version 58340 (0.0008) -[2023-10-10 14:57:50,343][76543] Updated weights for policy 0, policy_version 58433 (0.0008) -[2023-10-10 14:57:50,521][76542] Updated weights for policy 1, policy_version 58350 (0.0008) -[2023-10-10 14:57:50,723][76543] Updated weights for policy 0, policy_version 58443 (0.0009) -[2023-10-10 14:57:50,887][76542] Updated weights for policy 1, policy_version 58360 (0.0007) -[2023-10-10 14:57:51,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 119570432. Throughput: 0: 1823.1, 1: 1812.5. Samples: 29903964. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) -[2023-10-10 14:57:51,077][75634] Avg episode reward: [(0, '33.060'), (1, '39.920')] -[2023-10-10 14:57:51,098][76543] Updated weights for policy 0, policy_version 58453 (0.0008) -[2023-10-10 14:57:51,458][76543] Updated weights for policy 0, policy_version 58463 (0.0007) -[2023-10-10 14:57:54,596][76542] Updated weights for policy 1, policy_version 58370 (0.0008) -[2023-10-10 14:57:54,999][76542] Updated weights for policy 1, policy_version 58380 (0.0007) -[2023-10-10 14:57:55,239][76543] Updated weights for policy 0, policy_version 58473 (0.0007) -[2023-10-10 14:57:55,374][76542] Updated weights for policy 1, policy_version 58390 (0.0008) -[2023-10-10 14:57:55,601][76543] Updated weights for policy 0, policy_version 58483 (0.0007) -[2023-10-10 14:57:55,743][76542] Updated weights for policy 1, policy_version 58400 (0.0008) -[2023-10-10 14:57:55,993][76543] Updated weights for policy 0, policy_version 58493 (0.0010) -[2023-10-10 14:57:56,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 119668736. Throughput: 0: 1819.6, 1: 1824.9. Samples: 29926498. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) -[2023-10-10 14:57:56,077][75634] Avg episode reward: [(0, '34.190'), (1, '38.890')] -[2023-10-10 14:57:59,546][76542] Updated weights for policy 1, policy_version 58410 (0.0008) -[2023-10-10 14:57:59,676][76543] Updated weights for policy 0, policy_version 58503 (0.0009) -[2023-10-10 14:57:59,918][76542] Updated weights for policy 1, policy_version 58420 (0.0009) -[2023-10-10 14:58:00,059][76543] Updated weights for policy 0, policy_version 58513 (0.0008) -[2023-10-10 14:58:00,294][76542] Updated weights for policy 1, policy_version 58430 (0.0009) -[2023-10-10 14:58:00,421][76543] Updated weights for policy 0, policy_version 58523 (0.0007) -[2023-10-10 14:58:01,076][75634] Fps is (10 sec: 19660.9, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 119767040. Throughput: 0: 1830.2, 1: 1807.7. Samples: 29946824. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-10 14:58:01,077][75634] Avg episode reward: [(0, '34.800'), (1, '35.200')] -[2023-10-10 14:58:03,784][76542] Updated weights for policy 1, policy_version 58440 (0.0009) -[2023-10-10 14:58:04,076][76543] Updated weights for policy 0, policy_version 58533 (0.0009) -[2023-10-10 14:58:04,158][76542] Updated weights for policy 1, policy_version 58450 (0.0008) -[2023-10-10 14:58:04,437][76543] Updated weights for policy 0, policy_version 58543 (0.0009) -[2023-10-10 14:58:04,516][76542] Updated weights for policy 1, policy_version 58460 (0.0008) -[2023-10-10 14:58:04,813][76543] Updated weights for policy 0, policy_version 58553 (0.0008) -[2023-10-10 14:58:06,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 119832576. Throughput: 0: 1824.6, 1: 1810.9. Samples: 29959072. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-10 14:58:06,077][75634] Avg episode reward: [(0, '36.990'), (1, '32.030')] -[2023-10-10 14:58:08,336][76542] Updated weights for policy 1, policy_version 58470 (0.0008) -[2023-10-10 14:58:08,562][76543] Updated weights for policy 0, policy_version 58563 (0.0009) -[2023-10-10 14:58:08,698][76542] Updated weights for policy 1, policy_version 58480 (0.0008) -[2023-10-10 14:58:08,931][76543] Updated weights for policy 0, policy_version 58573 (0.0007) -[2023-10-10 14:58:09,070][76542] Updated weights for policy 1, policy_version 58490 (0.0009) -[2023-10-10 14:58:09,299][76543] Updated weights for policy 0, policy_version 58583 (0.0007) -[2023-10-10 14:58:11,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 119898112. Throughput: 0: 1823.6, 1: 1797.2. Samples: 29979342. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-10 14:58:11,077][75634] Avg episode reward: [(0, '35.540'), (1, '30.220')] -[2023-10-10 14:58:12,814][76543] Updated weights for policy 0, policy_version 58593 (0.0008) -[2023-10-10 14:58:12,832][76542] Updated weights for policy 1, policy_version 58500 (0.0008) -[2023-10-10 14:58:13,186][76543] Updated weights for policy 0, policy_version 58603 (0.0008) -[2023-10-10 14:58:13,194][76542] Updated weights for policy 1, policy_version 58510 (0.0009) -[2023-10-10 14:58:13,550][76542] Updated weights for policy 1, policy_version 58520 (0.0008) -[2023-10-10 14:58:13,559][76543] Updated weights for policy 0, policy_version 58613 (0.0007) -[2023-10-10 14:58:13,929][76543] Updated weights for policy 0, policy_version 58623 (0.0007) -[2023-10-10 14:58:16,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 119963648. Throughput: 0: 1825.9, 1: 1791.9. Samples: 30001688. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-10 14:58:16,077][75634] Avg episode reward: [(0, '41.400'), (1, '33.180')] -[2023-10-10 14:58:17,436][76542] Updated weights for policy 1, policy_version 58530 (0.0007) -[2023-10-10 14:58:17,488][76543] Updated weights for policy 0, policy_version 58633 (0.0007) -[2023-10-10 14:58:17,804][76542] Updated weights for policy 1, policy_version 58540 (0.0007) -[2023-10-10 14:58:17,858][76543] Updated weights for policy 0, policy_version 58643 (0.0007) -[2023-10-10 14:58:18,165][76542] Updated weights for policy 1, policy_version 58550 (0.0007) -[2023-10-10 14:58:18,224][76543] Updated weights for policy 0, policy_version 58653 (0.0008) -[2023-10-10 14:58:18,523][76542] Updated weights for policy 1, policy_version 58560 (0.0008) -[2023-10-10 14:58:21,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 120029184. Throughput: 0: 1823.8, 1: 1792.2. Samples: 30012002. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-10 14:58:21,077][75634] Avg episode reward: [(0, '36.460'), (1, '34.270')] -[2023-10-10 14:58:22,116][76543] Updated weights for policy 0, policy_version 58663 (0.0007) -[2023-10-10 14:58:22,204][76542] Updated weights for policy 1, policy_version 58570 (0.0007) -[2023-10-10 14:58:22,479][76543] Updated weights for policy 0, policy_version 58673 (0.0008) -[2023-10-10 14:58:22,568][76542] Updated weights for policy 1, policy_version 58580 (0.0008) -[2023-10-10 14:58:22,851][76543] Updated weights for policy 0, policy_version 58683 (0.0007) -[2023-10-10 14:58:22,942][76542] Updated weights for policy 1, policy_version 58590 (0.0008) -[2023-10-10 14:58:26,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 120094720. Throughput: 0: 1820.7, 1: 1791.5. Samples: 30034252. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-10 14:58:26,077][75634] Avg episode reward: [(0, '34.950'), (1, '33.940')] -[2023-10-10 14:58:26,448][76543] Updated weights for policy 0, policy_version 58693 (0.0008) -[2023-10-10 14:58:26,733][76542] Updated weights for policy 1, policy_version 58600 (0.0008) -[2023-10-10 14:58:26,822][76543] Updated weights for policy 0, policy_version 58703 (0.0008) -[2023-10-10 14:58:27,099][76542] Updated weights for policy 1, policy_version 58610 (0.0008) -[2023-10-10 14:58:27,190][76543] Updated weights for policy 0, policy_version 58713 (0.0007) -[2023-10-10 14:58:27,462][76542] Updated weights for policy 1, policy_version 58620 (0.0008) -[2023-10-10 14:58:30,887][76543] Updated weights for policy 0, policy_version 58723 (0.0007) -[2023-10-10 14:58:31,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 120160256. Throughput: 0: 1824.7, 1: 1806.3. Samples: 30057168. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-10 14:58:31,076][75634] Avg episode reward: [(0, '36.970'), (1, '35.560')] -[2023-10-10 14:58:31,077][76542] Updated weights for policy 1, policy_version 58630 (0.0008) -[2023-10-10 14:58:31,252][76543] Updated weights for policy 0, policy_version 58733 (0.0008) -[2023-10-10 14:58:31,435][76542] Updated weights for policy 1, policy_version 58640 (0.0008) -[2023-10-10 14:58:31,624][76543] Updated weights for policy 0, policy_version 58743 (0.0008) -[2023-10-10 14:58:31,803][76542] Updated weights for policy 1, policy_version 58650 (0.0008) -[2023-10-10 14:58:31,953][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000058752_60162048.pth... -[2023-10-10 14:58:31,986][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000057024_58392576.pth -[2023-10-10 14:58:32,021][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000058656_60063744.pth... -[2023-10-10 14:58:32,050][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000056928_58294272.pth -[2023-10-10 14:58:35,373][76543] Updated weights for policy 0, policy_version 58753 (0.0008) -[2023-10-10 14:58:35,431][76542] Updated weights for policy 1, policy_version 58660 (0.0008) -[2023-10-10 14:58:35,740][76543] Updated weights for policy 0, policy_version 58763 (0.0009) -[2023-10-10 14:58:35,801][76542] Updated weights for policy 1, policy_version 58670 (0.0007) -[2023-10-10 14:58:36,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 120225792. Throughput: 0: 1822.9, 1: 1802.5. Samples: 30067106. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-10 14:58:36,076][75634] Avg episode reward: [(0, '35.650'), (1, '37.380')] -[2023-10-10 14:58:36,111][76543] Updated weights for policy 0, policy_version 58773 (0.0008) -[2023-10-10 14:58:36,171][76542] Updated weights for policy 1, policy_version 58680 (0.0007) -[2023-10-10 14:58:36,482][76543] Updated weights for policy 0, policy_version 58783 (0.0008) -[2023-10-10 14:58:39,818][76542] Updated weights for policy 1, policy_version 58690 (0.0008) -[2023-10-10 14:58:40,086][76543] Updated weights for policy 0, policy_version 58793 (0.0007) -[2023-10-10 14:58:40,193][76542] Updated weights for policy 1, policy_version 58700 (0.0007) -[2023-10-10 14:58:40,456][76543] Updated weights for policy 0, policy_version 58803 (0.0007) -[2023-10-10 14:58:40,556][76542] Updated weights for policy 1, policy_version 58710 (0.0007) -[2023-10-10 14:58:40,828][76543] Updated weights for policy 0, policy_version 58813 (0.0009) -[2023-10-10 14:58:40,930][76542] Updated weights for policy 1, policy_version 58720 (0.0008) -[2023-10-10 14:58:41,076][75634] Fps is (10 sec: 19660.4, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 120356864. Throughput: 0: 1821.5, 1: 1812.9. Samples: 30090048. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:58:41,077][75634] Avg episode reward: [(0, '35.190'), (1, '37.750')] -[2023-10-10 14:58:44,511][76543] Updated weights for policy 0, policy_version 58823 (0.0009) -[2023-10-10 14:58:44,572][76542] Updated weights for policy 1, policy_version 58730 (0.0007) -[2023-10-10 14:58:44,889][76543] Updated weights for policy 0, policy_version 58833 (0.0008) -[2023-10-10 14:58:44,938][76542] Updated weights for policy 1, policy_version 58740 (0.0007) -[2023-10-10 14:58:45,257][76543] Updated weights for policy 0, policy_version 58843 (0.0010) -[2023-10-10 14:58:45,305][76542] Updated weights for policy 1, policy_version 58750 (0.0007) -[2023-10-10 14:58:46,076][75634] Fps is (10 sec: 19660.1, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 120422400. Throughput: 0: 1815.9, 1: 1815.7. Samples: 30110248. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:58:46,077][75634] Avg episode reward: [(0, '33.540'), (1, '36.130')] -[2023-10-10 14:58:49,012][76543] Updated weights for policy 0, policy_version 58853 (0.0009) -[2023-10-10 14:58:49,023][76542] Updated weights for policy 1, policy_version 58760 (0.0008) -[2023-10-10 14:58:49,384][76543] Updated weights for policy 0, policy_version 58863 (0.0009) -[2023-10-10 14:58:49,385][76542] Updated weights for policy 1, policy_version 58770 (0.0007) -[2023-10-10 14:58:49,750][76542] Updated weights for policy 1, policy_version 58780 (0.0008) -[2023-10-10 14:58:49,756][76543] Updated weights for policy 0, policy_version 58873 (0.0007) -[2023-10-10 14:58:51,076][75634] Fps is (10 sec: 13107.2, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 120487936. Throughput: 0: 1816.8, 1: 1816.4. Samples: 30122568. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:58:51,077][75634] Avg episode reward: [(0, '33.810'), (1, '37.740')] -[2023-10-10 14:58:53,395][76542] Updated weights for policy 1, policy_version 58790 (0.0009) -[2023-10-10 14:58:53,523][76543] Updated weights for policy 0, policy_version 58883 (0.0008) -[2023-10-10 14:58:53,757][76542] Updated weights for policy 1, policy_version 58800 (0.0008) -[2023-10-10 14:58:53,895][76543] Updated weights for policy 0, policy_version 58893 (0.0008) -[2023-10-10 14:58:54,118][76542] Updated weights for policy 1, policy_version 58810 (0.0007) -[2023-10-10 14:58:54,260][76543] Updated weights for policy 0, policy_version 58903 (0.0008) -[2023-10-10 14:58:56,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 120553472. Throughput: 0: 1812.8, 1: 1818.8. Samples: 30142762. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:58:56,076][75634] Avg episode reward: [(0, '34.330'), (1, '38.120')] -[2023-10-10 14:58:57,886][76542] Updated weights for policy 1, policy_version 58820 (0.0009) -[2023-10-10 14:58:58,082][76543] Updated weights for policy 0, policy_version 58913 (0.0009) -[2023-10-10 14:58:58,255][76542] Updated weights for policy 1, policy_version 58830 (0.0008) -[2023-10-10 14:58:58,443][76543] Updated weights for policy 0, policy_version 58923 (0.0007) -[2023-10-10 14:58:58,617][76542] Updated weights for policy 1, policy_version 58840 (0.0009) -[2023-10-10 14:58:58,806][76543] Updated weights for policy 0, policy_version 58933 (0.0008) -[2023-10-10 14:58:59,190][76543] Updated weights for policy 0, policy_version 58943 (0.0009) -[2023-10-10 14:59:01,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 120619008. Throughput: 0: 1806.4, 1: 1821.0. Samples: 30164924. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:59:01,077][75634] Avg episode reward: [(0, '37.770'), (1, '34.770')] -[2023-10-10 14:59:02,313][76542] Updated weights for policy 1, policy_version 58850 (0.0009) -[2023-10-10 14:59:02,690][76542] Updated weights for policy 1, policy_version 58860 (0.0008) -[2023-10-10 14:59:02,958][76543] Updated weights for policy 0, policy_version 58953 (0.0008) -[2023-10-10 14:59:03,058][76542] Updated weights for policy 1, policy_version 58870 (0.0007) -[2023-10-10 14:59:03,322][76543] Updated weights for policy 0, policy_version 58963 (0.0008) -[2023-10-10 14:59:03,427][76542] Updated weights for policy 1, policy_version 58880 (0.0008) -[2023-10-10 14:59:03,696][76543] Updated weights for policy 0, policy_version 58973 (0.0007) -[2023-10-10 14:59:06,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 120684544. Throughput: 0: 1815.5, 1: 1820.3. Samples: 30175612. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:59:06,076][75634] Avg episode reward: [(0, '37.850'), (1, '33.250')] -[2023-10-10 14:59:07,063][76542] Updated weights for policy 1, policy_version 58890 (0.0008) -[2023-10-10 14:59:07,386][76543] Updated weights for policy 0, policy_version 58983 (0.0007) -[2023-10-10 14:59:07,427][76542] Updated weights for policy 1, policy_version 58900 (0.0009) -[2023-10-10 14:59:07,758][76543] Updated weights for policy 0, policy_version 58993 (0.0009) -[2023-10-10 14:59:07,787][76542] Updated weights for policy 1, policy_version 58910 (0.0008) -[2023-10-10 14:59:08,137][76543] Updated weights for policy 0, policy_version 59003 (0.0008) -[2023-10-10 14:59:11,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 120750080. Throughput: 0: 1801.8, 1: 1824.8. Samples: 30197448. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:59:11,077][75634] Avg episode reward: [(0, '37.100'), (1, '36.840')] -[2023-10-10 14:59:11,679][76542] Updated weights for policy 1, policy_version 58920 (0.0007) -[2023-10-10 14:59:11,853][76543] Updated weights for policy 0, policy_version 59013 (0.0007) -[2023-10-10 14:59:12,054][76542] Updated weights for policy 1, policy_version 58930 (0.0008) -[2023-10-10 14:59:12,225][76543] Updated weights for policy 0, policy_version 59023 (0.0007) -[2023-10-10 14:59:12,413][76542] Updated weights for policy 1, policy_version 58940 (0.0008) -[2023-10-10 14:59:12,598][76543] Updated weights for policy 0, policy_version 59033 (0.0008) -[2023-10-10 14:59:16,027][76542] Updated weights for policy 1, policy_version 58950 (0.0007) -[2023-10-10 14:59:16,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 120815616. Throughput: 0: 1792.7, 1: 1820.9. Samples: 30219782. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 14:59:16,077][75634] Avg episode reward: [(0, '36.530'), (1, '38.860')] -[2023-10-10 14:59:16,325][76543] Updated weights for policy 0, policy_version 59043 (0.0009) -[2023-10-10 14:59:16,388][76542] Updated weights for policy 1, policy_version 58960 (0.0007) -[2023-10-10 14:59:16,700][76543] Updated weights for policy 0, policy_version 59053 (0.0010) -[2023-10-10 14:59:16,761][76542] Updated weights for policy 1, policy_version 58970 (0.0007) -[2023-10-10 14:59:17,072][76543] Updated weights for policy 0, policy_version 59063 (0.0008) -[2023-10-10 14:59:20,649][76542] Updated weights for policy 1, policy_version 58980 (0.0009) -[2023-10-10 14:59:20,743][76543] Updated weights for policy 0, policy_version 59073 (0.0008) -[2023-10-10 14:59:21,012][76542] Updated weights for policy 1, policy_version 58990 (0.0008) -[2023-10-10 14:59:21,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 120881152. Throughput: 0: 1793.9, 1: 1817.3. Samples: 30229614. Policy #0 lag: (min: 1.0, avg: 7.3, max: 32.0) -[2023-10-10 14:59:21,077][75634] Avg episode reward: [(0, '36.400'), (1, '31.970')] -[2023-10-10 14:59:21,101][76543] Updated weights for policy 0, policy_version 59083 (0.0008) -[2023-10-10 14:59:21,380][76542] Updated weights for policy 1, policy_version 59000 (0.0008) -[2023-10-10 14:59:21,470][76543] Updated weights for policy 0, policy_version 59093 (0.0008) -[2023-10-10 14:59:21,839][76543] Updated weights for policy 0, policy_version 59103 (0.0008) -[2023-10-10 14:59:25,094][76542] Updated weights for policy 1, policy_version 59010 (0.0008) -[2023-10-10 14:59:25,504][76542] Updated weights for policy 1, policy_version 59020 (0.0008) -[2023-10-10 14:59:25,650][76543] Updated weights for policy 0, policy_version 59113 (0.0007) -[2023-10-10 14:59:25,864][76542] Updated weights for policy 1, policy_version 59030 (0.0007) -[2023-10-10 14:59:26,025][76543] Updated weights for policy 0, policy_version 59123 (0.0007) -[2023-10-10 14:59:26,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 120946688. Throughput: 0: 1796.6, 1: 1806.8. Samples: 30252200. Policy #0 lag: (min: 1.0, avg: 7.3, max: 32.0) -[2023-10-10 14:59:26,077][75634] Avg episode reward: [(0, '39.650'), (1, '32.180')] -[2023-10-10 14:59:26,231][76542] Updated weights for policy 1, policy_version 59040 (0.0007) -[2023-10-10 14:59:26,392][76543] Updated weights for policy 0, policy_version 59133 (0.0008) -[2023-10-10 14:59:29,937][76542] Updated weights for policy 1, policy_version 59050 (0.0009) -[2023-10-10 14:59:30,213][76543] Updated weights for policy 0, policy_version 59143 (0.0008) -[2023-10-10 14:59:30,301][76542] Updated weights for policy 1, policy_version 59060 (0.0007) -[2023-10-10 14:59:30,594][76543] Updated weights for policy 0, policy_version 59153 (0.0009) -[2023-10-10 14:59:30,671][76542] Updated weights for policy 1, policy_version 59070 (0.0009) -[2023-10-10 14:59:30,961][76543] Updated weights for policy 0, policy_version 59163 (0.0009) -[2023-10-10 14:59:31,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 121044992. Throughput: 0: 1809.4, 1: 1801.9. Samples: 30272756. Policy #0 lag: (min: 1.0, avg: 7.3, max: 32.0) -[2023-10-10 14:59:31,077][75634] Avg episode reward: [(0, '44.130'), (1, '33.070')] -[2023-10-10 14:59:31,133][76362] Saving new best policy, reward=44.130! -[2023-10-10 14:59:34,422][76542] Updated weights for policy 1, policy_version 59080 (0.0008) -[2023-10-10 14:59:34,641][76543] Updated weights for policy 0, policy_version 59173 (0.0010) -[2023-10-10 14:59:34,797][76542] Updated weights for policy 1, policy_version 59090 (0.0008) -[2023-10-10 14:59:35,008][76543] Updated weights for policy 0, policy_version 59183 (0.0010) -[2023-10-10 14:59:35,161][76542] Updated weights for policy 1, policy_version 59100 (0.0008) -[2023-10-10 14:59:35,383][76543] Updated weights for policy 0, policy_version 59193 (0.0007) -[2023-10-10 14:59:36,076][75634] Fps is (10 sec: 19660.6, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 121143296. Throughput: 0: 1790.9, 1: 1805.1. Samples: 30284388. Policy #0 lag: (min: 1.0, avg: 7.3, max: 32.0) -[2023-10-10 14:59:36,077][75634] Avg episode reward: [(0, '38.680'), (1, '34.820')] -[2023-10-10 14:59:38,963][76542] Updated weights for policy 1, policy_version 59110 (0.0008) -[2023-10-10 14:59:39,024][76543] Updated weights for policy 0, policy_version 59203 (0.0007) -[2023-10-10 14:59:39,324][76542] Updated weights for policy 1, policy_version 59120 (0.0009) -[2023-10-10 14:59:39,399][76543] Updated weights for policy 0, policy_version 59213 (0.0010) -[2023-10-10 14:59:39,700][76542] Updated weights for policy 1, policy_version 59130 (0.0009) -[2023-10-10 14:59:39,760][76543] Updated weights for policy 0, policy_version 59223 (0.0008) -[2023-10-10 14:59:41,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14662.3). Total num frames: 121208832. Throughput: 0: 1811.5, 1: 1807.6. Samples: 30305622. Policy #0 lag: (min: 1.0, avg: 7.3, max: 32.0) -[2023-10-10 14:59:41,077][75634] Avg episode reward: [(0, '36.430'), (1, '33.490')] -[2023-10-10 14:59:43,361][76543] Updated weights for policy 0, policy_version 59233 (0.0007) -[2023-10-10 14:59:43,409][76542] Updated weights for policy 1, policy_version 59140 (0.0008) -[2023-10-10 14:59:43,736][76543] Updated weights for policy 0, policy_version 59243 (0.0007) -[2023-10-10 14:59:43,780][76542] Updated weights for policy 1, policy_version 59150 (0.0009) -[2023-10-10 14:59:44,100][76543] Updated weights for policy 0, policy_version 59253 (0.0007) -[2023-10-10 14:59:44,143][76542] Updated weights for policy 1, policy_version 59160 (0.0007) -[2023-10-10 14:59:44,486][76543] Updated weights for policy 0, policy_version 59263 (0.0010) -[2023-10-10 14:59:46,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 121274368. Throughput: 0: 1801.2, 1: 1801.2. Samples: 30327036. Policy #0 lag: (min: 1.0, avg: 7.3, max: 32.0) -[2023-10-10 14:59:46,077][75634] Avg episode reward: [(0, '34.660'), (1, '32.140')] -[2023-10-10 14:59:47,840][76542] Updated weights for policy 1, policy_version 59170 (0.0008) -[2023-10-10 14:59:48,096][76543] Updated weights for policy 0, policy_version 59273 (0.0008) -[2023-10-10 14:59:48,201][76542] Updated weights for policy 1, policy_version 59180 (0.0007) -[2023-10-10 14:59:48,461][76543] Updated weights for policy 0, policy_version 59283 (0.0007) -[2023-10-10 14:59:48,575][76542] Updated weights for policy 1, policy_version 59190 (0.0007) -[2023-10-10 14:59:48,849][76543] Updated weights for policy 0, policy_version 59293 (0.0008) -[2023-10-10 14:59:48,948][76542] Updated weights for policy 1, policy_version 59200 (0.0007) -[2023-10-10 14:59:51,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 121339904. Throughput: 0: 1805.7, 1: 1809.1. Samples: 30338276. Policy #0 lag: (min: 1.0, avg: 7.3, max: 32.0) -[2023-10-10 14:59:51,076][75634] Avg episode reward: [(0, '36.080'), (1, '33.840')] -[2023-10-10 14:59:52,567][76543] Updated weights for policy 0, policy_version 59303 (0.0008) -[2023-10-10 14:59:52,724][76542] Updated weights for policy 1, policy_version 59210 (0.0009) -[2023-10-10 14:59:52,929][76543] Updated weights for policy 0, policy_version 59313 (0.0007) -[2023-10-10 14:59:53,103][76542] Updated weights for policy 1, policy_version 59220 (0.0009) -[2023-10-10 14:59:53,311][76543] Updated weights for policy 0, policy_version 59323 (0.0008) -[2023-10-10 14:59:53,470][76542] Updated weights for policy 1, policy_version 59230 (0.0009) -[2023-10-10 14:59:56,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 121405440. Throughput: 0: 1805.5, 1: 1796.2. Samples: 30359528. Policy #0 lag: (min: 1.0, avg: 7.3, max: 32.0) -[2023-10-10 14:59:56,077][75634] Avg episode reward: [(0, '38.210'), (1, '37.960')] -[2023-10-10 14:59:56,971][76543] Updated weights for policy 0, policy_version 59333 (0.0007) -[2023-10-10 14:59:57,143][76542] Updated weights for policy 1, policy_version 59240 (0.0009) -[2023-10-10 14:59:57,337][76543] Updated weights for policy 0, policy_version 59343 (0.0009) -[2023-10-10 14:59:57,502][76542] Updated weights for policy 1, policy_version 59250 (0.0008) -[2023-10-10 14:59:57,710][76543] Updated weights for policy 0, policy_version 59353 (0.0007) -[2023-10-10 14:59:57,868][76542] Updated weights for policy 1, policy_version 59260 (0.0009) -[2023-10-10 15:00:01,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 121470976. Throughput: 0: 1809.5, 1: 1802.3. Samples: 30382310. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 15:00:01,076][75634] Avg episode reward: [(0, '37.300'), (1, '39.090')] -[2023-10-10 15:00:01,418][76543] Updated weights for policy 0, policy_version 59363 (0.0007) -[2023-10-10 15:00:01,536][76542] Updated weights for policy 1, policy_version 59270 (0.0009) -[2023-10-10 15:00:01,792][76543] Updated weights for policy 0, policy_version 59373 (0.0009) -[2023-10-10 15:00:01,900][76542] Updated weights for policy 1, policy_version 59280 (0.0009) -[2023-10-10 15:00:02,164][76543] Updated weights for policy 0, policy_version 59383 (0.0008) -[2023-10-10 15:00:02,271][76542] Updated weights for policy 1, policy_version 59290 (0.0008) -[2023-10-10 15:00:05,968][76543] Updated weights for policy 0, policy_version 59393 (0.0008) -[2023-10-10 15:00:06,010][76542] Updated weights for policy 1, policy_version 59300 (0.0008) -[2023-10-10 15:00:06,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 121536512. Throughput: 0: 1806.6, 1: 1806.7. Samples: 30392214. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 15:00:06,076][75634] Avg episode reward: [(0, '36.830'), (1, '35.110')] -[2023-10-10 15:00:06,345][76543] Updated weights for policy 0, policy_version 59403 (0.0007) -[2023-10-10 15:00:06,375][76542] Updated weights for policy 1, policy_version 59310 (0.0007) -[2023-10-10 15:00:06,712][76543] Updated weights for policy 0, policy_version 59413 (0.0007) -[2023-10-10 15:00:06,741][76542] Updated weights for policy 1, policy_version 59320 (0.0008) -[2023-10-10 15:00:07,083][76543] Updated weights for policy 0, policy_version 59423 (0.0008) -[2023-10-10 15:00:10,497][76542] Updated weights for policy 1, policy_version 59330 (0.0009) -[2023-10-10 15:00:10,912][76542] Updated weights for policy 1, policy_version 59340 (0.0008) -[2023-10-10 15:00:10,946][76543] Updated weights for policy 0, policy_version 59433 (0.0008) -[2023-10-10 15:00:11,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 121602048. Throughput: 0: 1805.1, 1: 1811.6. Samples: 30414950. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 15:00:11,077][75634] Avg episode reward: [(0, '33.960'), (1, '34.890')] -[2023-10-10 15:00:11,279][76542] Updated weights for policy 1, policy_version 59350 (0.0007) -[2023-10-10 15:00:11,321][76543] Updated weights for policy 0, policy_version 59443 (0.0008) -[2023-10-10 15:00:11,638][76542] Updated weights for policy 1, policy_version 59360 (0.0008) -[2023-10-10 15:00:11,694][76543] Updated weights for policy 0, policy_version 59453 (0.0008) -[2023-10-10 15:00:15,262][76542] Updated weights for policy 1, policy_version 59370 (0.0007) -[2023-10-10 15:00:15,500][76543] Updated weights for policy 0, policy_version 59463 (0.0008) -[2023-10-10 15:00:15,626][76542] Updated weights for policy 1, policy_version 59380 (0.0008) -[2023-10-10 15:00:15,878][76543] Updated weights for policy 0, policy_version 59473 (0.0007) -[2023-10-10 15:00:15,993][76542] Updated weights for policy 1, policy_version 59390 (0.0010) -[2023-10-10 15:00:16,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 121700352. Throughput: 0: 1819.6, 1: 1821.9. Samples: 30436620. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 15:00:16,076][75634] Avg episode reward: [(0, '34.810'), (1, '32.250')] -[2023-10-10 15:00:16,257][76543] Updated weights for policy 0, policy_version 59483 (0.0007) -[2023-10-10 15:00:19,704][76542] Updated weights for policy 1, policy_version 59400 (0.0008) -[2023-10-10 15:00:19,975][76543] Updated weights for policy 0, policy_version 59493 (0.0009) -[2023-10-10 15:00:20,073][76542] Updated weights for policy 1, policy_version 59410 (0.0009) -[2023-10-10 15:00:20,337][76543] Updated weights for policy 0, policy_version 59503 (0.0008) -[2023-10-10 15:00:20,441][76542] Updated weights for policy 1, policy_version 59420 (0.0008) -[2023-10-10 15:00:20,708][76543] Updated weights for policy 0, policy_version 59513 (0.0009) -[2023-10-10 15:00:21,076][75634] Fps is (10 sec: 19660.9, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 121798656. Throughput: 0: 1813.8, 1: 1811.7. Samples: 30447534. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 15:00:21,076][75634] Avg episode reward: [(0, '35.840'), (1, '31.460')] -[2023-10-10 15:00:23,932][76542] Updated weights for policy 1, policy_version 59430 (0.0007) -[2023-10-10 15:00:24,294][76542] Updated weights for policy 1, policy_version 59440 (0.0008) -[2023-10-10 15:00:24,563][76543] Updated weights for policy 0, policy_version 59523 (0.0009) -[2023-10-10 15:00:24,657][76542] Updated weights for policy 1, policy_version 59450 (0.0011) -[2023-10-10 15:00:24,926][76543] Updated weights for policy 0, policy_version 59533 (0.0008) -[2023-10-10 15:00:25,302][76543] Updated weights for policy 0, policy_version 59543 (0.0009) -[2023-10-10 15:00:26,076][75634] Fps is (10 sec: 16383.7, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 121864192. Throughput: 0: 1812.6, 1: 1816.8. Samples: 30468942. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 15:00:26,077][75634] Avg episode reward: [(0, '36.530'), (1, '30.900')] -[2023-10-10 15:00:28,228][76542] Updated weights for policy 1, policy_version 59460 (0.0007) -[2023-10-10 15:00:28,599][76542] Updated weights for policy 1, policy_version 59470 (0.0007) -[2023-10-10 15:00:28,971][76542] Updated weights for policy 1, policy_version 59480 (0.0008) -[2023-10-10 15:00:28,976][76543] Updated weights for policy 0, policy_version 59553 (0.0009) -[2023-10-10 15:00:29,342][76543] Updated weights for policy 0, policy_version 59563 (0.0008) -[2023-10-10 15:00:29,722][76543] Updated weights for policy 0, policy_version 59573 (0.0008) -[2023-10-10 15:00:30,083][76543] Updated weights for policy 0, policy_version 59583 (0.0008) -[2023-10-10 15:00:31,076][75634] Fps is (10 sec: 13106.7, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 121929728. Throughput: 0: 1798.9, 1: 1823.5. Samples: 30490044. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 15:00:31,077][75634] Avg episode reward: [(0, '38.630'), (1, '32.080')] -[2023-10-10 15:00:31,087][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000059488_60915712.pth... -[2023-10-10 15:00:31,088][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000059584_61014016.pth... -[2023-10-10 15:00:31,117][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000057792_59179008.pth -[2023-10-10 15:00:31,121][76421] Saving a milestone ./train_atari/atari_defender_APPO/checkpoint_p1/milestones/checkpoint_000059488_60915712.pth -[2023-10-10 15:00:31,124][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000057888_59277312.pth -[2023-10-10 15:00:31,128][76362] Saving a milestone ./train_atari/atari_defender_APPO/checkpoint_p0/milestones/checkpoint_000059584_61014016.pth -[2023-10-10 15:00:32,617][76542] Updated weights for policy 1, policy_version 59490 (0.0008) -[2023-10-10 15:00:32,982][76542] Updated weights for policy 1, policy_version 59500 (0.0010) -[2023-10-10 15:00:33,344][76542] Updated weights for policy 1, policy_version 59510 (0.0010) -[2023-10-10 15:00:33,710][76542] Updated weights for policy 1, policy_version 59520 (0.0009) -[2023-10-10 15:00:33,739][76543] Updated weights for policy 0, policy_version 59593 (0.0008) -[2023-10-10 15:00:34,113][76543] Updated weights for policy 0, policy_version 59603 (0.0008) -[2023-10-10 15:00:34,487][76543] Updated weights for policy 0, policy_version 59613 (0.0011) -[2023-10-10 15:00:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 121995264. Throughput: 0: 1809.8, 1: 1821.5. Samples: 30501682. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 15:00:36,077][75634] Avg episode reward: [(0, '36.400'), (1, '37.140')] -[2023-10-10 15:00:37,436][76542] Updated weights for policy 1, policy_version 59530 (0.0008) -[2023-10-10 15:00:37,818][76542] Updated weights for policy 1, policy_version 59540 (0.0008) -[2023-10-10 15:00:38,179][76542] Updated weights for policy 1, policy_version 59550 (0.0007) -[2023-10-10 15:00:38,245][76543] Updated weights for policy 0, policy_version 59623 (0.0009) -[2023-10-10 15:00:38,605][76543] Updated weights for policy 0, policy_version 59633 (0.0008) -[2023-10-10 15:00:38,971][76543] Updated weights for policy 0, policy_version 59643 (0.0008) -[2023-10-10 15:00:41,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 122060800. Throughput: 0: 1795.0, 1: 1833.3. Samples: 30522802. Policy #0 lag: (min: 14.0, avg: 15.3, max: 39.0) -[2023-10-10 15:00:41,077][75634] Avg episode reward: [(0, '40.590'), (1, '35.470')] -[2023-10-10 15:00:41,996][76542] Updated weights for policy 1, policy_version 59560 (0.0007) -[2023-10-10 15:00:42,352][76542] Updated weights for policy 1, policy_version 59570 (0.0008) -[2023-10-10 15:00:42,557][76543] Updated weights for policy 0, policy_version 59653 (0.0009) -[2023-10-10 15:00:42,718][76542] Updated weights for policy 1, policy_version 59580 (0.0008) -[2023-10-10 15:00:42,924][76543] Updated weights for policy 0, policy_version 59663 (0.0009) -[2023-10-10 15:00:43,293][76543] Updated weights for policy 0, policy_version 59673 (0.0008) -[2023-10-10 15:00:46,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 122126336. Throughput: 0: 1796.3, 1: 1828.2. Samples: 30545412. Policy #0 lag: (min: 14.0, avg: 15.3, max: 39.0) -[2023-10-10 15:00:46,076][75634] Avg episode reward: [(0, '40.440'), (1, '34.660')] -[2023-10-10 15:00:46,333][76542] Updated weights for policy 1, policy_version 59590 (0.0009) -[2023-10-10 15:00:46,699][76542] Updated weights for policy 1, policy_version 59600 (0.0011) -[2023-10-10 15:00:46,908][76543] Updated weights for policy 0, policy_version 59683 (0.0007) -[2023-10-10 15:00:47,061][76542] Updated weights for policy 1, policy_version 59610 (0.0009) -[2023-10-10 15:00:47,276][76543] Updated weights for policy 0, policy_version 59693 (0.0007) -[2023-10-10 15:00:47,643][76543] Updated weights for policy 0, policy_version 59703 (0.0008) -[2023-10-10 15:00:50,836][76542] Updated weights for policy 1, policy_version 59620 (0.0008) -[2023-10-10 15:00:51,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 122191872. Throughput: 0: 1800.0, 1: 1823.3. Samples: 30555262. Policy #0 lag: (min: 14.0, avg: 15.3, max: 39.0) -[2023-10-10 15:00:51,077][75634] Avg episode reward: [(0, '34.590'), (1, '34.700')] -[2023-10-10 15:00:51,204][76542] Updated weights for policy 1, policy_version 59630 (0.0009) -[2023-10-10 15:00:51,472][76543] Updated weights for policy 0, policy_version 59713 (0.0009) -[2023-10-10 15:00:51,569][76542] Updated weights for policy 1, policy_version 59640 (0.0007) -[2023-10-10 15:00:51,831][76543] Updated weights for policy 0, policy_version 59723 (0.0007) -[2023-10-10 15:00:52,197][76543] Updated weights for policy 0, policy_version 59733 (0.0009) -[2023-10-10 15:00:52,572][76543] Updated weights for policy 0, policy_version 59743 (0.0007) -[2023-10-10 15:00:55,288][76542] Updated weights for policy 1, policy_version 59650 (0.0008) -[2023-10-10 15:00:55,686][76542] Updated weights for policy 1, policy_version 59660 (0.0009) -[2023-10-10 15:00:56,052][76542] Updated weights for policy 1, policy_version 59670 (0.0009) -[2023-10-10 15:00:56,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 122257408. Throughput: 0: 1806.7, 1: 1821.5. Samples: 30578220. Policy #0 lag: (min: 14.0, avg: 15.3, max: 39.0) -[2023-10-10 15:00:56,076][75634] Avg episode reward: [(0, '31.820'), (1, '33.720')] -[2023-10-10 15:00:56,160][76543] Updated weights for policy 0, policy_version 59753 (0.0007) -[2023-10-10 15:00:56,417][76542] Updated weights for policy 1, policy_version 59680 (0.0007) -[2023-10-10 15:00:56,516][76543] Updated weights for policy 0, policy_version 59763 (0.0009) -[2023-10-10 15:00:56,878][76543] Updated weights for policy 0, policy_version 59773 (0.0008) -[2023-10-10 15:01:00,110][76542] Updated weights for policy 1, policy_version 59690 (0.0010) -[2023-10-10 15:01:00,471][76542] Updated weights for policy 1, policy_version 59700 (0.0009) -[2023-10-10 15:01:00,688][76543] Updated weights for policy 0, policy_version 59783 (0.0007) -[2023-10-10 15:01:00,844][76542] Updated weights for policy 1, policy_version 59710 (0.0007) -[2023-10-10 15:01:01,060][76543] Updated weights for policy 0, policy_version 59793 (0.0008) -[2023-10-10 15:01:01,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 122355712. Throughput: 0: 1806.1, 1: 1816.1. Samples: 30599622. Policy #0 lag: (min: 14.0, avg: 15.3, max: 39.0) -[2023-10-10 15:01:01,076][75634] Avg episode reward: [(0, '29.510'), (1, '33.520')] -[2023-10-10 15:01:01,428][76543] Updated weights for policy 0, policy_version 59803 (0.0010) -[2023-10-10 15:01:04,610][76542] Updated weights for policy 1, policy_version 59720 (0.0011) -[2023-10-10 15:01:04,981][76542] Updated weights for policy 1, policy_version 59730 (0.0009) -[2023-10-10 15:01:05,007][76543] Updated weights for policy 0, policy_version 59813 (0.0008) -[2023-10-10 15:01:05,345][76542] Updated weights for policy 1, policy_version 59740 (0.0007) -[2023-10-10 15:01:05,387][76543] Updated weights for policy 0, policy_version 59823 (0.0008) -[2023-10-10 15:01:05,750][76543] Updated weights for policy 0, policy_version 59833 (0.0007) -[2023-10-10 15:01:06,076][75634] Fps is (10 sec: 19660.6, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 122454016. Throughput: 0: 1804.0, 1: 1818.8. Samples: 30610562. Policy #0 lag: (min: 14.0, avg: 15.3, max: 39.0) -[2023-10-10 15:01:06,076][75634] Avg episode reward: [(0, '31.010'), (1, '34.520')] -[2023-10-10 15:01:09,065][76542] Updated weights for policy 1, policy_version 59750 (0.0007) -[2023-10-10 15:01:09,425][76542] Updated weights for policy 1, policy_version 59760 (0.0008) -[2023-10-10 15:01:09,526][76543] Updated weights for policy 0, policy_version 59843 (0.0007) -[2023-10-10 15:01:09,798][76542] Updated weights for policy 1, policy_version 59770 (0.0009) -[2023-10-10 15:01:09,903][76543] Updated weights for policy 0, policy_version 59853 (0.0008) -[2023-10-10 15:01:10,271][76543] Updated weights for policy 0, policy_version 59863 (0.0008) -[2023-10-10 15:01:11,076][75634] Fps is (10 sec: 16384.0, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 122519552. Throughput: 0: 1811.6, 1: 1816.4. Samples: 30632198. Policy #0 lag: (min: 14.0, avg: 15.3, max: 39.0) -[2023-10-10 15:01:11,076][75634] Avg episode reward: [(0, '30.830'), (1, '35.720')] -[2023-10-10 15:01:13,584][76542] Updated weights for policy 1, policy_version 59780 (0.0008) -[2023-10-10 15:01:13,953][76542] Updated weights for policy 1, policy_version 59790 (0.0007) -[2023-10-10 15:01:14,101][76543] Updated weights for policy 0, policy_version 59873 (0.0009) -[2023-10-10 15:01:14,315][76542] Updated weights for policy 1, policy_version 59800 (0.0008) -[2023-10-10 15:01:14,473][76543] Updated weights for policy 0, policy_version 59883 (0.0009) -[2023-10-10 15:01:14,839][76543] Updated weights for policy 0, policy_version 59893 (0.0009) -[2023-10-10 15:01:15,206][76543] Updated weights for policy 0, policy_version 59903 (0.0007) -[2023-10-10 15:01:16,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 122585088. Throughput: 0: 1812.1, 1: 1808.0. Samples: 30652944. Policy #0 lag: (min: 14.0, avg: 15.3, max: 39.0) -[2023-10-10 15:01:16,077][75634] Avg episode reward: [(0, '33.040'), (1, '38.230')] -[2023-10-10 15:01:18,127][76542] Updated weights for policy 1, policy_version 59810 (0.0009) -[2023-10-10 15:01:18,498][76542] Updated weights for policy 1, policy_version 59820 (0.0010) -[2023-10-10 15:01:18,803][76543] Updated weights for policy 0, policy_version 59913 (0.0009) -[2023-10-10 15:01:18,864][76542] Updated weights for policy 1, policy_version 59830 (0.0007) -[2023-10-10 15:01:19,168][76543] Updated weights for policy 0, policy_version 59923 (0.0009) -[2023-10-10 15:01:19,222][76542] Updated weights for policy 1, policy_version 59840 (0.0009) -[2023-10-10 15:01:19,539][76543] Updated weights for policy 0, policy_version 59933 (0.0009) -[2023-10-10 15:01:21,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 122650624. Throughput: 0: 1813.3, 1: 1814.0. Samples: 30664910. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 15:01:21,076][75634] Avg episode reward: [(0, '37.140'), (1, '35.740')] -[2023-10-10 15:01:22,872][76542] Updated weights for policy 1, policy_version 59850 (0.0008) -[2023-10-10 15:01:23,226][76543] Updated weights for policy 0, policy_version 59943 (0.0008) -[2023-10-10 15:01:23,236][76542] Updated weights for policy 1, policy_version 59860 (0.0009) -[2023-10-10 15:01:23,600][76543] Updated weights for policy 0, policy_version 59953 (0.0007) -[2023-10-10 15:01:23,602][76542] Updated weights for policy 1, policy_version 59870 (0.0008) -[2023-10-10 15:01:23,970][76543] Updated weights for policy 0, policy_version 59963 (0.0008) -[2023-10-10 15:01:26,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 122716160. Throughput: 0: 1820.3, 1: 1800.7. Samples: 30685746. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 15:01:26,077][75634] Avg episode reward: [(0, '41.550'), (1, '38.370')] -[2023-10-10 15:01:27,115][76542] Updated weights for policy 1, policy_version 59880 (0.0008) -[2023-10-10 15:01:27,486][76542] Updated weights for policy 1, policy_version 59890 (0.0008) -[2023-10-10 15:01:27,638][76543] Updated weights for policy 0, policy_version 59973 (0.0009) -[2023-10-10 15:01:27,846][76542] Updated weights for policy 1, policy_version 59900 (0.0007) -[2023-10-10 15:01:28,012][76543] Updated weights for policy 0, policy_version 59983 (0.0007) -[2023-10-10 15:01:28,385][76543] Updated weights for policy 0, policy_version 59993 (0.0010) -[2023-10-10 15:01:31,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 122781696. Throughput: 0: 1821.4, 1: 1809.3. Samples: 30708794. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 15:01:31,077][75634] Avg episode reward: [(0, '42.170'), (1, '33.460')] -[2023-10-10 15:01:31,565][76542] Updated weights for policy 1, policy_version 59910 (0.0008) -[2023-10-10 15:01:31,934][76542] Updated weights for policy 1, policy_version 59920 (0.0008) -[2023-10-10 15:01:32,000][76543] Updated weights for policy 0, policy_version 60003 (0.0008) -[2023-10-10 15:01:32,312][76542] Updated weights for policy 1, policy_version 59930 (0.0009) -[2023-10-10 15:01:32,383][76543] Updated weights for policy 0, policy_version 60013 (0.0008) -[2023-10-10 15:01:32,748][76543] Updated weights for policy 0, policy_version 60023 (0.0007) -[2023-10-10 15:01:35,950][76542] Updated weights for policy 1, policy_version 59940 (0.0008) -[2023-10-10 15:01:36,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 122847232. Throughput: 0: 1819.2, 1: 1813.1. Samples: 30718714. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 15:01:36,076][75634] Avg episode reward: [(0, '33.810'), (1, '30.480')] -[2023-10-10 15:01:36,324][76542] Updated weights for policy 1, policy_version 59950 (0.0007) -[2023-10-10 15:01:36,554][76543] Updated weights for policy 0, policy_version 60033 (0.0008) -[2023-10-10 15:01:36,683][76542] Updated weights for policy 1, policy_version 59960 (0.0007) -[2023-10-10 15:01:36,928][76543] Updated weights for policy 0, policy_version 60043 (0.0008) -[2023-10-10 15:01:37,296][76543] Updated weights for policy 0, policy_version 60053 (0.0008) -[2023-10-10 15:01:37,668][76543] Updated weights for policy 0, policy_version 60063 (0.0009) -[2023-10-10 15:01:40,413][76542] Updated weights for policy 1, policy_version 59970 (0.0008) -[2023-10-10 15:01:40,782][76542] Updated weights for policy 1, policy_version 59980 (0.0009) -[2023-10-10 15:01:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 122912768. Throughput: 0: 1817.6, 1: 1815.3. Samples: 30741704. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 15:01:41,076][75634] Avg episode reward: [(0, '37.650'), (1, '32.280')] -[2023-10-10 15:01:41,154][76542] Updated weights for policy 1, policy_version 59990 (0.0008) -[2023-10-10 15:01:41,269][76543] Updated weights for policy 0, policy_version 60073 (0.0009) -[2023-10-10 15:01:41,517][76542] Updated weights for policy 1, policy_version 60000 (0.0008) -[2023-10-10 15:01:41,629][76543] Updated weights for policy 0, policy_version 60083 (0.0008) -[2023-10-10 15:01:42,008][76543] Updated weights for policy 0, policy_version 60093 (0.0008) -[2023-10-10 15:01:45,293][76542] Updated weights for policy 1, policy_version 60010 (0.0007) -[2023-10-10 15:01:45,658][76542] Updated weights for policy 1, policy_version 60020 (0.0007) -[2023-10-10 15:01:45,709][76543] Updated weights for policy 0, policy_version 60103 (0.0007) -[2023-10-10 15:01:46,028][76542] Updated weights for policy 1, policy_version 60030 (0.0007) -[2023-10-10 15:01:46,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 122978304. Throughput: 0: 1820.4, 1: 1823.2. Samples: 30763582. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 15:01:46,076][75634] Avg episode reward: [(0, '41.720'), (1, '35.140')] -[2023-10-10 15:01:46,076][76543] Updated weights for policy 0, policy_version 60113 (0.0008) -[2023-10-10 15:01:46,452][76543] Updated weights for policy 0, policy_version 60123 (0.0008) -[2023-10-10 15:01:49,521][76542] Updated weights for policy 1, policy_version 60040 (0.0008) -[2023-10-10 15:01:49,895][76542] Updated weights for policy 1, policy_version 60050 (0.0009) -[2023-10-10 15:01:50,165][76543] Updated weights for policy 0, policy_version 60133 (0.0008) -[2023-10-10 15:01:50,264][76542] Updated weights for policy 1, policy_version 60060 (0.0009) -[2023-10-10 15:01:50,533][76543] Updated weights for policy 0, policy_version 60143 (0.0010) -[2023-10-10 15:01:50,902][76543] Updated weights for policy 0, policy_version 60153 (0.0009) -[2023-10-10 15:01:51,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 123076608. Throughput: 0: 1818.9, 1: 1822.1. Samples: 30774408. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 15:01:51,077][75634] Avg episode reward: [(0, '38.580'), (1, '35.820')] -[2023-10-10 15:01:53,868][76542] Updated weights for policy 1, policy_version 60070 (0.0008) -[2023-10-10 15:01:54,240][76542] Updated weights for policy 1, policy_version 60080 (0.0010) -[2023-10-10 15:01:54,611][76542] Updated weights for policy 1, policy_version 60090 (0.0010) -[2023-10-10 15:01:54,805][76543] Updated weights for policy 0, policy_version 60163 (0.0007) -[2023-10-10 15:01:55,188][76543] Updated weights for policy 0, policy_version 60173 (0.0008) -[2023-10-10 15:01:55,553][76543] Updated weights for policy 0, policy_version 60183 (0.0009) -[2023-10-10 15:01:56,076][75634] Fps is (10 sec: 19660.4, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 123174912. Throughput: 0: 1815.8, 1: 1822.7. Samples: 30795928. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 15:01:56,077][75634] Avg episode reward: [(0, '34.360'), (1, '37.000')] -[2023-10-10 15:01:58,294][76542] Updated weights for policy 1, policy_version 60100 (0.0008) -[2023-10-10 15:01:58,674][76542] Updated weights for policy 1, policy_version 60110 (0.0009) -[2023-10-10 15:01:59,006][76543] Updated weights for policy 0, policy_version 60193 (0.0007) -[2023-10-10 15:01:59,044][76542] Updated weights for policy 1, policy_version 60120 (0.0008) -[2023-10-10 15:01:59,373][76543] Updated weights for policy 0, policy_version 60203 (0.0008) -[2023-10-10 15:01:59,748][76543] Updated weights for policy 0, policy_version 60213 (0.0010) -[2023-10-10 15:02:00,109][76543] Updated weights for policy 0, policy_version 60223 (0.0010) -[2023-10-10 15:02:01,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 123240448. Throughput: 0: 1818.3, 1: 1827.0. Samples: 30816982. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 15:02:01,077][75634] Avg episode reward: [(0, '37.540'), (1, '37.840')] -[2023-10-10 15:02:02,839][76542] Updated weights for policy 1, policy_version 60130 (0.0009) -[2023-10-10 15:02:03,206][76542] Updated weights for policy 1, policy_version 60140 (0.0009) -[2023-10-10 15:02:03,580][76542] Updated weights for policy 1, policy_version 60150 (0.0009) -[2023-10-10 15:02:03,942][76543] Updated weights for policy 0, policy_version 60233 (0.0008) -[2023-10-10 15:02:03,943][76542] Updated weights for policy 1, policy_version 60160 (0.0009) -[2023-10-10 15:02:04,315][76543] Updated weights for policy 0, policy_version 60243 (0.0008) -[2023-10-10 15:02:04,683][76543] Updated weights for policy 0, policy_version 60253 (0.0010) -[2023-10-10 15:02:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 123305984. Throughput: 0: 1817.9, 1: 1822.1. Samples: 30828710. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 15:02:06,077][75634] Avg episode reward: [(0, '40.170'), (1, '35.150')] -[2023-10-10 15:02:07,703][76542] Updated weights for policy 1, policy_version 60170 (0.0010) -[2023-10-10 15:02:08,079][76542] Updated weights for policy 1, policy_version 60180 (0.0010) -[2023-10-10 15:02:08,304][76543] Updated weights for policy 0, policy_version 60263 (0.0009) -[2023-10-10 15:02:08,445][76542] Updated weights for policy 1, policy_version 60190 (0.0007) -[2023-10-10 15:02:08,669][76543] Updated weights for policy 0, policy_version 60273 (0.0009) -[2023-10-10 15:02:09,041][76543] Updated weights for policy 0, policy_version 60283 (0.0008) -[2023-10-10 15:02:11,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 123371520. Throughput: 0: 1814.6, 1: 1824.6. Samples: 30849512. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 15:02:11,077][75634] Avg episode reward: [(0, '40.760'), (1, '33.720')] -[2023-10-10 15:02:12,243][76542] Updated weights for policy 1, policy_version 60200 (0.0011) -[2023-10-10 15:02:12,598][76542] Updated weights for policy 1, policy_version 60210 (0.0010) -[2023-10-10 15:02:12,726][76543] Updated weights for policy 0, policy_version 60293 (0.0008) -[2023-10-10 15:02:12,970][76542] Updated weights for policy 1, policy_version 60220 (0.0009) -[2023-10-10 15:02:13,094][76543] Updated weights for policy 0, policy_version 60303 (0.0009) -[2023-10-10 15:02:13,472][76543] Updated weights for policy 0, policy_version 60313 (0.0009) -[2023-10-10 15:02:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 123437056. Throughput: 0: 1817.7, 1: 1809.9. Samples: 30872040. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 15:02:16,077][75634] Avg episode reward: [(0, '35.000'), (1, '33.520')] -[2023-10-10 15:02:16,872][76542] Updated weights for policy 1, policy_version 60230 (0.0007) -[2023-10-10 15:02:17,083][76543] Updated weights for policy 0, policy_version 60323 (0.0009) -[2023-10-10 15:02:17,238][76542] Updated weights for policy 1, policy_version 60240 (0.0009) -[2023-10-10 15:02:17,447][76543] Updated weights for policy 0, policy_version 60333 (0.0009) -[2023-10-10 15:02:17,602][76542] Updated weights for policy 1, policy_version 60250 (0.0007) -[2023-10-10 15:02:17,827][76543] Updated weights for policy 0, policy_version 60343 (0.0009) -[2023-10-10 15:02:21,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 123502592. Throughput: 0: 1816.4, 1: 1806.2. Samples: 30881734. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 15:02:21,077][75634] Avg episode reward: [(0, '34.450'), (1, '36.980')] -[2023-10-10 15:02:21,408][76542] Updated weights for policy 1, policy_version 60260 (0.0009) -[2023-10-10 15:02:21,541][76543] Updated weights for policy 0, policy_version 60353 (0.0008) -[2023-10-10 15:02:21,772][76542] Updated weights for policy 1, policy_version 60270 (0.0008) -[2023-10-10 15:02:21,914][76543] Updated weights for policy 0, policy_version 60363 (0.0008) -[2023-10-10 15:02:22,130][76542] Updated weights for policy 1, policy_version 60280 (0.0008) -[2023-10-10 15:02:22,278][76543] Updated weights for policy 0, policy_version 60373 (0.0008) -[2023-10-10 15:02:22,651][76543] Updated weights for policy 0, policy_version 60383 (0.0008) -[2023-10-10 15:02:25,908][76542] Updated weights for policy 1, policy_version 60290 (0.0008) -[2023-10-10 15:02:26,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 123568128. Throughput: 0: 1812.9, 1: 1804.3. Samples: 30904476. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 15:02:26,076][75634] Avg episode reward: [(0, '35.330'), (1, '33.560')] -[2023-10-10 15:02:26,313][76542] Updated weights for policy 1, policy_version 60300 (0.0007) -[2023-10-10 15:02:26,408][76543] Updated weights for policy 0, policy_version 60393 (0.0007) -[2023-10-10 15:02:26,688][76542] Updated weights for policy 1, policy_version 60310 (0.0007) -[2023-10-10 15:02:26,766][76543] Updated weights for policy 0, policy_version 60403 (0.0008) -[2023-10-10 15:02:27,052][76542] Updated weights for policy 1, policy_version 60320 (0.0009) -[2023-10-10 15:02:27,131][76543] Updated weights for policy 0, policy_version 60413 (0.0009) -[2023-10-10 15:02:30,757][76543] Updated weights for policy 0, policy_version 60423 (0.0009) -[2023-10-10 15:02:30,921][76542] Updated weights for policy 1, policy_version 60330 (0.0010) -[2023-10-10 15:02:31,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 123633664. Throughput: 0: 1814.7, 1: 1813.0. Samples: 30926830. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 15:02:31,076][75634] Avg episode reward: [(0, '30.730'), (1, '35.420')] -[2023-10-10 15:02:31,129][76543] Updated weights for policy 0, policy_version 60433 (0.0008) -[2023-10-10 15:02:31,287][76542] Updated weights for policy 1, policy_version 60340 (0.0008) -[2023-10-10 15:02:31,500][76543] Updated weights for policy 0, policy_version 60443 (0.0009) -[2023-10-10 15:02:31,646][76542] Updated weights for policy 1, policy_version 60350 (0.0008) -[2023-10-10 15:02:31,675][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000060448_61898752.pth... -[2023-10-10 15:02:31,709][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000058752_60162048.pth -[2023-10-10 15:02:31,718][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000060352_61800448.pth... -[2023-10-10 15:02:31,755][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000058656_60063744.pth -[2023-10-10 15:02:35,114][76543] Updated weights for policy 0, policy_version 60453 (0.0008) -[2023-10-10 15:02:35,307][76542] Updated weights for policy 1, policy_version 60360 (0.0008) -[2023-10-10 15:02:35,484][76543] Updated weights for policy 0, policy_version 60463 (0.0009) -[2023-10-10 15:02:35,675][76542] Updated weights for policy 1, policy_version 60370 (0.0007) -[2023-10-10 15:02:35,861][76543] Updated weights for policy 0, policy_version 60473 (0.0008) -[2023-10-10 15:02:36,047][76542] Updated weights for policy 1, policy_version 60380 (0.0007) -[2023-10-10 15:02:36,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 123699200. Throughput: 0: 1816.8, 1: 1792.1. Samples: 30936808. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 15:02:36,077][75634] Avg episode reward: [(0, '30.940'), (1, '36.530')] -[2023-10-10 15:02:39,652][76543] Updated weights for policy 0, policy_version 60483 (0.0008) -[2023-10-10 15:02:39,652][76542] Updated weights for policy 1, policy_version 60390 (0.0007) -[2023-10-10 15:02:40,009][76542] Updated weights for policy 1, policy_version 60400 (0.0007) -[2023-10-10 15:02:40,024][76543] Updated weights for policy 0, policy_version 60493 (0.0008) -[2023-10-10 15:02:40,376][76542] Updated weights for policy 1, policy_version 60410 (0.0007) -[2023-10-10 15:02:40,387][76543] Updated weights for policy 0, policy_version 60503 (0.0007) -[2023-10-10 15:02:41,076][75634] Fps is (10 sec: 19660.5, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 123830272. Throughput: 0: 1818.9, 1: 1807.0. Samples: 30959094. Policy #0 lag: (min: 16.0, avg: 41.8, max: 48.0) -[2023-10-10 15:02:41,076][75634] Avg episode reward: [(0, '32.120'), (1, '34.050')] -[2023-10-10 15:02:44,000][76543] Updated weights for policy 0, policy_version 60513 (0.0007) -[2023-10-10 15:02:44,039][76542] Updated weights for policy 1, policy_version 60420 (0.0007) -[2023-10-10 15:02:44,367][76543] Updated weights for policy 0, policy_version 60523 (0.0008) -[2023-10-10 15:02:44,409][76542] Updated weights for policy 1, policy_version 60430 (0.0008) -[2023-10-10 15:02:44,741][76543] Updated weights for policy 0, policy_version 60533 (0.0008) -[2023-10-10 15:02:44,770][76542] Updated weights for policy 1, policy_version 60440 (0.0008) -[2023-10-10 15:02:45,114][76543] Updated weights for policy 0, policy_version 60543 (0.0009) -[2023-10-10 15:02:46,076][75634] Fps is (10 sec: 19661.1, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 123895808. Throughput: 0: 1817.8, 1: 1787.3. Samples: 30979212. Policy #0 lag: (min: 16.0, avg: 41.8, max: 48.0) -[2023-10-10 15:02:46,077][75634] Avg episode reward: [(0, '37.760'), (1, '35.050')] -[2023-10-10 15:02:48,547][76542] Updated weights for policy 1, policy_version 60450 (0.0007) -[2023-10-10 15:02:48,775][76543] Updated weights for policy 0, policy_version 60553 (0.0009) -[2023-10-10 15:02:48,912][76542] Updated weights for policy 1, policy_version 60460 (0.0009) -[2023-10-10 15:02:49,143][76543] Updated weights for policy 0, policy_version 60563 (0.0009) -[2023-10-10 15:02:49,270][76542] Updated weights for policy 1, policy_version 60470 (0.0007) -[2023-10-10 15:02:49,508][76543] Updated weights for policy 0, policy_version 60573 (0.0008) -[2023-10-10 15:02:49,636][76542] Updated weights for policy 1, policy_version 60480 (0.0008) -[2023-10-10 15:02:51,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 123961344. Throughput: 0: 1822.1, 1: 1801.3. Samples: 30991762. Policy #0 lag: (min: 16.0, avg: 41.8, max: 48.0) -[2023-10-10 15:02:51,076][75634] Avg episode reward: [(0, '37.540'), (1, '35.090')] -[2023-10-10 15:02:53,278][76543] Updated weights for policy 0, policy_version 60583 (0.0008) -[2023-10-10 15:02:53,425][76542] Updated weights for policy 1, policy_version 60490 (0.0008) -[2023-10-10 15:02:53,654][76543] Updated weights for policy 0, policy_version 60593 (0.0008) -[2023-10-10 15:02:53,785][76542] Updated weights for policy 1, policy_version 60500 (0.0009) -[2023-10-10 15:02:54,026][76543] Updated weights for policy 0, policy_version 60603 (0.0008) -[2023-10-10 15:02:54,148][76542] Updated weights for policy 1, policy_version 60510 (0.0008) -[2023-10-10 15:02:56,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 124026880. Throughput: 0: 1816.4, 1: 1787.6. Samples: 31011690. Policy #0 lag: (min: 16.0, avg: 41.8, max: 48.0) -[2023-10-10 15:02:56,077][75634] Avg episode reward: [(0, '36.760'), (1, '34.170')] -[2023-10-10 15:02:57,699][76543] Updated weights for policy 0, policy_version 60613 (0.0009) -[2023-10-10 15:02:57,951][76542] Updated weights for policy 1, policy_version 60520 (0.0008) -[2023-10-10 15:02:58,061][76543] Updated weights for policy 0, policy_version 60623 (0.0007) -[2023-10-10 15:02:58,330][76542] Updated weights for policy 1, policy_version 60530 (0.0008) -[2023-10-10 15:02:58,431][76543] Updated weights for policy 0, policy_version 60633 (0.0007) -[2023-10-10 15:02:58,704][76542] Updated weights for policy 1, policy_version 60540 (0.0008) -[2023-10-10 15:03:01,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 124092416. Throughput: 0: 1815.7, 1: 1789.1. Samples: 31034254. Policy #0 lag: (min: 16.0, avg: 41.8, max: 48.0) -[2023-10-10 15:03:01,077][75634] Avg episode reward: [(0, '41.400'), (1, '39.290')] -[2023-10-10 15:03:02,018][76543] Updated weights for policy 0, policy_version 60643 (0.0009) -[2023-10-10 15:03:02,396][76543] Updated weights for policy 0, policy_version 60653 (0.0008) -[2023-10-10 15:03:02,547][76542] Updated weights for policy 1, policy_version 60550 (0.0010) -[2023-10-10 15:03:02,767][76543] Updated weights for policy 0, policy_version 60663 (0.0007) -[2023-10-10 15:03:02,912][76542] Updated weights for policy 1, policy_version 60560 (0.0007) -[2023-10-10 15:03:03,282][76542] Updated weights for policy 1, policy_version 60570 (0.0009) -[2023-10-10 15:03:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 124157952. Throughput: 0: 1819.7, 1: 1789.9. Samples: 31044168. Policy #0 lag: (min: 16.0, avg: 41.8, max: 48.0) -[2023-10-10 15:03:06,077][75634] Avg episode reward: [(0, '41.670'), (1, '36.640')] -[2023-10-10 15:03:06,494][76543] Updated weights for policy 0, policy_version 60673 (0.0009) -[2023-10-10 15:03:06,870][76543] Updated weights for policy 0, policy_version 60683 (0.0007) -[2023-10-10 15:03:06,992][76542] Updated weights for policy 1, policy_version 60580 (0.0009) -[2023-10-10 15:03:07,237][76543] Updated weights for policy 0, policy_version 60693 (0.0008) -[2023-10-10 15:03:07,346][76542] Updated weights for policy 1, policy_version 60590 (0.0008) -[2023-10-10 15:03:07,602][76543] Updated weights for policy 0, policy_version 60703 (0.0008) -[2023-10-10 15:03:07,715][76542] Updated weights for policy 1, policy_version 60600 (0.0007) -[2023-10-10 15:03:11,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 124223488. Throughput: 0: 1818.8, 1: 1794.9. Samples: 31067092. Policy #0 lag: (min: 16.0, avg: 41.8, max: 48.0) -[2023-10-10 15:03:11,077][75634] Avg episode reward: [(0, '34.960'), (1, '36.160')] -[2023-10-10 15:03:11,463][76543] Updated weights for policy 0, policy_version 60713 (0.0007) -[2023-10-10 15:03:11,509][76542] Updated weights for policy 1, policy_version 60610 (0.0008) -[2023-10-10 15:03:11,837][76543] Updated weights for policy 0, policy_version 60723 (0.0007) -[2023-10-10 15:03:11,898][76542] Updated weights for policy 1, policy_version 60620 (0.0007) -[2023-10-10 15:03:12,200][76543] Updated weights for policy 0, policy_version 60733 (0.0007) -[2023-10-10 15:03:12,267][76542] Updated weights for policy 1, policy_version 60630 (0.0007) -[2023-10-10 15:03:12,634][76542] Updated weights for policy 1, policy_version 60640 (0.0010) -[2023-10-10 15:03:15,933][76543] Updated weights for policy 0, policy_version 60743 (0.0009) -[2023-10-10 15:03:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 124289024. Throughput: 0: 1811.9, 1: 1803.0. Samples: 31089500. Policy #0 lag: (min: 16.0, avg: 41.8, max: 48.0) -[2023-10-10 15:03:16,077][75634] Avg episode reward: [(0, '32.760'), (1, '33.370')] -[2023-10-10 15:03:16,303][76543] Updated weights for policy 0, policy_version 60753 (0.0007) -[2023-10-10 15:03:16,362][76542] Updated weights for policy 1, policy_version 60650 (0.0008) -[2023-10-10 15:03:16,666][76543] Updated weights for policy 0, policy_version 60763 (0.0008) -[2023-10-10 15:03:16,720][76542] Updated weights for policy 1, policy_version 60660 (0.0007) -[2023-10-10 15:03:17,091][76542] Updated weights for policy 1, policy_version 60670 (0.0007) -[2023-10-10 15:03:20,423][76543] Updated weights for policy 0, policy_version 60773 (0.0009) -[2023-10-10 15:03:20,575][76542] Updated weights for policy 1, policy_version 60680 (0.0007) -[2023-10-10 15:03:20,789][76543] Updated weights for policy 0, policy_version 60783 (0.0009) -[2023-10-10 15:03:20,946][76542] Updated weights for policy 1, policy_version 60690 (0.0007) -[2023-10-10 15:03:21,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 124354560. Throughput: 0: 1809.2, 1: 1801.5. Samples: 31099290. Policy #0 lag: (min: 16.0, avg: 41.8, max: 48.0) -[2023-10-10 15:03:21,076][75634] Avg episode reward: [(0, '34.370'), (1, '34.110')] -[2023-10-10 15:03:21,150][76543] Updated weights for policy 0, policy_version 60793 (0.0007) -[2023-10-10 15:03:21,319][76542] Updated weights for policy 1, policy_version 60700 (0.0007) -[2023-10-10 15:03:24,810][76543] Updated weights for policy 0, policy_version 60803 (0.0008) -[2023-10-10 15:03:25,068][76542] Updated weights for policy 1, policy_version 60710 (0.0007) -[2023-10-10 15:03:25,176][76543] Updated weights for policy 0, policy_version 60813 (0.0007) -[2023-10-10 15:03:25,449][76542] Updated weights for policy 1, policy_version 60720 (0.0008) -[2023-10-10 15:03:25,553][76543] Updated weights for policy 0, policy_version 60823 (0.0007) -[2023-10-10 15:03:25,810][76542] Updated weights for policy 1, policy_version 60730 (0.0009) -[2023-10-10 15:03:26,076][75634] Fps is (10 sec: 19661.4, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 124485632. Throughput: 0: 1814.9, 1: 1808.5. Samples: 31122146. Policy #0 lag: (min: 10.0, avg: 13.1, max: 41.0) -[2023-10-10 15:03:26,076][75634] Avg episode reward: [(0, '35.600'), (1, '33.600')] -[2023-10-10 15:03:29,252][76543] Updated weights for policy 0, policy_version 60833 (0.0007) -[2023-10-10 15:03:29,480][76542] Updated weights for policy 1, policy_version 60740 (0.0010) -[2023-10-10 15:03:29,621][76543] Updated weights for policy 0, policy_version 60843 (0.0008) -[2023-10-10 15:03:29,845][76542] Updated weights for policy 1, policy_version 60750 (0.0009) -[2023-10-10 15:03:29,983][76543] Updated weights for policy 0, policy_version 60853 (0.0010) -[2023-10-10 15:03:30,210][76542] Updated weights for policy 1, policy_version 60760 (0.0008) -[2023-10-10 15:03:30,352][76543] Updated weights for policy 0, policy_version 60863 (0.0009) -[2023-10-10 15:03:31,076][75634] Fps is (10 sec: 19660.2, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 124551168. Throughput: 0: 1821.9, 1: 1800.0. Samples: 31142202. Policy #0 lag: (min: 10.0, avg: 13.1, max: 41.0) -[2023-10-10 15:03:31,077][75634] Avg episode reward: [(0, '36.340'), (1, '31.100')] -[2023-10-10 15:03:34,027][76543] Updated weights for policy 0, policy_version 60873 (0.0009) -[2023-10-10 15:03:34,116][76542] Updated weights for policy 1, policy_version 60770 (0.0009) -[2023-10-10 15:03:34,389][76543] Updated weights for policy 0, policy_version 60883 (0.0008) -[2023-10-10 15:03:34,482][76542] Updated weights for policy 1, policy_version 60780 (0.0007) -[2023-10-10 15:03:34,759][76543] Updated weights for policy 0, policy_version 60893 (0.0008) -[2023-10-10 15:03:34,847][76542] Updated weights for policy 1, policy_version 60790 (0.0008) -[2023-10-10 15:03:35,218][76542] Updated weights for policy 1, policy_version 60800 (0.0007) -[2023-10-10 15:03:36,076][75634] Fps is (10 sec: 13106.9, 60 sec: 15291.7, 300 sec: 14440.1). Total num frames: 124616704. Throughput: 0: 1811.6, 1: 1808.5. Samples: 31154668. Policy #0 lag: (min: 10.0, avg: 13.1, max: 41.0) -[2023-10-10 15:03:36,077][75634] Avg episode reward: [(0, '37.320'), (1, '36.760')] -[2023-10-10 15:03:38,467][76543] Updated weights for policy 0, policy_version 60903 (0.0008) -[2023-10-10 15:03:38,834][76543] Updated weights for policy 0, policy_version 60913 (0.0007) -[2023-10-10 15:03:38,925][76542] Updated weights for policy 1, policy_version 60810 (0.0009) -[2023-10-10 15:03:39,208][76543] Updated weights for policy 0, policy_version 60923 (0.0008) -[2023-10-10 15:03:39,290][76542] Updated weights for policy 1, policy_version 60820 (0.0008) -[2023-10-10 15:03:39,657][76542] Updated weights for policy 1, policy_version 60830 (0.0010) -[2023-10-10 15:03:41,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 124682240. Throughput: 0: 1819.5, 1: 1805.6. Samples: 31174820. Policy #0 lag: (min: 10.0, avg: 13.1, max: 41.0) -[2023-10-10 15:03:41,076][75634] Avg episode reward: [(0, '39.260'), (1, '37.930')] -[2023-10-10 15:03:42,911][76543] Updated weights for policy 0, policy_version 60933 (0.0008) -[2023-10-10 15:03:43,275][76543] Updated weights for policy 0, policy_version 60943 (0.0008) -[2023-10-10 15:03:43,453][76542] Updated weights for policy 1, policy_version 60840 (0.0009) -[2023-10-10 15:03:43,645][76543] Updated weights for policy 0, policy_version 60953 (0.0008) -[2023-10-10 15:03:43,813][76542] Updated weights for policy 1, policy_version 60850 (0.0008) -[2023-10-10 15:03:44,186][76542] Updated weights for policy 1, policy_version 60860 (0.0010) -[2023-10-10 15:03:46,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 124747776. Throughput: 0: 1810.6, 1: 1805.3. Samples: 31196972. Policy #0 lag: (min: 10.0, avg: 13.1, max: 41.0) -[2023-10-10 15:03:46,076][75634] Avg episode reward: [(0, '40.870'), (1, '39.180')] -[2023-10-10 15:03:47,370][76543] Updated weights for policy 0, policy_version 60963 (0.0008) -[2023-10-10 15:03:47,732][76543] Updated weights for policy 0, policy_version 60973 (0.0010) -[2023-10-10 15:03:47,954][76542] Updated weights for policy 1, policy_version 60870 (0.0009) -[2023-10-10 15:03:48,107][76543] Updated weights for policy 0, policy_version 60983 (0.0009) -[2023-10-10 15:03:48,310][76542] Updated weights for policy 1, policy_version 60880 (0.0008) -[2023-10-10 15:03:48,686][76542] Updated weights for policy 1, policy_version 60890 (0.0009) -[2023-10-10 15:03:51,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 124813312. Throughput: 0: 1817.0, 1: 1813.4. Samples: 31207536. Policy #0 lag: (min: 10.0, avg: 13.1, max: 41.0) -[2023-10-10 15:03:51,076][75634] Avg episode reward: [(0, '42.640'), (1, '38.260')] -[2023-10-10 15:03:51,824][76543] Updated weights for policy 0, policy_version 60993 (0.0007) -[2023-10-10 15:03:52,198][76543] Updated weights for policy 0, policy_version 61003 (0.0007) -[2023-10-10 15:03:52,312][76542] Updated weights for policy 1, policy_version 60900 (0.0007) -[2023-10-10 15:03:52,568][76543] Updated weights for policy 0, policy_version 61013 (0.0009) -[2023-10-10 15:03:52,677][76542] Updated weights for policy 1, policy_version 60910 (0.0007) -[2023-10-10 15:03:52,939][76543] Updated weights for policy 0, policy_version 61023 (0.0009) -[2023-10-10 15:03:53,047][76542] Updated weights for policy 1, policy_version 60920 (0.0008) -[2023-10-10 15:03:56,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 124878848. Throughput: 0: 1811.2, 1: 1798.6. Samples: 31229532. Policy #0 lag: (min: 10.0, avg: 13.1, max: 41.0) -[2023-10-10 15:03:56,076][75634] Avg episode reward: [(0, '42.450'), (1, '35.450')] -[2023-10-10 15:03:56,668][76543] Updated weights for policy 0, policy_version 61033 (0.0009) -[2023-10-10 15:03:56,797][76542] Updated weights for policy 1, policy_version 60930 (0.0010) -[2023-10-10 15:03:57,035][76543] Updated weights for policy 0, policy_version 61043 (0.0008) -[2023-10-10 15:03:57,200][76542] Updated weights for policy 1, policy_version 60940 (0.0009) -[2023-10-10 15:03:57,396][76543] Updated weights for policy 0, policy_version 61053 (0.0008) -[2023-10-10 15:03:57,570][76542] Updated weights for policy 1, policy_version 60950 (0.0009) -[2023-10-10 15:03:57,941][76542] Updated weights for policy 1, policy_version 60960 (0.0009) -[2023-10-10 15:04:01,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 124944384. Throughput: 0: 1808.8, 1: 1798.6. Samples: 31251834. Policy #0 lag: (min: 10.0, avg: 13.1, max: 41.0) -[2023-10-10 15:04:01,076][75634] Avg episode reward: [(0, '38.020'), (1, '37.730')] -[2023-10-10 15:04:01,183][76543] Updated weights for policy 0, policy_version 61063 (0.0007) -[2023-10-10 15:04:01,560][76543] Updated weights for policy 0, policy_version 61073 (0.0008) -[2023-10-10 15:04:01,719][76542] Updated weights for policy 1, policy_version 60970 (0.0008) -[2023-10-10 15:04:01,933][76543] Updated weights for policy 0, policy_version 61083 (0.0008) -[2023-10-10 15:04:02,085][76542] Updated weights for policy 1, policy_version 60980 (0.0008) -[2023-10-10 15:04:02,457][76542] Updated weights for policy 1, policy_version 60990 (0.0009) -[2023-10-10 15:04:05,596][76543] Updated weights for policy 0, policy_version 61093 (0.0008) -[2023-10-10 15:04:05,968][76543] Updated weights for policy 0, policy_version 61103 (0.0009) -[2023-10-10 15:04:06,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 125009920. Throughput: 0: 1815.6, 1: 1794.1. Samples: 31261730. Policy #0 lag: (min: 19.0, avg: 20.3, max: 43.0) -[2023-10-10 15:04:06,077][75634] Avg episode reward: [(0, '35.930'), (1, '39.290')] -[2023-10-10 15:04:06,256][76542] Updated weights for policy 1, policy_version 61000 (0.0008) -[2023-10-10 15:04:06,338][76543] Updated weights for policy 0, policy_version 61113 (0.0008) -[2023-10-10 15:04:06,621][76542] Updated weights for policy 1, policy_version 61010 (0.0009) -[2023-10-10 15:04:06,991][76542] Updated weights for policy 1, policy_version 61020 (0.0008) -[2023-10-10 15:04:10,165][76543] Updated weights for policy 0, policy_version 61123 (0.0008) -[2023-10-10 15:04:10,533][76543] Updated weights for policy 0, policy_version 61133 (0.0008) -[2023-10-10 15:04:10,665][76542] Updated weights for policy 1, policy_version 61030 (0.0008) -[2023-10-10 15:04:10,909][76543] Updated weights for policy 0, policy_version 61143 (0.0008) -[2023-10-10 15:04:11,029][76542] Updated weights for policy 1, policy_version 61040 (0.0008) -[2023-10-10 15:04:11,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 125075456. Throughput: 0: 1812.8, 1: 1799.4. Samples: 31284696. Policy #0 lag: (min: 19.0, avg: 20.3, max: 43.0) -[2023-10-10 15:04:11,076][75634] Avg episode reward: [(0, '34.100'), (1, '38.740')] -[2023-10-10 15:04:11,403][76542] Updated weights for policy 1, policy_version 61050 (0.0010) -[2023-10-10 15:04:14,420][76543] Updated weights for policy 0, policy_version 61153 (0.0007) -[2023-10-10 15:04:14,793][76543] Updated weights for policy 0, policy_version 61163 (0.0011) -[2023-10-10 15:04:15,085][76542] Updated weights for policy 1, policy_version 61060 (0.0007) -[2023-10-10 15:04:15,149][76543] Updated weights for policy 0, policy_version 61173 (0.0008) -[2023-10-10 15:04:15,462][76542] Updated weights for policy 1, policy_version 61070 (0.0007) -[2023-10-10 15:04:15,519][76543] Updated weights for policy 0, policy_version 61183 (0.0007) -[2023-10-10 15:04:15,822][76542] Updated weights for policy 1, policy_version 61080 (0.0007) -[2023-10-10 15:04:16,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 125173760. Throughput: 0: 1817.8, 1: 1810.7. Samples: 31305484. Policy #0 lag: (min: 19.0, avg: 20.3, max: 43.0) -[2023-10-10 15:04:16,077][75634] Avg episode reward: [(0, '33.220'), (1, '35.900')] -[2023-10-10 15:04:19,223][76543] Updated weights for policy 0, policy_version 61193 (0.0008) -[2023-10-10 15:04:19,434][76542] Updated weights for policy 1, policy_version 61090 (0.0008) -[2023-10-10 15:04:19,595][76543] Updated weights for policy 0, policy_version 61203 (0.0009) -[2023-10-10 15:04:19,800][76542] Updated weights for policy 1, policy_version 61100 (0.0008) -[2023-10-10 15:04:19,957][76543] Updated weights for policy 0, policy_version 61213 (0.0008) -[2023-10-10 15:04:20,165][76542] Updated weights for policy 1, policy_version 61110 (0.0007) -[2023-10-10 15:04:20,536][76542] Updated weights for policy 1, policy_version 61120 (0.0007) -[2023-10-10 15:04:21,076][75634] Fps is (10 sec: 19660.5, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 125272064. Throughput: 0: 1819.0, 1: 1803.0. Samples: 31317660. Policy #0 lag: (min: 19.0, avg: 20.3, max: 43.0) -[2023-10-10 15:04:21,077][75634] Avg episode reward: [(0, '33.220'), (1, '34.540')] -[2023-10-10 15:04:23,615][76543] Updated weights for policy 0, policy_version 61223 (0.0008) -[2023-10-10 15:04:23,990][76543] Updated weights for policy 0, policy_version 61233 (0.0008) -[2023-10-10 15:04:24,243][76542] Updated weights for policy 1, policy_version 61130 (0.0008) -[2023-10-10 15:04:24,363][76543] Updated weights for policy 0, policy_version 61243 (0.0007) -[2023-10-10 15:04:24,608][76542] Updated weights for policy 1, policy_version 61140 (0.0008) -[2023-10-10 15:04:24,978][76542] Updated weights for policy 1, policy_version 61150 (0.0009) -[2023-10-10 15:04:26,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 125337600. Throughput: 0: 1825.9, 1: 1809.5. Samples: 31338414. Policy #0 lag: (min: 19.0, avg: 20.3, max: 43.0) -[2023-10-10 15:04:26,078][75634] Avg episode reward: [(0, '35.690'), (1, '37.580')] -[2023-10-10 15:04:27,874][76543] Updated weights for policy 0, policy_version 61253 (0.0008) -[2023-10-10 15:04:28,245][76543] Updated weights for policy 0, policy_version 61263 (0.0011) -[2023-10-10 15:04:28,617][76543] Updated weights for policy 0, policy_version 61273 (0.0009) -[2023-10-10 15:04:28,714][76542] Updated weights for policy 1, policy_version 61160 (0.0008) -[2023-10-10 15:04:29,080][76542] Updated weights for policy 1, policy_version 61170 (0.0008) -[2023-10-10 15:04:29,436][76542] Updated weights for policy 1, policy_version 61180 (0.0010) -[2023-10-10 15:04:31,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 125403136. Throughput: 0: 1833.4, 1: 1803.9. Samples: 31360652. Policy #0 lag: (min: 19.0, avg: 20.3, max: 43.0) -[2023-10-10 15:04:31,077][75634] Avg episode reward: [(0, '38.500'), (1, '37.880')] -[2023-10-10 15:04:31,085][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000061184_62652416.pth... -[2023-10-10 15:04:31,085][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000061280_62750720.pth... -[2023-10-10 15:04:31,115][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000059488_60915712.pth -[2023-10-10 15:04:31,126][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000059584_61014016.pth -[2023-10-10 15:04:32,138][76543] Updated weights for policy 0, policy_version 61283 (0.0008) -[2023-10-10 15:04:32,503][76543] Updated weights for policy 0, policy_version 61293 (0.0008) -[2023-10-10 15:04:32,876][76543] Updated weights for policy 0, policy_version 61303 (0.0007) -[2023-10-10 15:04:33,034][76542] Updated weights for policy 1, policy_version 61190 (0.0010) -[2023-10-10 15:04:33,398][76542] Updated weights for policy 1, policy_version 61200 (0.0010) -[2023-10-10 15:04:33,770][76542] Updated weights for policy 1, policy_version 61210 (0.0008) -[2023-10-10 15:04:36,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 125468672. Throughput: 0: 1828.9, 1: 1808.8. Samples: 31371234. Policy #0 lag: (min: 19.0, avg: 20.3, max: 43.0) -[2023-10-10 15:04:36,077][75634] Avg episode reward: [(0, '36.970'), (1, '32.520')] -[2023-10-10 15:04:36,615][76543] Updated weights for policy 0, policy_version 61313 (0.0007) -[2023-10-10 15:04:36,979][76543] Updated weights for policy 0, policy_version 61323 (0.0007) -[2023-10-10 15:04:37,348][76543] Updated weights for policy 0, policy_version 61333 (0.0007) -[2023-10-10 15:04:37,454][76542] Updated weights for policy 1, policy_version 61220 (0.0007) -[2023-10-10 15:04:37,713][76543] Updated weights for policy 0, policy_version 61343 (0.0007) -[2023-10-10 15:04:37,820][76542] Updated weights for policy 1, policy_version 61230 (0.0009) -[2023-10-10 15:04:38,176][76542] Updated weights for policy 1, policy_version 61240 (0.0009) -[2023-10-10 15:04:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 125534208. Throughput: 0: 1837.0, 1: 1812.9. Samples: 31393780. Policy #0 lag: (min: 19.0, avg: 20.3, max: 43.0) -[2023-10-10 15:04:41,077][75634] Avg episode reward: [(0, '35.970'), (1, '32.790')] -[2023-10-10 15:04:41,330][76543] Updated weights for policy 0, policy_version 61353 (0.0009) -[2023-10-10 15:04:41,701][76543] Updated weights for policy 0, policy_version 61363 (0.0010) -[2023-10-10 15:04:41,893][76542] Updated weights for policy 1, policy_version 61250 (0.0010) -[2023-10-10 15:04:42,078][76543] Updated weights for policy 0, policy_version 61373 (0.0007) -[2023-10-10 15:04:42,300][76542] Updated weights for policy 1, policy_version 61260 (0.0007) -[2023-10-10 15:04:42,660][76542] Updated weights for policy 1, policy_version 61270 (0.0009) -[2023-10-10 15:04:43,029][76542] Updated weights for policy 1, policy_version 61280 (0.0010) -[2023-10-10 15:04:45,725][76543] Updated weights for policy 0, policy_version 61383 (0.0008) -[2023-10-10 15:04:46,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 125599744. Throughput: 0: 1840.5, 1: 1816.2. Samples: 31416388. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-10 15:04:46,077][75634] Avg episode reward: [(0, '36.030'), (1, '35.660')] -[2023-10-10 15:04:46,100][76543] Updated weights for policy 0, policy_version 61393 (0.0009) -[2023-10-10 15:04:46,469][76543] Updated weights for policy 0, policy_version 61403 (0.0009) -[2023-10-10 15:04:46,736][76542] Updated weights for policy 1, policy_version 61290 (0.0007) -[2023-10-10 15:04:47,107][76542] Updated weights for policy 1, policy_version 61300 (0.0007) -[2023-10-10 15:04:47,476][76542] Updated weights for policy 1, policy_version 61310 (0.0008) -[2023-10-10 15:04:50,329][76543] Updated weights for policy 0, policy_version 61413 (0.0009) -[2023-10-10 15:04:50,706][76543] Updated weights for policy 0, policy_version 61423 (0.0008) -[2023-10-10 15:04:51,071][76543] Updated weights for policy 0, policy_version 61433 (0.0007) -[2023-10-10 15:04:51,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 125665280. Throughput: 0: 1836.5, 1: 1815.9. Samples: 31426088. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-10 15:04:51,076][75634] Avg episode reward: [(0, '34.860'), (1, '32.930')] -[2023-10-10 15:04:51,201][76542] Updated weights for policy 1, policy_version 61320 (0.0008) -[2023-10-10 15:04:51,562][76542] Updated weights for policy 1, policy_version 61330 (0.0008) -[2023-10-10 15:04:51,931][76542] Updated weights for policy 1, policy_version 61340 (0.0009) -[2023-10-10 15:04:54,806][76543] Updated weights for policy 0, policy_version 61443 (0.0008) -[2023-10-10 15:04:55,177][76543] Updated weights for policy 0, policy_version 61453 (0.0008) -[2023-10-10 15:04:55,550][76543] Updated weights for policy 0, policy_version 61463 (0.0008) -[2023-10-10 15:04:55,597][76542] Updated weights for policy 1, policy_version 61350 (0.0008) -[2023-10-10 15:04:55,966][76542] Updated weights for policy 1, policy_version 61360 (0.0009) -[2023-10-10 15:04:56,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 125763584. Throughput: 0: 1831.9, 1: 1814.4. Samples: 31448780. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-10 15:04:56,076][75634] Avg episode reward: [(0, '34.960'), (1, '35.830')] -[2023-10-10 15:04:56,330][76542] Updated weights for policy 1, policy_version 61370 (0.0010) -[2023-10-10 15:04:59,289][76543] Updated weights for policy 0, policy_version 61473 (0.0007) -[2023-10-10 15:04:59,653][76543] Updated weights for policy 0, policy_version 61483 (0.0009) -[2023-10-10 15:05:00,025][76543] Updated weights for policy 0, policy_version 61493 (0.0009) -[2023-10-10 15:05:00,208][76542] Updated weights for policy 1, policy_version 61380 (0.0009) -[2023-10-10 15:05:00,392][76543] Updated weights for policy 0, policy_version 61503 (0.0007) -[2023-10-10 15:05:00,571][76542] Updated weights for policy 1, policy_version 61390 (0.0009) -[2023-10-10 15:05:00,937][76542] Updated weights for policy 1, policy_version 61400 (0.0009) -[2023-10-10 15:05:01,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 125829120. Throughput: 0: 1825.5, 1: 1813.0. Samples: 31469218. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-10 15:05:01,076][75634] Avg episode reward: [(0, '35.210'), (1, '35.740')] -[2023-10-10 15:05:03,983][76543] Updated weights for policy 0, policy_version 61513 (0.0009) -[2023-10-10 15:05:04,365][76543] Updated weights for policy 0, policy_version 61523 (0.0011) -[2023-10-10 15:05:04,542][76542] Updated weights for policy 1, policy_version 61410 (0.0008) -[2023-10-10 15:05:04,735][76543] Updated weights for policy 0, policy_version 61533 (0.0009) -[2023-10-10 15:05:04,913][76542] Updated weights for policy 1, policy_version 61420 (0.0008) -[2023-10-10 15:05:05,283][76542] Updated weights for policy 1, policy_version 61430 (0.0008) -[2023-10-10 15:05:05,650][76542] Updated weights for policy 1, policy_version 61440 (0.0008) -[2023-10-10 15:05:06,076][75634] Fps is (10 sec: 16383.7, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 125927424. Throughput: 0: 1826.3, 1: 1810.8. Samples: 31481332. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-10 15:05:06,077][75634] Avg episode reward: [(0, '35.110'), (1, '37.970')] -[2023-10-10 15:05:08,392][76543] Updated weights for policy 0, policy_version 61543 (0.0008) -[2023-10-10 15:05:08,754][76543] Updated weights for policy 0, policy_version 61553 (0.0008) -[2023-10-10 15:05:09,119][76543] Updated weights for policy 0, policy_version 61563 (0.0007) -[2023-10-10 15:05:09,389][76542] Updated weights for policy 1, policy_version 61450 (0.0007) -[2023-10-10 15:05:09,754][76542] Updated weights for policy 1, policy_version 61460 (0.0009) -[2023-10-10 15:05:10,122][76542] Updated weights for policy 1, policy_version 61470 (0.0008) -[2023-10-10 15:05:11,076][75634] Fps is (10 sec: 16383.9, 60 sec: 15291.7, 300 sec: 14551.2). Total num frames: 125992960. Throughput: 0: 1818.3, 1: 1816.7. Samples: 31501988. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-10 15:05:11,077][75634] Avg episode reward: [(0, '35.950'), (1, '37.880')] -[2023-10-10 15:05:12,864][76543] Updated weights for policy 0, policy_version 61573 (0.0009) -[2023-10-10 15:05:13,227][76543] Updated weights for policy 0, policy_version 61583 (0.0010) -[2023-10-10 15:05:13,605][76543] Updated weights for policy 0, policy_version 61593 (0.0007) -[2023-10-10 15:05:13,718][76542] Updated weights for policy 1, policy_version 61480 (0.0008) -[2023-10-10 15:05:14,087][76542] Updated weights for policy 1, policy_version 61490 (0.0007) -[2023-10-10 15:05:14,453][76542] Updated weights for policy 1, policy_version 61500 (0.0008) -[2023-10-10 15:05:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 126058496. Throughput: 0: 1817.2, 1: 1818.9. Samples: 31524276. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-10 15:05:16,077][75634] Avg episode reward: [(0, '39.930'), (1, '36.910')] -[2023-10-10 15:05:17,304][76543] Updated weights for policy 0, policy_version 61603 (0.0007) -[2023-10-10 15:05:17,681][76543] Updated weights for policy 0, policy_version 61613 (0.0007) -[2023-10-10 15:05:18,052][76543] Updated weights for policy 0, policy_version 61623 (0.0008) -[2023-10-10 15:05:18,057][76542] Updated weights for policy 1, policy_version 61510 (0.0010) -[2023-10-10 15:05:18,421][76542] Updated weights for policy 1, policy_version 61520 (0.0009) -[2023-10-10 15:05:18,793][76542] Updated weights for policy 1, policy_version 61530 (0.0010) -[2023-10-10 15:05:21,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 126124032. Throughput: 0: 1819.2, 1: 1820.6. Samples: 31535024. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-10 15:05:21,076][75634] Avg episode reward: [(0, '41.860'), (1, '38.090')] -[2023-10-10 15:05:21,678][76543] Updated weights for policy 0, policy_version 61633 (0.0008) -[2023-10-10 15:05:22,042][76543] Updated weights for policy 0, policy_version 61643 (0.0007) -[2023-10-10 15:05:22,363][76542] Updated weights for policy 1, policy_version 61540 (0.0008) -[2023-10-10 15:05:22,420][76543] Updated weights for policy 0, policy_version 61653 (0.0007) -[2023-10-10 15:05:22,730][76542] Updated weights for policy 1, policy_version 61550 (0.0007) -[2023-10-10 15:05:22,780][76543] Updated weights for policy 0, policy_version 61663 (0.0009) -[2023-10-10 15:05:23,094][76542] Updated weights for policy 1, policy_version 61560 (0.0008) -[2023-10-10 15:05:26,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.2). Total num frames: 126189568. Throughput: 0: 1819.7, 1: 1820.1. Samples: 31557570. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-10 15:05:26,077][75634] Avg episode reward: [(0, '38.320'), (1, '27.310')] -[2023-10-10 15:05:26,345][76543] Updated weights for policy 0, policy_version 61673 (0.0007) -[2023-10-10 15:05:26,716][76543] Updated weights for policy 0, policy_version 61683 (0.0009) -[2023-10-10 15:05:26,741][76542] Updated weights for policy 1, policy_version 61570 (0.0007) -[2023-10-10 15:05:27,091][76543] Updated weights for policy 0, policy_version 61693 (0.0007) -[2023-10-10 15:05:27,144][76542] Updated weights for policy 1, policy_version 61580 (0.0009) -[2023-10-10 15:05:27,512][76542] Updated weights for policy 1, policy_version 61590 (0.0007) -[2023-10-10 15:05:27,876][76542] Updated weights for policy 1, policy_version 61600 (0.0008) -[2023-10-10 15:05:30,712][76543] Updated weights for policy 0, policy_version 61703 (0.0007) -[2023-10-10 15:05:31,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 126255104. Throughput: 0: 1820.5, 1: 1826.5. Samples: 31580502. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-10 15:05:31,076][75634] Avg episode reward: [(0, '36.990'), (1, '27.020')] -[2023-10-10 15:05:31,094][76543] Updated weights for policy 0, policy_version 61713 (0.0008) -[2023-10-10 15:05:31,463][76543] Updated weights for policy 0, policy_version 61723 (0.0010) -[2023-10-10 15:05:31,515][76542] Updated weights for policy 1, policy_version 61610 (0.0009) -[2023-10-10 15:05:31,875][76542] Updated weights for policy 1, policy_version 61620 (0.0008) -[2023-10-10 15:05:32,244][76542] Updated weights for policy 1, policy_version 61630 (0.0009) -[2023-10-10 15:05:35,116][76543] Updated weights for policy 0, policy_version 61733 (0.0008) -[2023-10-10 15:05:35,475][76543] Updated weights for policy 0, policy_version 61743 (0.0008) -[2023-10-10 15:05:35,850][76543] Updated weights for policy 0, policy_version 61753 (0.0008) -[2023-10-10 15:05:35,984][76542] Updated weights for policy 1, policy_version 61640 (0.0008) -[2023-10-10 15:05:36,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 126320640. Throughput: 0: 1818.9, 1: 1826.1. Samples: 31590114. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-10 15:05:36,076][75634] Avg episode reward: [(0, '36.900'), (1, '29.980')] -[2023-10-10 15:05:36,366][76542] Updated weights for policy 1, policy_version 61650 (0.0008) -[2023-10-10 15:05:36,737][76542] Updated weights for policy 1, policy_version 61660 (0.0010) -[2023-10-10 15:05:39,486][76543] Updated weights for policy 0, policy_version 61763 (0.0009) -[2023-10-10 15:05:39,853][76543] Updated weights for policy 0, policy_version 61773 (0.0009) -[2023-10-10 15:05:40,228][76543] Updated weights for policy 0, policy_version 61783 (0.0008) -[2023-10-10 15:05:40,321][76542] Updated weights for policy 1, policy_version 61670 (0.0008) -[2023-10-10 15:05:40,683][76542] Updated weights for policy 1, policy_version 61680 (0.0009) -[2023-10-10 15:05:41,059][76542] Updated weights for policy 1, policy_version 61690 (0.0007) -[2023-10-10 15:05:41,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 126418944. Throughput: 0: 1825.0, 1: 1829.2. Samples: 31613218. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-10 15:05:41,076][75634] Avg episode reward: [(0, '35.230'), (1, '36.190')] -[2023-10-10 15:05:43,814][76543] Updated weights for policy 0, policy_version 61793 (0.0007) -[2023-10-10 15:05:44,186][76543] Updated weights for policy 0, policy_version 61803 (0.0008) -[2023-10-10 15:05:44,559][76543] Updated weights for policy 0, policy_version 61813 (0.0011) -[2023-10-10 15:05:44,808][76542] Updated weights for policy 1, policy_version 61700 (0.0008) -[2023-10-10 15:05:44,930][76543] Updated weights for policy 0, policy_version 61823 (0.0008) -[2023-10-10 15:05:45,178][76542] Updated weights for policy 1, policy_version 61710 (0.0010) -[2023-10-10 15:05:45,535][76542] Updated weights for policy 1, policy_version 61720 (0.0008) -[2023-10-10 15:05:46,076][75634] Fps is (10 sec: 19660.8, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 126517248. Throughput: 0: 1827.7, 1: 1821.3. Samples: 31633424. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-10 15:05:46,076][75634] Avg episode reward: [(0, '35.420'), (1, '36.660')] -[2023-10-10 15:05:48,526][76543] Updated weights for policy 0, policy_version 61833 (0.0009) -[2023-10-10 15:05:48,891][76543] Updated weights for policy 0, policy_version 61843 (0.0009) -[2023-10-10 15:05:49,261][76543] Updated weights for policy 0, policy_version 61853 (0.0008) -[2023-10-10 15:05:49,344][76542] Updated weights for policy 1, policy_version 61730 (0.0008) -[2023-10-10 15:05:49,709][76542] Updated weights for policy 1, policy_version 61740 (0.0008) -[2023-10-10 15:05:50,083][76542] Updated weights for policy 1, policy_version 61750 (0.0011) -[2023-10-10 15:05:50,443][76542] Updated weights for policy 1, policy_version 61760 (0.0010) -[2023-10-10 15:05:51,076][75634] Fps is (10 sec: 16384.0, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 126582784. Throughput: 0: 1833.8, 1: 1825.4. Samples: 31645996. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-10 15:05:51,076][75634] Avg episode reward: [(0, '35.540'), (1, '34.700')] -[2023-10-10 15:05:53,069][76543] Updated weights for policy 0, policy_version 61863 (0.0011) -[2023-10-10 15:05:53,447][76543] Updated weights for policy 0, policy_version 61873 (0.0008) -[2023-10-10 15:05:53,820][76543] Updated weights for policy 0, policy_version 61883 (0.0008) -[2023-10-10 15:05:54,373][76542] Updated weights for policy 1, policy_version 61770 (0.0009) -[2023-10-10 15:05:54,738][76542] Updated weights for policy 1, policy_version 61780 (0.0009) -[2023-10-10 15:05:55,106][76542] Updated weights for policy 1, policy_version 61790 (0.0008) -[2023-10-10 15:05:56,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 126648320. Throughput: 0: 1830.7, 1: 1820.8. Samples: 31666304. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-10 15:05:56,077][75634] Avg episode reward: [(0, '36.670'), (1, '39.420')] -[2023-10-10 15:05:57,437][76543] Updated weights for policy 0, policy_version 61893 (0.0010) -[2023-10-10 15:05:57,797][76543] Updated weights for policy 0, policy_version 61903 (0.0011) -[2023-10-10 15:05:58,171][76543] Updated weights for policy 0, policy_version 61913 (0.0008) -[2023-10-10 15:05:58,734][76542] Updated weights for policy 1, policy_version 61800 (0.0009) -[2023-10-10 15:05:59,109][76542] Updated weights for policy 1, policy_version 61810 (0.0007) -[2023-10-10 15:05:59,483][76542] Updated weights for policy 1, policy_version 61820 (0.0009) -[2023-10-10 15:06:01,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 126713856. Throughput: 0: 1838.2, 1: 1820.6. Samples: 31688920. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-10 15:06:01,077][75634] Avg episode reward: [(0, '34.960'), (1, '38.450')] -[2023-10-10 15:06:01,862][76543] Updated weights for policy 0, policy_version 61923 (0.0008) -[2023-10-10 15:06:02,242][76543] Updated weights for policy 0, policy_version 61933 (0.0009) -[2023-10-10 15:06:02,615][76543] Updated weights for policy 0, policy_version 61943 (0.0008) -[2023-10-10 15:06:03,229][76542] Updated weights for policy 1, policy_version 61830 (0.0008) -[2023-10-10 15:06:03,592][76542] Updated weights for policy 1, policy_version 61840 (0.0011) -[2023-10-10 15:06:03,967][76542] Updated weights for policy 1, policy_version 61850 (0.0008) -[2023-10-10 15:06:06,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 126779392. Throughput: 0: 1831.6, 1: 1820.8. Samples: 31699378. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:06:06,076][75634] Avg episode reward: [(0, '34.650'), (1, '33.040')] -[2023-10-10 15:06:06,427][76543] Updated weights for policy 0, policy_version 61953 (0.0008) -[2023-10-10 15:06:06,787][76543] Updated weights for policy 0, policy_version 61963 (0.0007) -[2023-10-10 15:06:07,165][76543] Updated weights for policy 0, policy_version 61973 (0.0008) -[2023-10-10 15:06:07,535][76543] Updated weights for policy 0, policy_version 61983 (0.0007) -[2023-10-10 15:06:07,660][76542] Updated weights for policy 1, policy_version 61860 (0.0008) -[2023-10-10 15:06:08,030][76542] Updated weights for policy 1, policy_version 61870 (0.0009) -[2023-10-10 15:06:08,398][76542] Updated weights for policy 1, policy_version 61880 (0.0008) -[2023-10-10 15:06:11,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 126844928. Throughput: 0: 1830.4, 1: 1810.7. Samples: 31721420. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:06:11,076][75634] Avg episode reward: [(0, '37.960'), (1, '34.010')] -[2023-10-10 15:06:11,215][76543] Updated weights for policy 0, policy_version 61993 (0.0009) -[2023-10-10 15:06:11,587][76543] Updated weights for policy 0, policy_version 62003 (0.0008) -[2023-10-10 15:06:11,954][76543] Updated weights for policy 0, policy_version 62013 (0.0011) -[2023-10-10 15:06:12,304][76542] Updated weights for policy 1, policy_version 61890 (0.0008) -[2023-10-10 15:06:12,680][76542] Updated weights for policy 1, policy_version 61900 (0.0007) -[2023-10-10 15:06:13,037][76542] Updated weights for policy 1, policy_version 61910 (0.0008) -[2023-10-10 15:06:13,406][76542] Updated weights for policy 1, policy_version 61920 (0.0011) -[2023-10-10 15:06:15,573][76543] Updated weights for policy 0, policy_version 62023 (0.0008) -[2023-10-10 15:06:15,957][76543] Updated weights for policy 0, policy_version 62033 (0.0008) -[2023-10-10 15:06:16,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 126910464. Throughput: 0: 1837.7, 1: 1801.4. Samples: 31744264. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:06:16,076][75634] Avg episode reward: [(0, '41.180'), (1, '33.550')] -[2023-10-10 15:06:16,331][76543] Updated weights for policy 0, policy_version 62043 (0.0009) -[2023-10-10 15:06:17,089][76542] Updated weights for policy 1, policy_version 61930 (0.0011) -[2023-10-10 15:06:17,453][76542] Updated weights for policy 1, policy_version 61940 (0.0010) -[2023-10-10 15:06:17,821][76542] Updated weights for policy 1, policy_version 61950 (0.0011) -[2023-10-10 15:06:19,919][76543] Updated weights for policy 0, policy_version 62053 (0.0008) -[2023-10-10 15:06:20,279][76543] Updated weights for policy 0, policy_version 62063 (0.0008) -[2023-10-10 15:06:20,650][76543] Updated weights for policy 0, policy_version 62073 (0.0008) -[2023-10-10 15:06:21,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 127008768. Throughput: 0: 1841.6, 1: 1801.8. Samples: 31754068. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:06:21,076][75634] Avg episode reward: [(0, '40.380'), (1, '37.440')] -[2023-10-10 15:06:21,499][76542] Updated weights for policy 1, policy_version 61960 (0.0010) -[2023-10-10 15:06:21,873][76542] Updated weights for policy 1, policy_version 61970 (0.0012) -[2023-10-10 15:06:22,247][76542] Updated weights for policy 1, policy_version 61980 (0.0008) -[2023-10-10 15:06:24,357][76543] Updated weights for policy 0, policy_version 62083 (0.0009) -[2023-10-10 15:06:24,730][76543] Updated weights for policy 0, policy_version 62093 (0.0008) -[2023-10-10 15:06:25,103][76543] Updated weights for policy 0, policy_version 62103 (0.0009) -[2023-10-10 15:06:25,840][76542] Updated weights for policy 1, policy_version 61990 (0.0007) -[2023-10-10 15:06:26,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 127074304. Throughput: 0: 1840.2, 1: 1798.9. Samples: 31776980. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:06:26,076][75634] Avg episode reward: [(0, '39.160'), (1, '34.960')] -[2023-10-10 15:06:26,203][76542] Updated weights for policy 1, policy_version 62000 (0.0007) -[2023-10-10 15:06:26,571][76542] Updated weights for policy 1, policy_version 62010 (0.0007) -[2023-10-10 15:06:28,595][76543] Updated weights for policy 0, policy_version 62113 (0.0012) -[2023-10-10 15:06:28,972][76543] Updated weights for policy 0, policy_version 62123 (0.0009) -[2023-10-10 15:06:29,336][76543] Updated weights for policy 0, policy_version 62133 (0.0010) -[2023-10-10 15:06:29,705][76543] Updated weights for policy 0, policy_version 62143 (0.0010) -[2023-10-10 15:06:30,319][76542] Updated weights for policy 1, policy_version 62020 (0.0008) -[2023-10-10 15:06:30,683][76542] Updated weights for policy 1, policy_version 62030 (0.0009) -[2023-10-10 15:06:31,042][76542] Updated weights for policy 1, policy_version 62040 (0.0008) -[2023-10-10 15:06:31,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 127139840. Throughput: 0: 1834.1, 1: 1817.7. Samples: 31797754. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:06:31,077][75634] Avg episode reward: [(0, '39.530'), (1, '36.330')] -[2023-10-10 15:06:31,089][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000062144_63635456.pth... -[2023-10-10 15:06:31,122][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000060448_61898752.pth -[2023-10-10 15:06:31,339][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000062048_63537152.pth... -[2023-10-10 15:06:31,370][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000060352_61800448.pth -[2023-10-10 15:06:33,276][76543] Updated weights for policy 0, policy_version 62153 (0.0008) -[2023-10-10 15:06:33,648][76543] Updated weights for policy 0, policy_version 62163 (0.0008) -[2023-10-10 15:06:34,019][76543] Updated weights for policy 0, policy_version 62173 (0.0010) -[2023-10-10 15:06:34,679][76542] Updated weights for policy 1, policy_version 62050 (0.0009) -[2023-10-10 15:06:35,047][76542] Updated weights for policy 1, policy_version 62060 (0.0008) -[2023-10-10 15:06:35,419][76542] Updated weights for policy 1, policy_version 62070 (0.0009) -[2023-10-10 15:06:35,789][76542] Updated weights for policy 1, policy_version 62080 (0.0007) -[2023-10-10 15:06:36,076][75634] Fps is (10 sec: 16383.7, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 127238144. Throughput: 0: 1828.6, 1: 1813.3. Samples: 31809884. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:06:36,077][75634] Avg episode reward: [(0, '39.160'), (1, '36.840')] -[2023-10-10 15:06:37,604][76543] Updated weights for policy 0, policy_version 62183 (0.0007) -[2023-10-10 15:06:37,977][76543] Updated weights for policy 0, policy_version 62193 (0.0010) -[2023-10-10 15:06:38,349][76543] Updated weights for policy 0, policy_version 62203 (0.0010) -[2023-10-10 15:06:39,532][76542] Updated weights for policy 1, policy_version 62090 (0.0008) -[2023-10-10 15:06:39,891][76542] Updated weights for policy 1, policy_version 62100 (0.0007) -[2023-10-10 15:06:40,258][76542] Updated weights for policy 1, policy_version 62110 (0.0011) -[2023-10-10 15:06:41,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 127303680. Throughput: 0: 1838.5, 1: 1821.6. Samples: 31831010. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:06:41,076][75634] Avg episode reward: [(0, '39.810'), (1, '35.210')] -[2023-10-10 15:06:41,995][76543] Updated weights for policy 0, policy_version 62213 (0.0008) -[2023-10-10 15:06:42,370][76543] Updated weights for policy 0, policy_version 62223 (0.0009) -[2023-10-10 15:06:42,742][76543] Updated weights for policy 0, policy_version 62233 (0.0008) -[2023-10-10 15:06:43,817][76542] Updated weights for policy 1, policy_version 62120 (0.0007) -[2023-10-10 15:06:44,184][76542] Updated weights for policy 1, policy_version 62130 (0.0008) -[2023-10-10 15:06:44,550][76542] Updated weights for policy 1, policy_version 62140 (0.0008) -[2023-10-10 15:06:46,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 127369216. Throughput: 0: 1841.0, 1: 1815.8. Samples: 31853478. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-10 15:06:46,077][75634] Avg episode reward: [(0, '39.320'), (1, '30.860')] -[2023-10-10 15:06:46,283][76543] Updated weights for policy 0, policy_version 62243 (0.0008) -[2023-10-10 15:06:46,654][76543] Updated weights for policy 0, policy_version 62253 (0.0008) -[2023-10-10 15:06:47,023][76543] Updated weights for policy 0, policy_version 62263 (0.0008) -[2023-10-10 15:06:48,159][76542] Updated weights for policy 1, policy_version 62150 (0.0009) -[2023-10-10 15:06:48,537][76542] Updated weights for policy 1, policy_version 62160 (0.0008) -[2023-10-10 15:06:48,908][76542] Updated weights for policy 1, policy_version 62170 (0.0010) -[2023-10-10 15:06:50,772][76543] Updated weights for policy 0, policy_version 62273 (0.0010) -[2023-10-10 15:06:51,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 127434752. Throughput: 0: 1839.6, 1: 1817.8. Samples: 31863962. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-10 15:06:51,076][75634] Avg episode reward: [(0, '39.570'), (1, '35.010')] -[2023-10-10 15:06:51,144][76543] Updated weights for policy 0, policy_version 62283 (0.0008) -[2023-10-10 15:06:51,519][76543] Updated weights for policy 0, policy_version 62293 (0.0010) -[2023-10-10 15:06:51,893][76543] Updated weights for policy 0, policy_version 62303 (0.0010) -[2023-10-10 15:06:52,620][76542] Updated weights for policy 1, policy_version 62180 (0.0007) -[2023-10-10 15:06:53,003][76542] Updated weights for policy 1, policy_version 62190 (0.0010) -[2023-10-10 15:06:53,365][76542] Updated weights for policy 1, policy_version 62200 (0.0011) -[2023-10-10 15:06:55,517][76543] Updated weights for policy 0, policy_version 62313 (0.0009) -[2023-10-10 15:06:55,884][76543] Updated weights for policy 0, policy_version 62323 (0.0007) -[2023-10-10 15:06:56,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 127500288. Throughput: 0: 1843.8, 1: 1822.7. Samples: 31886414. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-10 15:06:56,077][75634] Avg episode reward: [(0, '35.110'), (1, '34.150')] -[2023-10-10 15:06:56,260][76543] Updated weights for policy 0, policy_version 62333 (0.0007) -[2023-10-10 15:06:56,990][76542] Updated weights for policy 1, policy_version 62210 (0.0008) -[2023-10-10 15:06:57,400][76542] Updated weights for policy 1, policy_version 62220 (0.0009) -[2023-10-10 15:06:57,775][76542] Updated weights for policy 1, policy_version 62230 (0.0008) -[2023-10-10 15:06:58,137][76542] Updated weights for policy 1, policy_version 62240 (0.0009) -[2023-10-10 15:06:59,983][76543] Updated weights for policy 0, policy_version 62343 (0.0009) -[2023-10-10 15:07:00,360][76543] Updated weights for policy 0, policy_version 62353 (0.0010) -[2023-10-10 15:07:00,726][76543] Updated weights for policy 0, policy_version 62363 (0.0009) -[2023-10-10 15:07:01,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 127598592. Throughput: 0: 1823.6, 1: 1829.6. Samples: 31908658. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-10 15:07:01,077][75634] Avg episode reward: [(0, '37.060'), (1, '36.050')] -[2023-10-10 15:07:01,830][76542] Updated weights for policy 1, policy_version 62250 (0.0008) -[2023-10-10 15:07:02,187][76542] Updated weights for policy 1, policy_version 62260 (0.0008) -[2023-10-10 15:07:02,555][76542] Updated weights for policy 1, policy_version 62270 (0.0007) -[2023-10-10 15:07:04,363][76543] Updated weights for policy 0, policy_version 62373 (0.0009) -[2023-10-10 15:07:04,756][76543] Updated weights for policy 0, policy_version 62383 (0.0010) -[2023-10-10 15:07:05,126][76543] Updated weights for policy 0, policy_version 62393 (0.0009) -[2023-10-10 15:07:06,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 127664128. Throughput: 0: 1841.2, 1: 1827.6. Samples: 31919166. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-10 15:07:06,077][75634] Avg episode reward: [(0, '37.220'), (1, '35.250')] -[2023-10-10 15:07:06,271][76542] Updated weights for policy 1, policy_version 62280 (0.0011) -[2023-10-10 15:07:06,635][76542] Updated weights for policy 1, policy_version 62290 (0.0011) -[2023-10-10 15:07:07,005][76542] Updated weights for policy 1, policy_version 62300 (0.0009) -[2023-10-10 15:07:08,712][76543] Updated weights for policy 0, policy_version 62403 (0.0008) -[2023-10-10 15:07:09,081][76543] Updated weights for policy 0, policy_version 62413 (0.0010) -[2023-10-10 15:07:09,455][76543] Updated weights for policy 0, policy_version 62423 (0.0009) -[2023-10-10 15:07:10,819][76542] Updated weights for policy 1, policy_version 62310 (0.0009) -[2023-10-10 15:07:11,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 127729664. Throughput: 0: 1818.1, 1: 1829.4. Samples: 31941120. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-10 15:07:11,076][75634] Avg episode reward: [(0, '37.650'), (1, '34.860')] -[2023-10-10 15:07:11,197][76542] Updated weights for policy 1, policy_version 62320 (0.0008) -[2023-10-10 15:07:11,570][76542] Updated weights for policy 1, policy_version 62330 (0.0008) -[2023-10-10 15:07:13,268][76543] Updated weights for policy 0, policy_version 62433 (0.0010) -[2023-10-10 15:07:13,638][76543] Updated weights for policy 0, policy_version 62443 (0.0008) -[2023-10-10 15:07:14,016][76543] Updated weights for policy 0, policy_version 62453 (0.0008) -[2023-10-10 15:07:14,380][76543] Updated weights for policy 0, policy_version 62463 (0.0007) -[2023-10-10 15:07:15,139][76542] Updated weights for policy 1, policy_version 62340 (0.0007) -[2023-10-10 15:07:15,502][76542] Updated weights for policy 1, policy_version 62350 (0.0009) -[2023-10-10 15:07:15,877][76542] Updated weights for policy 1, policy_version 62360 (0.0008) -[2023-10-10 15:07:16,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 127795200. Throughput: 0: 1832.4, 1: 1827.7. Samples: 31962454. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-10 15:07:16,076][75634] Avg episode reward: [(0, '39.620'), (1, '37.720')] -[2023-10-10 15:07:18,216][76543] Updated weights for policy 0, policy_version 62473 (0.0008) -[2023-10-10 15:07:18,592][76543] Updated weights for policy 0, policy_version 62483 (0.0007) -[2023-10-10 15:07:18,968][76543] Updated weights for policy 0, policy_version 62493 (0.0009) -[2023-10-10 15:07:19,407][76542] Updated weights for policy 1, policy_version 62370 (0.0009) -[2023-10-10 15:07:19,784][76542] Updated weights for policy 1, policy_version 62380 (0.0009) -[2023-10-10 15:07:20,143][76542] Updated weights for policy 1, policy_version 62390 (0.0009) -[2023-10-10 15:07:20,516][76542] Updated weights for policy 1, policy_version 62400 (0.0009) -[2023-10-10 15:07:21,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 127893504. Throughput: 0: 1824.8, 1: 1830.0. Samples: 31974348. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-10 15:07:21,077][75634] Avg episode reward: [(0, '38.750'), (1, '37.990')] -[2023-10-10 15:07:22,552][76543] Updated weights for policy 0, policy_version 62503 (0.0010) -[2023-10-10 15:07:22,920][76543] Updated weights for policy 0, policy_version 62513 (0.0009) -[2023-10-10 15:07:23,287][76543] Updated weights for policy 0, policy_version 62523 (0.0008) -[2023-10-10 15:07:24,077][76542] Updated weights for policy 1, policy_version 62410 (0.0009) -[2023-10-10 15:07:24,447][76542] Updated weights for policy 1, policy_version 62420 (0.0009) -[2023-10-10 15:07:24,818][76542] Updated weights for policy 1, policy_version 62430 (0.0008) -[2023-10-10 15:07:26,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 127959040. Throughput: 0: 1822.0, 1: 1817.8. Samples: 31994798. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-10 15:07:26,076][75634] Avg episode reward: [(0, '37.190'), (1, '33.690')] -[2023-10-10 15:07:26,908][76543] Updated weights for policy 0, policy_version 62533 (0.0009) -[2023-10-10 15:07:27,281][76543] Updated weights for policy 0, policy_version 62543 (0.0007) -[2023-10-10 15:07:27,656][76543] Updated weights for policy 0, policy_version 62553 (0.0009) -[2023-10-10 15:07:28,661][76542] Updated weights for policy 1, policy_version 62440 (0.0008) -[2023-10-10 15:07:29,030][76542] Updated weights for policy 1, policy_version 62450 (0.0009) -[2023-10-10 15:07:29,405][76542] Updated weights for policy 1, policy_version 62460 (0.0009) -[2023-10-10 15:07:31,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 128024576. Throughput: 0: 1815.8, 1: 1821.7. Samples: 32017164. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-10 15:07:31,077][75634] Avg episode reward: [(0, '36.040'), (1, '36.160')] -[2023-10-10 15:07:31,356][76543] Updated weights for policy 0, policy_version 62563 (0.0008) -[2023-10-10 15:07:31,717][76543] Updated weights for policy 0, policy_version 62573 (0.0009) -[2023-10-10 15:07:32,096][76543] Updated weights for policy 0, policy_version 62583 (0.0007) -[2023-10-10 15:07:33,210][76542] Updated weights for policy 1, policy_version 62470 (0.0009) -[2023-10-10 15:07:33,581][76542] Updated weights for policy 1, policy_version 62480 (0.0007) -[2023-10-10 15:07:33,947][76542] Updated weights for policy 1, policy_version 62490 (0.0009) -[2023-10-10 15:07:35,969][76543] Updated weights for policy 0, policy_version 62593 (0.0009) -[2023-10-10 15:07:36,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 128090112. Throughput: 0: 1817.1, 1: 1822.8. Samples: 32027756. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-10 15:07:36,077][75634] Avg episode reward: [(0, '38.700'), (1, '33.340')] -[2023-10-10 15:07:36,337][76543] Updated weights for policy 0, policy_version 62603 (0.0007) -[2023-10-10 15:07:36,712][76543] Updated weights for policy 0, policy_version 62613 (0.0008) -[2023-10-10 15:07:37,084][76543] Updated weights for policy 0, policy_version 62623 (0.0009) -[2023-10-10 15:07:37,538][76542] Updated weights for policy 1, policy_version 62500 (0.0007) -[2023-10-10 15:07:37,902][76542] Updated weights for policy 1, policy_version 62510 (0.0009) -[2023-10-10 15:07:38,264][76542] Updated weights for policy 1, policy_version 62520 (0.0009) -[2023-10-10 15:07:40,574][76543] Updated weights for policy 0, policy_version 62633 (0.0008) -[2023-10-10 15:07:40,953][76543] Updated weights for policy 0, policy_version 62643 (0.0007) -[2023-10-10 15:07:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 128155648. Throughput: 0: 1821.5, 1: 1825.9. Samples: 32050546. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-10 15:07:41,076][75634] Avg episode reward: [(0, '34.320'), (1, '33.780')] -[2023-10-10 15:07:41,320][76543] Updated weights for policy 0, policy_version 62653 (0.0009) -[2023-10-10 15:07:42,005][76542] Updated weights for policy 1, policy_version 62530 (0.0010) -[2023-10-10 15:07:42,415][76542] Updated weights for policy 1, policy_version 62540 (0.0011) -[2023-10-10 15:07:42,795][76542] Updated weights for policy 1, policy_version 62550 (0.0008) -[2023-10-10 15:07:43,151][76542] Updated weights for policy 1, policy_version 62560 (0.0009) -[2023-10-10 15:07:44,807][76543] Updated weights for policy 0, policy_version 62663 (0.0008) -[2023-10-10 15:07:45,184][76543] Updated weights for policy 0, policy_version 62673 (0.0009) -[2023-10-10 15:07:45,561][76543] Updated weights for policy 0, policy_version 62683 (0.0009) -[2023-10-10 15:07:46,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 128253952. Throughput: 0: 1822.3, 1: 1826.2. Samples: 32072840. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-10 15:07:46,077][75634] Avg episode reward: [(0, '34.050'), (1, '33.520')] -[2023-10-10 15:07:46,767][76542] Updated weights for policy 1, policy_version 62570 (0.0008) -[2023-10-10 15:07:47,127][76542] Updated weights for policy 1, policy_version 62580 (0.0010) -[2023-10-10 15:07:47,491][76542] Updated weights for policy 1, policy_version 62590 (0.0010) -[2023-10-10 15:07:49,468][76543] Updated weights for policy 0, policy_version 62693 (0.0009) -[2023-10-10 15:07:49,840][76543] Updated weights for policy 0, policy_version 62703 (0.0008) -[2023-10-10 15:07:50,205][76543] Updated weights for policy 0, policy_version 62713 (0.0008) -[2023-10-10 15:07:51,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 128319488. Throughput: 0: 1822.9, 1: 1827.5. Samples: 32083436. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-10 15:07:51,076][75634] Avg episode reward: [(0, '34.440'), (1, '33.910')] -[2023-10-10 15:07:51,136][76542] Updated weights for policy 1, policy_version 62600 (0.0009) -[2023-10-10 15:07:51,509][76542] Updated weights for policy 1, policy_version 62610 (0.0008) -[2023-10-10 15:07:51,884][76542] Updated weights for policy 1, policy_version 62620 (0.0011) -[2023-10-10 15:07:53,688][76543] Updated weights for policy 0, policy_version 62723 (0.0008) -[2023-10-10 15:07:54,052][76543] Updated weights for policy 0, policy_version 62733 (0.0007) -[2023-10-10 15:07:54,419][76543] Updated weights for policy 0, policy_version 62743 (0.0007) -[2023-10-10 15:07:55,546][76542] Updated weights for policy 1, policy_version 62630 (0.0009) -[2023-10-10 15:07:55,919][76542] Updated weights for policy 1, policy_version 62640 (0.0007) -[2023-10-10 15:07:56,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 128385024. Throughput: 0: 1830.4, 1: 1827.6. Samples: 32105728. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-10 15:07:56,077][75634] Avg episode reward: [(0, '36.150'), (1, '39.050')] -[2023-10-10 15:07:56,276][76542] Updated weights for policy 1, policy_version 62650 (0.0007) -[2023-10-10 15:07:58,031][76543] Updated weights for policy 0, policy_version 62753 (0.0009) -[2023-10-10 15:07:58,392][76543] Updated weights for policy 0, policy_version 62763 (0.0010) -[2023-10-10 15:07:58,763][76543] Updated weights for policy 0, policy_version 62773 (0.0008) -[2023-10-10 15:07:59,133][76543] Updated weights for policy 0, policy_version 62783 (0.0007) -[2023-10-10 15:07:59,897][76542] Updated weights for policy 1, policy_version 62660 (0.0007) -[2023-10-10 15:08:00,270][76542] Updated weights for policy 1, policy_version 62670 (0.0009) -[2023-10-10 15:08:00,647][76542] Updated weights for policy 1, policy_version 62680 (0.0008) -[2023-10-10 15:08:01,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 128483328. Throughput: 0: 1838.2, 1: 1819.3. Samples: 32127042. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-10 15:08:01,076][75634] Avg episode reward: [(0, '38.650'), (1, '36.910')] -[2023-10-10 15:08:02,890][76543] Updated weights for policy 0, policy_version 62793 (0.0009) -[2023-10-10 15:08:03,263][76543] Updated weights for policy 0, policy_version 62803 (0.0008) -[2023-10-10 15:08:03,636][76543] Updated weights for policy 0, policy_version 62813 (0.0008) -[2023-10-10 15:08:04,364][76542] Updated weights for policy 1, policy_version 62690 (0.0008) -[2023-10-10 15:08:04,724][76542] Updated weights for policy 1, policy_version 62700 (0.0007) -[2023-10-10 15:08:05,101][76542] Updated weights for policy 1, policy_version 62710 (0.0007) -[2023-10-10 15:08:05,459][76542] Updated weights for policy 1, policy_version 62720 (0.0007) -[2023-10-10 15:08:06,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 128548864. Throughput: 0: 1830.7, 1: 1824.0. Samples: 32138810. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) -[2023-10-10 15:08:06,076][75634] Avg episode reward: [(0, '37.170'), (1, '35.350')] -[2023-10-10 15:08:07,191][76543] Updated weights for policy 0, policy_version 62823 (0.0009) -[2023-10-10 15:08:07,557][76543] Updated weights for policy 0, policy_version 62833 (0.0008) -[2023-10-10 15:08:07,970][76543] Updated weights for policy 0, policy_version 62843 (0.0009) -[2023-10-10 15:08:09,112][76542] Updated weights for policy 1, policy_version 62730 (0.0009) -[2023-10-10 15:08:09,488][76542] Updated weights for policy 1, policy_version 62740 (0.0008) -[2023-10-10 15:08:09,856][76542] Updated weights for policy 1, policy_version 62750 (0.0009) -[2023-10-10 15:08:11,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 128614400. Throughput: 0: 1844.1, 1: 1826.3. Samples: 32159964. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) -[2023-10-10 15:08:11,077][75634] Avg episode reward: [(0, '35.240'), (1, '33.480')] -[2023-10-10 15:08:11,600][76543] Updated weights for policy 0, policy_version 62853 (0.0008) -[2023-10-10 15:08:11,980][76543] Updated weights for policy 0, policy_version 62863 (0.0007) -[2023-10-10 15:08:12,343][76543] Updated weights for policy 0, policy_version 62873 (0.0007) -[2023-10-10 15:08:13,347][76542] Updated weights for policy 1, policy_version 62760 (0.0008) -[2023-10-10 15:08:13,711][76542] Updated weights for policy 1, policy_version 62770 (0.0009) -[2023-10-10 15:08:14,088][76542] Updated weights for policy 1, policy_version 62780 (0.0008) -[2023-10-10 15:08:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 128679936. Throughput: 0: 1840.9, 1: 1836.9. Samples: 32182666. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) -[2023-10-10 15:08:16,076][75634] Avg episode reward: [(0, '38.370'), (1, '35.940')] -[2023-10-10 15:08:16,095][76543] Updated weights for policy 0, policy_version 62883 (0.0007) -[2023-10-10 15:08:16,459][76543] Updated weights for policy 0, policy_version 62893 (0.0009) -[2023-10-10 15:08:16,838][76543] Updated weights for policy 0, policy_version 62903 (0.0010) -[2023-10-10 15:08:17,746][76542] Updated weights for policy 1, policy_version 62790 (0.0008) -[2023-10-10 15:08:18,116][76542] Updated weights for policy 1, policy_version 62800 (0.0008) -[2023-10-10 15:08:18,490][76542] Updated weights for policy 1, policy_version 62810 (0.0009) -[2023-10-10 15:08:20,563][76543] Updated weights for policy 0, policy_version 62913 (0.0008) -[2023-10-10 15:08:20,930][76543] Updated weights for policy 0, policy_version 62923 (0.0009) -[2023-10-10 15:08:21,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 128745472. Throughput: 0: 1839.5, 1: 1824.0. Samples: 32192616. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) -[2023-10-10 15:08:21,077][75634] Avg episode reward: [(0, '36.740'), (1, '39.210')] -[2023-10-10 15:08:21,311][76543] Updated weights for policy 0, policy_version 62933 (0.0007) -[2023-10-10 15:08:21,687][76543] Updated weights for policy 0, policy_version 62943 (0.0009) -[2023-10-10 15:08:22,232][76542] Updated weights for policy 1, policy_version 62820 (0.0009) -[2023-10-10 15:08:22,611][76542] Updated weights for policy 1, policy_version 62830 (0.0008) -[2023-10-10 15:08:22,973][76542] Updated weights for policy 1, policy_version 62840 (0.0009) -[2023-10-10 15:08:25,220][76543] Updated weights for policy 0, policy_version 62953 (0.0008) -[2023-10-10 15:08:25,593][76543] Updated weights for policy 0, policy_version 62963 (0.0008) -[2023-10-10 15:08:25,961][76543] Updated weights for policy 0, policy_version 62973 (0.0010) -[2023-10-10 15:08:26,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 128843776. Throughput: 0: 1838.0, 1: 1832.5. Samples: 32215720. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) -[2023-10-10 15:08:26,076][75634] Avg episode reward: [(0, '35.420'), (1, '34.600')] -[2023-10-10 15:08:26,794][76542] Updated weights for policy 1, policy_version 62850 (0.0008) -[2023-10-10 15:08:27,164][76542] Updated weights for policy 1, policy_version 62860 (0.0010) -[2023-10-10 15:08:27,527][76542] Updated weights for policy 1, policy_version 62870 (0.0010) -[2023-10-10 15:08:27,893][76542] Updated weights for policy 1, policy_version 62880 (0.0007) -[2023-10-10 15:08:29,589][76543] Updated weights for policy 0, policy_version 62983 (0.0008) -[2023-10-10 15:08:29,963][76543] Updated weights for policy 0, policy_version 62993 (0.0009) -[2023-10-10 15:08:30,327][76543] Updated weights for policy 0, policy_version 63003 (0.0010) -[2023-10-10 15:08:31,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 128909312. Throughput: 0: 1829.2, 1: 1831.3. Samples: 32237560. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) -[2023-10-10 15:08:31,077][75634] Avg episode reward: [(0, '33.560'), (1, '39.230')] -[2023-10-10 15:08:31,084][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000062880_64389120.pth... -[2023-10-10 15:08:31,085][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000063008_64520192.pth... -[2023-10-10 15:08:31,116][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000061184_62652416.pth -[2023-10-10 15:08:31,124][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000061280_62750720.pth -[2023-10-10 15:08:31,872][76542] Updated weights for policy 1, policy_version 62890 (0.0008) -[2023-10-10 15:08:32,243][76542] Updated weights for policy 1, policy_version 62900 (0.0008) -[2023-10-10 15:08:32,615][76542] Updated weights for policy 1, policy_version 62910 (0.0008) -[2023-10-10 15:08:34,118][76543] Updated weights for policy 0, policy_version 63013 (0.0010) -[2023-10-10 15:08:34,491][76543] Updated weights for policy 0, policy_version 63023 (0.0009) -[2023-10-10 15:08:34,854][76543] Updated weights for policy 0, policy_version 63033 (0.0011) -[2023-10-10 15:08:36,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 128974848. Throughput: 0: 1834.9, 1: 1830.0. Samples: 32248358. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) -[2023-10-10 15:08:36,077][75634] Avg episode reward: [(0, '36.790'), (1, '38.100')] -[2023-10-10 15:08:36,116][76542] Updated weights for policy 1, policy_version 62920 (0.0008) -[2023-10-10 15:08:36,481][76542] Updated weights for policy 1, policy_version 62930 (0.0008) -[2023-10-10 15:08:36,843][76542] Updated weights for policy 1, policy_version 62940 (0.0009) -[2023-10-10 15:08:38,467][76543] Updated weights for policy 0, policy_version 63043 (0.0008) -[2023-10-10 15:08:38,846][76543] Updated weights for policy 0, policy_version 63053 (0.0008) -[2023-10-10 15:08:39,222][76543] Updated weights for policy 0, policy_version 63063 (0.0011) -[2023-10-10 15:08:40,564][76542] Updated weights for policy 1, policy_version 62950 (0.0009) -[2023-10-10 15:08:40,938][76542] Updated weights for policy 1, policy_version 62960 (0.0010) -[2023-10-10 15:08:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 129040384. Throughput: 0: 1828.3, 1: 1828.8. Samples: 32270296. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) -[2023-10-10 15:08:41,076][75634] Avg episode reward: [(0, '35.630'), (1, '37.730')] -[2023-10-10 15:08:41,299][76542] Updated weights for policy 1, policy_version 62970 (0.0011) -[2023-10-10 15:08:42,986][76543] Updated weights for policy 0, policy_version 63073 (0.0007) -[2023-10-10 15:08:43,402][76543] Updated weights for policy 0, policy_version 63083 (0.0010) -[2023-10-10 15:08:43,785][76543] Updated weights for policy 0, policy_version 63093 (0.0008) -[2023-10-10 15:08:44,156][76543] Updated weights for policy 0, policy_version 63103 (0.0010) -[2023-10-10 15:08:45,048][76542] Updated weights for policy 1, policy_version 62980 (0.0010) -[2023-10-10 15:08:45,412][76542] Updated weights for policy 1, policy_version 62990 (0.0010) -[2023-10-10 15:08:45,777][76542] Updated weights for policy 1, policy_version 63000 (0.0007) -[2023-10-10 15:08:46,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 129138688. Throughput: 0: 1822.9, 1: 1825.4. Samples: 32291214. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:08:46,077][75634] Avg episode reward: [(0, '38.570'), (1, '34.750')] -[2023-10-10 15:08:47,721][76543] Updated weights for policy 0, policy_version 63113 (0.0008) -[2023-10-10 15:08:48,083][76543] Updated weights for policy 0, policy_version 63123 (0.0011) -[2023-10-10 15:08:48,462][76543] Updated weights for policy 0, policy_version 63133 (0.0010) -[2023-10-10 15:08:49,516][76542] Updated weights for policy 1, policy_version 63010 (0.0007) -[2023-10-10 15:08:49,891][76542] Updated weights for policy 1, policy_version 63020 (0.0009) -[2023-10-10 15:08:50,257][76542] Updated weights for policy 1, policy_version 63030 (0.0008) -[2023-10-10 15:08:50,614][76542] Updated weights for policy 1, policy_version 63040 (0.0007) -[2023-10-10 15:08:51,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 129204224. Throughput: 0: 1819.2, 1: 1817.4. Samples: 32302454. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:08:51,077][75634] Avg episode reward: [(0, '35.550'), (1, '33.730')] -[2023-10-10 15:08:52,207][76543] Updated weights for policy 0, policy_version 63143 (0.0008) -[2023-10-10 15:08:52,572][76543] Updated weights for policy 0, policy_version 63153 (0.0008) -[2023-10-10 15:08:52,946][76543] Updated weights for policy 0, policy_version 63163 (0.0007) -[2023-10-10 15:08:54,274][76542] Updated weights for policy 1, policy_version 63050 (0.0008) -[2023-10-10 15:08:54,645][76542] Updated weights for policy 1, policy_version 63060 (0.0008) -[2023-10-10 15:08:55,020][76542] Updated weights for policy 1, policy_version 63070 (0.0008) -[2023-10-10 15:08:56,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 129269760. Throughput: 0: 1821.0, 1: 1821.8. Samples: 32323890. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:08:56,076][75634] Avg episode reward: [(0, '34.930'), (1, '30.630')] -[2023-10-10 15:08:56,582][76543] Updated weights for policy 0, policy_version 63173 (0.0007) -[2023-10-10 15:08:56,955][76543] Updated weights for policy 0, policy_version 63183 (0.0010) -[2023-10-10 15:08:57,326][76543] Updated weights for policy 0, policy_version 63193 (0.0007) -[2023-10-10 15:08:58,696][76542] Updated weights for policy 1, policy_version 63080 (0.0008) -[2023-10-10 15:08:59,069][76542] Updated weights for policy 1, policy_version 63090 (0.0009) -[2023-10-10 15:08:59,448][76542] Updated weights for policy 1, policy_version 63100 (0.0008) -[2023-10-10 15:09:01,075][76543] Updated weights for policy 0, policy_version 63203 (0.0009) -[2023-10-10 15:09:01,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14662.3). Total num frames: 129335296. Throughput: 0: 1825.4, 1: 1810.0. Samples: 32346260. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:09:01,076][75634] Avg episode reward: [(0, '39.260'), (1, '33.950')] -[2023-10-10 15:09:01,439][76543] Updated weights for policy 0, policy_version 63213 (0.0010) -[2023-10-10 15:09:01,810][76543] Updated weights for policy 0, policy_version 63223 (0.0010) -[2023-10-10 15:09:03,049][76542] Updated weights for policy 1, policy_version 63110 (0.0007) -[2023-10-10 15:09:03,413][76542] Updated weights for policy 1, policy_version 63120 (0.0007) -[2023-10-10 15:09:03,794][76542] Updated weights for policy 1, policy_version 63130 (0.0009) -[2023-10-10 15:09:05,452][76543] Updated weights for policy 0, policy_version 63233 (0.0009) -[2023-10-10 15:09:05,825][76543] Updated weights for policy 0, policy_version 63243 (0.0007) -[2023-10-10 15:09:06,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14662.3). Total num frames: 129400832. Throughput: 0: 1827.3, 1: 1820.5. Samples: 32356766. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:09:06,077][75634] Avg episode reward: [(0, '39.580'), (1, '36.070')] -[2023-10-10 15:09:06,199][76543] Updated weights for policy 0, policy_version 63253 (0.0008) -[2023-10-10 15:09:06,570][76543] Updated weights for policy 0, policy_version 63263 (0.0007) -[2023-10-10 15:09:07,478][76542] Updated weights for policy 1, policy_version 63140 (0.0008) -[2023-10-10 15:09:07,847][76542] Updated weights for policy 1, policy_version 63150 (0.0009) -[2023-10-10 15:09:08,214][76542] Updated weights for policy 1, policy_version 63160 (0.0009) -[2023-10-10 15:09:10,305][76543] Updated weights for policy 0, policy_version 63273 (0.0009) -[2023-10-10 15:09:10,673][76543] Updated weights for policy 0, policy_version 63283 (0.0009) -[2023-10-10 15:09:11,053][76543] Updated weights for policy 0, policy_version 63293 (0.0009) -[2023-10-10 15:09:11,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 129466368. Throughput: 0: 1816.5, 1: 1815.4. Samples: 32379156. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:09:11,076][75634] Avg episode reward: [(0, '37.200'), (1, '35.440')] -[2023-10-10 15:09:11,719][76542] Updated weights for policy 1, policy_version 63170 (0.0010) -[2023-10-10 15:09:12,092][76542] Updated weights for policy 1, policy_version 63180 (0.0008) -[2023-10-10 15:09:12,462][76542] Updated weights for policy 1, policy_version 63190 (0.0008) -[2023-10-10 15:09:12,828][76542] Updated weights for policy 1, policy_version 63200 (0.0008) -[2023-10-10 15:09:14,843][76543] Updated weights for policy 0, policy_version 63303 (0.0008) -[2023-10-10 15:09:15,220][76543] Updated weights for policy 0, policy_version 63313 (0.0007) -[2023-10-10 15:09:15,589][76543] Updated weights for policy 0, policy_version 63323 (0.0008) -[2023-10-10 15:09:16,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 129564672. Throughput: 0: 1817.2, 1: 1814.4. Samples: 32400980. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:09:16,076][75634] Avg episode reward: [(0, '34.050'), (1, '32.410')] -[2023-10-10 15:09:16,705][76542] Updated weights for policy 1, policy_version 63210 (0.0009) -[2023-10-10 15:09:17,074][76542] Updated weights for policy 1, policy_version 63220 (0.0008) -[2023-10-10 15:09:17,442][76542] Updated weights for policy 1, policy_version 63230 (0.0008) -[2023-10-10 15:09:19,167][76543] Updated weights for policy 0, policy_version 63333 (0.0009) -[2023-10-10 15:09:19,540][76543] Updated weights for policy 0, policy_version 63343 (0.0011) -[2023-10-10 15:09:19,908][76543] Updated weights for policy 0, policy_version 63353 (0.0010) -[2023-10-10 15:09:21,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 129630208. Throughput: 0: 1817.1, 1: 1812.7. Samples: 32411700. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:09:21,076][75634] Avg episode reward: [(0, '33.030'), (1, '35.710')] -[2023-10-10 15:09:21,132][76542] Updated weights for policy 1, policy_version 63240 (0.0008) -[2023-10-10 15:09:21,502][76542] Updated weights for policy 1, policy_version 63250 (0.0011) -[2023-10-10 15:09:21,872][76542] Updated weights for policy 1, policy_version 63260 (0.0010) -[2023-10-10 15:09:23,564][76543] Updated weights for policy 0, policy_version 63363 (0.0009) -[2023-10-10 15:09:23,929][76543] Updated weights for policy 0, policy_version 63373 (0.0007) -[2023-10-10 15:09:24,304][76543] Updated weights for policy 0, policy_version 63383 (0.0008) -[2023-10-10 15:09:25,569][76542] Updated weights for policy 1, policy_version 63270 (0.0009) -[2023-10-10 15:09:25,936][76542] Updated weights for policy 1, policy_version 63280 (0.0008) -[2023-10-10 15:09:26,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 129695744. Throughput: 0: 1818.5, 1: 1805.7. Samples: 32433388. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 15:09:26,077][75634] Avg episode reward: [(0, '34.990'), (1, '36.020')] -[2023-10-10 15:09:26,295][76542] Updated weights for policy 1, policy_version 63290 (0.0009) -[2023-10-10 15:09:27,979][76543] Updated weights for policy 0, policy_version 63393 (0.0010) -[2023-10-10 15:09:28,404][76543] Updated weights for policy 0, policy_version 63403 (0.0008) -[2023-10-10 15:09:28,775][76543] Updated weights for policy 0, policy_version 63413 (0.0009) -[2023-10-10 15:09:29,151][76543] Updated weights for policy 0, policy_version 63423 (0.0008) -[2023-10-10 15:09:30,004][76542] Updated weights for policy 1, policy_version 63300 (0.0010) -[2023-10-10 15:09:30,373][76542] Updated weights for policy 1, policy_version 63310 (0.0008) -[2023-10-10 15:09:30,747][76542] Updated weights for policy 1, policy_version 63320 (0.0009) -[2023-10-10 15:09:31,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 129794048. Throughput: 0: 1817.5, 1: 1812.0. Samples: 32454542. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 15:09:31,077][75634] Avg episode reward: [(0, '34.370'), (1, '36.950')] -[2023-10-10 15:09:32,812][76543] Updated weights for policy 0, policy_version 63433 (0.0009) -[2023-10-10 15:09:33,181][76543] Updated weights for policy 0, policy_version 63443 (0.0012) -[2023-10-10 15:09:33,553][76543] Updated weights for policy 0, policy_version 63453 (0.0009) -[2023-10-10 15:09:34,195][76542] Updated weights for policy 1, policy_version 63330 (0.0008) -[2023-10-10 15:09:34,566][76542] Updated weights for policy 1, policy_version 63340 (0.0010) -[2023-10-10 15:09:34,936][76542] Updated weights for policy 1, policy_version 63350 (0.0012) -[2023-10-10 15:09:35,307][76542] Updated weights for policy 1, policy_version 63360 (0.0009) -[2023-10-10 15:09:36,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 129859584. Throughput: 0: 1819.8, 1: 1825.8. Samples: 32466504. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 15:09:36,077][75634] Avg episode reward: [(0, '35.690'), (1, '38.420')] -[2023-10-10 15:09:37,283][76543] Updated weights for policy 0, policy_version 63463 (0.0008) -[2023-10-10 15:09:37,658][76543] Updated weights for policy 0, policy_version 63473 (0.0007) -[2023-10-10 15:09:38,021][76543] Updated weights for policy 0, policy_version 63483 (0.0010) -[2023-10-10 15:09:39,187][76542] Updated weights for policy 1, policy_version 63370 (0.0010) -[2023-10-10 15:09:39,545][76542] Updated weights for policy 1, policy_version 63380 (0.0010) -[2023-10-10 15:09:39,913][76542] Updated weights for policy 1, policy_version 63390 (0.0010) -[2023-10-10 15:09:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 129925120. Throughput: 0: 1816.6, 1: 1815.9. Samples: 32487352. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 15:09:41,076][75634] Avg episode reward: [(0, '36.730'), (1, '39.280')] -[2023-10-10 15:09:41,621][76543] Updated weights for policy 0, policy_version 63493 (0.0010) -[2023-10-10 15:09:41,988][76543] Updated weights for policy 0, policy_version 63503 (0.0009) -[2023-10-10 15:09:42,358][76543] Updated weights for policy 0, policy_version 63513 (0.0008) -[2023-10-10 15:09:43,558][76542] Updated weights for policy 1, policy_version 63400 (0.0009) -[2023-10-10 15:09:43,929][76542] Updated weights for policy 1, policy_version 63410 (0.0007) -[2023-10-10 15:09:44,308][76542] Updated weights for policy 1, policy_version 63420 (0.0009) -[2023-10-10 15:09:46,070][76543] Updated weights for policy 0, policy_version 63523 (0.0011) -[2023-10-10 15:09:46,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14662.3). Total num frames: 129990656. Throughput: 0: 1817.1, 1: 1826.9. Samples: 32510244. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 15:09:46,077][75634] Avg episode reward: [(0, '36.640'), (1, '40.410')] -[2023-10-10 15:09:46,441][76543] Updated weights for policy 0, policy_version 63533 (0.0007) -[2023-10-10 15:09:46,811][76543] Updated weights for policy 0, policy_version 63543 (0.0007) -[2023-10-10 15:09:47,985][76542] Updated weights for policy 1, policy_version 63430 (0.0008) -[2023-10-10 15:09:48,347][76542] Updated weights for policy 1, policy_version 63440 (0.0009) -[2023-10-10 15:09:48,710][76542] Updated weights for policy 1, policy_version 63450 (0.0011) -[2023-10-10 15:09:50,396][76543] Updated weights for policy 0, policy_version 63553 (0.0009) -[2023-10-10 15:09:50,765][76543] Updated weights for policy 0, policy_version 63563 (0.0011) -[2023-10-10 15:09:51,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 130056192. Throughput: 0: 1818.1, 1: 1821.0. Samples: 32520524. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 15:09:51,076][75634] Avg episode reward: [(0, '38.460'), (1, '36.180')] -[2023-10-10 15:09:51,145][76543] Updated weights for policy 0, policy_version 63573 (0.0009) -[2023-10-10 15:09:51,527][76543] Updated weights for policy 0, policy_version 63583 (0.0009) -[2023-10-10 15:09:52,267][76542] Updated weights for policy 1, policy_version 63460 (0.0009) -[2023-10-10 15:09:52,638][76542] Updated weights for policy 1, policy_version 63470 (0.0008) -[2023-10-10 15:09:53,007][76542] Updated weights for policy 1, policy_version 63480 (0.0007) -[2023-10-10 15:09:55,105][76543] Updated weights for policy 0, policy_version 63593 (0.0007) -[2023-10-10 15:09:55,470][76543] Updated weights for policy 0, policy_version 63603 (0.0008) -[2023-10-10 15:09:55,843][76543] Updated weights for policy 0, policy_version 63613 (0.0010) -[2023-10-10 15:09:56,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 130154496. Throughput: 0: 1825.7, 1: 1822.8. Samples: 32543338. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 15:09:56,076][75634] Avg episode reward: [(0, '37.850'), (1, '34.710')] -[2023-10-10 15:09:56,674][76542] Updated weights for policy 1, policy_version 63490 (0.0008) -[2023-10-10 15:09:57,043][76542] Updated weights for policy 1, policy_version 63500 (0.0008) -[2023-10-10 15:09:57,418][76542] Updated weights for policy 1, policy_version 63510 (0.0008) -[2023-10-10 15:09:57,790][76542] Updated weights for policy 1, policy_version 63520 (0.0008) -[2023-10-10 15:09:59,531][76543] Updated weights for policy 0, policy_version 63623 (0.0009) -[2023-10-10 15:09:59,900][76543] Updated weights for policy 0, policy_version 63633 (0.0010) -[2023-10-10 15:10:00,277][76543] Updated weights for policy 0, policy_version 63643 (0.0010) -[2023-10-10 15:10:01,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 130220032. Throughput: 0: 1819.9, 1: 1829.8. Samples: 32565220. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 15:10:01,077][75634] Avg episode reward: [(0, '39.300'), (1, '34.470')] -[2023-10-10 15:10:01,601][76542] Updated weights for policy 1, policy_version 63530 (0.0012) -[2023-10-10 15:10:01,970][76542] Updated weights for policy 1, policy_version 63540 (0.0011) -[2023-10-10 15:10:02,344][76542] Updated weights for policy 1, policy_version 63550 (0.0010) -[2023-10-10 15:10:04,155][76543] Updated weights for policy 0, policy_version 63653 (0.0008) -[2023-10-10 15:10:04,517][76543] Updated weights for policy 0, policy_version 63663 (0.0010) -[2023-10-10 15:10:04,890][76543] Updated weights for policy 0, policy_version 63673 (0.0008) -[2023-10-10 15:10:06,060][76542] Updated weights for policy 1, policy_version 63560 (0.0007) -[2023-10-10 15:10:06,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 130285568. Throughput: 0: 1825.8, 1: 1827.7. Samples: 32576108. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-10 15:10:06,077][75634] Avg episode reward: [(0, '34.840'), (1, '34.040')] -[2023-10-10 15:10:06,434][76542] Updated weights for policy 1, policy_version 63570 (0.0008) -[2023-10-10 15:10:06,811][76542] Updated weights for policy 1, policy_version 63580 (0.0012) -[2023-10-10 15:10:08,701][76543] Updated weights for policy 0, policy_version 63683 (0.0008) -[2023-10-10 15:10:09,062][76543] Updated weights for policy 0, policy_version 63693 (0.0007) -[2023-10-10 15:10:09,439][76543] Updated weights for policy 0, policy_version 63703 (0.0007) -[2023-10-10 15:10:10,493][76542] Updated weights for policy 1, policy_version 63590 (0.0009) -[2023-10-10 15:10:10,863][76542] Updated weights for policy 1, policy_version 63600 (0.0007) -[2023-10-10 15:10:11,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 130351104. Throughput: 0: 1822.9, 1: 1835.7. Samples: 32598026. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-10 15:10:11,077][75634] Avg episode reward: [(0, '40.230'), (1, '32.390')] -[2023-10-10 15:10:11,237][76542] Updated weights for policy 1, policy_version 63610 (0.0007) -[2023-10-10 15:10:13,233][76543] Updated weights for policy 0, policy_version 63713 (0.0007) -[2023-10-10 15:10:13,631][76543] Updated weights for policy 0, policy_version 63723 (0.0010) -[2023-10-10 15:10:13,996][76543] Updated weights for policy 0, policy_version 63733 (0.0010) -[2023-10-10 15:10:14,360][76543] Updated weights for policy 0, policy_version 63743 (0.0009) -[2023-10-10 15:10:14,854][76542] Updated weights for policy 1, policy_version 63620 (0.0009) -[2023-10-10 15:10:15,213][76542] Updated weights for policy 1, policy_version 63630 (0.0007) -[2023-10-10 15:10:15,590][76542] Updated weights for policy 1, policy_version 63640 (0.0009) -[2023-10-10 15:10:16,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 130449408. Throughput: 0: 1824.8, 1: 1825.1. Samples: 32618788. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-10 15:10:16,077][75634] Avg episode reward: [(0, '35.620'), (1, '31.950')] -[2023-10-10 15:10:17,782][76543] Updated weights for policy 0, policy_version 63753 (0.0008) -[2023-10-10 15:10:18,155][76543] Updated weights for policy 0, policy_version 63763 (0.0008) -[2023-10-10 15:10:18,537][76543] Updated weights for policy 0, policy_version 63773 (0.0008) -[2023-10-10 15:10:19,331][76542] Updated weights for policy 1, policy_version 63650 (0.0008) -[2023-10-10 15:10:19,691][76542] Updated weights for policy 1, policy_version 63660 (0.0009) -[2023-10-10 15:10:20,058][76542] Updated weights for policy 1, policy_version 63670 (0.0011) -[2023-10-10 15:10:20,425][76542] Updated weights for policy 1, policy_version 63680 (0.0010) -[2023-10-10 15:10:21,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 130514944. Throughput: 0: 1829.9, 1: 1820.8. Samples: 32630788. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-10 15:10:21,077][75634] Avg episode reward: [(0, '33.790'), (1, '35.450')] -[2023-10-10 15:10:22,151][76543] Updated weights for policy 0, policy_version 63783 (0.0009) -[2023-10-10 15:10:22,518][76543] Updated weights for policy 0, policy_version 63793 (0.0010) -[2023-10-10 15:10:22,893][76543] Updated weights for policy 0, policy_version 63803 (0.0010) -[2023-10-10 15:10:24,101][76542] Updated weights for policy 1, policy_version 63690 (0.0008) -[2023-10-10 15:10:24,465][76542] Updated weights for policy 1, policy_version 63700 (0.0009) -[2023-10-10 15:10:24,829][76542] Updated weights for policy 1, policy_version 63710 (0.0010) -[2023-10-10 15:10:26,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 130580480. Throughput: 0: 1837.0, 1: 1821.4. Samples: 32651980. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-10 15:10:26,076][75634] Avg episode reward: [(0, '33.760'), (1, '33.810')] -[2023-10-10 15:10:26,612][76543] Updated weights for policy 0, policy_version 63813 (0.0007) -[2023-10-10 15:10:26,978][76543] Updated weights for policy 0, policy_version 63823 (0.0009) -[2023-10-10 15:10:27,348][76543] Updated weights for policy 0, policy_version 63833 (0.0007) -[2023-10-10 15:10:28,351][76542] Updated weights for policy 1, policy_version 63720 (0.0008) -[2023-10-10 15:10:28,713][76542] Updated weights for policy 1, policy_version 63730 (0.0009) -[2023-10-10 15:10:29,076][76542] Updated weights for policy 1, policy_version 63740 (0.0009) -[2023-10-10 15:10:30,862][76543] Updated weights for policy 0, policy_version 63843 (0.0009) -[2023-10-10 15:10:31,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14662.3). Total num frames: 130646016. Throughput: 0: 1833.6, 1: 1828.6. Samples: 32675044. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-10 15:10:31,076][75634] Avg episode reward: [(0, '33.340'), (1, '33.150')] -[2023-10-10 15:10:31,085][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000063744_65273856.pth... -[2023-10-10 15:10:31,117][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000062048_63537152.pth -[2023-10-10 15:10:31,230][76543] Updated weights for policy 0, policy_version 63853 (0.0008) -[2023-10-10 15:10:31,599][76543] Updated weights for policy 0, policy_version 63863 (0.0008) -[2023-10-10 15:10:31,928][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000063872_65404928.pth... -[2023-10-10 15:10:31,966][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000062144_63635456.pth -[2023-10-10 15:10:32,796][76542] Updated weights for policy 1, policy_version 63750 (0.0007) -[2023-10-10 15:10:33,171][76542] Updated weights for policy 1, policy_version 63760 (0.0008) -[2023-10-10 15:10:33,536][76542] Updated weights for policy 1, policy_version 63770 (0.0008) -[2023-10-10 15:10:35,071][76543] Updated weights for policy 0, policy_version 63873 (0.0008) -[2023-10-10 15:10:35,433][76543] Updated weights for policy 0, policy_version 63883 (0.0009) -[2023-10-10 15:10:35,805][76543] Updated weights for policy 0, policy_version 63893 (0.0010) -[2023-10-10 15:10:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 130711552. Throughput: 0: 1835.4, 1: 1824.6. Samples: 32685222. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-10 15:10:36,076][75634] Avg episode reward: [(0, '35.590'), (1, '33.920')] -[2023-10-10 15:10:36,175][76543] Updated weights for policy 0, policy_version 63903 (0.0011) -[2023-10-10 15:10:37,175][76542] Updated weights for policy 1, policy_version 63780 (0.0008) -[2023-10-10 15:10:37,553][76542] Updated weights for policy 1, policy_version 63790 (0.0007) -[2023-10-10 15:10:37,922][76542] Updated weights for policy 1, policy_version 63800 (0.0008) -[2023-10-10 15:10:39,834][76543] Updated weights for policy 0, policy_version 63913 (0.0009) -[2023-10-10 15:10:40,201][76543] Updated weights for policy 0, policy_version 63923 (0.0010) -[2023-10-10 15:10:40,575][76543] Updated weights for policy 0, policy_version 63933 (0.0008) -[2023-10-10 15:10:41,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 130809856. Throughput: 0: 1833.9, 1: 1824.6. Samples: 32707968. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-10 15:10:41,077][75634] Avg episode reward: [(0, '37.030'), (1, '34.180')] -[2023-10-10 15:10:41,694][76542] Updated weights for policy 1, policy_version 63810 (0.0007) -[2023-10-10 15:10:42,062][76542] Updated weights for policy 1, policy_version 63820 (0.0007) -[2023-10-10 15:10:42,425][76542] Updated weights for policy 1, policy_version 63830 (0.0010) -[2023-10-10 15:10:42,794][76542] Updated weights for policy 1, policy_version 63840 (0.0007) -[2023-10-10 15:10:44,150][76543] Updated weights for policy 0, policy_version 63943 (0.0009) -[2023-10-10 15:10:44,513][76543] Updated weights for policy 0, policy_version 63953 (0.0009) -[2023-10-10 15:10:44,878][76543] Updated weights for policy 0, policy_version 63963 (0.0007) -[2023-10-10 15:10:46,076][75634] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 130875392. Throughput: 0: 1828.5, 1: 1818.8. Samples: 32729346. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-10 15:10:46,077][75634] Avg episode reward: [(0, '39.380'), (1, '37.980')] -[2023-10-10 15:10:46,533][76542] Updated weights for policy 1, policy_version 63850 (0.0007) -[2023-10-10 15:10:46,902][76542] Updated weights for policy 1, policy_version 63860 (0.0007) -[2023-10-10 15:10:47,262][76542] Updated weights for policy 1, policy_version 63870 (0.0007) -[2023-10-10 15:10:48,505][76543] Updated weights for policy 0, policy_version 63973 (0.0008) -[2023-10-10 15:10:48,875][76543] Updated weights for policy 0, policy_version 63983 (0.0007) -[2023-10-10 15:10:49,247][76543] Updated weights for policy 0, policy_version 63993 (0.0010) -[2023-10-10 15:10:50,908][76542] Updated weights for policy 1, policy_version 63880 (0.0008) -[2023-10-10 15:10:51,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 130940928. Throughput: 0: 1838.3, 1: 1821.6. Samples: 32740804. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-10-10 15:10:51,077][75634] Avg episode reward: [(0, '40.280'), (1, '37.790')] -[2023-10-10 15:10:51,287][76542] Updated weights for policy 1, policy_version 63890 (0.0007) -[2023-10-10 15:10:51,657][76542] Updated weights for policy 1, policy_version 63900 (0.0008) -[2023-10-10 15:10:53,003][76543] Updated weights for policy 0, policy_version 64003 (0.0009) -[2023-10-10 15:10:53,368][76543] Updated weights for policy 0, policy_version 64013 (0.0007) -[2023-10-10 15:10:53,737][76543] Updated weights for policy 0, policy_version 64023 (0.0007) -[2023-10-10 15:10:55,303][76542] Updated weights for policy 1, policy_version 63910 (0.0009) -[2023-10-10 15:10:55,677][76542] Updated weights for policy 1, policy_version 63920 (0.0011) -[2023-10-10 15:10:56,048][76542] Updated weights for policy 1, policy_version 63930 (0.0009) -[2023-10-10 15:10:56,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 131006464. Throughput: 0: 1824.0, 1: 1823.7. Samples: 32762170. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-10-10 15:10:56,076][75634] Avg episode reward: [(0, '37.590'), (1, '39.540')] -[2023-10-10 15:10:57,435][76543] Updated weights for policy 0, policy_version 64033 (0.0008) -[2023-10-10 15:10:57,819][76543] Updated weights for policy 0, policy_version 64043 (0.0008) -[2023-10-10 15:10:58,196][76543] Updated weights for policy 0, policy_version 64053 (0.0009) -[2023-10-10 15:10:58,564][76543] Updated weights for policy 0, policy_version 64063 (0.0007) -[2023-10-10 15:10:59,706][76542] Updated weights for policy 1, policy_version 63940 (0.0008) -[2023-10-10 15:11:00,078][76542] Updated weights for policy 1, policy_version 63950 (0.0011) -[2023-10-10 15:11:00,446][76542] Updated weights for policy 1, policy_version 63960 (0.0008) -[2023-10-10 15:11:01,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 131104768. Throughput: 0: 1842.0, 1: 1825.0. Samples: 32783802. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-10-10 15:11:01,076][75634] Avg episode reward: [(0, '37.130'), (1, '37.110')] -[2023-10-10 15:11:02,186][76543] Updated weights for policy 0, policy_version 64073 (0.0009) -[2023-10-10 15:11:02,557][76543] Updated weights for policy 0, policy_version 64083 (0.0008) -[2023-10-10 15:11:02,938][76543] Updated weights for policy 0, policy_version 64093 (0.0010) -[2023-10-10 15:11:04,071][76542] Updated weights for policy 1, policy_version 63970 (0.0010) -[2023-10-10 15:11:04,442][76542] Updated weights for policy 1, policy_version 63980 (0.0009) -[2023-10-10 15:11:04,811][76542] Updated weights for policy 1, policy_version 63990 (0.0009) -[2023-10-10 15:11:05,176][76542] Updated weights for policy 1, policy_version 64000 (0.0008) -[2023-10-10 15:11:06,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 131170304. Throughput: 0: 1826.3, 1: 1830.3. Samples: 32795334. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-10-10 15:11:06,076][75634] Avg episode reward: [(0, '37.910'), (1, '38.810')] -[2023-10-10 15:11:06,755][76543] Updated weights for policy 0, policy_version 64103 (0.0010) -[2023-10-10 15:11:07,115][76543] Updated weights for policy 0, policy_version 64113 (0.0011) -[2023-10-10 15:11:07,488][76543] Updated weights for policy 0, policy_version 64123 (0.0008) -[2023-10-10 15:11:09,062][76542] Updated weights for policy 1, policy_version 64010 (0.0011) -[2023-10-10 15:11:09,426][76542] Updated weights for policy 1, policy_version 64020 (0.0011) -[2023-10-10 15:11:09,797][76542] Updated weights for policy 1, policy_version 64030 (0.0008) -[2023-10-10 15:11:11,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 131235840. Throughput: 0: 1830.6, 1: 1830.0. Samples: 32816706. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-10-10 15:11:11,076][75634] Avg episode reward: [(0, '35.330'), (1, '36.580')] -[2023-10-10 15:11:11,189][76543] Updated weights for policy 0, policy_version 64133 (0.0009) -[2023-10-10 15:11:11,561][76543] Updated weights for policy 0, policy_version 64143 (0.0008) -[2023-10-10 15:11:11,931][76543] Updated weights for policy 0, policy_version 64153 (0.0010) -[2023-10-10 15:11:13,473][76542] Updated weights for policy 1, policy_version 64040 (0.0008) -[2023-10-10 15:11:13,844][76542] Updated weights for policy 1, policy_version 64050 (0.0007) -[2023-10-10 15:11:14,216][76542] Updated weights for policy 1, policy_version 64060 (0.0008) -[2023-10-10 15:11:15,572][76543] Updated weights for policy 0, policy_version 64163 (0.0007) -[2023-10-10 15:11:15,947][76543] Updated weights for policy 0, policy_version 64173 (0.0008) -[2023-10-10 15:11:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 131301376. Throughput: 0: 1831.4, 1: 1818.3. Samples: 32839282. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-10-10 15:11:16,077][75634] Avg episode reward: [(0, '37.050'), (1, '34.980')] -[2023-10-10 15:11:16,314][76543] Updated weights for policy 0, policy_version 64183 (0.0007) -[2023-10-10 15:11:17,988][76542] Updated weights for policy 1, policy_version 64070 (0.0007) -[2023-10-10 15:11:18,366][76542] Updated weights for policy 1, policy_version 64080 (0.0008) -[2023-10-10 15:11:18,741][76542] Updated weights for policy 1, policy_version 64090 (0.0009) -[2023-10-10 15:11:20,065][76543] Updated weights for policy 0, policy_version 64193 (0.0007) -[2023-10-10 15:11:20,444][76543] Updated weights for policy 0, policy_version 64203 (0.0008) -[2023-10-10 15:11:20,810][76543] Updated weights for policy 0, policy_version 64213 (0.0010) -[2023-10-10 15:11:21,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 131366912. Throughput: 0: 1828.4, 1: 1822.8. Samples: 32849524. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-10-10 15:11:21,076][75634] Avg episode reward: [(0, '32.760'), (1, '37.860')] -[2023-10-10 15:11:21,176][76543] Updated weights for policy 0, policy_version 64223 (0.0010) -[2023-10-10 15:11:22,400][76542] Updated weights for policy 1, policy_version 64100 (0.0008) -[2023-10-10 15:11:22,773][76542] Updated weights for policy 1, policy_version 64110 (0.0008) -[2023-10-10 15:11:23,147][76542] Updated weights for policy 1, policy_version 64120 (0.0007) -[2023-10-10 15:11:24,707][76543] Updated weights for policy 0, policy_version 64233 (0.0010) -[2023-10-10 15:11:25,087][76543] Updated weights for policy 0, policy_version 64243 (0.0008) -[2023-10-10 15:11:25,459][76543] Updated weights for policy 0, policy_version 64253 (0.0008) -[2023-10-10 15:11:26,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 131465216. Throughput: 0: 1823.5, 1: 1816.9. Samples: 32871784. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-10-10 15:11:26,077][75634] Avg episode reward: [(0, '34.290'), (1, '35.730')] -[2023-10-10 15:11:26,858][76542] Updated weights for policy 1, policy_version 64130 (0.0009) -[2023-10-10 15:11:27,218][76542] Updated weights for policy 1, policy_version 64140 (0.0010) -[2023-10-10 15:11:27,589][76542] Updated weights for policy 1, policy_version 64150 (0.0009) -[2023-10-10 15:11:27,964][76542] Updated weights for policy 1, policy_version 64160 (0.0009) -[2023-10-10 15:11:29,236][76543] Updated weights for policy 0, policy_version 64263 (0.0010) -[2023-10-10 15:11:29,615][76543] Updated weights for policy 0, policy_version 64273 (0.0010) -[2023-10-10 15:11:29,983][76543] Updated weights for policy 0, policy_version 64283 (0.0010) -[2023-10-10 15:11:31,076][75634] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 131530752. Throughput: 0: 1817.8, 1: 1816.0. Samples: 32892866. Policy #0 lag: (min: 25.0, avg: 25.1, max: 29.0) -[2023-10-10 15:11:31,077][75634] Avg episode reward: [(0, '37.930'), (1, '34.630')] -[2023-10-10 15:11:31,597][76542] Updated weights for policy 1, policy_version 64170 (0.0008) -[2023-10-10 15:11:31,963][76542] Updated weights for policy 1, policy_version 64180 (0.0009) -[2023-10-10 15:11:32,331][76542] Updated weights for policy 1, policy_version 64190 (0.0008) -[2023-10-10 15:11:33,839][76543] Updated weights for policy 0, policy_version 64293 (0.0008) -[2023-10-10 15:11:34,210][76543] Updated weights for policy 0, policy_version 64303 (0.0008) -[2023-10-10 15:11:34,573][76543] Updated weights for policy 0, policy_version 64313 (0.0008) -[2023-10-10 15:11:35,906][76542] Updated weights for policy 1, policy_version 64200 (0.0007) -[2023-10-10 15:11:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 131596288. Throughput: 0: 1808.2, 1: 1818.7. Samples: 32904012. Policy #0 lag: (min: 25.0, avg: 25.1, max: 29.0) -[2023-10-10 15:11:36,077][75634] Avg episode reward: [(0, '35.840'), (1, '33.480')] -[2023-10-10 15:11:36,277][76542] Updated weights for policy 1, policy_version 64210 (0.0008) -[2023-10-10 15:11:36,649][76542] Updated weights for policy 1, policy_version 64220 (0.0009) -[2023-10-10 15:11:38,286][76543] Updated weights for policy 0, policy_version 64323 (0.0008) -[2023-10-10 15:11:38,661][76543] Updated weights for policy 0, policy_version 64333 (0.0008) -[2023-10-10 15:11:39,029][76543] Updated weights for policy 0, policy_version 64343 (0.0009) -[2023-10-10 15:11:40,460][76542] Updated weights for policy 1, policy_version 64230 (0.0009) -[2023-10-10 15:11:40,831][76542] Updated weights for policy 1, policy_version 64240 (0.0008) -[2023-10-10 15:11:41,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 131661824. Throughput: 0: 1815.5, 1: 1818.4. Samples: 32925696. Policy #0 lag: (min: 25.0, avg: 25.1, max: 29.0) -[2023-10-10 15:11:41,076][75634] Avg episode reward: [(0, '32.910'), (1, '34.980')] -[2023-10-10 15:11:41,198][76542] Updated weights for policy 1, policy_version 64250 (0.0008) -[2023-10-10 15:11:42,615][76543] Updated weights for policy 0, policy_version 64353 (0.0008) -[2023-10-10 15:11:43,030][76543] Updated weights for policy 0, policy_version 64363 (0.0010) -[2023-10-10 15:11:43,387][76543] Updated weights for policy 0, policy_version 64373 (0.0008) -[2023-10-10 15:11:43,767][76543] Updated weights for policy 0, policy_version 64383 (0.0008) -[2023-10-10 15:11:44,950][76542] Updated weights for policy 1, policy_version 64260 (0.0008) -[2023-10-10 15:11:45,311][76542] Updated weights for policy 1, policy_version 64270 (0.0008) -[2023-10-10 15:11:45,681][76542] Updated weights for policy 1, policy_version 64280 (0.0008) -[2023-10-10 15:11:46,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 131760128. Throughput: 0: 1807.2, 1: 1820.5. Samples: 32947048. Policy #0 lag: (min: 25.0, avg: 25.1, max: 29.0) -[2023-10-10 15:11:46,077][75634] Avg episode reward: [(0, '35.490'), (1, '37.100')] -[2023-10-10 15:11:47,533][76543] Updated weights for policy 0, policy_version 64393 (0.0007) -[2023-10-10 15:11:47,906][76543] Updated weights for policy 0, policy_version 64403 (0.0009) -[2023-10-10 15:11:48,278][76543] Updated weights for policy 0, policy_version 64413 (0.0009) -[2023-10-10 15:11:49,228][76542] Updated weights for policy 1, policy_version 64290 (0.0008) -[2023-10-10 15:11:49,600][76542] Updated weights for policy 1, policy_version 64300 (0.0007) -[2023-10-10 15:11:49,962][76542] Updated weights for policy 1, policy_version 64310 (0.0008) -[2023-10-10 15:11:50,327][76542] Updated weights for policy 1, policy_version 64320 (0.0008) -[2023-10-10 15:11:51,076][75634] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 131825664. Throughput: 0: 1806.5, 1: 1817.7. Samples: 32958424. Policy #0 lag: (min: 25.0, avg: 25.1, max: 29.0) -[2023-10-10 15:11:51,077][75634] Avg episode reward: [(0, '36.660'), (1, '32.030')] -[2023-10-10 15:11:51,969][76543] Updated weights for policy 0, policy_version 64423 (0.0008) -[2023-10-10 15:11:52,343][76543] Updated weights for policy 0, policy_version 64433 (0.0008) -[2023-10-10 15:11:52,714][76543] Updated weights for policy 0, policy_version 64443 (0.0007) -[2023-10-10 15:11:54,101][76542] Updated weights for policy 1, policy_version 64330 (0.0008) -[2023-10-10 15:11:54,468][76542] Updated weights for policy 1, policy_version 64340 (0.0008) -[2023-10-10 15:11:54,829][76542] Updated weights for policy 1, policy_version 64350 (0.0009) -[2023-10-10 15:11:56,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 131891200. Throughput: 0: 1806.0, 1: 1817.7. Samples: 32979774. Policy #0 lag: (min: 25.0, avg: 25.1, max: 29.0) -[2023-10-10 15:11:56,077][75634] Avg episode reward: [(0, '33.870'), (1, '33.810')] -[2023-10-10 15:11:56,384][76543] Updated weights for policy 0, policy_version 64453 (0.0009) -[2023-10-10 15:11:56,750][76543] Updated weights for policy 0, policy_version 64463 (0.0009) -[2023-10-10 15:11:57,125][76543] Updated weights for policy 0, policy_version 64473 (0.0009) -[2023-10-10 15:11:58,370][76542] Updated weights for policy 1, policy_version 64360 (0.0008) -[2023-10-10 15:11:58,735][76542] Updated weights for policy 1, policy_version 64370 (0.0008) -[2023-10-10 15:11:59,101][76542] Updated weights for policy 1, policy_version 64380 (0.0009) -[2023-10-10 15:12:00,772][76543] Updated weights for policy 0, policy_version 64483 (0.0007) -[2023-10-10 15:12:01,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 131956736. Throughput: 0: 1809.0, 1: 1820.2. Samples: 33002598. Policy #0 lag: (min: 25.0, avg: 25.1, max: 29.0) -[2023-10-10 15:12:01,077][75634] Avg episode reward: [(0, '34.290'), (1, '32.990')] -[2023-10-10 15:12:01,144][76543] Updated weights for policy 0, policy_version 64493 (0.0009) -[2023-10-10 15:12:01,513][76543] Updated weights for policy 0, policy_version 64503 (0.0008) -[2023-10-10 15:12:02,779][76542] Updated weights for policy 1, policy_version 64390 (0.0007) -[2023-10-10 15:12:03,137][76542] Updated weights for policy 1, policy_version 64400 (0.0007) -[2023-10-10 15:12:03,515][76542] Updated weights for policy 1, policy_version 64410 (0.0008) -[2023-10-10 15:12:05,131][76543] Updated weights for policy 0, policy_version 64513 (0.0010) -[2023-10-10 15:12:05,500][76543] Updated weights for policy 0, policy_version 64523 (0.0007) -[2023-10-10 15:12:05,877][76543] Updated weights for policy 0, policy_version 64533 (0.0007) -[2023-10-10 15:12:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 132022272. Throughput: 0: 1808.8, 1: 1815.1. Samples: 33012598. Policy #0 lag: (min: 25.0, avg: 25.1, max: 29.0) -[2023-10-10 15:12:06,076][75634] Avg episode reward: [(0, '35.210'), (1, '33.960')] -[2023-10-10 15:12:06,241][76543] Updated weights for policy 0, policy_version 64543 (0.0007) -[2023-10-10 15:12:07,221][76542] Updated weights for policy 1, policy_version 64420 (0.0009) -[2023-10-10 15:12:07,588][76542] Updated weights for policy 1, policy_version 64430 (0.0011) -[2023-10-10 15:12:07,951][76542] Updated weights for policy 1, policy_version 64440 (0.0008) -[2023-10-10 15:12:09,938][76543] Updated weights for policy 0, policy_version 64553 (0.0010) -[2023-10-10 15:12:10,320][76543] Updated weights for policy 0, policy_version 64563 (0.0010) -[2023-10-10 15:12:10,687][76543] Updated weights for policy 0, policy_version 64573 (0.0011) -[2023-10-10 15:12:11,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 132120576. Throughput: 0: 1816.4, 1: 1821.7. Samples: 33035498. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 15:12:11,077][75634] Avg episode reward: [(0, '33.300'), (1, '38.570')] -[2023-10-10 15:12:11,634][76542] Updated weights for policy 1, policy_version 64450 (0.0008) -[2023-10-10 15:12:11,996][76542] Updated weights for policy 1, policy_version 64460 (0.0008) -[2023-10-10 15:12:12,361][76542] Updated weights for policy 1, policy_version 64470 (0.0008) -[2023-10-10 15:12:12,743][76542] Updated weights for policy 1, policy_version 64480 (0.0008) -[2023-10-10 15:12:14,425][76543] Updated weights for policy 0, policy_version 64583 (0.0010) -[2023-10-10 15:12:14,802][76543] Updated weights for policy 0, policy_version 64593 (0.0007) -[2023-10-10 15:12:15,175][76543] Updated weights for policy 0, policy_version 64603 (0.0009) -[2023-10-10 15:12:16,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 132186112. Throughput: 0: 1824.6, 1: 1824.6. Samples: 33057078. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 15:12:16,077][75634] Avg episode reward: [(0, '33.260'), (1, '41.240')] -[2023-10-10 15:12:16,652][76542] Updated weights for policy 1, policy_version 64490 (0.0008) -[2023-10-10 15:12:17,026][76542] Updated weights for policy 1, policy_version 64500 (0.0007) -[2023-10-10 15:12:17,406][76542] Updated weights for policy 1, policy_version 64510 (0.0008) -[2023-10-10 15:12:18,815][76543] Updated weights for policy 0, policy_version 64613 (0.0009) -[2023-10-10 15:12:19,192][76543] Updated weights for policy 0, policy_version 64623 (0.0007) -[2023-10-10 15:12:19,555][76543] Updated weights for policy 0, policy_version 64633 (0.0010) -[2023-10-10 15:12:20,968][76542] Updated weights for policy 1, policy_version 64520 (0.0010) -[2023-10-10 15:12:21,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 132251648. Throughput: 0: 1826.4, 1: 1824.5. Samples: 33068298. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 15:12:21,076][75634] Avg episode reward: [(0, '33.010'), (1, '39.080')] -[2023-10-10 15:12:21,346][76542] Updated weights for policy 1, policy_version 64530 (0.0011) -[2023-10-10 15:12:21,707][76542] Updated weights for policy 1, policy_version 64540 (0.0010) -[2023-10-10 15:12:23,137][76543] Updated weights for policy 0, policy_version 64643 (0.0008) -[2023-10-10 15:12:23,508][76543] Updated weights for policy 0, policy_version 64653 (0.0007) -[2023-10-10 15:12:23,880][76543] Updated weights for policy 0, policy_version 64663 (0.0010) -[2023-10-10 15:12:25,538][76542] Updated weights for policy 1, policy_version 64550 (0.0009) -[2023-10-10 15:12:25,916][76542] Updated weights for policy 1, policy_version 64560 (0.0009) -[2023-10-10 15:12:26,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 132317184. Throughput: 0: 1825.4, 1: 1820.4. Samples: 33089754. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 15:12:26,077][75634] Avg episode reward: [(0, '35.680'), (1, '40.720')] -[2023-10-10 15:12:26,292][76542] Updated weights for policy 1, policy_version 64570 (0.0007) -[2023-10-10 15:12:27,450][76543] Updated weights for policy 0, policy_version 64673 (0.0008) -[2023-10-10 15:12:27,871][76543] Updated weights for policy 0, policy_version 64683 (0.0009) -[2023-10-10 15:12:28,249][76543] Updated weights for policy 0, policy_version 64693 (0.0008) -[2023-10-10 15:12:28,620][76543] Updated weights for policy 0, policy_version 64703 (0.0007) -[2023-10-10 15:12:29,832][76542] Updated weights for policy 1, policy_version 64580 (0.0008) -[2023-10-10 15:12:30,207][76542] Updated weights for policy 1, policy_version 64590 (0.0010) -[2023-10-10 15:12:30,569][76542] Updated weights for policy 1, policy_version 64600 (0.0008) -[2023-10-10 15:12:31,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 132415488. Throughput: 0: 1831.2, 1: 1822.6. Samples: 33111468. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 15:12:31,077][75634] Avg episode reward: [(0, '35.270'), (1, '35.090')] -[2023-10-10 15:12:31,087][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000064704_66256896.pth... -[2023-10-10 15:12:31,087][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000064608_66158592.pth... -[2023-10-10 15:12:31,124][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000063008_64520192.pth -[2023-10-10 15:12:31,124][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000062880_64389120.pth -[2023-10-10 15:12:32,265][76543] Updated weights for policy 0, policy_version 64713 (0.0009) -[2023-10-10 15:12:32,632][76543] Updated weights for policy 0, policy_version 64723 (0.0008) -[2023-10-10 15:12:33,008][76543] Updated weights for policy 0, policy_version 64733 (0.0008) -[2023-10-10 15:12:34,235][76542] Updated weights for policy 1, policy_version 64610 (0.0009) -[2023-10-10 15:12:34,598][76542] Updated weights for policy 1, policy_version 64620 (0.0011) -[2023-10-10 15:12:34,968][76542] Updated weights for policy 1, policy_version 64630 (0.0009) -[2023-10-10 15:12:35,337][76542] Updated weights for policy 1, policy_version 64640 (0.0007) -[2023-10-10 15:12:36,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 132481024. Throughput: 0: 1827.5, 1: 1823.0. Samples: 33122694. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 15:12:36,077][75634] Avg episode reward: [(0, '42.020'), (1, '32.710')] -[2023-10-10 15:12:36,620][76543] Updated weights for policy 0, policy_version 64743 (0.0007) -[2023-10-10 15:12:36,995][76543] Updated weights for policy 0, policy_version 64753 (0.0007) -[2023-10-10 15:12:37,372][76543] Updated weights for policy 0, policy_version 64763 (0.0007) -[2023-10-10 15:12:38,946][76542] Updated weights for policy 1, policy_version 64650 (0.0008) -[2023-10-10 15:12:39,320][76542] Updated weights for policy 1, policy_version 64660 (0.0012) -[2023-10-10 15:12:39,684][76542] Updated weights for policy 1, policy_version 64670 (0.0008) -[2023-10-10 15:12:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 132546560. Throughput: 0: 1839.1, 1: 1822.5. Samples: 33144546. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 15:12:41,076][75634] Avg episode reward: [(0, '37.790'), (1, '29.540')] -[2023-10-10 15:12:41,229][76543] Updated weights for policy 0, policy_version 64773 (0.0008) -[2023-10-10 15:12:41,600][76543] Updated weights for policy 0, policy_version 64783 (0.0007) -[2023-10-10 15:12:41,971][76543] Updated weights for policy 0, policy_version 64793 (0.0008) -[2023-10-10 15:12:43,360][76542] Updated weights for policy 1, policy_version 64680 (0.0008) -[2023-10-10 15:12:43,724][76542] Updated weights for policy 1, policy_version 64690 (0.0012) -[2023-10-10 15:12:44,093][76542] Updated weights for policy 1, policy_version 64700 (0.0009) -[2023-10-10 15:12:45,455][76543] Updated weights for policy 0, policy_version 64803 (0.0008) -[2023-10-10 15:12:45,818][76543] Updated weights for policy 0, policy_version 64813 (0.0007) -[2023-10-10 15:12:46,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 132612096. Throughput: 0: 1837.5, 1: 1824.8. Samples: 33167398. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 15:12:46,076][75634] Avg episode reward: [(0, '37.180'), (1, '30.230')] -[2023-10-10 15:12:46,188][76543] Updated weights for policy 0, policy_version 64823 (0.0007) -[2023-10-10 15:12:47,785][76542] Updated weights for policy 1, policy_version 64710 (0.0009) -[2023-10-10 15:12:48,162][76542] Updated weights for policy 1, policy_version 64720 (0.0009) -[2023-10-10 15:12:48,522][76542] Updated weights for policy 1, policy_version 64730 (0.0009) -[2023-10-10 15:12:49,935][76543] Updated weights for policy 0, policy_version 64833 (0.0008) -[2023-10-10 15:12:50,303][76543] Updated weights for policy 0, policy_version 64843 (0.0008) -[2023-10-10 15:12:50,671][76543] Updated weights for policy 0, policy_version 64853 (0.0008) -[2023-10-10 15:12:51,047][76543] Updated weights for policy 0, policy_version 64863 (0.0008) -[2023-10-10 15:12:51,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 132677632. Throughput: 0: 1837.5, 1: 1824.0. Samples: 33177362. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 15:12:51,076][75634] Avg episode reward: [(0, '38.910'), (1, '34.270')] -[2023-10-10 15:12:52,377][76542] Updated weights for policy 1, policy_version 64740 (0.0008) -[2023-10-10 15:12:52,745][76542] Updated weights for policy 1, policy_version 64750 (0.0008) -[2023-10-10 15:12:53,115][76542] Updated weights for policy 1, policy_version 64760 (0.0009) -[2023-10-10 15:12:54,562][76543] Updated weights for policy 0, policy_version 64873 (0.0007) -[2023-10-10 15:12:54,923][76543] Updated weights for policy 0, policy_version 64883 (0.0007) -[2023-10-10 15:12:55,300][76543] Updated weights for policy 0, policy_version 64893 (0.0008) -[2023-10-10 15:12:56,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 132775936. Throughput: 0: 1836.5, 1: 1823.6. Samples: 33200202. Policy #0 lag: (min: 26.0, avg: 28.0, max: 56.0) -[2023-10-10 15:12:56,077][75634] Avg episode reward: [(0, '38.140'), (1, '34.590')] -[2023-10-10 15:12:56,736][76542] Updated weights for policy 1, policy_version 64770 (0.0010) -[2023-10-10 15:12:57,110][76542] Updated weights for policy 1, policy_version 64780 (0.0010) -[2023-10-10 15:12:57,487][76542] Updated weights for policy 1, policy_version 64790 (0.0010) -[2023-10-10 15:12:57,855][76542] Updated weights for policy 1, policy_version 64800 (0.0008) -[2023-10-10 15:12:58,997][76543] Updated weights for policy 0, policy_version 64903 (0.0007) -[2023-10-10 15:12:59,372][76543] Updated weights for policy 0, policy_version 64913 (0.0009) -[2023-10-10 15:12:59,746][76543] Updated weights for policy 0, policy_version 64923 (0.0007) -[2023-10-10 15:13:01,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 132841472. Throughput: 0: 1838.8, 1: 1824.5. Samples: 33221926. Policy #0 lag: (min: 26.0, avg: 28.0, max: 56.0) -[2023-10-10 15:13:01,077][75634] Avg episode reward: [(0, '33.820'), (1, '38.320')] -[2023-10-10 15:13:01,656][76542] Updated weights for policy 1, policy_version 64810 (0.0007) -[2023-10-10 15:13:02,018][76542] Updated weights for policy 1, policy_version 64820 (0.0008) -[2023-10-10 15:13:02,389][76542] Updated weights for policy 1, policy_version 64830 (0.0009) -[2023-10-10 15:13:03,323][76543] Updated weights for policy 0, policy_version 64933 (0.0008) -[2023-10-10 15:13:03,697][76543] Updated weights for policy 0, policy_version 64943 (0.0010) -[2023-10-10 15:13:04,075][76543] Updated weights for policy 0, policy_version 64953 (0.0011) -[2023-10-10 15:13:06,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 132907008. Throughput: 0: 1843.1, 1: 1823.4. Samples: 33233290. Policy #0 lag: (min: 26.0, avg: 28.0, max: 56.0) -[2023-10-10 15:13:06,076][75634] Avg episode reward: [(0, '33.390'), (1, '38.940')] -[2023-10-10 15:13:06,090][76542] Updated weights for policy 1, policy_version 64840 (0.0008) -[2023-10-10 15:13:06,450][76542] Updated weights for policy 1, policy_version 64850 (0.0008) -[2023-10-10 15:13:06,824][76542] Updated weights for policy 1, policy_version 64860 (0.0008) -[2023-10-10 15:13:07,727][76543] Updated weights for policy 0, policy_version 64963 (0.0009) -[2023-10-10 15:13:08,094][76543] Updated weights for policy 0, policy_version 64973 (0.0009) -[2023-10-10 15:13:08,454][76543] Updated weights for policy 0, policy_version 64983 (0.0010) -[2023-10-10 15:13:10,562][76542] Updated weights for policy 1, policy_version 64870 (0.0009) -[2023-10-10 15:13:10,933][76542] Updated weights for policy 1, policy_version 64880 (0.0008) -[2023-10-10 15:13:11,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 132972544. Throughput: 0: 1843.8, 1: 1818.4. Samples: 33254550. Policy #0 lag: (min: 26.0, avg: 28.0, max: 56.0) -[2023-10-10 15:13:11,077][75634] Avg episode reward: [(0, '33.370'), (1, '38.730')] -[2023-10-10 15:13:11,299][76542] Updated weights for policy 1, policy_version 64890 (0.0009) -[2023-10-10 15:13:12,092][76543] Updated weights for policy 0, policy_version 64993 (0.0008) -[2023-10-10 15:13:12,463][76543] Updated weights for policy 0, policy_version 65003 (0.0008) -[2023-10-10 15:13:12,830][76543] Updated weights for policy 0, policy_version 65013 (0.0008) -[2023-10-10 15:13:13,205][76543] Updated weights for policy 0, policy_version 65023 (0.0009) -[2023-10-10 15:13:14,957][76542] Updated weights for policy 1, policy_version 64900 (0.0010) -[2023-10-10 15:13:15,331][76542] Updated weights for policy 1, policy_version 64910 (0.0008) -[2023-10-10 15:13:15,713][76542] Updated weights for policy 1, policy_version 64920 (0.0009) -[2023-10-10 15:13:16,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 133070848. Throughput: 0: 1845.5, 1: 1819.1. Samples: 33276376. Policy #0 lag: (min: 26.0, avg: 28.0, max: 56.0) -[2023-10-10 15:13:16,076][75634] Avg episode reward: [(0, '34.510'), (1, '37.250')] -[2023-10-10 15:13:16,869][76543] Updated weights for policy 0, policy_version 65033 (0.0008) -[2023-10-10 15:13:17,237][76543] Updated weights for policy 0, policy_version 65043 (0.0007) -[2023-10-10 15:13:17,607][76543] Updated weights for policy 0, policy_version 65053 (0.0009) -[2023-10-10 15:13:19,480][76542] Updated weights for policy 1, policy_version 64930 (0.0010) -[2023-10-10 15:13:19,844][76542] Updated weights for policy 1, policy_version 64940 (0.0008) -[2023-10-10 15:13:20,206][76542] Updated weights for policy 1, policy_version 64950 (0.0008) -[2023-10-10 15:13:20,577][76542] Updated weights for policy 1, policy_version 64960 (0.0007) -[2023-10-10 15:13:21,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 133136384. Throughput: 0: 1845.6, 1: 1812.3. Samples: 33287298. Policy #0 lag: (min: 26.0, avg: 28.0, max: 56.0) -[2023-10-10 15:13:21,076][75634] Avg episode reward: [(0, '35.840'), (1, '33.020')] -[2023-10-10 15:13:21,272][76543] Updated weights for policy 0, policy_version 65063 (0.0010) -[2023-10-10 15:13:21,643][76543] Updated weights for policy 0, policy_version 65073 (0.0010) -[2023-10-10 15:13:22,007][76543] Updated weights for policy 0, policy_version 65083 (0.0007) -[2023-10-10 15:13:24,265][76542] Updated weights for policy 1, policy_version 64970 (0.0008) -[2023-10-10 15:13:24,628][76542] Updated weights for policy 1, policy_version 64980 (0.0008) -[2023-10-10 15:13:24,996][76542] Updated weights for policy 1, policy_version 64990 (0.0008) -[2023-10-10 15:13:25,666][76543] Updated weights for policy 0, policy_version 65093 (0.0008) -[2023-10-10 15:13:26,034][76543] Updated weights for policy 0, policy_version 65103 (0.0007) -[2023-10-10 15:13:26,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 133201920. Throughput: 0: 1839.1, 1: 1816.6. Samples: 33309052. Policy #0 lag: (min: 26.0, avg: 28.0, max: 56.0) -[2023-10-10 15:13:26,076][75634] Avg episode reward: [(0, '34.570'), (1, '34.970')] -[2023-10-10 15:13:26,406][76543] Updated weights for policy 0, policy_version 65113 (0.0007) -[2023-10-10 15:13:28,678][76542] Updated weights for policy 1, policy_version 65000 (0.0009) -[2023-10-10 15:13:29,047][76542] Updated weights for policy 1, policy_version 65010 (0.0011) -[2023-10-10 15:13:29,417][76542] Updated weights for policy 1, policy_version 65020 (0.0010) -[2023-10-10 15:13:29,975][76543] Updated weights for policy 0, policy_version 65123 (0.0009) -[2023-10-10 15:13:30,340][76543] Updated weights for policy 0, policy_version 65133 (0.0007) -[2023-10-10 15:13:30,713][76543] Updated weights for policy 0, policy_version 65143 (0.0009) -[2023-10-10 15:13:31,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 133300224. Throughput: 0: 1830.3, 1: 1807.3. Samples: 33331094. Policy #0 lag: (min: 26.0, avg: 28.0, max: 56.0) -[2023-10-10 15:13:31,077][75634] Avg episode reward: [(0, '34.950'), (1, '39.310')] -[2023-10-10 15:13:33,030][76542] Updated weights for policy 1, policy_version 65030 (0.0008) -[2023-10-10 15:13:33,396][76542] Updated weights for policy 1, policy_version 65040 (0.0009) -[2023-10-10 15:13:33,766][76542] Updated weights for policy 1, policy_version 65050 (0.0008) -[2023-10-10 15:13:34,186][76543] Updated weights for policy 0, policy_version 65153 (0.0010) -[2023-10-10 15:13:34,553][76543] Updated weights for policy 0, policy_version 65163 (0.0011) -[2023-10-10 15:13:34,928][76543] Updated weights for policy 0, policy_version 65173 (0.0009) -[2023-10-10 15:13:35,305][76543] Updated weights for policy 0, policy_version 65183 (0.0007) -[2023-10-10 15:13:36,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 133365760. Throughput: 0: 1846.1, 1: 1812.5. Samples: 33342000. Policy #0 lag: (min: 26.0, avg: 28.0, max: 56.0) -[2023-10-10 15:13:36,076][75634] Avg episode reward: [(0, '36.090'), (1, '40.400')] -[2023-10-10 15:13:37,408][76542] Updated weights for policy 1, policy_version 65060 (0.0008) -[2023-10-10 15:13:37,769][76542] Updated weights for policy 1, policy_version 65070 (0.0008) -[2023-10-10 15:13:38,136][76542] Updated weights for policy 1, policy_version 65080 (0.0007) -[2023-10-10 15:13:39,135][76543] Updated weights for policy 0, policy_version 65193 (0.0007) -[2023-10-10 15:13:39,507][76543] Updated weights for policy 0, policy_version 65203 (0.0007) -[2023-10-10 15:13:39,881][76543] Updated weights for policy 0, policy_version 65213 (0.0009) -[2023-10-10 15:13:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 133431296. Throughput: 0: 1828.9, 1: 1810.5. Samples: 33363976. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:13:41,077][75634] Avg episode reward: [(0, '36.510'), (1, '33.520')] -[2023-10-10 15:13:41,804][76542] Updated weights for policy 1, policy_version 65090 (0.0009) -[2023-10-10 15:13:42,172][76542] Updated weights for policy 1, policy_version 65100 (0.0007) -[2023-10-10 15:13:42,529][76542] Updated weights for policy 1, policy_version 65110 (0.0008) -[2023-10-10 15:13:42,897][76542] Updated weights for policy 1, policy_version 65120 (0.0009) -[2023-10-10 15:13:43,647][76543] Updated weights for policy 0, policy_version 65223 (0.0007) -[2023-10-10 15:13:44,016][76543] Updated weights for policy 0, policy_version 65233 (0.0007) -[2023-10-10 15:13:44,383][76543] Updated weights for policy 0, policy_version 65243 (0.0009) -[2023-10-10 15:13:46,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 133496832. Throughput: 0: 1833.7, 1: 1801.0. Samples: 33385484. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:13:46,076][75634] Avg episode reward: [(0, '41.330'), (1, '35.540')] -[2023-10-10 15:13:46,712][76542] Updated weights for policy 1, policy_version 65130 (0.0007) -[2023-10-10 15:13:47,072][76542] Updated weights for policy 1, policy_version 65140 (0.0008) -[2023-10-10 15:13:47,449][76542] Updated weights for policy 1, policy_version 65150 (0.0008) -[2023-10-10 15:13:48,031][76543] Updated weights for policy 0, policy_version 65253 (0.0009) -[2023-10-10 15:13:48,410][76543] Updated weights for policy 0, policy_version 65263 (0.0008) -[2023-10-10 15:13:48,782][76543] Updated weights for policy 0, policy_version 65273 (0.0009) -[2023-10-10 15:13:51,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 133562368. Throughput: 0: 1828.8, 1: 1799.6. Samples: 33396566. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:13:51,077][75634] Avg episode reward: [(0, '40.390'), (1, '38.140')] -[2023-10-10 15:13:51,281][76542] Updated weights for policy 1, policy_version 65160 (0.0010) -[2023-10-10 15:13:51,653][76542] Updated weights for policy 1, policy_version 65170 (0.0011) -[2023-10-10 15:13:52,025][76542] Updated weights for policy 1, policy_version 65180 (0.0007) -[2023-10-10 15:13:52,576][76543] Updated weights for policy 0, policy_version 65283 (0.0008) -[2023-10-10 15:13:52,948][76543] Updated weights for policy 0, policy_version 65293 (0.0010) -[2023-10-10 15:13:53,316][76543] Updated weights for policy 0, policy_version 65303 (0.0008) -[2023-10-10 15:13:55,650][76542] Updated weights for policy 1, policy_version 65190 (0.0009) -[2023-10-10 15:13:56,014][76542] Updated weights for policy 1, policy_version 65200 (0.0007) -[2023-10-10 15:13:56,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 133627904. Throughput: 0: 1829.9, 1: 1801.6. Samples: 33417966. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:13:56,077][75634] Avg episode reward: [(0, '35.460'), (1, '35.110')] -[2023-10-10 15:13:56,389][76542] Updated weights for policy 1, policy_version 65210 (0.0010) -[2023-10-10 15:13:57,074][76543] Updated weights for policy 0, policy_version 65313 (0.0009) -[2023-10-10 15:13:57,439][76543] Updated weights for policy 0, policy_version 65323 (0.0008) -[2023-10-10 15:13:57,809][76543] Updated weights for policy 0, policy_version 65333 (0.0007) -[2023-10-10 15:13:58,183][76543] Updated weights for policy 0, policy_version 65343 (0.0007) -[2023-10-10 15:14:00,028][76542] Updated weights for policy 1, policy_version 65220 (0.0008) -[2023-10-10 15:14:00,402][76542] Updated weights for policy 1, policy_version 65230 (0.0007) -[2023-10-10 15:14:00,775][76542] Updated weights for policy 1, policy_version 65240 (0.0009) -[2023-10-10 15:14:01,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 133726208. Throughput: 0: 1823.2, 1: 1809.2. Samples: 33439832. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:14:01,076][75634] Avg episode reward: [(0, '34.380'), (1, '33.390')] -[2023-10-10 15:14:01,831][76543] Updated weights for policy 0, policy_version 65353 (0.0007) -[2023-10-10 15:14:02,207][76543] Updated weights for policy 0, policy_version 65363 (0.0009) -[2023-10-10 15:14:02,573][76543] Updated weights for policy 0, policy_version 65373 (0.0009) -[2023-10-10 15:14:04,474][76542] Updated weights for policy 1, policy_version 65250 (0.0010) -[2023-10-10 15:14:04,842][76542] Updated weights for policy 1, policy_version 65260 (0.0011) -[2023-10-10 15:14:05,208][76542] Updated weights for policy 1, policy_version 65270 (0.0010) -[2023-10-10 15:14:05,574][76542] Updated weights for policy 1, policy_version 65280 (0.0007) -[2023-10-10 15:14:06,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 133791744. Throughput: 0: 1826.8, 1: 1814.0. Samples: 33451134. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:14:06,077][75634] Avg episode reward: [(0, '35.430'), (1, '33.020')] -[2023-10-10 15:14:06,121][76543] Updated weights for policy 0, policy_version 65383 (0.0007) -[2023-10-10 15:14:06,494][76543] Updated weights for policy 0, policy_version 65393 (0.0007) -[2023-10-10 15:14:06,868][76543] Updated weights for policy 0, policy_version 65403 (0.0008) -[2023-10-10 15:14:09,411][76542] Updated weights for policy 1, policy_version 65290 (0.0009) -[2023-10-10 15:14:09,782][76542] Updated weights for policy 1, policy_version 65300 (0.0009) -[2023-10-10 15:14:10,153][76542] Updated weights for policy 1, policy_version 65310 (0.0007) -[2023-10-10 15:14:10,548][76543] Updated weights for policy 0, policy_version 65413 (0.0008) -[2023-10-10 15:14:10,905][76543] Updated weights for policy 0, policy_version 65423 (0.0008) -[2023-10-10 15:14:11,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 133857280. Throughput: 0: 1827.6, 1: 1815.9. Samples: 33473008. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:14:11,076][75634] Avg episode reward: [(0, '35.210'), (1, '37.070')] -[2023-10-10 15:14:11,285][76543] Updated weights for policy 0, policy_version 65433 (0.0007) -[2023-10-10 15:14:13,794][76542] Updated weights for policy 1, policy_version 65320 (0.0008) -[2023-10-10 15:14:14,148][76542] Updated weights for policy 1, policy_version 65330 (0.0007) -[2023-10-10 15:14:14,510][76542] Updated weights for policy 1, policy_version 65340 (0.0008) -[2023-10-10 15:14:14,972][76543] Updated weights for policy 0, policy_version 65443 (0.0009) -[2023-10-10 15:14:15,344][76543] Updated weights for policy 0, policy_version 65453 (0.0008) -[2023-10-10 15:14:15,709][76543] Updated weights for policy 0, policy_version 65463 (0.0008) -[2023-10-10 15:14:16,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 133955584. Throughput: 0: 1825.8, 1: 1812.5. Samples: 33494820. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:14:16,077][75634] Avg episode reward: [(0, '35.540'), (1, '36.290')] -[2023-10-10 15:14:18,331][76542] Updated weights for policy 1, policy_version 65350 (0.0008) -[2023-10-10 15:14:18,696][76542] Updated weights for policy 1, policy_version 65360 (0.0010) -[2023-10-10 15:14:19,063][76542] Updated weights for policy 1, policy_version 65370 (0.0007) -[2023-10-10 15:14:19,410][76543] Updated weights for policy 0, policy_version 65473 (0.0011) -[2023-10-10 15:14:19,786][76543] Updated weights for policy 0, policy_version 65483 (0.0007) -[2023-10-10 15:14:20,151][76543] Updated weights for policy 0, policy_version 65493 (0.0010) -[2023-10-10 15:14:20,527][76543] Updated weights for policy 0, policy_version 65503 (0.0009) -[2023-10-10 15:14:21,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 134021120. Throughput: 0: 1819.3, 1: 1818.0. Samples: 33505678. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:14:21,077][75634] Avg episode reward: [(0, '30.870'), (1, '36.530')] -[2023-10-10 15:14:22,827][76542] Updated weights for policy 1, policy_version 65380 (0.0009) -[2023-10-10 15:14:23,200][76542] Updated weights for policy 1, policy_version 65390 (0.0010) -[2023-10-10 15:14:23,565][76542] Updated weights for policy 1, policy_version 65400 (0.0010) -[2023-10-10 15:14:24,231][76543] Updated weights for policy 0, policy_version 65513 (0.0009) -[2023-10-10 15:14:24,598][76543] Updated weights for policy 0, policy_version 65523 (0.0010) -[2023-10-10 15:14:24,967][76543] Updated weights for policy 0, policy_version 65533 (0.0008) -[2023-10-10 15:14:26,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 134086656. Throughput: 0: 1825.5, 1: 1803.9. Samples: 33527298. Policy #0 lag: (min: 5.0, avg: 6.4, max: 31.0) -[2023-10-10 15:14:26,077][75634] Avg episode reward: [(0, '29.800'), (1, '35.900')] -[2023-10-10 15:14:27,416][76542] Updated weights for policy 1, policy_version 65410 (0.0010) -[2023-10-10 15:14:27,782][76542] Updated weights for policy 1, policy_version 65420 (0.0007) -[2023-10-10 15:14:28,150][76542] Updated weights for policy 1, policy_version 65430 (0.0009) -[2023-10-10 15:14:28,516][76542] Updated weights for policy 1, policy_version 65440 (0.0010) -[2023-10-10 15:14:28,714][76543] Updated weights for policy 0, policy_version 65543 (0.0007) -[2023-10-10 15:14:29,083][76543] Updated weights for policy 0, policy_version 65553 (0.0008) -[2023-10-10 15:14:29,455][76543] Updated weights for policy 0, policy_version 65563 (0.0010) -[2023-10-10 15:14:31,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 134152192. Throughput: 0: 1828.8, 1: 1814.4. Samples: 33549430. Policy #0 lag: (min: 5.0, avg: 6.4, max: 31.0) -[2023-10-10 15:14:31,076][75634] Avg episode reward: [(0, '35.300'), (1, '37.270')] -[2023-10-10 15:14:31,084][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000065568_67141632.pth... -[2023-10-10 15:14:31,084][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000065440_67010560.pth... -[2023-10-10 15:14:31,120][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000063872_65404928.pth -[2023-10-10 15:14:31,121][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000063744_65273856.pth -[2023-10-10 15:14:32,120][76542] Updated weights for policy 1, policy_version 65450 (0.0007) -[2023-10-10 15:14:32,490][76542] Updated weights for policy 1, policy_version 65460 (0.0008) -[2023-10-10 15:14:32,858][76542] Updated weights for policy 1, policy_version 65470 (0.0010) -[2023-10-10 15:14:33,101][76543] Updated weights for policy 0, policy_version 65573 (0.0008) -[2023-10-10 15:14:33,474][76543] Updated weights for policy 0, policy_version 65583 (0.0010) -[2023-10-10 15:14:33,859][76543] Updated weights for policy 0, policy_version 65593 (0.0010) -[2023-10-10 15:14:36,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 134217728. Throughput: 0: 1821.5, 1: 1819.4. Samples: 33560406. Policy #0 lag: (min: 5.0, avg: 6.4, max: 31.0) -[2023-10-10 15:14:36,076][75634] Avg episode reward: [(0, '35.960'), (1, '31.610')] -[2023-10-10 15:14:36,473][76542] Updated weights for policy 1, policy_version 65480 (0.0008) -[2023-10-10 15:14:36,846][76542] Updated weights for policy 1, policy_version 65490 (0.0008) -[2023-10-10 15:14:37,214][76542] Updated weights for policy 1, policy_version 65500 (0.0008) -[2023-10-10 15:14:37,529][76543] Updated weights for policy 0, policy_version 65603 (0.0010) -[2023-10-10 15:14:37,892][76543] Updated weights for policy 0, policy_version 65613 (0.0007) -[2023-10-10 15:14:38,267][76543] Updated weights for policy 0, policy_version 65623 (0.0010) -[2023-10-10 15:14:40,926][76542] Updated weights for policy 1, policy_version 65510 (0.0007) -[2023-10-10 15:14:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 134283264. Throughput: 0: 1824.2, 1: 1819.9. Samples: 33581950. Policy #0 lag: (min: 5.0, avg: 6.4, max: 31.0) -[2023-10-10 15:14:41,076][75634] Avg episode reward: [(0, '36.180'), (1, '33.320')] -[2023-10-10 15:14:41,302][76542] Updated weights for policy 1, policy_version 65520 (0.0008) -[2023-10-10 15:14:41,670][76542] Updated weights for policy 1, policy_version 65530 (0.0008) -[2023-10-10 15:14:41,872][76543] Updated weights for policy 0, policy_version 65633 (0.0007) -[2023-10-10 15:14:42,250][76543] Updated weights for policy 0, policy_version 65643 (0.0007) -[2023-10-10 15:14:42,626][76543] Updated weights for policy 0, policy_version 65653 (0.0007) -[2023-10-10 15:14:42,995][76543] Updated weights for policy 0, policy_version 65663 (0.0008) -[2023-10-10 15:14:45,320][76542] Updated weights for policy 1, policy_version 65540 (0.0009) -[2023-10-10 15:14:45,695][76542] Updated weights for policy 1, policy_version 65550 (0.0011) -[2023-10-10 15:14:46,066][76542] Updated weights for policy 1, policy_version 65560 (0.0011) -[2023-10-10 15:14:46,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 134348800. Throughput: 0: 1828.5, 1: 1821.6. Samples: 33604088. Policy #0 lag: (min: 5.0, avg: 6.4, max: 31.0) -[2023-10-10 15:14:46,077][75634] Avg episode reward: [(0, '35.510'), (1, '37.630')] -[2023-10-10 15:14:46,674][76543] Updated weights for policy 0, policy_version 65673 (0.0009) -[2023-10-10 15:14:47,044][76543] Updated weights for policy 0, policy_version 65683 (0.0008) -[2023-10-10 15:14:47,415][76543] Updated weights for policy 0, policy_version 65693 (0.0008) -[2023-10-10 15:14:49,724][76542] Updated weights for policy 1, policy_version 65570 (0.0008) -[2023-10-10 15:14:50,086][76542] Updated weights for policy 1, policy_version 65580 (0.0011) -[2023-10-10 15:14:50,450][76542] Updated weights for policy 1, policy_version 65590 (0.0010) -[2023-10-10 15:14:50,820][76542] Updated weights for policy 1, policy_version 65600 (0.0010) -[2023-10-10 15:14:50,949][76543] Updated weights for policy 0, policy_version 65703 (0.0009) -[2023-10-10 15:14:51,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 134447104. Throughput: 0: 1826.4, 1: 1808.7. Samples: 33614710. Policy #0 lag: (min: 5.0, avg: 6.4, max: 31.0) -[2023-10-10 15:14:51,076][75634] Avg episode reward: [(0, '40.190'), (1, '34.610')] -[2023-10-10 15:14:51,327][76543] Updated weights for policy 0, policy_version 65713 (0.0011) -[2023-10-10 15:14:51,698][76543] Updated weights for policy 0, policy_version 65723 (0.0010) -[2023-10-10 15:14:54,449][76542] Updated weights for policy 1, policy_version 65610 (0.0010) -[2023-10-10 15:14:54,813][76542] Updated weights for policy 1, policy_version 65620 (0.0008) -[2023-10-10 15:14:55,178][76542] Updated weights for policy 1, policy_version 65630 (0.0009) -[2023-10-10 15:14:55,412][76543] Updated weights for policy 0, policy_version 65733 (0.0008) -[2023-10-10 15:14:55,780][76543] Updated weights for policy 0, policy_version 65743 (0.0009) -[2023-10-10 15:14:56,076][75634] Fps is (10 sec: 16384.5, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 134512640. Throughput: 0: 1829.7, 1: 1811.1. Samples: 33636844. Policy #0 lag: (min: 5.0, avg: 6.4, max: 31.0) -[2023-10-10 15:14:56,076][75634] Avg episode reward: [(0, '38.920'), (1, '32.150')] -[2023-10-10 15:14:56,151][76543] Updated weights for policy 0, policy_version 65753 (0.0007) -[2023-10-10 15:14:58,895][76542] Updated weights for policy 1, policy_version 65640 (0.0007) -[2023-10-10 15:14:59,262][76542] Updated weights for policy 1, policy_version 65650 (0.0010) -[2023-10-10 15:14:59,636][76542] Updated weights for policy 1, policy_version 65660 (0.0008) -[2023-10-10 15:14:59,642][76543] Updated weights for policy 0, policy_version 65763 (0.0008) -[2023-10-10 15:15:00,016][76543] Updated weights for policy 0, policy_version 65773 (0.0007) -[2023-10-10 15:15:00,396][76543] Updated weights for policy 0, policy_version 65783 (0.0008) -[2023-10-10 15:15:01,076][75634] Fps is (10 sec: 16383.3, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 134610944. Throughput: 0: 1822.0, 1: 1810.3. Samples: 33658274. Policy #0 lag: (min: 5.0, avg: 6.4, max: 31.0) -[2023-10-10 15:15:01,078][75634] Avg episode reward: [(0, '38.000'), (1, '34.880')] -[2023-10-10 15:15:03,412][76542] Updated weights for policy 1, policy_version 65670 (0.0010) -[2023-10-10 15:15:03,781][76542] Updated weights for policy 1, policy_version 65680 (0.0007) -[2023-10-10 15:15:04,011][76543] Updated weights for policy 0, policy_version 65793 (0.0008) -[2023-10-10 15:15:04,153][76542] Updated weights for policy 1, policy_version 65690 (0.0007) -[2023-10-10 15:15:04,384][76543] Updated weights for policy 0, policy_version 65803 (0.0008) -[2023-10-10 15:15:04,752][76543] Updated weights for policy 0, policy_version 65813 (0.0010) -[2023-10-10 15:15:05,125][76543] Updated weights for policy 0, policy_version 65823 (0.0007) -[2023-10-10 15:15:06,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 134676480. Throughput: 0: 1839.0, 1: 1816.2. Samples: 33670162. Policy #0 lag: (min: 5.0, avg: 6.4, max: 31.0) -[2023-10-10 15:15:06,076][75634] Avg episode reward: [(0, '34.300'), (1, '35.420')] -[2023-10-10 15:15:07,913][76542] Updated weights for policy 1, policy_version 65700 (0.0009) -[2023-10-10 15:15:08,282][76542] Updated weights for policy 1, policy_version 65710 (0.0011) -[2023-10-10 15:15:08,650][76542] Updated weights for policy 1, policy_version 65720 (0.0008) -[2023-10-10 15:15:08,743][76543] Updated weights for policy 0, policy_version 65833 (0.0009) -[2023-10-10 15:15:09,117][76543] Updated weights for policy 0, policy_version 65843 (0.0009) -[2023-10-10 15:15:09,484][76543] Updated weights for policy 0, policy_version 65853 (0.0007) -[2023-10-10 15:15:11,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 134742016. Throughput: 0: 1823.4, 1: 1816.2. Samples: 33691078. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 15:15:11,077][75634] Avg episode reward: [(0, '33.340'), (1, '35.010')] -[2023-10-10 15:15:12,368][76542] Updated weights for policy 1, policy_version 65730 (0.0008) -[2023-10-10 15:15:12,738][76542] Updated weights for policy 1, policy_version 65740 (0.0009) -[2023-10-10 15:15:13,012][76543] Updated weights for policy 0, policy_version 65863 (0.0008) -[2023-10-10 15:15:13,105][76542] Updated weights for policy 1, policy_version 65750 (0.0009) -[2023-10-10 15:15:13,396][76543] Updated weights for policy 0, policy_version 65873 (0.0007) -[2023-10-10 15:15:13,470][76542] Updated weights for policy 1, policy_version 65760 (0.0007) -[2023-10-10 15:15:13,760][76543] Updated weights for policy 0, policy_version 65883 (0.0009) -[2023-10-10 15:15:16,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 134807552. Throughput: 0: 1830.4, 1: 1812.0. Samples: 33713342. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 15:15:16,077][75634] Avg episode reward: [(0, '34.100'), (1, '35.950')] -[2023-10-10 15:15:17,137][76542] Updated weights for policy 1, policy_version 65770 (0.0010) -[2023-10-10 15:15:17,506][76542] Updated weights for policy 1, policy_version 65780 (0.0010) -[2023-10-10 15:15:17,651][76543] Updated weights for policy 0, policy_version 65893 (0.0008) -[2023-10-10 15:15:17,869][76542] Updated weights for policy 1, policy_version 65790 (0.0009) -[2023-10-10 15:15:18,033][76543] Updated weights for policy 0, policy_version 65903 (0.0010) -[2023-10-10 15:15:18,405][76543] Updated weights for policy 0, policy_version 65913 (0.0009) -[2023-10-10 15:15:21,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 134873088. Throughput: 0: 1817.2, 1: 1813.4. Samples: 33723784. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 15:15:21,076][75634] Avg episode reward: [(0, '33.800'), (1, '38.030')] -[2023-10-10 15:15:21,675][76542] Updated weights for policy 1, policy_version 65800 (0.0008) -[2023-10-10 15:15:22,054][76542] Updated weights for policy 1, policy_version 65810 (0.0007) -[2023-10-10 15:15:22,078][76543] Updated weights for policy 0, policy_version 65923 (0.0007) -[2023-10-10 15:15:22,415][76542] Updated weights for policy 1, policy_version 65820 (0.0008) -[2023-10-10 15:15:22,453][76543] Updated weights for policy 0, policy_version 65933 (0.0007) -[2023-10-10 15:15:22,822][76543] Updated weights for policy 0, policy_version 65943 (0.0007) -[2023-10-10 15:15:26,053][76542] Updated weights for policy 1, policy_version 65830 (0.0009) -[2023-10-10 15:15:26,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 134938624. Throughput: 0: 1829.6, 1: 1813.1. Samples: 33745870. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 15:15:26,076][75634] Avg episode reward: [(0, '35.630'), (1, '36.800')] -[2023-10-10 15:15:26,384][76543] Updated weights for policy 0, policy_version 65953 (0.0009) -[2023-10-10 15:15:26,420][76542] Updated weights for policy 1, policy_version 65840 (0.0008) -[2023-10-10 15:15:26,759][76543] Updated weights for policy 0, policy_version 65963 (0.0007) -[2023-10-10 15:15:26,791][76542] Updated weights for policy 1, policy_version 65850 (0.0008) -[2023-10-10 15:15:27,122][76543] Updated weights for policy 0, policy_version 65973 (0.0009) -[2023-10-10 15:15:27,502][76543] Updated weights for policy 0, policy_version 65983 (0.0007) -[2023-10-10 15:15:30,497][76542] Updated weights for policy 1, policy_version 65860 (0.0008) -[2023-10-10 15:15:30,872][76542] Updated weights for policy 1, policy_version 65870 (0.0009) -[2023-10-10 15:15:31,016][76543] Updated weights for policy 0, policy_version 65993 (0.0007) -[2023-10-10 15:15:31,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 135004160. Throughput: 0: 1841.2, 1: 1812.8. Samples: 33768518. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 15:15:31,076][75634] Avg episode reward: [(0, '34.160'), (1, '33.700')] -[2023-10-10 15:15:31,238][76542] Updated weights for policy 1, policy_version 65880 (0.0008) -[2023-10-10 15:15:31,389][76543] Updated weights for policy 0, policy_version 66003 (0.0008) -[2023-10-10 15:15:31,754][76543] Updated weights for policy 0, policy_version 66013 (0.0008) -[2023-10-10 15:15:34,935][76542] Updated weights for policy 1, policy_version 65890 (0.0008) -[2023-10-10 15:15:35,291][76542] Updated weights for policy 1, policy_version 65900 (0.0008) -[2023-10-10 15:15:35,439][76543] Updated weights for policy 0, policy_version 66023 (0.0009) -[2023-10-10 15:15:35,659][76542] Updated weights for policy 1, policy_version 65910 (0.0010) -[2023-10-10 15:15:35,815][76543] Updated weights for policy 0, policy_version 66033 (0.0009) -[2023-10-10 15:15:36,026][76542] Updated weights for policy 1, policy_version 65920 (0.0009) -[2023-10-10 15:15:36,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 135102464. Throughput: 0: 1841.6, 1: 1810.6. Samples: 33779062. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 15:15:36,076][75634] Avg episode reward: [(0, '37.930'), (1, '32.780')] -[2023-10-10 15:15:36,180][76543] Updated weights for policy 0, policy_version 66043 (0.0008) -[2023-10-10 15:15:39,647][76542] Updated weights for policy 1, policy_version 65930 (0.0008) -[2023-10-10 15:15:39,881][76543] Updated weights for policy 0, policy_version 66053 (0.0008) -[2023-10-10 15:15:40,011][76542] Updated weights for policy 1, policy_version 65940 (0.0008) -[2023-10-10 15:15:40,240][76543] Updated weights for policy 0, policy_version 66063 (0.0009) -[2023-10-10 15:15:40,374][76542] Updated weights for policy 1, policy_version 65950 (0.0007) -[2023-10-10 15:15:40,605][76543] Updated weights for policy 0, policy_version 66073 (0.0009) -[2023-10-10 15:15:41,076][75634] Fps is (10 sec: 19660.4, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 135200768. Throughput: 0: 1830.2, 1: 1820.3. Samples: 33801116. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 15:15:41,077][75634] Avg episode reward: [(0, '34.830'), (1, '33.360')] -[2023-10-10 15:15:44,149][76542] Updated weights for policy 1, policy_version 65960 (0.0007) -[2023-10-10 15:15:44,383][76543] Updated weights for policy 0, policy_version 66083 (0.0010) -[2023-10-10 15:15:44,512][76542] Updated weights for policy 1, policy_version 65970 (0.0008) -[2023-10-10 15:15:44,754][76543] Updated weights for policy 0, policy_version 66093 (0.0009) -[2023-10-10 15:15:44,875][76542] Updated weights for policy 1, policy_version 65980 (0.0009) -[2023-10-10 15:15:45,118][76543] Updated weights for policy 0, policy_version 66103 (0.0007) -[2023-10-10 15:15:46,076][75634] Fps is (10 sec: 16383.7, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 135266304. Throughput: 0: 1819.7, 1: 1814.2. Samples: 33821800. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 15:15:46,077][75634] Avg episode reward: [(0, '35.870'), (1, '33.730')] -[2023-10-10 15:15:48,596][76542] Updated weights for policy 1, policy_version 65990 (0.0009) -[2023-10-10 15:15:48,962][76542] Updated weights for policy 1, policy_version 66000 (0.0008) -[2023-10-10 15:15:49,048][76543] Updated weights for policy 0, policy_version 66113 (0.0007) -[2023-10-10 15:15:49,331][76542] Updated weights for policy 1, policy_version 66010 (0.0007) -[2023-10-10 15:15:49,419][76543] Updated weights for policy 0, policy_version 66123 (0.0010) -[2023-10-10 15:15:49,788][76543] Updated weights for policy 0, policy_version 66133 (0.0010) -[2023-10-10 15:15:50,152][76543] Updated weights for policy 0, policy_version 66143 (0.0009) -[2023-10-10 15:15:51,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 135331840. Throughput: 0: 1817.6, 1: 1816.0. Samples: 33833674. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 15:15:51,076][75634] Avg episode reward: [(0, '38.260'), (1, '34.320')] -[2023-10-10 15:15:53,031][76542] Updated weights for policy 1, policy_version 66020 (0.0009) -[2023-10-10 15:15:53,399][76542] Updated weights for policy 1, policy_version 66030 (0.0009) -[2023-10-10 15:15:53,765][76542] Updated weights for policy 1, policy_version 66040 (0.0010) -[2023-10-10 15:15:53,867][76543] Updated weights for policy 0, policy_version 66153 (0.0008) -[2023-10-10 15:15:54,236][76543] Updated weights for policy 0, policy_version 66163 (0.0009) -[2023-10-10 15:15:54,607][76543] Updated weights for policy 0, policy_version 66173 (0.0009) -[2023-10-10 15:15:56,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 135397376. Throughput: 0: 1821.2, 1: 1810.1. Samples: 33854486. Policy #0 lag: (min: 0.0, avg: 24.4, max: 32.0) -[2023-10-10 15:15:56,077][75634] Avg episode reward: [(0, '38.340'), (1, '34.060')] -[2023-10-10 15:15:57,422][76542] Updated weights for policy 1, policy_version 66050 (0.0010) -[2023-10-10 15:15:57,792][76542] Updated weights for policy 1, policy_version 66060 (0.0010) -[2023-10-10 15:15:58,169][76542] Updated weights for policy 1, policy_version 66070 (0.0010) -[2023-10-10 15:15:58,250][76543] Updated weights for policy 0, policy_version 66183 (0.0008) -[2023-10-10 15:15:58,533][76542] Updated weights for policy 1, policy_version 66080 (0.0008) -[2023-10-10 15:15:58,629][76543] Updated weights for policy 0, policy_version 66193 (0.0009) -[2023-10-10 15:15:58,999][76543] Updated weights for policy 0, policy_version 66203 (0.0009) -[2023-10-10 15:16:01,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 135462912. Throughput: 0: 1821.0, 1: 1809.6. Samples: 33876718. Policy #0 lag: (min: 0.0, avg: 24.4, max: 32.0) -[2023-10-10 15:16:01,077][75634] Avg episode reward: [(0, '40.750'), (1, '34.940')] -[2023-10-10 15:16:02,268][76542] Updated weights for policy 1, policy_version 66090 (0.0011) -[2023-10-10 15:16:02,633][76542] Updated weights for policy 1, policy_version 66100 (0.0009) -[2023-10-10 15:16:02,720][76543] Updated weights for policy 0, policy_version 66213 (0.0007) -[2023-10-10 15:16:02,999][76542] Updated weights for policy 1, policy_version 66110 (0.0008) -[2023-10-10 15:16:03,078][76543] Updated weights for policy 0, policy_version 66223 (0.0008) -[2023-10-10 15:16:03,446][76543] Updated weights for policy 0, policy_version 66233 (0.0011) -[2023-10-10 15:16:06,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 135528448. Throughput: 0: 1827.7, 1: 1806.7. Samples: 33887332. Policy #0 lag: (min: 0.0, avg: 24.4, max: 32.0) -[2023-10-10 15:16:06,076][75634] Avg episode reward: [(0, '38.330'), (1, '38.560')] -[2023-10-10 15:16:06,742][76542] Updated weights for policy 1, policy_version 66120 (0.0007) -[2023-10-10 15:16:07,112][76542] Updated weights for policy 1, policy_version 66130 (0.0008) -[2023-10-10 15:16:07,182][76543] Updated weights for policy 0, policy_version 66243 (0.0008) -[2023-10-10 15:16:07,473][76542] Updated weights for policy 1, policy_version 66140 (0.0008) -[2023-10-10 15:16:07,550][76543] Updated weights for policy 0, policy_version 66253 (0.0008) -[2023-10-10 15:16:07,922][76543] Updated weights for policy 0, policy_version 66263 (0.0008) -[2023-10-10 15:16:11,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 135593984. Throughput: 0: 1822.2, 1: 1813.0. Samples: 33909454. Policy #0 lag: (min: 0.0, avg: 24.4, max: 32.0) -[2023-10-10 15:16:11,076][75634] Avg episode reward: [(0, '40.540'), (1, '37.330')] -[2023-10-10 15:16:11,095][76542] Updated weights for policy 1, policy_version 66150 (0.0009) -[2023-10-10 15:16:11,454][76542] Updated weights for policy 1, policy_version 66160 (0.0007) -[2023-10-10 15:16:11,685][76543] Updated weights for policy 0, policy_version 66273 (0.0009) -[2023-10-10 15:16:11,829][76542] Updated weights for policy 1, policy_version 66170 (0.0007) -[2023-10-10 15:16:12,052][76543] Updated weights for policy 0, policy_version 66283 (0.0008) -[2023-10-10 15:16:12,424][76543] Updated weights for policy 0, policy_version 66293 (0.0009) -[2023-10-10 15:16:12,796][76543] Updated weights for policy 0, policy_version 66303 (0.0009) -[2023-10-10 15:16:15,423][76542] Updated weights for policy 1, policy_version 66180 (0.0007) -[2023-10-10 15:16:15,788][76542] Updated weights for policy 1, policy_version 66190 (0.0007) -[2023-10-10 15:16:16,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 135659520. Throughput: 0: 1808.4, 1: 1820.4. Samples: 33931818. Policy #0 lag: (min: 0.0, avg: 24.4, max: 32.0) -[2023-10-10 15:16:16,076][75634] Avg episode reward: [(0, '38.190'), (1, '38.080')] -[2023-10-10 15:16:16,152][76542] Updated weights for policy 1, policy_version 66200 (0.0007) -[2023-10-10 15:16:16,594][76543] Updated weights for policy 0, policy_version 66313 (0.0010) -[2023-10-10 15:16:16,962][76543] Updated weights for policy 0, policy_version 66323 (0.0010) -[2023-10-10 15:16:17,333][76543] Updated weights for policy 0, policy_version 66333 (0.0008) -[2023-10-10 15:16:19,745][76542] Updated weights for policy 1, policy_version 66210 (0.0008) -[2023-10-10 15:16:20,119][76542] Updated weights for policy 1, policy_version 66220 (0.0011) -[2023-10-10 15:16:20,482][76542] Updated weights for policy 1, policy_version 66230 (0.0008) -[2023-10-10 15:16:20,840][76542] Updated weights for policy 1, policy_version 66240 (0.0008) -[2023-10-10 15:16:21,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 135757824. Throughput: 0: 1805.4, 1: 1822.2. Samples: 33942304. Policy #0 lag: (min: 0.0, avg: 24.4, max: 32.0) -[2023-10-10 15:16:21,077][75634] Avg episode reward: [(0, '36.930'), (1, '34.000')] -[2023-10-10 15:16:21,108][76543] Updated weights for policy 0, policy_version 66343 (0.0009) -[2023-10-10 15:16:21,484][76543] Updated weights for policy 0, policy_version 66353 (0.0009) -[2023-10-10 15:16:21,864][76543] Updated weights for policy 0, policy_version 66363 (0.0007) -[2023-10-10 15:16:24,640][76542] Updated weights for policy 1, policy_version 66250 (0.0010) -[2023-10-10 15:16:25,009][76542] Updated weights for policy 1, policy_version 66260 (0.0008) -[2023-10-10 15:16:25,372][76542] Updated weights for policy 1, policy_version 66270 (0.0008) -[2023-10-10 15:16:25,420][76543] Updated weights for policy 0, policy_version 66373 (0.0007) -[2023-10-10 15:16:25,793][76543] Updated weights for policy 0, policy_version 66383 (0.0007) -[2023-10-10 15:16:26,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 135823360. Throughput: 0: 1806.9, 1: 1819.3. Samples: 33964290. Policy #0 lag: (min: 0.0, avg: 24.4, max: 32.0) -[2023-10-10 15:16:26,076][75634] Avg episode reward: [(0, '36.730'), (1, '36.670')] -[2023-10-10 15:16:26,157][76543] Updated weights for policy 0, policy_version 66393 (0.0007) -[2023-10-10 15:16:29,109][76542] Updated weights for policy 1, policy_version 66280 (0.0007) -[2023-10-10 15:16:29,481][76542] Updated weights for policy 1, policy_version 66290 (0.0010) -[2023-10-10 15:16:29,684][76543] Updated weights for policy 0, policy_version 66403 (0.0007) -[2023-10-10 15:16:29,844][76542] Updated weights for policy 1, policy_version 66300 (0.0009) -[2023-10-10 15:16:30,042][76543] Updated weights for policy 0, policy_version 66413 (0.0008) -[2023-10-10 15:16:30,420][76543] Updated weights for policy 0, policy_version 66423 (0.0009) -[2023-10-10 15:16:31,076][75634] Fps is (10 sec: 16383.8, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 135921664. Throughput: 0: 1816.5, 1: 1819.8. Samples: 33985432. Policy #0 lag: (min: 0.0, avg: 24.4, max: 32.0) -[2023-10-10 15:16:31,077][75634] Avg episode reward: [(0, '40.890'), (1, '37.450')] -[2023-10-10 15:16:31,087][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000066304_67895296.pth... -[2023-10-10 15:16:31,087][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000066432_68026368.pth... -[2023-10-10 15:16:31,117][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000064704_66256896.pth -[2023-10-10 15:16:31,126][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000064608_66158592.pth -[2023-10-10 15:16:33,601][76542] Updated weights for policy 1, policy_version 66310 (0.0007) -[2023-10-10 15:16:33,972][76542] Updated weights for policy 1, policy_version 66320 (0.0009) -[2023-10-10 15:16:34,095][76543] Updated weights for policy 0, policy_version 66433 (0.0008) -[2023-10-10 15:16:34,342][76542] Updated weights for policy 1, policy_version 66330 (0.0010) -[2023-10-10 15:16:34,465][76543] Updated weights for policy 0, policy_version 66443 (0.0009) -[2023-10-10 15:16:34,836][76543] Updated weights for policy 0, policy_version 66453 (0.0010) -[2023-10-10 15:16:35,203][76543] Updated weights for policy 0, policy_version 66463 (0.0009) -[2023-10-10 15:16:36,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 135987200. Throughput: 0: 1809.7, 1: 1823.0. Samples: 33997144. Policy #0 lag: (min: 0.0, avg: 24.4, max: 32.0) -[2023-10-10 15:16:36,077][75634] Avg episode reward: [(0, '39.070'), (1, '37.870')] -[2023-10-10 15:16:37,933][76542] Updated weights for policy 1, policy_version 66340 (0.0010) -[2023-10-10 15:16:38,310][76542] Updated weights for policy 1, policy_version 66350 (0.0008) -[2023-10-10 15:16:38,678][76542] Updated weights for policy 1, policy_version 66360 (0.0007) -[2023-10-10 15:16:38,870][76543] Updated weights for policy 0, policy_version 66473 (0.0007) -[2023-10-10 15:16:39,248][76543] Updated weights for policy 0, policy_version 66483 (0.0008) -[2023-10-10 15:16:39,611][76543] Updated weights for policy 0, policy_version 66493 (0.0008) -[2023-10-10 15:16:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 136052736. Throughput: 0: 1811.9, 1: 1828.0. Samples: 34018282. Policy #0 lag: (min: 18.0, avg: 25.0, max: 50.0) -[2023-10-10 15:16:41,077][75634] Avg episode reward: [(0, '37.470'), (1, '37.340')] -[2023-10-10 15:16:42,394][76542] Updated weights for policy 1, policy_version 66370 (0.0008) -[2023-10-10 15:16:42,756][76542] Updated weights for policy 1, policy_version 66380 (0.0010) -[2023-10-10 15:16:43,128][76542] Updated weights for policy 1, policy_version 66390 (0.0008) -[2023-10-10 15:16:43,353][76543] Updated weights for policy 0, policy_version 66503 (0.0009) -[2023-10-10 15:16:43,488][76542] Updated weights for policy 1, policy_version 66400 (0.0008) -[2023-10-10 15:16:43,718][76543] Updated weights for policy 0, policy_version 66513 (0.0010) -[2023-10-10 15:16:44,094][76543] Updated weights for policy 0, policy_version 66523 (0.0011) -[2023-10-10 15:16:46,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 136118272. Throughput: 0: 1809.7, 1: 1828.3. Samples: 34040430. Policy #0 lag: (min: 18.0, avg: 25.0, max: 50.0) -[2023-10-10 15:16:46,077][75634] Avg episode reward: [(0, '37.190'), (1, '41.410')] -[2023-10-10 15:16:47,207][76542] Updated weights for policy 1, policy_version 66410 (0.0009) -[2023-10-10 15:16:47,571][76542] Updated weights for policy 1, policy_version 66420 (0.0009) -[2023-10-10 15:16:47,932][76543] Updated weights for policy 0, policy_version 66533 (0.0009) -[2023-10-10 15:16:47,945][76542] Updated weights for policy 1, policy_version 66430 (0.0009) -[2023-10-10 15:16:48,296][76543] Updated weights for policy 0, policy_version 66543 (0.0009) -[2023-10-10 15:16:48,667][76543] Updated weights for policy 0, policy_version 66553 (0.0010) -[2023-10-10 15:16:51,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 136183808. Throughput: 0: 1812.6, 1: 1826.7. Samples: 34051100. Policy #0 lag: (min: 18.0, avg: 25.0, max: 50.0) -[2023-10-10 15:16:51,076][75634] Avg episode reward: [(0, '38.180'), (1, '36.080')] -[2023-10-10 15:16:51,609][76542] Updated weights for policy 1, policy_version 66440 (0.0009) -[2023-10-10 15:16:51,983][76542] Updated weights for policy 1, policy_version 66450 (0.0009) -[2023-10-10 15:16:52,274][76543] Updated weights for policy 0, policy_version 66563 (0.0007) -[2023-10-10 15:16:52,349][76542] Updated weights for policy 1, policy_version 66460 (0.0008) -[2023-10-10 15:16:52,642][76543] Updated weights for policy 0, policy_version 66573 (0.0008) -[2023-10-10 15:16:53,009][76543] Updated weights for policy 0, policy_version 66583 (0.0011) -[2023-10-10 15:16:56,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 136249344. Throughput: 0: 1812.0, 1: 1827.3. Samples: 34073220. Policy #0 lag: (min: 18.0, avg: 25.0, max: 50.0) -[2023-10-10 15:16:56,077][75634] Avg episode reward: [(0, '37.360'), (1, '35.040')] -[2023-10-10 15:16:56,231][76542] Updated weights for policy 1, policy_version 66470 (0.0009) -[2023-10-10 15:16:56,625][76542] Updated weights for policy 1, policy_version 66480 (0.0008) -[2023-10-10 15:16:56,895][76543] Updated weights for policy 0, policy_version 66593 (0.0008) -[2023-10-10 15:16:56,991][76542] Updated weights for policy 1, policy_version 66490 (0.0007) -[2023-10-10 15:16:57,268][76543] Updated weights for policy 0, policy_version 66603 (0.0007) -[2023-10-10 15:16:57,641][76543] Updated weights for policy 0, policy_version 66613 (0.0010) -[2023-10-10 15:16:58,010][76543] Updated weights for policy 0, policy_version 66623 (0.0009) -[2023-10-10 15:17:00,593][76542] Updated weights for policy 1, policy_version 66500 (0.0009) -[2023-10-10 15:17:00,959][76542] Updated weights for policy 1, policy_version 66510 (0.0008) -[2023-10-10 15:17:01,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 136314880. Throughput: 0: 1807.4, 1: 1821.3. Samples: 34095108. Policy #0 lag: (min: 18.0, avg: 25.0, max: 50.0) -[2023-10-10 15:17:01,076][75634] Avg episode reward: [(0, '36.320'), (1, '33.910')] -[2023-10-10 15:17:01,327][76542] Updated weights for policy 1, policy_version 66520 (0.0008) -[2023-10-10 15:17:01,530][76543] Updated weights for policy 0, policy_version 66633 (0.0008) -[2023-10-10 15:17:01,901][76543] Updated weights for policy 0, policy_version 66643 (0.0010) -[2023-10-10 15:17:02,280][76543] Updated weights for policy 0, policy_version 66653 (0.0010) -[2023-10-10 15:17:04,916][76542] Updated weights for policy 1, policy_version 66530 (0.0007) -[2023-10-10 15:17:05,290][76542] Updated weights for policy 1, policy_version 66540 (0.0008) -[2023-10-10 15:17:05,662][76542] Updated weights for policy 1, policy_version 66550 (0.0008) -[2023-10-10 15:17:06,035][76542] Updated weights for policy 1, policy_version 66560 (0.0008) -[2023-10-10 15:17:06,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 136413184. Throughput: 0: 1811.2, 1: 1813.0. Samples: 34105394. Policy #0 lag: (min: 18.0, avg: 25.0, max: 50.0) -[2023-10-10 15:17:06,076][75634] Avg episode reward: [(0, '29.300'), (1, '33.130')] -[2023-10-10 15:17:06,128][76543] Updated weights for policy 0, policy_version 66663 (0.0010) -[2023-10-10 15:17:06,507][76543] Updated weights for policy 0, policy_version 66673 (0.0009) -[2023-10-10 15:17:06,864][76543] Updated weights for policy 0, policy_version 66683 (0.0007) -[2023-10-10 15:17:09,669][76542] Updated weights for policy 1, policy_version 66570 (0.0009) -[2023-10-10 15:17:10,045][76542] Updated weights for policy 1, policy_version 66580 (0.0011) -[2023-10-10 15:17:10,421][76542] Updated weights for policy 1, policy_version 66590 (0.0010) -[2023-10-10 15:17:10,493][76543] Updated weights for policy 0, policy_version 66693 (0.0007) -[2023-10-10 15:17:10,864][76543] Updated weights for policy 0, policy_version 66703 (0.0010) -[2023-10-10 15:17:11,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 136478720. Throughput: 0: 1811.6, 1: 1819.3. Samples: 34127682. Policy #0 lag: (min: 18.0, avg: 25.0, max: 50.0) -[2023-10-10 15:17:11,076][75634] Avg episode reward: [(0, '28.420'), (1, '34.570')] -[2023-10-10 15:17:11,239][76543] Updated weights for policy 0, policy_version 66713 (0.0009) -[2023-10-10 15:17:14,131][76542] Updated weights for policy 1, policy_version 66600 (0.0008) -[2023-10-10 15:17:14,505][76542] Updated weights for policy 1, policy_version 66610 (0.0010) -[2023-10-10 15:17:14,873][76542] Updated weights for policy 1, policy_version 66620 (0.0008) -[2023-10-10 15:17:14,931][76543] Updated weights for policy 0, policy_version 66723 (0.0009) -[2023-10-10 15:17:15,293][76543] Updated weights for policy 0, policy_version 66733 (0.0007) -[2023-10-10 15:17:15,662][76543] Updated weights for policy 0, policy_version 66743 (0.0009) -[2023-10-10 15:17:16,076][75634] Fps is (10 sec: 16383.6, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 136577024. Throughput: 0: 1813.5, 1: 1818.5. Samples: 34148870. Policy #0 lag: (min: 18.0, avg: 25.0, max: 50.0) -[2023-10-10 15:17:16,077][75634] Avg episode reward: [(0, '31.660'), (1, '37.020')] -[2023-10-10 15:17:18,588][76542] Updated weights for policy 1, policy_version 66630 (0.0007) -[2023-10-10 15:17:18,947][76542] Updated weights for policy 1, policy_version 66640 (0.0010) -[2023-10-10 15:17:19,312][76542] Updated weights for policy 1, policy_version 66650 (0.0008) -[2023-10-10 15:17:19,401][76543] Updated weights for policy 0, policy_version 66753 (0.0007) -[2023-10-10 15:17:19,775][76543] Updated weights for policy 0, policy_version 66763 (0.0009) -[2023-10-10 15:17:20,141][76543] Updated weights for policy 0, policy_version 66773 (0.0009) -[2023-10-10 15:17:20,523][76543] Updated weights for policy 0, policy_version 66783 (0.0007) -[2023-10-10 15:17:21,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 136642560. Throughput: 0: 1805.7, 1: 1816.8. Samples: 34160158. Policy #0 lag: (min: 18.0, avg: 25.0, max: 50.0) -[2023-10-10 15:17:21,077][75634] Avg episode reward: [(0, '31.920'), (1, '34.820')] -[2023-10-10 15:17:22,949][76542] Updated weights for policy 1, policy_version 66660 (0.0007) -[2023-10-10 15:17:23,317][76542] Updated weights for policy 1, policy_version 66670 (0.0007) -[2023-10-10 15:17:23,680][76542] Updated weights for policy 1, policy_version 66680 (0.0007) -[2023-10-10 15:17:24,283][76543] Updated weights for policy 0, policy_version 66793 (0.0007) -[2023-10-10 15:17:24,649][76543] Updated weights for policy 0, policy_version 66803 (0.0010) -[2023-10-10 15:17:25,019][76543] Updated weights for policy 0, policy_version 66813 (0.0008) -[2023-10-10 15:17:26,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 136708096. Throughput: 0: 1812.6, 1: 1817.8. Samples: 34181652. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:17:26,076][75634] Avg episode reward: [(0, '33.590'), (1, '35.990')] -[2023-10-10 15:17:27,530][76542] Updated weights for policy 1, policy_version 66690 (0.0008) -[2023-10-10 15:17:27,897][76542] Updated weights for policy 1, policy_version 66700 (0.0011) -[2023-10-10 15:17:28,269][76542] Updated weights for policy 1, policy_version 66710 (0.0009) -[2023-10-10 15:17:28,634][76542] Updated weights for policy 1, policy_version 66720 (0.0008) -[2023-10-10 15:17:28,801][76543] Updated weights for policy 0, policy_version 66823 (0.0010) -[2023-10-10 15:17:29,171][76543] Updated weights for policy 0, policy_version 66833 (0.0008) -[2023-10-10 15:17:29,542][76543] Updated weights for policy 0, policy_version 66843 (0.0007) -[2023-10-10 15:17:31,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 136773632. Throughput: 0: 1799.9, 1: 1813.9. Samples: 34203048. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:17:31,077][75634] Avg episode reward: [(0, '35.290'), (1, '37.440')] -[2023-10-10 15:17:32,466][76542] Updated weights for policy 1, policy_version 66730 (0.0009) -[2023-10-10 15:17:32,833][76542] Updated weights for policy 1, policy_version 66740 (0.0009) -[2023-10-10 15:17:33,217][76542] Updated weights for policy 1, policy_version 66750 (0.0010) -[2023-10-10 15:17:33,280][76543] Updated weights for policy 0, policy_version 66853 (0.0008) -[2023-10-10 15:17:33,664][76543] Updated weights for policy 0, policy_version 66863 (0.0009) -[2023-10-10 15:17:34,042][76543] Updated weights for policy 0, policy_version 66873 (0.0009) -[2023-10-10 15:17:36,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 136839168. Throughput: 0: 1807.3, 1: 1810.5. Samples: 34213900. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:17:36,077][75634] Avg episode reward: [(0, '38.010'), (1, '36.740')] -[2023-10-10 15:17:36,907][76542] Updated weights for policy 1, policy_version 66760 (0.0008) -[2023-10-10 15:17:37,283][76542] Updated weights for policy 1, policy_version 66770 (0.0009) -[2023-10-10 15:17:37,621][76543] Updated weights for policy 0, policy_version 66883 (0.0009) -[2023-10-10 15:17:37,652][76542] Updated weights for policy 1, policy_version 66780 (0.0010) -[2023-10-10 15:17:37,990][76543] Updated weights for policy 0, policy_version 66893 (0.0008) -[2023-10-10 15:17:38,359][76543] Updated weights for policy 0, policy_version 66903 (0.0009) -[2023-10-10 15:17:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 136904704. Throughput: 0: 1799.1, 1: 1810.0. Samples: 34235630. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:17:41,077][75634] Avg episode reward: [(0, '38.020'), (1, '33.910')] -[2023-10-10 15:17:41,168][76542] Updated weights for policy 1, policy_version 66790 (0.0008) -[2023-10-10 15:17:41,544][76542] Updated weights for policy 1, policy_version 66800 (0.0007) -[2023-10-10 15:17:41,901][76542] Updated weights for policy 1, policy_version 66810 (0.0007) -[2023-10-10 15:17:42,147][76543] Updated weights for policy 0, policy_version 66913 (0.0010) -[2023-10-10 15:17:42,522][76543] Updated weights for policy 0, policy_version 66923 (0.0012) -[2023-10-10 15:17:42,892][76543] Updated weights for policy 0, policy_version 66933 (0.0008) -[2023-10-10 15:17:43,259][76543] Updated weights for policy 0, policy_version 66943 (0.0010) -[2023-10-10 15:17:45,514][76542] Updated weights for policy 1, policy_version 66820 (0.0008) -[2023-10-10 15:17:45,878][76542] Updated weights for policy 1, policy_version 66830 (0.0007) -[2023-10-10 15:17:46,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 136970240. Throughput: 0: 1804.2, 1: 1817.2. Samples: 34258072. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:17:46,076][75634] Avg episode reward: [(0, '34.630'), (1, '35.540')] -[2023-10-10 15:17:46,244][76542] Updated weights for policy 1, policy_version 66840 (0.0007) -[2023-10-10 15:17:46,749][76543] Updated weights for policy 0, policy_version 66953 (0.0008) -[2023-10-10 15:17:47,124][76543] Updated weights for policy 0, policy_version 66963 (0.0008) -[2023-10-10 15:17:47,490][76543] Updated weights for policy 0, policy_version 66973 (0.0009) -[2023-10-10 15:17:49,990][76542] Updated weights for policy 1, policy_version 66850 (0.0008) -[2023-10-10 15:17:50,357][76542] Updated weights for policy 1, policy_version 66860 (0.0009) -[2023-10-10 15:17:50,735][76542] Updated weights for policy 1, policy_version 66870 (0.0007) -[2023-10-10 15:17:51,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 137035776. Throughput: 0: 1803.7, 1: 1818.9. Samples: 34268412. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:17:51,076][75634] Avg episode reward: [(0, '32.300'), (1, '37.200')] -[2023-10-10 15:17:51,093][76542] Updated weights for policy 1, policy_version 66880 (0.0007) -[2023-10-10 15:17:51,215][76543] Updated weights for policy 0, policy_version 66983 (0.0008) -[2023-10-10 15:17:51,588][76543] Updated weights for policy 0, policy_version 66993 (0.0007) -[2023-10-10 15:17:51,963][76543] Updated weights for policy 0, policy_version 67003 (0.0007) -[2023-10-10 15:17:54,725][76542] Updated weights for policy 1, policy_version 66890 (0.0008) -[2023-10-10 15:17:55,093][76542] Updated weights for policy 1, policy_version 66900 (0.0007) -[2023-10-10 15:17:55,461][76542] Updated weights for policy 1, policy_version 66910 (0.0008) -[2023-10-10 15:17:55,765][76543] Updated weights for policy 0, policy_version 67013 (0.0007) -[2023-10-10 15:17:56,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 137134080. Throughput: 0: 1812.0, 1: 1821.6. Samples: 34291194. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:17:56,076][75634] Avg episode reward: [(0, '34.490'), (1, '38.140')] -[2023-10-10 15:17:56,143][76543] Updated weights for policy 0, policy_version 67023 (0.0009) -[2023-10-10 15:17:56,517][76543] Updated weights for policy 0, policy_version 67033 (0.0008) -[2023-10-10 15:17:59,266][76542] Updated weights for policy 1, policy_version 66920 (0.0008) -[2023-10-10 15:17:59,631][76542] Updated weights for policy 1, policy_version 66930 (0.0008) -[2023-10-10 15:18:00,003][76542] Updated weights for policy 1, policy_version 66940 (0.0008) -[2023-10-10 15:18:00,213][76543] Updated weights for policy 0, policy_version 67043 (0.0008) -[2023-10-10 15:18:00,587][76543] Updated weights for policy 0, policy_version 67053 (0.0008) -[2023-10-10 15:18:00,953][76543] Updated weights for policy 0, policy_version 67063 (0.0008) -[2023-10-10 15:18:01,076][75634] Fps is (10 sec: 16383.5, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 137199616. Throughput: 0: 1823.2, 1: 1821.9. Samples: 34312900. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:18:01,077][75634] Avg episode reward: [(0, '34.290'), (1, '38.690')] -[2023-10-10 15:18:03,690][76542] Updated weights for policy 1, policy_version 66950 (0.0008) -[2023-10-10 15:18:04,063][76542] Updated weights for policy 1, policy_version 66960 (0.0007) -[2023-10-10 15:18:04,426][76542] Updated weights for policy 1, policy_version 66970 (0.0010) -[2023-10-10 15:18:04,531][76543] Updated weights for policy 0, policy_version 67073 (0.0010) -[2023-10-10 15:18:04,909][76543] Updated weights for policy 0, policy_version 67083 (0.0010) -[2023-10-10 15:18:05,281][76543] Updated weights for policy 0, policy_version 67093 (0.0008) -[2023-10-10 15:18:05,652][76543] Updated weights for policy 0, policy_version 67103 (0.0007) -[2023-10-10 15:18:06,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 137297920. Throughput: 0: 1818.9, 1: 1824.4. Samples: 34324110. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:18:06,076][75634] Avg episode reward: [(0, '34.120'), (1, '35.390')] -[2023-10-10 15:18:08,190][76542] Updated weights for policy 1, policy_version 66980 (0.0010) -[2023-10-10 15:18:08,559][76542] Updated weights for policy 1, policy_version 66990 (0.0007) -[2023-10-10 15:18:08,934][76542] Updated weights for policy 1, policy_version 67000 (0.0007) -[2023-10-10 15:18:09,302][76543] Updated weights for policy 0, policy_version 67113 (0.0009) -[2023-10-10 15:18:09,677][76543] Updated weights for policy 0, policy_version 67123 (0.0010) -[2023-10-10 15:18:10,051][76543] Updated weights for policy 0, policy_version 67133 (0.0007) -[2023-10-10 15:18:11,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 137363456. Throughput: 0: 1825.8, 1: 1818.9. Samples: 34345666. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:18:11,077][75634] Avg episode reward: [(0, '33.850'), (1, '36.830')] -[2023-10-10 15:18:12,632][76542] Updated weights for policy 1, policy_version 67010 (0.0008) -[2023-10-10 15:18:13,001][76542] Updated weights for policy 1, policy_version 67020 (0.0010) -[2023-10-10 15:18:13,363][76542] Updated weights for policy 1, policy_version 67030 (0.0011) -[2023-10-10 15:18:13,730][76543] Updated weights for policy 0, policy_version 67143 (0.0008) -[2023-10-10 15:18:13,733][76542] Updated weights for policy 1, policy_version 67040 (0.0008) -[2023-10-10 15:18:14,102][76543] Updated weights for policy 0, policy_version 67153 (0.0009) -[2023-10-10 15:18:14,484][76543] Updated weights for policy 0, policy_version 67163 (0.0008) -[2023-10-10 15:18:16,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 137428992. Throughput: 0: 1829.4, 1: 1825.6. Samples: 34367522. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:18:16,077][75634] Avg episode reward: [(0, '35.090'), (1, '34.800')] -[2023-10-10 15:18:17,451][76542] Updated weights for policy 1, policy_version 67050 (0.0010) -[2023-10-10 15:18:17,821][76542] Updated weights for policy 1, policy_version 67060 (0.0007) -[2023-10-10 15:18:18,083][76543] Updated weights for policy 0, policy_version 67173 (0.0008) -[2023-10-10 15:18:18,184][76542] Updated weights for policy 1, policy_version 67070 (0.0009) -[2023-10-10 15:18:18,462][76543] Updated weights for policy 0, policy_version 67183 (0.0008) -[2023-10-10 15:18:18,824][76543] Updated weights for policy 0, policy_version 67193 (0.0007) -[2023-10-10 15:18:21,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 137494528. Throughput: 0: 1827.9, 1: 1829.8. Samples: 34378498. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:18:21,077][75634] Avg episode reward: [(0, '39.950'), (1, '37.210')] -[2023-10-10 15:18:21,793][76542] Updated weights for policy 1, policy_version 67080 (0.0008) -[2023-10-10 15:18:22,157][76542] Updated weights for policy 1, policy_version 67090 (0.0007) -[2023-10-10 15:18:22,523][76542] Updated weights for policy 1, policy_version 67100 (0.0008) -[2023-10-10 15:18:22,540][76543] Updated weights for policy 0, policy_version 67203 (0.0009) -[2023-10-10 15:18:22,915][76543] Updated weights for policy 0, policy_version 67213 (0.0009) -[2023-10-10 15:18:23,278][76543] Updated weights for policy 0, policy_version 67223 (0.0010) -[2023-10-10 15:18:26,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 137560064. Throughput: 0: 1827.3, 1: 1826.5. Samples: 34400050. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:18:26,077][75634] Avg episode reward: [(0, '36.920'), (1, '33.980')] -[2023-10-10 15:18:26,357][76542] Updated weights for policy 1, policy_version 67110 (0.0008) -[2023-10-10 15:18:26,734][76542] Updated weights for policy 1, policy_version 67120 (0.0007) -[2023-10-10 15:18:26,956][76543] Updated weights for policy 0, policy_version 67233 (0.0010) -[2023-10-10 15:18:27,102][76542] Updated weights for policy 1, policy_version 67130 (0.0008) -[2023-10-10 15:18:27,332][76543] Updated weights for policy 0, policy_version 67243 (0.0007) -[2023-10-10 15:18:27,704][76543] Updated weights for policy 0, policy_version 67253 (0.0007) -[2023-10-10 15:18:28,066][76543] Updated weights for policy 0, policy_version 67263 (0.0007) -[2023-10-10 15:18:30,826][76542] Updated weights for policy 1, policy_version 67140 (0.0009) -[2023-10-10 15:18:31,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 137625600. Throughput: 0: 1823.5, 1: 1824.8. Samples: 34422246. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:18:31,076][75634] Avg episode reward: [(0, '37.550'), (1, '35.100')] -[2023-10-10 15:18:31,083][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000067264_68878336.pth... -[2023-10-10 15:18:31,118][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000065568_67141632.pth -[2023-10-10 15:18:31,198][76542] Updated weights for policy 1, policy_version 67150 (0.0009) -[2023-10-10 15:18:31,561][76542] Updated weights for policy 1, policy_version 67160 (0.0010) -[2023-10-10 15:18:31,853][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000067168_68780032.pth... -[2023-10-10 15:18:31,860][76543] Updated weights for policy 0, policy_version 67273 (0.0008) -[2023-10-10 15:18:31,886][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000065440_67010560.pth -[2023-10-10 15:18:32,230][76543] Updated weights for policy 0, policy_version 67283 (0.0008) -[2023-10-10 15:18:32,601][76543] Updated weights for policy 0, policy_version 67293 (0.0009) -[2023-10-10 15:18:35,162][76542] Updated weights for policy 1, policy_version 67170 (0.0008) -[2023-10-10 15:18:35,535][76542] Updated weights for policy 1, policy_version 67180 (0.0007) -[2023-10-10 15:18:35,908][76542] Updated weights for policy 1, policy_version 67190 (0.0008) -[2023-10-10 15:18:36,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 137691136. Throughput: 0: 1822.0, 1: 1820.2. Samples: 34432310. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:18:36,076][75634] Avg episode reward: [(0, '37.080'), (1, '33.710')] -[2023-10-10 15:18:36,276][76542] Updated weights for policy 1, policy_version 67200 (0.0008) -[2023-10-10 15:18:36,431][76543] Updated weights for policy 0, policy_version 67303 (0.0009) -[2023-10-10 15:18:36,793][76543] Updated weights for policy 0, policy_version 67313 (0.0010) -[2023-10-10 15:18:37,167][76543] Updated weights for policy 0, policy_version 67323 (0.0011) -[2023-10-10 15:18:39,859][76542] Updated weights for policy 1, policy_version 67210 (0.0008) -[2023-10-10 15:18:40,229][76542] Updated weights for policy 1, policy_version 67220 (0.0010) -[2023-10-10 15:18:40,601][76542] Updated weights for policy 1, policy_version 67230 (0.0010) -[2023-10-10 15:18:40,911][76543] Updated weights for policy 0, policy_version 67333 (0.0011) -[2023-10-10 15:18:41,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 137789440. Throughput: 0: 1814.9, 1: 1818.3. Samples: 34454692. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:18:41,077][75634] Avg episode reward: [(0, '36.120'), (1, '35.530')] -[2023-10-10 15:18:41,292][76543] Updated weights for policy 0, policy_version 67343 (0.0007) -[2023-10-10 15:18:41,670][76543] Updated weights for policy 0, policy_version 67353 (0.0008) -[2023-10-10 15:18:44,468][76542] Updated weights for policy 1, policy_version 67240 (0.0009) -[2023-10-10 15:18:44,839][76542] Updated weights for policy 1, policy_version 67250 (0.0011) -[2023-10-10 15:18:45,202][76543] Updated weights for policy 0, policy_version 67363 (0.0009) -[2023-10-10 15:18:45,214][76542] Updated weights for policy 1, policy_version 67260 (0.0008) -[2023-10-10 15:18:45,565][76543] Updated weights for policy 0, policy_version 67373 (0.0009) -[2023-10-10 15:18:45,938][76543] Updated weights for policy 0, policy_version 67383 (0.0008) -[2023-10-10 15:18:46,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 137854976. Throughput: 0: 1813.9, 1: 1807.7. Samples: 34475870. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:18:46,076][75634] Avg episode reward: [(0, '37.160'), (1, '37.220')] -[2023-10-10 15:18:48,868][76542] Updated weights for policy 1, policy_version 67270 (0.0007) -[2023-10-10 15:18:49,232][76542] Updated weights for policy 1, policy_version 67280 (0.0009) -[2023-10-10 15:18:49,602][76542] Updated weights for policy 1, policy_version 67290 (0.0008) -[2023-10-10 15:18:49,807][76543] Updated weights for policy 0, policy_version 67393 (0.0009) -[2023-10-10 15:18:50,180][76543] Updated weights for policy 0, policy_version 67403 (0.0007) -[2023-10-10 15:18:50,557][76543] Updated weights for policy 0, policy_version 67413 (0.0007) -[2023-10-10 15:18:50,929][76543] Updated weights for policy 0, policy_version 67423 (0.0009) -[2023-10-10 15:18:51,076][75634] Fps is (10 sec: 16384.2, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 137953280. Throughput: 0: 1809.3, 1: 1811.7. Samples: 34487056. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:18:51,077][75634] Avg episode reward: [(0, '41.300'), (1, '39.200')] -[2023-10-10 15:18:53,408][76542] Updated weights for policy 1, policy_version 67300 (0.0009) -[2023-10-10 15:18:53,767][76542] Updated weights for policy 1, policy_version 67310 (0.0010) -[2023-10-10 15:18:54,128][76542] Updated weights for policy 1, policy_version 67320 (0.0009) -[2023-10-10 15:18:54,510][76543] Updated weights for policy 0, policy_version 67433 (0.0010) -[2023-10-10 15:18:54,867][76543] Updated weights for policy 0, policy_version 67443 (0.0010) -[2023-10-10 15:18:55,233][76543] Updated weights for policy 0, policy_version 67453 (0.0011) -[2023-10-10 15:18:56,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 138018816. Throughput: 0: 1814.5, 1: 1801.4. Samples: 34508380. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) -[2023-10-10 15:18:56,077][75634] Avg episode reward: [(0, '41.920'), (1, '37.780')] -[2023-10-10 15:18:57,901][76542] Updated weights for policy 1, policy_version 67330 (0.0008) -[2023-10-10 15:18:58,272][76542] Updated weights for policy 1, policy_version 67340 (0.0008) -[2023-10-10 15:18:58,640][76542] Updated weights for policy 1, policy_version 67350 (0.0008) -[2023-10-10 15:18:59,001][76542] Updated weights for policy 1, policy_version 67360 (0.0008) -[2023-10-10 15:18:59,074][76543] Updated weights for policy 0, policy_version 67463 (0.0008) -[2023-10-10 15:18:59,450][76543] Updated weights for policy 0, policy_version 67473 (0.0011) -[2023-10-10 15:18:59,824][76543] Updated weights for policy 0, policy_version 67483 (0.0010) -[2023-10-10 15:19:01,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 138084352. Throughput: 0: 1803.0, 1: 1800.8. Samples: 34529692. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) -[2023-10-10 15:19:01,076][75634] Avg episode reward: [(0, '37.070'), (1, '36.060')] -[2023-10-10 15:19:02,672][76542] Updated weights for policy 1, policy_version 67370 (0.0008) -[2023-10-10 15:19:03,045][76542] Updated weights for policy 1, policy_version 67380 (0.0007) -[2023-10-10 15:19:03,412][76542] Updated weights for policy 1, policy_version 67390 (0.0007) -[2023-10-10 15:19:03,486][76543] Updated weights for policy 0, policy_version 67493 (0.0009) -[2023-10-10 15:19:03,856][76543] Updated weights for policy 0, policy_version 67503 (0.0008) -[2023-10-10 15:19:04,221][76543] Updated weights for policy 0, policy_version 67513 (0.0010) -[2023-10-10 15:19:06,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 138149888. Throughput: 0: 1817.5, 1: 1807.6. Samples: 34541626. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) -[2023-10-10 15:19:06,077][75634] Avg episode reward: [(0, '38.910'), (1, '36.820')] -[2023-10-10 15:19:07,088][76542] Updated weights for policy 1, policy_version 67400 (0.0008) -[2023-10-10 15:19:07,445][76542] Updated weights for policy 1, policy_version 67410 (0.0007) -[2023-10-10 15:19:07,810][76542] Updated weights for policy 1, policy_version 67420 (0.0009) -[2023-10-10 15:19:07,837][76543] Updated weights for policy 0, policy_version 67523 (0.0007) -[2023-10-10 15:19:08,205][76543] Updated weights for policy 0, policy_version 67533 (0.0009) -[2023-10-10 15:19:08,580][76543] Updated weights for policy 0, policy_version 67543 (0.0008) -[2023-10-10 15:19:11,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 138215424. Throughput: 0: 1813.7, 1: 1809.3. Samples: 34563086. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) -[2023-10-10 15:19:11,077][75634] Avg episode reward: [(0, '37.870'), (1, '38.450')] -[2023-10-10 15:19:11,581][76542] Updated weights for policy 1, policy_version 67430 (0.0009) -[2023-10-10 15:19:11,953][76542] Updated weights for policy 1, policy_version 67440 (0.0008) -[2023-10-10 15:19:12,304][76543] Updated weights for policy 0, policy_version 67553 (0.0010) -[2023-10-10 15:19:12,321][76542] Updated weights for policy 1, policy_version 67450 (0.0007) -[2023-10-10 15:19:12,668][76543] Updated weights for policy 0, policy_version 67563 (0.0008) -[2023-10-10 15:19:13,034][76543] Updated weights for policy 0, policy_version 67573 (0.0009) -[2023-10-10 15:19:13,407][76543] Updated weights for policy 0, policy_version 67583 (0.0009) -[2023-10-10 15:19:16,009][76542] Updated weights for policy 1, policy_version 67460 (0.0009) -[2023-10-10 15:19:16,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 138280960. Throughput: 0: 1817.0, 1: 1818.8. Samples: 34585856. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) -[2023-10-10 15:19:16,076][75634] Avg episode reward: [(0, '36.520'), (1, '37.790')] -[2023-10-10 15:19:16,376][76542] Updated weights for policy 1, policy_version 67470 (0.0008) -[2023-10-10 15:19:16,749][76542] Updated weights for policy 1, policy_version 67480 (0.0009) -[2023-10-10 15:19:17,077][76543] Updated weights for policy 0, policy_version 67593 (0.0007) -[2023-10-10 15:19:17,447][76543] Updated weights for policy 0, policy_version 67603 (0.0008) -[2023-10-10 15:19:17,811][76543] Updated weights for policy 0, policy_version 67613 (0.0007) -[2023-10-10 15:19:20,366][76542] Updated weights for policy 1, policy_version 67490 (0.0009) -[2023-10-10 15:19:20,736][76542] Updated weights for policy 1, policy_version 67500 (0.0008) -[2023-10-10 15:19:21,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 138346496. Throughput: 0: 1822.0, 1: 1817.4. Samples: 34596084. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) -[2023-10-10 15:19:21,076][75634] Avg episode reward: [(0, '34.440'), (1, '35.120')] -[2023-10-10 15:19:21,104][76542] Updated weights for policy 1, policy_version 67510 (0.0008) -[2023-10-10 15:19:21,471][76542] Updated weights for policy 1, policy_version 67520 (0.0008) -[2023-10-10 15:19:21,606][76543] Updated weights for policy 0, policy_version 67623 (0.0007) -[2023-10-10 15:19:21,999][76543] Updated weights for policy 0, policy_version 67633 (0.0008) -[2023-10-10 15:19:22,369][76543] Updated weights for policy 0, policy_version 67643 (0.0007) -[2023-10-10 15:19:24,790][76542] Updated weights for policy 1, policy_version 67530 (0.0007) -[2023-10-10 15:19:25,152][76542] Updated weights for policy 1, policy_version 67540 (0.0008) -[2023-10-10 15:19:25,521][76542] Updated weights for policy 1, policy_version 67550 (0.0007) -[2023-10-10 15:19:25,946][76543] Updated weights for policy 0, policy_version 67653 (0.0008) -[2023-10-10 15:19:26,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 138444800. Throughput: 0: 1818.1, 1: 1825.2. Samples: 34618638. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) -[2023-10-10 15:19:26,077][75634] Avg episode reward: [(0, '33.170'), (1, '33.190')] -[2023-10-10 15:19:26,309][76543] Updated weights for policy 0, policy_version 67663 (0.0011) -[2023-10-10 15:19:26,683][76543] Updated weights for policy 0, policy_version 67673 (0.0008) -[2023-10-10 15:19:29,076][76542] Updated weights for policy 1, policy_version 67560 (0.0009) -[2023-10-10 15:19:29,451][76542] Updated weights for policy 1, policy_version 67570 (0.0012) -[2023-10-10 15:19:29,817][76542] Updated weights for policy 1, policy_version 67580 (0.0010) -[2023-10-10 15:19:30,444][76543] Updated weights for policy 0, policy_version 67683 (0.0009) -[2023-10-10 15:19:30,816][76543] Updated weights for policy 0, policy_version 67693 (0.0009) -[2023-10-10 15:19:31,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 138510336. Throughput: 0: 1819.7, 1: 1833.7. Samples: 34640274. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) -[2023-10-10 15:19:31,076][75634] Avg episode reward: [(0, '31.160'), (1, '34.130')] -[2023-10-10 15:19:31,191][76543] Updated weights for policy 0, policy_version 67703 (0.0009) -[2023-10-10 15:19:33,585][76542] Updated weights for policy 1, policy_version 67590 (0.0008) -[2023-10-10 15:19:33,964][76542] Updated weights for policy 1, policy_version 67600 (0.0007) -[2023-10-10 15:19:34,333][76542] Updated weights for policy 1, policy_version 67610 (0.0007) -[2023-10-10 15:19:34,920][76543] Updated weights for policy 0, policy_version 67713 (0.0010) -[2023-10-10 15:19:35,283][76543] Updated weights for policy 0, policy_version 67723 (0.0011) -[2023-10-10 15:19:35,664][76543] Updated weights for policy 0, policy_version 67733 (0.0009) -[2023-10-10 15:19:36,044][76543] Updated weights for policy 0, policy_version 67743 (0.0010) -[2023-10-10 15:19:36,076][75634] Fps is (10 sec: 16384.0, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 138608640. Throughput: 0: 1818.4, 1: 1825.1. Samples: 34651014. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) -[2023-10-10 15:19:36,076][75634] Avg episode reward: [(0, '32.860'), (1, '32.950')] -[2023-10-10 15:19:37,943][76542] Updated weights for policy 1, policy_version 67620 (0.0008) -[2023-10-10 15:19:38,314][76542] Updated weights for policy 1, policy_version 67630 (0.0009) -[2023-10-10 15:19:38,686][76542] Updated weights for policy 1, policy_version 67640 (0.0011) -[2023-10-10 15:19:39,659][76543] Updated weights for policy 0, policy_version 67753 (0.0009) -[2023-10-10 15:19:40,026][76543] Updated weights for policy 0, policy_version 67763 (0.0011) -[2023-10-10 15:19:40,407][76543] Updated weights for policy 0, policy_version 67773 (0.0010) -[2023-10-10 15:19:41,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 138674176. Throughput: 0: 1814.1, 1: 1838.8. Samples: 34672762. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:19:41,077][75634] Avg episode reward: [(0, '38.620'), (1, '31.960')] -[2023-10-10 15:19:42,387][76542] Updated weights for policy 1, policy_version 67650 (0.0010) -[2023-10-10 15:19:42,760][76542] Updated weights for policy 1, policy_version 67660 (0.0007) -[2023-10-10 15:19:43,126][76542] Updated weights for policy 1, policy_version 67670 (0.0007) -[2023-10-10 15:19:43,500][76542] Updated weights for policy 1, policy_version 67680 (0.0011) -[2023-10-10 15:19:44,046][76543] Updated weights for policy 0, policy_version 67783 (0.0008) -[2023-10-10 15:19:44,406][76543] Updated weights for policy 0, policy_version 67793 (0.0008) -[2023-10-10 15:19:44,783][76543] Updated weights for policy 0, policy_version 67803 (0.0007) -[2023-10-10 15:19:46,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 138739712. Throughput: 0: 1817.7, 1: 1836.4. Samples: 34694130. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:19:46,077][75634] Avg episode reward: [(0, '39.600'), (1, '31.910')] -[2023-10-10 15:19:47,092][76542] Updated weights for policy 1, policy_version 67690 (0.0008) -[2023-10-10 15:19:47,457][76542] Updated weights for policy 1, policy_version 67700 (0.0009) -[2023-10-10 15:19:47,823][76542] Updated weights for policy 1, policy_version 67710 (0.0011) -[2023-10-10 15:19:48,457][76543] Updated weights for policy 0, policy_version 67813 (0.0010) -[2023-10-10 15:19:48,834][76543] Updated weights for policy 0, policy_version 67823 (0.0008) -[2023-10-10 15:19:49,212][76543] Updated weights for policy 0, policy_version 67833 (0.0008) -[2023-10-10 15:19:51,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 138805248. Throughput: 0: 1812.1, 1: 1833.7. Samples: 34705688. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:19:51,076][75634] Avg episode reward: [(0, '39.340'), (1, '32.840')] -[2023-10-10 15:19:51,518][76542] Updated weights for policy 1, policy_version 67720 (0.0011) -[2023-10-10 15:19:51,884][76542] Updated weights for policy 1, policy_version 67730 (0.0008) -[2023-10-10 15:19:52,252][76542] Updated weights for policy 1, policy_version 67740 (0.0009) -[2023-10-10 15:19:52,979][76543] Updated weights for policy 0, policy_version 67843 (0.0009) -[2023-10-10 15:19:53,349][76543] Updated weights for policy 0, policy_version 67853 (0.0007) -[2023-10-10 15:19:53,722][76543] Updated weights for policy 0, policy_version 67863 (0.0007) -[2023-10-10 15:19:55,904][76542] Updated weights for policy 1, policy_version 67750 (0.0008) -[2023-10-10 15:19:56,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 138870784. Throughput: 0: 1806.7, 1: 1837.7. Samples: 34727084. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:19:56,077][75634] Avg episode reward: [(0, '41.150'), (1, '35.840')] -[2023-10-10 15:19:56,271][76542] Updated weights for policy 1, policy_version 67760 (0.0007) -[2023-10-10 15:19:56,641][76542] Updated weights for policy 1, policy_version 67770 (0.0010) -[2023-10-10 15:19:57,273][76543] Updated weights for policy 0, policy_version 67873 (0.0008) -[2023-10-10 15:19:57,636][76543] Updated weights for policy 0, policy_version 67883 (0.0009) -[2023-10-10 15:19:58,004][76543] Updated weights for policy 0, policy_version 67893 (0.0008) -[2023-10-10 15:19:58,382][76543] Updated weights for policy 0, policy_version 67903 (0.0009) -[2023-10-10 15:20:00,317][76542] Updated weights for policy 1, policy_version 67780 (0.0010) -[2023-10-10 15:20:00,716][76542] Updated weights for policy 1, policy_version 67790 (0.0008) -[2023-10-10 15:20:01,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 138936320. Throughput: 0: 1811.2, 1: 1824.4. Samples: 34749458. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:20:01,077][75634] Avg episode reward: [(0, '39.250'), (1, '35.840')] -[2023-10-10 15:20:01,089][76542] Updated weights for policy 1, policy_version 67800 (0.0008) -[2023-10-10 15:20:02,104][76543] Updated weights for policy 0, policy_version 67913 (0.0010) -[2023-10-10 15:20:02,476][76543] Updated weights for policy 0, policy_version 67923 (0.0007) -[2023-10-10 15:20:02,843][76543] Updated weights for policy 0, policy_version 67933 (0.0008) -[2023-10-10 15:20:04,968][76542] Updated weights for policy 1, policy_version 67810 (0.0009) -[2023-10-10 15:20:05,329][76542] Updated weights for policy 1, policy_version 67820 (0.0008) -[2023-10-10 15:20:05,693][76542] Updated weights for policy 1, policy_version 67830 (0.0010) -[2023-10-10 15:20:06,056][76542] Updated weights for policy 1, policy_version 67840 (0.0007) -[2023-10-10 15:20:06,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 139034624. Throughput: 0: 1807.9, 1: 1834.0. Samples: 34759968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:20:06,076][75634] Avg episode reward: [(0, '38.380'), (1, '36.790')] -[2023-10-10 15:20:06,597][76543] Updated weights for policy 0, policy_version 67943 (0.0008) -[2023-10-10 15:20:06,967][76543] Updated weights for policy 0, policy_version 67953 (0.0010) -[2023-10-10 15:20:07,343][76543] Updated weights for policy 0, policy_version 67963 (0.0011) -[2023-10-10 15:20:09,755][76542] Updated weights for policy 1, policy_version 67850 (0.0007) -[2023-10-10 15:20:10,114][76542] Updated weights for policy 1, policy_version 67860 (0.0007) -[2023-10-10 15:20:10,467][76542] Updated weights for policy 1, policy_version 67870 (0.0008) -[2023-10-10 15:20:10,928][76543] Updated weights for policy 0, policy_version 67973 (0.0008) -[2023-10-10 15:20:11,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 139100160. Throughput: 0: 1818.2, 1: 1822.5. Samples: 34782470. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:20:11,077][75634] Avg episode reward: [(0, '40.330'), (1, '36.310')] -[2023-10-10 15:20:11,325][76543] Updated weights for policy 0, policy_version 67983 (0.0010) -[2023-10-10 15:20:11,695][76543] Updated weights for policy 0, policy_version 67993 (0.0008) -[2023-10-10 15:20:14,100][76542] Updated weights for policy 1, policy_version 67880 (0.0009) -[2023-10-10 15:20:14,462][76542] Updated weights for policy 1, policy_version 67890 (0.0011) -[2023-10-10 15:20:14,828][76542] Updated weights for policy 1, policy_version 67900 (0.0009) -[2023-10-10 15:20:15,537][76543] Updated weights for policy 0, policy_version 68003 (0.0007) -[2023-10-10 15:20:15,903][76543] Updated weights for policy 0, policy_version 68013 (0.0008) -[2023-10-10 15:20:16,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 139165696. Throughput: 0: 1818.2, 1: 1822.8. Samples: 34804118. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:20:16,077][75634] Avg episode reward: [(0, '33.780'), (1, '34.840')] -[2023-10-10 15:20:16,270][76543] Updated weights for policy 0, policy_version 68023 (0.0008) -[2023-10-10 15:20:18,493][76542] Updated weights for policy 1, policy_version 67910 (0.0009) -[2023-10-10 15:20:18,856][76542] Updated weights for policy 1, policy_version 67920 (0.0009) -[2023-10-10 15:20:19,225][76542] Updated weights for policy 1, policy_version 67930 (0.0010) -[2023-10-10 15:20:19,899][76543] Updated weights for policy 0, policy_version 68033 (0.0008) -[2023-10-10 15:20:20,265][76543] Updated weights for policy 0, policy_version 68043 (0.0012) -[2023-10-10 15:20:20,646][76543] Updated weights for policy 0, policy_version 68053 (0.0012) -[2023-10-10 15:20:21,012][76543] Updated weights for policy 0, policy_version 68063 (0.0011) -[2023-10-10 15:20:21,076][75634] Fps is (10 sec: 16384.2, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 139264000. Throughput: 0: 1816.2, 1: 1827.9. Samples: 34815000. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:20:21,076][75634] Avg episode reward: [(0, '34.650'), (1, '35.280')] -[2023-10-10 15:20:22,917][76542] Updated weights for policy 1, policy_version 67940 (0.0010) -[2023-10-10 15:20:23,287][76542] Updated weights for policy 1, policy_version 67950 (0.0008) -[2023-10-10 15:20:23,660][76542] Updated weights for policy 1, policy_version 67960 (0.0009) -[2023-10-10 15:20:24,724][76543] Updated weights for policy 0, policy_version 68073 (0.0009) -[2023-10-10 15:20:25,102][76543] Updated weights for policy 0, policy_version 68083 (0.0007) -[2023-10-10 15:20:25,472][76543] Updated weights for policy 0, policy_version 68093 (0.0008) -[2023-10-10 15:20:26,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 139329536. Throughput: 0: 1816.8, 1: 1824.6. Samples: 34836628. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-10 15:20:26,077][75634] Avg episode reward: [(0, '33.110'), (1, '36.400')] -[2023-10-10 15:20:27,260][76542] Updated weights for policy 1, policy_version 67970 (0.0008) -[2023-10-10 15:20:27,628][76542] Updated weights for policy 1, policy_version 67980 (0.0008) -[2023-10-10 15:20:28,003][76542] Updated weights for policy 1, policy_version 67990 (0.0007) -[2023-10-10 15:20:28,370][76542] Updated weights for policy 1, policy_version 68000 (0.0009) -[2023-10-10 15:20:29,128][76543] Updated weights for policy 0, policy_version 68103 (0.0007) -[2023-10-10 15:20:29,507][76543] Updated weights for policy 0, policy_version 68113 (0.0008) -[2023-10-10 15:20:29,866][76543] Updated weights for policy 0, policy_version 68123 (0.0010) -[2023-10-10 15:20:31,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 139395072. Throughput: 0: 1814.0, 1: 1830.8. Samples: 34858146. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-10 15:20:31,077][75634] Avg episode reward: [(0, '36.060'), (1, '37.770')] -[2023-10-10 15:20:31,085][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000068000_69632000.pth... -[2023-10-10 15:20:31,086][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000068128_69763072.pth... -[2023-10-10 15:20:31,117][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000066304_67895296.pth -[2023-10-10 15:20:31,121][76421] Saving a milestone ./train_atari/atari_defender_APPO/checkpoint_p1/milestones/checkpoint_000068000_69632000.pth -[2023-10-10 15:20:31,122][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000066432_68026368.pth -[2023-10-10 15:20:31,126][76362] Saving a milestone ./train_atari/atari_defender_APPO/checkpoint_p0/milestones/checkpoint_000068128_69763072.pth -[2023-10-10 15:20:31,915][76542] Updated weights for policy 1, policy_version 68010 (0.0009) -[2023-10-10 15:20:32,292][76542] Updated weights for policy 1, policy_version 68020 (0.0008) -[2023-10-10 15:20:32,663][76542] Updated weights for policy 1, policy_version 68030 (0.0009) -[2023-10-10 15:20:33,470][76543] Updated weights for policy 0, policy_version 68133 (0.0011) -[2023-10-10 15:20:33,833][76543] Updated weights for policy 0, policy_version 68143 (0.0008) -[2023-10-10 15:20:34,198][76543] Updated weights for policy 0, policy_version 68153 (0.0009) -[2023-10-10 15:20:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 139460608. Throughput: 0: 1816.2, 1: 1826.5. Samples: 34869610. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-10 15:20:36,077][75634] Avg episode reward: [(0, '34.710'), (1, '36.820')] -[2023-10-10 15:20:36,452][76542] Updated weights for policy 1, policy_version 68040 (0.0010) -[2023-10-10 15:20:36,822][76542] Updated weights for policy 1, policy_version 68050 (0.0008) -[2023-10-10 15:20:37,189][76542] Updated weights for policy 1, policy_version 68060 (0.0011) -[2023-10-10 15:20:38,049][76543] Updated weights for policy 0, policy_version 68163 (0.0010) -[2023-10-10 15:20:38,413][76543] Updated weights for policy 0, policy_version 68173 (0.0010) -[2023-10-10 15:20:38,773][76543] Updated weights for policy 0, policy_version 68183 (0.0008) -[2023-10-10 15:20:41,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 139526144. Throughput: 0: 1814.7, 1: 1813.0. Samples: 34890332. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-10 15:20:41,076][75634] Avg episode reward: [(0, '34.920'), (1, '33.300')] -[2023-10-10 15:20:41,085][76542] Updated weights for policy 1, policy_version 68070 (0.0010) -[2023-10-10 15:20:41,457][76542] Updated weights for policy 1, policy_version 68080 (0.0009) -[2023-10-10 15:20:41,816][76542] Updated weights for policy 1, policy_version 68090 (0.0007) -[2023-10-10 15:20:42,395][76543] Updated weights for policy 0, policy_version 68193 (0.0007) -[2023-10-10 15:20:42,757][76543] Updated weights for policy 0, policy_version 68203 (0.0008) -[2023-10-10 15:20:43,129][76543] Updated weights for policy 0, policy_version 68213 (0.0007) -[2023-10-10 15:20:43,497][76543] Updated weights for policy 0, policy_version 68223 (0.0007) -[2023-10-10 15:20:45,477][76542] Updated weights for policy 1, policy_version 68100 (0.0010) -[2023-10-10 15:20:45,847][76542] Updated weights for policy 1, policy_version 68110 (0.0007) -[2023-10-10 15:20:46,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 139591680. Throughput: 0: 1813.3, 1: 1817.5. Samples: 34912842. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-10 15:20:46,076][75634] Avg episode reward: [(0, '34.940'), (1, '32.830')] -[2023-10-10 15:20:46,208][76542] Updated weights for policy 1, policy_version 68120 (0.0009) -[2023-10-10 15:20:47,211][76543] Updated weights for policy 0, policy_version 68233 (0.0009) -[2023-10-10 15:20:47,581][76543] Updated weights for policy 0, policy_version 68243 (0.0009) -[2023-10-10 15:20:47,951][76543] Updated weights for policy 0, policy_version 68253 (0.0007) -[2023-10-10 15:20:50,014][76542] Updated weights for policy 1, policy_version 68130 (0.0010) -[2023-10-10 15:20:50,384][76542] Updated weights for policy 1, policy_version 68140 (0.0007) -[2023-10-10 15:20:50,757][76542] Updated weights for policy 1, policy_version 68150 (0.0008) -[2023-10-10 15:20:51,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 139657216. Throughput: 0: 1813.7, 1: 1812.0. Samples: 34923124. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-10 15:20:51,077][75634] Avg episode reward: [(0, '33.610'), (1, '35.310')] -[2023-10-10 15:20:51,117][76542] Updated weights for policy 1, policy_version 68160 (0.0008) -[2023-10-10 15:20:51,668][76543] Updated weights for policy 0, policy_version 68263 (0.0009) -[2023-10-10 15:20:52,046][76543] Updated weights for policy 0, policy_version 68273 (0.0009) -[2023-10-10 15:20:52,409][76543] Updated weights for policy 0, policy_version 68283 (0.0008) -[2023-10-10 15:20:54,904][76542] Updated weights for policy 1, policy_version 68170 (0.0008) -[2023-10-10 15:20:55,276][76542] Updated weights for policy 1, policy_version 68180 (0.0007) -[2023-10-10 15:20:55,660][76542] Updated weights for policy 1, policy_version 68190 (0.0009) -[2023-10-10 15:20:56,049][76543] Updated weights for policy 0, policy_version 68293 (0.0008) -[2023-10-10 15:20:56,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 139755520. Throughput: 0: 1814.3, 1: 1816.3. Samples: 34945848. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-10 15:20:56,076][75634] Avg episode reward: [(0, '34.580'), (1, '34.720')] -[2023-10-10 15:20:56,435][76543] Updated weights for policy 0, policy_version 68303 (0.0008) -[2023-10-10 15:20:56,805][76543] Updated weights for policy 0, policy_version 68313 (0.0007) -[2023-10-10 15:20:59,285][76542] Updated weights for policy 1, policy_version 68200 (0.0008) -[2023-10-10 15:20:59,652][76542] Updated weights for policy 1, policy_version 68210 (0.0010) -[2023-10-10 15:21:00,029][76542] Updated weights for policy 1, policy_version 68220 (0.0010) -[2023-10-10 15:21:00,633][76543] Updated weights for policy 0, policy_version 68323 (0.0007) -[2023-10-10 15:21:01,001][76543] Updated weights for policy 0, policy_version 68333 (0.0008) -[2023-10-10 15:21:01,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 139821056. Throughput: 0: 1813.4, 1: 1809.6. Samples: 34967156. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-10 15:21:01,077][75634] Avg episode reward: [(0, '34.250'), (1, '33.810')] -[2023-10-10 15:21:01,369][76543] Updated weights for policy 0, policy_version 68343 (0.0011) -[2023-10-10 15:21:03,815][76542] Updated weights for policy 1, policy_version 68230 (0.0009) -[2023-10-10 15:21:04,182][76542] Updated weights for policy 1, policy_version 68240 (0.0007) -[2023-10-10 15:21:04,547][76542] Updated weights for policy 1, policy_version 68250 (0.0009) -[2023-10-10 15:21:05,119][76543] Updated weights for policy 0, policy_version 68353 (0.0009) -[2023-10-10 15:21:05,497][76543] Updated weights for policy 0, policy_version 68363 (0.0008) -[2023-10-10 15:21:05,861][76543] Updated weights for policy 0, policy_version 68373 (0.0008) -[2023-10-10 15:21:06,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 139886592. Throughput: 0: 1815.1, 1: 1814.7. Samples: 34978342. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-10 15:21:06,077][75634] Avg episode reward: [(0, '37.300'), (1, '33.980')] -[2023-10-10 15:21:06,224][76543] Updated weights for policy 0, policy_version 68383 (0.0008) -[2023-10-10 15:21:08,212][76542] Updated weights for policy 1, policy_version 68260 (0.0008) -[2023-10-10 15:21:08,582][76542] Updated weights for policy 1, policy_version 68270 (0.0007) -[2023-10-10 15:21:08,949][76542] Updated weights for policy 1, policy_version 68280 (0.0007) -[2023-10-10 15:21:09,747][76543] Updated weights for policy 0, policy_version 68393 (0.0008) -[2023-10-10 15:21:10,113][76543] Updated weights for policy 0, policy_version 68403 (0.0008) -[2023-10-10 15:21:10,481][76543] Updated weights for policy 0, policy_version 68413 (0.0007) -[2023-10-10 15:21:11,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 139984896. Throughput: 0: 1826.9, 1: 1807.4. Samples: 35000172. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:21:11,076][75634] Avg episode reward: [(0, '43.190'), (1, '38.560')] -[2023-10-10 15:21:12,615][76542] Updated weights for policy 1, policy_version 68290 (0.0009) -[2023-10-10 15:21:12,973][76542] Updated weights for policy 1, policy_version 68300 (0.0007) -[2023-10-10 15:21:13,349][76542] Updated weights for policy 1, policy_version 68310 (0.0008) -[2023-10-10 15:21:13,715][76542] Updated weights for policy 1, policy_version 68320 (0.0009) -[2023-10-10 15:21:14,107][76543] Updated weights for policy 0, policy_version 68423 (0.0008) -[2023-10-10 15:21:14,478][76543] Updated weights for policy 0, policy_version 68433 (0.0007) -[2023-10-10 15:21:14,842][76543] Updated weights for policy 0, policy_version 68443 (0.0008) -[2023-10-10 15:21:16,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 140050432. Throughput: 0: 1829.7, 1: 1803.8. Samples: 35021654. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:21:16,076][75634] Avg episode reward: [(0, '37.820'), (1, '39.050')] -[2023-10-10 15:21:17,377][76542] Updated weights for policy 1, policy_version 68330 (0.0008) -[2023-10-10 15:21:17,753][76542] Updated weights for policy 1, policy_version 68340 (0.0007) -[2023-10-10 15:21:18,123][76542] Updated weights for policy 1, policy_version 68350 (0.0007) -[2023-10-10 15:21:18,414][76543] Updated weights for policy 0, policy_version 68453 (0.0007) -[2023-10-10 15:21:18,786][76543] Updated weights for policy 0, policy_version 68463 (0.0007) -[2023-10-10 15:21:19,163][76543] Updated weights for policy 0, policy_version 68473 (0.0008) -[2023-10-10 15:21:21,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 140115968. Throughput: 0: 1829.2, 1: 1808.2. Samples: 35033294. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:21:21,076][75634] Avg episode reward: [(0, '35.850'), (1, '37.120')] -[2023-10-10 15:21:21,864][76542] Updated weights for policy 1, policy_version 68360 (0.0009) -[2023-10-10 15:21:22,233][76542] Updated weights for policy 1, policy_version 68370 (0.0007) -[2023-10-10 15:21:22,599][76542] Updated weights for policy 1, policy_version 68380 (0.0007) -[2023-10-10 15:21:22,818][76543] Updated weights for policy 0, policy_version 68483 (0.0007) -[2023-10-10 15:21:23,195][76543] Updated weights for policy 0, policy_version 68493 (0.0009) -[2023-10-10 15:21:23,578][76543] Updated weights for policy 0, policy_version 68503 (0.0009) -[2023-10-10 15:21:26,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 140181504. Throughput: 0: 1833.1, 1: 1814.8. Samples: 35054490. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:21:26,077][75634] Avg episode reward: [(0, '37.250'), (1, '35.050')] -[2023-10-10 15:21:26,265][76542] Updated weights for policy 1, policy_version 68390 (0.0011) -[2023-10-10 15:21:26,631][76542] Updated weights for policy 1, policy_version 68400 (0.0009) -[2023-10-10 15:21:26,998][76542] Updated weights for policy 1, policy_version 68410 (0.0007) -[2023-10-10 15:21:27,252][76543] Updated weights for policy 0, policy_version 68513 (0.0011) -[2023-10-10 15:21:27,626][76543] Updated weights for policy 0, policy_version 68523 (0.0010) -[2023-10-10 15:21:27,988][76543] Updated weights for policy 0, policy_version 68533 (0.0010) -[2023-10-10 15:21:28,360][76543] Updated weights for policy 0, policy_version 68543 (0.0009) -[2023-10-10 15:21:30,910][76542] Updated weights for policy 1, policy_version 68420 (0.0008) -[2023-10-10 15:21:31,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 140247040. Throughput: 0: 1831.8, 1: 1821.9. Samples: 35077258. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:21:31,077][75634] Avg episode reward: [(0, '36.140'), (1, '32.540')] -[2023-10-10 15:21:31,289][76542] Updated weights for policy 1, policy_version 68430 (0.0008) -[2023-10-10 15:21:31,658][76542] Updated weights for policy 1, policy_version 68440 (0.0010) -[2023-10-10 15:21:32,037][76543] Updated weights for policy 0, policy_version 68553 (0.0009) -[2023-10-10 15:21:32,409][76543] Updated weights for policy 0, policy_version 68563 (0.0008) -[2023-10-10 15:21:32,781][76543] Updated weights for policy 0, policy_version 68573 (0.0009) -[2023-10-10 15:21:35,411][76542] Updated weights for policy 1, policy_version 68450 (0.0008) -[2023-10-10 15:21:35,774][76542] Updated weights for policy 1, policy_version 68460 (0.0009) -[2023-10-10 15:21:36,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 140312576. Throughput: 0: 1830.6, 1: 1812.9. Samples: 35087084. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:21:36,076][75634] Avg episode reward: [(0, '35.130'), (1, '30.260')] -[2023-10-10 15:21:36,143][76542] Updated weights for policy 1, policy_version 68470 (0.0009) -[2023-10-10 15:21:36,393][76543] Updated weights for policy 0, policy_version 68583 (0.0009) -[2023-10-10 15:21:36,508][76542] Updated weights for policy 1, policy_version 68480 (0.0008) -[2023-10-10 15:21:36,765][76543] Updated weights for policy 0, policy_version 68593 (0.0008) -[2023-10-10 15:21:37,146][76543] Updated weights for policy 0, policy_version 68603 (0.0008) -[2023-10-10 15:21:40,351][76542] Updated weights for policy 1, policy_version 68490 (0.0008) -[2023-10-10 15:21:40,717][76542] Updated weights for policy 1, policy_version 68500 (0.0009) -[2023-10-10 15:21:40,868][76543] Updated weights for policy 0, policy_version 68613 (0.0009) -[2023-10-10 15:21:41,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 140378112. Throughput: 0: 1834.3, 1: 1808.8. Samples: 35109784. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:21:41,076][75634] Avg episode reward: [(0, '35.120'), (1, '31.520')] -[2023-10-10 15:21:41,086][76542] Updated weights for policy 1, policy_version 68510 (0.0009) -[2023-10-10 15:21:41,240][76543] Updated weights for policy 0, policy_version 68623 (0.0007) -[2023-10-10 15:21:41,616][76543] Updated weights for policy 0, policy_version 68633 (0.0007) -[2023-10-10 15:21:44,713][76542] Updated weights for policy 1, policy_version 68520 (0.0009) -[2023-10-10 15:21:45,078][76542] Updated weights for policy 1, policy_version 68530 (0.0008) -[2023-10-10 15:21:45,301][76543] Updated weights for policy 0, policy_version 68643 (0.0009) -[2023-10-10 15:21:45,439][76542] Updated weights for policy 1, policy_version 68540 (0.0009) -[2023-10-10 15:21:45,668][76543] Updated weights for policy 0, policy_version 68653 (0.0008) -[2023-10-10 15:21:46,036][76543] Updated weights for policy 0, policy_version 68663 (0.0009) -[2023-10-10 15:21:46,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 140476416. Throughput: 0: 1830.6, 1: 1808.7. Samples: 35130924. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:21:46,076][75634] Avg episode reward: [(0, '33.700'), (1, '33.300')] -[2023-10-10 15:21:49,124][76542] Updated weights for policy 1, policy_version 68550 (0.0007) -[2023-10-10 15:21:49,481][76542] Updated weights for policy 1, policy_version 68560 (0.0010) -[2023-10-10 15:21:49,710][76543] Updated weights for policy 0, policy_version 68673 (0.0009) -[2023-10-10 15:21:49,843][76542] Updated weights for policy 1, policy_version 68570 (0.0008) -[2023-10-10 15:21:50,076][76543] Updated weights for policy 0, policy_version 68683 (0.0009) -[2023-10-10 15:21:50,449][76543] Updated weights for policy 0, policy_version 68693 (0.0007) -[2023-10-10 15:21:50,825][76543] Updated weights for policy 0, policy_version 68703 (0.0010) -[2023-10-10 15:21:51,076][75634] Fps is (10 sec: 19660.4, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 140574720. Throughput: 0: 1833.5, 1: 1817.1. Samples: 35142616. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:21:51,077][75634] Avg episode reward: [(0, '34.010'), (1, '37.520')] -[2023-10-10 15:21:53,458][76542] Updated weights for policy 1, policy_version 68580 (0.0007) -[2023-10-10 15:21:53,821][76542] Updated weights for policy 1, policy_version 68590 (0.0007) -[2023-10-10 15:21:54,180][76542] Updated weights for policy 1, policy_version 68600 (0.0007) -[2023-10-10 15:21:54,350][76543] Updated weights for policy 0, policy_version 68713 (0.0007) -[2023-10-10 15:21:54,722][76543] Updated weights for policy 0, policy_version 68723 (0.0008) -[2023-10-10 15:21:55,081][76543] Updated weights for policy 0, policy_version 68733 (0.0008) -[2023-10-10 15:21:56,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 140640256. Throughput: 0: 1825.4, 1: 1820.4. Samples: 35164232. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:21:56,077][75634] Avg episode reward: [(0, '35.840'), (1, '35.590')] -[2023-10-10 15:21:57,804][76542] Updated weights for policy 1, policy_version 68610 (0.0008) -[2023-10-10 15:21:58,184][76542] Updated weights for policy 1, policy_version 68620 (0.0011) -[2023-10-10 15:21:58,555][76542] Updated weights for policy 1, policy_version 68630 (0.0010) -[2023-10-10 15:21:58,785][76543] Updated weights for policy 0, policy_version 68743 (0.0008) -[2023-10-10 15:21:58,913][76542] Updated weights for policy 1, policy_version 68640 (0.0008) -[2023-10-10 15:21:59,159][76543] Updated weights for policy 0, policy_version 68753 (0.0008) -[2023-10-10 15:21:59,520][76543] Updated weights for policy 0, policy_version 68763 (0.0008) -[2023-10-10 15:22:01,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 140705792. Throughput: 0: 1829.5, 1: 1815.4. Samples: 35185674. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:22:01,076][75634] Avg episode reward: [(0, '36.820'), (1, '36.140')] -[2023-10-10 15:22:02,648][76542] Updated weights for policy 1, policy_version 68650 (0.0009) -[2023-10-10 15:22:03,017][76542] Updated weights for policy 1, policy_version 68660 (0.0009) -[2023-10-10 15:22:03,336][76543] Updated weights for policy 0, policy_version 68773 (0.0009) -[2023-10-10 15:22:03,384][76542] Updated weights for policy 1, policy_version 68670 (0.0009) -[2023-10-10 15:22:03,720][76543] Updated weights for policy 0, policy_version 68783 (0.0009) -[2023-10-10 15:22:04,094][76543] Updated weights for policy 0, policy_version 68793 (0.0010) -[2023-10-10 15:22:06,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 140771328. Throughput: 0: 1825.9, 1: 1811.4. Samples: 35196970. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:22:06,076][75634] Avg episode reward: [(0, '34.250'), (1, '37.500')] -[2023-10-10 15:22:06,944][76542] Updated weights for policy 1, policy_version 68680 (0.0007) -[2023-10-10 15:22:07,309][76542] Updated weights for policy 1, policy_version 68690 (0.0007) -[2023-10-10 15:22:07,685][76542] Updated weights for policy 1, policy_version 68700 (0.0007) -[2023-10-10 15:22:07,868][76543] Updated weights for policy 0, policy_version 68803 (0.0010) -[2023-10-10 15:22:08,252][76543] Updated weights for policy 0, policy_version 68813 (0.0009) -[2023-10-10 15:22:08,623][76543] Updated weights for policy 0, policy_version 68823 (0.0010) -[2023-10-10 15:22:11,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 140836864. Throughput: 0: 1825.6, 1: 1817.2. Samples: 35218414. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:22:11,077][75634] Avg episode reward: [(0, '33.860'), (1, '38.140')] -[2023-10-10 15:22:11,266][76542] Updated weights for policy 1, policy_version 68710 (0.0010) -[2023-10-10 15:22:11,632][76542] Updated weights for policy 1, policy_version 68720 (0.0010) -[2023-10-10 15:22:12,000][76542] Updated weights for policy 1, policy_version 68730 (0.0010) -[2023-10-10 15:22:12,244][76543] Updated weights for policy 0, policy_version 68833 (0.0009) -[2023-10-10 15:22:12,627][76543] Updated weights for policy 0, policy_version 68843 (0.0010) -[2023-10-10 15:22:12,999][76543] Updated weights for policy 0, policy_version 68853 (0.0008) -[2023-10-10 15:22:13,362][76543] Updated weights for policy 0, policy_version 68863 (0.0008) -[2023-10-10 15:22:15,607][76542] Updated weights for policy 1, policy_version 68740 (0.0010) -[2023-10-10 15:22:15,998][76542] Updated weights for policy 1, policy_version 68750 (0.0009) -[2023-10-10 15:22:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 140902400. Throughput: 0: 1826.5, 1: 1812.5. Samples: 35241012. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:22:16,076][75634] Avg episode reward: [(0, '36.620'), (1, '39.560')] -[2023-10-10 15:22:16,362][76542] Updated weights for policy 1, policy_version 68760 (0.0008) -[2023-10-10 15:22:16,848][76543] Updated weights for policy 0, policy_version 68873 (0.0007) -[2023-10-10 15:22:17,212][76543] Updated weights for policy 0, policy_version 68883 (0.0009) -[2023-10-10 15:22:17,585][76543] Updated weights for policy 0, policy_version 68893 (0.0007) -[2023-10-10 15:22:20,069][76542] Updated weights for policy 1, policy_version 68770 (0.0009) -[2023-10-10 15:22:20,438][76542] Updated weights for policy 1, policy_version 68780 (0.0008) -[2023-10-10 15:22:20,809][76542] Updated weights for policy 1, policy_version 68790 (0.0009) -[2023-10-10 15:22:21,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 140967936. Throughput: 0: 1832.7, 1: 1823.7. Samples: 35251622. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:22:21,076][75634] Avg episode reward: [(0, '39.280'), (1, '35.030')] -[2023-10-10 15:22:21,169][76542] Updated weights for policy 1, policy_version 68800 (0.0008) -[2023-10-10 15:22:21,185][76543] Updated weights for policy 0, policy_version 68903 (0.0008) -[2023-10-10 15:22:21,553][76543] Updated weights for policy 0, policy_version 68913 (0.0008) -[2023-10-10 15:22:21,922][76543] Updated weights for policy 0, policy_version 68923 (0.0010) -[2023-10-10 15:22:25,030][76542] Updated weights for policy 1, policy_version 68810 (0.0007) -[2023-10-10 15:22:25,389][76542] Updated weights for policy 1, policy_version 68820 (0.0007) -[2023-10-10 15:22:25,713][76543] Updated weights for policy 0, policy_version 68933 (0.0008) -[2023-10-10 15:22:25,757][76542] Updated weights for policy 1, policy_version 68830 (0.0007) -[2023-10-10 15:22:26,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 141066240. Throughput: 0: 1829.4, 1: 1826.3. Samples: 35274292. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:22:26,076][75634] Avg episode reward: [(0, '38.750'), (1, '34.200')] -[2023-10-10 15:22:26,087][76543] Updated weights for policy 0, policy_version 68943 (0.0007) -[2023-10-10 15:22:26,456][76543] Updated weights for policy 0, policy_version 68953 (0.0010) -[2023-10-10 15:22:29,497][76542] Updated weights for policy 1, policy_version 68840 (0.0009) -[2023-10-10 15:22:29,870][76542] Updated weights for policy 1, policy_version 68850 (0.0008) -[2023-10-10 15:22:30,150][76543] Updated weights for policy 0, policy_version 68963 (0.0007) -[2023-10-10 15:22:30,245][76542] Updated weights for policy 1, policy_version 68860 (0.0008) -[2023-10-10 15:22:30,519][76543] Updated weights for policy 0, policy_version 68973 (0.0007) -[2023-10-10 15:22:30,900][76543] Updated weights for policy 0, policy_version 68983 (0.0009) -[2023-10-10 15:22:31,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 141131776. Throughput: 0: 1825.9, 1: 1823.0. Samples: 35295124. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:22:31,077][75634] Avg episode reward: [(0, '39.720'), (1, '35.420')] -[2023-10-10 15:22:31,086][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000068864_70516736.pth... -[2023-10-10 15:22:31,122][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000067168_68780032.pth -[2023-10-10 15:22:31,223][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000068992_70647808.pth... -[2023-10-10 15:22:31,262][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000067264_68878336.pth -[2023-10-10 15:22:34,039][76542] Updated weights for policy 1, policy_version 68870 (0.0007) -[2023-10-10 15:22:34,356][76543] Updated weights for policy 0, policy_version 68993 (0.0010) -[2023-10-10 15:22:34,405][76542] Updated weights for policy 1, policy_version 68880 (0.0010) -[2023-10-10 15:22:34,727][76543] Updated weights for policy 0, policy_version 69003 (0.0008) -[2023-10-10 15:22:34,771][76542] Updated weights for policy 1, policy_version 68890 (0.0008) -[2023-10-10 15:22:35,093][76543] Updated weights for policy 0, policy_version 69013 (0.0009) -[2023-10-10 15:22:35,460][76543] Updated weights for policy 0, policy_version 69023 (0.0008) -[2023-10-10 15:22:36,076][75634] Fps is (10 sec: 16384.1, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 141230080. Throughput: 0: 1836.9, 1: 1817.5. Samples: 35307066. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:22:36,076][75634] Avg episode reward: [(0, '35.380'), (1, '34.510')] -[2023-10-10 15:22:38,588][76542] Updated weights for policy 1, policy_version 68900 (0.0007) -[2023-10-10 15:22:38,961][76542] Updated weights for policy 1, policy_version 68910 (0.0007) -[2023-10-10 15:22:39,209][76543] Updated weights for policy 0, policy_version 69033 (0.0010) -[2023-10-10 15:22:39,326][76542] Updated weights for policy 1, policy_version 68920 (0.0008) -[2023-10-10 15:22:39,584][76543] Updated weights for policy 0, policy_version 69043 (0.0009) -[2023-10-10 15:22:39,953][76543] Updated weights for policy 0, policy_version 69053 (0.0009) -[2023-10-10 15:22:41,076][75634] Fps is (10 sec: 16384.4, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 141295616. Throughput: 0: 1828.5, 1: 1810.3. Samples: 35327980. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:22:41,076][75634] Avg episode reward: [(0, '35.310'), (1, '35.580')] -[2023-10-10 15:22:42,901][76542] Updated weights for policy 1, policy_version 68930 (0.0008) -[2023-10-10 15:22:43,278][76542] Updated weights for policy 1, policy_version 68940 (0.0009) -[2023-10-10 15:22:43,574][76543] Updated weights for policy 0, policy_version 69063 (0.0008) -[2023-10-10 15:22:43,655][76542] Updated weights for policy 1, policy_version 68950 (0.0008) -[2023-10-10 15:22:43,945][76543] Updated weights for policy 0, policy_version 69073 (0.0007) -[2023-10-10 15:22:44,013][76542] Updated weights for policy 1, policy_version 68960 (0.0008) -[2023-10-10 15:22:44,308][76543] Updated weights for policy 0, policy_version 69083 (0.0007) -[2023-10-10 15:22:46,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 141361152. Throughput: 0: 1827.4, 1: 1813.5. Samples: 35349512. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:22:46,077][75634] Avg episode reward: [(0, '35.550'), (1, '32.720')] -[2023-10-10 15:22:47,846][76542] Updated weights for policy 1, policy_version 68970 (0.0009) -[2023-10-10 15:22:47,961][76543] Updated weights for policy 0, policy_version 69093 (0.0009) -[2023-10-10 15:22:48,201][76542] Updated weights for policy 1, policy_version 68980 (0.0009) -[2023-10-10 15:22:48,330][76543] Updated weights for policy 0, policy_version 69103 (0.0007) -[2023-10-10 15:22:48,567][76542] Updated weights for policy 1, policy_version 68990 (0.0007) -[2023-10-10 15:22:48,704][76543] Updated weights for policy 0, policy_version 69113 (0.0007) -[2023-10-10 15:22:51,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 141426688. Throughput: 0: 1819.1, 1: 1808.2. Samples: 35360202. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:22:51,077][75634] Avg episode reward: [(0, '40.190'), (1, '34.910')] -[2023-10-10 15:22:52,214][76542] Updated weights for policy 1, policy_version 69000 (0.0007) -[2023-10-10 15:22:52,475][76543] Updated weights for policy 0, policy_version 69123 (0.0008) -[2023-10-10 15:22:52,586][76542] Updated weights for policy 1, policy_version 69010 (0.0007) -[2023-10-10 15:22:52,835][76543] Updated weights for policy 0, policy_version 69133 (0.0007) -[2023-10-10 15:22:52,942][76542] Updated weights for policy 1, policy_version 69020 (0.0007) -[2023-10-10 15:22:53,207][76543] Updated weights for policy 0, policy_version 69143 (0.0007) -[2023-10-10 15:22:56,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 141492224. Throughput: 0: 1832.3, 1: 1802.2. Samples: 35381968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:22:56,077][75634] Avg episode reward: [(0, '43.860'), (1, '36.460')] -[2023-10-10 15:22:56,736][76542] Updated weights for policy 1, policy_version 69030 (0.0010) -[2023-10-10 15:22:56,826][76543] Updated weights for policy 0, policy_version 69153 (0.0009) -[2023-10-10 15:22:57,104][76542] Updated weights for policy 1, policy_version 69040 (0.0009) -[2023-10-10 15:22:57,191][76543] Updated weights for policy 0, policy_version 69163 (0.0007) -[2023-10-10 15:22:57,472][76542] Updated weights for policy 1, policy_version 69050 (0.0007) -[2023-10-10 15:22:57,568][76543] Updated weights for policy 0, policy_version 69173 (0.0007) -[2023-10-10 15:22:57,934][76543] Updated weights for policy 0, policy_version 69183 (0.0007) -[2023-10-10 15:23:01,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 141557760. Throughput: 0: 1832.8, 1: 1799.6. Samples: 35404474. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:23:01,077][75634] Avg episode reward: [(0, '43.150'), (1, '37.860')] -[2023-10-10 15:23:01,369][76542] Updated weights for policy 1, policy_version 69060 (0.0009) -[2023-10-10 15:23:01,713][76543] Updated weights for policy 0, policy_version 69193 (0.0008) -[2023-10-10 15:23:01,739][76542] Updated weights for policy 1, policy_version 69070 (0.0008) -[2023-10-10 15:23:02,068][76543] Updated weights for policy 0, policy_version 69203 (0.0009) -[2023-10-10 15:23:02,108][76542] Updated weights for policy 1, policy_version 69080 (0.0007) -[2023-10-10 15:23:02,438][76543] Updated weights for policy 0, policy_version 69213 (0.0008) -[2023-10-10 15:23:05,721][76542] Updated weights for policy 1, policy_version 69090 (0.0007) -[2023-10-10 15:23:06,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 141623296. Throughput: 0: 1827.4, 1: 1791.3. Samples: 35414466. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:23:06,076][75634] Avg episode reward: [(0, '40.690'), (1, '36.750')] -[2023-10-10 15:23:06,092][76542] Updated weights for policy 1, policy_version 69100 (0.0008) -[2023-10-10 15:23:06,098][76543] Updated weights for policy 0, policy_version 69223 (0.0008) -[2023-10-10 15:23:06,461][76542] Updated weights for policy 1, policy_version 69110 (0.0008) -[2023-10-10 15:23:06,474][76543] Updated weights for policy 0, policy_version 69233 (0.0009) -[2023-10-10 15:23:06,828][76542] Updated weights for policy 1, policy_version 69120 (0.0008) -[2023-10-10 15:23:06,847][76543] Updated weights for policy 0, policy_version 69243 (0.0008) -[2023-10-10 15:23:10,620][76543] Updated weights for policy 0, policy_version 69253 (0.0010) -[2023-10-10 15:23:10,656][76542] Updated weights for policy 1, policy_version 69130 (0.0008) -[2023-10-10 15:23:11,005][76543] Updated weights for policy 0, policy_version 69263 (0.0007) -[2023-10-10 15:23:11,020][76542] Updated weights for policy 1, policy_version 69140 (0.0009) -[2023-10-10 15:23:11,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 141688832. Throughput: 0: 1823.1, 1: 1789.9. Samples: 35436874. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:23:11,076][75634] Avg episode reward: [(0, '37.750'), (1, '35.980')] -[2023-10-10 15:23:11,369][76543] Updated weights for policy 0, policy_version 69273 (0.0008) -[2023-10-10 15:23:11,385][76542] Updated weights for policy 1, policy_version 69150 (0.0008) -[2023-10-10 15:23:15,122][76542] Updated weights for policy 1, policy_version 69160 (0.0008) -[2023-10-10 15:23:15,158][76543] Updated weights for policy 0, policy_version 69283 (0.0008) -[2023-10-10 15:23:15,486][76542] Updated weights for policy 1, policy_version 69170 (0.0007) -[2023-10-10 15:23:15,527][76543] Updated weights for policy 0, policy_version 69293 (0.0008) -[2023-10-10 15:23:15,861][76542] Updated weights for policy 1, policy_version 69180 (0.0008) -[2023-10-10 15:23:15,907][76543] Updated weights for policy 0, policy_version 69303 (0.0008) -[2023-10-10 15:23:16,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 141787136. Throughput: 0: 1820.9, 1: 1795.6. Samples: 35457866. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:23:16,076][75634] Avg episode reward: [(0, '35.490'), (1, '35.150')] -[2023-10-10 15:23:19,657][76542] Updated weights for policy 1, policy_version 69190 (0.0008) -[2023-10-10 15:23:19,739][76543] Updated weights for policy 0, policy_version 69313 (0.0008) -[2023-10-10 15:23:20,031][76542] Updated weights for policy 1, policy_version 69200 (0.0010) -[2023-10-10 15:23:20,105][76543] Updated weights for policy 0, policy_version 69323 (0.0011) -[2023-10-10 15:23:20,394][76542] Updated weights for policy 1, policy_version 69210 (0.0008) -[2023-10-10 15:23:20,479][76543] Updated weights for policy 0, policy_version 69333 (0.0007) -[2023-10-10 15:23:20,846][76543] Updated weights for policy 0, policy_version 69343 (0.0008) -[2023-10-10 15:23:21,076][75634] Fps is (10 sec: 19660.8, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 141885440. Throughput: 0: 1813.1, 1: 1786.0. Samples: 35469024. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:23:21,076][75634] Avg episode reward: [(0, '35.060'), (1, '34.350')] -[2023-10-10 15:23:24,062][76542] Updated weights for policy 1, policy_version 69220 (0.0010) -[2023-10-10 15:23:24,426][76542] Updated weights for policy 1, policy_version 69230 (0.0007) -[2023-10-10 15:23:24,472][76543] Updated weights for policy 0, policy_version 69353 (0.0010) -[2023-10-10 15:23:24,794][76542] Updated weights for policy 1, policy_version 69240 (0.0008) -[2023-10-10 15:23:24,842][76543] Updated weights for policy 0, policy_version 69363 (0.0008) -[2023-10-10 15:23:25,207][76543] Updated weights for policy 0, policy_version 69373 (0.0010) -[2023-10-10 15:23:26,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 141950976. Throughput: 0: 1811.1, 1: 1797.6. Samples: 35490372. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 15:23:26,077][75634] Avg episode reward: [(0, '37.490'), (1, '34.760')] -[2023-10-10 15:23:28,565][76542] Updated weights for policy 1, policy_version 69250 (0.0008) -[2023-10-10 15:23:28,937][76542] Updated weights for policy 1, policy_version 69260 (0.0007) -[2023-10-10 15:23:29,077][76543] Updated weights for policy 0, policy_version 69383 (0.0009) -[2023-10-10 15:23:29,302][76542] Updated weights for policy 1, policy_version 69270 (0.0008) -[2023-10-10 15:23:29,435][76543] Updated weights for policy 0, policy_version 69393 (0.0007) -[2023-10-10 15:23:29,657][76542] Updated weights for policy 1, policy_version 69280 (0.0009) -[2023-10-10 15:23:29,814][76543] Updated weights for policy 0, policy_version 69403 (0.0010) -[2023-10-10 15:23:31,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 142016512. Throughput: 0: 1800.6, 1: 1783.6. Samples: 35510800. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 15:23:31,077][75634] Avg episode reward: [(0, '35.740'), (1, '36.450')] -[2023-10-10 15:23:33,386][76542] Updated weights for policy 1, policy_version 69290 (0.0008) -[2023-10-10 15:23:33,619][76543] Updated weights for policy 0, policy_version 69413 (0.0009) -[2023-10-10 15:23:33,751][76542] Updated weights for policy 1, policy_version 69300 (0.0007) -[2023-10-10 15:23:33,985][76543] Updated weights for policy 0, policy_version 69423 (0.0008) -[2023-10-10 15:23:34,127][76542] Updated weights for policy 1, policy_version 69310 (0.0008) -[2023-10-10 15:23:34,359][76543] Updated weights for policy 0, policy_version 69433 (0.0009) -[2023-10-10 15:23:36,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 142082048. Throughput: 0: 1810.2, 1: 1806.8. Samples: 35522966. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 15:23:36,077][75634] Avg episode reward: [(0, '36.440'), (1, '34.530')] -[2023-10-10 15:23:37,821][76542] Updated weights for policy 1, policy_version 69320 (0.0008) -[2023-10-10 15:23:38,165][76543] Updated weights for policy 0, policy_version 69443 (0.0010) -[2023-10-10 15:23:38,179][76542] Updated weights for policy 1, policy_version 69330 (0.0007) -[2023-10-10 15:23:38,536][76543] Updated weights for policy 0, policy_version 69453 (0.0009) -[2023-10-10 15:23:38,543][76542] Updated weights for policy 1, policy_version 69340 (0.0010) -[2023-10-10 15:23:38,918][76543] Updated weights for policy 0, policy_version 69463 (0.0007) -[2023-10-10 15:23:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 142147584. Throughput: 0: 1798.1, 1: 1791.7. Samples: 35543510. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 15:23:41,077][75634] Avg episode reward: [(0, '33.990'), (1, '35.410')] -[2023-10-10 15:23:42,231][76542] Updated weights for policy 1, policy_version 69350 (0.0011) -[2023-10-10 15:23:42,440][76543] Updated weights for policy 0, policy_version 69473 (0.0009) -[2023-10-10 15:23:42,597][76542] Updated weights for policy 1, policy_version 69360 (0.0007) -[2023-10-10 15:23:42,805][76543] Updated weights for policy 0, policy_version 69483 (0.0007) -[2023-10-10 15:23:42,954][76542] Updated weights for policy 1, policy_version 69370 (0.0008) -[2023-10-10 15:23:43,171][76543] Updated weights for policy 0, policy_version 69493 (0.0008) -[2023-10-10 15:23:43,543][76543] Updated weights for policy 0, policy_version 69503 (0.0009) -[2023-10-10 15:23:46,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 142213120. Throughput: 0: 1802.1, 1: 1805.2. Samples: 35566804. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 15:23:46,077][75634] Avg episode reward: [(0, '34.250'), (1, '35.340')] -[2023-10-10 15:23:46,582][76542] Updated weights for policy 1, policy_version 69380 (0.0007) -[2023-10-10 15:23:46,967][76542] Updated weights for policy 1, policy_version 69390 (0.0007) -[2023-10-10 15:23:47,210][76543] Updated weights for policy 0, policy_version 69513 (0.0009) -[2023-10-10 15:23:47,345][76542] Updated weights for policy 1, policy_version 69400 (0.0008) -[2023-10-10 15:23:47,574][76543] Updated weights for policy 0, policy_version 69523 (0.0008) -[2023-10-10 15:23:47,951][76543] Updated weights for policy 0, policy_version 69533 (0.0011) -[2023-10-10 15:23:51,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 142278656. Throughput: 0: 1798.1, 1: 1800.3. Samples: 35576396. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 15:23:51,077][75634] Avg episode reward: [(0, '35.060'), (1, '32.680')] -[2023-10-10 15:23:51,245][76542] Updated weights for policy 1, policy_version 69410 (0.0009) -[2023-10-10 15:23:51,571][76543] Updated weights for policy 0, policy_version 69543 (0.0010) -[2023-10-10 15:23:51,613][76542] Updated weights for policy 1, policy_version 69420 (0.0008) -[2023-10-10 15:23:51,950][76543] Updated weights for policy 0, policy_version 69553 (0.0008) -[2023-10-10 15:23:51,981][76542] Updated weights for policy 1, policy_version 69430 (0.0008) -[2023-10-10 15:23:52,329][76543] Updated weights for policy 0, policy_version 69563 (0.0009) -[2023-10-10 15:23:52,346][76542] Updated weights for policy 1, policy_version 69440 (0.0007) -[2023-10-10 15:23:56,019][76542] Updated weights for policy 1, policy_version 69450 (0.0009) -[2023-10-10 15:23:56,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 142344192. Throughput: 0: 1799.1, 1: 1803.4. Samples: 35598986. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 15:23:56,077][75634] Avg episode reward: [(0, '33.040'), (1, '32.940')] -[2023-10-10 15:23:56,107][76543] Updated weights for policy 0, policy_version 69573 (0.0008) -[2023-10-10 15:23:56,386][76542] Updated weights for policy 1, policy_version 69460 (0.0007) -[2023-10-10 15:23:56,487][76543] Updated weights for policy 0, policy_version 69583 (0.0007) -[2023-10-10 15:23:56,751][76542] Updated weights for policy 1, policy_version 69470 (0.0008) -[2023-10-10 15:23:56,862][76543] Updated weights for policy 0, policy_version 69593 (0.0007) -[2023-10-10 15:24:00,583][76542] Updated weights for policy 1, policy_version 69480 (0.0008) -[2023-10-10 15:24:00,608][76543] Updated weights for policy 0, policy_version 69603 (0.0009) -[2023-10-10 15:24:00,945][76542] Updated weights for policy 1, policy_version 69490 (0.0008) -[2023-10-10 15:24:00,976][76543] Updated weights for policy 0, policy_version 69613 (0.0009) -[2023-10-10 15:24:01,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 142409728. Throughput: 0: 1801.2, 1: 1821.1. Samples: 35620872. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 15:24:01,077][75634] Avg episode reward: [(0, '31.960'), (1, '31.560')] -[2023-10-10 15:24:01,310][76542] Updated weights for policy 1, policy_version 69500 (0.0008) -[2023-10-10 15:24:01,348][76543] Updated weights for policy 0, policy_version 69623 (0.0007) -[2023-10-10 15:24:05,055][76543] Updated weights for policy 0, policy_version 69633 (0.0009) -[2023-10-10 15:24:05,146][76542] Updated weights for policy 1, policy_version 69510 (0.0008) -[2023-10-10 15:24:05,409][76543] Updated weights for policy 0, policy_version 69643 (0.0007) -[2023-10-10 15:24:05,510][76542] Updated weights for policy 1, policy_version 69520 (0.0009) -[2023-10-10 15:24:05,780][76543] Updated weights for policy 0, policy_version 69653 (0.0007) -[2023-10-10 15:24:05,881][76542] Updated weights for policy 1, policy_version 69530 (0.0008) -[2023-10-10 15:24:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 142475264. Throughput: 0: 1795.4, 1: 1807.4. Samples: 35631150. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-10 15:24:06,077][75634] Avg episode reward: [(0, '32.210'), (1, '35.250')] -[2023-10-10 15:24:06,154][76543] Updated weights for policy 0, policy_version 69663 (0.0009) -[2023-10-10 15:24:09,509][76542] Updated weights for policy 1, policy_version 69540 (0.0008) -[2023-10-10 15:24:09,826][76543] Updated weights for policy 0, policy_version 69673 (0.0007) -[2023-10-10 15:24:09,877][76542] Updated weights for policy 1, policy_version 69550 (0.0008) -[2023-10-10 15:24:10,193][76543] Updated weights for policy 0, policy_version 69683 (0.0007) -[2023-10-10 15:24:10,237][76542] Updated weights for policy 1, policy_version 69560 (0.0009) -[2023-10-10 15:24:10,559][76543] Updated weights for policy 0, policy_version 69693 (0.0007) -[2023-10-10 15:24:11,076][75634] Fps is (10 sec: 19660.8, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 142606336. Throughput: 0: 1804.7, 1: 1819.4. Samples: 35653456. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-10 15:24:11,077][75634] Avg episode reward: [(0, '32.210'), (1, '36.540')] -[2023-10-10 15:24:13,785][76542] Updated weights for policy 1, policy_version 69570 (0.0009) -[2023-10-10 15:24:14,153][76542] Updated weights for policy 1, policy_version 69580 (0.0009) -[2023-10-10 15:24:14,205][76543] Updated weights for policy 0, policy_version 69703 (0.0009) -[2023-10-10 15:24:14,519][76542] Updated weights for policy 1, policy_version 69590 (0.0008) -[2023-10-10 15:24:14,577][76543] Updated weights for policy 0, policy_version 69713 (0.0009) -[2023-10-10 15:24:14,892][76542] Updated weights for policy 1, policy_version 69600 (0.0008) -[2023-10-10 15:24:14,942][76543] Updated weights for policy 0, policy_version 69723 (0.0010) -[2023-10-10 15:24:16,076][75634] Fps is (10 sec: 19661.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 142671872. Throughput: 0: 1812.6, 1: 1805.4. Samples: 35673612. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-10 15:24:16,076][75634] Avg episode reward: [(0, '37.940'), (1, '37.130')] -[2023-10-10 15:24:18,541][76543] Updated weights for policy 0, policy_version 69733 (0.0007) -[2023-10-10 15:24:18,656][76542] Updated weights for policy 1, policy_version 69610 (0.0008) -[2023-10-10 15:24:18,911][76543] Updated weights for policy 0, policy_version 69743 (0.0007) -[2023-10-10 15:24:19,016][76542] Updated weights for policy 1, policy_version 69620 (0.0007) -[2023-10-10 15:24:19,286][76543] Updated weights for policy 0, policy_version 69753 (0.0008) -[2023-10-10 15:24:19,392][76542] Updated weights for policy 1, policy_version 69630 (0.0007) -[2023-10-10 15:24:21,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 142737408. Throughput: 0: 1815.1, 1: 1808.9. Samples: 35686044. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-10 15:24:21,077][75634] Avg episode reward: [(0, '38.600'), (1, '38.340')] -[2023-10-10 15:24:23,071][76543] Updated weights for policy 0, policy_version 69763 (0.0010) -[2023-10-10 15:24:23,150][76542] Updated weights for policy 1, policy_version 69640 (0.0008) -[2023-10-10 15:24:23,442][76543] Updated weights for policy 0, policy_version 69773 (0.0008) -[2023-10-10 15:24:23,521][76542] Updated weights for policy 1, policy_version 69650 (0.0008) -[2023-10-10 15:24:23,820][76543] Updated weights for policy 0, policy_version 69783 (0.0009) -[2023-10-10 15:24:23,886][76542] Updated weights for policy 1, policy_version 69660 (0.0009) -[2023-10-10 15:24:26,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 142802944. Throughput: 0: 1813.8, 1: 1805.5. Samples: 35706378. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-10 15:24:26,077][75634] Avg episode reward: [(0, '39.270'), (1, '35.100')] -[2023-10-10 15:24:27,567][76543] Updated weights for policy 0, policy_version 69793 (0.0009) -[2023-10-10 15:24:27,572][76542] Updated weights for policy 1, policy_version 69670 (0.0007) -[2023-10-10 15:24:27,932][76542] Updated weights for policy 1, policy_version 69680 (0.0008) -[2023-10-10 15:24:27,940][76543] Updated weights for policy 0, policy_version 69803 (0.0007) -[2023-10-10 15:24:28,297][76542] Updated weights for policy 1, policy_version 69690 (0.0007) -[2023-10-10 15:24:28,308][76543] Updated weights for policy 0, policy_version 69813 (0.0007) -[2023-10-10 15:24:28,677][76543] Updated weights for policy 0, policy_version 69823 (0.0007) -[2023-10-10 15:24:31,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 142868480. Throughput: 0: 1806.5, 1: 1805.5. Samples: 35729342. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-10 15:24:31,076][75634] Avg episode reward: [(0, '34.780'), (1, '35.060')] -[2023-10-10 15:24:31,085][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000069824_71499776.pth... -[2023-10-10 15:24:31,086][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000069696_71368704.pth... -[2023-10-10 15:24:31,115][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000068128_69763072.pth -[2023-10-10 15:24:31,127][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000068000_69632000.pth -[2023-10-10 15:24:32,106][76542] Updated weights for policy 1, policy_version 69700 (0.0008) -[2023-10-10 15:24:32,486][76542] Updated weights for policy 1, policy_version 69710 (0.0009) -[2023-10-10 15:24:32,497][76543] Updated weights for policy 0, policy_version 69833 (0.0007) -[2023-10-10 15:24:32,861][76542] Updated weights for policy 1, policy_version 69720 (0.0010) -[2023-10-10 15:24:32,865][76543] Updated weights for policy 0, policy_version 69843 (0.0007) -[2023-10-10 15:24:33,225][76543] Updated weights for policy 0, policy_version 69853 (0.0008) -[2023-10-10 15:24:36,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 142934016. Throughput: 0: 1812.2, 1: 1808.5. Samples: 35739330. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-10 15:24:36,076][75634] Avg episode reward: [(0, '33.890'), (1, '34.700')] -[2023-10-10 15:24:36,521][76542] Updated weights for policy 1, policy_version 69730 (0.0007) -[2023-10-10 15:24:36,854][76543] Updated weights for policy 0, policy_version 69863 (0.0008) -[2023-10-10 15:24:36,883][76542] Updated weights for policy 1, policy_version 69740 (0.0009) -[2023-10-10 15:24:37,220][76543] Updated weights for policy 0, policy_version 69873 (0.0007) -[2023-10-10 15:24:37,258][76542] Updated weights for policy 1, policy_version 69750 (0.0009) -[2023-10-10 15:24:37,588][76543] Updated weights for policy 0, policy_version 69883 (0.0008) -[2023-10-10 15:24:37,618][76542] Updated weights for policy 1, policy_version 69760 (0.0009) -[2023-10-10 15:24:41,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 142999552. Throughput: 0: 1805.7, 1: 1812.5. Samples: 35761804. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-10 15:24:41,076][75634] Avg episode reward: [(0, '33.920'), (1, '34.950')] -[2023-10-10 15:24:41,318][76542] Updated weights for policy 1, policy_version 69770 (0.0007) -[2023-10-10 15:24:41,331][76543] Updated weights for policy 0, policy_version 69893 (0.0008) -[2023-10-10 15:24:41,674][76542] Updated weights for policy 1, policy_version 69780 (0.0007) -[2023-10-10 15:24:41,719][76543] Updated weights for policy 0, policy_version 69903 (0.0007) -[2023-10-10 15:24:42,046][76542] Updated weights for policy 1, policy_version 69790 (0.0007) -[2023-10-10 15:24:42,090][76543] Updated weights for policy 0, policy_version 69913 (0.0009) -[2023-10-10 15:24:45,789][76542] Updated weights for policy 1, policy_version 69800 (0.0007) -[2023-10-10 15:24:45,804][76543] Updated weights for policy 0, policy_version 69923 (0.0007) -[2023-10-10 15:24:46,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 143065088. Throughput: 0: 1807.8, 1: 1814.1. Samples: 35783854. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-10 15:24:46,077][75634] Avg episode reward: [(0, '35.330'), (1, '34.220')] -[2023-10-10 15:24:46,145][76542] Updated weights for policy 1, policy_version 69810 (0.0007) -[2023-10-10 15:24:46,162][76543] Updated weights for policy 0, policy_version 69933 (0.0009) -[2023-10-10 15:24:46,524][76542] Updated weights for policy 1, policy_version 69820 (0.0007) -[2023-10-10 15:24:46,548][76543] Updated weights for policy 0, policy_version 69943 (0.0009) -[2023-10-10 15:24:50,260][76542] Updated weights for policy 1, policy_version 69830 (0.0007) -[2023-10-10 15:24:50,262][76543] Updated weights for policy 0, policy_version 69953 (0.0008) -[2023-10-10 15:24:50,626][76542] Updated weights for policy 1, policy_version 69840 (0.0007) -[2023-10-10 15:24:50,631][76543] Updated weights for policy 0, policy_version 69963 (0.0007) -[2023-10-10 15:24:50,982][76542] Updated weights for policy 1, policy_version 69850 (0.0007) -[2023-10-10 15:24:51,000][76543] Updated weights for policy 0, policy_version 69973 (0.0009) -[2023-10-10 15:24:51,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 143130624. Throughput: 0: 1808.5, 1: 1809.8. Samples: 35793970. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-10 15:24:51,076][75634] Avg episode reward: [(0, '37.320'), (1, '33.960')] -[2023-10-10 15:24:51,371][76543] Updated weights for policy 0, policy_version 69983 (0.0008) -[2023-10-10 15:24:54,658][76542] Updated weights for policy 1, policy_version 69860 (0.0008) -[2023-10-10 15:24:55,024][76542] Updated weights for policy 1, policy_version 69870 (0.0008) -[2023-10-10 15:24:55,067][76543] Updated weights for policy 0, policy_version 69993 (0.0007) -[2023-10-10 15:24:55,390][76542] Updated weights for policy 1, policy_version 69880 (0.0007) -[2023-10-10 15:24:55,436][76543] Updated weights for policy 0, policy_version 70003 (0.0008) -[2023-10-10 15:24:55,813][76543] Updated weights for policy 0, policy_version 70013 (0.0007) -[2023-10-10 15:24:56,076][75634] Fps is (10 sec: 19660.5, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 143261696. Throughput: 0: 1805.6, 1: 1816.8. Samples: 35816462. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:24:56,077][75634] Avg episode reward: [(0, '39.220'), (1, '37.390')] -[2023-10-10 15:24:59,081][76542] Updated weights for policy 1, policy_version 69890 (0.0007) -[2023-10-10 15:24:59,447][76542] Updated weights for policy 1, policy_version 69900 (0.0008) -[2023-10-10 15:24:59,488][76543] Updated weights for policy 0, policy_version 70023 (0.0009) -[2023-10-10 15:24:59,819][76542] Updated weights for policy 1, policy_version 69910 (0.0009) -[2023-10-10 15:24:59,857][76543] Updated weights for policy 0, policy_version 70033 (0.0010) -[2023-10-10 15:25:00,190][76542] Updated weights for policy 1, policy_version 69920 (0.0007) -[2023-10-10 15:25:00,229][76543] Updated weights for policy 0, policy_version 70043 (0.0009) -[2023-10-10 15:25:01,076][75634] Fps is (10 sec: 19660.6, 60 sec: 15291.8, 300 sec: 14551.2). Total num frames: 143327232. Throughput: 0: 1810.1, 1: 1819.2. Samples: 35836932. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:25:01,077][75634] Avg episode reward: [(0, '37.430'), (1, '39.500')] -[2023-10-10 15:25:03,860][76542] Updated weights for policy 1, policy_version 69930 (0.0008) -[2023-10-10 15:25:03,877][76543] Updated weights for policy 0, policy_version 70053 (0.0008) -[2023-10-10 15:25:04,235][76542] Updated weights for policy 1, policy_version 69940 (0.0008) -[2023-10-10 15:25:04,245][76543] Updated weights for policy 0, policy_version 70063 (0.0008) -[2023-10-10 15:25:04,600][76542] Updated weights for policy 1, policy_version 69950 (0.0009) -[2023-10-10 15:25:04,610][76543] Updated weights for policy 0, policy_version 70073 (0.0008) -[2023-10-10 15:25:06,076][75634] Fps is (10 sec: 13107.5, 60 sec: 15291.8, 300 sec: 14551.2). Total num frames: 143392768. Throughput: 0: 1800.4, 1: 1830.2. Samples: 35849420. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:25:06,076][75634] Avg episode reward: [(0, '34.450'), (1, '33.120')] -[2023-10-10 15:25:08,422][76542] Updated weights for policy 1, policy_version 69960 (0.0007) -[2023-10-10 15:25:08,457][76543] Updated weights for policy 0, policy_version 70083 (0.0008) -[2023-10-10 15:25:08,786][76542] Updated weights for policy 1, policy_version 69970 (0.0008) -[2023-10-10 15:25:08,823][76543] Updated weights for policy 0, policy_version 70093 (0.0008) -[2023-10-10 15:25:09,153][76542] Updated weights for policy 1, policy_version 69980 (0.0008) -[2023-10-10 15:25:09,195][76543] Updated weights for policy 0, policy_version 70103 (0.0008) -[2023-10-10 15:25:11,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 143458304. Throughput: 0: 1809.5, 1: 1819.2. Samples: 35869668. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:25:11,076][75634] Avg episode reward: [(0, '38.460'), (1, '32.390')] -[2023-10-10 15:25:12,852][76542] Updated weights for policy 1, policy_version 69990 (0.0010) -[2023-10-10 15:25:12,999][76543] Updated weights for policy 0, policy_version 70113 (0.0008) -[2023-10-10 15:25:13,210][76542] Updated weights for policy 1, policy_version 70000 (0.0008) -[2023-10-10 15:25:13,366][76543] Updated weights for policy 0, policy_version 70123 (0.0007) -[2023-10-10 15:25:13,581][76542] Updated weights for policy 1, policy_version 70010 (0.0008) -[2023-10-10 15:25:13,732][76543] Updated weights for policy 0, policy_version 70133 (0.0008) -[2023-10-10 15:25:14,108][76543] Updated weights for policy 0, policy_version 70143 (0.0009) -[2023-10-10 15:25:16,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 143523840. Throughput: 0: 1803.0, 1: 1809.4. Samples: 35891898. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:25:16,077][75634] Avg episode reward: [(0, '39.270'), (1, '34.710')] -[2023-10-10 15:25:17,259][76542] Updated weights for policy 1, policy_version 70020 (0.0007) -[2023-10-10 15:25:17,646][76542] Updated weights for policy 1, policy_version 70030 (0.0009) -[2023-10-10 15:25:17,734][76543] Updated weights for policy 0, policy_version 70153 (0.0007) -[2023-10-10 15:25:18,013][76542] Updated weights for policy 1, policy_version 70040 (0.0008) -[2023-10-10 15:25:18,097][76543] Updated weights for policy 0, policy_version 70163 (0.0007) -[2023-10-10 15:25:18,480][76543] Updated weights for policy 0, policy_version 70173 (0.0007) -[2023-10-10 15:25:21,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 143589376. Throughput: 0: 1815.3, 1: 1808.0. Samples: 35902380. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:25:21,077][75634] Avg episode reward: [(0, '37.880'), (1, '34.760')] -[2023-10-10 15:25:21,752][76542] Updated weights for policy 1, policy_version 70050 (0.0007) -[2023-10-10 15:25:22,129][76542] Updated weights for policy 1, policy_version 70060 (0.0007) -[2023-10-10 15:25:22,157][76543] Updated weights for policy 0, policy_version 70183 (0.0007) -[2023-10-10 15:25:22,491][76542] Updated weights for policy 1, policy_version 70070 (0.0008) -[2023-10-10 15:25:22,531][76543] Updated weights for policy 0, policy_version 70193 (0.0008) -[2023-10-10 15:25:22,862][76542] Updated weights for policy 1, policy_version 70080 (0.0007) -[2023-10-10 15:25:22,889][76543] Updated weights for policy 0, policy_version 70203 (0.0007) -[2023-10-10 15:25:26,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 143654912. Throughput: 0: 1811.8, 1: 1806.6. Samples: 35924634. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:25:26,076][75634] Avg episode reward: [(0, '37.430'), (1, '33.610')] -[2023-10-10 15:25:26,600][76542] Updated weights for policy 1, policy_version 70090 (0.0008) -[2023-10-10 15:25:26,677][76543] Updated weights for policy 0, policy_version 70213 (0.0008) -[2023-10-10 15:25:26,970][76542] Updated weights for policy 1, policy_version 70100 (0.0007) -[2023-10-10 15:25:27,070][76543] Updated weights for policy 0, policy_version 70223 (0.0008) -[2023-10-10 15:25:27,338][76542] Updated weights for policy 1, policy_version 70110 (0.0008) -[2023-10-10 15:25:27,436][76543] Updated weights for policy 0, policy_version 70233 (0.0007) -[2023-10-10 15:25:31,015][76542] Updated weights for policy 1, policy_version 70120 (0.0012) -[2023-10-10 15:25:31,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 143720448. Throughput: 0: 1811.0, 1: 1815.9. Samples: 35947066. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:25:31,077][75634] Avg episode reward: [(0, '35.480'), (1, '33.390')] -[2023-10-10 15:25:31,204][76543] Updated weights for policy 0, policy_version 70243 (0.0010) -[2023-10-10 15:25:31,373][76542] Updated weights for policy 1, policy_version 70130 (0.0009) -[2023-10-10 15:25:31,573][76543] Updated weights for policy 0, policy_version 70253 (0.0008) -[2023-10-10 15:25:31,754][76542] Updated weights for policy 1, policy_version 70140 (0.0007) -[2023-10-10 15:25:31,935][76543] Updated weights for policy 0, policy_version 70263 (0.0008) -[2023-10-10 15:25:35,402][76542] Updated weights for policy 1, policy_version 70150 (0.0009) -[2023-10-10 15:25:35,603][76543] Updated weights for policy 0, policy_version 70273 (0.0010) -[2023-10-10 15:25:35,779][76542] Updated weights for policy 1, policy_version 70160 (0.0009) -[2023-10-10 15:25:35,969][76543] Updated weights for policy 0, policy_version 70283 (0.0008) -[2023-10-10 15:25:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 143785984. Throughput: 0: 1811.5, 1: 1810.2. Samples: 35956948. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:25:36,076][75634] Avg episode reward: [(0, '39.560'), (1, '36.260')] -[2023-10-10 15:25:36,140][76542] Updated weights for policy 1, policy_version 70170 (0.0009) -[2023-10-10 15:25:36,343][76543] Updated weights for policy 0, policy_version 70293 (0.0007) -[2023-10-10 15:25:36,713][76543] Updated weights for policy 0, policy_version 70303 (0.0007) -[2023-10-10 15:25:39,745][76542] Updated weights for policy 1, policy_version 70180 (0.0008) -[2023-10-10 15:25:40,104][76542] Updated weights for policy 1, policy_version 70190 (0.0009) -[2023-10-10 15:25:40,296][76543] Updated weights for policy 0, policy_version 70313 (0.0007) -[2023-10-10 15:25:40,471][76542] Updated weights for policy 1, policy_version 70200 (0.0008) -[2023-10-10 15:25:40,663][76543] Updated weights for policy 0, policy_version 70323 (0.0007) -[2023-10-10 15:25:41,033][76543] Updated weights for policy 0, policy_version 70333 (0.0008) -[2023-10-10 15:25:41,076][75634] Fps is (10 sec: 16384.5, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 143884288. Throughput: 0: 1814.9, 1: 1811.2. Samples: 35979636. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:25:41,076][75634] Avg episode reward: [(0, '38.010'), (1, '35.630')] -[2023-10-10 15:25:44,162][76542] Updated weights for policy 1, policy_version 70210 (0.0008) -[2023-10-10 15:25:44,537][76542] Updated weights for policy 1, policy_version 70220 (0.0009) -[2023-10-10 15:25:44,885][76543] Updated weights for policy 0, policy_version 70343 (0.0008) -[2023-10-10 15:25:44,905][76542] Updated weights for policy 1, policy_version 70230 (0.0008) -[2023-10-10 15:25:45,245][76543] Updated weights for policy 0, policy_version 70353 (0.0008) -[2023-10-10 15:25:45,269][76542] Updated weights for policy 1, policy_version 70240 (0.0007) -[2023-10-10 15:25:45,619][76543] Updated weights for policy 0, policy_version 70363 (0.0010) -[2023-10-10 15:25:46,076][75634] Fps is (10 sec: 19660.2, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 143982592. Throughput: 0: 1822.3, 1: 1807.8. Samples: 36000288. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 15:25:46,077][75634] Avg episode reward: [(0, '38.130'), (1, '35.980')] -[2023-10-10 15:25:48,917][76542] Updated weights for policy 1, policy_version 70250 (0.0008) -[2023-10-10 15:25:49,211][76543] Updated weights for policy 0, policy_version 70373 (0.0008) -[2023-10-10 15:25:49,279][76542] Updated weights for policy 1, policy_version 70260 (0.0010) -[2023-10-10 15:25:49,581][76543] Updated weights for policy 0, policy_version 70383 (0.0007) -[2023-10-10 15:25:49,655][76542] Updated weights for policy 1, policy_version 70270 (0.0009) -[2023-10-10 15:25:49,957][76543] Updated weights for policy 0, policy_version 70393 (0.0009) -[2023-10-10 15:25:51,076][75634] Fps is (10 sec: 16383.7, 60 sec: 15291.7, 300 sec: 14551.2). Total num frames: 144048128. Throughput: 0: 1813.2, 1: 1806.4. Samples: 36012306. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 15:25:51,077][75634] Avg episode reward: [(0, '39.870'), (1, '31.570')] -[2023-10-10 15:25:53,424][76542] Updated weights for policy 1, policy_version 70280 (0.0008) -[2023-10-10 15:25:53,627][76543] Updated weights for policy 0, policy_version 70403 (0.0010) -[2023-10-10 15:25:53,793][76542] Updated weights for policy 1, policy_version 70290 (0.0007) -[2023-10-10 15:25:53,987][76543] Updated weights for policy 0, policy_version 70413 (0.0009) -[2023-10-10 15:25:54,152][76542] Updated weights for policy 1, policy_version 70300 (0.0008) -[2023-10-10 15:25:54,353][76543] Updated weights for policy 0, policy_version 70423 (0.0009) -[2023-10-10 15:25:56,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 144113664. Throughput: 0: 1826.2, 1: 1807.5. Samples: 36033184. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 15:25:56,077][75634] Avg episode reward: [(0, '34.590'), (1, '34.580')] -[2023-10-10 15:25:57,840][76542] Updated weights for policy 1, policy_version 70310 (0.0009) -[2023-10-10 15:25:58,072][76543] Updated weights for policy 0, policy_version 70433 (0.0009) -[2023-10-10 15:25:58,202][76542] Updated weights for policy 1, policy_version 70320 (0.0009) -[2023-10-10 15:25:58,445][76543] Updated weights for policy 0, policy_version 70443 (0.0007) -[2023-10-10 15:25:58,577][76542] Updated weights for policy 1, policy_version 70330 (0.0008) -[2023-10-10 15:25:58,806][76543] Updated weights for policy 0, policy_version 70453 (0.0008) -[2023-10-10 15:25:59,181][76543] Updated weights for policy 0, policy_version 70463 (0.0008) -[2023-10-10 15:26:01,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 144179200. Throughput: 0: 1816.2, 1: 1810.1. Samples: 36055084. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 15:26:01,076][75634] Avg episode reward: [(0, '33.620'), (1, '36.870')] -[2023-10-10 15:26:02,453][76542] Updated weights for policy 1, policy_version 70340 (0.0009) -[2023-10-10 15:26:02,825][76543] Updated weights for policy 0, policy_version 70473 (0.0007) -[2023-10-10 15:26:02,845][76542] Updated weights for policy 1, policy_version 70350 (0.0009) -[2023-10-10 15:26:03,195][76543] Updated weights for policy 0, policy_version 70483 (0.0008) -[2023-10-10 15:26:03,216][76542] Updated weights for policy 1, policy_version 70360 (0.0008) -[2023-10-10 15:26:03,556][76543] Updated weights for policy 0, policy_version 70493 (0.0008) -[2023-10-10 15:26:06,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 144244736. Throughput: 0: 1820.1, 1: 1807.0. Samples: 36065600. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 15:26:06,077][75634] Avg episode reward: [(0, '35.190'), (1, '36.930')] -[2023-10-10 15:26:06,968][76542] Updated weights for policy 1, policy_version 70370 (0.0008) -[2023-10-10 15:26:07,337][76542] Updated weights for policy 1, policy_version 70380 (0.0009) -[2023-10-10 15:26:07,347][76543] Updated weights for policy 0, policy_version 70503 (0.0008) -[2023-10-10 15:26:07,699][76542] Updated weights for policy 1, policy_version 70390 (0.0009) -[2023-10-10 15:26:07,719][76543] Updated weights for policy 0, policy_version 70513 (0.0009) -[2023-10-10 15:26:08,063][76542] Updated weights for policy 1, policy_version 70400 (0.0008) -[2023-10-10 15:26:08,083][76543] Updated weights for policy 0, policy_version 70523 (0.0007) -[2023-10-10 15:26:11,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 144310272. Throughput: 0: 1816.4, 1: 1808.9. Samples: 36087772. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 15:26:11,077][75634] Avg episode reward: [(0, '34.830'), (1, '35.160')] -[2023-10-10 15:26:11,746][76542] Updated weights for policy 1, policy_version 70410 (0.0009) -[2023-10-10 15:26:11,825][76543] Updated weights for policy 0, policy_version 70533 (0.0008) -[2023-10-10 15:26:12,103][76542] Updated weights for policy 1, policy_version 70420 (0.0007) -[2023-10-10 15:26:12,201][76543] Updated weights for policy 0, policy_version 70543 (0.0009) -[2023-10-10 15:26:12,475][76542] Updated weights for policy 1, policy_version 70430 (0.0008) -[2023-10-10 15:26:12,561][76543] Updated weights for policy 0, policy_version 70553 (0.0007) -[2023-10-10 15:26:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 144375808. Throughput: 0: 1815.3, 1: 1805.9. Samples: 36110020. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 15:26:16,077][75634] Avg episode reward: [(0, '37.900'), (1, '37.470')] -[2023-10-10 15:26:16,164][76542] Updated weights for policy 1, policy_version 70440 (0.0009) -[2023-10-10 15:26:16,316][76543] Updated weights for policy 0, policy_version 70563 (0.0007) -[2023-10-10 15:26:16,529][76542] Updated weights for policy 1, policy_version 70450 (0.0009) -[2023-10-10 15:26:16,689][76543] Updated weights for policy 0, policy_version 70573 (0.0007) -[2023-10-10 15:26:16,900][76542] Updated weights for policy 1, policy_version 70460 (0.0009) -[2023-10-10 15:26:17,057][76543] Updated weights for policy 0, policy_version 70583 (0.0007) -[2023-10-10 15:26:20,624][76542] Updated weights for policy 1, policy_version 70470 (0.0009) -[2023-10-10 15:26:20,786][76543] Updated weights for policy 0, policy_version 70593 (0.0008) -[2023-10-10 15:26:20,985][76542] Updated weights for policy 1, policy_version 70480 (0.0008) -[2023-10-10 15:26:21,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 144441344. Throughput: 0: 1814.0, 1: 1803.5. Samples: 36119734. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 15:26:21,076][75634] Avg episode reward: [(0, '34.550'), (1, '41.480')] -[2023-10-10 15:26:21,157][76543] Updated weights for policy 0, policy_version 70603 (0.0008) -[2023-10-10 15:26:21,345][76542] Updated weights for policy 1, policy_version 70490 (0.0008) -[2023-10-10 15:26:21,523][76543] Updated weights for policy 0, policy_version 70613 (0.0009) -[2023-10-10 15:26:21,878][76543] Updated weights for policy 0, policy_version 70623 (0.0009) -[2023-10-10 15:26:25,098][76542] Updated weights for policy 1, policy_version 70500 (0.0009) -[2023-10-10 15:26:25,477][76542] Updated weights for policy 1, policy_version 70510 (0.0007) -[2023-10-10 15:26:25,589][76543] Updated weights for policy 0, policy_version 70633 (0.0008) -[2023-10-10 15:26:25,835][76542] Updated weights for policy 1, policy_version 70520 (0.0007) -[2023-10-10 15:26:25,969][76543] Updated weights for policy 0, policy_version 70643 (0.0007) -[2023-10-10 15:26:26,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 144506880. Throughput: 0: 1811.9, 1: 1809.6. Samples: 36142602. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 15:26:26,076][75634] Avg episode reward: [(0, '31.510'), (1, '42.040')] -[2023-10-10 15:26:26,126][76421] Saving new best policy, reward=42.040! -[2023-10-10 15:26:26,331][76543] Updated weights for policy 0, policy_version 70653 (0.0007) -[2023-10-10 15:26:29,595][76542] Updated weights for policy 1, policy_version 70530 (0.0007) -[2023-10-10 15:26:29,963][76542] Updated weights for policy 1, policy_version 70540 (0.0009) -[2023-10-10 15:26:30,115][76543] Updated weights for policy 0, policy_version 70663 (0.0008) -[2023-10-10 15:26:30,326][76542] Updated weights for policy 1, policy_version 70550 (0.0007) -[2023-10-10 15:26:30,480][76543] Updated weights for policy 0, policy_version 70673 (0.0008) -[2023-10-10 15:26:30,695][76542] Updated weights for policy 1, policy_version 70560 (0.0008) -[2023-10-10 15:26:30,856][76543] Updated weights for policy 0, policy_version 70683 (0.0009) -[2023-10-10 15:26:31,076][75634] Fps is (10 sec: 19660.2, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 144637952. Throughput: 0: 1816.0, 1: 1808.3. Samples: 36163378. Policy #0 lag: (min: 3.0, avg: 5.9, max: 35.0) -[2023-10-10 15:26:31,077][75634] Avg episode reward: [(0, '34.090'), (1, '39.180')] -[2023-10-10 15:26:31,088][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000070560_72253440.pth... -[2023-10-10 15:26:31,088][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000070688_72384512.pth... -[2023-10-10 15:26:31,124][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000068992_70647808.pth -[2023-10-10 15:26:31,129][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000068864_70516736.pth -[2023-10-10 15:26:34,325][76542] Updated weights for policy 1, policy_version 70570 (0.0008) -[2023-10-10 15:26:34,438][76543] Updated weights for policy 0, policy_version 70693 (0.0009) -[2023-10-10 15:26:34,690][76542] Updated weights for policy 1, policy_version 70580 (0.0007) -[2023-10-10 15:26:34,805][76543] Updated weights for policy 0, policy_version 70703 (0.0008) -[2023-10-10 15:26:35,056][76542] Updated weights for policy 1, policy_version 70590 (0.0009) -[2023-10-10 15:26:35,167][76543] Updated weights for policy 0, policy_version 70713 (0.0008) -[2023-10-10 15:26:36,076][75634] Fps is (10 sec: 19660.6, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 144703488. Throughput: 0: 1810.9, 1: 1814.2. Samples: 36175434. Policy #0 lag: (min: 3.0, avg: 5.9, max: 35.0) -[2023-10-10 15:26:36,076][75634] Avg episode reward: [(0, '33.240'), (1, '38.760')] -[2023-10-10 15:26:38,647][76543] Updated weights for policy 0, policy_version 70723 (0.0007) -[2023-10-10 15:26:38,687][76542] Updated weights for policy 1, policy_version 70600 (0.0008) -[2023-10-10 15:26:39,018][76543] Updated weights for policy 0, policy_version 70733 (0.0007) -[2023-10-10 15:26:39,055][76542] Updated weights for policy 1, policy_version 70610 (0.0008) -[2023-10-10 15:26:39,381][76543] Updated weights for policy 0, policy_version 70743 (0.0009) -[2023-10-10 15:26:39,418][76542] Updated weights for policy 1, policy_version 70620 (0.0008) -[2023-10-10 15:26:41,076][75634] Fps is (10 sec: 13107.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 144769024. Throughput: 0: 1812.9, 1: 1812.0. Samples: 36196302. Policy #0 lag: (min: 3.0, avg: 5.9, max: 35.0) -[2023-10-10 15:26:41,076][75634] Avg episode reward: [(0, '35.050'), (1, '37.540')] -[2023-10-10 15:26:43,001][76542] Updated weights for policy 1, policy_version 70630 (0.0010) -[2023-10-10 15:26:43,274][76543] Updated weights for policy 0, policy_version 70753 (0.0008) -[2023-10-10 15:26:43,373][76542] Updated weights for policy 1, policy_version 70640 (0.0009) -[2023-10-10 15:26:43,633][76543] Updated weights for policy 0, policy_version 70763 (0.0007) -[2023-10-10 15:26:43,738][76542] Updated weights for policy 1, policy_version 70650 (0.0007) -[2023-10-10 15:26:43,996][76543] Updated weights for policy 0, policy_version 70773 (0.0007) -[2023-10-10 15:26:44,366][76543] Updated weights for policy 0, policy_version 70783 (0.0007) -[2023-10-10 15:26:46,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 144834560. Throughput: 0: 1811.0, 1: 1819.2. Samples: 36218444. Policy #0 lag: (min: 3.0, avg: 5.9, max: 35.0) -[2023-10-10 15:26:46,077][75634] Avg episode reward: [(0, '36.430'), (1, '40.970')] -[2023-10-10 15:26:47,433][76542] Updated weights for policy 1, policy_version 70660 (0.0007) -[2023-10-10 15:26:47,809][76542] Updated weights for policy 1, policy_version 70670 (0.0010) -[2023-10-10 15:26:48,060][76543] Updated weights for policy 0, policy_version 70793 (0.0008) -[2023-10-10 15:26:48,181][76542] Updated weights for policy 1, policy_version 70680 (0.0011) -[2023-10-10 15:26:48,432][76543] Updated weights for policy 0, policy_version 70803 (0.0007) -[2023-10-10 15:26:48,796][76543] Updated weights for policy 0, policy_version 70813 (0.0007) -[2023-10-10 15:26:51,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 144900096. Throughput: 0: 1813.2, 1: 1821.5. Samples: 36229162. Policy #0 lag: (min: 3.0, avg: 5.9, max: 35.0) -[2023-10-10 15:26:51,077][75634] Avg episode reward: [(0, '38.030'), (1, '33.830')] -[2023-10-10 15:26:51,830][76542] Updated weights for policy 1, policy_version 70690 (0.0008) -[2023-10-10 15:26:52,196][76542] Updated weights for policy 1, policy_version 70700 (0.0008) -[2023-10-10 15:26:52,530][76543] Updated weights for policy 0, policy_version 70823 (0.0008) -[2023-10-10 15:26:52,575][76542] Updated weights for policy 1, policy_version 70710 (0.0008) -[2023-10-10 15:26:52,904][76543] Updated weights for policy 0, policy_version 70833 (0.0008) -[2023-10-10 15:26:52,936][76542] Updated weights for policy 1, policy_version 70720 (0.0008) -[2023-10-10 15:26:53,278][76543] Updated weights for policy 0, policy_version 70843 (0.0008) -[2023-10-10 15:26:56,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 144965632. Throughput: 0: 1806.5, 1: 1825.7. Samples: 36251222. Policy #0 lag: (min: 3.0, avg: 5.9, max: 35.0) -[2023-10-10 15:26:56,076][75634] Avg episode reward: [(0, '37.390'), (1, '32.350')] -[2023-10-10 15:26:56,492][76542] Updated weights for policy 1, policy_version 70730 (0.0008) -[2023-10-10 15:26:56,860][76542] Updated weights for policy 1, policy_version 70740 (0.0007) -[2023-10-10 15:26:57,138][76543] Updated weights for policy 0, policy_version 70853 (0.0009) -[2023-10-10 15:26:57,230][76542] Updated weights for policy 1, policy_version 70750 (0.0007) -[2023-10-10 15:26:57,522][76543] Updated weights for policy 0, policy_version 70863 (0.0007) -[2023-10-10 15:26:57,902][76543] Updated weights for policy 0, policy_version 70873 (0.0010) -[2023-10-10 15:27:00,877][76542] Updated weights for policy 1, policy_version 70760 (0.0008) -[2023-10-10 15:27:01,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 145031168. Throughput: 0: 1813.3, 1: 1827.6. Samples: 36273860. Policy #0 lag: (min: 3.0, avg: 5.9, max: 35.0) -[2023-10-10 15:27:01,077][75634] Avg episode reward: [(0, '36.890'), (1, '34.550')] -[2023-10-10 15:27:01,244][76542] Updated weights for policy 1, policy_version 70770 (0.0008) -[2023-10-10 15:27:01,606][76543] Updated weights for policy 0, policy_version 70883 (0.0010) -[2023-10-10 15:27:01,620][76542] Updated weights for policy 1, policy_version 70780 (0.0008) -[2023-10-10 15:27:01,978][76543] Updated weights for policy 0, policy_version 70893 (0.0008) -[2023-10-10 15:27:02,348][76543] Updated weights for policy 0, policy_version 70903 (0.0008) -[2023-10-10 15:27:05,249][76542] Updated weights for policy 1, policy_version 70790 (0.0008) -[2023-10-10 15:27:05,619][76542] Updated weights for policy 1, policy_version 70800 (0.0007) -[2023-10-10 15:27:05,987][76542] Updated weights for policy 1, policy_version 70810 (0.0009) -[2023-10-10 15:27:06,069][76543] Updated weights for policy 0, policy_version 70913 (0.0008) -[2023-10-10 15:27:06,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 145096704. Throughput: 0: 1816.0, 1: 1834.4. Samples: 36284000. Policy #0 lag: (min: 3.0, avg: 5.9, max: 35.0) -[2023-10-10 15:27:06,077][75634] Avg episode reward: [(0, '38.000'), (1, '36.080')] -[2023-10-10 15:27:06,440][76543] Updated weights for policy 0, policy_version 70923 (0.0007) -[2023-10-10 15:27:06,813][76543] Updated weights for policy 0, policy_version 70933 (0.0007) -[2023-10-10 15:27:07,182][76543] Updated weights for policy 0, policy_version 70943 (0.0007) -[2023-10-10 15:27:09,642][76542] Updated weights for policy 1, policy_version 70820 (0.0007) -[2023-10-10 15:27:10,016][76542] Updated weights for policy 1, policy_version 70830 (0.0007) -[2023-10-10 15:27:10,378][76542] Updated weights for policy 1, policy_version 70840 (0.0009) -[2023-10-10 15:27:10,807][76543] Updated weights for policy 0, policy_version 70953 (0.0010) -[2023-10-10 15:27:11,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 145195008. Throughput: 0: 1816.8, 1: 1832.0. Samples: 36306800. Policy #0 lag: (min: 3.0, avg: 5.9, max: 35.0) -[2023-10-10 15:27:11,077][75634] Avg episode reward: [(0, '37.380'), (1, '33.020')] -[2023-10-10 15:27:11,173][76543] Updated weights for policy 0, policy_version 70963 (0.0009) -[2023-10-10 15:27:11,533][76543] Updated weights for policy 0, policy_version 70973 (0.0007) -[2023-10-10 15:27:14,256][76542] Updated weights for policy 1, policy_version 70850 (0.0009) -[2023-10-10 15:27:14,621][76542] Updated weights for policy 1, policy_version 70860 (0.0011) -[2023-10-10 15:27:14,891][76543] Updated weights for policy 0, policy_version 70983 (0.0008) -[2023-10-10 15:27:14,988][76542] Updated weights for policy 1, policy_version 70870 (0.0008) -[2023-10-10 15:27:15,266][76543] Updated weights for policy 0, policy_version 70993 (0.0008) -[2023-10-10 15:27:15,355][76542] Updated weights for policy 1, policy_version 70880 (0.0007) -[2023-10-10 15:27:15,635][76543] Updated weights for policy 0, policy_version 71003 (0.0007) -[2023-10-10 15:27:16,076][75634] Fps is (10 sec: 19660.9, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 145293312. Throughput: 0: 1823.5, 1: 1828.7. Samples: 36327726. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 15:27:16,077][75634] Avg episode reward: [(0, '39.100'), (1, '32.640')] -[2023-10-10 15:27:19,052][76542] Updated weights for policy 1, policy_version 70890 (0.0008) -[2023-10-10 15:27:19,185][76543] Updated weights for policy 0, policy_version 71013 (0.0008) -[2023-10-10 15:27:19,415][76542] Updated weights for policy 1, policy_version 70900 (0.0007) -[2023-10-10 15:27:19,562][76543] Updated weights for policy 0, policy_version 71023 (0.0009) -[2023-10-10 15:27:19,783][76542] Updated weights for policy 1, policy_version 70910 (0.0007) -[2023-10-10 15:27:19,926][76543] Updated weights for policy 0, policy_version 71033 (0.0008) -[2023-10-10 15:27:21,076][75634] Fps is (10 sec: 16384.5, 60 sec: 15291.7, 300 sec: 14551.2). Total num frames: 145358848. Throughput: 0: 1833.3, 1: 1823.1. Samples: 36339972. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 15:27:21,076][75634] Avg episode reward: [(0, '37.560'), (1, '30.420')] -[2023-10-10 15:27:23,569][76542] Updated weights for policy 1, policy_version 70920 (0.0009) -[2023-10-10 15:27:23,679][76543] Updated weights for policy 0, policy_version 71043 (0.0008) -[2023-10-10 15:27:23,931][76542] Updated weights for policy 1, policy_version 70930 (0.0008) -[2023-10-10 15:27:24,057][76543] Updated weights for policy 0, policy_version 71053 (0.0007) -[2023-10-10 15:27:24,300][76542] Updated weights for policy 1, policy_version 70940 (0.0007) -[2023-10-10 15:27:24,429][76543] Updated weights for policy 0, policy_version 71063 (0.0008) -[2023-10-10 15:27:26,076][75634] Fps is (10 sec: 13107.4, 60 sec: 15291.7, 300 sec: 14551.2). Total num frames: 145424384. Throughput: 0: 1826.0, 1: 1818.8. Samples: 36360318. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 15:27:26,076][75634] Avg episode reward: [(0, '31.990'), (1, '32.010')] -[2023-10-10 15:27:27,957][76543] Updated weights for policy 0, policy_version 71073 (0.0011) -[2023-10-10 15:27:28,001][76542] Updated weights for policy 1, policy_version 70950 (0.0009) -[2023-10-10 15:27:28,323][76543] Updated weights for policy 0, policy_version 71083 (0.0008) -[2023-10-10 15:27:28,379][76542] Updated weights for policy 1, policy_version 70960 (0.0009) -[2023-10-10 15:27:28,695][76543] Updated weights for policy 0, policy_version 71093 (0.0008) -[2023-10-10 15:27:28,750][76542] Updated weights for policy 1, policy_version 70970 (0.0009) -[2023-10-10 15:27:29,069][76543] Updated weights for policy 0, policy_version 71103 (0.0008) -[2023-10-10 15:27:31,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 145489920. Throughput: 0: 1835.2, 1: 1812.7. Samples: 36382600. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 15:27:31,077][75634] Avg episode reward: [(0, '32.560'), (1, '35.140')] -[2023-10-10 15:27:32,637][76542] Updated weights for policy 1, policy_version 70980 (0.0010) -[2023-10-10 15:27:32,692][76543] Updated weights for policy 0, policy_version 71113 (0.0008) -[2023-10-10 15:27:33,034][76542] Updated weights for policy 1, policy_version 70990 (0.0007) -[2023-10-10 15:27:33,064][76543] Updated weights for policy 0, policy_version 71123 (0.0007) -[2023-10-10 15:27:33,402][76542] Updated weights for policy 1, policy_version 71000 (0.0007) -[2023-10-10 15:27:33,431][76543] Updated weights for policy 0, policy_version 71133 (0.0009) -[2023-10-10 15:27:36,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 145555456. Throughput: 0: 1823.1, 1: 1812.9. Samples: 36392780. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 15:27:36,077][75634] Avg episode reward: [(0, '35.660'), (1, '31.220')] -[2023-10-10 15:27:37,154][76542] Updated weights for policy 1, policy_version 71010 (0.0008) -[2023-10-10 15:27:37,168][76543] Updated weights for policy 0, policy_version 71143 (0.0009) -[2023-10-10 15:27:37,524][76542] Updated weights for policy 1, policy_version 71020 (0.0008) -[2023-10-10 15:27:37,540][76543] Updated weights for policy 0, policy_version 71153 (0.0008) -[2023-10-10 15:27:37,890][76542] Updated weights for policy 1, policy_version 71030 (0.0009) -[2023-10-10 15:27:37,908][76543] Updated weights for policy 0, policy_version 71163 (0.0007) -[2023-10-10 15:27:38,257][76542] Updated weights for policy 1, policy_version 71040 (0.0008) -[2023-10-10 15:27:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 145620992. Throughput: 0: 1838.0, 1: 1807.7. Samples: 36415280. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 15:27:41,077][75634] Avg episode reward: [(0, '37.430'), (1, '32.820')] -[2023-10-10 15:27:41,541][76543] Updated weights for policy 0, policy_version 71173 (0.0009) -[2023-10-10 15:27:41,913][76543] Updated weights for policy 0, policy_version 71183 (0.0007) -[2023-10-10 15:27:41,936][76542] Updated weights for policy 1, policy_version 71050 (0.0008) -[2023-10-10 15:27:42,286][76543] Updated weights for policy 0, policy_version 71193 (0.0007) -[2023-10-10 15:27:42,296][76542] Updated weights for policy 1, policy_version 71060 (0.0007) -[2023-10-10 15:27:42,667][76542] Updated weights for policy 1, policy_version 71070 (0.0007) -[2023-10-10 15:27:45,948][76543] Updated weights for policy 0, policy_version 71203 (0.0009) -[2023-10-10 15:27:46,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 145686528. Throughput: 0: 1840.5, 1: 1806.6. Samples: 36437982. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 15:27:46,077][75634] Avg episode reward: [(0, '40.600'), (1, '35.520')] -[2023-10-10 15:27:46,313][76543] Updated weights for policy 0, policy_version 71213 (0.0007) -[2023-10-10 15:27:46,397][76542] Updated weights for policy 1, policy_version 71080 (0.0008) -[2023-10-10 15:27:46,687][76543] Updated weights for policy 0, policy_version 71223 (0.0007) -[2023-10-10 15:27:46,759][76542] Updated weights for policy 1, policy_version 71090 (0.0008) -[2023-10-10 15:27:47,125][76542] Updated weights for policy 1, policy_version 71100 (0.0007) -[2023-10-10 15:27:50,353][76543] Updated weights for policy 0, policy_version 71233 (0.0007) -[2023-10-10 15:27:50,710][76543] Updated weights for policy 0, policy_version 71243 (0.0009) -[2023-10-10 15:27:50,867][76542] Updated weights for policy 1, policy_version 71110 (0.0007) -[2023-10-10 15:27:51,073][76543] Updated weights for policy 0, policy_version 71253 (0.0007) -[2023-10-10 15:27:51,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 145752064. Throughput: 0: 1839.3, 1: 1800.3. Samples: 36447784. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 15:27:51,076][75634] Avg episode reward: [(0, '39.840'), (1, '38.380')] -[2023-10-10 15:27:51,229][76542] Updated weights for policy 1, policy_version 71120 (0.0008) -[2023-10-10 15:27:51,442][76543] Updated weights for policy 0, policy_version 71263 (0.0008) -[2023-10-10 15:27:51,597][76542] Updated weights for policy 1, policy_version 71130 (0.0007) -[2023-10-10 15:27:55,169][76543] Updated weights for policy 0, policy_version 71273 (0.0008) -[2023-10-10 15:27:55,294][76542] Updated weights for policy 1, policy_version 71140 (0.0009) -[2023-10-10 15:27:55,554][76543] Updated weights for policy 0, policy_version 71283 (0.0007) -[2023-10-10 15:27:55,659][76542] Updated weights for policy 1, policy_version 71150 (0.0009) -[2023-10-10 15:27:55,925][76543] Updated weights for policy 0, policy_version 71293 (0.0009) -[2023-10-10 15:27:56,018][76542] Updated weights for policy 1, policy_version 71160 (0.0007) -[2023-10-10 15:27:56,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 145850368. Throughput: 0: 1845.3, 1: 1799.7. Samples: 36470828. Policy #0 lag: (min: 16.0, avg: 34.4, max: 48.0) -[2023-10-10 15:27:56,077][75634] Avg episode reward: [(0, '39.080'), (1, '39.170')] -[2023-10-10 15:27:59,461][76543] Updated weights for policy 0, policy_version 71303 (0.0008) -[2023-10-10 15:27:59,738][76542] Updated weights for policy 1, policy_version 71170 (0.0009) -[2023-10-10 15:27:59,829][76543] Updated weights for policy 0, policy_version 71313 (0.0008) -[2023-10-10 15:28:00,102][76542] Updated weights for policy 1, policy_version 71180 (0.0009) -[2023-10-10 15:28:00,196][76543] Updated weights for policy 0, policy_version 71323 (0.0007) -[2023-10-10 15:28:00,472][76542] Updated weights for policy 1, policy_version 71190 (0.0007) -[2023-10-10 15:28:00,834][76542] Updated weights for policy 1, policy_version 71200 (0.0009) -[2023-10-10 15:28:01,076][75634] Fps is (10 sec: 19660.8, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 145948672. Throughput: 0: 1825.8, 1: 1803.6. Samples: 36491048. Policy #0 lag: (min: 16.0, avg: 34.4, max: 48.0) -[2023-10-10 15:28:01,076][75634] Avg episode reward: [(0, '38.630'), (1, '33.380')] -[2023-10-10 15:28:03,824][76543] Updated weights for policy 0, policy_version 71333 (0.0007) -[2023-10-10 15:28:04,190][76543] Updated weights for policy 0, policy_version 71343 (0.0008) -[2023-10-10 15:28:04,498][76542] Updated weights for policy 1, policy_version 71210 (0.0007) -[2023-10-10 15:28:04,565][76543] Updated weights for policy 0, policy_version 71353 (0.0010) -[2023-10-10 15:28:04,867][76542] Updated weights for policy 1, policy_version 71220 (0.0007) -[2023-10-10 15:28:05,231][76542] Updated weights for policy 1, policy_version 71230 (0.0007) -[2023-10-10 15:28:06,076][75634] Fps is (10 sec: 16384.2, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 146014208. Throughput: 0: 1837.6, 1: 1802.9. Samples: 36503792. Policy #0 lag: (min: 16.0, avg: 34.4, max: 48.0) -[2023-10-10 15:28:06,076][75634] Avg episode reward: [(0, '39.910'), (1, '29.910')] -[2023-10-10 15:28:08,207][76543] Updated weights for policy 0, policy_version 71363 (0.0009) -[2023-10-10 15:28:08,577][76543] Updated weights for policy 0, policy_version 71373 (0.0010) -[2023-10-10 15:28:08,944][76542] Updated weights for policy 1, policy_version 71240 (0.0008) -[2023-10-10 15:28:08,947][76543] Updated weights for policy 0, policy_version 71383 (0.0008) -[2023-10-10 15:28:09,310][76542] Updated weights for policy 1, policy_version 71250 (0.0009) -[2023-10-10 15:28:09,683][76542] Updated weights for policy 1, policy_version 71260 (0.0010) -[2023-10-10 15:28:11,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 146079744. Throughput: 0: 1825.2, 1: 1811.6. Samples: 36523976. Policy #0 lag: (min: 16.0, avg: 34.4, max: 48.0) -[2023-10-10 15:28:11,077][75634] Avg episode reward: [(0, '39.660'), (1, '30.350')] -[2023-10-10 15:28:12,609][76543] Updated weights for policy 0, policy_version 71393 (0.0008) -[2023-10-10 15:28:12,980][76543] Updated weights for policy 0, policy_version 71403 (0.0008) -[2023-10-10 15:28:13,334][76542] Updated weights for policy 1, policy_version 71270 (0.0009) -[2023-10-10 15:28:13,346][76543] Updated weights for policy 0, policy_version 71413 (0.0008) -[2023-10-10 15:28:13,704][76543] Updated weights for policy 0, policy_version 71423 (0.0008) -[2023-10-10 15:28:13,715][76542] Updated weights for policy 1, policy_version 71280 (0.0008) -[2023-10-10 15:28:14,080][76542] Updated weights for policy 1, policy_version 71290 (0.0008) -[2023-10-10 15:28:16,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 146145280. Throughput: 0: 1833.2, 1: 1806.9. Samples: 36546406. Policy #0 lag: (min: 16.0, avg: 34.4, max: 48.0) -[2023-10-10 15:28:16,076][75634] Avg episode reward: [(0, '42.000'), (1, '34.100')] -[2023-10-10 15:28:17,498][76543] Updated weights for policy 0, policy_version 71433 (0.0010) -[2023-10-10 15:28:17,862][76543] Updated weights for policy 0, policy_version 71443 (0.0007) -[2023-10-10 15:28:17,956][76542] Updated weights for policy 1, policy_version 71300 (0.0009) -[2023-10-10 15:28:18,230][76543] Updated weights for policy 0, policy_version 71453 (0.0007) -[2023-10-10 15:28:18,346][76542] Updated weights for policy 1, policy_version 71310 (0.0010) -[2023-10-10 15:28:18,713][76542] Updated weights for policy 1, policy_version 71320 (0.0011) -[2023-10-10 15:28:21,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 146210816. Throughput: 0: 1828.1, 1: 1817.7. Samples: 36556842. Policy #0 lag: (min: 16.0, avg: 34.4, max: 48.0) -[2023-10-10 15:28:21,077][75634] Avg episode reward: [(0, '42.870'), (1, '37.160')] -[2023-10-10 15:28:21,910][76543] Updated weights for policy 0, policy_version 71463 (0.0008) -[2023-10-10 15:28:22,282][76543] Updated weights for policy 0, policy_version 71473 (0.0009) -[2023-10-10 15:28:22,471][76542] Updated weights for policy 1, policy_version 71330 (0.0009) -[2023-10-10 15:28:22,649][76543] Updated weights for policy 0, policy_version 71483 (0.0008) -[2023-10-10 15:28:22,836][76542] Updated weights for policy 1, policy_version 71340 (0.0008) -[2023-10-10 15:28:23,214][76542] Updated weights for policy 1, policy_version 71350 (0.0009) -[2023-10-10 15:28:23,576][76542] Updated weights for policy 1, policy_version 71360 (0.0009) -[2023-10-10 15:28:26,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 146276352. Throughput: 0: 1828.5, 1: 1808.5. Samples: 36578948. Policy #0 lag: (min: 16.0, avg: 34.4, max: 48.0) -[2023-10-10 15:28:26,077][75634] Avg episode reward: [(0, '36.090'), (1, '39.310')] -[2023-10-10 15:28:26,494][76543] Updated weights for policy 0, policy_version 71493 (0.0009) -[2023-10-10 15:28:26,883][76543] Updated weights for policy 0, policy_version 71503 (0.0009) -[2023-10-10 15:28:27,205][76542] Updated weights for policy 1, policy_version 71370 (0.0008) -[2023-10-10 15:28:27,252][76543] Updated weights for policy 0, policy_version 71513 (0.0008) -[2023-10-10 15:28:27,581][76542] Updated weights for policy 1, policy_version 71380 (0.0009) -[2023-10-10 15:28:27,940][76542] Updated weights for policy 1, policy_version 71390 (0.0008) -[2023-10-10 15:28:30,906][76543] Updated weights for policy 0, policy_version 71523 (0.0007) -[2023-10-10 15:28:31,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 146341888. Throughput: 0: 1821.4, 1: 1812.2. Samples: 36601494. Policy #0 lag: (min: 16.0, avg: 34.4, max: 48.0) -[2023-10-10 15:28:31,077][75634] Avg episode reward: [(0, '29.730'), (1, '42.730')] -[2023-10-10 15:28:31,085][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000071392_73105408.pth... -[2023-10-10 15:28:31,120][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000069696_71368704.pth -[2023-10-10 15:28:31,124][76421] Saving new best policy, reward=42.730! -[2023-10-10 15:28:31,273][76543] Updated weights for policy 0, policy_version 71533 (0.0008) -[2023-10-10 15:28:31,641][76543] Updated weights for policy 0, policy_version 71543 (0.0007) -[2023-10-10 15:28:31,778][76542] Updated weights for policy 1, policy_version 71400 (0.0009) -[2023-10-10 15:28:31,969][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000071552_73269248.pth... -[2023-10-10 15:28:32,001][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000069824_71499776.pth -[2023-10-10 15:28:32,153][76542] Updated weights for policy 1, policy_version 71410 (0.0008) -[2023-10-10 15:28:32,522][76542] Updated weights for policy 1, policy_version 71420 (0.0007) -[2023-10-10 15:28:35,290][76543] Updated weights for policy 0, policy_version 71553 (0.0007) -[2023-10-10 15:28:35,661][76543] Updated weights for policy 0, policy_version 71563 (0.0008) -[2023-10-10 15:28:36,035][76543] Updated weights for policy 0, policy_version 71573 (0.0007) -[2023-10-10 15:28:36,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 146407424. Throughput: 0: 1824.3, 1: 1811.1. Samples: 36611374. Policy #0 lag: (min: 16.0, avg: 34.4, max: 48.0) -[2023-10-10 15:28:36,076][75634] Avg episode reward: [(0, '28.960'), (1, '42.900')] -[2023-10-10 15:28:36,162][76542] Updated weights for policy 1, policy_version 71430 (0.0009) -[2023-10-10 15:28:36,411][76543] Updated weights for policy 0, policy_version 71583 (0.0010) -[2023-10-10 15:28:36,525][76542] Updated weights for policy 1, policy_version 71440 (0.0009) -[2023-10-10 15:28:36,895][76542] Updated weights for policy 1, policy_version 71450 (0.0010) -[2023-10-10 15:28:37,114][76421] Saving new best policy, reward=42.900! -[2023-10-10 15:28:40,154][76543] Updated weights for policy 0, policy_version 71593 (0.0010) -[2023-10-10 15:28:40,486][76542] Updated weights for policy 1, policy_version 71460 (0.0009) -[2023-10-10 15:28:40,518][76543] Updated weights for policy 0, policy_version 71603 (0.0008) -[2023-10-10 15:28:40,849][76542] Updated weights for policy 1, policy_version 71470 (0.0009) -[2023-10-10 15:28:40,887][76543] Updated weights for policy 0, policy_version 71613 (0.0008) -[2023-10-10 15:28:41,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 146505728. Throughput: 0: 1816.2, 1: 1818.1. Samples: 36634372. Policy #0 lag: (min: 18.0, avg: 18.2, max: 27.0) -[2023-10-10 15:28:41,077][75634] Avg episode reward: [(0, '34.210'), (1, '38.350')] -[2023-10-10 15:28:41,215][76542] Updated weights for policy 1, policy_version 71480 (0.0010) -[2023-10-10 15:28:44,623][76543] Updated weights for policy 0, policy_version 71623 (0.0010) -[2023-10-10 15:28:44,961][76542] Updated weights for policy 1, policy_version 71490 (0.0012) -[2023-10-10 15:28:44,990][76543] Updated weights for policy 0, policy_version 71633 (0.0009) -[2023-10-10 15:28:45,326][76542] Updated weights for policy 1, policy_version 71500 (0.0008) -[2023-10-10 15:28:45,365][76543] Updated weights for policy 0, policy_version 71643 (0.0009) -[2023-10-10 15:28:45,695][76542] Updated weights for policy 1, policy_version 71510 (0.0007) -[2023-10-10 15:28:46,065][76542] Updated weights for policy 1, policy_version 71520 (0.0007) -[2023-10-10 15:28:46,076][75634] Fps is (10 sec: 19660.6, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 146604032. Throughput: 0: 1822.7, 1: 1822.8. Samples: 36655094. Policy #0 lag: (min: 18.0, avg: 18.2, max: 27.0) -[2023-10-10 15:28:46,077][75634] Avg episode reward: [(0, '35.730'), (1, '32.890')] -[2023-10-10 15:28:48,962][76543] Updated weights for policy 0, policy_version 71653 (0.0008) -[2023-10-10 15:28:49,330][76543] Updated weights for policy 0, policy_version 71663 (0.0009) -[2023-10-10 15:28:49,675][76542] Updated weights for policy 1, policy_version 71530 (0.0007) -[2023-10-10 15:28:49,707][76543] Updated weights for policy 0, policy_version 71673 (0.0008) -[2023-10-10 15:28:50,041][76542] Updated weights for policy 1, policy_version 71540 (0.0008) -[2023-10-10 15:28:50,416][76542] Updated weights for policy 1, policy_version 71550 (0.0007) -[2023-10-10 15:28:51,076][75634] Fps is (10 sec: 16384.3, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 146669568. Throughput: 0: 1814.4, 1: 1812.3. Samples: 36666998. Policy #0 lag: (min: 18.0, avg: 18.2, max: 27.0) -[2023-10-10 15:28:51,077][75634] Avg episode reward: [(0, '36.590'), (1, '28.120')] -[2023-10-10 15:28:53,381][76543] Updated weights for policy 0, policy_version 71683 (0.0009) -[2023-10-10 15:28:53,758][76543] Updated weights for policy 0, policy_version 71693 (0.0009) -[2023-10-10 15:28:54,039][76542] Updated weights for policy 1, policy_version 71560 (0.0008) -[2023-10-10 15:28:54,139][76543] Updated weights for policy 0, policy_version 71703 (0.0007) -[2023-10-10 15:28:54,405][76542] Updated weights for policy 1, policy_version 71570 (0.0008) -[2023-10-10 15:28:54,777][76542] Updated weights for policy 1, policy_version 71580 (0.0009) -[2023-10-10 15:28:56,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 146735104. Throughput: 0: 1820.2, 1: 1817.9. Samples: 36687688. Policy #0 lag: (min: 18.0, avg: 18.2, max: 27.0) -[2023-10-10 15:28:56,076][75634] Avg episode reward: [(0, '34.420'), (1, '28.670')] -[2023-10-10 15:28:57,628][76543] Updated weights for policy 0, policy_version 71713 (0.0008) -[2023-10-10 15:28:58,000][76543] Updated weights for policy 0, policy_version 71723 (0.0008) -[2023-10-10 15:28:58,376][76543] Updated weights for policy 0, policy_version 71733 (0.0008) -[2023-10-10 15:28:58,450][76542] Updated weights for policy 1, policy_version 71590 (0.0009) -[2023-10-10 15:28:58,745][76543] Updated weights for policy 0, policy_version 71743 (0.0008) -[2023-10-10 15:28:58,820][76542] Updated weights for policy 1, policy_version 71600 (0.0008) -[2023-10-10 15:28:59,179][76542] Updated weights for policy 1, policy_version 71610 (0.0008) -[2023-10-10 15:29:01,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14662.3). Total num frames: 146800640. Throughput: 0: 1824.5, 1: 1812.6. Samples: 36710076. Policy #0 lag: (min: 18.0, avg: 18.2, max: 27.0) -[2023-10-10 15:29:01,077][75634] Avg episode reward: [(0, '33.450'), (1, '29.500')] -[2023-10-10 15:29:02,442][76543] Updated weights for policy 0, policy_version 71753 (0.0011) -[2023-10-10 15:29:02,814][76543] Updated weights for policy 0, policy_version 71763 (0.0008) -[2023-10-10 15:29:02,925][76542] Updated weights for policy 1, policy_version 71620 (0.0007) -[2023-10-10 15:29:03,177][76543] Updated weights for policy 0, policy_version 71773 (0.0008) -[2023-10-10 15:29:03,326][76542] Updated weights for policy 1, policy_version 71630 (0.0007) -[2023-10-10 15:29:03,694][76542] Updated weights for policy 1, policy_version 71640 (0.0010) -[2023-10-10 15:29:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 146866176. Throughput: 0: 1819.3, 1: 1813.9. Samples: 36720336. Policy #0 lag: (min: 18.0, avg: 18.2, max: 27.0) -[2023-10-10 15:29:06,076][75634] Avg episode reward: [(0, '33.380'), (1, '30.610')] -[2023-10-10 15:29:06,914][76543] Updated weights for policy 0, policy_version 71783 (0.0010) -[2023-10-10 15:29:07,293][76543] Updated weights for policy 0, policy_version 71793 (0.0009) -[2023-10-10 15:29:07,299][76542] Updated weights for policy 1, policy_version 71650 (0.0011) -[2023-10-10 15:29:07,667][76543] Updated weights for policy 0, policy_version 71803 (0.0007) -[2023-10-10 15:29:07,675][76542] Updated weights for policy 1, policy_version 71660 (0.0009) -[2023-10-10 15:29:08,043][76542] Updated weights for policy 1, policy_version 71670 (0.0010) -[2023-10-10 15:29:08,411][76542] Updated weights for policy 1, policy_version 71680 (0.0011) -[2023-10-10 15:29:11,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 146931712. Throughput: 0: 1822.3, 1: 1813.5. Samples: 36742558. Policy #0 lag: (min: 18.0, avg: 18.2, max: 27.0) -[2023-10-10 15:29:11,076][75634] Avg episode reward: [(0, '34.190'), (1, '32.080')] -[2023-10-10 15:29:11,385][76543] Updated weights for policy 0, policy_version 71813 (0.0008) -[2023-10-10 15:29:11,752][76543] Updated weights for policy 0, policy_version 71823 (0.0009) -[2023-10-10 15:29:12,119][76543] Updated weights for policy 0, policy_version 71833 (0.0007) -[2023-10-10 15:29:12,153][76542] Updated weights for policy 1, policy_version 71690 (0.0007) -[2023-10-10 15:29:12,511][76542] Updated weights for policy 1, policy_version 71700 (0.0007) -[2023-10-10 15:29:12,875][76542] Updated weights for policy 1, policy_version 71710 (0.0010) -[2023-10-10 15:29:15,764][76543] Updated weights for policy 0, policy_version 71843 (0.0008) -[2023-10-10 15:29:16,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 146997248. Throughput: 0: 1830.7, 1: 1807.4. Samples: 36765206. Policy #0 lag: (min: 18.0, avg: 18.2, max: 27.0) -[2023-10-10 15:29:16,077][75634] Avg episode reward: [(0, '38.460'), (1, '37.220')] -[2023-10-10 15:29:16,139][76543] Updated weights for policy 0, policy_version 71853 (0.0008) -[2023-10-10 15:29:16,505][76543] Updated weights for policy 0, policy_version 71863 (0.0007) -[2023-10-10 15:29:16,680][76542] Updated weights for policy 1, policy_version 71720 (0.0008) -[2023-10-10 15:29:17,050][76542] Updated weights for policy 1, policy_version 71730 (0.0009) -[2023-10-10 15:29:17,413][76542] Updated weights for policy 1, policy_version 71740 (0.0011) -[2023-10-10 15:29:20,351][76543] Updated weights for policy 0, policy_version 71873 (0.0008) -[2023-10-10 15:29:20,716][76543] Updated weights for policy 0, policy_version 71883 (0.0008) -[2023-10-10 15:29:21,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 147062784. Throughput: 0: 1825.1, 1: 1809.8. Samples: 36774944. Policy #0 lag: (min: 18.0, avg: 18.2, max: 27.0) -[2023-10-10 15:29:21,076][75634] Avg episode reward: [(0, '37.540'), (1, '40.490')] -[2023-10-10 15:29:21,085][76543] Updated weights for policy 0, policy_version 71893 (0.0010) -[2023-10-10 15:29:21,184][76542] Updated weights for policy 1, policy_version 71750 (0.0008) -[2023-10-10 15:29:21,455][76543] Updated weights for policy 0, policy_version 71903 (0.0007) -[2023-10-10 15:29:21,558][76542] Updated weights for policy 1, policy_version 71760 (0.0009) -[2023-10-10 15:29:21,918][76542] Updated weights for policy 1, policy_version 71770 (0.0009) -[2023-10-10 15:29:24,997][76543] Updated weights for policy 0, policy_version 71913 (0.0009) -[2023-10-10 15:29:25,367][76543] Updated weights for policy 0, policy_version 71923 (0.0010) -[2023-10-10 15:29:25,590][76542] Updated weights for policy 1, policy_version 71780 (0.0008) -[2023-10-10 15:29:25,734][76543] Updated weights for policy 0, policy_version 71933 (0.0010) -[2023-10-10 15:29:25,960][76542] Updated weights for policy 1, policy_version 71790 (0.0008) -[2023-10-10 15:29:26,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 147161088. Throughput: 0: 1827.7, 1: 1802.3. Samples: 36797724. Policy #0 lag: (min: 31.0, avg: 33.0, max: 61.0) -[2023-10-10 15:29:26,076][75634] Avg episode reward: [(0, '37.240'), (1, '33.150')] -[2023-10-10 15:29:26,338][76542] Updated weights for policy 1, policy_version 71800 (0.0010) -[2023-10-10 15:29:29,520][76543] Updated weights for policy 0, policy_version 71943 (0.0008) -[2023-10-10 15:29:29,889][76543] Updated weights for policy 0, policy_version 71953 (0.0009) -[2023-10-10 15:29:30,002][76542] Updated weights for policy 1, policy_version 71810 (0.0008) -[2023-10-10 15:29:30,262][76543] Updated weights for policy 0, policy_version 71963 (0.0007) -[2023-10-10 15:29:30,368][76542] Updated weights for policy 1, policy_version 71820 (0.0008) -[2023-10-10 15:29:30,730][76542] Updated weights for policy 1, policy_version 71830 (0.0010) -[2023-10-10 15:29:31,076][75634] Fps is (10 sec: 16383.3, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 147226624. Throughput: 0: 1822.3, 1: 1807.3. Samples: 36818426. Policy #0 lag: (min: 31.0, avg: 33.0, max: 61.0) -[2023-10-10 15:29:31,077][75634] Avg episode reward: [(0, '35.130'), (1, '38.050')] -[2023-10-10 15:29:31,113][76542] Updated weights for policy 1, policy_version 71840 (0.0008) -[2023-10-10 15:29:33,923][76543] Updated weights for policy 0, policy_version 71973 (0.0007) -[2023-10-10 15:29:34,292][76543] Updated weights for policy 0, policy_version 71983 (0.0007) -[2023-10-10 15:29:34,654][76543] Updated weights for policy 0, policy_version 71993 (0.0008) -[2023-10-10 15:29:34,919][76542] Updated weights for policy 1, policy_version 71850 (0.0008) -[2023-10-10 15:29:35,284][76542] Updated weights for policy 1, policy_version 71860 (0.0010) -[2023-10-10 15:29:35,654][76542] Updated weights for policy 1, policy_version 71870 (0.0010) -[2023-10-10 15:29:36,076][75634] Fps is (10 sec: 16383.7, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 147324928. Throughput: 0: 1821.6, 1: 1806.2. Samples: 36830248. Policy #0 lag: (min: 31.0, avg: 33.0, max: 61.0) -[2023-10-10 15:29:36,077][75634] Avg episode reward: [(0, '33.760'), (1, '35.300')] -[2023-10-10 15:29:38,323][76543] Updated weights for policy 0, policy_version 72003 (0.0008) -[2023-10-10 15:29:38,693][76543] Updated weights for policy 0, policy_version 72013 (0.0008) -[2023-10-10 15:29:39,065][76543] Updated weights for policy 0, policy_version 72023 (0.0008) -[2023-10-10 15:29:39,585][76542] Updated weights for policy 1, policy_version 71880 (0.0008) -[2023-10-10 15:29:39,953][76542] Updated weights for policy 1, policy_version 71890 (0.0010) -[2023-10-10 15:29:40,314][76542] Updated weights for policy 1, policy_version 71900 (0.0010) -[2023-10-10 15:29:41,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 147390464. Throughput: 0: 1817.8, 1: 1814.8. Samples: 36851158. Policy #0 lag: (min: 31.0, avg: 33.0, max: 61.0) -[2023-10-10 15:29:41,077][75634] Avg episode reward: [(0, '36.160'), (1, '33.140')] -[2023-10-10 15:29:42,754][76543] Updated weights for policy 0, policy_version 72033 (0.0008) -[2023-10-10 15:29:43,130][76543] Updated weights for policy 0, policy_version 72043 (0.0009) -[2023-10-10 15:29:43,501][76543] Updated weights for policy 0, policy_version 72053 (0.0007) -[2023-10-10 15:29:43,865][76543] Updated weights for policy 0, policy_version 72063 (0.0007) -[2023-10-10 15:29:43,993][76542] Updated weights for policy 1, policy_version 71910 (0.0008) -[2023-10-10 15:29:44,361][76542] Updated weights for policy 1, policy_version 71920 (0.0011) -[2023-10-10 15:29:44,739][76542] Updated weights for policy 1, policy_version 71930 (0.0010) -[2023-10-10 15:29:46,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14662.3). Total num frames: 147456000. Throughput: 0: 1809.5, 1: 1805.1. Samples: 36872732. Policy #0 lag: (min: 31.0, avg: 33.0, max: 61.0) -[2023-10-10 15:29:46,077][75634] Avg episode reward: [(0, '34.460'), (1, '30.240')] -[2023-10-10 15:29:47,551][76543] Updated weights for policy 0, policy_version 72073 (0.0008) -[2023-10-10 15:29:47,920][76543] Updated weights for policy 0, policy_version 72083 (0.0009) -[2023-10-10 15:29:48,293][76543] Updated weights for policy 0, policy_version 72093 (0.0010) -[2023-10-10 15:29:48,645][76542] Updated weights for policy 1, policy_version 71940 (0.0010) -[2023-10-10 15:29:49,043][76542] Updated weights for policy 1, policy_version 71950 (0.0007) -[2023-10-10 15:29:49,409][76542] Updated weights for policy 1, policy_version 71960 (0.0009) -[2023-10-10 15:29:51,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 147521536. Throughput: 0: 1813.8, 1: 1819.0. Samples: 36883812. Policy #0 lag: (min: 31.0, avg: 33.0, max: 61.0) -[2023-10-10 15:29:51,077][75634] Avg episode reward: [(0, '38.140'), (1, '33.210')] -[2023-10-10 15:29:52,023][76543] Updated weights for policy 0, policy_version 72103 (0.0008) -[2023-10-10 15:29:52,400][76543] Updated weights for policy 0, policy_version 72113 (0.0007) -[2023-10-10 15:29:52,770][76543] Updated weights for policy 0, policy_version 72123 (0.0007) -[2023-10-10 15:29:52,945][76542] Updated weights for policy 1, policy_version 71970 (0.0009) -[2023-10-10 15:29:53,316][76542] Updated weights for policy 1, policy_version 71980 (0.0008) -[2023-10-10 15:29:53,687][76542] Updated weights for policy 1, policy_version 71990 (0.0008) -[2023-10-10 15:29:54,060][76542] Updated weights for policy 1, policy_version 72000 (0.0007) -[2023-10-10 15:29:56,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 147587072. Throughput: 0: 1811.7, 1: 1799.5. Samples: 36905062. Policy #0 lag: (min: 31.0, avg: 33.0, max: 61.0) -[2023-10-10 15:29:56,076][75634] Avg episode reward: [(0, '36.400'), (1, '37.800')] -[2023-10-10 15:29:56,468][76543] Updated weights for policy 0, policy_version 72133 (0.0007) -[2023-10-10 15:29:56,836][76543] Updated weights for policy 0, policy_version 72143 (0.0010) -[2023-10-10 15:29:57,202][76543] Updated weights for policy 0, policy_version 72153 (0.0011) -[2023-10-10 15:29:57,734][76542] Updated weights for policy 1, policy_version 72010 (0.0009) -[2023-10-10 15:29:58,094][76542] Updated weights for policy 1, policy_version 72020 (0.0009) -[2023-10-10 15:29:58,466][76542] Updated weights for policy 1, policy_version 72030 (0.0008) -[2023-10-10 15:30:00,939][76543] Updated weights for policy 0, policy_version 72163 (0.0009) -[2023-10-10 15:30:01,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 147652608. Throughput: 0: 1808.6, 1: 1810.7. Samples: 36928076. Policy #0 lag: (min: 31.0, avg: 33.0, max: 61.0) -[2023-10-10 15:30:01,076][75634] Avg episode reward: [(0, '35.400'), (1, '33.440')] -[2023-10-10 15:30:01,327][76543] Updated weights for policy 0, policy_version 72173 (0.0007) -[2023-10-10 15:30:01,699][76543] Updated weights for policy 0, policy_version 72183 (0.0007) -[2023-10-10 15:30:02,157][76542] Updated weights for policy 1, policy_version 72040 (0.0008) -[2023-10-10 15:30:02,525][76542] Updated weights for policy 1, policy_version 72050 (0.0007) -[2023-10-10 15:30:02,893][76542] Updated weights for policy 1, policy_version 72060 (0.0008) -[2023-10-10 15:30:05,215][76543] Updated weights for policy 0, policy_version 72193 (0.0009) -[2023-10-10 15:30:05,591][76543] Updated weights for policy 0, policy_version 72203 (0.0007) -[2023-10-10 15:30:05,955][76543] Updated weights for policy 0, policy_version 72213 (0.0007) -[2023-10-10 15:30:06,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 147718144. Throughput: 0: 1813.4, 1: 1809.7. Samples: 36937984. Policy #0 lag: (min: 31.0, avg: 33.0, max: 61.0) -[2023-10-10 15:30:06,076][75634] Avg episode reward: [(0, '37.190'), (1, '34.720')] -[2023-10-10 15:30:06,328][76543] Updated weights for policy 0, policy_version 72223 (0.0007) -[2023-10-10 15:30:06,475][76542] Updated weights for policy 1, policy_version 72070 (0.0008) -[2023-10-10 15:30:06,841][76542] Updated weights for policy 1, policy_version 72080 (0.0008) -[2023-10-10 15:30:07,210][76542] Updated weights for policy 1, policy_version 72090 (0.0008) -[2023-10-10 15:30:10,022][76543] Updated weights for policy 0, policy_version 72233 (0.0007) -[2023-10-10 15:30:10,401][76543] Updated weights for policy 0, policy_version 72243 (0.0008) -[2023-10-10 15:30:10,771][76543] Updated weights for policy 0, policy_version 72253 (0.0009) -[2023-10-10 15:30:10,923][76542] Updated weights for policy 1, policy_version 72100 (0.0009) -[2023-10-10 15:30:11,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 147816448. Throughput: 0: 1819.1, 1: 1805.7. Samples: 36960840. Policy #0 lag: (min: 31.0, avg: 33.0, max: 61.0) -[2023-10-10 15:30:11,076][75634] Avg episode reward: [(0, '41.140'), (1, '36.900')] -[2023-10-10 15:30:11,300][76542] Updated weights for policy 1, policy_version 72110 (0.0007) -[2023-10-10 15:30:11,664][76542] Updated weights for policy 1, policy_version 72120 (0.0009) -[2023-10-10 15:30:14,467][76543] Updated weights for policy 0, policy_version 72263 (0.0008) -[2023-10-10 15:30:14,841][76543] Updated weights for policy 0, policy_version 72273 (0.0008) -[2023-10-10 15:30:15,216][76543] Updated weights for policy 0, policy_version 72283 (0.0007) -[2023-10-10 15:30:15,509][76542] Updated weights for policy 1, policy_version 72130 (0.0009) -[2023-10-10 15:30:15,876][76542] Updated weights for policy 1, policy_version 72140 (0.0008) -[2023-10-10 15:30:16,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 147881984. Throughput: 0: 1820.5, 1: 1815.5. Samples: 36982044. Policy #0 lag: (min: 31.0, avg: 33.0, max: 62.0) -[2023-10-10 15:30:16,077][75634] Avg episode reward: [(0, '43.830'), (1, '38.540')] -[2023-10-10 15:30:16,233][76542] Updated weights for policy 1, policy_version 72150 (0.0008) -[2023-10-10 15:30:16,610][76542] Updated weights for policy 1, policy_version 72160 (0.0007) -[2023-10-10 15:30:18,873][76543] Updated weights for policy 0, policy_version 72293 (0.0009) -[2023-10-10 15:30:19,242][76543] Updated weights for policy 0, policy_version 72303 (0.0008) -[2023-10-10 15:30:19,611][76543] Updated weights for policy 0, policy_version 72313 (0.0009) -[2023-10-10 15:30:20,242][76542] Updated weights for policy 1, policy_version 72170 (0.0008) -[2023-10-10 15:30:20,620][76542] Updated weights for policy 1, policy_version 72180 (0.0007) -[2023-10-10 15:30:20,990][76542] Updated weights for policy 1, policy_version 72190 (0.0009) -[2023-10-10 15:30:21,076][75634] Fps is (10 sec: 16383.8, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 147980288. Throughput: 0: 1823.8, 1: 1805.6. Samples: 36993568. Policy #0 lag: (min: 31.0, avg: 33.0, max: 62.0) -[2023-10-10 15:30:21,077][75634] Avg episode reward: [(0, '36.550'), (1, '38.450')] -[2023-10-10 15:30:23,381][76543] Updated weights for policy 0, policy_version 72323 (0.0009) -[2023-10-10 15:30:23,746][76543] Updated weights for policy 0, policy_version 72333 (0.0008) -[2023-10-10 15:30:24,114][76543] Updated weights for policy 0, policy_version 72343 (0.0007) -[2023-10-10 15:30:24,571][76542] Updated weights for policy 1, policy_version 72200 (0.0010) -[2023-10-10 15:30:24,934][76542] Updated weights for policy 1, policy_version 72210 (0.0010) -[2023-10-10 15:30:25,307][76542] Updated weights for policy 1, policy_version 72220 (0.0008) -[2023-10-10 15:30:26,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 148045824. Throughput: 0: 1821.8, 1: 1812.5. Samples: 37014702. Policy #0 lag: (min: 31.0, avg: 33.0, max: 62.0) -[2023-10-10 15:30:26,076][75634] Avg episode reward: [(0, '36.770'), (1, '35.890')] -[2023-10-10 15:30:27,927][76543] Updated weights for policy 0, policy_version 72353 (0.0007) -[2023-10-10 15:30:28,286][76543] Updated weights for policy 0, policy_version 72363 (0.0009) -[2023-10-10 15:30:28,663][76543] Updated weights for policy 0, policy_version 72373 (0.0009) -[2023-10-10 15:30:29,029][76543] Updated weights for policy 0, policy_version 72383 (0.0011) -[2023-10-10 15:30:29,354][76542] Updated weights for policy 1, policy_version 72230 (0.0008) -[2023-10-10 15:30:29,718][76542] Updated weights for policy 1, policy_version 72240 (0.0010) -[2023-10-10 15:30:30,091][76542] Updated weights for policy 1, policy_version 72250 (0.0010) -[2023-10-10 15:30:31,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 148111360. Throughput: 0: 1807.4, 1: 1794.0. Samples: 37034792. Policy #0 lag: (min: 31.0, avg: 33.0, max: 62.0) -[2023-10-10 15:30:31,077][75634] Avg episode reward: [(0, '37.610'), (1, '34.940')] -[2023-10-10 15:30:31,086][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000072384_74121216.pth... -[2023-10-10 15:30:31,086][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000072256_73990144.pth... -[2023-10-10 15:30:31,124][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000070560_72253440.pth -[2023-10-10 15:30:31,127][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000070688_72384512.pth -[2023-10-10 15:30:33,044][76543] Updated weights for policy 0, policy_version 72393 (0.0009) -[2023-10-10 15:30:33,411][76543] Updated weights for policy 0, policy_version 72403 (0.0009) -[2023-10-10 15:30:33,779][76543] Updated weights for policy 0, policy_version 72413 (0.0008) -[2023-10-10 15:30:33,994][76542] Updated weights for policy 1, policy_version 72260 (0.0010) -[2023-10-10 15:30:34,389][76542] Updated weights for policy 1, policy_version 72270 (0.0011) -[2023-10-10 15:30:34,749][76542] Updated weights for policy 1, policy_version 72280 (0.0010) -[2023-10-10 15:30:36,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 148176896. Throughput: 0: 1818.1, 1: 1801.5. Samples: 37046694. Policy #0 lag: (min: 31.0, avg: 33.0, max: 62.0) -[2023-10-10 15:30:36,077][75634] Avg episode reward: [(0, '37.730'), (1, '35.460')] -[2023-10-10 15:30:37,728][76543] Updated weights for policy 0, policy_version 72423 (0.0007) -[2023-10-10 15:30:38,095][76543] Updated weights for policy 0, policy_version 72433 (0.0009) -[2023-10-10 15:30:38,462][76543] Updated weights for policy 0, policy_version 72443 (0.0010) -[2023-10-10 15:30:38,715][76542] Updated weights for policy 1, policy_version 72290 (0.0008) -[2023-10-10 15:30:39,071][76542] Updated weights for policy 1, policy_version 72300 (0.0010) -[2023-10-10 15:30:39,438][76542] Updated weights for policy 1, policy_version 72310 (0.0011) -[2023-10-10 15:30:39,802][76542] Updated weights for policy 1, policy_version 72320 (0.0013) -[2023-10-10 15:30:41,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 148242432. Throughput: 0: 1787.0, 1: 1785.9. Samples: 37065844. Policy #0 lag: (min: 31.0, avg: 33.0, max: 62.0) -[2023-10-10 15:30:41,077][75634] Avg episode reward: [(0, '38.900'), (1, '36.660')] -[2023-10-10 15:30:42,666][76543] Updated weights for policy 0, policy_version 72453 (0.0009) -[2023-10-10 15:30:43,031][76543] Updated weights for policy 0, policy_version 72463 (0.0009) -[2023-10-10 15:30:43,395][76543] Updated weights for policy 0, policy_version 72473 (0.0011) -[2023-10-10 15:30:44,030][76542] Updated weights for policy 1, policy_version 72330 (0.0010) -[2023-10-10 15:30:44,398][76542] Updated weights for policy 1, policy_version 72340 (0.0010) -[2023-10-10 15:30:44,766][76542] Updated weights for policy 1, policy_version 72350 (0.0009) -[2023-10-10 15:30:46,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 148307968. Throughput: 0: 1760.8, 1: 1748.8. Samples: 37086006. Policy #0 lag: (min: 31.0, avg: 33.0, max: 62.0) -[2023-10-10 15:30:46,076][75634] Avg episode reward: [(0, '38.000'), (1, '38.200')] -[2023-10-10 15:30:47,567][76543] Updated weights for policy 0, policy_version 72483 (0.0010) -[2023-10-10 15:30:47,978][76543] Updated weights for policy 0, policy_version 72493 (0.0009) -[2023-10-10 15:30:48,348][76543] Updated weights for policy 0, policy_version 72503 (0.0008) -[2023-10-10 15:30:48,878][76542] Updated weights for policy 1, policy_version 72360 (0.0008) -[2023-10-10 15:30:49,248][76542] Updated weights for policy 1, policy_version 72370 (0.0007) -[2023-10-10 15:30:49,626][76542] Updated weights for policy 1, policy_version 72380 (0.0008) -[2023-10-10 15:30:51,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 148373504. Throughput: 0: 1755.3, 1: 1764.8. Samples: 37096392. Policy #0 lag: (min: 31.0, avg: 33.0, max: 62.0) -[2023-10-10 15:30:51,076][75634] Avg episode reward: [(0, '35.150'), (1, '35.410')] -[2023-10-10 15:30:52,091][76543] Updated weights for policy 0, policy_version 72513 (0.0008) -[2023-10-10 15:30:52,474][76543] Updated weights for policy 0, policy_version 72523 (0.0008) -[2023-10-10 15:30:52,838][76543] Updated weights for policy 0, policy_version 72533 (0.0008) -[2023-10-10 15:30:53,209][76543] Updated weights for policy 0, policy_version 72543 (0.0010) -[2023-10-10 15:30:53,522][76542] Updated weights for policy 1, policy_version 72390 (0.0009) -[2023-10-10 15:30:53,894][76542] Updated weights for policy 1, policy_version 72400 (0.0010) -[2023-10-10 15:30:54,256][76542] Updated weights for policy 1, policy_version 72410 (0.0010) -[2023-10-10 15:30:56,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 148439040. Throughput: 0: 1724.2, 1: 1727.1. Samples: 37116148. Policy #0 lag: (min: 31.0, avg: 33.0, max: 62.0) -[2023-10-10 15:30:56,076][75634] Avg episode reward: [(0, '33.190'), (1, '35.540')] -[2023-10-10 15:30:57,154][76543] Updated weights for policy 0, policy_version 72553 (0.0010) -[2023-10-10 15:30:57,512][76543] Updated weights for policy 0, policy_version 72563 (0.0010) -[2023-10-10 15:30:57,891][76543] Updated weights for policy 0, policy_version 72573 (0.0010) -[2023-10-10 15:30:58,107][76542] Updated weights for policy 1, policy_version 72420 (0.0010) -[2023-10-10 15:30:58,473][76542] Updated weights for policy 1, policy_version 72430 (0.0009) -[2023-10-10 15:30:58,850][76542] Updated weights for policy 1, policy_version 72440 (0.0008) -[2023-10-10 15:31:01,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 148504576. Throughput: 0: 1732.8, 1: 1720.2. Samples: 37137430. Policy #0 lag: (min: 31.0, avg: 33.0, max: 62.0) -[2023-10-10 15:31:01,076][75634] Avg episode reward: [(0, '33.940'), (1, '30.440')] -[2023-10-10 15:31:01,890][76543] Updated weights for policy 0, policy_version 72583 (0.0011) -[2023-10-10 15:31:02,261][76543] Updated weights for policy 0, policy_version 72593 (0.0011) -[2023-10-10 15:31:02,633][76543] Updated weights for policy 0, policy_version 72603 (0.0009) -[2023-10-10 15:31:03,010][76542] Updated weights for policy 1, policy_version 72450 (0.0008) -[2023-10-10 15:31:03,376][76542] Updated weights for policy 1, policy_version 72460 (0.0010) -[2023-10-10 15:31:03,739][76542] Updated weights for policy 1, policy_version 72470 (0.0010) -[2023-10-10 15:31:04,112][76542] Updated weights for policy 1, policy_version 72480 (0.0010) -[2023-10-10 15:31:06,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 148570112. Throughput: 0: 1694.9, 1: 1710.3. Samples: 37146804. Policy #0 lag: (min: 4.0, avg: 29.7, max: 32.0) -[2023-10-10 15:31:06,076][75634] Avg episode reward: [(0, '37.210'), (1, '30.910')] -[2023-10-10 15:31:06,515][76543] Updated weights for policy 0, policy_version 72613 (0.0008) -[2023-10-10 15:31:06,882][76543] Updated weights for policy 0, policy_version 72623 (0.0007) -[2023-10-10 15:31:07,253][76543] Updated weights for policy 0, policy_version 72633 (0.0009) -[2023-10-10 15:31:07,777][76542] Updated weights for policy 1, policy_version 72490 (0.0010) -[2023-10-10 15:31:08,135][76542] Updated weights for policy 1, policy_version 72500 (0.0007) -[2023-10-10 15:31:08,507][76542] Updated weights for policy 1, policy_version 72510 (0.0009) -[2023-10-10 15:31:10,990][76543] Updated weights for policy 0, policy_version 72643 (0.0009) -[2023-10-10 15:31:11,076][75634] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 14440.1). Total num frames: 148635648. Throughput: 0: 1721.5, 1: 1702.8. Samples: 37168794. Policy #0 lag: (min: 4.0, avg: 29.7, max: 32.0) -[2023-10-10 15:31:11,077][75634] Avg episode reward: [(0, '35.570'), (1, '33.250')] -[2023-10-10 15:31:11,367][76543] Updated weights for policy 0, policy_version 72653 (0.0007) -[2023-10-10 15:31:11,729][76543] Updated weights for policy 0, policy_version 72663 (0.0009) -[2023-10-10 15:31:12,233][76542] Updated weights for policy 1, policy_version 72520 (0.0009) -[2023-10-10 15:31:12,606][76542] Updated weights for policy 1, policy_version 72530 (0.0008) -[2023-10-10 15:31:12,971][76542] Updated weights for policy 1, policy_version 72540 (0.0008) -[2023-10-10 15:31:15,363][76543] Updated weights for policy 0, policy_version 72673 (0.0010) -[2023-10-10 15:31:15,734][76543] Updated weights for policy 0, policy_version 72683 (0.0010) -[2023-10-10 15:31:16,076][75634] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 14440.1). Total num frames: 148701184. Throughput: 0: 1743.1, 1: 1741.0. Samples: 37191576. Policy #0 lag: (min: 4.0, avg: 29.7, max: 32.0) -[2023-10-10 15:31:16,076][75634] Avg episode reward: [(0, '36.840'), (1, '31.120')] -[2023-10-10 15:31:16,096][76543] Updated weights for policy 0, policy_version 72693 (0.0011) -[2023-10-10 15:31:16,463][76543] Updated weights for policy 0, policy_version 72703 (0.0008) -[2023-10-10 15:31:16,692][76542] Updated weights for policy 1, policy_version 72550 (0.0007) -[2023-10-10 15:31:17,060][76542] Updated weights for policy 1, policy_version 72560 (0.0008) -[2023-10-10 15:31:17,431][76542] Updated weights for policy 1, policy_version 72570 (0.0008) -[2023-10-10 15:31:20,048][76543] Updated weights for policy 0, policy_version 72713 (0.0010) -[2023-10-10 15:31:20,418][76543] Updated weights for policy 0, policy_version 72723 (0.0011) -[2023-10-10 15:31:20,788][76543] Updated weights for policy 0, policy_version 72733 (0.0011) -[2023-10-10 15:31:21,076][75634] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 14551.2). Total num frames: 148799488. Throughput: 0: 1731.9, 1: 1710.5. Samples: 37201600. Policy #0 lag: (min: 4.0, avg: 29.7, max: 32.0) -[2023-10-10 15:31:21,077][75634] Avg episode reward: [(0, '31.200'), (1, '31.730')] -[2023-10-10 15:31:21,259][76542] Updated weights for policy 1, policy_version 72580 (0.0010) -[2023-10-10 15:31:21,651][76542] Updated weights for policy 1, policy_version 72590 (0.0007) -[2023-10-10 15:31:22,019][76542] Updated weights for policy 1, policy_version 72600 (0.0007) -[2023-10-10 15:31:24,454][76543] Updated weights for policy 0, policy_version 72743 (0.0010) -[2023-10-10 15:31:24,820][76543] Updated weights for policy 0, policy_version 72753 (0.0012) -[2023-10-10 15:31:25,187][76543] Updated weights for policy 0, policy_version 72763 (0.0008) -[2023-10-10 15:31:25,789][76542] Updated weights for policy 1, policy_version 72610 (0.0008) -[2023-10-10 15:31:26,076][75634] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 14329.1). Total num frames: 148865024. Throughput: 0: 1768.9, 1: 1755.3. Samples: 37224432. Policy #0 lag: (min: 4.0, avg: 29.7, max: 32.0) -[2023-10-10 15:31:26,077][75634] Avg episode reward: [(0, '36.530'), (1, '37.860')] -[2023-10-10 15:31:26,161][76542] Updated weights for policy 1, policy_version 72620 (0.0008) -[2023-10-10 15:31:26,534][76542] Updated weights for policy 1, policy_version 72630 (0.0008) -[2023-10-10 15:31:26,905][76542] Updated weights for policy 1, policy_version 72640 (0.0008) -[2023-10-10 15:31:28,747][76543] Updated weights for policy 0, policy_version 72773 (0.0009) -[2023-10-10 15:31:29,118][76543] Updated weights for policy 0, policy_version 72783 (0.0010) -[2023-10-10 15:31:29,488][76543] Updated weights for policy 0, policy_version 72793 (0.0010) -[2023-10-10 15:31:30,674][76542] Updated weights for policy 1, policy_version 72650 (0.0009) -[2023-10-10 15:31:31,041][76542] Updated weights for policy 1, policy_version 72660 (0.0008) -[2023-10-10 15:31:31,076][75634] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 14329.1). Total num frames: 148930560. Throughput: 0: 1769.4, 1: 1773.9. Samples: 37245454. Policy #0 lag: (min: 4.0, avg: 29.7, max: 32.0) -[2023-10-10 15:31:31,076][75634] Avg episode reward: [(0, '38.480'), (1, '38.220')] -[2023-10-10 15:31:31,407][76542] Updated weights for policy 1, policy_version 72670 (0.0008) -[2023-10-10 15:31:33,330][76543] Updated weights for policy 0, policy_version 72803 (0.0010) -[2023-10-10 15:31:33,721][76543] Updated weights for policy 0, policy_version 72813 (0.0009) -[2023-10-10 15:31:34,096][76543] Updated weights for policy 0, policy_version 72823 (0.0010) -[2023-10-10 15:31:35,242][76542] Updated weights for policy 1, policy_version 72680 (0.0010) -[2023-10-10 15:31:35,618][76542] Updated weights for policy 1, policy_version 72690 (0.0011) -[2023-10-10 15:31:35,991][76542] Updated weights for policy 1, policy_version 72700 (0.0010) -[2023-10-10 15:31:36,076][75634] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 14329.1). Total num frames: 148996096. Throughput: 0: 1803.5, 1: 1768.4. Samples: 37257126. Policy #0 lag: (min: 4.0, avg: 29.7, max: 32.0) -[2023-10-10 15:31:36,076][75634] Avg episode reward: [(0, '40.310'), (1, '33.490')] -[2023-10-10 15:31:37,715][76543] Updated weights for policy 0, policy_version 72833 (0.0009) -[2023-10-10 15:31:38,077][76543] Updated weights for policy 0, policy_version 72843 (0.0010) -[2023-10-10 15:31:38,445][76543] Updated weights for policy 0, policy_version 72853 (0.0009) -[2023-10-10 15:31:38,817][76543] Updated weights for policy 0, policy_version 72863 (0.0010) -[2023-10-10 15:31:39,463][76542] Updated weights for policy 1, policy_version 72710 (0.0010) -[2023-10-10 15:31:39,834][76542] Updated weights for policy 1, policy_version 72720 (0.0008) -[2023-10-10 15:31:40,199][76542] Updated weights for policy 1, policy_version 72730 (0.0007) -[2023-10-10 15:31:41,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 149094400. Throughput: 0: 1792.2, 1: 1801.2. Samples: 37277854. Policy #0 lag: (min: 4.0, avg: 29.7, max: 32.0) -[2023-10-10 15:31:41,077][75634] Avg episode reward: [(0, '40.000'), (1, '36.360')] -[2023-10-10 15:31:42,723][76543] Updated weights for policy 0, policy_version 72873 (0.0008) -[2023-10-10 15:31:43,091][76543] Updated weights for policy 0, policy_version 72883 (0.0008) -[2023-10-10 15:31:43,454][76543] Updated weights for policy 0, policy_version 72893 (0.0007) -[2023-10-10 15:31:43,748][76542] Updated weights for policy 1, policy_version 72740 (0.0007) -[2023-10-10 15:31:44,116][76542] Updated weights for policy 1, policy_version 72750 (0.0007) -[2023-10-10 15:31:44,486][76542] Updated weights for policy 1, policy_version 72760 (0.0009) -[2023-10-10 15:31:46,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 149159936. Throughput: 0: 1806.9, 1: 1799.3. Samples: 37299712. Policy #0 lag: (min: 4.0, avg: 29.7, max: 32.0) -[2023-10-10 15:31:46,076][75634] Avg episode reward: [(0, '34.350'), (1, '36.290')] -[2023-10-10 15:31:47,297][76543] Updated weights for policy 0, policy_version 72903 (0.0009) -[2023-10-10 15:31:47,664][76543] Updated weights for policy 0, policy_version 72913 (0.0011) -[2023-10-10 15:31:48,051][76543] Updated weights for policy 0, policy_version 72923 (0.0009) -[2023-10-10 15:31:48,215][76542] Updated weights for policy 1, policy_version 72770 (0.0007) -[2023-10-10 15:31:48,588][76542] Updated weights for policy 1, policy_version 72780 (0.0007) -[2023-10-10 15:31:48,950][76542] Updated weights for policy 1, policy_version 72790 (0.0009) -[2023-10-10 15:31:49,316][76542] Updated weights for policy 1, policy_version 72800 (0.0009) -[2023-10-10 15:31:51,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 149225472. Throughput: 0: 1815.4, 1: 1817.2. Samples: 37310274. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-10 15:31:51,077][75634] Avg episode reward: [(0, '32.800'), (1, '32.850')] -[2023-10-10 15:31:51,786][76543] Updated weights for policy 0, policy_version 72933 (0.0009) -[2023-10-10 15:31:52,153][76543] Updated weights for policy 0, policy_version 72943 (0.0011) -[2023-10-10 15:31:52,517][76543] Updated weights for policy 0, policy_version 72953 (0.0008) -[2023-10-10 15:31:52,944][76542] Updated weights for policy 1, policy_version 72810 (0.0009) -[2023-10-10 15:31:53,299][76542] Updated weights for policy 1, policy_version 72820 (0.0008) -[2023-10-10 15:31:53,662][76542] Updated weights for policy 1, policy_version 72830 (0.0011) -[2023-10-10 15:31:56,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 149291008. Throughput: 0: 1820.4, 1: 1816.3. Samples: 37332444. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-10 15:31:56,077][75634] Avg episode reward: [(0, '37.580'), (1, '34.980')] -[2023-10-10 15:31:56,161][76543] Updated weights for policy 0, policy_version 72963 (0.0007) -[2023-10-10 15:31:56,542][76543] Updated weights for policy 0, policy_version 72973 (0.0008) -[2023-10-10 15:31:56,913][76543] Updated weights for policy 0, policy_version 72983 (0.0008) -[2023-10-10 15:31:57,398][76542] Updated weights for policy 1, policy_version 72840 (0.0007) -[2023-10-10 15:31:57,764][76542] Updated weights for policy 1, policy_version 72850 (0.0008) -[2023-10-10 15:31:58,125][76542] Updated weights for policy 1, policy_version 72860 (0.0011) -[2023-10-10 15:32:00,439][76543] Updated weights for policy 0, policy_version 72993 (0.0008) -[2023-10-10 15:32:00,813][76543] Updated weights for policy 0, policy_version 73003 (0.0010) -[2023-10-10 15:32:01,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 149356544. Throughput: 0: 1822.7, 1: 1816.2. Samples: 37355326. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-10 15:32:01,077][75634] Avg episode reward: [(0, '36.410'), (1, '37.780')] -[2023-10-10 15:32:01,178][76543] Updated weights for policy 0, policy_version 73013 (0.0008) -[2023-10-10 15:32:01,546][76543] Updated weights for policy 0, policy_version 73023 (0.0007) -[2023-10-10 15:32:01,786][76542] Updated weights for policy 1, policy_version 72870 (0.0008) -[2023-10-10 15:32:02,149][76542] Updated weights for policy 1, policy_version 72880 (0.0008) -[2023-10-10 15:32:02,517][76542] Updated weights for policy 1, policy_version 72890 (0.0007) -[2023-10-10 15:32:05,077][76543] Updated weights for policy 0, policy_version 73033 (0.0008) -[2023-10-10 15:32:05,446][76543] Updated weights for policy 0, policy_version 73043 (0.0009) -[2023-10-10 15:32:05,827][76543] Updated weights for policy 0, policy_version 73053 (0.0009) -[2023-10-10 15:32:06,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 149454848. Throughput: 0: 1821.3, 1: 1820.2. Samples: 37365470. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-10 15:32:06,077][75634] Avg episode reward: [(0, '33.940'), (1, '39.290')] -[2023-10-10 15:32:06,272][76542] Updated weights for policy 1, policy_version 72900 (0.0009) -[2023-10-10 15:32:06,651][76542] Updated weights for policy 1, policy_version 72910 (0.0008) -[2023-10-10 15:32:07,014][76542] Updated weights for policy 1, policy_version 72920 (0.0010) -[2023-10-10 15:32:09,463][76543] Updated weights for policy 0, policy_version 73063 (0.0008) -[2023-10-10 15:32:09,828][76543] Updated weights for policy 0, policy_version 73073 (0.0010) -[2023-10-10 15:32:10,203][76543] Updated weights for policy 0, policy_version 73083 (0.0008) -[2023-10-10 15:32:10,729][76542] Updated weights for policy 1, policy_version 72930 (0.0010) -[2023-10-10 15:32:11,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 149520384. Throughput: 0: 1824.1, 1: 1818.1. Samples: 37388332. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-10 15:32:11,077][75634] Avg episode reward: [(0, '35.260'), (1, '35.610')] -[2023-10-10 15:32:11,102][76542] Updated weights for policy 1, policy_version 72940 (0.0009) -[2023-10-10 15:32:11,464][76542] Updated weights for policy 1, policy_version 72950 (0.0008) -[2023-10-10 15:32:11,840][76542] Updated weights for policy 1, policy_version 72960 (0.0007) -[2023-10-10 15:32:13,771][76543] Updated weights for policy 0, policy_version 73093 (0.0008) -[2023-10-10 15:32:14,145][76543] Updated weights for policy 0, policy_version 73103 (0.0007) -[2023-10-10 15:32:14,514][76543] Updated weights for policy 0, policy_version 73113 (0.0010) -[2023-10-10 15:32:15,585][76542] Updated weights for policy 1, policy_version 72970 (0.0008) -[2023-10-10 15:32:15,955][76542] Updated weights for policy 1, policy_version 72980 (0.0010) -[2023-10-10 15:32:16,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 149585920. Throughput: 0: 1820.4, 1: 1813.4. Samples: 37408978. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-10 15:32:16,077][75634] Avg episode reward: [(0, '40.000'), (1, '36.210')] -[2023-10-10 15:32:16,320][76542] Updated weights for policy 1, policy_version 72990 (0.0008) -[2023-10-10 15:32:18,244][76543] Updated weights for policy 0, policy_version 73123 (0.0008) -[2023-10-10 15:32:18,619][76543] Updated weights for policy 0, policy_version 73133 (0.0010) -[2023-10-10 15:32:18,991][76543] Updated weights for policy 0, policy_version 73143 (0.0009) -[2023-10-10 15:32:19,994][76542] Updated weights for policy 1, policy_version 73000 (0.0008) -[2023-10-10 15:32:20,350][76542] Updated weights for policy 1, policy_version 73010 (0.0007) -[2023-10-10 15:32:20,733][76542] Updated weights for policy 1, policy_version 73020 (0.0008) -[2023-10-10 15:32:21,076][75634] Fps is (10 sec: 16384.5, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 149684224. Throughput: 0: 1822.2, 1: 1817.5. Samples: 37420914. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-10 15:32:21,076][75634] Avg episode reward: [(0, '36.980'), (1, '37.190')] -[2023-10-10 15:32:22,664][76543] Updated weights for policy 0, policy_version 73153 (0.0008) -[2023-10-10 15:32:23,036][76543] Updated weights for policy 0, policy_version 73163 (0.0009) -[2023-10-10 15:32:23,411][76543] Updated weights for policy 0, policy_version 73173 (0.0008) -[2023-10-10 15:32:23,784][76543] Updated weights for policy 0, policy_version 73183 (0.0009) -[2023-10-10 15:32:24,375][76542] Updated weights for policy 1, policy_version 73030 (0.0010) -[2023-10-10 15:32:24,745][76542] Updated weights for policy 1, policy_version 73040 (0.0010) -[2023-10-10 15:32:25,120][76542] Updated weights for policy 1, policy_version 73050 (0.0009) -[2023-10-10 15:32:26,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 149749760. Throughput: 0: 1828.6, 1: 1816.1. Samples: 37441864. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-10 15:32:26,076][75634] Avg episode reward: [(0, '36.160'), (1, '36.250')] -[2023-10-10 15:32:27,369][76543] Updated weights for policy 0, policy_version 73193 (0.0007) -[2023-10-10 15:32:27,746][76543] Updated weights for policy 0, policy_version 73203 (0.0007) -[2023-10-10 15:32:28,115][76543] Updated weights for policy 0, policy_version 73213 (0.0009) -[2023-10-10 15:32:28,694][76542] Updated weights for policy 1, policy_version 73060 (0.0010) -[2023-10-10 15:32:29,072][76542] Updated weights for policy 1, policy_version 73070 (0.0009) -[2023-10-10 15:32:29,437][76542] Updated weights for policy 1, policy_version 73080 (0.0008) -[2023-10-10 15:32:31,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 149815296. Throughput: 0: 1837.3, 1: 1821.5. Samples: 37464360. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-10 15:32:31,076][75634] Avg episode reward: [(0, '35.600'), (1, '33.400')] -[2023-10-10 15:32:31,085][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000073216_74973184.pth... -[2023-10-10 15:32:31,085][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000073088_74842112.pth... -[2023-10-10 15:32:31,118][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000071552_73269248.pth -[2023-10-10 15:32:31,120][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000071392_73105408.pth -[2023-10-10 15:32:31,763][76543] Updated weights for policy 0, policy_version 73223 (0.0008) -[2023-10-10 15:32:32,121][76543] Updated weights for policy 0, policy_version 73233 (0.0011) -[2023-10-10 15:32:32,488][76543] Updated weights for policy 0, policy_version 73243 (0.0009) -[2023-10-10 15:32:33,140][76542] Updated weights for policy 1, policy_version 73090 (0.0009) -[2023-10-10 15:32:33,511][76542] Updated weights for policy 1, policy_version 73100 (0.0008) -[2023-10-10 15:32:33,878][76542] Updated weights for policy 1, policy_version 73110 (0.0011) -[2023-10-10 15:32:34,242][76542] Updated weights for policy 1, policy_version 73120 (0.0009) -[2023-10-10 15:32:36,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 149880832. Throughput: 0: 1840.6, 1: 1823.5. Samples: 37475158. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-10 15:32:36,077][75634] Avg episode reward: [(0, '33.410'), (1, '32.820')] -[2023-10-10 15:32:36,225][76543] Updated weights for policy 0, policy_version 73253 (0.0007) -[2023-10-10 15:32:36,592][76543] Updated weights for policy 0, policy_version 73263 (0.0007) -[2023-10-10 15:32:36,968][76543] Updated weights for policy 0, policy_version 73273 (0.0009) -[2023-10-10 15:32:37,961][76542] Updated weights for policy 1, policy_version 73130 (0.0007) -[2023-10-10 15:32:38,328][76542] Updated weights for policy 1, policy_version 73140 (0.0007) -[2023-10-10 15:32:38,691][76542] Updated weights for policy 1, policy_version 73150 (0.0008) -[2023-10-10 15:32:40,710][76543] Updated weights for policy 0, policy_version 73283 (0.0007) -[2023-10-10 15:32:41,073][76543] Updated weights for policy 0, policy_version 73293 (0.0008) -[2023-10-10 15:32:41,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 149946368. Throughput: 0: 1837.5, 1: 1824.8. Samples: 37497248. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:32:41,077][75634] Avg episode reward: [(0, '35.090'), (1, '33.970')] -[2023-10-10 15:32:41,447][76543] Updated weights for policy 0, policy_version 73303 (0.0008) -[2023-10-10 15:32:42,390][76542] Updated weights for policy 1, policy_version 73160 (0.0007) -[2023-10-10 15:32:42,755][76542] Updated weights for policy 1, policy_version 73170 (0.0008) -[2023-10-10 15:32:43,123][76542] Updated weights for policy 1, policy_version 73180 (0.0011) -[2023-10-10 15:32:45,187][76543] Updated weights for policy 0, policy_version 73313 (0.0008) -[2023-10-10 15:32:45,564][76543] Updated weights for policy 0, policy_version 73323 (0.0010) -[2023-10-10 15:32:45,932][76543] Updated weights for policy 0, policy_version 73333 (0.0007) -[2023-10-10 15:32:46,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 150011904. Throughput: 0: 1828.5, 1: 1824.6. Samples: 37519714. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:32:46,076][75634] Avg episode reward: [(0, '38.130'), (1, '33.240')] -[2023-10-10 15:32:46,301][76543] Updated weights for policy 0, policy_version 73343 (0.0008) -[2023-10-10 15:32:46,979][76542] Updated weights for policy 1, policy_version 73190 (0.0008) -[2023-10-10 15:32:47,336][76542] Updated weights for policy 1, policy_version 73200 (0.0008) -[2023-10-10 15:32:47,710][76542] Updated weights for policy 1, policy_version 73210 (0.0007) -[2023-10-10 15:32:49,905][76543] Updated weights for policy 0, policy_version 73353 (0.0010) -[2023-10-10 15:32:50,271][76543] Updated weights for policy 0, policy_version 73363 (0.0011) -[2023-10-10 15:32:50,639][76543] Updated weights for policy 0, policy_version 73373 (0.0011) -[2023-10-10 15:32:51,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 150110208. Throughput: 0: 1831.5, 1: 1821.9. Samples: 37529874. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:32:51,077][75634] Avg episode reward: [(0, '34.370'), (1, '36.880')] -[2023-10-10 15:32:51,340][76542] Updated weights for policy 1, policy_version 73220 (0.0009) -[2023-10-10 15:32:51,726][76542] Updated weights for policy 1, policy_version 73230 (0.0009) -[2023-10-10 15:32:52,088][76542] Updated weights for policy 1, policy_version 73240 (0.0008) -[2023-10-10 15:32:54,304][76543] Updated weights for policy 0, policy_version 73383 (0.0009) -[2023-10-10 15:32:54,675][76543] Updated weights for policy 0, policy_version 73393 (0.0010) -[2023-10-10 15:32:55,042][76543] Updated weights for policy 0, policy_version 73403 (0.0009) -[2023-10-10 15:32:55,752][76542] Updated weights for policy 1, policy_version 73250 (0.0011) -[2023-10-10 15:32:56,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 150175744. Throughput: 0: 1826.9, 1: 1821.3. Samples: 37552498. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:32:56,077][75634] Avg episode reward: [(0, '36.510'), (1, '34.010')] -[2023-10-10 15:32:56,125][76542] Updated weights for policy 1, policy_version 73260 (0.0009) -[2023-10-10 15:32:56,490][76542] Updated weights for policy 1, policy_version 73270 (0.0007) -[2023-10-10 15:32:56,856][76542] Updated weights for policy 1, policy_version 73280 (0.0009) -[2023-10-10 15:32:58,690][76543] Updated weights for policy 0, policy_version 73413 (0.0010) -[2023-10-10 15:32:59,062][76543] Updated weights for policy 0, policy_version 73423 (0.0009) -[2023-10-10 15:32:59,435][76543] Updated weights for policy 0, policy_version 73433 (0.0008) -[2023-10-10 15:33:00,513][76542] Updated weights for policy 1, policy_version 73290 (0.0008) -[2023-10-10 15:33:00,871][76542] Updated weights for policy 1, policy_version 73300 (0.0008) -[2023-10-10 15:33:01,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 150241280. Throughput: 0: 1830.0, 1: 1825.0. Samples: 37573450. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:33:01,077][75634] Avg episode reward: [(0, '36.080'), (1, '33.200')] -[2023-10-10 15:33:01,248][76542] Updated weights for policy 1, policy_version 73310 (0.0008) -[2023-10-10 15:33:03,028][76543] Updated weights for policy 0, policy_version 73443 (0.0008) -[2023-10-10 15:33:03,429][76543] Updated weights for policy 0, policy_version 73453 (0.0011) -[2023-10-10 15:33:03,800][76543] Updated weights for policy 0, policy_version 73463 (0.0008) -[2023-10-10 15:33:04,876][76542] Updated weights for policy 1, policy_version 73320 (0.0008) -[2023-10-10 15:33:05,240][76542] Updated weights for policy 1, policy_version 73330 (0.0007) -[2023-10-10 15:33:05,610][76542] Updated weights for policy 1, policy_version 73340 (0.0008) -[2023-10-10 15:33:06,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 150339584. Throughput: 0: 1820.7, 1: 1830.1. Samples: 37585198. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:33:06,077][75634] Avg episode reward: [(0, '34.110'), (1, '35.050')] -[2023-10-10 15:33:07,626][76543] Updated weights for policy 0, policy_version 73473 (0.0008) -[2023-10-10 15:33:07,989][76543] Updated weights for policy 0, policy_version 73483 (0.0008) -[2023-10-10 15:33:08,362][76543] Updated weights for policy 0, policy_version 73493 (0.0007) -[2023-10-10 15:33:08,727][76543] Updated weights for policy 0, policy_version 73503 (0.0007) -[2023-10-10 15:33:09,329][76542] Updated weights for policy 1, policy_version 73350 (0.0010) -[2023-10-10 15:33:09,697][76542] Updated weights for policy 1, policy_version 73360 (0.0007) -[2023-10-10 15:33:10,065][76542] Updated weights for policy 1, policy_version 73370 (0.0008) -[2023-10-10 15:33:11,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 150405120. Throughput: 0: 1818.2, 1: 1825.5. Samples: 37605830. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:33:11,076][75634] Avg episode reward: [(0, '37.290'), (1, '33.020')] -[2023-10-10 15:33:12,264][76543] Updated weights for policy 0, policy_version 73513 (0.0008) -[2023-10-10 15:33:12,629][76543] Updated weights for policy 0, policy_version 73523 (0.0007) -[2023-10-10 15:33:13,000][76543] Updated weights for policy 0, policy_version 73533 (0.0007) -[2023-10-10 15:33:13,875][76542] Updated weights for policy 1, policy_version 73380 (0.0010) -[2023-10-10 15:33:14,247][76542] Updated weights for policy 1, policy_version 73390 (0.0008) -[2023-10-10 15:33:14,618][76542] Updated weights for policy 1, policy_version 73400 (0.0009) -[2023-10-10 15:33:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 150470656. Throughput: 0: 1824.3, 1: 1818.2. Samples: 37628274. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:33:16,077][75634] Avg episode reward: [(0, '38.350'), (1, '32.740')] -[2023-10-10 15:33:16,653][76543] Updated weights for policy 0, policy_version 73543 (0.0007) -[2023-10-10 15:33:17,025][76543] Updated weights for policy 0, policy_version 73553 (0.0008) -[2023-10-10 15:33:17,391][76543] Updated weights for policy 0, policy_version 73563 (0.0007) -[2023-10-10 15:33:18,360][76542] Updated weights for policy 1, policy_version 73410 (0.0010) -[2023-10-10 15:33:18,723][76542] Updated weights for policy 1, policy_version 73420 (0.0007) -[2023-10-10 15:33:19,097][76542] Updated weights for policy 1, policy_version 73430 (0.0007) -[2023-10-10 15:33:19,461][76542] Updated weights for policy 1, policy_version 73440 (0.0007) -[2023-10-10 15:33:20,999][76543] Updated weights for policy 0, policy_version 73573 (0.0009) -[2023-10-10 15:33:21,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 150536192. Throughput: 0: 1823.7, 1: 1819.1. Samples: 37639082. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:33:21,077][75634] Avg episode reward: [(0, '35.170'), (1, '30.600')] -[2023-10-10 15:33:21,379][76543] Updated weights for policy 0, policy_version 73583 (0.0008) -[2023-10-10 15:33:21,750][76543] Updated weights for policy 0, policy_version 73593 (0.0008) -[2023-10-10 15:33:23,153][76542] Updated weights for policy 1, policy_version 73450 (0.0010) -[2023-10-10 15:33:23,519][76542] Updated weights for policy 1, policy_version 73460 (0.0009) -[2023-10-10 15:33:23,889][76542] Updated weights for policy 1, policy_version 73470 (0.0008) -[2023-10-10 15:33:25,317][76543] Updated weights for policy 0, policy_version 73603 (0.0007) -[2023-10-10 15:33:25,688][76543] Updated weights for policy 0, policy_version 73613 (0.0011) -[2023-10-10 15:33:26,063][76543] Updated weights for policy 0, policy_version 73623 (0.0007) -[2023-10-10 15:33:26,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 150601728. Throughput: 0: 1831.9, 1: 1807.3. Samples: 37661012. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:33:26,076][75634] Avg episode reward: [(0, '39.250'), (1, '33.180')] -[2023-10-10 15:33:27,520][76542] Updated weights for policy 1, policy_version 73480 (0.0009) -[2023-10-10 15:33:27,897][76542] Updated weights for policy 1, policy_version 73490 (0.0007) -[2023-10-10 15:33:28,267][76542] Updated weights for policy 1, policy_version 73500 (0.0008) -[2023-10-10 15:33:29,679][76543] Updated weights for policy 0, policy_version 73633 (0.0010) -[2023-10-10 15:33:30,048][76543] Updated weights for policy 0, policy_version 73643 (0.0009) -[2023-10-10 15:33:30,411][76543] Updated weights for policy 0, policy_version 73653 (0.0009) -[2023-10-10 15:33:30,791][76543] Updated weights for policy 0, policy_version 73663 (0.0009) -[2023-10-10 15:33:31,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 150700032. Throughput: 0: 1824.2, 1: 1815.2. Samples: 37683488. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 15:33:31,077][75634] Avg episode reward: [(0, '40.060'), (1, '33.970')] -[2023-10-10 15:33:31,828][76542] Updated weights for policy 1, policy_version 73510 (0.0008) -[2023-10-10 15:33:32,191][76542] Updated weights for policy 1, policy_version 73520 (0.0010) -[2023-10-10 15:33:32,557][76542] Updated weights for policy 1, policy_version 73530 (0.0007) -[2023-10-10 15:33:34,385][76543] Updated weights for policy 0, policy_version 73673 (0.0009) -[2023-10-10 15:33:34,748][76543] Updated weights for policy 0, policy_version 73683 (0.0010) -[2023-10-10 15:33:35,129][76543] Updated weights for policy 0, policy_version 73693 (0.0008) -[2023-10-10 15:33:36,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 150765568. Throughput: 0: 1838.4, 1: 1815.2. Samples: 37694286. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 15:33:36,077][75634] Avg episode reward: [(0, '36.190'), (1, '35.880')] -[2023-10-10 15:33:36,449][76542] Updated weights for policy 1, policy_version 73540 (0.0008) -[2023-10-10 15:33:36,845][76542] Updated weights for policy 1, policy_version 73550 (0.0008) -[2023-10-10 15:33:37,219][76542] Updated weights for policy 1, policy_version 73560 (0.0009) -[2023-10-10 15:33:38,753][76543] Updated weights for policy 0, policy_version 73703 (0.0010) -[2023-10-10 15:33:39,129][76543] Updated weights for policy 0, policy_version 73713 (0.0008) -[2023-10-10 15:33:39,505][76543] Updated weights for policy 0, policy_version 73723 (0.0010) -[2023-10-10 15:33:40,883][76542] Updated weights for policy 1, policy_version 73570 (0.0008) -[2023-10-10 15:33:41,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 150831104. Throughput: 0: 1822.2, 1: 1815.2. Samples: 37716180. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 15:33:41,077][75634] Avg episode reward: [(0, '38.360'), (1, '36.190')] -[2023-10-10 15:33:41,249][76542] Updated weights for policy 1, policy_version 73580 (0.0007) -[2023-10-10 15:33:41,628][76542] Updated weights for policy 1, policy_version 73590 (0.0008) -[2023-10-10 15:33:41,990][76542] Updated weights for policy 1, policy_version 73600 (0.0008) -[2023-10-10 15:33:43,196][76543] Updated weights for policy 0, policy_version 73733 (0.0008) -[2023-10-10 15:33:43,566][76543] Updated weights for policy 0, policy_version 73743 (0.0007) -[2023-10-10 15:33:43,938][76543] Updated weights for policy 0, policy_version 73753 (0.0008) -[2023-10-10 15:33:45,620][76542] Updated weights for policy 1, policy_version 73610 (0.0007) -[2023-10-10 15:33:45,981][76542] Updated weights for policy 1, policy_version 73620 (0.0008) -[2023-10-10 15:33:46,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 150896640. Throughput: 0: 1836.0, 1: 1818.7. Samples: 37737910. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 15:33:46,076][75634] Avg episode reward: [(0, '35.710'), (1, '36.420')] -[2023-10-10 15:33:46,363][76542] Updated weights for policy 1, policy_version 73630 (0.0008) -[2023-10-10 15:33:47,618][76543] Updated weights for policy 0, policy_version 73763 (0.0008) -[2023-10-10 15:33:48,010][76543] Updated weights for policy 0, policy_version 73773 (0.0009) -[2023-10-10 15:33:48,384][76543] Updated weights for policy 0, policy_version 73783 (0.0009) -[2023-10-10 15:33:50,069][76542] Updated weights for policy 1, policy_version 73640 (0.0010) -[2023-10-10 15:33:50,438][76542] Updated weights for policy 1, policy_version 73650 (0.0010) -[2023-10-10 15:33:50,806][76542] Updated weights for policy 1, policy_version 73660 (0.0007) -[2023-10-10 15:33:51,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 150994944. Throughput: 0: 1828.7, 1: 1813.8. Samples: 37749110. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 15:33:51,076][75634] Avg episode reward: [(0, '34.290'), (1, '38.210')] -[2023-10-10 15:33:52,259][76543] Updated weights for policy 0, policy_version 73793 (0.0008) -[2023-10-10 15:33:52,629][76543] Updated weights for policy 0, policy_version 73803 (0.0008) -[2023-10-10 15:33:53,004][76543] Updated weights for policy 0, policy_version 73813 (0.0010) -[2023-10-10 15:33:53,376][76543] Updated weights for policy 0, policy_version 73823 (0.0009) -[2023-10-10 15:33:54,483][76542] Updated weights for policy 1, policy_version 73670 (0.0007) -[2023-10-10 15:33:54,856][76542] Updated weights for policy 1, policy_version 73680 (0.0008) -[2023-10-10 15:33:55,224][76542] Updated weights for policy 1, policy_version 73690 (0.0009) -[2023-10-10 15:33:56,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 151060480. Throughput: 0: 1845.2, 1: 1820.5. Samples: 37770786. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 15:33:56,077][75634] Avg episode reward: [(0, '36.560'), (1, '33.370')] -[2023-10-10 15:33:56,882][76543] Updated weights for policy 0, policy_version 73833 (0.0007) -[2023-10-10 15:33:57,262][76543] Updated weights for policy 0, policy_version 73843 (0.0007) -[2023-10-10 15:33:57,627][76543] Updated weights for policy 0, policy_version 73853 (0.0010) -[2023-10-10 15:33:58,788][76542] Updated weights for policy 1, policy_version 73700 (0.0008) -[2023-10-10 15:33:59,170][76542] Updated weights for policy 1, policy_version 73710 (0.0009) -[2023-10-10 15:33:59,529][76542] Updated weights for policy 1, policy_version 73720 (0.0009) -[2023-10-10 15:34:01,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 151126016. Throughput: 0: 1838.9, 1: 1817.7. Samples: 37792820. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 15:34:01,076][75634] Avg episode reward: [(0, '35.340'), (1, '36.810')] -[2023-10-10 15:34:01,255][76543] Updated weights for policy 0, policy_version 73863 (0.0010) -[2023-10-10 15:34:01,626][76543] Updated weights for policy 0, policy_version 73873 (0.0009) -[2023-10-10 15:34:01,990][76543] Updated weights for policy 0, policy_version 73883 (0.0012) -[2023-10-10 15:34:03,378][76542] Updated weights for policy 1, policy_version 73730 (0.0009) -[2023-10-10 15:34:03,744][76542] Updated weights for policy 1, policy_version 73740 (0.0009) -[2023-10-10 15:34:04,114][76542] Updated weights for policy 1, policy_version 73750 (0.0009) -[2023-10-10 15:34:04,481][76542] Updated weights for policy 1, policy_version 73760 (0.0009) -[2023-10-10 15:34:05,721][76543] Updated weights for policy 0, policy_version 73893 (0.0009) -[2023-10-10 15:34:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 151191552. Throughput: 0: 1837.3, 1: 1824.0. Samples: 37803842. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 15:34:06,077][75634] Avg episode reward: [(0, '37.010'), (1, '35.190')] -[2023-10-10 15:34:06,095][76543] Updated weights for policy 0, policy_version 73903 (0.0007) -[2023-10-10 15:34:06,458][76543] Updated weights for policy 0, policy_version 73913 (0.0008) -[2023-10-10 15:34:08,256][76542] Updated weights for policy 1, policy_version 73770 (0.0007) -[2023-10-10 15:34:08,623][76542] Updated weights for policy 1, policy_version 73780 (0.0008) -[2023-10-10 15:34:09,000][76542] Updated weights for policy 1, policy_version 73790 (0.0012) -[2023-10-10 15:34:10,124][76543] Updated weights for policy 0, policy_version 73923 (0.0010) -[2023-10-10 15:34:10,488][76543] Updated weights for policy 0, policy_version 73933 (0.0008) -[2023-10-10 15:34:10,864][76543] Updated weights for policy 0, policy_version 73943 (0.0008) -[2023-10-10 15:34:11,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 151257088. Throughput: 0: 1836.5, 1: 1822.4. Samples: 37825660. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 15:34:11,076][75634] Avg episode reward: [(0, '41.370'), (1, '34.580')] -[2023-10-10 15:34:12,617][76542] Updated weights for policy 1, policy_version 73800 (0.0009) -[2023-10-10 15:34:12,983][76542] Updated weights for policy 1, policy_version 73810 (0.0009) -[2023-10-10 15:34:13,353][76542] Updated weights for policy 1, policy_version 73820 (0.0009) -[2023-10-10 15:34:14,443][76543] Updated weights for policy 0, policy_version 73953 (0.0008) -[2023-10-10 15:34:14,802][76543] Updated weights for policy 0, policy_version 73963 (0.0009) -[2023-10-10 15:34:15,178][76543] Updated weights for policy 0, policy_version 73973 (0.0010) -[2023-10-10 15:34:15,553][76543] Updated weights for policy 0, policy_version 73983 (0.0008) -[2023-10-10 15:34:16,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 151355392. Throughput: 0: 1829.5, 1: 1819.9. Samples: 37847710. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-10 15:34:16,077][75634] Avg episode reward: [(0, '43.000'), (1, '34.180')] -[2023-10-10 15:34:16,964][76542] Updated weights for policy 1, policy_version 73830 (0.0008) -[2023-10-10 15:34:17,339][76542] Updated weights for policy 1, policy_version 73840 (0.0007) -[2023-10-10 15:34:17,714][76542] Updated weights for policy 1, policy_version 73850 (0.0007) -[2023-10-10 15:34:19,340][76543] Updated weights for policy 0, policy_version 73993 (0.0010) -[2023-10-10 15:34:19,715][76543] Updated weights for policy 0, policy_version 74003 (0.0008) -[2023-10-10 15:34:20,082][76543] Updated weights for policy 0, policy_version 74013 (0.0009) -[2023-10-10 15:34:21,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 151420928. Throughput: 0: 1834.1, 1: 1823.6. Samples: 37858884. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-10 15:34:21,076][75634] Avg episode reward: [(0, '37.180'), (1, '33.750')] -[2023-10-10 15:34:21,256][76542] Updated weights for policy 1, policy_version 73860 (0.0007) -[2023-10-10 15:34:21,626][76542] Updated weights for policy 1, policy_version 73870 (0.0007) -[2023-10-10 15:34:21,993][76542] Updated weights for policy 1, policy_version 73880 (0.0008) -[2023-10-10 15:34:23,756][76543] Updated weights for policy 0, policy_version 74023 (0.0010) -[2023-10-10 15:34:24,127][76543] Updated weights for policy 0, policy_version 74033 (0.0008) -[2023-10-10 15:34:24,495][76543] Updated weights for policy 0, policy_version 74043 (0.0009) -[2023-10-10 15:34:25,709][76542] Updated weights for policy 1, policy_version 73890 (0.0007) -[2023-10-10 15:34:26,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14440.2). Total num frames: 151486464. Throughput: 0: 1831.2, 1: 1836.8. Samples: 37881238. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-10 15:34:26,076][75634] Avg episode reward: [(0, '37.650'), (1, '37.150')] -[2023-10-10 15:34:26,084][76542] Updated weights for policy 1, policy_version 73900 (0.0008) -[2023-10-10 15:34:26,463][76542] Updated weights for policy 1, policy_version 73910 (0.0007) -[2023-10-10 15:34:26,825][76542] Updated weights for policy 1, policy_version 73920 (0.0008) -[2023-10-10 15:34:28,180][76543] Updated weights for policy 0, policy_version 74053 (0.0008) -[2023-10-10 15:34:28,554][76543] Updated weights for policy 0, policy_version 74063 (0.0007) -[2023-10-10 15:34:28,923][76543] Updated weights for policy 0, policy_version 74073 (0.0007) -[2023-10-10 15:34:30,436][76542] Updated weights for policy 1, policy_version 73930 (0.0008) -[2023-10-10 15:34:30,802][76542] Updated weights for policy 1, policy_version 73940 (0.0008) -[2023-10-10 15:34:31,076][75634] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 151552000. Throughput: 0: 1831.9, 1: 1831.7. Samples: 37902770. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-10 15:34:31,077][75634] Avg episode reward: [(0, '35.570'), (1, '37.520')] -[2023-10-10 15:34:31,085][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000074080_75857920.pth... -[2023-10-10 15:34:31,119][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000072384_74121216.pth -[2023-10-10 15:34:31,168][76542] Updated weights for policy 1, policy_version 73950 (0.0007) -[2023-10-10 15:34:31,238][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000073952_75726848.pth... -[2023-10-10 15:34:31,277][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000072256_73990144.pth -[2023-10-10 15:34:32,593][76543] Updated weights for policy 0, policy_version 74083 (0.0010) -[2023-10-10 15:34:32,970][76543] Updated weights for policy 0, policy_version 74093 (0.0011) -[2023-10-10 15:34:33,342][76543] Updated weights for policy 0, policy_version 74103 (0.0009) -[2023-10-10 15:34:34,912][76542] Updated weights for policy 1, policy_version 73960 (0.0008) -[2023-10-10 15:34:35,276][76542] Updated weights for policy 1, policy_version 73970 (0.0009) -[2023-10-10 15:34:35,646][76542] Updated weights for policy 1, policy_version 73980 (0.0007) -[2023-10-10 15:34:36,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 151650304. Throughput: 0: 1830.2, 1: 1838.3. Samples: 37914192. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-10 15:34:36,076][75634] Avg episode reward: [(0, '32.250'), (1, '33.900')] -[2023-10-10 15:34:36,946][76543] Updated weights for policy 0, policy_version 74113 (0.0008) -[2023-10-10 15:34:37,320][76543] Updated weights for policy 0, policy_version 74123 (0.0011) -[2023-10-10 15:34:37,695][76543] Updated weights for policy 0, policy_version 74133 (0.0010) -[2023-10-10 15:34:38,063][76543] Updated weights for policy 0, policy_version 74143 (0.0010) -[2023-10-10 15:34:39,347][76542] Updated weights for policy 1, policy_version 73990 (0.0007) -[2023-10-10 15:34:39,716][76542] Updated weights for policy 1, policy_version 74000 (0.0008) -[2023-10-10 15:34:40,087][76542] Updated weights for policy 1, policy_version 74010 (0.0009) -[2023-10-10 15:34:41,076][75634] Fps is (10 sec: 16384.5, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 151715840. Throughput: 0: 1831.0, 1: 1831.9. Samples: 37935616. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-10 15:34:41,076][75634] Avg episode reward: [(0, '31.590'), (1, '37.300')] -[2023-10-10 15:34:41,679][76543] Updated weights for policy 0, policy_version 74153 (0.0011) -[2023-10-10 15:34:42,038][76543] Updated weights for policy 0, policy_version 74163 (0.0009) -[2023-10-10 15:34:42,408][76543] Updated weights for policy 0, policy_version 74173 (0.0008) -[2023-10-10 15:34:43,701][76542] Updated weights for policy 1, policy_version 74020 (0.0008) -[2023-10-10 15:34:44,073][76542] Updated weights for policy 1, policy_version 74030 (0.0011) -[2023-10-10 15:34:44,432][76542] Updated weights for policy 1, policy_version 74040 (0.0009) -[2023-10-10 15:34:46,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 151781376. Throughput: 0: 1823.0, 1: 1836.6. Samples: 37957504. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-10 15:34:46,077][75634] Avg episode reward: [(0, '32.850'), (1, '39.620')] -[2023-10-10 15:34:46,167][76543] Updated weights for policy 0, policy_version 74183 (0.0008) -[2023-10-10 15:34:46,536][76543] Updated weights for policy 0, policy_version 74193 (0.0008) -[2023-10-10 15:34:46,915][76543] Updated weights for policy 0, policy_version 74203 (0.0010) -[2023-10-10 15:34:48,112][76542] Updated weights for policy 1, policy_version 74050 (0.0010) -[2023-10-10 15:34:48,484][76542] Updated weights for policy 1, policy_version 74060 (0.0010) -[2023-10-10 15:34:48,850][76542] Updated weights for policy 1, policy_version 74070 (0.0007) -[2023-10-10 15:34:49,214][76542] Updated weights for policy 1, policy_version 74080 (0.0009) -[2023-10-10 15:34:50,520][76543] Updated weights for policy 0, policy_version 74213 (0.0010) -[2023-10-10 15:34:50,882][76543] Updated weights for policy 0, policy_version 74223 (0.0007) -[2023-10-10 15:34:51,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 151846912. Throughput: 0: 1821.2, 1: 1827.7. Samples: 37968042. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-10 15:34:51,076][75634] Avg episode reward: [(0, '32.900'), (1, '37.000')] -[2023-10-10 15:34:51,260][76543] Updated weights for policy 0, policy_version 74233 (0.0007) -[2023-10-10 15:34:52,713][76542] Updated weights for policy 1, policy_version 74090 (0.0010) -[2023-10-10 15:34:53,072][76542] Updated weights for policy 1, policy_version 74100 (0.0011) -[2023-10-10 15:34:53,435][76542] Updated weights for policy 1, policy_version 74110 (0.0007) -[2023-10-10 15:34:54,958][76543] Updated weights for policy 0, policy_version 74243 (0.0007) -[2023-10-10 15:34:55,324][76543] Updated weights for policy 0, policy_version 74253 (0.0007) -[2023-10-10 15:34:55,697][76543] Updated weights for policy 0, policy_version 74263 (0.0009) -[2023-10-10 15:34:56,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 151945216. Throughput: 0: 1822.0, 1: 1842.9. Samples: 37990580. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-10 15:34:56,076][75634] Avg episode reward: [(0, '31.760'), (1, '34.450')] -[2023-10-10 15:34:57,118][76542] Updated weights for policy 1, policy_version 74120 (0.0008) -[2023-10-10 15:34:57,482][76542] Updated weights for policy 1, policy_version 74130 (0.0008) -[2023-10-10 15:34:57,845][76542] Updated weights for policy 1, policy_version 74140 (0.0008) -[2023-10-10 15:34:59,238][76543] Updated weights for policy 0, policy_version 74273 (0.0008) -[2023-10-10 15:34:59,599][76543] Updated weights for policy 0, policy_version 74283 (0.0008) -[2023-10-10 15:34:59,974][76543] Updated weights for policy 0, policy_version 74293 (0.0010) -[2023-10-10 15:35:00,356][76543] Updated weights for policy 0, policy_version 74303 (0.0008) -[2023-10-10 15:35:01,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 152010752. Throughput: 0: 1820.7, 1: 1842.8. Samples: 38012570. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-10 15:35:01,077][75634] Avg episode reward: [(0, '33.040'), (1, '36.340')] -[2023-10-10 15:35:01,473][76542] Updated weights for policy 1, policy_version 74150 (0.0008) -[2023-10-10 15:35:01,843][76542] Updated weights for policy 1, policy_version 74160 (0.0009) -[2023-10-10 15:35:02,216][76542] Updated weights for policy 1, policy_version 74170 (0.0007) -[2023-10-10 15:35:03,996][76543] Updated weights for policy 0, policy_version 74313 (0.0008) -[2023-10-10 15:35:04,368][76543] Updated weights for policy 0, policy_version 74323 (0.0008) -[2023-10-10 15:35:04,733][76543] Updated weights for policy 0, policy_version 74333 (0.0008) -[2023-10-10 15:35:05,791][76542] Updated weights for policy 1, policy_version 74180 (0.0007) -[2023-10-10 15:35:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 152076288. Throughput: 0: 1826.7, 1: 1838.4. Samples: 38023814. Policy #0 lag: (min: 31.0, avg: 32.5, max: 56.0) -[2023-10-10 15:35:06,076][75634] Avg episode reward: [(0, '36.080'), (1, '40.430')] -[2023-10-10 15:35:06,155][76542] Updated weights for policy 1, policy_version 74190 (0.0008) -[2023-10-10 15:35:06,521][76542] Updated weights for policy 1, policy_version 74200 (0.0009) -[2023-10-10 15:35:08,443][76543] Updated weights for policy 0, policy_version 74343 (0.0009) -[2023-10-10 15:35:08,799][76543] Updated weights for policy 0, policy_version 74353 (0.0008) -[2023-10-10 15:35:09,174][76543] Updated weights for policy 0, policy_version 74363 (0.0008) -[2023-10-10 15:35:10,295][76542] Updated weights for policy 1, policy_version 74210 (0.0009) -[2023-10-10 15:35:10,712][76542] Updated weights for policy 1, policy_version 74220 (0.0010) -[2023-10-10 15:35:11,076][76542] Updated weights for policy 1, policy_version 74230 (0.0010) -[2023-10-10 15:35:11,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 152141824. Throughput: 0: 1815.6, 1: 1836.7. Samples: 38045590. Policy #0 lag: (min: 31.0, avg: 32.5, max: 56.0) -[2023-10-10 15:35:11,077][75634] Avg episode reward: [(0, '35.710'), (1, '39.640')] -[2023-10-10 15:35:11,451][76542] Updated weights for policy 1, policy_version 74240 (0.0011) -[2023-10-10 15:35:12,857][76543] Updated weights for policy 0, policy_version 74373 (0.0008) -[2023-10-10 15:35:13,237][76543] Updated weights for policy 0, policy_version 74383 (0.0008) -[2023-10-10 15:35:13,607][76543] Updated weights for policy 0, policy_version 74393 (0.0007) -[2023-10-10 15:35:15,152][76542] Updated weights for policy 1, policy_version 74250 (0.0007) -[2023-10-10 15:35:15,520][76542] Updated weights for policy 1, policy_version 74260 (0.0008) -[2023-10-10 15:35:15,889][76542] Updated weights for policy 1, policy_version 74270 (0.0008) -[2023-10-10 15:35:16,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 152240128. Throughput: 0: 1828.8, 1: 1817.9. Samples: 38066870. Policy #0 lag: (min: 31.0, avg: 32.5, max: 56.0) -[2023-10-10 15:35:16,077][75634] Avg episode reward: [(0, '34.000'), (1, '35.330')] -[2023-10-10 15:35:17,142][76543] Updated weights for policy 0, policy_version 74403 (0.0007) -[2023-10-10 15:35:17,510][76543] Updated weights for policy 0, policy_version 74413 (0.0007) -[2023-10-10 15:35:17,884][76543] Updated weights for policy 0, policy_version 74423 (0.0008) -[2023-10-10 15:35:19,611][76542] Updated weights for policy 1, policy_version 74280 (0.0009) -[2023-10-10 15:35:19,978][76542] Updated weights for policy 1, policy_version 74290 (0.0010) -[2023-10-10 15:35:20,346][76542] Updated weights for policy 1, policy_version 74300 (0.0009) -[2023-10-10 15:35:21,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 152305664. Throughput: 0: 1824.8, 1: 1819.1. Samples: 38078170. Policy #0 lag: (min: 31.0, avg: 32.5, max: 56.0) -[2023-10-10 15:35:21,077][75634] Avg episode reward: [(0, '36.560'), (1, '36.160')] -[2023-10-10 15:35:21,531][76543] Updated weights for policy 0, policy_version 74433 (0.0008) -[2023-10-10 15:35:21,929][76543] Updated weights for policy 0, policy_version 74443 (0.0009) -[2023-10-10 15:35:22,290][76543] Updated weights for policy 0, policy_version 74453 (0.0010) -[2023-10-10 15:35:22,655][76543] Updated weights for policy 0, policy_version 74463 (0.0011) -[2023-10-10 15:35:24,177][76542] Updated weights for policy 1, policy_version 74310 (0.0008) -[2023-10-10 15:35:24,544][76542] Updated weights for policy 1, policy_version 74320 (0.0008) -[2023-10-10 15:35:24,909][76542] Updated weights for policy 1, policy_version 74330 (0.0010) -[2023-10-10 15:35:26,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 152371200. Throughput: 0: 1839.3, 1: 1809.3. Samples: 38099802. Policy #0 lag: (min: 31.0, avg: 32.5, max: 56.0) -[2023-10-10 15:35:26,076][75634] Avg episode reward: [(0, '39.970'), (1, '33.920')] -[2023-10-10 15:35:26,224][76543] Updated weights for policy 0, policy_version 74473 (0.0009) -[2023-10-10 15:35:26,598][76543] Updated weights for policy 0, policy_version 74483 (0.0008) -[2023-10-10 15:35:26,959][76543] Updated weights for policy 0, policy_version 74493 (0.0009) -[2023-10-10 15:35:28,762][76542] Updated weights for policy 1, policy_version 74340 (0.0010) -[2023-10-10 15:35:29,142][76542] Updated weights for policy 1, policy_version 74350 (0.0008) -[2023-10-10 15:35:29,504][76542] Updated weights for policy 1, policy_version 74360 (0.0008) -[2023-10-10 15:35:30,651][76543] Updated weights for policy 0, policy_version 74503 (0.0009) -[2023-10-10 15:35:31,018][76543] Updated weights for policy 0, policy_version 74513 (0.0008) -[2023-10-10 15:35:31,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 152436736. Throughput: 0: 1846.1, 1: 1814.0. Samples: 38122210. Policy #0 lag: (min: 31.0, avg: 32.5, max: 56.0) -[2023-10-10 15:35:31,077][75634] Avg episode reward: [(0, '37.470'), (1, '33.980')] -[2023-10-10 15:35:31,395][76543] Updated weights for policy 0, policy_version 74523 (0.0007) -[2023-10-10 15:35:33,194][76542] Updated weights for policy 1, policy_version 74370 (0.0009) -[2023-10-10 15:35:33,574][76542] Updated weights for policy 1, policy_version 74380 (0.0007) -[2023-10-10 15:35:33,937][76542] Updated weights for policy 1, policy_version 74390 (0.0008) -[2023-10-10 15:35:34,303][76542] Updated weights for policy 1, policy_version 74400 (0.0011) -[2023-10-10 15:35:34,988][76543] Updated weights for policy 0, policy_version 74533 (0.0008) -[2023-10-10 15:35:35,361][76543] Updated weights for policy 0, policy_version 74543 (0.0007) -[2023-10-10 15:35:35,725][76543] Updated weights for policy 0, policy_version 74553 (0.0007) -[2023-10-10 15:35:36,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 152535040. Throughput: 0: 1848.5, 1: 1816.0. Samples: 38132942. Policy #0 lag: (min: 31.0, avg: 32.5, max: 56.0) -[2023-10-10 15:35:36,076][75634] Avg episode reward: [(0, '36.110'), (1, '36.250')] -[2023-10-10 15:35:38,013][76542] Updated weights for policy 1, policy_version 74410 (0.0009) -[2023-10-10 15:35:38,386][76542] Updated weights for policy 1, policy_version 74420 (0.0012) -[2023-10-10 15:35:38,751][76542] Updated weights for policy 1, policy_version 74430 (0.0008) -[2023-10-10 15:35:39,497][76543] Updated weights for policy 0, policy_version 74563 (0.0008) -[2023-10-10 15:35:39,857][76543] Updated weights for policy 0, policy_version 74573 (0.0009) -[2023-10-10 15:35:40,230][76543] Updated weights for policy 0, policy_version 74583 (0.0007) -[2023-10-10 15:35:41,076][75634] Fps is (10 sec: 16384.6, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 152600576. Throughput: 0: 1841.0, 1: 1810.3. Samples: 38154888. Policy #0 lag: (min: 31.0, avg: 32.5, max: 56.0) -[2023-10-10 15:35:41,077][75634] Avg episode reward: [(0, '34.790'), (1, '34.190')] -[2023-10-10 15:35:42,463][76542] Updated weights for policy 1, policy_version 74440 (0.0009) -[2023-10-10 15:35:42,833][76542] Updated weights for policy 1, policy_version 74450 (0.0009) -[2023-10-10 15:35:43,198][76542] Updated weights for policy 1, policy_version 74460 (0.0010) -[2023-10-10 15:35:43,657][76543] Updated weights for policy 0, policy_version 74593 (0.0009) -[2023-10-10 15:35:44,020][76543] Updated weights for policy 0, policy_version 74603 (0.0008) -[2023-10-10 15:35:44,388][76543] Updated weights for policy 0, policy_version 74613 (0.0008) -[2023-10-10 15:35:44,764][76543] Updated weights for policy 0, policy_version 74623 (0.0008) -[2023-10-10 15:35:46,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 152666112. Throughput: 0: 1840.0, 1: 1805.2. Samples: 38176606. Policy #0 lag: (min: 31.0, avg: 32.5, max: 56.0) -[2023-10-10 15:35:46,077][75634] Avg episode reward: [(0, '31.410'), (1, '34.150')] -[2023-10-10 15:35:46,855][76542] Updated weights for policy 1, policy_version 74470 (0.0008) -[2023-10-10 15:35:47,226][76542] Updated weights for policy 1, policy_version 74480 (0.0008) -[2023-10-10 15:35:47,598][76542] Updated weights for policy 1, policy_version 74490 (0.0007) -[2023-10-10 15:35:48,381][76543] Updated weights for policy 0, policy_version 74633 (0.0008) -[2023-10-10 15:35:48,753][76543] Updated weights for policy 0, policy_version 74643 (0.0012) -[2023-10-10 15:35:49,125][76543] Updated weights for policy 0, policy_version 74653 (0.0008) -[2023-10-10 15:35:51,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 152731648. Throughput: 0: 1841.2, 1: 1806.8. Samples: 38187976. Policy #0 lag: (min: 31.0, avg: 32.5, max: 56.0) -[2023-10-10 15:35:51,076][75634] Avg episode reward: [(0, '33.230'), (1, '35.180')] -[2023-10-10 15:35:51,255][76542] Updated weights for policy 1, policy_version 74500 (0.0009) -[2023-10-10 15:35:51,620][76542] Updated weights for policy 1, policy_version 74510 (0.0007) -[2023-10-10 15:35:51,987][76542] Updated weights for policy 1, policy_version 74520 (0.0007) -[2023-10-10 15:35:52,943][76543] Updated weights for policy 0, policy_version 74663 (0.0011) -[2023-10-10 15:35:53,317][76543] Updated weights for policy 0, policy_version 74673 (0.0010) -[2023-10-10 15:35:53,694][76543] Updated weights for policy 0, policy_version 74683 (0.0011) -[2023-10-10 15:35:55,623][76542] Updated weights for policy 1, policy_version 74530 (0.0009) -[2023-10-10 15:35:55,993][76542] Updated weights for policy 1, policy_version 74540 (0.0007) -[2023-10-10 15:35:56,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 152797184. Throughput: 0: 1842.0, 1: 1802.5. Samples: 38209590. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 15:35:56,076][75634] Avg episode reward: [(0, '34.500'), (1, '34.110')] -[2023-10-10 15:35:56,360][76542] Updated weights for policy 1, policy_version 74550 (0.0007) -[2023-10-10 15:35:56,728][76542] Updated weights for policy 1, policy_version 74560 (0.0007) -[2023-10-10 15:35:57,426][76543] Updated weights for policy 0, policy_version 74693 (0.0009) -[2023-10-10 15:35:57,802][76543] Updated weights for policy 0, policy_version 74703 (0.0008) -[2023-10-10 15:35:58,178][76543] Updated weights for policy 0, policy_version 74713 (0.0009) -[2023-10-10 15:36:00,188][76542] Updated weights for policy 1, policy_version 74570 (0.0011) -[2023-10-10 15:36:00,560][76542] Updated weights for policy 1, policy_version 74580 (0.0009) -[2023-10-10 15:36:00,930][76542] Updated weights for policy 1, policy_version 74590 (0.0008) -[2023-10-10 15:36:01,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 152895488. Throughput: 0: 1842.9, 1: 1816.1. Samples: 38231520. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 15:36:01,076][75634] Avg episode reward: [(0, '36.330'), (1, '33.490')] -[2023-10-10 15:36:01,919][76543] Updated weights for policy 0, policy_version 74723 (0.0010) -[2023-10-10 15:36:02,295][76543] Updated weights for policy 0, policy_version 74733 (0.0011) -[2023-10-10 15:36:02,664][76543] Updated weights for policy 0, policy_version 74743 (0.0010) -[2023-10-10 15:36:04,656][76542] Updated weights for policy 1, policy_version 74600 (0.0008) -[2023-10-10 15:36:05,027][76542] Updated weights for policy 1, policy_version 74610 (0.0007) -[2023-10-10 15:36:05,398][76542] Updated weights for policy 1, policy_version 74620 (0.0009) -[2023-10-10 15:36:06,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 152961024. Throughput: 0: 1833.3, 1: 1822.4. Samples: 38242680. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 15:36:06,077][75634] Avg episode reward: [(0, '37.790'), (1, '33.540')] -[2023-10-10 15:36:06,463][76543] Updated weights for policy 0, policy_version 74753 (0.0011) -[2023-10-10 15:36:06,836][76543] Updated weights for policy 0, policy_version 74763 (0.0010) -[2023-10-10 15:36:07,192][76543] Updated weights for policy 0, policy_version 74773 (0.0010) -[2023-10-10 15:36:07,570][76543] Updated weights for policy 0, policy_version 74783 (0.0010) -[2023-10-10 15:36:09,071][76542] Updated weights for policy 1, policy_version 74630 (0.0009) -[2023-10-10 15:36:09,449][76542] Updated weights for policy 1, policy_version 74640 (0.0008) -[2023-10-10 15:36:09,814][76542] Updated weights for policy 1, policy_version 74650 (0.0008) -[2023-10-10 15:36:11,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 153026560. Throughput: 0: 1827.2, 1: 1821.7. Samples: 38264000. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 15:36:11,076][75634] Avg episode reward: [(0, '39.650'), (1, '37.080')] -[2023-10-10 15:36:11,483][76543] Updated weights for policy 0, policy_version 74793 (0.0010) -[2023-10-10 15:36:11,859][76543] Updated weights for policy 0, policy_version 74803 (0.0009) -[2023-10-10 15:36:12,224][76543] Updated weights for policy 0, policy_version 74813 (0.0007) -[2023-10-10 15:36:13,468][76542] Updated weights for policy 1, policy_version 74660 (0.0009) -[2023-10-10 15:36:13,827][76542] Updated weights for policy 1, policy_version 74670 (0.0008) -[2023-10-10 15:36:14,201][76542] Updated weights for policy 1, policy_version 74680 (0.0008) -[2023-10-10 15:36:15,908][76543] Updated weights for policy 0, policy_version 74823 (0.0008) -[2023-10-10 15:36:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 153092096. Throughput: 0: 1817.1, 1: 1822.0. Samples: 38285966. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 15:36:16,077][75634] Avg episode reward: [(0, '41.050'), (1, '34.310')] -[2023-10-10 15:36:16,272][76543] Updated weights for policy 0, policy_version 74833 (0.0007) -[2023-10-10 15:36:16,638][76543] Updated weights for policy 0, policy_version 74843 (0.0007) -[2023-10-10 15:36:17,856][76542] Updated weights for policy 1, policy_version 74690 (0.0008) -[2023-10-10 15:36:18,219][76542] Updated weights for policy 1, policy_version 74700 (0.0007) -[2023-10-10 15:36:18,581][76542] Updated weights for policy 1, policy_version 74710 (0.0007) -[2023-10-10 15:36:18,949][76542] Updated weights for policy 1, policy_version 74720 (0.0008) -[2023-10-10 15:36:20,286][76543] Updated weights for policy 0, policy_version 74853 (0.0009) -[2023-10-10 15:36:20,662][76543] Updated weights for policy 0, policy_version 74863 (0.0008) -[2023-10-10 15:36:21,031][76543] Updated weights for policy 0, policy_version 74873 (0.0007) -[2023-10-10 15:36:21,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 153157632. Throughput: 0: 1815.7, 1: 1813.4. Samples: 38296252. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 15:36:21,076][75634] Avg episode reward: [(0, '39.470'), (1, '32.440')] -[2023-10-10 15:36:22,806][76542] Updated weights for policy 1, policy_version 74730 (0.0010) -[2023-10-10 15:36:23,172][76542] Updated weights for policy 1, policy_version 74740 (0.0010) -[2023-10-10 15:36:23,547][76542] Updated weights for policy 1, policy_version 74750 (0.0008) -[2023-10-10 15:36:24,745][76543] Updated weights for policy 0, policy_version 74883 (0.0010) -[2023-10-10 15:36:25,118][76543] Updated weights for policy 0, policy_version 74893 (0.0010) -[2023-10-10 15:36:25,475][76543] Updated weights for policy 0, policy_version 74903 (0.0010) -[2023-10-10 15:36:26,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 153255936. Throughput: 0: 1820.4, 1: 1819.2. Samples: 38318670. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 15:36:26,076][75634] Avg episode reward: [(0, '39.790'), (1, '32.750')] -[2023-10-10 15:36:27,234][76542] Updated weights for policy 1, policy_version 74760 (0.0007) -[2023-10-10 15:36:27,598][76542] Updated weights for policy 1, policy_version 74770 (0.0008) -[2023-10-10 15:36:27,960][76542] Updated weights for policy 1, policy_version 74780 (0.0008) -[2023-10-10 15:36:29,139][76543] Updated weights for policy 0, policy_version 74913 (0.0010) -[2023-10-10 15:36:29,505][76543] Updated weights for policy 0, policy_version 74923 (0.0010) -[2023-10-10 15:36:29,880][76543] Updated weights for policy 0, policy_version 74933 (0.0008) -[2023-10-10 15:36:30,239][76543] Updated weights for policy 0, policy_version 74943 (0.0008) -[2023-10-10 15:36:31,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 153321472. Throughput: 0: 1814.6, 1: 1822.3. Samples: 38340266. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 15:36:31,077][75634] Avg episode reward: [(0, '43.800'), (1, '35.120')] -[2023-10-10 15:36:31,087][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000074784_76578816.pth... -[2023-10-10 15:36:31,087][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000074944_76742656.pth... -[2023-10-10 15:36:31,117][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000073088_74842112.pth -[2023-10-10 15:36:31,129][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000073216_74973184.pth -[2023-10-10 15:36:31,584][76542] Updated weights for policy 1, policy_version 74790 (0.0009) -[2023-10-10 15:36:31,953][76542] Updated weights for policy 1, policy_version 74800 (0.0007) -[2023-10-10 15:36:32,322][76542] Updated weights for policy 1, policy_version 74810 (0.0009) -[2023-10-10 15:36:33,644][76543] Updated weights for policy 0, policy_version 74953 (0.0010) -[2023-10-10 15:36:34,016][76543] Updated weights for policy 0, policy_version 74963 (0.0011) -[2023-10-10 15:36:34,388][76543] Updated weights for policy 0, policy_version 74973 (0.0011) -[2023-10-10 15:36:36,007][76542] Updated weights for policy 1, policy_version 74820 (0.0009) -[2023-10-10 15:36:36,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 153387008. Throughput: 0: 1820.7, 1: 1820.7. Samples: 38351836. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 15:36:36,077][75634] Avg episode reward: [(0, '36.170'), (1, '43.020')] -[2023-10-10 15:36:36,373][76542] Updated weights for policy 1, policy_version 74830 (0.0009) -[2023-10-10 15:36:36,739][76542] Updated weights for policy 1, policy_version 74840 (0.0010) -[2023-10-10 15:36:37,032][76421] Saving new best policy, reward=43.020! -[2023-10-10 15:36:38,089][76543] Updated weights for policy 0, policy_version 74983 (0.0008) -[2023-10-10 15:36:38,463][76543] Updated weights for policy 0, policy_version 74993 (0.0007) -[2023-10-10 15:36:38,840][76543] Updated weights for policy 0, policy_version 75003 (0.0008) -[2023-10-10 15:36:40,778][76542] Updated weights for policy 1, policy_version 74850 (0.0009) -[2023-10-10 15:36:41,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 153452544. Throughput: 0: 1812.1, 1: 1815.8. Samples: 38372848. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-10 15:36:41,076][75634] Avg episode reward: [(0, '32.660'), (1, '39.380')] -[2023-10-10 15:36:41,178][76542] Updated weights for policy 1, policy_version 74860 (0.0011) -[2023-10-10 15:36:41,554][76542] Updated weights for policy 1, policy_version 74870 (0.0009) -[2023-10-10 15:36:41,931][76542] Updated weights for policy 1, policy_version 74880 (0.0010) -[2023-10-10 15:36:42,359][76543] Updated weights for policy 0, policy_version 75013 (0.0010) -[2023-10-10 15:36:42,728][76543] Updated weights for policy 0, policy_version 75023 (0.0009) -[2023-10-10 15:36:43,103][76543] Updated weights for policy 0, policy_version 75033 (0.0009) -[2023-10-10 15:36:45,621][76542] Updated weights for policy 1, policy_version 74890 (0.0009) -[2023-10-10 15:36:45,985][76542] Updated weights for policy 1, policy_version 74900 (0.0010) -[2023-10-10 15:36:46,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 153518080. Throughput: 0: 1817.7, 1: 1813.9. Samples: 38394940. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-10 15:36:46,076][75634] Avg episode reward: [(0, '30.810'), (1, '37.090')] -[2023-10-10 15:36:46,355][76542] Updated weights for policy 1, policy_version 74910 (0.0010) -[2023-10-10 15:36:46,735][76543] Updated weights for policy 0, policy_version 75043 (0.0007) -[2023-10-10 15:36:47,103][76543] Updated weights for policy 0, policy_version 75053 (0.0008) -[2023-10-10 15:36:47,470][76543] Updated weights for policy 0, policy_version 75063 (0.0007) -[2023-10-10 15:36:49,965][76542] Updated weights for policy 1, policy_version 74920 (0.0010) -[2023-10-10 15:36:50,332][76542] Updated weights for policy 1, policy_version 74930 (0.0009) -[2023-10-10 15:36:50,698][76542] Updated weights for policy 1, policy_version 74940 (0.0007) -[2023-10-10 15:36:51,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 153616384. Throughput: 0: 1818.7, 1: 1801.3. Samples: 38405580. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-10 15:36:51,076][75634] Avg episode reward: [(0, '30.380'), (1, '35.750')] -[2023-10-10 15:36:51,276][76543] Updated weights for policy 0, policy_version 75073 (0.0008) -[2023-10-10 15:36:51,652][76543] Updated weights for policy 0, policy_version 75083 (0.0009) -[2023-10-10 15:36:52,024][76543] Updated weights for policy 0, policy_version 75093 (0.0008) -[2023-10-10 15:36:52,394][76543] Updated weights for policy 0, policy_version 75103 (0.0009) -[2023-10-10 15:36:54,198][76542] Updated weights for policy 1, policy_version 74950 (0.0008) -[2023-10-10 15:36:54,558][76542] Updated weights for policy 1, policy_version 74960 (0.0008) -[2023-10-10 15:36:54,925][76542] Updated weights for policy 1, policy_version 74970 (0.0009) -[2023-10-10 15:36:56,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 153681920. Throughput: 0: 1823.1, 1: 1811.5. Samples: 38427554. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-10 15:36:56,077][75634] Avg episode reward: [(0, '31.780'), (1, '37.790')] -[2023-10-10 15:36:56,253][76543] Updated weights for policy 0, policy_version 75113 (0.0009) -[2023-10-10 15:36:56,620][76543] Updated weights for policy 0, policy_version 75123 (0.0008) -[2023-10-10 15:36:56,995][76543] Updated weights for policy 0, policy_version 75133 (0.0009) -[2023-10-10 15:36:58,595][76542] Updated weights for policy 1, policy_version 74980 (0.0009) -[2023-10-10 15:36:58,963][76542] Updated weights for policy 1, policy_version 74990 (0.0010) -[2023-10-10 15:36:59,331][76542] Updated weights for policy 1, policy_version 75000 (0.0008) -[2023-10-10 15:37:00,510][76543] Updated weights for policy 0, policy_version 75143 (0.0007) -[2023-10-10 15:37:00,880][76543] Updated weights for policy 0, policy_version 75153 (0.0009) -[2023-10-10 15:37:01,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 153747456. Throughput: 0: 1829.1, 1: 1812.4. Samples: 38449832. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-10 15:37:01,076][75634] Avg episode reward: [(0, '37.220'), (1, '32.650')] -[2023-10-10 15:37:01,253][76543] Updated weights for policy 0, policy_version 75163 (0.0007) -[2023-10-10 15:37:03,170][76542] Updated weights for policy 1, policy_version 75010 (0.0009) -[2023-10-10 15:37:03,544][76542] Updated weights for policy 1, policy_version 75020 (0.0008) -[2023-10-10 15:37:03,909][76542] Updated weights for policy 1, policy_version 75030 (0.0007) -[2023-10-10 15:37:04,282][76542] Updated weights for policy 1, policy_version 75040 (0.0007) -[2023-10-10 15:37:05,108][76543] Updated weights for policy 0, policy_version 75173 (0.0007) -[2023-10-10 15:37:05,492][76543] Updated weights for policy 0, policy_version 75183 (0.0007) -[2023-10-10 15:37:05,859][76543] Updated weights for policy 0, policy_version 75193 (0.0008) -[2023-10-10 15:37:06,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 153812992. Throughput: 0: 1830.9, 1: 1818.1. Samples: 38460456. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-10 15:37:06,076][75634] Avg episode reward: [(0, '38.940'), (1, '31.970')] -[2023-10-10 15:37:08,061][76542] Updated weights for policy 1, policy_version 75050 (0.0008) -[2023-10-10 15:37:08,423][76542] Updated weights for policy 1, policy_version 75060 (0.0008) -[2023-10-10 15:37:08,796][76542] Updated weights for policy 1, policy_version 75070 (0.0007) -[2023-10-10 15:37:09,436][76543] Updated weights for policy 0, policy_version 75203 (0.0008) -[2023-10-10 15:37:09,801][76543] Updated weights for policy 0, policy_version 75213 (0.0008) -[2023-10-10 15:37:10,179][76543] Updated weights for policy 0, policy_version 75223 (0.0010) -[2023-10-10 15:37:11,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 153911296. Throughput: 0: 1830.8, 1: 1812.3. Samples: 38482608. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-10 15:37:11,076][75634] Avg episode reward: [(0, '35.370'), (1, '32.720')] -[2023-10-10 15:37:12,580][76542] Updated weights for policy 1, policy_version 75080 (0.0007) -[2023-10-10 15:37:12,946][76542] Updated weights for policy 1, policy_version 75090 (0.0008) -[2023-10-10 15:37:13,319][76542] Updated weights for policy 1, policy_version 75100 (0.0010) -[2023-10-10 15:37:13,949][76543] Updated weights for policy 0, policy_version 75233 (0.0010) -[2023-10-10 15:37:14,321][76543] Updated weights for policy 0, policy_version 75243 (0.0009) -[2023-10-10 15:37:14,685][76543] Updated weights for policy 0, policy_version 75253 (0.0008) -[2023-10-10 15:37:15,056][76543] Updated weights for policy 0, policy_version 75263 (0.0010) -[2023-10-10 15:37:16,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 153976832. Throughput: 0: 1823.1, 1: 1816.9. Samples: 38504066. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-10 15:37:16,077][75634] Avg episode reward: [(0, '35.400'), (1, '35.920')] -[2023-10-10 15:37:16,880][76542] Updated weights for policy 1, policy_version 75110 (0.0011) -[2023-10-10 15:37:17,247][76542] Updated weights for policy 1, policy_version 75120 (0.0008) -[2023-10-10 15:37:17,616][76542] Updated weights for policy 1, policy_version 75130 (0.0010) -[2023-10-10 15:37:18,754][76543] Updated weights for policy 0, policy_version 75273 (0.0008) -[2023-10-10 15:37:19,122][76543] Updated weights for policy 0, policy_version 75283 (0.0007) -[2023-10-10 15:37:19,490][76543] Updated weights for policy 0, policy_version 75293 (0.0008) -[2023-10-10 15:37:21,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 154042368. Throughput: 0: 1820.5, 1: 1819.6. Samples: 38515642. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-10 15:37:21,076][75634] Avg episode reward: [(0, '36.090'), (1, '36.530')] -[2023-10-10 15:37:21,214][76542] Updated weights for policy 1, policy_version 75140 (0.0008) -[2023-10-10 15:37:21,584][76542] Updated weights for policy 1, policy_version 75150 (0.0011) -[2023-10-10 15:37:21,950][76542] Updated weights for policy 1, policy_version 75160 (0.0008) -[2023-10-10 15:37:22,967][76543] Updated weights for policy 0, policy_version 75303 (0.0009) -[2023-10-10 15:37:23,338][76543] Updated weights for policy 0, policy_version 75313 (0.0011) -[2023-10-10 15:37:23,710][76543] Updated weights for policy 0, policy_version 75323 (0.0008) -[2023-10-10 15:37:25,605][76542] Updated weights for policy 1, policy_version 75170 (0.0009) -[2023-10-10 15:37:26,014][76542] Updated weights for policy 1, policy_version 75180 (0.0009) -[2023-10-10 15:37:26,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 154107904. Throughput: 0: 1828.1, 1: 1826.8. Samples: 38537320. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-10 15:37:26,077][75634] Avg episode reward: [(0, '39.840'), (1, '36.370')] -[2023-10-10 15:37:26,386][76542] Updated weights for policy 1, policy_version 75190 (0.0008) -[2023-10-10 15:37:26,751][76542] Updated weights for policy 1, policy_version 75200 (0.0008) -[2023-10-10 15:37:27,358][76543] Updated weights for policy 0, policy_version 75333 (0.0009) -[2023-10-10 15:37:27,731][76543] Updated weights for policy 0, policy_version 75343 (0.0010) -[2023-10-10 15:37:28,095][76543] Updated weights for policy 0, policy_version 75353 (0.0010) -[2023-10-10 15:37:30,432][76542] Updated weights for policy 1, policy_version 75210 (0.0009) -[2023-10-10 15:37:30,797][76542] Updated weights for policy 1, policy_version 75220 (0.0009) -[2023-10-10 15:37:31,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 154173440. Throughput: 0: 1824.3, 1: 1824.9. Samples: 38559156. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-10 15:37:31,077][75634] Avg episode reward: [(0, '41.220'), (1, '39.590')] -[2023-10-10 15:37:31,160][76542] Updated weights for policy 1, policy_version 75230 (0.0010) -[2023-10-10 15:37:31,716][76543] Updated weights for policy 0, policy_version 75363 (0.0009) -[2023-10-10 15:37:32,087][76543] Updated weights for policy 0, policy_version 75373 (0.0008) -[2023-10-10 15:37:32,465][76543] Updated weights for policy 0, policy_version 75383 (0.0008) -[2023-10-10 15:37:34,829][76542] Updated weights for policy 1, policy_version 75240 (0.0009) -[2023-10-10 15:37:35,200][76542] Updated weights for policy 1, policy_version 75250 (0.0007) -[2023-10-10 15:37:35,565][76542] Updated weights for policy 1, policy_version 75260 (0.0007) -[2023-10-10 15:37:36,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 154271744. Throughput: 0: 1821.8, 1: 1829.7. Samples: 38569898. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) -[2023-10-10 15:37:36,076][75634] Avg episode reward: [(0, '40.220'), (1, '37.390')] -[2023-10-10 15:37:36,141][76543] Updated weights for policy 0, policy_version 75393 (0.0010) -[2023-10-10 15:37:36,514][76543] Updated weights for policy 0, policy_version 75403 (0.0008) -[2023-10-10 15:37:36,883][76543] Updated weights for policy 0, policy_version 75413 (0.0008) -[2023-10-10 15:37:37,251][76543] Updated weights for policy 0, policy_version 75423 (0.0009) -[2023-10-10 15:37:39,174][76542] Updated weights for policy 1, policy_version 75270 (0.0009) -[2023-10-10 15:37:39,547][76542] Updated weights for policy 1, policy_version 75280 (0.0007) -[2023-10-10 15:37:39,920][76542] Updated weights for policy 1, policy_version 75290 (0.0007) -[2023-10-10 15:37:41,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 154337280. Throughput: 0: 1818.3, 1: 1830.7. Samples: 38591758. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) -[2023-10-10 15:37:41,077][75634] Avg episode reward: [(0, '38.280'), (1, '36.730')] -[2023-10-10 15:37:41,228][76543] Updated weights for policy 0, policy_version 75433 (0.0010) -[2023-10-10 15:37:41,604][76543] Updated weights for policy 0, policy_version 75443 (0.0010) -[2023-10-10 15:37:41,969][76543] Updated weights for policy 0, policy_version 75453 (0.0007) -[2023-10-10 15:37:43,464][76542] Updated weights for policy 1, policy_version 75300 (0.0008) -[2023-10-10 15:37:43,832][76542] Updated weights for policy 1, policy_version 75310 (0.0007) -[2023-10-10 15:37:44,197][76542] Updated weights for policy 1, policy_version 75320 (0.0008) -[2023-10-10 15:37:45,571][76543] Updated weights for policy 0, policy_version 75463 (0.0008) -[2023-10-10 15:37:45,936][76543] Updated weights for policy 0, policy_version 75473 (0.0008) -[2023-10-10 15:37:46,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 154402816. Throughput: 0: 1815.4, 1: 1829.8. Samples: 38613866. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) -[2023-10-10 15:37:46,077][75634] Avg episode reward: [(0, '37.750'), (1, '34.030')] -[2023-10-10 15:37:46,300][76543] Updated weights for policy 0, policy_version 75483 (0.0007) -[2023-10-10 15:37:47,990][76542] Updated weights for policy 1, policy_version 75330 (0.0007) -[2023-10-10 15:37:48,352][76542] Updated weights for policy 1, policy_version 75340 (0.0008) -[2023-10-10 15:37:48,720][76542] Updated weights for policy 1, policy_version 75350 (0.0007) -[2023-10-10 15:37:49,093][76542] Updated weights for policy 1, policy_version 75360 (0.0009) -[2023-10-10 15:37:50,072][76543] Updated weights for policy 0, policy_version 75493 (0.0008) -[2023-10-10 15:37:50,439][76543] Updated weights for policy 0, policy_version 75503 (0.0008) -[2023-10-10 15:37:50,805][76543] Updated weights for policy 0, policy_version 75513 (0.0009) -[2023-10-10 15:37:51,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 154501120. Throughput: 0: 1814.7, 1: 1825.1. Samples: 38624248. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) -[2023-10-10 15:37:51,076][75634] Avg episode reward: [(0, '38.970'), (1, '34.450')] -[2023-10-10 15:37:52,856][76542] Updated weights for policy 1, policy_version 75370 (0.0010) -[2023-10-10 15:37:53,232][76542] Updated weights for policy 1, policy_version 75380 (0.0011) -[2023-10-10 15:37:53,595][76542] Updated weights for policy 1, policy_version 75390 (0.0011) -[2023-10-10 15:37:54,547][76543] Updated weights for policy 0, policy_version 75523 (0.0008) -[2023-10-10 15:37:54,922][76543] Updated weights for policy 0, policy_version 75533 (0.0008) -[2023-10-10 15:37:55,295][76543] Updated weights for policy 0, policy_version 75543 (0.0008) -[2023-10-10 15:37:56,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 154566656. Throughput: 0: 1815.7, 1: 1824.8. Samples: 38646432. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) -[2023-10-10 15:37:56,077][75634] Avg episode reward: [(0, '38.800'), (1, '35.520')] -[2023-10-10 15:37:57,221][76542] Updated weights for policy 1, policy_version 75400 (0.0008) -[2023-10-10 15:37:57,586][76542] Updated weights for policy 1, policy_version 75410 (0.0008) -[2023-10-10 15:37:57,958][76542] Updated weights for policy 1, policy_version 75420 (0.0009) -[2023-10-10 15:37:59,054][76543] Updated weights for policy 0, policy_version 75553 (0.0008) -[2023-10-10 15:37:59,427][76543] Updated weights for policy 0, policy_version 75563 (0.0007) -[2023-10-10 15:37:59,796][76543] Updated weights for policy 0, policy_version 75573 (0.0008) -[2023-10-10 15:38:00,166][76543] Updated weights for policy 0, policy_version 75583 (0.0010) -[2023-10-10 15:38:01,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 154632192. Throughput: 0: 1818.9, 1: 1823.5. Samples: 38667974. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) -[2023-10-10 15:38:01,076][75634] Avg episode reward: [(0, '32.630'), (1, '35.720')] -[2023-10-10 15:38:01,669][76542] Updated weights for policy 1, policy_version 75430 (0.0010) -[2023-10-10 15:38:02,043][76542] Updated weights for policy 1, policy_version 75440 (0.0010) -[2023-10-10 15:38:02,404][76542] Updated weights for policy 1, policy_version 75450 (0.0010) -[2023-10-10 15:38:03,513][76543] Updated weights for policy 0, policy_version 75593 (0.0009) -[2023-10-10 15:38:03,877][76543] Updated weights for policy 0, policy_version 75603 (0.0011) -[2023-10-10 15:38:04,251][76543] Updated weights for policy 0, policy_version 75613 (0.0007) -[2023-10-10 15:38:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 154697728. Throughput: 0: 1824.0, 1: 1818.7. Samples: 38679562. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) -[2023-10-10 15:38:06,076][75634] Avg episode reward: [(0, '34.550'), (1, '37.290')] -[2023-10-10 15:38:06,083][76542] Updated weights for policy 1, policy_version 75460 (0.0009) -[2023-10-10 15:38:06,453][76542] Updated weights for policy 1, policy_version 75470 (0.0007) -[2023-10-10 15:38:06,813][76542] Updated weights for policy 1, policy_version 75480 (0.0007) -[2023-10-10 15:38:08,083][76543] Updated weights for policy 0, policy_version 75623 (0.0009) -[2023-10-10 15:38:08,458][76543] Updated weights for policy 0, policy_version 75633 (0.0010) -[2023-10-10 15:38:08,836][76543] Updated weights for policy 0, policy_version 75643 (0.0009) -[2023-10-10 15:38:10,390][76542] Updated weights for policy 1, policy_version 75490 (0.0007) -[2023-10-10 15:38:10,760][76542] Updated weights for policy 1, policy_version 75500 (0.0009) -[2023-10-10 15:38:11,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 154763264. Throughput: 0: 1818.7, 1: 1818.4. Samples: 38700986. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) -[2023-10-10 15:38:11,077][75634] Avg episode reward: [(0, '34.480'), (1, '35.640')] -[2023-10-10 15:38:11,128][76542] Updated weights for policy 1, policy_version 75510 (0.0010) -[2023-10-10 15:38:11,496][76542] Updated weights for policy 1, policy_version 75520 (0.0008) -[2023-10-10 15:38:12,712][76543] Updated weights for policy 0, policy_version 75653 (0.0008) -[2023-10-10 15:38:13,083][76543] Updated weights for policy 0, policy_version 75663 (0.0009) -[2023-10-10 15:38:13,457][76543] Updated weights for policy 0, policy_version 75673 (0.0008) -[2023-10-10 15:38:15,139][76542] Updated weights for policy 1, policy_version 75530 (0.0010) -[2023-10-10 15:38:15,513][76542] Updated weights for policy 1, policy_version 75540 (0.0009) -[2023-10-10 15:38:15,885][76542] Updated weights for policy 1, policy_version 75550 (0.0009) -[2023-10-10 15:38:16,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 154861568. Throughput: 0: 1815.6, 1: 1818.8. Samples: 38722702. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) -[2023-10-10 15:38:16,077][75634] Avg episode reward: [(0, '33.960'), (1, '37.320')] -[2023-10-10 15:38:16,910][76543] Updated weights for policy 0, policy_version 75683 (0.0008) -[2023-10-10 15:38:17,276][76543] Updated weights for policy 0, policy_version 75693 (0.0007) -[2023-10-10 15:38:17,644][76543] Updated weights for policy 0, policy_version 75703 (0.0011) -[2023-10-10 15:38:19,632][76542] Updated weights for policy 1, policy_version 75560 (0.0010) -[2023-10-10 15:38:19,996][76542] Updated weights for policy 1, policy_version 75570 (0.0008) -[2023-10-10 15:38:20,363][76542] Updated weights for policy 1, policy_version 75580 (0.0011) -[2023-10-10 15:38:21,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 154927104. Throughput: 0: 1820.5, 1: 1826.4. Samples: 38734012. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) -[2023-10-10 15:38:21,077][75634] Avg episode reward: [(0, '36.020'), (1, '34.300')] -[2023-10-10 15:38:21,260][76543] Updated weights for policy 0, policy_version 75713 (0.0007) -[2023-10-10 15:38:21,630][76543] Updated weights for policy 0, policy_version 75723 (0.0008) -[2023-10-10 15:38:22,008][76543] Updated weights for policy 0, policy_version 75733 (0.0008) -[2023-10-10 15:38:22,374][76543] Updated weights for policy 0, policy_version 75743 (0.0009) -[2023-10-10 15:38:23,922][76542] Updated weights for policy 1, policy_version 75590 (0.0009) -[2023-10-10 15:38:24,295][76542] Updated weights for policy 1, policy_version 75600 (0.0007) -[2023-10-10 15:38:24,663][76542] Updated weights for policy 1, policy_version 75610 (0.0008) -[2023-10-10 15:38:26,048][76543] Updated weights for policy 0, policy_version 75753 (0.0008) -[2023-10-10 15:38:26,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 154992640. Throughput: 0: 1828.7, 1: 1820.5. Samples: 38755972. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-10 15:38:26,077][75634] Avg episode reward: [(0, '35.690'), (1, '34.530')] -[2023-10-10 15:38:26,427][76543] Updated weights for policy 0, policy_version 75763 (0.0007) -[2023-10-10 15:38:26,791][76543] Updated weights for policy 0, policy_version 75773 (0.0007) -[2023-10-10 15:38:28,414][76542] Updated weights for policy 1, policy_version 75620 (0.0009) -[2023-10-10 15:38:28,793][76542] Updated weights for policy 1, policy_version 75630 (0.0010) -[2023-10-10 15:38:29,157][76542] Updated weights for policy 1, policy_version 75640 (0.0007) -[2023-10-10 15:38:30,491][76543] Updated weights for policy 0, policy_version 75783 (0.0008) -[2023-10-10 15:38:30,859][76543] Updated weights for policy 0, policy_version 75793 (0.0009) -[2023-10-10 15:38:31,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 155058176. Throughput: 0: 1827.7, 1: 1826.6. Samples: 38778310. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-10 15:38:31,077][75634] Avg episode reward: [(0, '41.410'), (1, '32.560')] -[2023-10-10 15:38:31,085][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000075648_77463552.pth... -[2023-10-10 15:38:31,121][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000073952_75726848.pth -[2023-10-10 15:38:31,237][76543] Updated weights for policy 0, policy_version 75803 (0.0011) -[2023-10-10 15:38:31,419][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000075808_77627392.pth... -[2023-10-10 15:38:31,459][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000074080_75857920.pth -[2023-10-10 15:38:32,908][76542] Updated weights for policy 1, policy_version 75650 (0.0007) -[2023-10-10 15:38:33,281][76542] Updated weights for policy 1, policy_version 75660 (0.0008) -[2023-10-10 15:38:33,643][76542] Updated weights for policy 1, policy_version 75670 (0.0009) -[2023-10-10 15:38:34,013][76542] Updated weights for policy 1, policy_version 75680 (0.0008) -[2023-10-10 15:38:34,924][76543] Updated weights for policy 0, policy_version 75813 (0.0007) -[2023-10-10 15:38:35,300][76543] Updated weights for policy 0, policy_version 75823 (0.0008) -[2023-10-10 15:38:35,663][76543] Updated weights for policy 0, policy_version 75833 (0.0007) -[2023-10-10 15:38:36,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 155156480. Throughput: 0: 1827.3, 1: 1827.0. Samples: 38788690. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-10 15:38:36,076][75634] Avg episode reward: [(0, '41.550'), (1, '33.360')] -[2023-10-10 15:38:37,793][76542] Updated weights for policy 1, policy_version 75690 (0.0008) -[2023-10-10 15:38:38,163][76542] Updated weights for policy 1, policy_version 75700 (0.0008) -[2023-10-10 15:38:38,530][76542] Updated weights for policy 1, policy_version 75710 (0.0008) -[2023-10-10 15:38:39,243][76543] Updated weights for policy 0, policy_version 75843 (0.0008) -[2023-10-10 15:38:39,603][76543] Updated weights for policy 0, policy_version 75853 (0.0009) -[2023-10-10 15:38:39,971][76543] Updated weights for policy 0, policy_version 75863 (0.0011) -[2023-10-10 15:38:41,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 155222016. Throughput: 0: 1826.9, 1: 1834.3. Samples: 38811188. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-10 15:38:41,076][75634] Avg episode reward: [(0, '41.500'), (1, '40.640')] -[2023-10-10 15:38:42,205][76542] Updated weights for policy 1, policy_version 75720 (0.0013) -[2023-10-10 15:38:42,571][76542] Updated weights for policy 1, policy_version 75730 (0.0010) -[2023-10-10 15:38:42,938][76542] Updated weights for policy 1, policy_version 75740 (0.0011) -[2023-10-10 15:38:43,671][76543] Updated weights for policy 0, policy_version 75873 (0.0010) -[2023-10-10 15:38:44,045][76543] Updated weights for policy 0, policy_version 75883 (0.0007) -[2023-10-10 15:38:44,419][76543] Updated weights for policy 0, policy_version 75893 (0.0008) -[2023-10-10 15:38:44,788][76543] Updated weights for policy 0, policy_version 75903 (0.0011) -[2023-10-10 15:38:46,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 155287552. Throughput: 0: 1832.0, 1: 1830.0. Samples: 38832762. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-10 15:38:46,077][75634] Avg episode reward: [(0, '41.790'), (1, '35.310')] -[2023-10-10 15:38:46,578][76542] Updated weights for policy 1, policy_version 75750 (0.0009) -[2023-10-10 15:38:46,949][76542] Updated weights for policy 1, policy_version 75760 (0.0007) -[2023-10-10 15:38:47,318][76542] Updated weights for policy 1, policy_version 75770 (0.0009) -[2023-10-10 15:38:48,481][76543] Updated weights for policy 0, policy_version 75913 (0.0010) -[2023-10-10 15:38:48,855][76543] Updated weights for policy 0, policy_version 75923 (0.0011) -[2023-10-10 15:38:49,221][76543] Updated weights for policy 0, policy_version 75933 (0.0008) -[2023-10-10 15:38:51,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 155353088. Throughput: 0: 1824.9, 1: 1831.6. Samples: 38844104. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-10 15:38:51,076][75634] Avg episode reward: [(0, '41.800'), (1, '36.800')] -[2023-10-10 15:38:51,115][76542] Updated weights for policy 1, policy_version 75780 (0.0011) -[2023-10-10 15:38:51,480][76542] Updated weights for policy 1, policy_version 75790 (0.0010) -[2023-10-10 15:38:51,855][76542] Updated weights for policy 1, policy_version 75800 (0.0009) -[2023-10-10 15:38:52,921][76543] Updated weights for policy 0, policy_version 75943 (0.0011) -[2023-10-10 15:38:53,295][76543] Updated weights for policy 0, policy_version 75953 (0.0008) -[2023-10-10 15:38:53,664][76543] Updated weights for policy 0, policy_version 75963 (0.0008) -[2023-10-10 15:38:55,594][76542] Updated weights for policy 1, policy_version 75810 (0.0010) -[2023-10-10 15:38:55,992][76542] Updated weights for policy 1, policy_version 75820 (0.0010) -[2023-10-10 15:38:56,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 155418624. Throughput: 0: 1832.4, 1: 1823.4. Samples: 38865496. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-10 15:38:56,076][75634] Avg episode reward: [(0, '40.540'), (1, '37.820')] -[2023-10-10 15:38:56,352][76542] Updated weights for policy 1, policy_version 75830 (0.0008) -[2023-10-10 15:38:56,710][76542] Updated weights for policy 1, policy_version 75840 (0.0007) -[2023-10-10 15:38:57,214][76543] Updated weights for policy 0, policy_version 75973 (0.0009) -[2023-10-10 15:38:57,588][76543] Updated weights for policy 0, policy_version 75983 (0.0008) -[2023-10-10 15:38:57,950][76543] Updated weights for policy 0, policy_version 75993 (0.0009) -[2023-10-10 15:39:00,376][76542] Updated weights for policy 1, policy_version 75850 (0.0008) -[2023-10-10 15:39:00,748][76542] Updated weights for policy 1, policy_version 75860 (0.0007) -[2023-10-10 15:39:01,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 155484160. Throughput: 0: 1840.0, 1: 1827.2. Samples: 38887730. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-10 15:39:01,077][75634] Avg episode reward: [(0, '37.540'), (1, '39.600')] -[2023-10-10 15:39:01,116][76542] Updated weights for policy 1, policy_version 75870 (0.0007) -[2023-10-10 15:39:01,555][76543] Updated weights for policy 0, policy_version 76003 (0.0010) -[2023-10-10 15:39:01,924][76543] Updated weights for policy 0, policy_version 76013 (0.0010) -[2023-10-10 15:39:02,299][76543] Updated weights for policy 0, policy_version 76023 (0.0010) -[2023-10-10 15:39:04,847][76542] Updated weights for policy 1, policy_version 75880 (0.0008) -[2023-10-10 15:39:05,218][76542] Updated weights for policy 1, policy_version 75890 (0.0007) -[2023-10-10 15:39:05,578][76542] Updated weights for policy 1, policy_version 75900 (0.0008) -[2023-10-10 15:39:05,828][76543] Updated weights for policy 0, policy_version 76033 (0.0011) -[2023-10-10 15:39:06,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 155582464. Throughput: 0: 1837.6, 1: 1816.8. Samples: 38898456. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-10 15:39:06,076][75634] Avg episode reward: [(0, '36.110'), (1, '38.930')] -[2023-10-10 15:39:06,195][76543] Updated weights for policy 0, policy_version 76043 (0.0008) -[2023-10-10 15:39:06,570][76543] Updated weights for policy 0, policy_version 76053 (0.0007) -[2023-10-10 15:39:06,935][76543] Updated weights for policy 0, policy_version 76063 (0.0008) -[2023-10-10 15:39:09,184][76542] Updated weights for policy 1, policy_version 75910 (0.0009) -[2023-10-10 15:39:09,541][76542] Updated weights for policy 1, policy_version 75920 (0.0010) -[2023-10-10 15:39:09,912][76542] Updated weights for policy 1, policy_version 75930 (0.0008) -[2023-10-10 15:39:10,574][76543] Updated weights for policy 0, policy_version 76073 (0.0008) -[2023-10-10 15:39:10,935][76543] Updated weights for policy 0, policy_version 76083 (0.0010) -[2023-10-10 15:39:11,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 155648000. Throughput: 0: 1841.7, 1: 1821.3. Samples: 38920806. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-10 15:39:11,076][75634] Avg episode reward: [(0, '34.250'), (1, '33.980')] -[2023-10-10 15:39:11,314][76543] Updated weights for policy 0, policy_version 76093 (0.0008) -[2023-10-10 15:39:13,587][76542] Updated weights for policy 1, policy_version 75940 (0.0007) -[2023-10-10 15:39:13,960][76542] Updated weights for policy 1, policy_version 75950 (0.0007) -[2023-10-10 15:39:14,323][76542] Updated weights for policy 1, policy_version 75960 (0.0008) -[2023-10-10 15:39:15,113][76543] Updated weights for policy 0, policy_version 76103 (0.0007) -[2023-10-10 15:39:15,500][76543] Updated weights for policy 0, policy_version 76113 (0.0009) -[2023-10-10 15:39:15,878][76543] Updated weights for policy 0, policy_version 76123 (0.0009) -[2023-10-10 15:39:16,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 155746304. Throughput: 0: 1834.0, 1: 1817.6. Samples: 38942632. Policy #0 lag: (min: 21.0, avg: 28.4, max: 53.0) -[2023-10-10 15:39:16,077][75634] Avg episode reward: [(0, '33.130'), (1, '37.800')] -[2023-10-10 15:39:17,920][76542] Updated weights for policy 1, policy_version 75970 (0.0008) -[2023-10-10 15:39:18,289][76542] Updated weights for policy 1, policy_version 75980 (0.0007) -[2023-10-10 15:39:18,654][76542] Updated weights for policy 1, policy_version 75990 (0.0008) -[2023-10-10 15:39:19,024][76542] Updated weights for policy 1, policy_version 76000 (0.0010) -[2023-10-10 15:39:19,356][76543] Updated weights for policy 0, policy_version 76133 (0.0009) -[2023-10-10 15:39:19,726][76543] Updated weights for policy 0, policy_version 76143 (0.0009) -[2023-10-10 15:39:20,097][76543] Updated weights for policy 0, policy_version 76153 (0.0010) -[2023-10-10 15:39:21,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 155811840. Throughput: 0: 1843.7, 1: 1820.3. Samples: 38953572. Policy #0 lag: (min: 21.0, avg: 28.4, max: 53.0) -[2023-10-10 15:39:21,077][75634] Avg episode reward: [(0, '34.550'), (1, '36.510')] -[2023-10-10 15:39:22,757][76542] Updated weights for policy 1, policy_version 76010 (0.0008) -[2023-10-10 15:39:23,125][76542] Updated weights for policy 1, policy_version 76020 (0.0008) -[2023-10-10 15:39:23,488][76542] Updated weights for policy 1, policy_version 76030 (0.0009) -[2023-10-10 15:39:23,717][76543] Updated weights for policy 0, policy_version 76163 (0.0008) -[2023-10-10 15:39:24,086][76543] Updated weights for policy 0, policy_version 76173 (0.0009) -[2023-10-10 15:39:24,468][76543] Updated weights for policy 0, policy_version 76183 (0.0010) -[2023-10-10 15:39:26,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 155877376. Throughput: 0: 1822.6, 1: 1820.3. Samples: 38975118. Policy #0 lag: (min: 21.0, avg: 28.4, max: 53.0) -[2023-10-10 15:39:26,077][75634] Avg episode reward: [(0, '36.050'), (1, '31.880')] -[2023-10-10 15:39:27,221][76542] Updated weights for policy 1, policy_version 76040 (0.0009) -[2023-10-10 15:39:27,586][76542] Updated weights for policy 1, policy_version 76050 (0.0008) -[2023-10-10 15:39:27,955][76542] Updated weights for policy 1, policy_version 76060 (0.0008) -[2023-10-10 15:39:28,167][76543] Updated weights for policy 0, policy_version 76193 (0.0009) -[2023-10-10 15:39:28,540][76543] Updated weights for policy 0, policy_version 76203 (0.0008) -[2023-10-10 15:39:28,904][76543] Updated weights for policy 0, policy_version 76213 (0.0009) -[2023-10-10 15:39:29,277][76543] Updated weights for policy 0, policy_version 76223 (0.0009) -[2023-10-10 15:39:31,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 155942912. Throughput: 0: 1834.1, 1: 1818.7. Samples: 38997140. Policy #0 lag: (min: 21.0, avg: 28.4, max: 53.0) -[2023-10-10 15:39:31,077][75634] Avg episode reward: [(0, '33.640'), (1, '34.040')] -[2023-10-10 15:39:31,595][76542] Updated weights for policy 1, policy_version 76070 (0.0008) -[2023-10-10 15:39:31,963][76542] Updated weights for policy 1, policy_version 76080 (0.0009) -[2023-10-10 15:39:32,332][76542] Updated weights for policy 1, policy_version 76090 (0.0008) -[2023-10-10 15:39:32,955][76543] Updated weights for policy 0, policy_version 76233 (0.0011) -[2023-10-10 15:39:33,332][76543] Updated weights for policy 0, policy_version 76243 (0.0010) -[2023-10-10 15:39:33,699][76543] Updated weights for policy 0, policy_version 76253 (0.0008) -[2023-10-10 15:39:35,826][76542] Updated weights for policy 1, policy_version 76100 (0.0009) -[2023-10-10 15:39:36,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 156008448. Throughput: 0: 1820.4, 1: 1816.6. Samples: 39007768. Policy #0 lag: (min: 21.0, avg: 28.4, max: 53.0) -[2023-10-10 15:39:36,077][75634] Avg episode reward: [(0, '36.780'), (1, '35.470')] -[2023-10-10 15:39:36,206][76542] Updated weights for policy 1, policy_version 76110 (0.0010) -[2023-10-10 15:39:36,563][76542] Updated weights for policy 1, policy_version 76120 (0.0008) -[2023-10-10 15:39:37,455][76543] Updated weights for policy 0, policy_version 76263 (0.0007) -[2023-10-10 15:39:37,822][76543] Updated weights for policy 0, policy_version 76273 (0.0011) -[2023-10-10 15:39:38,189][76543] Updated weights for policy 0, policy_version 76283 (0.0010) -[2023-10-10 15:39:40,364][76542] Updated weights for policy 1, policy_version 76130 (0.0008) -[2023-10-10 15:39:40,766][76542] Updated weights for policy 1, policy_version 76140 (0.0009) -[2023-10-10 15:39:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 156073984. Throughput: 0: 1827.0, 1: 1819.4. Samples: 39029584. Policy #0 lag: (min: 21.0, avg: 28.4, max: 53.0) -[2023-10-10 15:39:41,077][75634] Avg episode reward: [(0, '38.790'), (1, '37.000')] -[2023-10-10 15:39:41,132][76542] Updated weights for policy 1, policy_version 76150 (0.0010) -[2023-10-10 15:39:41,494][76542] Updated weights for policy 1, policy_version 76160 (0.0010) -[2023-10-10 15:39:41,975][76543] Updated weights for policy 0, policy_version 76293 (0.0009) -[2023-10-10 15:39:42,337][76543] Updated weights for policy 0, policy_version 76303 (0.0008) -[2023-10-10 15:39:42,717][76543] Updated weights for policy 0, policy_version 76313 (0.0008) -[2023-10-10 15:39:45,355][76542] Updated weights for policy 1, policy_version 76170 (0.0009) -[2023-10-10 15:39:45,727][76542] Updated weights for policy 1, policy_version 76180 (0.0009) -[2023-10-10 15:39:46,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 156139520. Throughput: 0: 1822.2, 1: 1811.2. Samples: 39051234. Policy #0 lag: (min: 21.0, avg: 28.4, max: 53.0) -[2023-10-10 15:39:46,077][75634] Avg episode reward: [(0, '36.590'), (1, '38.600')] -[2023-10-10 15:39:46,088][76542] Updated weights for policy 1, policy_version 76190 (0.0008) -[2023-10-10 15:39:46,469][76543] Updated weights for policy 0, policy_version 76323 (0.0008) -[2023-10-10 15:39:46,843][76543] Updated weights for policy 0, policy_version 76333 (0.0007) -[2023-10-10 15:39:47,203][76543] Updated weights for policy 0, policy_version 76343 (0.0011) -[2023-10-10 15:39:49,898][76542] Updated weights for policy 1, policy_version 76200 (0.0007) -[2023-10-10 15:39:50,270][76542] Updated weights for policy 1, policy_version 76210 (0.0012) -[2023-10-10 15:39:50,633][76542] Updated weights for policy 1, policy_version 76220 (0.0010) -[2023-10-10 15:39:50,788][76543] Updated weights for policy 0, policy_version 76353 (0.0011) -[2023-10-10 15:39:51,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 156237824. Throughput: 0: 1820.7, 1: 1814.5. Samples: 39062040. Policy #0 lag: (min: 21.0, avg: 28.4, max: 53.0) -[2023-10-10 15:39:51,076][75634] Avg episode reward: [(0, '38.690'), (1, '39.270')] -[2023-10-10 15:39:51,153][76543] Updated weights for policy 0, policy_version 76363 (0.0011) -[2023-10-10 15:39:51,523][76543] Updated weights for policy 0, policy_version 76373 (0.0009) -[2023-10-10 15:39:51,894][76543] Updated weights for policy 0, policy_version 76383 (0.0007) -[2023-10-10 15:39:54,390][76542] Updated weights for policy 1, policy_version 76230 (0.0009) -[2023-10-10 15:39:54,766][76542] Updated weights for policy 1, policy_version 76240 (0.0009) -[2023-10-10 15:39:55,137][76542] Updated weights for policy 1, policy_version 76250 (0.0007) -[2023-10-10 15:39:55,688][76543] Updated weights for policy 0, policy_version 76393 (0.0008) -[2023-10-10 15:39:56,058][76543] Updated weights for policy 0, policy_version 76403 (0.0011) -[2023-10-10 15:39:56,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 156303360. Throughput: 0: 1816.2, 1: 1816.6. Samples: 39084282. Policy #0 lag: (min: 21.0, avg: 28.4, max: 53.0) -[2023-10-10 15:39:56,077][75634] Avg episode reward: [(0, '37.800'), (1, '36.780')] -[2023-10-10 15:39:56,430][76543] Updated weights for policy 0, policy_version 76413 (0.0009) -[2023-10-10 15:39:58,939][76542] Updated weights for policy 1, policy_version 76260 (0.0007) -[2023-10-10 15:39:59,309][76542] Updated weights for policy 1, policy_version 76270 (0.0008) -[2023-10-10 15:39:59,680][76542] Updated weights for policy 1, policy_version 76280 (0.0007) -[2023-10-10 15:40:00,191][76543] Updated weights for policy 0, policy_version 76423 (0.0008) -[2023-10-10 15:40:00,558][76543] Updated weights for policy 0, policy_version 76433 (0.0009) -[2023-10-10 15:40:00,932][76543] Updated weights for policy 0, policy_version 76443 (0.0008) -[2023-10-10 15:40:01,076][75634] Fps is (10 sec: 13106.6, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 156368896. Throughput: 0: 1815.9, 1: 1815.5. Samples: 39106042. Policy #0 lag: (min: 21.0, avg: 28.4, max: 53.0) -[2023-10-10 15:40:01,078][75634] Avg episode reward: [(0, '34.780'), (1, '36.050')] -[2023-10-10 15:40:03,219][76542] Updated weights for policy 1, policy_version 76290 (0.0007) -[2023-10-10 15:40:03,591][76542] Updated weights for policy 1, policy_version 76300 (0.0009) -[2023-10-10 15:40:03,952][76542] Updated weights for policy 1, policy_version 76310 (0.0009) -[2023-10-10 15:40:04,326][76542] Updated weights for policy 1, policy_version 76320 (0.0009) -[2023-10-10 15:40:04,554][76543] Updated weights for policy 0, policy_version 76453 (0.0009) -[2023-10-10 15:40:04,932][76543] Updated weights for policy 0, policy_version 76463 (0.0009) -[2023-10-10 15:40:05,295][76543] Updated weights for policy 0, policy_version 76473 (0.0009) -[2023-10-10 15:40:06,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 156467200. Throughput: 0: 1815.3, 1: 1821.4. Samples: 39117222. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 15:40:06,076][75634] Avg episode reward: [(0, '36.810'), (1, '34.970')] -[2023-10-10 15:40:08,016][76542] Updated weights for policy 1, policy_version 76330 (0.0007) -[2023-10-10 15:40:08,382][76542] Updated weights for policy 1, policy_version 76340 (0.0007) -[2023-10-10 15:40:08,747][76542] Updated weights for policy 1, policy_version 76350 (0.0007) -[2023-10-10 15:40:09,154][76543] Updated weights for policy 0, policy_version 76483 (0.0008) -[2023-10-10 15:40:09,527][76543] Updated weights for policy 0, policy_version 76493 (0.0009) -[2023-10-10 15:40:09,898][76543] Updated weights for policy 0, policy_version 76503 (0.0009) -[2023-10-10 15:40:11,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 156532736. Throughput: 0: 1826.9, 1: 1818.8. Samples: 39139176. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 15:40:11,077][75634] Avg episode reward: [(0, '35.300'), (1, '36.480')] -[2023-10-10 15:40:12,225][76542] Updated weights for policy 1, policy_version 76360 (0.0007) -[2023-10-10 15:40:12,594][76542] Updated weights for policy 1, policy_version 76370 (0.0007) -[2023-10-10 15:40:12,964][76542] Updated weights for policy 1, policy_version 76380 (0.0009) -[2023-10-10 15:40:13,456][76543] Updated weights for policy 0, policy_version 76513 (0.0008) -[2023-10-10 15:40:13,821][76543] Updated weights for policy 0, policy_version 76523 (0.0010) -[2023-10-10 15:40:14,182][76543] Updated weights for policy 0, policy_version 76533 (0.0009) -[2023-10-10 15:40:14,555][76543] Updated weights for policy 0, policy_version 76543 (0.0010) -[2023-10-10 15:40:16,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 156598272. Throughput: 0: 1818.6, 1: 1827.3. Samples: 39161204. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 15:40:16,076][75634] Avg episode reward: [(0, '36.650'), (1, '33.820')] -[2023-10-10 15:40:16,599][76542] Updated weights for policy 1, policy_version 76390 (0.0009) -[2023-10-10 15:40:16,958][76542] Updated weights for policy 1, policy_version 76400 (0.0010) -[2023-10-10 15:40:17,332][76542] Updated weights for policy 1, policy_version 76410 (0.0008) -[2023-10-10 15:40:18,200][76543] Updated weights for policy 0, policy_version 76553 (0.0008) -[2023-10-10 15:40:18,572][76543] Updated weights for policy 0, policy_version 76563 (0.0008) -[2023-10-10 15:40:18,947][76543] Updated weights for policy 0, policy_version 76573 (0.0008) -[2023-10-10 15:40:20,959][76542] Updated weights for policy 1, policy_version 76420 (0.0009) -[2023-10-10 15:40:21,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 156663808. Throughput: 0: 1823.8, 1: 1830.7. Samples: 39172220. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 15:40:21,077][75634] Avg episode reward: [(0, '33.680'), (1, '38.030')] -[2023-10-10 15:40:21,334][76542] Updated weights for policy 1, policy_version 76430 (0.0009) -[2023-10-10 15:40:21,697][76542] Updated weights for policy 1, policy_version 76440 (0.0008) -[2023-10-10 15:40:22,623][76543] Updated weights for policy 0, policy_version 76583 (0.0008) -[2023-10-10 15:40:22,987][76543] Updated weights for policy 0, policy_version 76593 (0.0010) -[2023-10-10 15:40:23,351][76543] Updated weights for policy 0, policy_version 76603 (0.0011) -[2023-10-10 15:40:25,326][76542] Updated weights for policy 1, policy_version 76450 (0.0008) -[2023-10-10 15:40:25,724][76542] Updated weights for policy 1, policy_version 76460 (0.0008) -[2023-10-10 15:40:26,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 156729344. Throughput: 0: 1822.8, 1: 1831.2. Samples: 39194014. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 15:40:26,076][75634] Avg episode reward: [(0, '34.820'), (1, '35.760')] -[2023-10-10 15:40:26,095][76542] Updated weights for policy 1, policy_version 76470 (0.0009) -[2023-10-10 15:40:26,469][76542] Updated weights for policy 1, policy_version 76480 (0.0008) -[2023-10-10 15:40:26,888][76543] Updated weights for policy 0, policy_version 76613 (0.0010) -[2023-10-10 15:40:27,259][76543] Updated weights for policy 0, policy_version 76623 (0.0011) -[2023-10-10 15:40:27,629][76543] Updated weights for policy 0, policy_version 76633 (0.0010) -[2023-10-10 15:40:30,034][76542] Updated weights for policy 1, policy_version 76490 (0.0009) -[2023-10-10 15:40:30,406][76542] Updated weights for policy 1, policy_version 76500 (0.0007) -[2023-10-10 15:40:30,770][76542] Updated weights for policy 1, policy_version 76510 (0.0008) -[2023-10-10 15:40:31,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 156827648. Throughput: 0: 1823.9, 1: 1832.5. Samples: 39215772. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 15:40:31,077][75634] Avg episode reward: [(0, '34.740'), (1, '34.230')] -[2023-10-10 15:40:31,086][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000076640_78479360.pth... -[2023-10-10 15:40:31,087][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000076512_78348288.pth... -[2023-10-10 15:40:31,122][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000074784_76578816.pth -[2023-10-10 15:40:31,124][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000074944_76742656.pth -[2023-10-10 15:40:31,126][76421] Saving a milestone ./train_atari/atari_defender_APPO/checkpoint_p1/milestones/checkpoint_000076512_78348288.pth -[2023-10-10 15:40:31,128][76362] Saving a milestone ./train_atari/atari_defender_APPO/checkpoint_p0/milestones/checkpoint_000076640_78479360.pth -[2023-10-10 15:40:31,468][76543] Updated weights for policy 0, policy_version 76643 (0.0010) -[2023-10-10 15:40:31,845][76543] Updated weights for policy 0, policy_version 76653 (0.0008) -[2023-10-10 15:40:32,220][76543] Updated weights for policy 0, policy_version 76663 (0.0007) -[2023-10-10 15:40:34,453][76542] Updated weights for policy 1, policy_version 76520 (0.0009) -[2023-10-10 15:40:34,812][76542] Updated weights for policy 1, policy_version 76530 (0.0007) -[2023-10-10 15:40:35,190][76542] Updated weights for policy 1, policy_version 76540 (0.0008) -[2023-10-10 15:40:35,816][76543] Updated weights for policy 0, policy_version 76673 (0.0010) -[2023-10-10 15:40:36,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 156893184. Throughput: 0: 1822.8, 1: 1844.4. Samples: 39227066. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 15:40:36,076][75634] Avg episode reward: [(0, '33.660'), (1, '34.340')] -[2023-10-10 15:40:36,191][76543] Updated weights for policy 0, policy_version 76683 (0.0010) -[2023-10-10 15:40:36,555][76543] Updated weights for policy 0, policy_version 76693 (0.0011) -[2023-10-10 15:40:36,936][76543] Updated weights for policy 0, policy_version 76703 (0.0009) -[2023-10-10 15:40:38,792][76542] Updated weights for policy 1, policy_version 76550 (0.0009) -[2023-10-10 15:40:39,160][76542] Updated weights for policy 1, policy_version 76560 (0.0008) -[2023-10-10 15:40:39,518][76542] Updated weights for policy 1, policy_version 76570 (0.0007) -[2023-10-10 15:40:40,622][76543] Updated weights for policy 0, policy_version 76713 (0.0008) -[2023-10-10 15:40:40,988][76543] Updated weights for policy 0, policy_version 76723 (0.0008) -[2023-10-10 15:40:41,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 156958720. Throughput: 0: 1821.6, 1: 1830.6. Samples: 39248632. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 15:40:41,077][75634] Avg episode reward: [(0, '36.470'), (1, '33.200')] -[2023-10-10 15:40:41,371][76543] Updated weights for policy 0, policy_version 76733 (0.0009) -[2023-10-10 15:40:43,334][76542] Updated weights for policy 1, policy_version 76580 (0.0010) -[2023-10-10 15:40:43,695][76542] Updated weights for policy 1, policy_version 76590 (0.0008) -[2023-10-10 15:40:44,059][76542] Updated weights for policy 1, policy_version 76600 (0.0007) -[2023-10-10 15:40:45,052][76543] Updated weights for policy 0, policy_version 76743 (0.0008) -[2023-10-10 15:40:45,426][76543] Updated weights for policy 0, policy_version 76753 (0.0007) -[2023-10-10 15:40:45,798][76543] Updated weights for policy 0, policy_version 76763 (0.0009) -[2023-10-10 15:40:46,076][75634] Fps is (10 sec: 16383.6, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 157057024. Throughput: 0: 1819.4, 1: 1839.0. Samples: 39270670. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-10 15:40:46,077][75634] Avg episode reward: [(0, '34.310'), (1, '38.940')] -[2023-10-10 15:40:47,798][76542] Updated weights for policy 1, policy_version 76610 (0.0010) -[2023-10-10 15:40:48,166][76542] Updated weights for policy 1, policy_version 76620 (0.0008) -[2023-10-10 15:40:48,531][76542] Updated weights for policy 1, policy_version 76630 (0.0007) -[2023-10-10 15:40:48,906][76542] Updated weights for policy 1, policy_version 76640 (0.0007) -[2023-10-10 15:40:49,395][76543] Updated weights for policy 0, policy_version 76773 (0.0009) -[2023-10-10 15:40:49,763][76543] Updated weights for policy 0, policy_version 76783 (0.0011) -[2023-10-10 15:40:50,126][76543] Updated weights for policy 0, policy_version 76793 (0.0010) -[2023-10-10 15:40:51,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 157122560. Throughput: 0: 1824.9, 1: 1826.6. Samples: 39281538. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-10 15:40:51,076][75634] Avg episode reward: [(0, '33.540'), (1, '38.200')] -[2023-10-10 15:40:52,616][76542] Updated weights for policy 1, policy_version 76650 (0.0008) -[2023-10-10 15:40:52,977][76542] Updated weights for policy 1, policy_version 76660 (0.0010) -[2023-10-10 15:40:53,344][76542] Updated weights for policy 1, policy_version 76670 (0.0008) -[2023-10-10 15:40:53,860][76543] Updated weights for policy 0, policy_version 76803 (0.0009) -[2023-10-10 15:40:54,227][76543] Updated weights for policy 0, policy_version 76813 (0.0007) -[2023-10-10 15:40:54,595][76543] Updated weights for policy 0, policy_version 76823 (0.0011) -[2023-10-10 15:40:56,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 157188096. Throughput: 0: 1819.2, 1: 1830.9. Samples: 39303430. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-10 15:40:56,077][75634] Avg episode reward: [(0, '36.550'), (1, '35.550')] -[2023-10-10 15:40:56,997][76542] Updated weights for policy 1, policy_version 76680 (0.0008) -[2023-10-10 15:40:57,372][76542] Updated weights for policy 1, policy_version 76690 (0.0008) -[2023-10-10 15:40:57,731][76542] Updated weights for policy 1, policy_version 76700 (0.0008) -[2023-10-10 15:40:58,438][76543] Updated weights for policy 0, policy_version 76833 (0.0011) -[2023-10-10 15:40:58,818][76543] Updated weights for policy 0, policy_version 76843 (0.0007) -[2023-10-10 15:40:59,184][76543] Updated weights for policy 0, policy_version 76853 (0.0008) -[2023-10-10 15:40:59,556][76543] Updated weights for policy 0, policy_version 76863 (0.0008) -[2023-10-10 15:41:01,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 157253632. Throughput: 0: 1817.0, 1: 1827.5. Samples: 39325208. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-10 15:41:01,077][75634] Avg episode reward: [(0, '36.400'), (1, '43.730')] -[2023-10-10 15:41:01,380][76542] Updated weights for policy 1, policy_version 76710 (0.0009) -[2023-10-10 15:41:01,754][76542] Updated weights for policy 1, policy_version 76720 (0.0009) -[2023-10-10 15:41:02,116][76542] Updated weights for policy 1, policy_version 76730 (0.0008) -[2023-10-10 15:41:02,332][76421] Saving new best policy, reward=43.730! -[2023-10-10 15:41:03,295][76543] Updated weights for policy 0, policy_version 76873 (0.0008) -[2023-10-10 15:41:03,663][76543] Updated weights for policy 0, policy_version 76883 (0.0008) -[2023-10-10 15:41:04,029][76543] Updated weights for policy 0, policy_version 76893 (0.0007) -[2023-10-10 15:41:05,967][76542] Updated weights for policy 1, policy_version 76740 (0.0008) -[2023-10-10 15:41:06,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 157319168. Throughput: 0: 1821.7, 1: 1824.9. Samples: 39336316. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-10 15:41:06,076][75634] Avg episode reward: [(0, '33.590'), (1, '42.120')] -[2023-10-10 15:41:06,334][76542] Updated weights for policy 1, policy_version 76750 (0.0008) -[2023-10-10 15:41:06,705][76542] Updated weights for policy 1, policy_version 76760 (0.0008) -[2023-10-10 15:41:07,762][76543] Updated weights for policy 0, policy_version 76903 (0.0010) -[2023-10-10 15:41:08,128][76543] Updated weights for policy 0, policy_version 76913 (0.0008) -[2023-10-10 15:41:08,499][76543] Updated weights for policy 0, policy_version 76923 (0.0010) -[2023-10-10 15:41:10,396][76542] Updated weights for policy 1, policy_version 76770 (0.0010) -[2023-10-10 15:41:10,788][76542] Updated weights for policy 1, policy_version 76780 (0.0009) -[2023-10-10 15:41:11,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 157384704. Throughput: 0: 1817.2, 1: 1827.4. Samples: 39358022. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-10 15:41:11,077][75634] Avg episode reward: [(0, '37.360'), (1, '29.890')] -[2023-10-10 15:41:11,146][76542] Updated weights for policy 1, policy_version 76790 (0.0008) -[2023-10-10 15:41:11,513][76542] Updated weights for policy 1, policy_version 76800 (0.0007) -[2023-10-10 15:41:12,108][76543] Updated weights for policy 0, policy_version 76933 (0.0009) -[2023-10-10 15:41:12,478][76543] Updated weights for policy 0, policy_version 76943 (0.0008) -[2023-10-10 15:41:12,844][76543] Updated weights for policy 0, policy_version 76953 (0.0008) -[2023-10-10 15:41:15,176][76542] Updated weights for policy 1, policy_version 76810 (0.0008) -[2023-10-10 15:41:15,541][76542] Updated weights for policy 1, policy_version 76820 (0.0007) -[2023-10-10 15:41:15,911][76542] Updated weights for policy 1, policy_version 76830 (0.0007) -[2023-10-10 15:41:16,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 157483008. Throughput: 0: 1815.7, 1: 1825.7. Samples: 39379632. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-10 15:41:16,076][75634] Avg episode reward: [(0, '38.760'), (1, '30.720')] -[2023-10-10 15:41:16,553][76543] Updated weights for policy 0, policy_version 76963 (0.0008) -[2023-10-10 15:41:16,928][76543] Updated weights for policy 0, policy_version 76973 (0.0008) -[2023-10-10 15:41:17,311][76543] Updated weights for policy 0, policy_version 76983 (0.0007) -[2023-10-10 15:41:19,596][76542] Updated weights for policy 1, policy_version 76840 (0.0008) -[2023-10-10 15:41:19,962][76542] Updated weights for policy 1, policy_version 76850 (0.0008) -[2023-10-10 15:41:20,340][76542] Updated weights for policy 1, policy_version 76860 (0.0008) -[2023-10-10 15:41:20,852][76543] Updated weights for policy 0, policy_version 76993 (0.0008) -[2023-10-10 15:41:21,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 157548544. Throughput: 0: 1819.3, 1: 1817.4. Samples: 39390718. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-10 15:41:21,077][75634] Avg episode reward: [(0, '42.370'), (1, '31.240')] -[2023-10-10 15:41:21,221][76543] Updated weights for policy 0, policy_version 77003 (0.0008) -[2023-10-10 15:41:21,601][76543] Updated weights for policy 0, policy_version 77013 (0.0008) -[2023-10-10 15:41:21,970][76543] Updated weights for policy 0, policy_version 77023 (0.0009) -[2023-10-10 15:41:24,044][76542] Updated weights for policy 1, policy_version 76870 (0.0008) -[2023-10-10 15:41:24,409][76542] Updated weights for policy 1, policy_version 76880 (0.0009) -[2023-10-10 15:41:24,781][76542] Updated weights for policy 1, policy_version 76890 (0.0010) -[2023-10-10 15:41:25,620][76543] Updated weights for policy 0, policy_version 77033 (0.0010) -[2023-10-10 15:41:25,987][76543] Updated weights for policy 0, policy_version 77043 (0.0010) -[2023-10-10 15:41:26,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 157614080. Throughput: 0: 1819.6, 1: 1824.0. Samples: 39412598. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-10 15:41:26,077][75634] Avg episode reward: [(0, '39.830'), (1, '25.450')] -[2023-10-10 15:41:26,348][76543] Updated weights for policy 0, policy_version 77053 (0.0010) -[2023-10-10 15:41:28,412][76542] Updated weights for policy 1, policy_version 76900 (0.0009) -[2023-10-10 15:41:28,774][76542] Updated weights for policy 1, policy_version 76910 (0.0009) -[2023-10-10 15:41:29,147][76542] Updated weights for policy 1, policy_version 76920 (0.0009) -[2023-10-10 15:41:30,225][76543] Updated weights for policy 0, policy_version 77063 (0.0009) -[2023-10-10 15:41:30,614][76543] Updated weights for policy 0, policy_version 77073 (0.0009) -[2023-10-10 15:41:30,979][76543] Updated weights for policy 0, policy_version 77083 (0.0009) -[2023-10-10 15:41:31,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 157679616. Throughput: 0: 1823.8, 1: 1823.2. Samples: 39434786. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-10 15:41:31,076][75634] Avg episode reward: [(0, '39.610'), (1, '27.720')] -[2023-10-10 15:41:32,802][76542] Updated weights for policy 1, policy_version 76930 (0.0011) -[2023-10-10 15:41:33,159][76542] Updated weights for policy 1, policy_version 76940 (0.0007) -[2023-10-10 15:41:33,536][76542] Updated weights for policy 1, policy_version 76950 (0.0009) -[2023-10-10 15:41:33,900][76542] Updated weights for policy 1, policy_version 76960 (0.0010) -[2023-10-10 15:41:34,474][76543] Updated weights for policy 0, policy_version 77093 (0.0007) -[2023-10-10 15:41:34,838][76543] Updated weights for policy 0, policy_version 77103 (0.0007) -[2023-10-10 15:41:35,215][76543] Updated weights for policy 0, policy_version 77113 (0.0007) -[2023-10-10 15:41:36,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 157777920. Throughput: 0: 1818.3, 1: 1821.9. Samples: 39445350. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-10 15:41:36,077][75634] Avg episode reward: [(0, '39.000'), (1, '31.250')] -[2023-10-10 15:41:37,699][76542] Updated weights for policy 1, policy_version 76970 (0.0009) -[2023-10-10 15:41:38,062][76542] Updated weights for policy 1, policy_version 76980 (0.0009) -[2023-10-10 15:41:38,433][76542] Updated weights for policy 1, policy_version 76990 (0.0007) -[2023-10-10 15:41:38,840][76543] Updated weights for policy 0, policy_version 77123 (0.0008) -[2023-10-10 15:41:39,201][76543] Updated weights for policy 0, policy_version 77133 (0.0007) -[2023-10-10 15:41:39,573][76543] Updated weights for policy 0, policy_version 77143 (0.0007) -[2023-10-10 15:41:41,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 157843456. Throughput: 0: 1814.8, 1: 1824.1. Samples: 39467182. Policy #0 lag: (min: 10.0, avg: 10.9, max: 28.0) -[2023-10-10 15:41:41,076][75634] Avg episode reward: [(0, '33.490'), (1, '31.440')] -[2023-10-10 15:41:41,990][76542] Updated weights for policy 1, policy_version 77000 (0.0009) -[2023-10-10 15:41:42,359][76542] Updated weights for policy 1, policy_version 77010 (0.0009) -[2023-10-10 15:41:42,730][76542] Updated weights for policy 1, policy_version 77020 (0.0008) -[2023-10-10 15:41:43,183][76543] Updated weights for policy 0, policy_version 77153 (0.0010) -[2023-10-10 15:41:43,558][76543] Updated weights for policy 0, policy_version 77163 (0.0010) -[2023-10-10 15:41:43,940][76543] Updated weights for policy 0, policy_version 77173 (0.0009) -[2023-10-10 15:41:44,314][76543] Updated weights for policy 0, policy_version 77183 (0.0010) -[2023-10-10 15:41:46,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 157908992. Throughput: 0: 1825.7, 1: 1821.7. Samples: 39489344. Policy #0 lag: (min: 10.0, avg: 10.9, max: 28.0) -[2023-10-10 15:41:46,076][75634] Avg episode reward: [(0, '36.370'), (1, '36.800')] -[2023-10-10 15:41:46,371][76542] Updated weights for policy 1, policy_version 77030 (0.0009) -[2023-10-10 15:41:46,747][76542] Updated weights for policy 1, policy_version 77040 (0.0008) -[2023-10-10 15:41:47,106][76542] Updated weights for policy 1, policy_version 77050 (0.0007) -[2023-10-10 15:41:47,965][76543] Updated weights for policy 0, policy_version 77193 (0.0009) -[2023-10-10 15:41:48,339][76543] Updated weights for policy 0, policy_version 77203 (0.0008) -[2023-10-10 15:41:48,697][76543] Updated weights for policy 0, policy_version 77213 (0.0008) -[2023-10-10 15:41:50,828][76542] Updated weights for policy 1, policy_version 77060 (0.0009) -[2023-10-10 15:41:51,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 157974528. Throughput: 0: 1816.8, 1: 1824.7. Samples: 39500184. Policy #0 lag: (min: 10.0, avg: 10.9, max: 28.0) -[2023-10-10 15:41:51,077][75634] Avg episode reward: [(0, '37.820'), (1, '31.830')] -[2023-10-10 15:41:51,191][76542] Updated weights for policy 1, policy_version 77070 (0.0010) -[2023-10-10 15:41:51,555][76542] Updated weights for policy 1, policy_version 77080 (0.0008) -[2023-10-10 15:41:52,312][76543] Updated weights for policy 0, policy_version 77223 (0.0008) -[2023-10-10 15:41:52,672][76543] Updated weights for policy 0, policy_version 77233 (0.0008) -[2023-10-10 15:41:53,034][76543] Updated weights for policy 0, policy_version 77243 (0.0008) -[2023-10-10 15:41:55,374][76542] Updated weights for policy 1, policy_version 77090 (0.0007) -[2023-10-10 15:41:55,777][76542] Updated weights for policy 1, policy_version 77100 (0.0007) -[2023-10-10 15:41:56,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 158040064. Throughput: 0: 1832.2, 1: 1821.3. Samples: 39522428. Policy #0 lag: (min: 10.0, avg: 10.9, max: 28.0) -[2023-10-10 15:41:56,076][75634] Avg episode reward: [(0, '37.610'), (1, '33.610')] -[2023-10-10 15:41:56,138][76542] Updated weights for policy 1, policy_version 77110 (0.0007) -[2023-10-10 15:41:56,510][76542] Updated weights for policy 1, policy_version 77120 (0.0009) -[2023-10-10 15:41:56,805][76543] Updated weights for policy 0, policy_version 77253 (0.0010) -[2023-10-10 15:41:57,168][76543] Updated weights for policy 0, policy_version 77263 (0.0007) -[2023-10-10 15:41:57,543][76543] Updated weights for policy 0, policy_version 77273 (0.0008) -[2023-10-10 15:42:00,214][76542] Updated weights for policy 1, policy_version 77130 (0.0007) -[2023-10-10 15:42:00,577][76542] Updated weights for policy 1, policy_version 77140 (0.0012) -[2023-10-10 15:42:00,937][76542] Updated weights for policy 1, policy_version 77150 (0.0010) -[2023-10-10 15:42:01,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 158138368. Throughput: 0: 1830.6, 1: 1821.2. Samples: 39543960. Policy #0 lag: (min: 10.0, avg: 10.9, max: 28.0) -[2023-10-10 15:42:01,076][75634] Avg episode reward: [(0, '40.940'), (1, '31.720')] -[2023-10-10 15:42:01,158][76543] Updated weights for policy 0, policy_version 77283 (0.0009) -[2023-10-10 15:42:01,534][76543] Updated weights for policy 0, policy_version 77293 (0.0008) -[2023-10-10 15:42:01,899][76543] Updated weights for policy 0, policy_version 77303 (0.0007) -[2023-10-10 15:42:04,504][76542] Updated weights for policy 1, policy_version 77160 (0.0010) -[2023-10-10 15:42:04,872][76542] Updated weights for policy 1, policy_version 77170 (0.0009) -[2023-10-10 15:42:05,245][76542] Updated weights for policy 1, policy_version 77180 (0.0008) -[2023-10-10 15:42:05,555][76543] Updated weights for policy 0, policy_version 77313 (0.0008) -[2023-10-10 15:42:05,926][76543] Updated weights for policy 0, policy_version 77323 (0.0008) -[2023-10-10 15:42:06,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 158203904. Throughput: 0: 1833.9, 1: 1824.4. Samples: 39555338. Policy #0 lag: (min: 10.0, avg: 10.9, max: 28.0) -[2023-10-10 15:42:06,077][75634] Avg episode reward: [(0, '38.260'), (1, '33.370')] -[2023-10-10 15:42:06,302][76543] Updated weights for policy 0, policy_version 77333 (0.0010) -[2023-10-10 15:42:06,673][76543] Updated weights for policy 0, policy_version 77343 (0.0008) -[2023-10-10 15:42:08,942][76542] Updated weights for policy 1, policy_version 77190 (0.0009) -[2023-10-10 15:42:09,315][76542] Updated weights for policy 1, policy_version 77200 (0.0009) -[2023-10-10 15:42:09,673][76542] Updated weights for policy 1, policy_version 77210 (0.0009) -[2023-10-10 15:42:10,554][76543] Updated weights for policy 0, policy_version 77353 (0.0007) -[2023-10-10 15:42:10,923][76543] Updated weights for policy 0, policy_version 77363 (0.0009) -[2023-10-10 15:42:11,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 158269440. Throughput: 0: 1828.9, 1: 1821.4. Samples: 39576860. Policy #0 lag: (min: 10.0, avg: 10.9, max: 28.0) -[2023-10-10 15:42:11,076][75634] Avg episode reward: [(0, '41.430'), (1, '35.710')] -[2023-10-10 15:42:11,295][76543] Updated weights for policy 0, policy_version 77373 (0.0008) -[2023-10-10 15:42:13,332][76542] Updated weights for policy 1, policy_version 77220 (0.0009) -[2023-10-10 15:42:13,704][76542] Updated weights for policy 1, policy_version 77230 (0.0010) -[2023-10-10 15:42:14,062][76542] Updated weights for policy 1, policy_version 77240 (0.0010) -[2023-10-10 15:42:15,078][76543] Updated weights for policy 0, policy_version 77383 (0.0007) -[2023-10-10 15:42:15,457][76543] Updated weights for policy 0, policy_version 77393 (0.0008) -[2023-10-10 15:42:15,828][76543] Updated weights for policy 0, policy_version 77403 (0.0008) -[2023-10-10 15:42:16,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 158367744. Throughput: 0: 1825.6, 1: 1819.2. Samples: 39598800. Policy #0 lag: (min: 10.0, avg: 10.9, max: 28.0) -[2023-10-10 15:42:16,076][75634] Avg episode reward: [(0, '34.760'), (1, '38.730')] -[2023-10-10 15:42:17,725][76542] Updated weights for policy 1, policy_version 77250 (0.0010) -[2023-10-10 15:42:18,095][76542] Updated weights for policy 1, policy_version 77260 (0.0008) -[2023-10-10 15:42:18,455][76542] Updated weights for policy 1, policy_version 77270 (0.0007) -[2023-10-10 15:42:18,822][76542] Updated weights for policy 1, policy_version 77280 (0.0007) -[2023-10-10 15:42:19,361][76543] Updated weights for policy 0, policy_version 77413 (0.0009) -[2023-10-10 15:42:19,738][76543] Updated weights for policy 0, policy_version 77423 (0.0009) -[2023-10-10 15:42:20,110][76543] Updated weights for policy 0, policy_version 77433 (0.0007) -[2023-10-10 15:42:21,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 158433280. Throughput: 0: 1830.6, 1: 1814.9. Samples: 39609396. Policy #0 lag: (min: 10.0, avg: 10.9, max: 28.0) -[2023-10-10 15:42:21,076][75634] Avg episode reward: [(0, '36.510'), (1, '39.650')] -[2023-10-10 15:42:22,493][76542] Updated weights for policy 1, policy_version 77290 (0.0009) -[2023-10-10 15:42:22,856][76542] Updated weights for policy 1, policy_version 77300 (0.0008) -[2023-10-10 15:42:23,221][76542] Updated weights for policy 1, policy_version 77310 (0.0008) -[2023-10-10 15:42:23,725][76543] Updated weights for policy 0, policy_version 77443 (0.0009) -[2023-10-10 15:42:24,093][76543] Updated weights for policy 0, policy_version 77453 (0.0010) -[2023-10-10 15:42:24,470][76543] Updated weights for policy 0, policy_version 77463 (0.0009) -[2023-10-10 15:42:26,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 158498816. Throughput: 0: 1833.9, 1: 1821.5. Samples: 39631672. Policy #0 lag: (min: 10.0, avg: 10.9, max: 28.0) -[2023-10-10 15:42:26,077][75634] Avg episode reward: [(0, '38.490'), (1, '37.140')] -[2023-10-10 15:42:26,907][76542] Updated weights for policy 1, policy_version 77320 (0.0010) -[2023-10-10 15:42:27,280][76542] Updated weights for policy 1, policy_version 77330 (0.0010) -[2023-10-10 15:42:27,652][76542] Updated weights for policy 1, policy_version 77340 (0.0009) -[2023-10-10 15:42:28,141][76543] Updated weights for policy 0, policy_version 77473 (0.0008) -[2023-10-10 15:42:28,510][76543] Updated weights for policy 0, policy_version 77483 (0.0010) -[2023-10-10 15:42:28,883][76543] Updated weights for policy 0, policy_version 77493 (0.0010) -[2023-10-10 15:42:29,257][76543] Updated weights for policy 0, policy_version 77503 (0.0010) -[2023-10-10 15:42:31,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 158564352. Throughput: 0: 1833.2, 1: 1820.2. Samples: 39653744. Policy #0 lag: (min: 16.0, avg: 38.4, max: 48.0) -[2023-10-10 15:42:31,076][75634] Avg episode reward: [(0, '38.710'), (1, '38.830')] -[2023-10-10 15:42:31,085][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000077504_79364096.pth... -[2023-10-10 15:42:31,119][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000075808_77627392.pth -[2023-10-10 15:42:31,292][76542] Updated weights for policy 1, policy_version 77350 (0.0010) -[2023-10-10 15:42:31,670][76542] Updated weights for policy 1, policy_version 77360 (0.0009) -[2023-10-10 15:42:32,037][76542] Updated weights for policy 1, policy_version 77370 (0.0009) -[2023-10-10 15:42:32,263][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000077376_79233024.pth... -[2023-10-10 15:42:32,293][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000075648_77463552.pth -[2023-10-10 15:42:32,904][76543] Updated weights for policy 0, policy_version 77513 (0.0007) -[2023-10-10 15:42:33,274][76543] Updated weights for policy 0, policy_version 77523 (0.0008) -[2023-10-10 15:42:33,650][76543] Updated weights for policy 0, policy_version 77533 (0.0007) -[2023-10-10 15:42:35,738][76542] Updated weights for policy 1, policy_version 77380 (0.0007) -[2023-10-10 15:42:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 158629888. Throughput: 0: 1830.6, 1: 1818.5. Samples: 39664394. Policy #0 lag: (min: 16.0, avg: 38.4, max: 48.0) -[2023-10-10 15:42:36,077][75634] Avg episode reward: [(0, '39.660'), (1, '35.280')] -[2023-10-10 15:42:36,118][76542] Updated weights for policy 1, policy_version 77390 (0.0009) -[2023-10-10 15:42:36,480][76542] Updated weights for policy 1, policy_version 77400 (0.0011) -[2023-10-10 15:42:37,203][76543] Updated weights for policy 0, policy_version 77543 (0.0009) -[2023-10-10 15:42:37,574][76543] Updated weights for policy 0, policy_version 77553 (0.0010) -[2023-10-10 15:42:37,940][76543] Updated weights for policy 0, policy_version 77563 (0.0010) -[2023-10-10 15:42:40,189][76542] Updated weights for policy 1, policy_version 77410 (0.0009) -[2023-10-10 15:42:40,607][76542] Updated weights for policy 1, policy_version 77420 (0.0008) -[2023-10-10 15:42:40,971][76542] Updated weights for policy 1, policy_version 77430 (0.0007) -[2023-10-10 15:42:41,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 158695424. Throughput: 0: 1829.9, 1: 1821.5. Samples: 39686738. Policy #0 lag: (min: 16.0, avg: 38.4, max: 48.0) -[2023-10-10 15:42:41,077][75634] Avg episode reward: [(0, '37.850'), (1, '31.410')] -[2023-10-10 15:42:41,342][76542] Updated weights for policy 1, policy_version 77440 (0.0007) -[2023-10-10 15:42:41,793][76543] Updated weights for policy 0, policy_version 77573 (0.0009) -[2023-10-10 15:42:42,166][76543] Updated weights for policy 0, policy_version 77583 (0.0010) -[2023-10-10 15:42:42,545][76543] Updated weights for policy 0, policy_version 77593 (0.0009) -[2023-10-10 15:42:44,999][76542] Updated weights for policy 1, policy_version 77450 (0.0009) -[2023-10-10 15:42:45,360][76542] Updated weights for policy 1, policy_version 77460 (0.0008) -[2023-10-10 15:42:45,724][76542] Updated weights for policy 1, policy_version 77470 (0.0009) -[2023-10-10 15:42:46,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 158793728. Throughput: 0: 1825.0, 1: 1818.9. Samples: 39707936. Policy #0 lag: (min: 16.0, avg: 38.4, max: 48.0) -[2023-10-10 15:42:46,077][75634] Avg episode reward: [(0, '33.220'), (1, '31.170')] -[2023-10-10 15:42:46,180][76543] Updated weights for policy 0, policy_version 77603 (0.0008) -[2023-10-10 15:42:46,547][76543] Updated weights for policy 0, policy_version 77613 (0.0007) -[2023-10-10 15:42:46,916][76543] Updated weights for policy 0, policy_version 77623 (0.0008) -[2023-10-10 15:42:49,389][76542] Updated weights for policy 1, policy_version 77480 (0.0009) -[2023-10-10 15:42:49,752][76542] Updated weights for policy 1, policy_version 77490 (0.0008) -[2023-10-10 15:42:50,115][76542] Updated weights for policy 1, policy_version 77500 (0.0007) -[2023-10-10 15:42:50,481][76543] Updated weights for policy 0, policy_version 77633 (0.0011) -[2023-10-10 15:42:50,846][76543] Updated weights for policy 0, policy_version 77643 (0.0007) -[2023-10-10 15:42:51,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 158859264. Throughput: 0: 1818.1, 1: 1824.3. Samples: 39719246. Policy #0 lag: (min: 16.0, avg: 38.4, max: 48.0) -[2023-10-10 15:42:51,076][75634] Avg episode reward: [(0, '32.650'), (1, '31.840')] -[2023-10-10 15:42:51,223][76543] Updated weights for policy 0, policy_version 77653 (0.0011) -[2023-10-10 15:42:51,603][76543] Updated weights for policy 0, policy_version 77663 (0.0009) -[2023-10-10 15:42:53,710][76542] Updated weights for policy 1, policy_version 77510 (0.0008) -[2023-10-10 15:42:54,079][76542] Updated weights for policy 1, policy_version 77520 (0.0008) -[2023-10-10 15:42:54,457][76542] Updated weights for policy 1, policy_version 77530 (0.0009) -[2023-10-10 15:42:55,267][76543] Updated weights for policy 0, policy_version 77673 (0.0009) -[2023-10-10 15:42:55,639][76543] Updated weights for policy 0, policy_version 77683 (0.0008) -[2023-10-10 15:42:56,009][76543] Updated weights for policy 0, policy_version 77693 (0.0009) -[2023-10-10 15:42:56,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 158924800. Throughput: 0: 1825.8, 1: 1818.1. Samples: 39740836. Policy #0 lag: (min: 16.0, avg: 38.4, max: 48.0) -[2023-10-10 15:42:56,077][75634] Avg episode reward: [(0, '33.840'), (1, '34.870')] -[2023-10-10 15:42:58,088][76542] Updated weights for policy 1, policy_version 77540 (0.0009) -[2023-10-10 15:42:58,468][76542] Updated weights for policy 1, policy_version 77550 (0.0007) -[2023-10-10 15:42:58,830][76542] Updated weights for policy 1, policy_version 77560 (0.0008) -[2023-10-10 15:42:59,660][76543] Updated weights for policy 0, policy_version 77703 (0.0008) -[2023-10-10 15:43:00,030][76543] Updated weights for policy 0, policy_version 77713 (0.0010) -[2023-10-10 15:43:00,401][76543] Updated weights for policy 0, policy_version 77723 (0.0007) -[2023-10-10 15:43:01,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 159023104. Throughput: 0: 1819.9, 1: 1825.5. Samples: 39762842. Policy #0 lag: (min: 16.0, avg: 38.4, max: 48.0) -[2023-10-10 15:43:01,077][75634] Avg episode reward: [(0, '33.800'), (1, '32.760')] -[2023-10-10 15:43:02,553][76542] Updated weights for policy 1, policy_version 77570 (0.0008) -[2023-10-10 15:43:02,924][76542] Updated weights for policy 1, policy_version 77580 (0.0007) -[2023-10-10 15:43:03,287][76542] Updated weights for policy 1, policy_version 77590 (0.0009) -[2023-10-10 15:43:03,644][76542] Updated weights for policy 1, policy_version 77600 (0.0007) -[2023-10-10 15:43:04,038][76543] Updated weights for policy 0, policy_version 77733 (0.0008) -[2023-10-10 15:43:04,412][76543] Updated weights for policy 0, policy_version 77743 (0.0008) -[2023-10-10 15:43:04,777][76543] Updated weights for policy 0, policy_version 77753 (0.0010) -[2023-10-10 15:43:06,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 159088640. Throughput: 0: 1834.1, 1: 1823.9. Samples: 39774008. Policy #0 lag: (min: 16.0, avg: 38.4, max: 48.0) -[2023-10-10 15:43:06,077][75634] Avg episode reward: [(0, '33.260'), (1, '36.180')] -[2023-10-10 15:43:07,419][76542] Updated weights for policy 1, policy_version 77610 (0.0010) -[2023-10-10 15:43:07,782][76542] Updated weights for policy 1, policy_version 77620 (0.0010) -[2023-10-10 15:43:08,155][76542] Updated weights for policy 1, policy_version 77630 (0.0007) -[2023-10-10 15:43:08,453][76543] Updated weights for policy 0, policy_version 77763 (0.0008) -[2023-10-10 15:43:08,826][76543] Updated weights for policy 0, policy_version 77773 (0.0009) -[2023-10-10 15:43:09,191][76543] Updated weights for policy 0, policy_version 77783 (0.0008) -[2023-10-10 15:43:11,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 159154176. Throughput: 0: 1820.4, 1: 1830.2. Samples: 39795948. Policy #0 lag: (min: 16.0, avg: 38.4, max: 48.0) -[2023-10-10 15:43:11,076][75634] Avg episode reward: [(0, '35.820'), (1, '35.350')] -[2023-10-10 15:43:11,694][76542] Updated weights for policy 1, policy_version 77640 (0.0009) -[2023-10-10 15:43:12,071][76542] Updated weights for policy 1, policy_version 77650 (0.0011) -[2023-10-10 15:43:12,441][76542] Updated weights for policy 1, policy_version 77660 (0.0009) -[2023-10-10 15:43:12,824][76543] Updated weights for policy 0, policy_version 77793 (0.0007) -[2023-10-10 15:43:13,197][76543] Updated weights for policy 0, policy_version 77803 (0.0007) -[2023-10-10 15:43:13,575][76543] Updated weights for policy 0, policy_version 77813 (0.0007) -[2023-10-10 15:43:13,939][76543] Updated weights for policy 0, policy_version 77823 (0.0007) -[2023-10-10 15:43:16,009][76542] Updated weights for policy 1, policy_version 77670 (0.0009) -[2023-10-10 15:43:16,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 159219712. Throughput: 0: 1829.5, 1: 1832.2. Samples: 39818518. Policy #0 lag: (min: 16.0, avg: 38.4, max: 48.0) -[2023-10-10 15:43:16,077][75634] Avg episode reward: [(0, '39.460'), (1, '32.130')] -[2023-10-10 15:43:16,385][76542] Updated weights for policy 1, policy_version 77680 (0.0007) -[2023-10-10 15:43:16,755][76542] Updated weights for policy 1, policy_version 77690 (0.0008) -[2023-10-10 15:43:17,590][76543] Updated weights for policy 0, policy_version 77833 (0.0009) -[2023-10-10 15:43:17,955][76543] Updated weights for policy 0, policy_version 77843 (0.0010) -[2023-10-10 15:43:18,339][76543] Updated weights for policy 0, policy_version 77853 (0.0009) -[2023-10-10 15:43:20,359][76542] Updated weights for policy 1, policy_version 77700 (0.0009) -[2023-10-10 15:43:20,726][76542] Updated weights for policy 1, policy_version 77710 (0.0011) -[2023-10-10 15:43:21,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 159285248. Throughput: 0: 1825.1, 1: 1834.0. Samples: 39829056. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-10 15:43:21,077][75634] Avg episode reward: [(0, '37.930'), (1, '37.860')] -[2023-10-10 15:43:21,091][76542] Updated weights for policy 1, policy_version 77720 (0.0007) -[2023-10-10 15:43:21,883][76543] Updated weights for policy 0, policy_version 77863 (0.0009) -[2023-10-10 15:43:22,254][76543] Updated weights for policy 0, policy_version 77873 (0.0008) -[2023-10-10 15:43:22,619][76543] Updated weights for policy 0, policy_version 77883 (0.0008) -[2023-10-10 15:43:24,715][76542] Updated weights for policy 1, policy_version 77730 (0.0009) -[2023-10-10 15:43:25,087][76542] Updated weights for policy 1, policy_version 77740 (0.0009) -[2023-10-10 15:43:25,458][76542] Updated weights for policy 1, policy_version 77750 (0.0007) -[2023-10-10 15:43:25,833][76542] Updated weights for policy 1, policy_version 77760 (0.0008) -[2023-10-10 15:43:26,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 159383552. Throughput: 0: 1837.0, 1: 1831.5. Samples: 39851820. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-10 15:43:26,077][75634] Avg episode reward: [(0, '33.970'), (1, '37.890')] -[2023-10-10 15:43:26,217][76543] Updated weights for policy 0, policy_version 77893 (0.0008) -[2023-10-10 15:43:26,597][76543] Updated weights for policy 0, policy_version 77903 (0.0009) -[2023-10-10 15:43:26,956][76543] Updated weights for policy 0, policy_version 77913 (0.0008) -[2023-10-10 15:43:29,780][76542] Updated weights for policy 1, policy_version 77770 (0.0009) -[2023-10-10 15:43:30,149][76542] Updated weights for policy 1, policy_version 77780 (0.0011) -[2023-10-10 15:43:30,517][76542] Updated weights for policy 1, policy_version 77790 (0.0008) -[2023-10-10 15:43:30,777][76543] Updated weights for policy 0, policy_version 77923 (0.0009) -[2023-10-10 15:43:31,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 159449088. Throughput: 0: 1839.9, 1: 1820.1. Samples: 39872638. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-10 15:43:31,077][75634] Avg episode reward: [(0, '31.320'), (1, '35.710')] -[2023-10-10 15:43:31,147][76543] Updated weights for policy 0, policy_version 77933 (0.0008) -[2023-10-10 15:43:31,521][76543] Updated weights for policy 0, policy_version 77943 (0.0007) -[2023-10-10 15:43:34,301][76542] Updated weights for policy 1, policy_version 77800 (0.0008) -[2023-10-10 15:43:34,671][76542] Updated weights for policy 1, policy_version 77810 (0.0007) -[2023-10-10 15:43:35,044][76542] Updated weights for policy 1, policy_version 77820 (0.0008) -[2023-10-10 15:43:35,198][76543] Updated weights for policy 0, policy_version 77953 (0.0009) -[2023-10-10 15:43:35,559][76543] Updated weights for policy 0, policy_version 77963 (0.0008) -[2023-10-10 15:43:35,932][76543] Updated weights for policy 0, policy_version 77973 (0.0007) -[2023-10-10 15:43:36,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 159514624. Throughput: 0: 1841.7, 1: 1816.0. Samples: 39883840. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-10 15:43:36,077][75634] Avg episode reward: [(0, '32.800'), (1, '35.750')] -[2023-10-10 15:43:36,304][76543] Updated weights for policy 0, policy_version 77983 (0.0007) -[2023-10-10 15:43:38,776][76542] Updated weights for policy 1, policy_version 77830 (0.0008) -[2023-10-10 15:43:39,145][76542] Updated weights for policy 1, policy_version 77840 (0.0009) -[2023-10-10 15:43:39,516][76542] Updated weights for policy 1, policy_version 77850 (0.0008) -[2023-10-10 15:43:39,987][76543] Updated weights for policy 0, policy_version 77993 (0.0009) -[2023-10-10 15:43:40,361][76543] Updated weights for policy 0, policy_version 78003 (0.0011) -[2023-10-10 15:43:40,722][76543] Updated weights for policy 0, policy_version 78013 (0.0009) -[2023-10-10 15:43:41,076][75634] Fps is (10 sec: 16384.1, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 159612928. Throughput: 0: 1837.5, 1: 1815.1. Samples: 39905204. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-10 15:43:41,077][75634] Avg episode reward: [(0, '33.350'), (1, '37.520')] -[2023-10-10 15:43:43,289][76542] Updated weights for policy 1, policy_version 77860 (0.0009) -[2023-10-10 15:43:43,665][76542] Updated weights for policy 1, policy_version 77870 (0.0011) -[2023-10-10 15:43:44,041][76542] Updated weights for policy 1, policy_version 77880 (0.0010) -[2023-10-10 15:43:44,446][76543] Updated weights for policy 0, policy_version 78023 (0.0009) -[2023-10-10 15:43:44,819][76543] Updated weights for policy 0, policy_version 78033 (0.0007) -[2023-10-10 15:43:45,190][76543] Updated weights for policy 0, policy_version 78043 (0.0007) -[2023-10-10 15:43:46,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 159678464. Throughput: 0: 1824.7, 1: 1811.3. Samples: 39926462. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-10 15:43:46,076][75634] Avg episode reward: [(0, '37.130'), (1, '37.590')] -[2023-10-10 15:43:47,740][76542] Updated weights for policy 1, policy_version 77890 (0.0008) -[2023-10-10 15:43:48,114][76542] Updated weights for policy 1, policy_version 77900 (0.0010) -[2023-10-10 15:43:48,483][76542] Updated weights for policy 1, policy_version 77910 (0.0009) -[2023-10-10 15:43:48,848][76542] Updated weights for policy 1, policy_version 77920 (0.0007) -[2023-10-10 15:43:48,883][76543] Updated weights for policy 0, policy_version 78053 (0.0007) -[2023-10-10 15:43:49,271][76543] Updated weights for policy 0, policy_version 78063 (0.0011) -[2023-10-10 15:43:49,635][76543] Updated weights for policy 0, policy_version 78073 (0.0012) -[2023-10-10 15:43:51,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 159744000. Throughput: 0: 1826.6, 1: 1818.5. Samples: 39938036. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-10 15:43:51,076][75634] Avg episode reward: [(0, '34.150'), (1, '36.320')] -[2023-10-10 15:43:52,518][76542] Updated weights for policy 1, policy_version 77930 (0.0009) -[2023-10-10 15:43:52,883][76542] Updated weights for policy 1, policy_version 77940 (0.0009) -[2023-10-10 15:43:53,225][76543] Updated weights for policy 0, policy_version 78083 (0.0010) -[2023-10-10 15:43:53,257][76542] Updated weights for policy 1, policy_version 77950 (0.0008) -[2023-10-10 15:43:53,600][76543] Updated weights for policy 0, policy_version 78093 (0.0007) -[2023-10-10 15:43:53,963][76543] Updated weights for policy 0, policy_version 78103 (0.0007) -[2023-10-10 15:43:56,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 159809536. Throughput: 0: 1821.5, 1: 1805.9. Samples: 39959182. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-10 15:43:56,077][75634] Avg episode reward: [(0, '30.990'), (1, '34.020')] -[2023-10-10 15:43:57,003][76542] Updated weights for policy 1, policy_version 77960 (0.0008) -[2023-10-10 15:43:57,374][76542] Updated weights for policy 1, policy_version 77970 (0.0007) -[2023-10-10 15:43:57,736][76542] Updated weights for policy 1, policy_version 77980 (0.0008) -[2023-10-10 15:43:57,767][76543] Updated weights for policy 0, policy_version 78113 (0.0009) -[2023-10-10 15:43:58,137][76543] Updated weights for policy 0, policy_version 78123 (0.0009) -[2023-10-10 15:43:58,496][76543] Updated weights for policy 0, policy_version 78133 (0.0008) -[2023-10-10 15:43:58,862][76543] Updated weights for policy 0, policy_version 78143 (0.0007) -[2023-10-10 15:44:01,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 159875072. Throughput: 0: 1823.9, 1: 1803.0. Samples: 39981726. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-10 15:44:01,077][75634] Avg episode reward: [(0, '37.620'), (1, '35.490')] -[2023-10-10 15:44:01,504][76542] Updated weights for policy 1, policy_version 77990 (0.0009) -[2023-10-10 15:44:01,869][76542] Updated weights for policy 1, policy_version 78000 (0.0009) -[2023-10-10 15:44:02,243][76542] Updated weights for policy 1, policy_version 78010 (0.0008) -[2023-10-10 15:44:02,492][76543] Updated weights for policy 0, policy_version 78153 (0.0007) -[2023-10-10 15:44:02,860][76543] Updated weights for policy 0, policy_version 78163 (0.0008) -[2023-10-10 15:44:03,243][76543] Updated weights for policy 0, policy_version 78173 (0.0007) -[2023-10-10 15:44:06,026][76542] Updated weights for policy 1, policy_version 78020 (0.0008) -[2023-10-10 15:44:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 159940608. Throughput: 0: 1820.4, 1: 1799.0. Samples: 39991932. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-10 15:44:06,077][75634] Avg episode reward: [(0, '38.230'), (1, '35.480')] -[2023-10-10 15:44:06,384][76542] Updated weights for policy 1, policy_version 78030 (0.0007) -[2023-10-10 15:44:06,753][76542] Updated weights for policy 1, policy_version 78040 (0.0007) -[2023-10-10 15:44:06,768][76543] Updated weights for policy 0, policy_version 78183 (0.0009) -[2023-10-10 15:44:07,140][76543] Updated weights for policy 0, policy_version 78193 (0.0008) -[2023-10-10 15:44:07,508][76543] Updated weights for policy 0, policy_version 78203 (0.0007) -[2023-10-10 15:44:10,345][76542] Updated weights for policy 1, policy_version 78050 (0.0008) -[2023-10-10 15:44:10,705][76542] Updated weights for policy 1, policy_version 78060 (0.0009) -[2023-10-10 15:44:11,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14440.2). Total num frames: 160006144. Throughput: 0: 1824.7, 1: 1795.6. Samples: 40014732. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 15:44:11,076][76542] Updated weights for policy 1, policy_version 78070 (0.0008) -[2023-10-10 15:44:11,076][75634] Avg episode reward: [(0, '39.060'), (1, '34.980')] -[2023-10-10 15:44:11,082][76543] Updated weights for policy 0, policy_version 78213 (0.0008) -[2023-10-10 15:44:11,440][76542] Updated weights for policy 1, policy_version 78080 (0.0007) -[2023-10-10 15:44:11,458][76543] Updated weights for policy 0, policy_version 78223 (0.0010) -[2023-10-10 15:44:11,825][76543] Updated weights for policy 0, policy_version 78233 (0.0009) -[2023-10-10 15:44:15,208][76542] Updated weights for policy 1, policy_version 78090 (0.0011) -[2023-10-10 15:44:15,573][76542] Updated weights for policy 1, policy_version 78100 (0.0008) -[2023-10-10 15:44:15,707][76543] Updated weights for policy 0, policy_version 78243 (0.0008) -[2023-10-10 15:44:15,933][76542] Updated weights for policy 1, policy_version 78110 (0.0007) -[2023-10-10 15:44:16,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 160104448. Throughput: 0: 1822.1, 1: 1815.7. Samples: 40036338. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 15:44:16,076][75634] Avg episode reward: [(0, '40.220'), (1, '34.190')] -[2023-10-10 15:44:16,082][76543] Updated weights for policy 0, policy_version 78253 (0.0007) -[2023-10-10 15:44:16,451][76543] Updated weights for policy 0, policy_version 78263 (0.0008) -[2023-10-10 15:44:19,541][76542] Updated weights for policy 1, policy_version 78120 (0.0010) -[2023-10-10 15:44:19,907][76542] Updated weights for policy 1, policy_version 78130 (0.0009) -[2023-10-10 15:44:20,079][76543] Updated weights for policy 0, policy_version 78273 (0.0009) -[2023-10-10 15:44:20,272][76542] Updated weights for policy 1, policy_version 78140 (0.0007) -[2023-10-10 15:44:20,442][76543] Updated weights for policy 0, policy_version 78283 (0.0007) -[2023-10-10 15:44:20,809][76543] Updated weights for policy 0, policy_version 78293 (0.0010) -[2023-10-10 15:44:21,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 160169984. Throughput: 0: 1824.9, 1: 1816.7. Samples: 40047714. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 15:44:21,076][75634] Avg episode reward: [(0, '37.920'), (1, '38.460')] -[2023-10-10 15:44:21,186][76543] Updated weights for policy 0, policy_version 78303 (0.0008) -[2023-10-10 15:44:23,903][76542] Updated weights for policy 1, policy_version 78150 (0.0007) -[2023-10-10 15:44:24,268][76542] Updated weights for policy 1, policy_version 78160 (0.0008) -[2023-10-10 15:44:24,630][76542] Updated weights for policy 1, policy_version 78170 (0.0008) -[2023-10-10 15:44:24,867][76543] Updated weights for policy 0, policy_version 78313 (0.0008) -[2023-10-10 15:44:25,233][76543] Updated weights for policy 0, policy_version 78323 (0.0008) -[2023-10-10 15:44:25,617][76543] Updated weights for policy 0, policy_version 78333 (0.0007) -[2023-10-10 15:44:26,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 160268288. Throughput: 0: 1827.2, 1: 1822.4. Samples: 40069434. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 15:44:26,076][75634] Avg episode reward: [(0, '35.710'), (1, '36.670')] -[2023-10-10 15:44:28,344][76542] Updated weights for policy 1, policy_version 78180 (0.0008) -[2023-10-10 15:44:28,713][76542] Updated weights for policy 1, policy_version 78190 (0.0010) -[2023-10-10 15:44:29,077][76542] Updated weights for policy 1, policy_version 78200 (0.0009) -[2023-10-10 15:44:29,285][76543] Updated weights for policy 0, policy_version 78343 (0.0008) -[2023-10-10 15:44:29,649][76543] Updated weights for policy 0, policy_version 78353 (0.0007) -[2023-10-10 15:44:30,017][76543] Updated weights for policy 0, policy_version 78363 (0.0011) -[2023-10-10 15:44:31,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 160333824. Throughput: 0: 1823.9, 1: 1818.6. Samples: 40090374. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 15:44:31,077][75634] Avg episode reward: [(0, '39.980'), (1, '38.690')] -[2023-10-10 15:44:31,090][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000078368_80248832.pth... -[2023-10-10 15:44:31,090][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000078208_80084992.pth... -[2023-10-10 15:44:31,119][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000076640_78479360.pth -[2023-10-10 15:44:31,129][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000076512_78348288.pth -[2023-10-10 15:44:32,869][76542] Updated weights for policy 1, policy_version 78210 (0.0008) -[2023-10-10 15:44:33,231][76542] Updated weights for policy 1, policy_version 78220 (0.0007) -[2023-10-10 15:44:33,599][76542] Updated weights for policy 1, policy_version 78230 (0.0008) -[2023-10-10 15:44:33,657][76543] Updated weights for policy 0, policy_version 78373 (0.0007) -[2023-10-10 15:44:33,975][76542] Updated weights for policy 1, policy_version 78240 (0.0007) -[2023-10-10 15:44:34,040][76543] Updated weights for policy 0, policy_version 78383 (0.0008) -[2023-10-10 15:44:34,408][76543] Updated weights for policy 0, policy_version 78393 (0.0008) -[2023-10-10 15:44:36,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 160399360. Throughput: 0: 1835.7, 1: 1818.0. Samples: 40102454. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 15:44:36,077][75634] Avg episode reward: [(0, '38.120'), (1, '35.090')] -[2023-10-10 15:44:37,685][76542] Updated weights for policy 1, policy_version 78250 (0.0007) -[2023-10-10 15:44:38,058][76542] Updated weights for policy 1, policy_version 78260 (0.0009) -[2023-10-10 15:44:38,061][76543] Updated weights for policy 0, policy_version 78403 (0.0009) -[2023-10-10 15:44:38,420][76542] Updated weights for policy 1, policy_version 78270 (0.0008) -[2023-10-10 15:44:38,440][76543] Updated weights for policy 0, policy_version 78413 (0.0007) -[2023-10-10 15:44:38,809][76543] Updated weights for policy 0, policy_version 78423 (0.0008) -[2023-10-10 15:44:41,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14662.3). Total num frames: 160464896. Throughput: 0: 1831.2, 1: 1813.0. Samples: 40123168. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 15:44:41,076][75634] Avg episode reward: [(0, '37.220'), (1, '34.730')] -[2023-10-10 15:44:42,148][76542] Updated weights for policy 1, policy_version 78280 (0.0011) -[2023-10-10 15:44:42,515][76542] Updated weights for policy 1, policy_version 78290 (0.0009) -[2023-10-10 15:44:42,530][76543] Updated weights for policy 0, policy_version 78433 (0.0010) -[2023-10-10 15:44:42,869][76542] Updated weights for policy 1, policy_version 78300 (0.0008) -[2023-10-10 15:44:42,893][76543] Updated weights for policy 0, policy_version 78443 (0.0009) -[2023-10-10 15:44:43,267][76543] Updated weights for policy 0, policy_version 78453 (0.0007) -[2023-10-10 15:44:43,632][76543] Updated weights for policy 0, policy_version 78463 (0.0007) -[2023-10-10 15:44:46,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 160530432. Throughput: 0: 1831.3, 1: 1816.5. Samples: 40145880. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 15:44:46,076][75634] Avg episode reward: [(0, '37.030'), (1, '36.530')] -[2023-10-10 15:44:46,513][76542] Updated weights for policy 1, policy_version 78310 (0.0008) -[2023-10-10 15:44:46,879][76542] Updated weights for policy 1, policy_version 78320 (0.0008) -[2023-10-10 15:44:47,240][76542] Updated weights for policy 1, policy_version 78330 (0.0009) -[2023-10-10 15:44:47,349][76543] Updated weights for policy 0, policy_version 78473 (0.0009) -[2023-10-10 15:44:47,716][76543] Updated weights for policy 0, policy_version 78483 (0.0008) -[2023-10-10 15:44:48,094][76543] Updated weights for policy 0, policy_version 78493 (0.0008) -[2023-10-10 15:44:50,873][76542] Updated weights for policy 1, policy_version 78340 (0.0009) -[2023-10-10 15:44:51,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 160595968. Throughput: 0: 1821.3, 1: 1822.5. Samples: 40155902. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 15:44:51,076][75634] Avg episode reward: [(0, '36.090'), (1, '30.650')] -[2023-10-10 15:44:51,244][76542] Updated weights for policy 1, policy_version 78350 (0.0008) -[2023-10-10 15:44:51,603][76542] Updated weights for policy 1, policy_version 78360 (0.0007) -[2023-10-10 15:44:51,851][76543] Updated weights for policy 0, policy_version 78503 (0.0007) -[2023-10-10 15:44:52,224][76543] Updated weights for policy 0, policy_version 78513 (0.0007) -[2023-10-10 15:44:52,592][76543] Updated weights for policy 0, policy_version 78523 (0.0007) -[2023-10-10 15:44:55,263][76542] Updated weights for policy 1, policy_version 78370 (0.0009) -[2023-10-10 15:44:55,636][76542] Updated weights for policy 1, policy_version 78380 (0.0007) -[2023-10-10 15:44:55,991][76542] Updated weights for policy 1, policy_version 78390 (0.0009) -[2023-10-10 15:44:56,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 160661504. Throughput: 0: 1814.8, 1: 1827.4. Samples: 40178632. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-10 15:44:56,077][75634] Avg episode reward: [(0, '36.270'), (1, '31.310')] -[2023-10-10 15:44:56,341][76543] Updated weights for policy 0, policy_version 78533 (0.0008) -[2023-10-10 15:44:56,353][76542] Updated weights for policy 1, policy_version 78400 (0.0007) -[2023-10-10 15:44:56,714][76543] Updated weights for policy 0, policy_version 78543 (0.0007) -[2023-10-10 15:44:57,095][76543] Updated weights for policy 0, policy_version 78553 (0.0009) -[2023-10-10 15:45:00,190][76542] Updated weights for policy 1, policy_version 78410 (0.0009) -[2023-10-10 15:45:00,573][76542] Updated weights for policy 1, policy_version 78420 (0.0008) -[2023-10-10 15:45:00,785][76543] Updated weights for policy 0, policy_version 78563 (0.0009) -[2023-10-10 15:45:00,939][76542] Updated weights for policy 1, policy_version 78430 (0.0009) -[2023-10-10 15:45:01,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 160759808. Throughput: 0: 1819.9, 1: 1820.5. Samples: 40200156. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 15:45:01,077][75634] Avg episode reward: [(0, '35.920'), (1, '33.810')] -[2023-10-10 15:45:01,159][76543] Updated weights for policy 0, policy_version 78573 (0.0008) -[2023-10-10 15:45:01,532][76543] Updated weights for policy 0, policy_version 78583 (0.0008) -[2023-10-10 15:45:04,558][76542] Updated weights for policy 1, policy_version 78440 (0.0009) -[2023-10-10 15:45:04,931][76542] Updated weights for policy 1, policy_version 78450 (0.0010) -[2023-10-10 15:45:05,236][76543] Updated weights for policy 0, policy_version 78593 (0.0009) -[2023-10-10 15:45:05,303][76542] Updated weights for policy 1, policy_version 78460 (0.0009) -[2023-10-10 15:45:05,612][76543] Updated weights for policy 0, policy_version 78603 (0.0009) -[2023-10-10 15:45:05,985][76543] Updated weights for policy 0, policy_version 78613 (0.0007) -[2023-10-10 15:45:06,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 160825344. Throughput: 0: 1817.7, 1: 1813.6. Samples: 40211124. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 15:45:06,076][75634] Avg episode reward: [(0, '40.250'), (1, '35.190')] -[2023-10-10 15:45:06,350][76543] Updated weights for policy 0, policy_version 78623 (0.0008) -[2023-10-10 15:45:09,060][76542] Updated weights for policy 1, policy_version 78470 (0.0008) -[2023-10-10 15:45:09,438][76542] Updated weights for policy 1, policy_version 78480 (0.0009) -[2023-10-10 15:45:09,802][76542] Updated weights for policy 1, policy_version 78490 (0.0008) -[2023-10-10 15:45:10,032][76543] Updated weights for policy 0, policy_version 78633 (0.0007) -[2023-10-10 15:45:10,401][76543] Updated weights for policy 0, policy_version 78643 (0.0009) -[2023-10-10 15:45:10,770][76543] Updated weights for policy 0, policy_version 78653 (0.0008) -[2023-10-10 15:45:11,076][75634] Fps is (10 sec: 16384.4, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 160923648. Throughput: 0: 1810.6, 1: 1813.5. Samples: 40232520. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 15:45:11,076][75634] Avg episode reward: [(0, '35.610'), (1, '38.470')] -[2023-10-10 15:45:13,593][76542] Updated weights for policy 1, policy_version 78500 (0.0009) -[2023-10-10 15:45:13,965][76542] Updated weights for policy 1, policy_version 78510 (0.0009) -[2023-10-10 15:45:14,338][76542] Updated weights for policy 1, policy_version 78520 (0.0008) -[2023-10-10 15:45:14,550][76543] Updated weights for policy 0, policy_version 78663 (0.0008) -[2023-10-10 15:45:14,919][76543] Updated weights for policy 0, policy_version 78673 (0.0009) -[2023-10-10 15:45:15,291][76543] Updated weights for policy 0, policy_version 78683 (0.0007) -[2023-10-10 15:45:16,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 160989184. Throughput: 0: 1817.8, 1: 1811.1. Samples: 40253674. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 15:45:16,076][75634] Avg episode reward: [(0, '33.500'), (1, '42.670')] -[2023-10-10 15:45:17,924][76542] Updated weights for policy 1, policy_version 78530 (0.0009) -[2023-10-10 15:45:18,288][76542] Updated weights for policy 1, policy_version 78540 (0.0010) -[2023-10-10 15:45:18,655][76542] Updated weights for policy 1, policy_version 78550 (0.0010) -[2023-10-10 15:45:19,020][76542] Updated weights for policy 1, policy_version 78560 (0.0008) -[2023-10-10 15:45:19,042][76543] Updated weights for policy 0, policy_version 78693 (0.0008) -[2023-10-10 15:45:19,419][76543] Updated weights for policy 0, policy_version 78703 (0.0011) -[2023-10-10 15:45:19,794][76543] Updated weights for policy 0, policy_version 78713 (0.0009) -[2023-10-10 15:45:21,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 161054720. Throughput: 0: 1802.2, 1: 1817.3. Samples: 40265332. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 15:45:21,077][75634] Avg episode reward: [(0, '33.730'), (1, '39.200')] -[2023-10-10 15:45:22,706][76542] Updated weights for policy 1, policy_version 78570 (0.0008) -[2023-10-10 15:45:23,085][76542] Updated weights for policy 1, policy_version 78580 (0.0009) -[2023-10-10 15:45:23,336][76543] Updated weights for policy 0, policy_version 78723 (0.0010) -[2023-10-10 15:45:23,445][76542] Updated weights for policy 1, policy_version 78590 (0.0008) -[2023-10-10 15:45:23,700][76543] Updated weights for policy 0, policy_version 78733 (0.0008) -[2023-10-10 15:45:24,064][76543] Updated weights for policy 0, policy_version 78743 (0.0007) -[2023-10-10 15:45:26,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 161120256. Throughput: 0: 1812.0, 1: 1817.3. Samples: 40286486. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 15:45:26,076][75634] Avg episode reward: [(0, '35.180'), (1, '34.430')] -[2023-10-10 15:45:27,253][76542] Updated weights for policy 1, policy_version 78600 (0.0008) -[2023-10-10 15:45:27,623][76542] Updated weights for policy 1, policy_version 78610 (0.0008) -[2023-10-10 15:45:27,815][76543] Updated weights for policy 0, policy_version 78753 (0.0008) -[2023-10-10 15:45:27,997][76542] Updated weights for policy 1, policy_version 78620 (0.0008) -[2023-10-10 15:45:28,175][76543] Updated weights for policy 0, policy_version 78763 (0.0011) -[2023-10-10 15:45:28,549][76543] Updated weights for policy 0, policy_version 78773 (0.0007) -[2023-10-10 15:45:28,927][76543] Updated weights for policy 0, policy_version 78783 (0.0008) -[2023-10-10 15:45:31,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 161185792. Throughput: 0: 1813.1, 1: 1809.1. Samples: 40308880. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 15:45:31,077][75634] Avg episode reward: [(0, '34.420'), (1, '32.350')] -[2023-10-10 15:45:31,732][76542] Updated weights for policy 1, policy_version 78630 (0.0008) -[2023-10-10 15:45:32,102][76542] Updated weights for policy 1, policy_version 78640 (0.0008) -[2023-10-10 15:45:32,480][76542] Updated weights for policy 1, policy_version 78650 (0.0008) -[2023-10-10 15:45:32,693][76543] Updated weights for policy 0, policy_version 78793 (0.0009) -[2023-10-10 15:45:33,067][76543] Updated weights for policy 0, policy_version 78803 (0.0010) -[2023-10-10 15:45:33,445][76543] Updated weights for policy 0, policy_version 78813 (0.0009) -[2023-10-10 15:45:36,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 161251328. Throughput: 0: 1821.3, 1: 1802.7. Samples: 40318980. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 15:45:36,076][75634] Avg episode reward: [(0, '35.840'), (1, '31.220')] -[2023-10-10 15:45:36,163][76542] Updated weights for policy 1, policy_version 78660 (0.0008) -[2023-10-10 15:45:36,532][76542] Updated weights for policy 1, policy_version 78670 (0.0009) -[2023-10-10 15:45:36,900][76542] Updated weights for policy 1, policy_version 78680 (0.0008) -[2023-10-10 15:45:37,122][76543] Updated weights for policy 0, policy_version 78823 (0.0010) -[2023-10-10 15:45:37,492][76543] Updated weights for policy 0, policy_version 78833 (0.0010) -[2023-10-10 15:45:37,868][76543] Updated weights for policy 0, policy_version 78843 (0.0007) -[2023-10-10 15:45:40,703][76542] Updated weights for policy 1, policy_version 78690 (0.0009) -[2023-10-10 15:45:41,067][76542] Updated weights for policy 1, policy_version 78700 (0.0010) -[2023-10-10 15:45:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 161316864. Throughput: 0: 1811.6, 1: 1801.2. Samples: 40341212. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 15:45:41,077][75634] Avg episode reward: [(0, '33.630'), (1, '32.290')] -[2023-10-10 15:45:41,432][76542] Updated weights for policy 1, policy_version 78710 (0.0008) -[2023-10-10 15:45:41,583][76543] Updated weights for policy 0, policy_version 78853 (0.0009) -[2023-10-10 15:45:41,791][76542] Updated weights for policy 1, policy_version 78720 (0.0009) -[2023-10-10 15:45:41,963][76543] Updated weights for policy 0, policy_version 78863 (0.0009) -[2023-10-10 15:45:42,338][76543] Updated weights for policy 0, policy_version 78873 (0.0009) -[2023-10-10 15:45:45,522][76542] Updated weights for policy 1, policy_version 78730 (0.0009) -[2023-10-10 15:45:45,879][76543] Updated weights for policy 0, policy_version 78883 (0.0008) -[2023-10-10 15:45:45,893][76542] Updated weights for policy 1, policy_version 78740 (0.0007) -[2023-10-10 15:45:46,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 161382400. Throughput: 0: 1810.9, 1: 1808.5. Samples: 40363030. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 15:45:46,077][75634] Avg episode reward: [(0, '31.740'), (1, '28.850')] -[2023-10-10 15:45:46,247][76543] Updated weights for policy 0, policy_version 78893 (0.0007) -[2023-10-10 15:45:46,255][76542] Updated weights for policy 1, policy_version 78750 (0.0007) -[2023-10-10 15:45:46,628][76543] Updated weights for policy 0, policy_version 78903 (0.0008) -[2023-10-10 15:45:49,886][76542] Updated weights for policy 1, policy_version 78760 (0.0008) -[2023-10-10 15:45:50,217][76543] Updated weights for policy 0, policy_version 78913 (0.0007) -[2023-10-10 15:45:50,257][76542] Updated weights for policy 1, policy_version 78770 (0.0008) -[2023-10-10 15:45:50,586][76543] Updated weights for policy 0, policy_version 78923 (0.0007) -[2023-10-10 15:45:50,626][76542] Updated weights for policy 1, policy_version 78780 (0.0008) -[2023-10-10 15:45:50,957][76543] Updated weights for policy 0, policy_version 78933 (0.0008) -[2023-10-10 15:45:51,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 161480704. Throughput: 0: 1809.0, 1: 1800.1. Samples: 40373536. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 15:45:51,076][75634] Avg episode reward: [(0, '37.600'), (1, '34.350')] -[2023-10-10 15:45:51,319][76543] Updated weights for policy 0, policy_version 78943 (0.0010) -[2023-10-10 15:45:54,307][76542] Updated weights for policy 1, policy_version 78790 (0.0009) -[2023-10-10 15:45:54,675][76542] Updated weights for policy 1, policy_version 78800 (0.0009) -[2023-10-10 15:45:55,039][76543] Updated weights for policy 0, policy_version 78953 (0.0008) -[2023-10-10 15:45:55,043][76542] Updated weights for policy 1, policy_version 78810 (0.0010) -[2023-10-10 15:45:55,408][76543] Updated weights for policy 0, policy_version 78963 (0.0007) -[2023-10-10 15:45:55,789][76543] Updated weights for policy 0, policy_version 78973 (0.0008) -[2023-10-10 15:45:56,076][75634] Fps is (10 sec: 19661.1, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 161579008. Throughput: 0: 1815.6, 1: 1812.3. Samples: 40395776. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 15:45:56,076][75634] Avg episode reward: [(0, '39.430'), (1, '38.390')] -[2023-10-10 15:45:58,692][76542] Updated weights for policy 1, policy_version 78820 (0.0009) -[2023-10-10 15:45:59,062][76542] Updated weights for policy 1, policy_version 78830 (0.0007) -[2023-10-10 15:45:59,409][76543] Updated weights for policy 0, policy_version 78983 (0.0010) -[2023-10-10 15:45:59,420][76542] Updated weights for policy 1, policy_version 78840 (0.0008) -[2023-10-10 15:45:59,783][76543] Updated weights for policy 0, policy_version 78993 (0.0009) -[2023-10-10 15:46:00,154][76543] Updated weights for policy 0, policy_version 79003 (0.0009) -[2023-10-10 15:46:01,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 161644544. Throughput: 0: 1813.4, 1: 1804.1. Samples: 40416462. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 15:46:01,077][75634] Avg episode reward: [(0, '38.180'), (1, '37.400')] -[2023-10-10 15:46:03,228][76542] Updated weights for policy 1, policy_version 78850 (0.0008) -[2023-10-10 15:46:03,600][76542] Updated weights for policy 1, policy_version 78860 (0.0007) -[2023-10-10 15:46:03,959][76542] Updated weights for policy 1, policy_version 78870 (0.0007) -[2023-10-10 15:46:04,077][76543] Updated weights for policy 0, policy_version 79013 (0.0010) -[2023-10-10 15:46:04,322][76542] Updated weights for policy 1, policy_version 78880 (0.0008) -[2023-10-10 15:46:04,464][76543] Updated weights for policy 0, policy_version 79023 (0.0009) -[2023-10-10 15:46:04,840][76543] Updated weights for policy 0, policy_version 79033 (0.0010) -[2023-10-10 15:46:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 161710080. Throughput: 0: 1815.1, 1: 1809.2. Samples: 40428426. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 15:46:06,076][75634] Avg episode reward: [(0, '37.650'), (1, '40.770')] -[2023-10-10 15:46:08,139][76542] Updated weights for policy 1, policy_version 78890 (0.0010) -[2023-10-10 15:46:08,509][76542] Updated weights for policy 1, policy_version 78900 (0.0007) -[2023-10-10 15:46:08,546][76543] Updated weights for policy 0, policy_version 79043 (0.0009) -[2023-10-10 15:46:08,877][76542] Updated weights for policy 1, policy_version 78910 (0.0008) -[2023-10-10 15:46:08,910][76543] Updated weights for policy 0, policy_version 79053 (0.0009) -[2023-10-10 15:46:09,272][76543] Updated weights for policy 0, policy_version 79063 (0.0007) -[2023-10-10 15:46:11,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 161775616. Throughput: 0: 1817.9, 1: 1801.2. Samples: 40449346. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 15:46:11,076][75634] Avg episode reward: [(0, '40.160'), (1, '36.570')] -[2023-10-10 15:46:12,440][76542] Updated weights for policy 1, policy_version 78920 (0.0009) -[2023-10-10 15:46:12,804][76542] Updated weights for policy 1, policy_version 78930 (0.0008) -[2023-10-10 15:46:13,026][76543] Updated weights for policy 0, policy_version 79073 (0.0009) -[2023-10-10 15:46:13,168][76542] Updated weights for policy 1, policy_version 78940 (0.0009) -[2023-10-10 15:46:13,395][76543] Updated weights for policy 0, policy_version 79083 (0.0008) -[2023-10-10 15:46:13,774][76543] Updated weights for policy 0, policy_version 79093 (0.0011) -[2023-10-10 15:46:14,143][76543] Updated weights for policy 0, policy_version 79103 (0.0009) -[2023-10-10 15:46:16,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 161841152. Throughput: 0: 1809.3, 1: 1810.3. Samples: 40471762. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 15:46:16,076][75634] Avg episode reward: [(0, '40.220'), (1, '32.960')] -[2023-10-10 15:46:16,873][76542] Updated weights for policy 1, policy_version 78950 (0.0008) -[2023-10-10 15:46:17,238][76542] Updated weights for policy 1, policy_version 78960 (0.0010) -[2023-10-10 15:46:17,615][76542] Updated weights for policy 1, policy_version 78970 (0.0008) -[2023-10-10 15:46:17,809][76543] Updated weights for policy 0, policy_version 79113 (0.0008) -[2023-10-10 15:46:18,184][76543] Updated weights for policy 0, policy_version 79123 (0.0007) -[2023-10-10 15:46:18,551][76543] Updated weights for policy 0, policy_version 79133 (0.0007) -[2023-10-10 15:46:21,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 161906688. Throughput: 0: 1819.0, 1: 1818.9. Samples: 40482686. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 15:46:21,076][75634] Avg episode reward: [(0, '41.470'), (1, '35.920')] -[2023-10-10 15:46:21,404][76542] Updated weights for policy 1, policy_version 78980 (0.0009) -[2023-10-10 15:46:21,778][76542] Updated weights for policy 1, policy_version 78990 (0.0008) -[2023-10-10 15:46:22,151][76542] Updated weights for policy 1, policy_version 79000 (0.0008) -[2023-10-10 15:46:22,163][76543] Updated weights for policy 0, policy_version 79143 (0.0008) -[2023-10-10 15:46:22,531][76543] Updated weights for policy 0, policy_version 79153 (0.0007) -[2023-10-10 15:46:22,901][76543] Updated weights for policy 0, policy_version 79163 (0.0009) -[2023-10-10 15:46:25,819][76542] Updated weights for policy 1, policy_version 79010 (0.0008) -[2023-10-10 15:46:26,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 161972224. Throughput: 0: 1826.4, 1: 1815.3. Samples: 40505090. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 15:46:26,077][75634] Avg episode reward: [(0, '44.240'), (1, '36.340')] -[2023-10-10 15:46:26,078][76362] Saving new best policy, reward=44.240! -[2023-10-10 15:46:26,191][76542] Updated weights for policy 1, policy_version 79020 (0.0007) -[2023-10-10 15:46:26,509][76543] Updated weights for policy 0, policy_version 79173 (0.0007) -[2023-10-10 15:46:26,548][76542] Updated weights for policy 1, policy_version 79030 (0.0007) -[2023-10-10 15:46:26,883][76543] Updated weights for policy 0, policy_version 79183 (0.0007) -[2023-10-10 15:46:26,917][76542] Updated weights for policy 1, policy_version 79040 (0.0007) -[2023-10-10 15:46:27,256][76543] Updated weights for policy 0, policy_version 79193 (0.0007) -[2023-10-10 15:46:30,790][76542] Updated weights for policy 1, policy_version 79050 (0.0007) -[2023-10-10 15:46:30,813][76543] Updated weights for policy 0, policy_version 79203 (0.0007) -[2023-10-10 15:46:31,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 162037760. Throughput: 0: 1831.7, 1: 1824.7. Samples: 40527566. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 15:46:31,076][75634] Avg episode reward: [(0, '38.670'), (1, '41.470')] -[2023-10-10 15:46:31,164][76542] Updated weights for policy 1, policy_version 79060 (0.0007) -[2023-10-10 15:46:31,169][76543] Updated weights for policy 0, policy_version 79213 (0.0008) -[2023-10-10 15:46:31,521][76542] Updated weights for policy 1, policy_version 79070 (0.0007) -[2023-10-10 15:46:31,540][76543] Updated weights for policy 0, policy_version 79223 (0.0007) -[2023-10-10 15:46:31,593][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000079072_80969728.pth... -[2023-10-10 15:46:31,632][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000077376_79233024.pth -[2023-10-10 15:46:31,876][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000079232_81133568.pth... -[2023-10-10 15:46:31,912][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000077504_79364096.pth -[2023-10-10 15:46:35,069][76542] Updated weights for policy 1, policy_version 79080 (0.0009) -[2023-10-10 15:46:35,218][76543] Updated weights for policy 0, policy_version 79233 (0.0007) -[2023-10-10 15:46:35,436][76542] Updated weights for policy 1, policy_version 79090 (0.0008) -[2023-10-10 15:46:35,587][76543] Updated weights for policy 0, policy_version 79243 (0.0007) -[2023-10-10 15:46:35,805][76542] Updated weights for policy 1, policy_version 79100 (0.0007) -[2023-10-10 15:46:35,958][76543] Updated weights for policy 0, policy_version 79253 (0.0008) -[2023-10-10 15:46:36,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 162136064. Throughput: 0: 1833.6, 1: 1819.4. Samples: 40537924. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 15:46:36,076][75634] Avg episode reward: [(0, '37.070'), (1, '37.450')] -[2023-10-10 15:46:36,323][76543] Updated weights for policy 0, policy_version 79263 (0.0008) -[2023-10-10 15:46:39,610][76542] Updated weights for policy 1, policy_version 79110 (0.0008) -[2023-10-10 15:46:39,971][76542] Updated weights for policy 1, policy_version 79120 (0.0008) -[2023-10-10 15:46:40,026][76543] Updated weights for policy 0, policy_version 79273 (0.0009) -[2023-10-10 15:46:40,347][76542] Updated weights for policy 1, policy_version 79130 (0.0007) -[2023-10-10 15:46:40,385][76543] Updated weights for policy 0, policy_version 79283 (0.0008) -[2023-10-10 15:46:40,759][76543] Updated weights for policy 0, policy_version 79293 (0.0009) -[2023-10-10 15:46:41,076][75634] Fps is (10 sec: 19660.6, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 162234368. Throughput: 0: 1830.3, 1: 1823.1. Samples: 40560182. Policy #0 lag: (min: 15.0, avg: 17.0, max: 46.0) -[2023-10-10 15:46:41,077][75634] Avg episode reward: [(0, '39.810'), (1, '39.480')] -[2023-10-10 15:46:44,081][76542] Updated weights for policy 1, policy_version 79140 (0.0007) -[2023-10-10 15:46:44,355][76543] Updated weights for policy 0, policy_version 79303 (0.0008) -[2023-10-10 15:46:44,443][76542] Updated weights for policy 1, policy_version 79150 (0.0007) -[2023-10-10 15:46:44,715][76543] Updated weights for policy 0, policy_version 79313 (0.0009) -[2023-10-10 15:46:44,811][76542] Updated weights for policy 1, policy_version 79160 (0.0007) -[2023-10-10 15:46:45,085][76543] Updated weights for policy 0, policy_version 79323 (0.0008) -[2023-10-10 15:46:46,076][75634] Fps is (10 sec: 16383.6, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 162299904. Throughput: 0: 1831.4, 1: 1817.0. Samples: 40580640. Policy #0 lag: (min: 15.0, avg: 17.0, max: 46.0) -[2023-10-10 15:46:46,077][75634] Avg episode reward: [(0, '34.490'), (1, '41.410')] -[2023-10-10 15:46:48,542][76542] Updated weights for policy 1, policy_version 79170 (0.0008) -[2023-10-10 15:46:48,742][76543] Updated weights for policy 0, policy_version 79333 (0.0007) -[2023-10-10 15:46:48,899][76542] Updated weights for policy 1, policy_version 79180 (0.0008) -[2023-10-10 15:46:49,134][76543] Updated weights for policy 0, policy_version 79343 (0.0008) -[2023-10-10 15:46:49,263][76542] Updated weights for policy 1, policy_version 79190 (0.0007) -[2023-10-10 15:46:49,505][76543] Updated weights for policy 0, policy_version 79353 (0.0008) -[2023-10-10 15:46:49,631][76542] Updated weights for policy 1, policy_version 79200 (0.0009) -[2023-10-10 15:46:51,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 162365440. Throughput: 0: 1836.4, 1: 1822.8. Samples: 40593086. Policy #0 lag: (min: 15.0, avg: 17.0, max: 46.0) -[2023-10-10 15:46:51,077][75634] Avg episode reward: [(0, '35.090'), (1, '40.540')] -[2023-10-10 15:46:53,226][76543] Updated weights for policy 0, policy_version 79363 (0.0008) -[2023-10-10 15:46:53,527][76542] Updated weights for policy 1, policy_version 79210 (0.0008) -[2023-10-10 15:46:53,591][76543] Updated weights for policy 0, policy_version 79373 (0.0008) -[2023-10-10 15:46:53,891][76542] Updated weights for policy 1, policy_version 79220 (0.0008) -[2023-10-10 15:46:53,958][76543] Updated weights for policy 0, policy_version 79383 (0.0007) -[2023-10-10 15:46:54,256][76542] Updated weights for policy 1, policy_version 79230 (0.0009) -[2023-10-10 15:46:56,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 162430976. Throughput: 0: 1826.2, 1: 1808.3. Samples: 40612896. Policy #0 lag: (min: 15.0, avg: 17.0, max: 46.0) -[2023-10-10 15:46:56,077][75634] Avg episode reward: [(0, '36.440'), (1, '31.700')] -[2023-10-10 15:46:57,658][76543] Updated weights for policy 0, policy_version 79393 (0.0008) -[2023-10-10 15:46:58,025][76543] Updated weights for policy 0, policy_version 79403 (0.0010) -[2023-10-10 15:46:58,084][76542] Updated weights for policy 1, policy_version 79240 (0.0009) -[2023-10-10 15:46:58,397][76543] Updated weights for policy 0, policy_version 79413 (0.0008) -[2023-10-10 15:46:58,442][76542] Updated weights for policy 1, policy_version 79250 (0.0009) -[2023-10-10 15:46:58,774][76543] Updated weights for policy 0, policy_version 79423 (0.0007) -[2023-10-10 15:46:58,809][76542] Updated weights for policy 1, policy_version 79260 (0.0007) -[2023-10-10 15:47:01,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 162496512. Throughput: 0: 1831.4, 1: 1799.2. Samples: 40635142. Policy #0 lag: (min: 15.0, avg: 17.0, max: 46.0) -[2023-10-10 15:47:01,077][75634] Avg episode reward: [(0, '37.100'), (1, '33.840')] -[2023-10-10 15:47:02,530][76542] Updated weights for policy 1, policy_version 79270 (0.0011) -[2023-10-10 15:47:02,550][76543] Updated weights for policy 0, policy_version 79433 (0.0007) -[2023-10-10 15:47:02,904][76542] Updated weights for policy 1, policy_version 79280 (0.0007) -[2023-10-10 15:47:02,912][76543] Updated weights for policy 0, policy_version 79443 (0.0008) -[2023-10-10 15:47:03,275][76542] Updated weights for policy 1, policy_version 79290 (0.0007) -[2023-10-10 15:47:03,284][76543] Updated weights for policy 0, policy_version 79453 (0.0009) -[2023-10-10 15:47:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 162562048. Throughput: 0: 1820.3, 1: 1794.2. Samples: 40645338. Policy #0 lag: (min: 15.0, avg: 17.0, max: 46.0) -[2023-10-10 15:47:06,077][75634] Avg episode reward: [(0, '37.490'), (1, '36.570')] -[2023-10-10 15:47:06,958][76542] Updated weights for policy 1, policy_version 79300 (0.0008) -[2023-10-10 15:47:07,039][76543] Updated weights for policy 0, policy_version 79463 (0.0008) -[2023-10-10 15:47:07,324][76542] Updated weights for policy 1, policy_version 79310 (0.0008) -[2023-10-10 15:47:07,400][76543] Updated weights for policy 0, policy_version 79473 (0.0008) -[2023-10-10 15:47:07,698][76542] Updated weights for policy 1, policy_version 79320 (0.0009) -[2023-10-10 15:47:07,776][76543] Updated weights for policy 0, policy_version 79483 (0.0007) -[2023-10-10 15:47:11,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 162627584. Throughput: 0: 1819.5, 1: 1794.9. Samples: 40667738. Policy #0 lag: (min: 15.0, avg: 17.0, max: 46.0) -[2023-10-10 15:47:11,077][75634] Avg episode reward: [(0, '37.140'), (1, '37.900')] -[2023-10-10 15:47:11,408][76542] Updated weights for policy 1, policy_version 79330 (0.0008) -[2023-10-10 15:47:11,472][76543] Updated weights for policy 0, policy_version 79493 (0.0008) -[2023-10-10 15:47:11,765][76542] Updated weights for policy 1, policy_version 79340 (0.0008) -[2023-10-10 15:47:11,851][76543] Updated weights for policy 0, policy_version 79503 (0.0008) -[2023-10-10 15:47:12,125][76542] Updated weights for policy 1, policy_version 79350 (0.0008) -[2023-10-10 15:47:12,209][76543] Updated weights for policy 0, policy_version 79513 (0.0008) -[2023-10-10 15:47:12,488][76542] Updated weights for policy 1, policy_version 79360 (0.0007) -[2023-10-10 15:47:15,839][76543] Updated weights for policy 0, policy_version 79523 (0.0007) -[2023-10-10 15:47:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 162693120. Throughput: 0: 1819.0, 1: 1802.8. Samples: 40690550. Policy #0 lag: (min: 15.0, avg: 17.0, max: 46.0) -[2023-10-10 15:47:16,077][75634] Avg episode reward: [(0, '37.880'), (1, '34.380')] -[2023-10-10 15:47:16,210][76543] Updated weights for policy 0, policy_version 79533 (0.0008) -[2023-10-10 15:47:16,289][76542] Updated weights for policy 1, policy_version 79370 (0.0007) -[2023-10-10 15:47:16,581][76543] Updated weights for policy 0, policy_version 79543 (0.0008) -[2023-10-10 15:47:16,657][76542] Updated weights for policy 1, policy_version 79380 (0.0007) -[2023-10-10 15:47:17,024][76542] Updated weights for policy 1, policy_version 79390 (0.0007) -[2023-10-10 15:47:20,279][76543] Updated weights for policy 0, policy_version 79553 (0.0009) -[2023-10-10 15:47:20,648][76543] Updated weights for policy 0, policy_version 79563 (0.0008) -[2023-10-10 15:47:20,824][76542] Updated weights for policy 1, policy_version 79400 (0.0007) -[2023-10-10 15:47:21,008][76543] Updated weights for policy 0, policy_version 79573 (0.0008) -[2023-10-10 15:47:21,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 162758656. Throughput: 0: 1813.8, 1: 1789.6. Samples: 40700078. Policy #0 lag: (min: 15.0, avg: 17.0, max: 46.0) -[2023-10-10 15:47:21,076][75634] Avg episode reward: [(0, '34.790'), (1, '33.090')] -[2023-10-10 15:47:21,191][76542] Updated weights for policy 1, policy_version 79410 (0.0007) -[2023-10-10 15:47:21,378][76543] Updated weights for policy 0, policy_version 79583 (0.0008) -[2023-10-10 15:47:21,554][76542] Updated weights for policy 1, policy_version 79420 (0.0007) -[2023-10-10 15:47:25,049][76543] Updated weights for policy 0, policy_version 79593 (0.0007) -[2023-10-10 15:47:25,272][76542] Updated weights for policy 1, policy_version 79430 (0.0008) -[2023-10-10 15:47:25,424][76543] Updated weights for policy 0, policy_version 79603 (0.0008) -[2023-10-10 15:47:25,644][76542] Updated weights for policy 1, policy_version 79440 (0.0007) -[2023-10-10 15:47:25,787][76543] Updated weights for policy 0, policy_version 79613 (0.0008) -[2023-10-10 15:47:26,006][76542] Updated weights for policy 1, policy_version 79450 (0.0009) -[2023-10-10 15:47:26,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 162856960. Throughput: 0: 1816.4, 1: 1800.2. Samples: 40722930. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-10 15:47:26,076][75634] Avg episode reward: [(0, '35.760'), (1, '38.200')] -[2023-10-10 15:47:29,310][76543] Updated weights for policy 0, policy_version 79623 (0.0007) -[2023-10-10 15:47:29,681][76543] Updated weights for policy 0, policy_version 79633 (0.0007) -[2023-10-10 15:47:29,760][76542] Updated weights for policy 1, policy_version 79460 (0.0007) -[2023-10-10 15:47:30,058][76543] Updated weights for policy 0, policy_version 79643 (0.0008) -[2023-10-10 15:47:30,114][76542] Updated weights for policy 1, policy_version 79470 (0.0007) -[2023-10-10 15:47:30,485][76542] Updated weights for policy 1, policy_version 79480 (0.0007) -[2023-10-10 15:47:31,076][75634] Fps is (10 sec: 19659.8, 60 sec: 15291.6, 300 sec: 14662.3). Total num frames: 162955264. Throughput: 0: 1818.0, 1: 1793.8. Samples: 40743174. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-10 15:47:31,077][75634] Avg episode reward: [(0, '36.950'), (1, '37.870')] -[2023-10-10 15:47:33,811][76543] Updated weights for policy 0, policy_version 79653 (0.0008) -[2023-10-10 15:47:34,123][76542] Updated weights for policy 1, policy_version 79490 (0.0009) -[2023-10-10 15:47:34,199][76543] Updated weights for policy 0, policy_version 79663 (0.0009) -[2023-10-10 15:47:34,489][76542] Updated weights for policy 1, policy_version 79500 (0.0007) -[2023-10-10 15:47:34,571][76543] Updated weights for policy 0, policy_version 79673 (0.0009) -[2023-10-10 15:47:34,851][76542] Updated weights for policy 1, policy_version 79510 (0.0008) -[2023-10-10 15:47:35,208][76542] Updated weights for policy 1, policy_version 79520 (0.0011) -[2023-10-10 15:47:36,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 163020800. Throughput: 0: 1816.8, 1: 1797.6. Samples: 40755734. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-10 15:47:36,076][75634] Avg episode reward: [(0, '37.860'), (1, '38.440')] -[2023-10-10 15:47:38,186][76543] Updated weights for policy 0, policy_version 79683 (0.0008) -[2023-10-10 15:47:38,544][76543] Updated weights for policy 0, policy_version 79693 (0.0008) -[2023-10-10 15:47:38,916][76543] Updated weights for policy 0, policy_version 79703 (0.0009) -[2023-10-10 15:47:38,979][76542] Updated weights for policy 1, policy_version 79530 (0.0008) -[2023-10-10 15:47:39,351][76542] Updated weights for policy 1, policy_version 79540 (0.0008) -[2023-10-10 15:47:39,717][76542] Updated weights for policy 1, policy_version 79550 (0.0008) -[2023-10-10 15:47:41,076][75634] Fps is (10 sec: 13107.8, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 163086336. Throughput: 0: 1816.3, 1: 1798.8. Samples: 40775576. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-10 15:47:41,077][75634] Avg episode reward: [(0, '38.130'), (1, '33.050')] -[2023-10-10 15:47:42,656][76543] Updated weights for policy 0, policy_version 79713 (0.0010) -[2023-10-10 15:47:43,021][76543] Updated weights for policy 0, policy_version 79723 (0.0009) -[2023-10-10 15:47:43,358][76542] Updated weights for policy 1, policy_version 79560 (0.0009) -[2023-10-10 15:47:43,391][76543] Updated weights for policy 0, policy_version 79733 (0.0008) -[2023-10-10 15:47:43,717][76542] Updated weights for policy 1, policy_version 79570 (0.0009) -[2023-10-10 15:47:43,756][76543] Updated weights for policy 0, policy_version 79743 (0.0009) -[2023-10-10 15:47:44,086][76542] Updated weights for policy 1, policy_version 79580 (0.0009) -[2023-10-10 15:47:46,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 163151872. Throughput: 0: 1822.2, 1: 1799.9. Samples: 40798136. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-10 15:47:46,076][75634] Avg episode reward: [(0, '35.800'), (1, '35.910')] -[2023-10-10 15:47:47,485][76543] Updated weights for policy 0, policy_version 79753 (0.0009) -[2023-10-10 15:47:47,834][76542] Updated weights for policy 1, policy_version 79590 (0.0009) -[2023-10-10 15:47:47,844][76543] Updated weights for policy 0, policy_version 79763 (0.0008) -[2023-10-10 15:47:48,193][76542] Updated weights for policy 1, policy_version 79600 (0.0008) -[2023-10-10 15:47:48,216][76543] Updated weights for policy 0, policy_version 79773 (0.0009) -[2023-10-10 15:47:48,571][76542] Updated weights for policy 1, policy_version 79610 (0.0009) -[2023-10-10 15:47:51,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 163217408. Throughput: 0: 1820.6, 1: 1804.5. Samples: 40808464. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-10 15:47:51,076][75634] Avg episode reward: [(0, '37.030'), (1, '33.420')] -[2023-10-10 15:47:51,887][76543] Updated weights for policy 0, policy_version 79783 (0.0008) -[2023-10-10 15:47:52,169][76542] Updated weights for policy 1, policy_version 79620 (0.0007) -[2023-10-10 15:47:52,260][76543] Updated weights for policy 0, policy_version 79793 (0.0009) -[2023-10-10 15:47:52,533][76542] Updated weights for policy 1, policy_version 79630 (0.0009) -[2023-10-10 15:47:52,630][76543] Updated weights for policy 0, policy_version 79803 (0.0008) -[2023-10-10 15:47:52,907][76542] Updated weights for policy 1, policy_version 79640 (0.0008) -[2023-10-10 15:47:56,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 163282944. Throughput: 0: 1826.4, 1: 1802.9. Samples: 40831056. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-10 15:47:56,076][75634] Avg episode reward: [(0, '35.760'), (1, '36.520')] -[2023-10-10 15:47:56,333][76543] Updated weights for policy 0, policy_version 79813 (0.0008) -[2023-10-10 15:47:56,693][76542] Updated weights for policy 1, policy_version 79650 (0.0008) -[2023-10-10 15:47:56,705][76543] Updated weights for policy 0, policy_version 79823 (0.0008) -[2023-10-10 15:47:57,065][76542] Updated weights for policy 1, policy_version 79660 (0.0009) -[2023-10-10 15:47:57,084][76543] Updated weights for policy 0, policy_version 79833 (0.0008) -[2023-10-10 15:47:57,424][76542] Updated weights for policy 1, policy_version 79670 (0.0009) -[2023-10-10 15:47:57,797][76542] Updated weights for policy 1, policy_version 79680 (0.0008) -[2023-10-10 15:48:00,728][76543] Updated weights for policy 0, policy_version 79843 (0.0009) -[2023-10-10 15:48:01,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 163348480. Throughput: 0: 1821.2, 1: 1804.3. Samples: 40853694. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-10 15:48:01,076][75634] Avg episode reward: [(0, '36.520'), (1, '36.820')] -[2023-10-10 15:48:01,100][76543] Updated weights for policy 0, policy_version 79853 (0.0011) -[2023-10-10 15:48:01,470][76543] Updated weights for policy 0, policy_version 79863 (0.0008) -[2023-10-10 15:48:01,661][76542] Updated weights for policy 1, policy_version 79690 (0.0007) -[2023-10-10 15:48:02,026][76542] Updated weights for policy 1, policy_version 79700 (0.0007) -[2023-10-10 15:48:02,402][76542] Updated weights for policy 1, policy_version 79710 (0.0008) -[2023-10-10 15:48:05,167][76543] Updated weights for policy 0, policy_version 79873 (0.0009) -[2023-10-10 15:48:05,532][76543] Updated weights for policy 0, policy_version 79883 (0.0009) -[2023-10-10 15:48:05,908][76543] Updated weights for policy 0, policy_version 79893 (0.0007) -[2023-10-10 15:48:06,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 163414016. Throughput: 0: 1827.2, 1: 1802.9. Samples: 40863430. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-10 15:48:06,076][75634] Avg episode reward: [(0, '36.110'), (1, '36.870')] -[2023-10-10 15:48:06,172][76542] Updated weights for policy 1, policy_version 79720 (0.0009) -[2023-10-10 15:48:06,270][76543] Updated weights for policy 0, policy_version 79903 (0.0008) -[2023-10-10 15:48:06,552][76542] Updated weights for policy 1, policy_version 79730 (0.0009) -[2023-10-10 15:48:06,917][76542] Updated weights for policy 1, policy_version 79740 (0.0007) -[2023-10-10 15:48:09,942][76543] Updated weights for policy 0, policy_version 79913 (0.0009) -[2023-10-10 15:48:10,321][76543] Updated weights for policy 0, policy_version 79923 (0.0009) -[2023-10-10 15:48:10,496][76542] Updated weights for policy 1, policy_version 79750 (0.0007) -[2023-10-10 15:48:10,684][76543] Updated weights for policy 0, policy_version 79933 (0.0008) -[2023-10-10 15:48:10,861][76542] Updated weights for policy 1, policy_version 79760 (0.0010) -[2023-10-10 15:48:11,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 163512320. Throughput: 0: 1823.1, 1: 1804.3. Samples: 40886164. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-10 15:48:11,077][75634] Avg episode reward: [(0, '38.170'), (1, '35.770')] -[2023-10-10 15:48:11,225][76542] Updated weights for policy 1, policy_version 79770 (0.0010) -[2023-10-10 15:48:14,332][76543] Updated weights for policy 0, policy_version 79943 (0.0008) -[2023-10-10 15:48:14,709][76543] Updated weights for policy 0, policy_version 79953 (0.0009) -[2023-10-10 15:48:14,965][76542] Updated weights for policy 1, policy_version 79780 (0.0009) -[2023-10-10 15:48:15,075][76543] Updated weights for policy 0, policy_version 79963 (0.0008) -[2023-10-10 15:48:15,329][76542] Updated weights for policy 1, policy_version 79790 (0.0010) -[2023-10-10 15:48:15,685][76542] Updated weights for policy 1, policy_version 79800 (0.0010) -[2023-10-10 15:48:16,076][75634] Fps is (10 sec: 19660.4, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 163610624. Throughput: 0: 1819.7, 1: 1809.3. Samples: 40906476. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-10 15:48:16,077][75634] Avg episode reward: [(0, '36.380'), (1, '35.130')] -[2023-10-10 15:48:18,728][76543] Updated weights for policy 0, policy_version 79973 (0.0007) -[2023-10-10 15:48:19,096][76543] Updated weights for policy 0, policy_version 79983 (0.0009) -[2023-10-10 15:48:19,239][76542] Updated weights for policy 1, policy_version 79810 (0.0010) -[2023-10-10 15:48:19,469][76543] Updated weights for policy 0, policy_version 79993 (0.0008) -[2023-10-10 15:48:19,611][76542] Updated weights for policy 1, policy_version 79820 (0.0008) -[2023-10-10 15:48:19,972][76542] Updated weights for policy 1, policy_version 79830 (0.0008) -[2023-10-10 15:48:20,336][76542] Updated weights for policy 1, policy_version 79840 (0.0008) -[2023-10-10 15:48:21,076][75634] Fps is (10 sec: 16383.9, 60 sec: 15291.7, 300 sec: 14551.2). Total num frames: 163676160. Throughput: 0: 1823.6, 1: 1810.7. Samples: 40919278. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 15:48:21,077][75634] Avg episode reward: [(0, '35.090'), (1, '37.840')] -[2023-10-10 15:48:23,191][76543] Updated weights for policy 0, policy_version 80003 (0.0008) -[2023-10-10 15:48:23,565][76543] Updated weights for policy 0, policy_version 80013 (0.0007) -[2023-10-10 15:48:23,936][76543] Updated weights for policy 0, policy_version 80023 (0.0007) -[2023-10-10 15:48:24,197][76542] Updated weights for policy 1, policy_version 79850 (0.0009) -[2023-10-10 15:48:24,567][76542] Updated weights for policy 1, policy_version 79860 (0.0007) -[2023-10-10 15:48:24,936][76542] Updated weights for policy 1, policy_version 79870 (0.0008) -[2023-10-10 15:48:26,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 163741696. Throughput: 0: 1827.4, 1: 1816.8. Samples: 40939564. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 15:48:26,077][75634] Avg episode reward: [(0, '30.550'), (1, '37.720')] -[2023-10-10 15:48:27,504][76543] Updated weights for policy 0, policy_version 80033 (0.0008) -[2023-10-10 15:48:27,861][76543] Updated weights for policy 0, policy_version 80043 (0.0007) -[2023-10-10 15:48:28,229][76543] Updated weights for policy 0, policy_version 80053 (0.0008) -[2023-10-10 15:48:28,552][76542] Updated weights for policy 1, policy_version 79880 (0.0008) -[2023-10-10 15:48:28,607][76543] Updated weights for policy 0, policy_version 80063 (0.0008) -[2023-10-10 15:48:28,927][76542] Updated weights for policy 1, policy_version 79890 (0.0007) -[2023-10-10 15:48:29,293][76542] Updated weights for policy 1, policy_version 79900 (0.0009) -[2023-10-10 15:48:31,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 163807232. Throughput: 0: 1830.1, 1: 1809.3. Samples: 40961910. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 15:48:31,077][75634] Avg episode reward: [(0, '34.060'), (1, '32.550')] -[2023-10-10 15:48:31,089][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000080064_81985536.pth... -[2023-10-10 15:48:31,089][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000079904_81821696.pth... -[2023-10-10 15:48:31,120][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000078208_80084992.pth -[2023-10-10 15:48:31,121][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000078368_80248832.pth -[2023-10-10 15:48:32,341][76543] Updated weights for policy 0, policy_version 80073 (0.0008) -[2023-10-10 15:48:32,696][76543] Updated weights for policy 0, policy_version 80083 (0.0008) -[2023-10-10 15:48:32,849][76542] Updated weights for policy 1, policy_version 79910 (0.0009) -[2023-10-10 15:48:33,068][76543] Updated weights for policy 0, policy_version 80093 (0.0007) -[2023-10-10 15:48:33,224][76542] Updated weights for policy 1, policy_version 79920 (0.0008) -[2023-10-10 15:48:33,594][76542] Updated weights for policy 1, policy_version 79930 (0.0010) -[2023-10-10 15:48:36,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 163872768. Throughput: 0: 1821.2, 1: 1814.3. Samples: 40972064. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 15:48:36,077][75634] Avg episode reward: [(0, '33.450'), (1, '36.070')] -[2023-10-10 15:48:36,744][76543] Updated weights for policy 0, policy_version 80103 (0.0009) -[2023-10-10 15:48:37,121][76543] Updated weights for policy 0, policy_version 80113 (0.0009) -[2023-10-10 15:48:37,273][76542] Updated weights for policy 1, policy_version 79940 (0.0009) -[2023-10-10 15:48:37,481][76543] Updated weights for policy 0, policy_version 80123 (0.0008) -[2023-10-10 15:48:37,636][76542] Updated weights for policy 1, policy_version 79950 (0.0009) -[2023-10-10 15:48:38,006][76542] Updated weights for policy 1, policy_version 79960 (0.0008) -[2023-10-10 15:48:41,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 163938304. Throughput: 0: 1827.2, 1: 1814.2. Samples: 40994918. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 15:48:41,076][75634] Avg episode reward: [(0, '34.630'), (1, '37.840')] -[2023-10-10 15:48:41,254][76543] Updated weights for policy 0, policy_version 80133 (0.0007) -[2023-10-10 15:48:41,629][76543] Updated weights for policy 0, policy_version 80143 (0.0007) -[2023-10-10 15:48:41,724][76542] Updated weights for policy 1, policy_version 79970 (0.0007) -[2023-10-10 15:48:41,993][76543] Updated weights for policy 0, policy_version 80153 (0.0007) -[2023-10-10 15:48:42,096][76542] Updated weights for policy 1, policy_version 79980 (0.0008) -[2023-10-10 15:48:42,451][76542] Updated weights for policy 1, policy_version 79990 (0.0007) -[2023-10-10 15:48:42,828][76542] Updated weights for policy 1, policy_version 80000 (0.0009) -[2023-10-10 15:48:45,670][76543] Updated weights for policy 0, policy_version 80163 (0.0008) -[2023-10-10 15:48:46,037][76543] Updated weights for policy 0, policy_version 80173 (0.0007) -[2023-10-10 15:48:46,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 164003840. Throughput: 0: 1825.6, 1: 1820.1. Samples: 41017750. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 15:48:46,076][75634] Avg episode reward: [(0, '35.120'), (1, '37.580')] -[2023-10-10 15:48:46,390][76542] Updated weights for policy 1, policy_version 80010 (0.0009) -[2023-10-10 15:48:46,410][76543] Updated weights for policy 0, policy_version 80183 (0.0008) -[2023-10-10 15:48:46,748][76542] Updated weights for policy 1, policy_version 80020 (0.0008) -[2023-10-10 15:48:47,118][76542] Updated weights for policy 1, policy_version 80030 (0.0007) -[2023-10-10 15:48:50,115][76543] Updated weights for policy 0, policy_version 80193 (0.0008) -[2023-10-10 15:48:50,492][76543] Updated weights for policy 0, policy_version 80203 (0.0009) -[2023-10-10 15:48:50,851][76543] Updated weights for policy 0, policy_version 80213 (0.0008) -[2023-10-10 15:48:50,941][76542] Updated weights for policy 1, policy_version 80040 (0.0008) -[2023-10-10 15:48:51,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 164069376. Throughput: 0: 1821.3, 1: 1820.6. Samples: 41027314. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 15:48:51,076][75634] Avg episode reward: [(0, '34.260'), (1, '34.680')] -[2023-10-10 15:48:51,219][76543] Updated weights for policy 0, policy_version 80223 (0.0007) -[2023-10-10 15:48:51,317][76542] Updated weights for policy 1, policy_version 80050 (0.0008) -[2023-10-10 15:48:51,672][76542] Updated weights for policy 1, policy_version 80060 (0.0012) -[2023-10-10 15:48:54,700][76543] Updated weights for policy 0, policy_version 80233 (0.0008) -[2023-10-10 15:48:55,069][76543] Updated weights for policy 0, policy_version 80243 (0.0008) -[2023-10-10 15:48:55,441][76543] Updated weights for policy 0, policy_version 80253 (0.0008) -[2023-10-10 15:48:55,451][76542] Updated weights for policy 1, policy_version 80070 (0.0009) -[2023-10-10 15:48:55,817][76542] Updated weights for policy 1, policy_version 80080 (0.0007) -[2023-10-10 15:48:56,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 164167680. Throughput: 0: 1823.1, 1: 1815.7. Samples: 41049910. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 15:48:56,077][75634] Avg episode reward: [(0, '33.980'), (1, '33.290')] -[2023-10-10 15:48:56,187][76542] Updated weights for policy 1, policy_version 80090 (0.0008) -[2023-10-10 15:48:59,213][76543] Updated weights for policy 0, policy_version 80263 (0.0008) -[2023-10-10 15:48:59,588][76543] Updated weights for policy 0, policy_version 80273 (0.0009) -[2023-10-10 15:48:59,729][76542] Updated weights for policy 1, policy_version 80100 (0.0009) -[2023-10-10 15:48:59,955][76543] Updated weights for policy 0, policy_version 80283 (0.0010) -[2023-10-10 15:49:00,092][76542] Updated weights for policy 1, policy_version 80110 (0.0010) -[2023-10-10 15:49:00,452][76542] Updated weights for policy 1, policy_version 80120 (0.0007) -[2023-10-10 15:49:01,076][75634] Fps is (10 sec: 19660.8, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 164265984. Throughput: 0: 1821.4, 1: 1814.2. Samples: 41070076. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 15:49:01,076][75634] Avg episode reward: [(0, '40.740'), (1, '35.220')] -[2023-10-10 15:49:03,597][76543] Updated weights for policy 0, policy_version 80293 (0.0008) -[2023-10-10 15:49:03,982][76543] Updated weights for policy 0, policy_version 80303 (0.0011) -[2023-10-10 15:49:04,241][76542] Updated weights for policy 1, policy_version 80130 (0.0009) -[2023-10-10 15:49:04,357][76543] Updated weights for policy 0, policy_version 80313 (0.0007) -[2023-10-10 15:49:04,601][76542] Updated weights for policy 1, policy_version 80140 (0.0007) -[2023-10-10 15:49:04,967][76542] Updated weights for policy 1, policy_version 80150 (0.0007) -[2023-10-10 15:49:05,329][76542] Updated weights for policy 1, policy_version 80160 (0.0010) -[2023-10-10 15:49:06,076][75634] Fps is (10 sec: 16384.3, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 164331520. Throughput: 0: 1823.0, 1: 1815.0. Samples: 41082990. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 15:49:06,076][75634] Avg episode reward: [(0, '38.820'), (1, '35.670')] -[2023-10-10 15:49:08,056][76543] Updated weights for policy 0, policy_version 80323 (0.0008) -[2023-10-10 15:49:08,424][76543] Updated weights for policy 0, policy_version 80333 (0.0008) -[2023-10-10 15:49:08,789][76543] Updated weights for policy 0, policy_version 80343 (0.0008) -[2023-10-10 15:49:09,086][76542] Updated weights for policy 1, policy_version 80170 (0.0008) -[2023-10-10 15:49:09,451][76542] Updated weights for policy 1, policy_version 80180 (0.0008) -[2023-10-10 15:49:09,821][76542] Updated weights for policy 1, policy_version 80190 (0.0008) -[2023-10-10 15:49:11,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 164397056. Throughput: 0: 1818.0, 1: 1811.2. Samples: 41102874. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:49:11,076][75634] Avg episode reward: [(0, '37.940'), (1, '31.570')] -[2023-10-10 15:49:12,500][76543] Updated weights for policy 0, policy_version 80353 (0.0008) -[2023-10-10 15:49:12,868][76543] Updated weights for policy 0, policy_version 80363 (0.0011) -[2023-10-10 15:49:13,239][76543] Updated weights for policy 0, policy_version 80373 (0.0007) -[2023-10-10 15:49:13,463][76542] Updated weights for policy 1, policy_version 80200 (0.0008) -[2023-10-10 15:49:13,604][76543] Updated weights for policy 0, policy_version 80383 (0.0008) -[2023-10-10 15:49:13,838][76542] Updated weights for policy 1, policy_version 80210 (0.0007) -[2023-10-10 15:49:14,207][76542] Updated weights for policy 1, policy_version 80220 (0.0008) -[2023-10-10 15:49:16,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 164462592. Throughput: 0: 1819.1, 1: 1816.4. Samples: 41125506. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:49:16,077][75634] Avg episode reward: [(0, '40.560'), (1, '32.360')] -[2023-10-10 15:49:17,359][76543] Updated weights for policy 0, policy_version 80393 (0.0007) -[2023-10-10 15:49:17,735][76543] Updated weights for policy 0, policy_version 80403 (0.0009) -[2023-10-10 15:49:17,951][76542] Updated weights for policy 1, policy_version 80230 (0.0009) -[2023-10-10 15:49:18,100][76543] Updated weights for policy 0, policy_version 80413 (0.0008) -[2023-10-10 15:49:18,315][76542] Updated weights for policy 1, policy_version 80240 (0.0009) -[2023-10-10 15:49:18,677][76542] Updated weights for policy 1, policy_version 80250 (0.0007) -[2023-10-10 15:49:21,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 164528128. Throughput: 0: 1824.8, 1: 1811.1. Samples: 41135678. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:49:21,077][75634] Avg episode reward: [(0, '43.380'), (1, '36.600')] -[2023-10-10 15:49:21,777][76543] Updated weights for policy 0, policy_version 80423 (0.0008) -[2023-10-10 15:49:22,156][76543] Updated weights for policy 0, policy_version 80433 (0.0009) -[2023-10-10 15:49:22,424][76542] Updated weights for policy 1, policy_version 80260 (0.0009) -[2023-10-10 15:49:22,518][76543] Updated weights for policy 0, policy_version 80443 (0.0007) -[2023-10-10 15:49:22,790][76542] Updated weights for policy 1, policy_version 80270 (0.0009) -[2023-10-10 15:49:23,165][76542] Updated weights for policy 1, policy_version 80280 (0.0010) -[2023-10-10 15:49:26,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.2). Total num frames: 164593664. Throughput: 0: 1817.6, 1: 1809.8. Samples: 41158148. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:49:26,076][75634] Avg episode reward: [(0, '44.870'), (1, '34.270')] -[2023-10-10 15:49:26,337][76543] Updated weights for policy 0, policy_version 80453 (0.0008) -[2023-10-10 15:49:26,703][76543] Updated weights for policy 0, policy_version 80463 (0.0007) -[2023-10-10 15:49:26,731][76542] Updated weights for policy 1, policy_version 80290 (0.0010) -[2023-10-10 15:49:27,070][76543] Updated weights for policy 0, policy_version 80473 (0.0007) -[2023-10-10 15:49:27,105][76542] Updated weights for policy 1, policy_version 80300 (0.0009) -[2023-10-10 15:49:27,321][76362] Saving new best policy, reward=44.870! -[2023-10-10 15:49:27,463][76542] Updated weights for policy 1, policy_version 80310 (0.0008) -[2023-10-10 15:49:27,827][76542] Updated weights for policy 1, policy_version 80320 (0.0009) -[2023-10-10 15:49:31,013][76543] Updated weights for policy 0, policy_version 80483 (0.0009) -[2023-10-10 15:49:31,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 164659200. Throughput: 0: 1817.6, 1: 1809.0. Samples: 41180948. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:49:31,076][75634] Avg episode reward: [(0, '43.200'), (1, '34.980')] -[2023-10-10 15:49:31,379][76543] Updated weights for policy 0, policy_version 80493 (0.0007) -[2023-10-10 15:49:31,687][76542] Updated weights for policy 1, policy_version 80330 (0.0007) -[2023-10-10 15:49:31,748][76543] Updated weights for policy 0, policy_version 80503 (0.0007) -[2023-10-10 15:49:32,048][76542] Updated weights for policy 1, policy_version 80340 (0.0007) -[2023-10-10 15:49:32,422][76542] Updated weights for policy 1, policy_version 80350 (0.0007) -[2023-10-10 15:49:35,383][76543] Updated weights for policy 0, policy_version 80513 (0.0009) -[2023-10-10 15:49:35,754][76543] Updated weights for policy 0, policy_version 80523 (0.0008) -[2023-10-10 15:49:36,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 164724736. Throughput: 0: 1819.2, 1: 1811.5. Samples: 41190696. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:49:36,077][75634] Avg episode reward: [(0, '36.000'), (1, '36.660')] -[2023-10-10 15:49:36,115][76543] Updated weights for policy 0, policy_version 80533 (0.0007) -[2023-10-10 15:49:36,137][76542] Updated weights for policy 1, policy_version 80360 (0.0008) -[2023-10-10 15:49:36,486][76543] Updated weights for policy 0, policy_version 80543 (0.0008) -[2023-10-10 15:49:36,514][76542] Updated weights for policy 1, policy_version 80370 (0.0008) -[2023-10-10 15:49:36,876][76542] Updated weights for policy 1, policy_version 80380 (0.0010) -[2023-10-10 15:49:40,019][76543] Updated weights for policy 0, policy_version 80553 (0.0010) -[2023-10-10 15:49:40,385][76543] Updated weights for policy 0, policy_version 80563 (0.0010) -[2023-10-10 15:49:40,557][76542] Updated weights for policy 1, policy_version 80390 (0.0008) -[2023-10-10 15:49:40,756][76543] Updated weights for policy 0, policy_version 80573 (0.0009) -[2023-10-10 15:49:40,926][76542] Updated weights for policy 1, policy_version 80400 (0.0008) -[2023-10-10 15:49:41,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 164823040. Throughput: 0: 1823.2, 1: 1813.2. Samples: 41213544. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:49:41,077][75634] Avg episode reward: [(0, '37.470'), (1, '35.580')] -[2023-10-10 15:49:41,302][76542] Updated weights for policy 1, policy_version 80410 (0.0009) -[2023-10-10 15:49:44,332][76543] Updated weights for policy 0, policy_version 80583 (0.0008) -[2023-10-10 15:49:44,702][76543] Updated weights for policy 0, policy_version 80593 (0.0009) -[2023-10-10 15:49:45,072][76543] Updated weights for policy 0, policy_version 80603 (0.0010) -[2023-10-10 15:49:45,171][76542] Updated weights for policy 1, policy_version 80420 (0.0008) -[2023-10-10 15:49:45,542][76542] Updated weights for policy 1, policy_version 80430 (0.0007) -[2023-10-10 15:49:45,907][76542] Updated weights for policy 1, policy_version 80440 (0.0009) -[2023-10-10 15:49:46,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 164888576. Throughput: 0: 1821.3, 1: 1822.5. Samples: 41234048. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:49:46,076][75634] Avg episode reward: [(0, '36.280'), (1, '39.170')] -[2023-10-10 15:49:48,979][76543] Updated weights for policy 0, policy_version 80613 (0.0009) -[2023-10-10 15:49:49,364][76543] Updated weights for policy 0, policy_version 80623 (0.0011) -[2023-10-10 15:49:49,698][76542] Updated weights for policy 1, policy_version 80450 (0.0008) -[2023-10-10 15:49:49,731][76543] Updated weights for policy 0, policy_version 80633 (0.0009) -[2023-10-10 15:49:50,060][76542] Updated weights for policy 1, policy_version 80460 (0.0009) -[2023-10-10 15:49:50,435][76542] Updated weights for policy 1, policy_version 80470 (0.0008) -[2023-10-10 15:49:50,801][76542] Updated weights for policy 1, policy_version 80480 (0.0007) -[2023-10-10 15:49:51,076][75634] Fps is (10 sec: 16384.0, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 164986880. Throughput: 0: 1812.5, 1: 1804.6. Samples: 41245760. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:49:51,077][75634] Avg episode reward: [(0, '35.440'), (1, '34.870')] -[2023-10-10 15:49:53,397][76543] Updated weights for policy 0, policy_version 80643 (0.0009) -[2023-10-10 15:49:53,774][76543] Updated weights for policy 0, policy_version 80653 (0.0008) -[2023-10-10 15:49:54,140][76543] Updated weights for policy 0, policy_version 80663 (0.0009) -[2023-10-10 15:49:54,424][76542] Updated weights for policy 1, policy_version 80490 (0.0009) -[2023-10-10 15:49:54,797][76542] Updated weights for policy 1, policy_version 80500 (0.0008) -[2023-10-10 15:49:55,167][76542] Updated weights for policy 1, policy_version 80510 (0.0008) -[2023-10-10 15:49:56,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 165052416. Throughput: 0: 1819.3, 1: 1818.5. Samples: 41266576. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:49:56,077][75634] Avg episode reward: [(0, '34.010'), (1, '36.050')] -[2023-10-10 15:49:57,843][76543] Updated weights for policy 0, policy_version 80673 (0.0007) -[2023-10-10 15:49:58,217][76543] Updated weights for policy 0, policy_version 80683 (0.0009) -[2023-10-10 15:49:58,586][76543] Updated weights for policy 0, policy_version 80693 (0.0010) -[2023-10-10 15:49:58,912][76542] Updated weights for policy 1, policy_version 80520 (0.0009) -[2023-10-10 15:49:58,951][76543] Updated weights for policy 0, policy_version 80703 (0.0008) -[2023-10-10 15:49:59,277][76542] Updated weights for policy 1, policy_version 80530 (0.0009) -[2023-10-10 15:49:59,644][76542] Updated weights for policy 1, policy_version 80540 (0.0007) -[2023-10-10 15:50:01,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 165117952. Throughput: 0: 1815.1, 1: 1806.0. Samples: 41288454. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:50:01,076][75634] Avg episode reward: [(0, '33.110'), (1, '33.770')] -[2023-10-10 15:50:02,393][76543] Updated weights for policy 0, policy_version 80713 (0.0007) -[2023-10-10 15:50:02,764][76543] Updated weights for policy 0, policy_version 80723 (0.0007) -[2023-10-10 15:50:03,138][76543] Updated weights for policy 0, policy_version 80733 (0.0008) -[2023-10-10 15:50:03,510][76542] Updated weights for policy 1, policy_version 80550 (0.0007) -[2023-10-10 15:50:03,873][76542] Updated weights for policy 1, policy_version 80560 (0.0009) -[2023-10-10 15:50:04,243][76542] Updated weights for policy 1, policy_version 80570 (0.0009) -[2023-10-10 15:50:06,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 165183488. Throughput: 0: 1821.6, 1: 1822.8. Samples: 41299676. Policy #0 lag: (min: 1.0, avg: 15.4, max: 33.0) -[2023-10-10 15:50:06,077][75634] Avg episode reward: [(0, '33.930'), (1, '34.720')] -[2023-10-10 15:50:06,900][76543] Updated weights for policy 0, policy_version 80743 (0.0007) -[2023-10-10 15:50:07,265][76543] Updated weights for policy 0, policy_version 80753 (0.0008) -[2023-10-10 15:50:07,639][76543] Updated weights for policy 0, policy_version 80763 (0.0007) -[2023-10-10 15:50:07,913][76542] Updated weights for policy 1, policy_version 80580 (0.0009) -[2023-10-10 15:50:08,274][76542] Updated weights for policy 1, policy_version 80590 (0.0010) -[2023-10-10 15:50:08,643][76542] Updated weights for policy 1, policy_version 80600 (0.0010) -[2023-10-10 15:50:11,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 165249024. Throughput: 0: 1822.8, 1: 1810.6. Samples: 41321654. Policy #0 lag: (min: 1.0, avg: 15.4, max: 33.0) -[2023-10-10 15:50:11,076][75634] Avg episode reward: [(0, '33.100'), (1, '32.980')] -[2023-10-10 15:50:11,342][76543] Updated weights for policy 0, policy_version 80773 (0.0008) -[2023-10-10 15:50:11,714][76543] Updated weights for policy 0, policy_version 80783 (0.0008) -[2023-10-10 15:50:12,084][76543] Updated weights for policy 0, policy_version 80793 (0.0008) -[2023-10-10 15:50:12,315][76542] Updated weights for policy 1, policy_version 80610 (0.0010) -[2023-10-10 15:50:12,688][76542] Updated weights for policy 1, policy_version 80620 (0.0007) -[2023-10-10 15:50:13,049][76542] Updated weights for policy 1, policy_version 80630 (0.0008) -[2023-10-10 15:50:13,422][76542] Updated weights for policy 1, policy_version 80640 (0.0008) -[2023-10-10 15:50:15,702][76543] Updated weights for policy 0, policy_version 80803 (0.0008) -[2023-10-10 15:50:16,070][76543] Updated weights for policy 0, policy_version 80813 (0.0010) -[2023-10-10 15:50:16,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 165314560. Throughput: 0: 1826.0, 1: 1810.5. Samples: 41344588. Policy #0 lag: (min: 1.0, avg: 15.4, max: 33.0) -[2023-10-10 15:50:16,076][75634] Avg episode reward: [(0, '32.330'), (1, '31.360')] -[2023-10-10 15:50:16,444][76543] Updated weights for policy 0, policy_version 80823 (0.0007) -[2023-10-10 15:50:17,136][76542] Updated weights for policy 1, policy_version 80650 (0.0011) -[2023-10-10 15:50:17,497][76542] Updated weights for policy 1, policy_version 80660 (0.0012) -[2023-10-10 15:50:17,876][76542] Updated weights for policy 1, policy_version 80670 (0.0008) -[2023-10-10 15:50:20,048][76543] Updated weights for policy 0, policy_version 80833 (0.0007) -[2023-10-10 15:50:20,421][76543] Updated weights for policy 0, policy_version 80843 (0.0010) -[2023-10-10 15:50:20,783][76543] Updated weights for policy 0, policy_version 80853 (0.0011) -[2023-10-10 15:50:21,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 165380096. Throughput: 0: 1829.3, 1: 1809.4. Samples: 41354440. Policy #0 lag: (min: 1.0, avg: 15.4, max: 33.0) -[2023-10-10 15:50:21,077][75634] Avg episode reward: [(0, '32.160'), (1, '33.210')] -[2023-10-10 15:50:21,156][76543] Updated weights for policy 0, policy_version 80863 (0.0011) -[2023-10-10 15:50:21,586][76542] Updated weights for policy 1, policy_version 80680 (0.0008) -[2023-10-10 15:50:21,956][76542] Updated weights for policy 1, policy_version 80690 (0.0007) -[2023-10-10 15:50:22,333][76542] Updated weights for policy 1, policy_version 80700 (0.0010) -[2023-10-10 15:50:24,818][76543] Updated weights for policy 0, policy_version 80873 (0.0010) -[2023-10-10 15:50:25,184][76543] Updated weights for policy 0, policy_version 80883 (0.0008) -[2023-10-10 15:50:25,553][76543] Updated weights for policy 0, policy_version 80893 (0.0009) -[2023-10-10 15:50:25,900][76542] Updated weights for policy 1, policy_version 80710 (0.0008) -[2023-10-10 15:50:26,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 165478400. Throughput: 0: 1826.9, 1: 1817.8. Samples: 41377558. Policy #0 lag: (min: 1.0, avg: 15.4, max: 33.0) -[2023-10-10 15:50:26,076][75634] Avg episode reward: [(0, '35.080'), (1, '35.670')] -[2023-10-10 15:50:26,269][76542] Updated weights for policy 1, policy_version 80720 (0.0010) -[2023-10-10 15:50:26,631][76542] Updated weights for policy 1, policy_version 80730 (0.0008) -[2023-10-10 15:50:29,098][76543] Updated weights for policy 0, policy_version 80903 (0.0010) -[2023-10-10 15:50:29,469][76543] Updated weights for policy 0, policy_version 80913 (0.0010) -[2023-10-10 15:50:29,829][76543] Updated weights for policy 0, policy_version 80923 (0.0009) -[2023-10-10 15:50:30,239][76542] Updated weights for policy 1, policy_version 80740 (0.0009) -[2023-10-10 15:50:30,610][76542] Updated weights for policy 1, policy_version 80750 (0.0010) -[2023-10-10 15:50:30,970][76542] Updated weights for policy 1, policy_version 80760 (0.0010) -[2023-10-10 15:50:31,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 165543936. Throughput: 0: 1830.3, 1: 1819.2. Samples: 41398274. Policy #0 lag: (min: 1.0, avg: 15.4, max: 33.0) -[2023-10-10 15:50:31,076][75634] Avg episode reward: [(0, '35.940'), (1, '40.050')] -[2023-10-10 15:50:31,085][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000080928_82870272.pth... -[2023-10-10 15:50:31,119][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000079232_81133568.pth -[2023-10-10 15:50:31,272][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000080768_82706432.pth... -[2023-10-10 15:50:31,311][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000079072_80969728.pth -[2023-10-10 15:50:33,448][76543] Updated weights for policy 0, policy_version 80933 (0.0008) -[2023-10-10 15:50:33,834][76543] Updated weights for policy 0, policy_version 80943 (0.0007) -[2023-10-10 15:50:34,219][76543] Updated weights for policy 0, policy_version 80953 (0.0007) -[2023-10-10 15:50:34,659][76542] Updated weights for policy 1, policy_version 80770 (0.0010) -[2023-10-10 15:50:35,038][76542] Updated weights for policy 1, policy_version 80780 (0.0010) -[2023-10-10 15:50:35,393][76542] Updated weights for policy 1, policy_version 80790 (0.0010) -[2023-10-10 15:50:35,763][76542] Updated weights for policy 1, policy_version 80800 (0.0009) -[2023-10-10 15:50:36,076][75634] Fps is (10 sec: 16383.6, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 165642240. Throughput: 0: 1837.1, 1: 1824.5. Samples: 41410532. Policy #0 lag: (min: 1.0, avg: 15.4, max: 33.0) -[2023-10-10 15:50:36,077][75634] Avg episode reward: [(0, '37.200'), (1, '36.950')] -[2023-10-10 15:50:37,819][76543] Updated weights for policy 0, policy_version 80963 (0.0010) -[2023-10-10 15:50:38,193][76543] Updated weights for policy 0, policy_version 80973 (0.0009) -[2023-10-10 15:50:38,552][76543] Updated weights for policy 0, policy_version 80983 (0.0008) -[2023-10-10 15:50:39,632][76542] Updated weights for policy 1, policy_version 80810 (0.0012) -[2023-10-10 15:50:39,997][76542] Updated weights for policy 1, policy_version 80820 (0.0009) -[2023-10-10 15:50:40,360][76542] Updated weights for policy 1, policy_version 80830 (0.0010) -[2023-10-10 15:50:41,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 165707776. Throughput: 0: 1833.0, 1: 1825.5. Samples: 41431206. Policy #0 lag: (min: 1.0, avg: 15.4, max: 33.0) -[2023-10-10 15:50:41,076][75634] Avg episode reward: [(0, '34.670'), (1, '36.600')] -[2023-10-10 15:50:42,257][76543] Updated weights for policy 0, policy_version 80993 (0.0010) -[2023-10-10 15:50:42,630][76543] Updated weights for policy 0, policy_version 81003 (0.0011) -[2023-10-10 15:50:43,007][76543] Updated weights for policy 0, policy_version 81013 (0.0011) -[2023-10-10 15:50:43,376][76543] Updated weights for policy 0, policy_version 81023 (0.0008) -[2023-10-10 15:50:43,951][76542] Updated weights for policy 1, policy_version 80840 (0.0011) -[2023-10-10 15:50:44,316][76542] Updated weights for policy 1, policy_version 80850 (0.0009) -[2023-10-10 15:50:44,680][76542] Updated weights for policy 1, policy_version 80860 (0.0011) -[2023-10-10 15:50:46,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 165773312. Throughput: 0: 1839.3, 1: 1822.9. Samples: 41453256. Policy #0 lag: (min: 1.0, avg: 15.4, max: 33.0) -[2023-10-10 15:50:46,077][75634] Avg episode reward: [(0, '37.640'), (1, '37.920')] -[2023-10-10 15:50:46,964][76543] Updated weights for policy 0, policy_version 81033 (0.0008) -[2023-10-10 15:50:47,338][76543] Updated weights for policy 0, policy_version 81043 (0.0011) -[2023-10-10 15:50:47,712][76543] Updated weights for policy 0, policy_version 81053 (0.0011) -[2023-10-10 15:50:48,341][76542] Updated weights for policy 1, policy_version 80870 (0.0009) -[2023-10-10 15:50:48,720][76542] Updated weights for policy 1, policy_version 80880 (0.0010) -[2023-10-10 15:50:49,092][76542] Updated weights for policy 1, policy_version 80890 (0.0008) -[2023-10-10 15:50:51,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 165838848. Throughput: 0: 1835.6, 1: 1819.0. Samples: 41464134. Policy #0 lag: (min: 1.0, avg: 15.4, max: 33.0) -[2023-10-10 15:50:51,077][75634] Avg episode reward: [(0, '35.790'), (1, '38.500')] -[2023-10-10 15:50:51,366][76543] Updated weights for policy 0, policy_version 81063 (0.0008) -[2023-10-10 15:50:51,734][76543] Updated weights for policy 0, policy_version 81073 (0.0009) -[2023-10-10 15:50:52,103][76543] Updated weights for policy 0, policy_version 81083 (0.0007) -[2023-10-10 15:50:52,774][76542] Updated weights for policy 1, policy_version 80900 (0.0009) -[2023-10-10 15:50:53,140][76542] Updated weights for policy 1, policy_version 80910 (0.0010) -[2023-10-10 15:50:53,503][76542] Updated weights for policy 1, policy_version 80920 (0.0011) -[2023-10-10 15:50:55,860][76543] Updated weights for policy 0, policy_version 81093 (0.0008) -[2023-10-10 15:50:56,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 165904384. Throughput: 0: 1838.0, 1: 1815.9. Samples: 41486078. Policy #0 lag: (min: 1.0, avg: 15.4, max: 33.0) -[2023-10-10 15:50:56,077][75634] Avg episode reward: [(0, '33.730'), (1, '32.920')] -[2023-10-10 15:50:56,226][76543] Updated weights for policy 0, policy_version 81103 (0.0008) -[2023-10-10 15:50:56,596][76543] Updated weights for policy 0, policy_version 81113 (0.0008) -[2023-10-10 15:50:57,113][76542] Updated weights for policy 1, policy_version 80930 (0.0010) -[2023-10-10 15:50:57,481][76542] Updated weights for policy 1, policy_version 80940 (0.0007) -[2023-10-10 15:50:57,851][76542] Updated weights for policy 1, policy_version 80950 (0.0009) -[2023-10-10 15:50:58,218][76542] Updated weights for policy 1, policy_version 80960 (0.0010) -[2023-10-10 15:51:00,322][76543] Updated weights for policy 0, policy_version 81123 (0.0009) -[2023-10-10 15:51:00,682][76543] Updated weights for policy 0, policy_version 81133 (0.0007) -[2023-10-10 15:51:01,055][76543] Updated weights for policy 0, policy_version 81143 (0.0007) -[2023-10-10 15:51:01,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 165969920. Throughput: 0: 1833.5, 1: 1818.8. Samples: 41508940. Policy #0 lag: (min: 27.0, avg: 30.3, max: 59.0) -[2023-10-10 15:51:01,076][75634] Avg episode reward: [(0, '37.540'), (1, '32.770')] -[2023-10-10 15:51:01,999][76542] Updated weights for policy 1, policy_version 80970 (0.0007) -[2023-10-10 15:51:02,366][76542] Updated weights for policy 1, policy_version 80980 (0.0007) -[2023-10-10 15:51:02,742][76542] Updated weights for policy 1, policy_version 80990 (0.0008) -[2023-10-10 15:51:04,716][76543] Updated weights for policy 0, policy_version 81153 (0.0008) -[2023-10-10 15:51:05,079][76543] Updated weights for policy 0, policy_version 81163 (0.0010) -[2023-10-10 15:51:05,459][76543] Updated weights for policy 0, policy_version 81173 (0.0008) -[2023-10-10 15:51:05,824][76543] Updated weights for policy 0, policy_version 81183 (0.0010) -[2023-10-10 15:51:06,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 166068224. Throughput: 0: 1834.8, 1: 1820.1. Samples: 41518912. Policy #0 lag: (min: 27.0, avg: 30.3, max: 59.0) -[2023-10-10 15:51:06,077][75634] Avg episode reward: [(0, '38.940'), (1, '31.910')] -[2023-10-10 15:51:06,285][76542] Updated weights for policy 1, policy_version 81000 (0.0008) -[2023-10-10 15:51:06,653][76542] Updated weights for policy 1, policy_version 81010 (0.0007) -[2023-10-10 15:51:07,030][76542] Updated weights for policy 1, policy_version 81020 (0.0008) -[2023-10-10 15:51:09,590][76543] Updated weights for policy 0, policy_version 81193 (0.0008) -[2023-10-10 15:51:09,966][76543] Updated weights for policy 0, policy_version 81203 (0.0009) -[2023-10-10 15:51:10,327][76543] Updated weights for policy 0, policy_version 81213 (0.0009) -[2023-10-10 15:51:10,834][76542] Updated weights for policy 1, policy_version 81030 (0.0010) -[2023-10-10 15:51:11,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 166133760. Throughput: 0: 1834.3, 1: 1817.5. Samples: 41541888. Policy #0 lag: (min: 27.0, avg: 30.3, max: 59.0) -[2023-10-10 15:51:11,077][75634] Avg episode reward: [(0, '43.410'), (1, '36.600')] -[2023-10-10 15:51:11,200][76542] Updated weights for policy 1, policy_version 81040 (0.0007) -[2023-10-10 15:51:11,559][76542] Updated weights for policy 1, policy_version 81050 (0.0009) -[2023-10-10 15:51:13,999][76543] Updated weights for policy 0, policy_version 81223 (0.0010) -[2023-10-10 15:51:14,357][76543] Updated weights for policy 0, policy_version 81233 (0.0009) -[2023-10-10 15:51:14,723][76543] Updated weights for policy 0, policy_version 81243 (0.0009) -[2023-10-10 15:51:15,252][76542] Updated weights for policy 1, policy_version 81060 (0.0008) -[2023-10-10 15:51:15,618][76542] Updated weights for policy 1, policy_version 81070 (0.0007) -[2023-10-10 15:51:15,990][76542] Updated weights for policy 1, policy_version 81080 (0.0007) -[2023-10-10 15:51:16,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 166199296. Throughput: 0: 1829.9, 1: 1817.7. Samples: 41562414. Policy #0 lag: (min: 27.0, avg: 30.3, max: 59.0) -[2023-10-10 15:51:16,076][75634] Avg episode reward: [(0, '42.480'), (1, '34.310')] -[2023-10-10 15:51:18,443][76543] Updated weights for policy 0, policy_version 81253 (0.0011) -[2023-10-10 15:51:18,807][76543] Updated weights for policy 0, policy_version 81263 (0.0012) -[2023-10-10 15:51:19,183][76543] Updated weights for policy 0, policy_version 81273 (0.0010) -[2023-10-10 15:51:19,681][76542] Updated weights for policy 1, policy_version 81090 (0.0007) -[2023-10-10 15:51:20,044][76542] Updated weights for policy 1, policy_version 81100 (0.0010) -[2023-10-10 15:51:20,417][76542] Updated weights for policy 1, policy_version 81110 (0.0008) -[2023-10-10 15:51:20,787][76542] Updated weights for policy 1, policy_version 81120 (0.0009) -[2023-10-10 15:51:21,076][75634] Fps is (10 sec: 16384.4, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 166297600. Throughput: 0: 1828.9, 1: 1814.8. Samples: 41574500. Policy #0 lag: (min: 27.0, avg: 30.3, max: 59.0) -[2023-10-10 15:51:21,076][75634] Avg episode reward: [(0, '40.190'), (1, '32.250')] -[2023-10-10 15:51:23,097][76543] Updated weights for policy 0, policy_version 81283 (0.0008) -[2023-10-10 15:51:23,502][76543] Updated weights for policy 0, policy_version 81293 (0.0011) -[2023-10-10 15:51:23,865][76543] Updated weights for policy 0, policy_version 81303 (0.0009) -[2023-10-10 15:51:24,482][76542] Updated weights for policy 1, policy_version 81130 (0.0009) -[2023-10-10 15:51:24,856][76542] Updated weights for policy 1, policy_version 81140 (0.0008) -[2023-10-10 15:51:25,229][76542] Updated weights for policy 1, policy_version 81150 (0.0008) -[2023-10-10 15:51:26,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 166363136. Throughput: 0: 1820.1, 1: 1816.0. Samples: 41594832. Policy #0 lag: (min: 27.0, avg: 30.3, max: 59.0) -[2023-10-10 15:51:26,076][75634] Avg episode reward: [(0, '39.700'), (1, '34.810')] -[2023-10-10 15:51:27,473][76543] Updated weights for policy 0, policy_version 81313 (0.0008) -[2023-10-10 15:51:27,837][76543] Updated weights for policy 0, policy_version 81323 (0.0008) -[2023-10-10 15:51:28,202][76543] Updated weights for policy 0, policy_version 81333 (0.0007) -[2023-10-10 15:51:28,571][76543] Updated weights for policy 0, policy_version 81343 (0.0009) -[2023-10-10 15:51:28,986][76542] Updated weights for policy 1, policy_version 81160 (0.0007) -[2023-10-10 15:51:29,356][76542] Updated weights for policy 1, policy_version 81170 (0.0007) -[2023-10-10 15:51:29,714][76542] Updated weights for policy 1, policy_version 81180 (0.0009) -[2023-10-10 15:51:31,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 166428672. Throughput: 0: 1824.9, 1: 1817.0. Samples: 41617142. Policy #0 lag: (min: 27.0, avg: 30.3, max: 59.0) -[2023-10-10 15:51:31,076][75634] Avg episode reward: [(0, '37.890'), (1, '35.560')] -[2023-10-10 15:51:32,187][76543] Updated weights for policy 0, policy_version 81353 (0.0008) -[2023-10-10 15:51:32,546][76543] Updated weights for policy 0, policy_version 81363 (0.0008) -[2023-10-10 15:51:32,914][76543] Updated weights for policy 0, policy_version 81373 (0.0008) -[2023-10-10 15:51:33,483][76542] Updated weights for policy 1, policy_version 81190 (0.0009) -[2023-10-10 15:51:33,842][76542] Updated weights for policy 1, policy_version 81200 (0.0007) -[2023-10-10 15:51:34,210][76542] Updated weights for policy 1, policy_version 81210 (0.0007) -[2023-10-10 15:51:36,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 166494208. Throughput: 0: 1816.4, 1: 1822.8. Samples: 41627896. Policy #0 lag: (min: 27.0, avg: 30.3, max: 59.0) -[2023-10-10 15:51:36,077][75634] Avg episode reward: [(0, '39.120'), (1, '38.460')] -[2023-10-10 15:51:36,630][76543] Updated weights for policy 0, policy_version 81383 (0.0009) -[2023-10-10 15:51:36,991][76543] Updated weights for policy 0, policy_version 81393 (0.0008) -[2023-10-10 15:51:37,365][76543] Updated weights for policy 0, policy_version 81403 (0.0009) -[2023-10-10 15:51:37,876][76542] Updated weights for policy 1, policy_version 81220 (0.0008) -[2023-10-10 15:51:38,247][76542] Updated weights for policy 1, policy_version 81230 (0.0007) -[2023-10-10 15:51:38,616][76542] Updated weights for policy 1, policy_version 81240 (0.0007) -[2023-10-10 15:51:40,903][76543] Updated weights for policy 0, policy_version 81413 (0.0010) -[2023-10-10 15:51:41,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 166559744. Throughput: 0: 1820.3, 1: 1825.4. Samples: 41650132. Policy #0 lag: (min: 27.0, avg: 30.3, max: 59.0) -[2023-10-10 15:51:41,077][75634] Avg episode reward: [(0, '41.860'), (1, '32.390')] -[2023-10-10 15:51:41,270][76543] Updated weights for policy 0, policy_version 81423 (0.0008) -[2023-10-10 15:51:41,639][76543] Updated weights for policy 0, policy_version 81433 (0.0008) -[2023-10-10 15:51:42,270][76542] Updated weights for policy 1, policy_version 81250 (0.0008) -[2023-10-10 15:51:42,637][76542] Updated weights for policy 1, policy_version 81260 (0.0009) -[2023-10-10 15:51:42,995][76542] Updated weights for policy 1, policy_version 81270 (0.0008) -[2023-10-10 15:51:43,371][76542] Updated weights for policy 1, policy_version 81280 (0.0009) -[2023-10-10 15:51:45,258][76543] Updated weights for policy 0, policy_version 81443 (0.0009) -[2023-10-10 15:51:45,625][76543] Updated weights for policy 0, policy_version 81453 (0.0008) -[2023-10-10 15:51:45,999][76543] Updated weights for policy 0, policy_version 81463 (0.0008) -[2023-10-10 15:51:46,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 166625280. Throughput: 0: 1826.8, 1: 1825.7. Samples: 41673304. Policy #0 lag: (min: 27.0, avg: 30.3, max: 59.0) -[2023-10-10 15:51:46,076][75634] Avg episode reward: [(0, '39.610'), (1, '38.810')] -[2023-10-10 15:51:47,019][76542] Updated weights for policy 1, policy_version 81290 (0.0011) -[2023-10-10 15:51:47,392][76542] Updated weights for policy 1, policy_version 81300 (0.0009) -[2023-10-10 15:51:47,765][76542] Updated weights for policy 1, policy_version 81310 (0.0008) -[2023-10-10 15:51:49,635][76543] Updated weights for policy 0, policy_version 81473 (0.0007) -[2023-10-10 15:51:50,003][76543] Updated weights for policy 0, policy_version 81483 (0.0007) -[2023-10-10 15:51:50,391][76543] Updated weights for policy 0, policy_version 81493 (0.0007) -[2023-10-10 15:51:50,757][76543] Updated weights for policy 0, policy_version 81503 (0.0008) -[2023-10-10 15:51:51,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 166723584. Throughput: 0: 1828.4, 1: 1826.8. Samples: 41683396. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:51:51,077][75634] Avg episode reward: [(0, '36.560'), (1, '39.230')] -[2023-10-10 15:51:51,483][76542] Updated weights for policy 1, policy_version 81320 (0.0010) -[2023-10-10 15:51:51,834][76542] Updated weights for policy 1, policy_version 81330 (0.0009) -[2023-10-10 15:51:52,199][76542] Updated weights for policy 1, policy_version 81340 (0.0008) -[2023-10-10 15:51:54,454][76543] Updated weights for policy 0, policy_version 81513 (0.0009) -[2023-10-10 15:51:54,819][76543] Updated weights for policy 0, policy_version 81523 (0.0008) -[2023-10-10 15:51:55,194][76543] Updated weights for policy 0, policy_version 81533 (0.0009) -[2023-10-10 15:51:55,884][76542] Updated weights for policy 1, policy_version 81350 (0.0008) -[2023-10-10 15:51:56,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 166789120. Throughput: 0: 1825.6, 1: 1824.7. Samples: 41706152. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:51:56,076][75634] Avg episode reward: [(0, '40.890'), (1, '35.960')] -[2023-10-10 15:51:56,244][76542] Updated weights for policy 1, policy_version 81360 (0.0007) -[2023-10-10 15:51:56,617][76542] Updated weights for policy 1, policy_version 81370 (0.0009) -[2023-10-10 15:51:58,857][76543] Updated weights for policy 0, policy_version 81543 (0.0007) -[2023-10-10 15:51:59,216][76543] Updated weights for policy 0, policy_version 81553 (0.0008) -[2023-10-10 15:51:59,590][76543] Updated weights for policy 0, policy_version 81563 (0.0008) -[2023-10-10 15:52:00,301][76542] Updated weights for policy 1, policy_version 81380 (0.0008) -[2023-10-10 15:52:00,671][76542] Updated weights for policy 1, policy_version 81390 (0.0007) -[2023-10-10 15:52:01,045][76542] Updated weights for policy 1, policy_version 81400 (0.0007) -[2023-10-10 15:52:01,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 166854656. Throughput: 0: 1832.5, 1: 1825.8. Samples: 41727040. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:52:01,077][75634] Avg episode reward: [(0, '42.280'), (1, '31.770')] -[2023-10-10 15:52:03,105][76543] Updated weights for policy 0, policy_version 81573 (0.0010) -[2023-10-10 15:52:03,474][76543] Updated weights for policy 0, policy_version 81583 (0.0009) -[2023-10-10 15:52:03,845][76543] Updated weights for policy 0, policy_version 81593 (0.0007) -[2023-10-10 15:52:04,823][76542] Updated weights for policy 1, policy_version 81410 (0.0009) -[2023-10-10 15:52:05,188][76542] Updated weights for policy 1, policy_version 81420 (0.0010) -[2023-10-10 15:52:05,564][76542] Updated weights for policy 1, policy_version 81430 (0.0007) -[2023-10-10 15:52:05,932][76542] Updated weights for policy 1, policy_version 81440 (0.0007) -[2023-10-10 15:52:06,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 166952960. Throughput: 0: 1830.7, 1: 1820.6. Samples: 41738806. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:52:06,076][75634] Avg episode reward: [(0, '40.470'), (1, '33.190')] -[2023-10-10 15:52:07,328][76543] Updated weights for policy 0, policy_version 81603 (0.0009) -[2023-10-10 15:52:07,692][76543] Updated weights for policy 0, policy_version 81613 (0.0012) -[2023-10-10 15:52:08,061][76543] Updated weights for policy 0, policy_version 81623 (0.0010) -[2023-10-10 15:52:09,527][76542] Updated weights for policy 1, policy_version 81450 (0.0010) -[2023-10-10 15:52:09,889][76542] Updated weights for policy 1, policy_version 81460 (0.0007) -[2023-10-10 15:52:10,263][76542] Updated weights for policy 1, policy_version 81470 (0.0008) -[2023-10-10 15:52:11,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 167018496. Throughput: 0: 1849.0, 1: 1822.9. Samples: 41760068. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:52:11,076][75634] Avg episode reward: [(0, '37.930'), (1, '35.080')] -[2023-10-10 15:52:11,894][76543] Updated weights for policy 0, policy_version 81633 (0.0009) -[2023-10-10 15:52:12,301][76543] Updated weights for policy 0, policy_version 81643 (0.0010) -[2023-10-10 15:52:12,675][76543] Updated weights for policy 0, policy_version 81653 (0.0010) -[2023-10-10 15:52:13,044][76543] Updated weights for policy 0, policy_version 81663 (0.0011) -[2023-10-10 15:52:13,929][76542] Updated weights for policy 1, policy_version 81480 (0.0009) -[2023-10-10 15:52:14,295][76542] Updated weights for policy 1, policy_version 81490 (0.0009) -[2023-10-10 15:52:14,661][76542] Updated weights for policy 1, policy_version 81500 (0.0009) -[2023-10-10 15:52:16,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 167084032. Throughput: 0: 1840.9, 1: 1825.5. Samples: 41782130. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:52:16,077][75634] Avg episode reward: [(0, '36.480'), (1, '34.410')] -[2023-10-10 15:52:16,536][76543] Updated weights for policy 0, policy_version 81673 (0.0008) -[2023-10-10 15:52:16,912][76543] Updated weights for policy 0, policy_version 81683 (0.0007) -[2023-10-10 15:52:17,280][76543] Updated weights for policy 0, policy_version 81693 (0.0010) -[2023-10-10 15:52:18,324][76542] Updated weights for policy 1, policy_version 81510 (0.0010) -[2023-10-10 15:52:18,691][76542] Updated weights for policy 1, policy_version 81520 (0.0008) -[2023-10-10 15:52:19,066][76542] Updated weights for policy 1, policy_version 81530 (0.0008) -[2023-10-10 15:52:21,075][76543] Updated weights for policy 0, policy_version 81703 (0.0007) -[2023-10-10 15:52:21,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 167149568. Throughput: 0: 1850.7, 1: 1819.9. Samples: 41793072. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:52:21,076][75634] Avg episode reward: [(0, '33.430'), (1, '32.830')] -[2023-10-10 15:52:21,450][76543] Updated weights for policy 0, policy_version 81713 (0.0007) -[2023-10-10 15:52:21,822][76543] Updated weights for policy 0, policy_version 81723 (0.0008) -[2023-10-10 15:52:22,795][76542] Updated weights for policy 1, policy_version 81540 (0.0008) -[2023-10-10 15:52:23,177][76542] Updated weights for policy 1, policy_version 81550 (0.0010) -[2023-10-10 15:52:23,547][76542] Updated weights for policy 1, policy_version 81560 (0.0009) -[2023-10-10 15:52:25,493][76543] Updated weights for policy 0, policy_version 81733 (0.0009) -[2023-10-10 15:52:25,851][76543] Updated weights for policy 0, policy_version 81743 (0.0010) -[2023-10-10 15:52:26,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14440.2). Total num frames: 167215104. Throughput: 0: 1840.9, 1: 1824.1. Samples: 41815056. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:52:26,076][75634] Avg episode reward: [(0, '33.090'), (1, '35.690')] -[2023-10-10 15:52:26,227][76543] Updated weights for policy 0, policy_version 81753 (0.0010) -[2023-10-10 15:52:26,995][76542] Updated weights for policy 1, policy_version 81570 (0.0008) -[2023-10-10 15:52:27,359][76542] Updated weights for policy 1, policy_version 81580 (0.0007) -[2023-10-10 15:52:27,722][76542] Updated weights for policy 1, policy_version 81590 (0.0010) -[2023-10-10 15:52:28,088][76542] Updated weights for policy 1, policy_version 81600 (0.0011) -[2023-10-10 15:52:29,900][76543] Updated weights for policy 0, policy_version 81763 (0.0007) -[2023-10-10 15:52:30,270][76543] Updated weights for policy 0, policy_version 81773 (0.0008) -[2023-10-10 15:52:30,634][76543] Updated weights for policy 0, policy_version 81783 (0.0009) -[2023-10-10 15:52:31,076][75634] Fps is (10 sec: 16383.5, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 167313408. Throughput: 0: 1826.5, 1: 1832.5. Samples: 41837958. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:52:31,077][75634] Avg episode reward: [(0, '32.250'), (1, '36.520')] -[2023-10-10 15:52:31,088][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000081600_83558400.pth... -[2023-10-10 15:52:31,088][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000081792_83755008.pth... -[2023-10-10 15:52:31,127][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000079904_81821696.pth -[2023-10-10 15:52:31,133][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000080064_81985536.pth -[2023-10-10 15:52:31,840][76542] Updated weights for policy 1, policy_version 81610 (0.0010) -[2023-10-10 15:52:32,222][76542] Updated weights for policy 1, policy_version 81620 (0.0008) -[2023-10-10 15:52:32,589][76542] Updated weights for policy 1, policy_version 81630 (0.0009) -[2023-10-10 15:52:34,224][76543] Updated weights for policy 0, policy_version 81793 (0.0007) -[2023-10-10 15:52:34,595][76543] Updated weights for policy 0, policy_version 81803 (0.0010) -[2023-10-10 15:52:34,971][76543] Updated weights for policy 0, policy_version 81813 (0.0010) -[2023-10-10 15:52:35,344][76543] Updated weights for policy 0, policy_version 81823 (0.0009) -[2023-10-10 15:52:36,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 167378944. Throughput: 0: 1834.8, 1: 1826.9. Samples: 41848170. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:52:36,077][75634] Avg episode reward: [(0, '31.880'), (1, '36.400')] -[2023-10-10 15:52:36,278][76542] Updated weights for policy 1, policy_version 81640 (0.0008) -[2023-10-10 15:52:36,647][76542] Updated weights for policy 1, policy_version 81650 (0.0007) -[2023-10-10 15:52:37,005][76542] Updated weights for policy 1, policy_version 81660 (0.0007) -[2023-10-10 15:52:38,961][76543] Updated weights for policy 0, policy_version 81833 (0.0007) -[2023-10-10 15:52:39,326][76543] Updated weights for policy 0, policy_version 81843 (0.0010) -[2023-10-10 15:52:39,696][76543] Updated weights for policy 0, policy_version 81853 (0.0011) -[2023-10-10 15:52:40,767][76542] Updated weights for policy 1, policy_version 81670 (0.0010) -[2023-10-10 15:52:41,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 167444480. Throughput: 0: 1824.6, 1: 1822.8. Samples: 41870282. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:52:41,076][75634] Avg episode reward: [(0, '36.930'), (1, '33.890')] -[2023-10-10 15:52:41,128][76542] Updated weights for policy 1, policy_version 81680 (0.0009) -[2023-10-10 15:52:41,502][76542] Updated weights for policy 1, policy_version 81690 (0.0008) -[2023-10-10 15:52:43,332][76543] Updated weights for policy 0, policy_version 81863 (0.0008) -[2023-10-10 15:52:43,708][76543] Updated weights for policy 0, policy_version 81873 (0.0007) -[2023-10-10 15:52:44,077][76543] Updated weights for policy 0, policy_version 81883 (0.0008) -[2023-10-10 15:52:45,245][76542] Updated weights for policy 1, policy_version 81700 (0.0009) -[2023-10-10 15:52:45,620][76542] Updated weights for policy 1, policy_version 81710 (0.0011) -[2023-10-10 15:52:45,994][76542] Updated weights for policy 1, policy_version 81720 (0.0010) -[2023-10-10 15:52:46,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 167510016. Throughput: 0: 1835.6, 1: 1821.1. Samples: 41891590. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:52:46,077][75634] Avg episode reward: [(0, '34.950'), (1, '36.760')] -[2023-10-10 15:52:47,917][76543] Updated weights for policy 0, policy_version 81893 (0.0009) -[2023-10-10 15:52:48,283][76543] Updated weights for policy 0, policy_version 81903 (0.0009) -[2023-10-10 15:52:48,648][76543] Updated weights for policy 0, policy_version 81913 (0.0010) -[2023-10-10 15:52:49,808][76542] Updated weights for policy 1, policy_version 81730 (0.0011) -[2023-10-10 15:52:50,172][76542] Updated weights for policy 1, policy_version 81740 (0.0009) -[2023-10-10 15:52:50,544][76542] Updated weights for policy 1, policy_version 81750 (0.0009) -[2023-10-10 15:52:50,910][76542] Updated weights for policy 1, policy_version 81760 (0.0009) -[2023-10-10 15:52:51,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 167608320. Throughput: 0: 1822.9, 1: 1822.3. Samples: 41902842. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:52:51,077][75634] Avg episode reward: [(0, '33.030'), (1, '36.730')] -[2023-10-10 15:52:52,362][76543] Updated weights for policy 0, policy_version 81923 (0.0009) -[2023-10-10 15:52:52,740][76543] Updated weights for policy 0, policy_version 81933 (0.0008) -[2023-10-10 15:52:53,096][76543] Updated weights for policy 0, policy_version 81943 (0.0009) -[2023-10-10 15:52:54,432][76542] Updated weights for policy 1, policy_version 81770 (0.0009) -[2023-10-10 15:52:54,793][76542] Updated weights for policy 1, policy_version 81780 (0.0009) -[2023-10-10 15:52:55,166][76542] Updated weights for policy 1, policy_version 81790 (0.0009) -[2023-10-10 15:52:56,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 167673856. Throughput: 0: 1823.1, 1: 1820.9. Samples: 41924050. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:52:56,077][75634] Avg episode reward: [(0, '35.000'), (1, '32.660')] -[2023-10-10 15:52:56,777][76543] Updated weights for policy 0, policy_version 81953 (0.0008) -[2023-10-10 15:52:57,192][76543] Updated weights for policy 0, policy_version 81963 (0.0010) -[2023-10-10 15:52:57,563][76543] Updated weights for policy 0, policy_version 81973 (0.0009) -[2023-10-10 15:52:57,930][76543] Updated weights for policy 0, policy_version 81983 (0.0009) -[2023-10-10 15:52:58,814][76542] Updated weights for policy 1, policy_version 81800 (0.0010) -[2023-10-10 15:52:59,176][76542] Updated weights for policy 1, policy_version 81810 (0.0008) -[2023-10-10 15:52:59,548][76542] Updated weights for policy 1, policy_version 81820 (0.0008) -[2023-10-10 15:53:01,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 167739392. Throughput: 0: 1819.5, 1: 1822.4. Samples: 41946014. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:53:01,076][75634] Avg episode reward: [(0, '36.640'), (1, '36.380')] -[2023-10-10 15:53:01,520][76543] Updated weights for policy 0, policy_version 81993 (0.0008) -[2023-10-10 15:53:01,886][76543] Updated weights for policy 0, policy_version 82003 (0.0008) -[2023-10-10 15:53:02,257][76543] Updated weights for policy 0, policy_version 82013 (0.0008) -[2023-10-10 15:53:03,297][76542] Updated weights for policy 1, policy_version 81830 (0.0009) -[2023-10-10 15:53:03,672][76542] Updated weights for policy 1, policy_version 81840 (0.0009) -[2023-10-10 15:53:04,043][76542] Updated weights for policy 1, policy_version 81850 (0.0008) -[2023-10-10 15:53:05,913][76543] Updated weights for policy 0, policy_version 82023 (0.0010) -[2023-10-10 15:53:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 167804928. Throughput: 0: 1814.0, 1: 1822.5. Samples: 41956716. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:53:06,077][75634] Avg episode reward: [(0, '38.090'), (1, '39.710')] -[2023-10-10 15:53:06,288][76543] Updated weights for policy 0, policy_version 82033 (0.0011) -[2023-10-10 15:53:06,655][76543] Updated weights for policy 0, policy_version 82043 (0.0009) -[2023-10-10 15:53:07,814][76542] Updated weights for policy 1, policy_version 81860 (0.0008) -[2023-10-10 15:53:08,179][76542] Updated weights for policy 1, policy_version 81870 (0.0007) -[2023-10-10 15:53:08,543][76542] Updated weights for policy 1, policy_version 81880 (0.0007) -[2023-10-10 15:53:10,329][76543] Updated weights for policy 0, policy_version 82053 (0.0009) -[2023-10-10 15:53:10,700][76543] Updated weights for policy 0, policy_version 82063 (0.0008) -[2023-10-10 15:53:11,063][76543] Updated weights for policy 0, policy_version 82073 (0.0008) -[2023-10-10 15:53:11,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 167870464. Throughput: 0: 1820.8, 1: 1823.6. Samples: 41979056. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:53:11,077][75634] Avg episode reward: [(0, '38.970'), (1, '33.610')] -[2023-10-10 15:53:12,231][76542] Updated weights for policy 1, policy_version 81890 (0.0007) -[2023-10-10 15:53:12,604][76542] Updated weights for policy 1, policy_version 81900 (0.0009) -[2023-10-10 15:53:12,975][76542] Updated weights for policy 1, policy_version 81910 (0.0007) -[2023-10-10 15:53:13,339][76542] Updated weights for policy 1, policy_version 81920 (0.0010) -[2023-10-10 15:53:14,817][76543] Updated weights for policy 0, policy_version 82083 (0.0008) -[2023-10-10 15:53:15,184][76543] Updated weights for policy 0, policy_version 82093 (0.0007) -[2023-10-10 15:53:15,555][76543] Updated weights for policy 0, policy_version 82103 (0.0010) -[2023-10-10 15:53:16,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 167968768. Throughput: 0: 1816.7, 1: 1809.5. Samples: 42001138. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:53:16,076][75634] Avg episode reward: [(0, '38.950'), (1, '33.690')] -[2023-10-10 15:53:17,027][76542] Updated weights for policy 1, policy_version 81930 (0.0008) -[2023-10-10 15:53:17,390][76542] Updated weights for policy 1, policy_version 81940 (0.0009) -[2023-10-10 15:53:17,761][76542] Updated weights for policy 1, policy_version 81950 (0.0011) -[2023-10-10 15:53:19,259][76543] Updated weights for policy 0, policy_version 82113 (0.0009) -[2023-10-10 15:53:19,631][76543] Updated weights for policy 0, policy_version 82123 (0.0009) -[2023-10-10 15:53:19,997][76543] Updated weights for policy 0, policy_version 82133 (0.0010) -[2023-10-10 15:53:20,375][76543] Updated weights for policy 0, policy_version 82143 (0.0008) -[2023-10-10 15:53:21,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 168034304. Throughput: 0: 1818.4, 1: 1814.0. Samples: 42011630. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:53:21,076][75634] Avg episode reward: [(0, '38.500'), (1, '37.010')] -[2023-10-10 15:53:21,279][76542] Updated weights for policy 1, policy_version 81960 (0.0008) -[2023-10-10 15:53:21,639][76542] Updated weights for policy 1, policy_version 81970 (0.0010) -[2023-10-10 15:53:22,007][76542] Updated weights for policy 1, policy_version 81980 (0.0009) -[2023-10-10 15:53:23,971][76543] Updated weights for policy 0, policy_version 82153 (0.0010) -[2023-10-10 15:53:24,334][76543] Updated weights for policy 0, policy_version 82163 (0.0011) -[2023-10-10 15:53:24,710][76543] Updated weights for policy 0, policy_version 82173 (0.0011) -[2023-10-10 15:53:25,651][76542] Updated weights for policy 1, policy_version 81990 (0.0008) -[2023-10-10 15:53:26,016][76542] Updated weights for policy 1, policy_version 82000 (0.0009) -[2023-10-10 15:53:26,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 168099840. Throughput: 0: 1816.0, 1: 1822.3. Samples: 42034006. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:53:26,076][75634] Avg episode reward: [(0, '39.680'), (1, '37.060')] -[2023-10-10 15:53:26,379][76542] Updated weights for policy 1, policy_version 82010 (0.0008) -[2023-10-10 15:53:28,428][76543] Updated weights for policy 0, policy_version 82183 (0.0010) -[2023-10-10 15:53:28,788][76543] Updated weights for policy 0, policy_version 82193 (0.0007) -[2023-10-10 15:53:29,171][76543] Updated weights for policy 0, policy_version 82203 (0.0010) -[2023-10-10 15:53:30,060][76542] Updated weights for policy 1, policy_version 82020 (0.0008) -[2023-10-10 15:53:30,426][76542] Updated weights for policy 1, policy_version 82030 (0.0009) -[2023-10-10 15:53:30,792][76542] Updated weights for policy 1, policy_version 82040 (0.0008) -[2023-10-10 15:53:31,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 168165376. Throughput: 0: 1816.8, 1: 1816.4. Samples: 42055084. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:53:31,076][75634] Avg episode reward: [(0, '38.020'), (1, '36.760')] -[2023-10-10 15:53:32,838][76543] Updated weights for policy 0, policy_version 82213 (0.0010) -[2023-10-10 15:53:33,217][76543] Updated weights for policy 0, policy_version 82223 (0.0010) -[2023-10-10 15:53:33,590][76543] Updated weights for policy 0, policy_version 82233 (0.0010) -[2023-10-10 15:53:34,413][76542] Updated weights for policy 1, policy_version 82050 (0.0008) -[2023-10-10 15:53:34,777][76542] Updated weights for policy 1, policy_version 82060 (0.0008) -[2023-10-10 15:53:35,143][76542] Updated weights for policy 1, policy_version 82070 (0.0007) -[2023-10-10 15:53:35,518][76542] Updated weights for policy 1, policy_version 82080 (0.0009) -[2023-10-10 15:53:36,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 168263680. Throughput: 0: 1813.4, 1: 1834.4. Samples: 42066994. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:53:36,077][75634] Avg episode reward: [(0, '39.290'), (1, '36.470')] -[2023-10-10 15:53:37,334][76543] Updated weights for policy 0, policy_version 82243 (0.0009) -[2023-10-10 15:53:37,713][76543] Updated weights for policy 0, policy_version 82253 (0.0008) -[2023-10-10 15:53:38,082][76543] Updated weights for policy 0, policy_version 82263 (0.0008) -[2023-10-10 15:53:39,206][76542] Updated weights for policy 1, policy_version 82090 (0.0007) -[2023-10-10 15:53:39,571][76542] Updated weights for policy 1, policy_version 82100 (0.0010) -[2023-10-10 15:53:39,938][76542] Updated weights for policy 1, policy_version 82110 (0.0009) -[2023-10-10 15:53:41,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 168329216. Throughput: 0: 1814.4, 1: 1823.7. Samples: 42087764. Policy #0 lag: (min: 9.0, avg: 17.9, max: 41.0) -[2023-10-10 15:53:41,077][75634] Avg episode reward: [(0, '42.640'), (1, '37.610')] -[2023-10-10 15:53:41,868][76543] Updated weights for policy 0, policy_version 82273 (0.0008) -[2023-10-10 15:53:42,283][76543] Updated weights for policy 0, policy_version 82283 (0.0009) -[2023-10-10 15:53:42,660][76543] Updated weights for policy 0, policy_version 82293 (0.0009) -[2023-10-10 15:53:43,026][76543] Updated weights for policy 0, policy_version 82303 (0.0009) -[2023-10-10 15:53:43,687][76542] Updated weights for policy 1, policy_version 82120 (0.0010) -[2023-10-10 15:53:44,059][76542] Updated weights for policy 1, policy_version 82130 (0.0007) -[2023-10-10 15:53:44,426][76542] Updated weights for policy 1, policy_version 82140 (0.0011) -[2023-10-10 15:53:46,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 168394752. Throughput: 0: 1818.3, 1: 1821.7. Samples: 42109814. Policy #0 lag: (min: 9.0, avg: 17.9, max: 41.0) -[2023-10-10 15:53:46,076][75634] Avg episode reward: [(0, '41.780'), (1, '34.570')] -[2023-10-10 15:53:46,635][76543] Updated weights for policy 0, policy_version 82313 (0.0010) -[2023-10-10 15:53:47,012][76543] Updated weights for policy 0, policy_version 82323 (0.0008) -[2023-10-10 15:53:47,381][76543] Updated weights for policy 0, policy_version 82333 (0.0010) -[2023-10-10 15:53:48,224][76542] Updated weights for policy 1, policy_version 82150 (0.0009) -[2023-10-10 15:53:48,588][76542] Updated weights for policy 1, policy_version 82160 (0.0008) -[2023-10-10 15:53:48,951][76542] Updated weights for policy 1, policy_version 82170 (0.0007) -[2023-10-10 15:53:50,901][76543] Updated weights for policy 0, policy_version 82343 (0.0010) -[2023-10-10 15:53:51,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 168460288. Throughput: 0: 1820.0, 1: 1819.9. Samples: 42120510. Policy #0 lag: (min: 9.0, avg: 17.9, max: 41.0) -[2023-10-10 15:53:51,076][75634] Avg episode reward: [(0, '38.450'), (1, '35.740')] -[2023-10-10 15:53:51,270][76543] Updated weights for policy 0, policy_version 82353 (0.0007) -[2023-10-10 15:53:51,647][76543] Updated weights for policy 0, policy_version 82363 (0.0007) -[2023-10-10 15:53:52,707][76542] Updated weights for policy 1, policy_version 82180 (0.0009) -[2023-10-10 15:53:53,077][76542] Updated weights for policy 1, policy_version 82190 (0.0010) -[2023-10-10 15:53:53,450][76542] Updated weights for policy 1, policy_version 82200 (0.0010) -[2023-10-10 15:53:55,339][76543] Updated weights for policy 0, policy_version 82373 (0.0007) -[2023-10-10 15:53:55,715][76543] Updated weights for policy 0, policy_version 82383 (0.0008) -[2023-10-10 15:53:56,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 168525824. Throughput: 0: 1821.6, 1: 1819.4. Samples: 42142900. Policy #0 lag: (min: 9.0, avg: 17.9, max: 41.0) -[2023-10-10 15:53:56,076][75634] Avg episode reward: [(0, '34.940'), (1, '37.630')] -[2023-10-10 15:53:56,077][76543] Updated weights for policy 0, policy_version 82393 (0.0009) -[2023-10-10 15:53:57,154][76542] Updated weights for policy 1, policy_version 82210 (0.0007) -[2023-10-10 15:53:57,526][76542] Updated weights for policy 1, policy_version 82220 (0.0010) -[2023-10-10 15:53:57,895][76542] Updated weights for policy 1, policy_version 82230 (0.0012) -[2023-10-10 15:53:58,263][76542] Updated weights for policy 1, policy_version 82240 (0.0010) -[2023-10-10 15:53:59,802][76543] Updated weights for policy 0, policy_version 82403 (0.0009) -[2023-10-10 15:54:00,171][76543] Updated weights for policy 0, policy_version 82413 (0.0007) -[2023-10-10 15:54:00,539][76543] Updated weights for policy 0, policy_version 82423 (0.0009) -[2023-10-10 15:54:01,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 168624128. Throughput: 0: 1817.2, 1: 1824.3. Samples: 42165004. Policy #0 lag: (min: 9.0, avg: 17.9, max: 41.0) -[2023-10-10 15:54:01,076][75634] Avg episode reward: [(0, '38.730'), (1, '32.160')] -[2023-10-10 15:54:01,988][76542] Updated weights for policy 1, policy_version 82250 (0.0007) -[2023-10-10 15:54:02,355][76542] Updated weights for policy 1, policy_version 82260 (0.0007) -[2023-10-10 15:54:02,711][76542] Updated weights for policy 1, policy_version 82270 (0.0007) -[2023-10-10 15:54:04,041][76543] Updated weights for policy 0, policy_version 82433 (0.0007) -[2023-10-10 15:54:04,408][76543] Updated weights for policy 0, policy_version 82443 (0.0008) -[2023-10-10 15:54:04,788][76543] Updated weights for policy 0, policy_version 82453 (0.0008) -[2023-10-10 15:54:05,162][76543] Updated weights for policy 0, policy_version 82463 (0.0010) -[2023-10-10 15:54:06,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 168689664. Throughput: 0: 1822.2, 1: 1828.9. Samples: 42175930. Policy #0 lag: (min: 9.0, avg: 17.9, max: 41.0) -[2023-10-10 15:54:06,077][75634] Avg episode reward: [(0, '35.720'), (1, '33.170')] -[2023-10-10 15:54:06,230][76542] Updated weights for policy 1, policy_version 82280 (0.0008) -[2023-10-10 15:54:06,607][76542] Updated weights for policy 1, policy_version 82290 (0.0009) -[2023-10-10 15:54:06,982][76542] Updated weights for policy 1, policy_version 82300 (0.0008) -[2023-10-10 15:54:09,032][76543] Updated weights for policy 0, policy_version 82473 (0.0009) -[2023-10-10 15:54:09,407][76543] Updated weights for policy 0, policy_version 82483 (0.0010) -[2023-10-10 15:54:09,780][76543] Updated weights for policy 0, policy_version 82493 (0.0009) -[2023-10-10 15:54:10,767][76542] Updated weights for policy 1, policy_version 82310 (0.0008) -[2023-10-10 15:54:11,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 168755200. Throughput: 0: 1821.7, 1: 1822.4. Samples: 42197994. Policy #0 lag: (min: 9.0, avg: 17.9, max: 41.0) -[2023-10-10 15:54:11,076][75634] Avg episode reward: [(0, '37.650'), (1, '37.110')] -[2023-10-10 15:54:11,132][76542] Updated weights for policy 1, policy_version 82320 (0.0009) -[2023-10-10 15:54:11,495][76542] Updated weights for policy 1, policy_version 82330 (0.0007) -[2023-10-10 15:54:13,393][76543] Updated weights for policy 0, policy_version 82503 (0.0009) -[2023-10-10 15:54:13,759][76543] Updated weights for policy 0, policy_version 82513 (0.0009) -[2023-10-10 15:54:14,130][76543] Updated weights for policy 0, policy_version 82523 (0.0009) -[2023-10-10 15:54:15,209][76542] Updated weights for policy 1, policy_version 82340 (0.0009) -[2023-10-10 15:54:15,592][76542] Updated weights for policy 1, policy_version 82350 (0.0009) -[2023-10-10 15:54:15,952][76542] Updated weights for policy 1, policy_version 82360 (0.0008) -[2023-10-10 15:54:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 168820736. Throughput: 0: 1821.5, 1: 1829.2. Samples: 42219368. Policy #0 lag: (min: 9.0, avg: 17.9, max: 41.0) -[2023-10-10 15:54:16,077][75634] Avg episode reward: [(0, '34.180'), (1, '37.390')] -[2023-10-10 15:54:17,910][76543] Updated weights for policy 0, policy_version 82533 (0.0009) -[2023-10-10 15:54:18,281][76543] Updated weights for policy 0, policy_version 82543 (0.0007) -[2023-10-10 15:54:18,650][76543] Updated weights for policy 0, policy_version 82553 (0.0010) -[2023-10-10 15:54:19,447][76542] Updated weights for policy 1, policy_version 82370 (0.0008) -[2023-10-10 15:54:19,814][76542] Updated weights for policy 1, policy_version 82380 (0.0008) -[2023-10-10 15:54:20,186][76542] Updated weights for policy 1, policy_version 82390 (0.0007) -[2023-10-10 15:54:20,549][76542] Updated weights for policy 1, policy_version 82400 (0.0007) -[2023-10-10 15:54:21,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 168919040. Throughput: 0: 1825.1, 1: 1821.6. Samples: 42231092. Policy #0 lag: (min: 9.0, avg: 17.9, max: 41.0) -[2023-10-10 15:54:21,077][75634] Avg episode reward: [(0, '33.080'), (1, '32.970')] -[2023-10-10 15:54:22,242][76543] Updated weights for policy 0, policy_version 82563 (0.0009) -[2023-10-10 15:54:22,624][76543] Updated weights for policy 0, policy_version 82573 (0.0009) -[2023-10-10 15:54:22,987][76543] Updated weights for policy 0, policy_version 82583 (0.0009) -[2023-10-10 15:54:24,172][76542] Updated weights for policy 1, policy_version 82410 (0.0007) -[2023-10-10 15:54:24,535][76542] Updated weights for policy 1, policy_version 82420 (0.0007) -[2023-10-10 15:54:24,904][76542] Updated weights for policy 1, policy_version 82430 (0.0008) -[2023-10-10 15:54:26,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 168984576. Throughput: 0: 1829.7, 1: 1825.1. Samples: 42252228. Policy #0 lag: (min: 9.0, avg: 17.9, max: 41.0) -[2023-10-10 15:54:26,077][75634] Avg episode reward: [(0, '32.410'), (1, '35.080')] -[2023-10-10 15:54:26,655][76543] Updated weights for policy 0, policy_version 82593 (0.0008) -[2023-10-10 15:54:27,034][76543] Updated weights for policy 0, policy_version 82603 (0.0007) -[2023-10-10 15:54:27,419][76543] Updated weights for policy 0, policy_version 82613 (0.0010) -[2023-10-10 15:54:27,780][76543] Updated weights for policy 0, policy_version 82623 (0.0011) -[2023-10-10 15:54:28,565][76542] Updated weights for policy 1, policy_version 82440 (0.0008) -[2023-10-10 15:54:28,934][76542] Updated weights for policy 1, policy_version 82450 (0.0008) -[2023-10-10 15:54:29,307][76542] Updated weights for policy 1, policy_version 82460 (0.0008) -[2023-10-10 15:54:31,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 169050112. Throughput: 0: 1828.3, 1: 1838.7. Samples: 42274830. Policy #0 lag: (min: 9.0, avg: 17.9, max: 41.0) -[2023-10-10 15:54:31,077][75634] Avg episode reward: [(0, '33.010'), (1, '37.740')] -[2023-10-10 15:54:31,086][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000082464_84443136.pth... -[2023-10-10 15:54:31,122][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000080768_82706432.pth -[2023-10-10 15:54:31,415][76543] Updated weights for policy 0, policy_version 82633 (0.0008) -[2023-10-10 15:54:31,791][76543] Updated weights for policy 0, policy_version 82643 (0.0008) -[2023-10-10 15:54:32,159][76543] Updated weights for policy 0, policy_version 82653 (0.0008) -[2023-10-10 15:54:32,267][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000082656_84639744.pth... -[2023-10-10 15:54:32,297][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000080928_82870272.pth -[2023-10-10 15:54:32,862][76542] Updated weights for policy 1, policy_version 82470 (0.0009) -[2023-10-10 15:54:33,230][76542] Updated weights for policy 1, policy_version 82480 (0.0010) -[2023-10-10 15:54:33,596][76542] Updated weights for policy 1, policy_version 82490 (0.0008) -[2023-10-10 15:54:35,849][76543] Updated weights for policy 0, policy_version 82663 (0.0008) -[2023-10-10 15:54:36,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 169115648. Throughput: 0: 1826.9, 1: 1830.3. Samples: 42285082. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 15:54:36,076][75634] Avg episode reward: [(0, '32.270'), (1, '35.200')] -[2023-10-10 15:54:36,207][76543] Updated weights for policy 0, policy_version 82673 (0.0007) -[2023-10-10 15:54:36,590][76543] Updated weights for policy 0, policy_version 82683 (0.0008) -[2023-10-10 15:54:37,263][76542] Updated weights for policy 1, policy_version 82500 (0.0009) -[2023-10-10 15:54:37,630][76542] Updated weights for policy 1, policy_version 82510 (0.0009) -[2023-10-10 15:54:37,992][76542] Updated weights for policy 1, policy_version 82520 (0.0009) -[2023-10-10 15:54:40,359][76543] Updated weights for policy 0, policy_version 82693 (0.0009) -[2023-10-10 15:54:40,739][76543] Updated weights for policy 0, policy_version 82703 (0.0009) -[2023-10-10 15:54:41,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 169181184. Throughput: 0: 1818.4, 1: 1842.0. Samples: 42307622. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 15:54:41,076][75634] Avg episode reward: [(0, '31.370'), (1, '36.370')] -[2023-10-10 15:54:41,115][76543] Updated weights for policy 0, policy_version 82713 (0.0010) -[2023-10-10 15:54:41,593][76542] Updated weights for policy 1, policy_version 82530 (0.0008) -[2023-10-10 15:54:41,963][76542] Updated weights for policy 1, policy_version 82540 (0.0007) -[2023-10-10 15:54:42,343][76542] Updated weights for policy 1, policy_version 82550 (0.0007) -[2023-10-10 15:54:42,712][76542] Updated weights for policy 1, policy_version 82560 (0.0008) -[2023-10-10 15:54:44,795][76543] Updated weights for policy 0, policy_version 82723 (0.0007) -[2023-10-10 15:54:45,176][76543] Updated weights for policy 0, policy_version 82733 (0.0009) -[2023-10-10 15:54:45,550][76543] Updated weights for policy 0, policy_version 82743 (0.0009) -[2023-10-10 15:54:46,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 169279488. Throughput: 0: 1824.8, 1: 1841.4. Samples: 42329984. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 15:54:46,077][75634] Avg episode reward: [(0, '36.900'), (1, '36.090')] -[2023-10-10 15:54:46,352][76542] Updated weights for policy 1, policy_version 82570 (0.0010) -[2023-10-10 15:54:46,717][76542] Updated weights for policy 1, policy_version 82580 (0.0008) -[2023-10-10 15:54:47,085][76542] Updated weights for policy 1, policy_version 82590 (0.0009) -[2023-10-10 15:54:49,319][76543] Updated weights for policy 0, policy_version 82753 (0.0009) -[2023-10-10 15:54:49,684][76543] Updated weights for policy 0, policy_version 82763 (0.0009) -[2023-10-10 15:54:50,061][76543] Updated weights for policy 0, policy_version 82773 (0.0008) -[2023-10-10 15:54:50,432][76543] Updated weights for policy 0, policy_version 82783 (0.0008) -[2023-10-10 15:54:50,838][76542] Updated weights for policy 1, policy_version 82600 (0.0008) -[2023-10-10 15:54:51,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 169345024. Throughput: 0: 1818.2, 1: 1833.1. Samples: 42340240. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 15:54:51,077][75634] Avg episode reward: [(0, '39.520'), (1, '37.100')] -[2023-10-10 15:54:51,217][76542] Updated weights for policy 1, policy_version 82610 (0.0009) -[2023-10-10 15:54:51,586][76542] Updated weights for policy 1, policy_version 82620 (0.0009) -[2023-10-10 15:54:54,031][76543] Updated weights for policy 0, policy_version 82793 (0.0010) -[2023-10-10 15:54:54,401][76543] Updated weights for policy 0, policy_version 82803 (0.0011) -[2023-10-10 15:54:54,767][76543] Updated weights for policy 0, policy_version 82813 (0.0010) -[2023-10-10 15:54:55,294][76542] Updated weights for policy 1, policy_version 82630 (0.0008) -[2023-10-10 15:54:55,667][76542] Updated weights for policy 1, policy_version 82640 (0.0009) -[2023-10-10 15:54:56,035][76542] Updated weights for policy 1, policy_version 82650 (0.0007) -[2023-10-10 15:54:56,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 169410560. Throughput: 0: 1818.8, 1: 1835.0. Samples: 42362418. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 15:54:56,077][75634] Avg episode reward: [(0, '33.470'), (1, '39.450')] -[2023-10-10 15:54:58,308][76543] Updated weights for policy 0, policy_version 82823 (0.0008) -[2023-10-10 15:54:58,670][76543] Updated weights for policy 0, policy_version 82833 (0.0009) -[2023-10-10 15:54:59,038][76543] Updated weights for policy 0, policy_version 82843 (0.0011) -[2023-10-10 15:54:59,554][76542] Updated weights for policy 1, policy_version 82660 (0.0007) -[2023-10-10 15:54:59,916][76542] Updated weights for policy 1, policy_version 82670 (0.0008) -[2023-10-10 15:55:00,290][76542] Updated weights for policy 1, policy_version 82680 (0.0008) -[2023-10-10 15:55:01,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 169508864. Throughput: 0: 1820.9, 1: 1823.1. Samples: 42383350. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 15:55:01,077][75634] Avg episode reward: [(0, '35.390'), (1, '37.400')] -[2023-10-10 15:55:02,789][76543] Updated weights for policy 0, policy_version 82853 (0.0010) -[2023-10-10 15:55:03,168][76543] Updated weights for policy 0, policy_version 82863 (0.0010) -[2023-10-10 15:55:03,544][76543] Updated weights for policy 0, policy_version 82873 (0.0007) -[2023-10-10 15:55:03,884][76542] Updated weights for policy 1, policy_version 82690 (0.0010) -[2023-10-10 15:55:04,257][76542] Updated weights for policy 1, policy_version 82700 (0.0008) -[2023-10-10 15:55:04,629][76542] Updated weights for policy 1, policy_version 82710 (0.0011) -[2023-10-10 15:55:05,000][76542] Updated weights for policy 1, policy_version 82720 (0.0009) -[2023-10-10 15:55:06,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 169574400. Throughput: 0: 1815.9, 1: 1836.8. Samples: 42395462. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 15:55:06,077][75634] Avg episode reward: [(0, '36.940'), (1, '33.820')] -[2023-10-10 15:55:07,209][76543] Updated weights for policy 0, policy_version 82883 (0.0007) -[2023-10-10 15:55:07,574][76543] Updated weights for policy 0, policy_version 82893 (0.0008) -[2023-10-10 15:55:07,943][76543] Updated weights for policy 0, policy_version 82903 (0.0008) -[2023-10-10 15:55:08,716][76542] Updated weights for policy 1, policy_version 82730 (0.0009) -[2023-10-10 15:55:09,088][76542] Updated weights for policy 1, policy_version 82740 (0.0010) -[2023-10-10 15:55:09,459][76542] Updated weights for policy 1, policy_version 82750 (0.0008) -[2023-10-10 15:55:11,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 169639936. Throughput: 0: 1814.9, 1: 1825.4. Samples: 42416044. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 15:55:11,076][75634] Avg episode reward: [(0, '37.700'), (1, '35.020')] -[2023-10-10 15:55:11,785][76543] Updated weights for policy 0, policy_version 82913 (0.0009) -[2023-10-10 15:55:12,184][76543] Updated weights for policy 0, policy_version 82923 (0.0009) -[2023-10-10 15:55:12,551][76543] Updated weights for policy 0, policy_version 82933 (0.0007) -[2023-10-10 15:55:12,923][76543] Updated weights for policy 0, policy_version 82943 (0.0007) -[2023-10-10 15:55:13,153][76542] Updated weights for policy 1, policy_version 82760 (0.0007) -[2023-10-10 15:55:13,518][76542] Updated weights for policy 1, policy_version 82770 (0.0008) -[2023-10-10 15:55:13,883][76542] Updated weights for policy 1, policy_version 82780 (0.0010) -[2023-10-10 15:55:16,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 169705472. Throughput: 0: 1814.6, 1: 1830.0. Samples: 42438834. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 15:55:16,077][75634] Avg episode reward: [(0, '38.410'), (1, '33.670')] -[2023-10-10 15:55:16,607][76543] Updated weights for policy 0, policy_version 82953 (0.0008) -[2023-10-10 15:55:16,968][76543] Updated weights for policy 0, policy_version 82963 (0.0011) -[2023-10-10 15:55:17,337][76543] Updated weights for policy 0, policy_version 82973 (0.0011) -[2023-10-10 15:55:17,634][76542] Updated weights for policy 1, policy_version 82790 (0.0011) -[2023-10-10 15:55:18,008][76542] Updated weights for policy 1, policy_version 82800 (0.0009) -[2023-10-10 15:55:18,370][76542] Updated weights for policy 1, policy_version 82810 (0.0007) -[2023-10-10 15:55:21,048][76543] Updated weights for policy 0, policy_version 82983 (0.0010) -[2023-10-10 15:55:21,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 169771008. Throughput: 0: 1817.3, 1: 1823.6. Samples: 42448924. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 15:55:21,077][75634] Avg episode reward: [(0, '37.450'), (1, '33.680')] -[2023-10-10 15:55:21,413][76543] Updated weights for policy 0, policy_version 82993 (0.0009) -[2023-10-10 15:55:21,781][76543] Updated weights for policy 0, policy_version 83003 (0.0008) -[2023-10-10 15:55:22,175][76542] Updated weights for policy 1, policy_version 82820 (0.0009) -[2023-10-10 15:55:22,538][76542] Updated weights for policy 1, policy_version 82830 (0.0008) -[2023-10-10 15:55:22,909][76542] Updated weights for policy 1, policy_version 82840 (0.0007) -[2023-10-10 15:55:25,490][76543] Updated weights for policy 0, policy_version 83013 (0.0009) -[2023-10-10 15:55:25,863][76543] Updated weights for policy 0, policy_version 83023 (0.0009) -[2023-10-10 15:55:26,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 169836544. Throughput: 0: 1820.6, 1: 1823.9. Samples: 42471622. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-10 15:55:26,076][75634] Avg episode reward: [(0, '33.500'), (1, '30.870')] -[2023-10-10 15:55:26,217][76543] Updated weights for policy 0, policy_version 83033 (0.0008) -[2023-10-10 15:55:26,565][76542] Updated weights for policy 1, policy_version 82850 (0.0010) -[2023-10-10 15:55:26,933][76542] Updated weights for policy 1, policy_version 82860 (0.0011) -[2023-10-10 15:55:27,303][76542] Updated weights for policy 1, policy_version 82870 (0.0011) -[2023-10-10 15:55:27,666][76542] Updated weights for policy 1, policy_version 82880 (0.0009) -[2023-10-10 15:55:29,850][76543] Updated weights for policy 0, policy_version 83043 (0.0008) -[2023-10-10 15:55:30,230][76543] Updated weights for policy 0, policy_version 83053 (0.0008) -[2023-10-10 15:55:30,599][76543] Updated weights for policy 0, policy_version 83063 (0.0011) -[2023-10-10 15:55:31,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 169934848. Throughput: 0: 1819.6, 1: 1820.6. Samples: 42493790. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:55:31,076][75634] Avg episode reward: [(0, '36.340'), (1, '34.460')] -[2023-10-10 15:55:31,563][76542] Updated weights for policy 1, policy_version 82890 (0.0010) -[2023-10-10 15:55:31,935][76542] Updated weights for policy 1, policy_version 82900 (0.0008) -[2023-10-10 15:55:32,295][76542] Updated weights for policy 1, policy_version 82910 (0.0010) -[2023-10-10 15:55:34,155][76543] Updated weights for policy 0, policy_version 83073 (0.0009) -[2023-10-10 15:55:34,524][76543] Updated weights for policy 0, policy_version 83083 (0.0008) -[2023-10-10 15:55:34,900][76543] Updated weights for policy 0, policy_version 83093 (0.0009) -[2023-10-10 15:55:35,270][76543] Updated weights for policy 0, policy_version 83103 (0.0011) -[2023-10-10 15:55:36,044][76542] Updated weights for policy 1, policy_version 82920 (0.0008) -[2023-10-10 15:55:36,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 170000384. Throughput: 0: 1823.4, 1: 1823.1. Samples: 42504332. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:55:36,076][75634] Avg episode reward: [(0, '36.710'), (1, '38.050')] -[2023-10-10 15:55:36,413][76542] Updated weights for policy 1, policy_version 82930 (0.0008) -[2023-10-10 15:55:36,780][76542] Updated weights for policy 1, policy_version 82940 (0.0008) -[2023-10-10 15:55:39,054][76543] Updated weights for policy 0, policy_version 83113 (0.0009) -[2023-10-10 15:55:39,427][76543] Updated weights for policy 0, policy_version 83123 (0.0011) -[2023-10-10 15:55:39,782][76543] Updated weights for policy 0, policy_version 83133 (0.0010) -[2023-10-10 15:55:40,533][76542] Updated weights for policy 1, policy_version 82950 (0.0008) -[2023-10-10 15:55:40,905][76542] Updated weights for policy 1, policy_version 82960 (0.0008) -[2023-10-10 15:55:41,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 170065920. Throughput: 0: 1823.7, 1: 1823.5. Samples: 42526542. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:55:41,076][75634] Avg episode reward: [(0, '33.530'), (1, '37.470')] -[2023-10-10 15:55:41,271][76542] Updated weights for policy 1, policy_version 82970 (0.0009) -[2023-10-10 15:55:43,491][76543] Updated weights for policy 0, policy_version 83143 (0.0007) -[2023-10-10 15:55:43,862][76543] Updated weights for policy 0, policy_version 83153 (0.0008) -[2023-10-10 15:55:44,234][76543] Updated weights for policy 0, policy_version 83163 (0.0009) -[2023-10-10 15:55:44,835][76542] Updated weights for policy 1, policy_version 82980 (0.0009) -[2023-10-10 15:55:45,201][76542] Updated weights for policy 1, policy_version 82990 (0.0010) -[2023-10-10 15:55:45,569][76542] Updated weights for policy 1, policy_version 83000 (0.0009) -[2023-10-10 15:55:46,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 170164224. Throughput: 0: 1817.0, 1: 1825.9. Samples: 42547282. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:55:46,077][75634] Avg episode reward: [(0, '33.840'), (1, '34.830')] -[2023-10-10 15:55:47,790][76543] Updated weights for policy 0, policy_version 83173 (0.0009) -[2023-10-10 15:55:48,158][76543] Updated weights for policy 0, policy_version 83183 (0.0010) -[2023-10-10 15:55:48,533][76543] Updated weights for policy 0, policy_version 83193 (0.0008) -[2023-10-10 15:55:48,998][76542] Updated weights for policy 1, policy_version 83010 (0.0008) -[2023-10-10 15:55:49,377][76542] Updated weights for policy 1, policy_version 83020 (0.0009) -[2023-10-10 15:55:49,740][76542] Updated weights for policy 1, policy_version 83030 (0.0007) -[2023-10-10 15:55:50,109][76542] Updated weights for policy 1, policy_version 83040 (0.0008) -[2023-10-10 15:55:51,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 170229760. Throughput: 0: 1821.2, 1: 1825.1. Samples: 42559548. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:55:51,077][75634] Avg episode reward: [(0, '34.690'), (1, '33.240')] -[2023-10-10 15:55:52,087][76543] Updated weights for policy 0, policy_version 83203 (0.0007) -[2023-10-10 15:55:52,448][76543] Updated weights for policy 0, policy_version 83213 (0.0008) -[2023-10-10 15:55:52,816][76543] Updated weights for policy 0, policy_version 83223 (0.0008) -[2023-10-10 15:55:53,798][76542] Updated weights for policy 1, policy_version 83050 (0.0008) -[2023-10-10 15:55:54,161][76542] Updated weights for policy 1, policy_version 83060 (0.0008) -[2023-10-10 15:55:54,524][76542] Updated weights for policy 1, policy_version 83070 (0.0011) -[2023-10-10 15:55:56,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 170295296. Throughput: 0: 1833.5, 1: 1824.1. Samples: 42580636. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:55:56,076][75634] Avg episode reward: [(0, '38.200'), (1, '33.130')] -[2023-10-10 15:55:56,494][76543] Updated weights for policy 0, policy_version 83233 (0.0007) -[2023-10-10 15:55:56,902][76543] Updated weights for policy 0, policy_version 83243 (0.0008) -[2023-10-10 15:55:57,274][76543] Updated weights for policy 0, policy_version 83253 (0.0011) -[2023-10-10 15:55:57,638][76543] Updated weights for policy 0, policy_version 83263 (0.0008) -[2023-10-10 15:55:58,156][76542] Updated weights for policy 1, policy_version 83080 (0.0010) -[2023-10-10 15:55:58,525][76542] Updated weights for policy 1, policy_version 83090 (0.0008) -[2023-10-10 15:55:58,892][76542] Updated weights for policy 1, policy_version 83100 (0.0008) -[2023-10-10 15:56:01,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 170360832. Throughput: 0: 1831.4, 1: 1822.0. Samples: 42603234. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:56:01,076][75634] Avg episode reward: [(0, '38.900'), (1, '35.200')] -[2023-10-10 15:56:01,416][76543] Updated weights for policy 0, policy_version 83273 (0.0008) -[2023-10-10 15:56:01,788][76543] Updated weights for policy 0, policy_version 83283 (0.0011) -[2023-10-10 15:56:02,154][76543] Updated weights for policy 0, policy_version 83293 (0.0010) -[2023-10-10 15:56:02,873][76542] Updated weights for policy 1, policy_version 83110 (0.0009) -[2023-10-10 15:56:03,229][76542] Updated weights for policy 1, policy_version 83120 (0.0009) -[2023-10-10 15:56:03,593][76542] Updated weights for policy 1, policy_version 83130 (0.0008) -[2023-10-10 15:56:05,890][76543] Updated weights for policy 0, policy_version 83303 (0.0007) -[2023-10-10 15:56:06,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 170426368. Throughput: 0: 1826.9, 1: 1822.5. Samples: 42613148. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:56:06,077][75634] Avg episode reward: [(0, '36.700'), (1, '33.420')] -[2023-10-10 15:56:06,253][76543] Updated weights for policy 0, policy_version 83313 (0.0008) -[2023-10-10 15:56:06,625][76543] Updated weights for policy 0, policy_version 83323 (0.0008) -[2023-10-10 15:56:07,061][76542] Updated weights for policy 1, policy_version 83140 (0.0010) -[2023-10-10 15:56:07,430][76542] Updated weights for policy 1, policy_version 83150 (0.0008) -[2023-10-10 15:56:07,803][76542] Updated weights for policy 1, policy_version 83160 (0.0007) -[2023-10-10 15:56:10,383][76543] Updated weights for policy 0, policy_version 83333 (0.0010) -[2023-10-10 15:56:10,749][76543] Updated weights for policy 0, policy_version 83343 (0.0009) -[2023-10-10 15:56:11,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 170491904. Throughput: 0: 1832.7, 1: 1825.2. Samples: 42636228. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:56:11,077][75634] Avg episode reward: [(0, '40.480'), (1, '35.110')] -[2023-10-10 15:56:11,130][76543] Updated weights for policy 0, policy_version 83353 (0.0007) -[2023-10-10 15:56:11,455][76542] Updated weights for policy 1, policy_version 83170 (0.0008) -[2023-10-10 15:56:11,820][76542] Updated weights for policy 1, policy_version 83180 (0.0007) -[2023-10-10 15:56:12,185][76542] Updated weights for policy 1, policy_version 83190 (0.0008) -[2023-10-10 15:56:12,550][76542] Updated weights for policy 1, policy_version 83200 (0.0007) -[2023-10-10 15:56:14,566][76543] Updated weights for policy 0, policy_version 83363 (0.0007) -[2023-10-10 15:56:14,944][76543] Updated weights for policy 0, policy_version 83373 (0.0010) -[2023-10-10 15:56:15,319][76543] Updated weights for policy 0, policy_version 83383 (0.0010) -[2023-10-10 15:56:16,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 170590208. Throughput: 0: 1827.7, 1: 1824.0. Samples: 42658118. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:56:16,076][75634] Avg episode reward: [(0, '37.590'), (1, '40.590')] -[2023-10-10 15:56:16,305][76542] Updated weights for policy 1, policy_version 83210 (0.0012) -[2023-10-10 15:56:16,670][76542] Updated weights for policy 1, policy_version 83220 (0.0007) -[2023-10-10 15:56:17,036][76542] Updated weights for policy 1, policy_version 83230 (0.0008) -[2023-10-10 15:56:18,847][76543] Updated weights for policy 0, policy_version 83393 (0.0007) -[2023-10-10 15:56:19,225][76543] Updated weights for policy 0, policy_version 83403 (0.0008) -[2023-10-10 15:56:19,596][76543] Updated weights for policy 0, policy_version 83413 (0.0008) -[2023-10-10 15:56:19,965][76543] Updated weights for policy 0, policy_version 83423 (0.0010) -[2023-10-10 15:56:20,725][76542] Updated weights for policy 1, policy_version 83240 (0.0009) -[2023-10-10 15:56:21,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 170655744. Throughput: 0: 1830.8, 1: 1827.8. Samples: 42668968. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) -[2023-10-10 15:56:21,076][75634] Avg episode reward: [(0, '38.090'), (1, '41.480')] -[2023-10-10 15:56:21,106][76542] Updated weights for policy 1, policy_version 83250 (0.0007) -[2023-10-10 15:56:21,477][76542] Updated weights for policy 1, policy_version 83260 (0.0008) -[2023-10-10 15:56:23,770][76543] Updated weights for policy 0, policy_version 83433 (0.0007) -[2023-10-10 15:56:24,145][76543] Updated weights for policy 0, policy_version 83443 (0.0007) -[2023-10-10 15:56:24,513][76543] Updated weights for policy 0, policy_version 83453 (0.0009) -[2023-10-10 15:56:25,298][76542] Updated weights for policy 1, policy_version 83270 (0.0010) -[2023-10-10 15:56:25,664][76542] Updated weights for policy 1, policy_version 83280 (0.0010) -[2023-10-10 15:56:26,035][76542] Updated weights for policy 1, policy_version 83290 (0.0009) -[2023-10-10 15:56:26,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 170721280. Throughput: 0: 1820.1, 1: 1824.3. Samples: 42690538. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) -[2023-10-10 15:56:26,076][75634] Avg episode reward: [(0, '41.350'), (1, '36.700')] -[2023-10-10 15:56:28,329][76543] Updated weights for policy 0, policy_version 83463 (0.0009) -[2023-10-10 15:56:28,699][76543] Updated weights for policy 0, policy_version 83473 (0.0008) -[2023-10-10 15:56:29,073][76543] Updated weights for policy 0, policy_version 83483 (0.0010) -[2023-10-10 15:56:29,665][76542] Updated weights for policy 1, policy_version 83300 (0.0009) -[2023-10-10 15:56:30,042][76542] Updated weights for policy 1, policy_version 83310 (0.0009) -[2023-10-10 15:56:30,418][76542] Updated weights for policy 1, policy_version 83320 (0.0007) -[2023-10-10 15:56:31,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 170819584. Throughput: 0: 1828.8, 1: 1818.3. Samples: 42711398. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) -[2023-10-10 15:56:31,076][75634] Avg episode reward: [(0, '41.080'), (1, '37.310')] -[2023-10-10 15:56:31,086][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000083488_85491712.pth... -[2023-10-10 15:56:31,087][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000083328_85327872.pth... -[2023-10-10 15:56:31,128][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000081792_83755008.pth -[2023-10-10 15:56:31,128][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000081600_83558400.pth -[2023-10-10 15:56:32,759][76543] Updated weights for policy 0, policy_version 83493 (0.0010) -[2023-10-10 15:56:33,117][76543] Updated weights for policy 0, policy_version 83503 (0.0010) -[2023-10-10 15:56:33,484][76543] Updated weights for policy 0, policy_version 83513 (0.0010) -[2023-10-10 15:56:34,166][76542] Updated weights for policy 1, policy_version 83330 (0.0009) -[2023-10-10 15:56:34,534][76542] Updated weights for policy 1, policy_version 83340 (0.0009) -[2023-10-10 15:56:34,902][76542] Updated weights for policy 1, policy_version 83350 (0.0011) -[2023-10-10 15:56:35,275][76542] Updated weights for policy 1, policy_version 83360 (0.0008) -[2023-10-10 15:56:36,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 170885120. Throughput: 0: 1826.6, 1: 1816.1. Samples: 42723468. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) -[2023-10-10 15:56:36,076][75634] Avg episode reward: [(0, '45.310'), (1, '36.160')] -[2023-10-10 15:56:36,077][76362] Saving new best policy, reward=45.310! -[2023-10-10 15:56:37,097][76543] Updated weights for policy 0, policy_version 83523 (0.0007) -[2023-10-10 15:56:37,465][76543] Updated weights for policy 0, policy_version 83533 (0.0008) -[2023-10-10 15:56:37,839][76543] Updated weights for policy 0, policy_version 83543 (0.0008) -[2023-10-10 15:56:38,889][76542] Updated weights for policy 1, policy_version 83370 (0.0008) -[2023-10-10 15:56:39,261][76542] Updated weights for policy 1, policy_version 83380 (0.0010) -[2023-10-10 15:56:39,629][76542] Updated weights for policy 1, policy_version 83390 (0.0009) -[2023-10-10 15:56:41,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 170950656. Throughput: 0: 1819.8, 1: 1815.4. Samples: 42744220. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) -[2023-10-10 15:56:41,076][75634] Avg episode reward: [(0, '47.340'), (1, '40.130')] -[2023-10-10 15:56:41,077][76362] Saving new best policy, reward=47.340! -[2023-10-10 15:56:41,590][76543] Updated weights for policy 0, policy_version 83553 (0.0008) -[2023-10-10 15:56:42,013][76543] Updated weights for policy 0, policy_version 83563 (0.0008) -[2023-10-10 15:56:42,388][76543] Updated weights for policy 0, policy_version 83573 (0.0010) -[2023-10-10 15:56:42,756][76543] Updated weights for policy 0, policy_version 83583 (0.0009) -[2023-10-10 15:56:43,234][76542] Updated weights for policy 1, policy_version 83400 (0.0008) -[2023-10-10 15:56:43,604][76542] Updated weights for policy 1, policy_version 83410 (0.0009) -[2023-10-10 15:56:43,976][76542] Updated weights for policy 1, policy_version 83420 (0.0009) -[2023-10-10 15:56:46,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 171016192. Throughput: 0: 1825.7, 1: 1813.4. Samples: 42766996. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) -[2023-10-10 15:56:46,077][75634] Avg episode reward: [(0, '45.870'), (1, '31.680')] -[2023-10-10 15:56:46,235][76543] Updated weights for policy 0, policy_version 83593 (0.0007) -[2023-10-10 15:56:46,603][76543] Updated weights for policy 0, policy_version 83603 (0.0007) -[2023-10-10 15:56:46,982][76543] Updated weights for policy 0, policy_version 83613 (0.0009) -[2023-10-10 15:56:47,699][76542] Updated weights for policy 1, policy_version 83430 (0.0008) -[2023-10-10 15:56:48,065][76542] Updated weights for policy 1, policy_version 83440 (0.0008) -[2023-10-10 15:56:48,437][76542] Updated weights for policy 1, policy_version 83450 (0.0009) -[2023-10-10 15:56:50,528][76543] Updated weights for policy 0, policy_version 83623 (0.0007) -[2023-10-10 15:56:50,890][76543] Updated weights for policy 0, policy_version 83633 (0.0008) -[2023-10-10 15:56:51,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 171081728. Throughput: 0: 1831.0, 1: 1812.3. Samples: 42777096. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) -[2023-10-10 15:56:51,077][75634] Avg episode reward: [(0, '44.190'), (1, '32.810')] -[2023-10-10 15:56:51,262][76543] Updated weights for policy 0, policy_version 83643 (0.0009) -[2023-10-10 15:56:52,186][76542] Updated weights for policy 1, policy_version 83460 (0.0007) -[2023-10-10 15:56:52,554][76542] Updated weights for policy 1, policy_version 83470 (0.0008) -[2023-10-10 15:56:52,925][76542] Updated weights for policy 1, policy_version 83480 (0.0008) -[2023-10-10 15:56:54,968][76543] Updated weights for policy 0, policy_version 83653 (0.0009) -[2023-10-10 15:56:55,337][76543] Updated weights for policy 0, policy_version 83663 (0.0008) -[2023-10-10 15:56:55,713][76543] Updated weights for policy 0, policy_version 83673 (0.0007) -[2023-10-10 15:56:56,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 171180032. Throughput: 0: 1832.5, 1: 1812.1. Samples: 42800236. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) -[2023-10-10 15:56:56,076][75634] Avg episode reward: [(0, '37.360'), (1, '35.470')] -[2023-10-10 15:56:56,503][76542] Updated weights for policy 1, policy_version 83490 (0.0007) -[2023-10-10 15:56:56,872][76542] Updated weights for policy 1, policy_version 83500 (0.0008) -[2023-10-10 15:56:57,247][76542] Updated weights for policy 1, policy_version 83510 (0.0009) -[2023-10-10 15:56:57,620][76542] Updated weights for policy 1, policy_version 83520 (0.0011) -[2023-10-10 15:56:59,244][76543] Updated weights for policy 0, policy_version 83683 (0.0009) -[2023-10-10 15:56:59,614][76543] Updated weights for policy 0, policy_version 83693 (0.0011) -[2023-10-10 15:56:59,979][76543] Updated weights for policy 0, policy_version 83703 (0.0009) -[2023-10-10 15:57:01,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 171245568. Throughput: 0: 1824.4, 1: 1808.4. Samples: 42821594. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) -[2023-10-10 15:57:01,077][75634] Avg episode reward: [(0, '37.290'), (1, '35.860')] -[2023-10-10 15:57:01,476][76542] Updated weights for policy 1, policy_version 83530 (0.0009) -[2023-10-10 15:57:01,838][76542] Updated weights for policy 1, policy_version 83540 (0.0009) -[2023-10-10 15:57:02,208][76542] Updated weights for policy 1, policy_version 83550 (0.0007) -[2023-10-10 15:57:03,620][76543] Updated weights for policy 0, policy_version 83713 (0.0009) -[2023-10-10 15:57:03,986][76543] Updated weights for policy 0, policy_version 83723 (0.0010) -[2023-10-10 15:57:04,367][76543] Updated weights for policy 0, policy_version 83733 (0.0011) -[2023-10-10 15:57:04,735][76543] Updated weights for policy 0, policy_version 83743 (0.0011) -[2023-10-10 15:57:06,004][76542] Updated weights for policy 1, policy_version 83560 (0.0010) -[2023-10-10 15:57:06,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 171311104. Throughput: 0: 1841.0, 1: 1807.7. Samples: 42833160. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) -[2023-10-10 15:57:06,077][75634] Avg episode reward: [(0, '37.300'), (1, '33.950')] -[2023-10-10 15:57:06,381][76542] Updated weights for policy 1, policy_version 83570 (0.0008) -[2023-10-10 15:57:06,750][76542] Updated weights for policy 1, policy_version 83580 (0.0008) -[2023-10-10 15:57:08,416][76543] Updated weights for policy 0, policy_version 83753 (0.0008) -[2023-10-10 15:57:08,793][76543] Updated weights for policy 0, policy_version 83763 (0.0009) -[2023-10-10 15:57:09,160][76543] Updated weights for policy 0, policy_version 83773 (0.0009) -[2023-10-10 15:57:10,486][76542] Updated weights for policy 1, policy_version 83590 (0.0008) -[2023-10-10 15:57:10,849][76542] Updated weights for policy 1, policy_version 83600 (0.0007) -[2023-10-10 15:57:11,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 171376640. Throughput: 0: 1834.5, 1: 1805.9. Samples: 42854360. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) -[2023-10-10 15:57:11,077][75634] Avg episode reward: [(0, '37.110'), (1, '31.460')] -[2023-10-10 15:57:11,206][76542] Updated weights for policy 1, policy_version 83610 (0.0007) -[2023-10-10 15:57:12,910][76543] Updated weights for policy 0, policy_version 83783 (0.0009) -[2023-10-10 15:57:13,271][76543] Updated weights for policy 0, policy_version 83793 (0.0008) -[2023-10-10 15:57:13,644][76543] Updated weights for policy 0, policy_version 83803 (0.0008) -[2023-10-10 15:57:14,629][76542] Updated weights for policy 1, policy_version 83620 (0.0008) -[2023-10-10 15:57:14,983][76542] Updated weights for policy 1, policy_version 83630 (0.0008) -[2023-10-10 15:57:15,357][76542] Updated weights for policy 1, policy_version 83640 (0.0010) -[2023-10-10 15:57:16,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 171474944. Throughput: 0: 1845.7, 1: 1813.5. Samples: 42876062. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-10 15:57:16,076][75634] Avg episode reward: [(0, '35.990'), (1, '32.340')] -[2023-10-10 15:57:17,195][76543] Updated weights for policy 0, policy_version 83813 (0.0009) -[2023-10-10 15:57:17,569][76543] Updated weights for policy 0, policy_version 83823 (0.0010) -[2023-10-10 15:57:17,941][76543] Updated weights for policy 0, policy_version 83833 (0.0011) -[2023-10-10 15:57:18,970][76542] Updated weights for policy 1, policy_version 83650 (0.0010) -[2023-10-10 15:57:19,341][76542] Updated weights for policy 1, policy_version 83660 (0.0008) -[2023-10-10 15:57:19,717][76542] Updated weights for policy 1, policy_version 83670 (0.0010) -[2023-10-10 15:57:20,079][76542] Updated weights for policy 1, policy_version 83680 (0.0009) -[2023-10-10 15:57:21,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 171540480. Throughput: 0: 1830.0, 1: 1820.1. Samples: 42887724. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-10 15:57:21,077][75634] Avg episode reward: [(0, '38.710'), (1, '38.750')] -[2023-10-10 15:57:21,696][76543] Updated weights for policy 0, policy_version 83843 (0.0009) -[2023-10-10 15:57:22,070][76543] Updated weights for policy 0, policy_version 83853 (0.0008) -[2023-10-10 15:57:22,446][76543] Updated weights for policy 0, policy_version 83863 (0.0010) -[2023-10-10 15:57:23,851][76542] Updated weights for policy 1, policy_version 83690 (0.0009) -[2023-10-10 15:57:24,216][76542] Updated weights for policy 1, policy_version 83700 (0.0008) -[2023-10-10 15:57:24,591][76542] Updated weights for policy 1, policy_version 83710 (0.0008) -[2023-10-10 15:57:26,005][76543] Updated weights for policy 0, policy_version 83873 (0.0008) -[2023-10-10 15:57:26,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 171606016. Throughput: 0: 1843.5, 1: 1821.3. Samples: 42909138. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-10 15:57:26,077][75634] Avg episode reward: [(0, '38.650'), (1, '36.820')] -[2023-10-10 15:57:26,375][76543] Updated weights for policy 0, policy_version 83883 (0.0009) -[2023-10-10 15:57:26,750][76543] Updated weights for policy 0, policy_version 83893 (0.0009) -[2023-10-10 15:57:27,112][76543] Updated weights for policy 0, policy_version 83903 (0.0007) -[2023-10-10 15:57:28,109][76542] Updated weights for policy 1, policy_version 83720 (0.0009) -[2023-10-10 15:57:28,471][76542] Updated weights for policy 1, policy_version 83730 (0.0008) -[2023-10-10 15:57:28,837][76542] Updated weights for policy 1, policy_version 83740 (0.0007) -[2023-10-10 15:57:30,835][76543] Updated weights for policy 0, policy_version 83913 (0.0010) -[2023-10-10 15:57:31,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 171671552. Throughput: 0: 1846.4, 1: 1830.9. Samples: 42932474. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-10 15:57:31,076][75634] Avg episode reward: [(0, '38.990'), (1, '36.070')] -[2023-10-10 15:57:31,207][76543] Updated weights for policy 0, policy_version 83923 (0.0010) -[2023-10-10 15:57:31,577][76543] Updated weights for policy 0, policy_version 83933 (0.0009) -[2023-10-10 15:57:32,615][76542] Updated weights for policy 1, policy_version 83750 (0.0009) -[2023-10-10 15:57:32,982][76542] Updated weights for policy 1, policy_version 83760 (0.0008) -[2023-10-10 15:57:33,351][76542] Updated weights for policy 1, policy_version 83770 (0.0009) -[2023-10-10 15:57:35,010][76543] Updated weights for policy 0, policy_version 83943 (0.0007) -[2023-10-10 15:57:35,379][76543] Updated weights for policy 0, policy_version 83953 (0.0007) -[2023-10-10 15:57:35,756][76543] Updated weights for policy 0, policy_version 83963 (0.0008) -[2023-10-10 15:57:36,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 171769856. Throughput: 0: 1841.3, 1: 1829.6. Samples: 42942284. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-10 15:57:36,076][75634] Avg episode reward: [(0, '34.030'), (1, '37.630')] -[2023-10-10 15:57:37,009][76542] Updated weights for policy 1, policy_version 83780 (0.0010) -[2023-10-10 15:57:37,378][76542] Updated weights for policy 1, policy_version 83790 (0.0010) -[2023-10-10 15:57:37,745][76542] Updated weights for policy 1, policy_version 83800 (0.0010) -[2023-10-10 15:57:39,571][76543] Updated weights for policy 0, policy_version 83973 (0.0008) -[2023-10-10 15:57:39,945][76543] Updated weights for policy 0, policy_version 83983 (0.0008) -[2023-10-10 15:57:40,326][76543] Updated weights for policy 0, policy_version 83993 (0.0008) -[2023-10-10 15:57:41,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 171835392. Throughput: 0: 1838.3, 1: 1832.0. Samples: 42965398. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-10 15:57:41,076][75634] Avg episode reward: [(0, '30.170'), (1, '35.740')] -[2023-10-10 15:57:41,415][76542] Updated weights for policy 1, policy_version 83810 (0.0010) -[2023-10-10 15:57:41,783][76542] Updated weights for policy 1, policy_version 83820 (0.0007) -[2023-10-10 15:57:42,144][76542] Updated weights for policy 1, policy_version 83830 (0.0008) -[2023-10-10 15:57:42,511][76542] Updated weights for policy 1, policy_version 83840 (0.0008) -[2023-10-10 15:57:43,873][76543] Updated weights for policy 0, policy_version 84003 (0.0007) -[2023-10-10 15:57:44,250][76543] Updated weights for policy 0, policy_version 84013 (0.0007) -[2023-10-10 15:57:44,618][76543] Updated weights for policy 0, policy_version 84023 (0.0009) -[2023-10-10 15:57:46,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 171900928. Throughput: 0: 1837.1, 1: 1837.7. Samples: 42986960. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-10 15:57:46,076][75634] Avg episode reward: [(0, '31.410'), (1, '30.510')] -[2023-10-10 15:57:46,256][76542] Updated weights for policy 1, policy_version 83850 (0.0009) -[2023-10-10 15:57:46,622][76542] Updated weights for policy 1, policy_version 83860 (0.0007) -[2023-10-10 15:57:46,994][76542] Updated weights for policy 1, policy_version 83870 (0.0008) -[2023-10-10 15:57:48,312][76543] Updated weights for policy 0, policy_version 84033 (0.0007) -[2023-10-10 15:57:48,676][76543] Updated weights for policy 0, policy_version 84043 (0.0007) -[2023-10-10 15:57:49,049][76543] Updated weights for policy 0, policy_version 84053 (0.0007) -[2023-10-10 15:57:49,416][76543] Updated weights for policy 0, policy_version 84063 (0.0008) -[2023-10-10 15:57:50,698][76542] Updated weights for policy 1, policy_version 83880 (0.0009) -[2023-10-10 15:57:51,062][76542] Updated weights for policy 1, policy_version 83890 (0.0010) -[2023-10-10 15:57:51,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 171966464. Throughput: 0: 1835.0, 1: 1838.6. Samples: 42998474. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-10 15:57:51,076][75634] Avg episode reward: [(0, '31.610'), (1, '31.780')] -[2023-10-10 15:57:51,423][76542] Updated weights for policy 1, policy_version 83900 (0.0007) -[2023-10-10 15:57:53,130][76543] Updated weights for policy 0, policy_version 84073 (0.0008) -[2023-10-10 15:57:53,495][76543] Updated weights for policy 0, policy_version 84083 (0.0009) -[2023-10-10 15:57:53,876][76543] Updated weights for policy 0, policy_version 84093 (0.0010) -[2023-10-10 15:57:55,089][76542] Updated weights for policy 1, policy_version 83910 (0.0007) -[2023-10-10 15:57:55,459][76542] Updated weights for policy 1, policy_version 83920 (0.0007) -[2023-10-10 15:57:55,813][76542] Updated weights for policy 1, policy_version 83930 (0.0007) -[2023-10-10 15:57:56,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 172064768. Throughput: 0: 1836.6, 1: 1843.3. Samples: 43019956. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-10 15:57:56,077][75634] Avg episode reward: [(0, '35.500'), (1, '31.650')] -[2023-10-10 15:57:57,430][76543] Updated weights for policy 0, policy_version 84103 (0.0008) -[2023-10-10 15:57:57,799][76543] Updated weights for policy 0, policy_version 84113 (0.0010) -[2023-10-10 15:57:58,174][76543] Updated weights for policy 0, policy_version 84123 (0.0009) -[2023-10-10 15:57:59,505][76542] Updated weights for policy 1, policy_version 83940 (0.0009) -[2023-10-10 15:57:59,870][76542] Updated weights for policy 1, policy_version 83950 (0.0011) -[2023-10-10 15:58:00,241][76542] Updated weights for policy 1, policy_version 83960 (0.0009) -[2023-10-10 15:58:01,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 172130304. Throughput: 0: 1842.0, 1: 1832.0. Samples: 43041394. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-10 15:58:01,076][75634] Avg episode reward: [(0, '36.120'), (1, '35.090')] -[2023-10-10 15:58:01,824][76543] Updated weights for policy 0, policy_version 84133 (0.0008) -[2023-10-10 15:58:02,199][76543] Updated weights for policy 0, policy_version 84143 (0.0010) -[2023-10-10 15:58:02,569][76543] Updated weights for policy 0, policy_version 84153 (0.0008) -[2023-10-10 15:58:03,862][76542] Updated weights for policy 1, policy_version 83970 (0.0009) -[2023-10-10 15:58:04,234][76542] Updated weights for policy 1, policy_version 83980 (0.0007) -[2023-10-10 15:58:04,594][76542] Updated weights for policy 1, policy_version 83990 (0.0008) -[2023-10-10 15:58:04,966][76542] Updated weights for policy 1, policy_version 84000 (0.0007) -[2023-10-10 15:58:06,061][76543] Updated weights for policy 0, policy_version 84163 (0.0008) -[2023-10-10 15:58:06,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 172195840. Throughput: 0: 1840.8, 1: 1831.6. Samples: 43052986. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-10 15:58:06,076][75634] Avg episode reward: [(0, '37.130'), (1, '37.560')] -[2023-10-10 15:58:06,429][76543] Updated weights for policy 0, policy_version 84173 (0.0007) -[2023-10-10 15:58:06,805][76543] Updated weights for policy 0, policy_version 84183 (0.0007) -[2023-10-10 15:58:08,646][76542] Updated weights for policy 1, policy_version 84010 (0.0011) -[2023-10-10 15:58:09,015][76542] Updated weights for policy 1, policy_version 84020 (0.0009) -[2023-10-10 15:58:09,375][76542] Updated weights for policy 1, policy_version 84030 (0.0009) -[2023-10-10 15:58:10,499][76543] Updated weights for policy 0, policy_version 84193 (0.0009) -[2023-10-10 15:58:10,865][76543] Updated weights for policy 0, policy_version 84203 (0.0009) -[2023-10-10 15:58:11,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 172261376. Throughput: 0: 1845.1, 1: 1831.3. Samples: 43074576. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-10 15:58:11,076][75634] Avg episode reward: [(0, '34.950'), (1, '37.620')] -[2023-10-10 15:58:11,232][76543] Updated weights for policy 0, policy_version 84213 (0.0009) -[2023-10-10 15:58:11,604][76543] Updated weights for policy 0, policy_version 84223 (0.0009) -[2023-10-10 15:58:12,930][76542] Updated weights for policy 1, policy_version 84040 (0.0011) -[2023-10-10 15:58:13,303][76542] Updated weights for policy 1, policy_version 84050 (0.0010) -[2023-10-10 15:58:13,666][76542] Updated weights for policy 1, policy_version 84060 (0.0011) -[2023-10-10 15:58:15,409][76543] Updated weights for policy 0, policy_version 84233 (0.0008) -[2023-10-10 15:58:15,776][76543] Updated weights for policy 0, policy_version 84243 (0.0008) -[2023-10-10 15:58:16,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 172326912. Throughput: 0: 1829.0, 1: 1830.4. Samples: 43097148. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-10 15:58:16,077][75634] Avg episode reward: [(0, '33.060'), (1, '39.760')] -[2023-10-10 15:58:16,141][76543] Updated weights for policy 0, policy_version 84253 (0.0007) -[2023-10-10 15:58:17,398][76542] Updated weights for policy 1, policy_version 84070 (0.0010) -[2023-10-10 15:58:17,772][76542] Updated weights for policy 1, policy_version 84080 (0.0009) -[2023-10-10 15:58:18,128][76542] Updated weights for policy 1, policy_version 84090 (0.0007) -[2023-10-10 15:58:19,800][76543] Updated weights for policy 0, policy_version 84263 (0.0007) -[2023-10-10 15:58:20,185][76543] Updated weights for policy 0, policy_version 84273 (0.0009) -[2023-10-10 15:58:20,553][76543] Updated weights for policy 0, policy_version 84283 (0.0011) -[2023-10-10 15:58:21,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 172425216. Throughput: 0: 1839.5, 1: 1830.1. Samples: 43107414. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-10 15:58:21,076][75634] Avg episode reward: [(0, '35.290'), (1, '35.910')] -[2023-10-10 15:58:21,842][76542] Updated weights for policy 1, policy_version 84100 (0.0009) -[2023-10-10 15:58:22,215][76542] Updated weights for policy 1, policy_version 84110 (0.0008) -[2023-10-10 15:58:22,575][76542] Updated weights for policy 1, policy_version 84120 (0.0010) -[2023-10-10 15:58:24,236][76543] Updated weights for policy 0, policy_version 84293 (0.0009) -[2023-10-10 15:58:24,596][76543] Updated weights for policy 0, policy_version 84303 (0.0010) -[2023-10-10 15:58:24,965][76543] Updated weights for policy 0, policy_version 84313 (0.0010) -[2023-10-10 15:58:26,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 172490752. Throughput: 0: 1825.6, 1: 1825.8. Samples: 43129708. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-10 15:58:26,076][75634] Avg episode reward: [(0, '35.520'), (1, '32.150')] -[2023-10-10 15:58:26,206][76542] Updated weights for policy 1, policy_version 84130 (0.0008) -[2023-10-10 15:58:26,573][76542] Updated weights for policy 1, policy_version 84140 (0.0010) -[2023-10-10 15:58:26,935][76542] Updated weights for policy 1, policy_version 84150 (0.0009) -[2023-10-10 15:58:27,303][76542] Updated weights for policy 1, policy_version 84160 (0.0008) -[2023-10-10 15:58:28,562][76543] Updated weights for policy 0, policy_version 84323 (0.0008) -[2023-10-10 15:58:28,928][76543] Updated weights for policy 0, policy_version 84333 (0.0009) -[2023-10-10 15:58:29,289][76543] Updated weights for policy 0, policy_version 84343 (0.0007) -[2023-10-10 15:58:31,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 172556288. Throughput: 0: 1830.9, 1: 1822.2. Samples: 43151352. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-10 15:58:31,076][75634] Avg episode reward: [(0, '33.810'), (1, '34.070')] -[2023-10-10 15:58:31,084][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000084352_86376448.pth... -[2023-10-10 15:58:31,114][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000082656_84639744.pth -[2023-10-10 15:58:31,132][76542] Updated weights for policy 1, policy_version 84170 (0.0009) -[2023-10-10 15:58:31,508][76542] Updated weights for policy 1, policy_version 84180 (0.0007) -[2023-10-10 15:58:31,882][76542] Updated weights for policy 1, policy_version 84190 (0.0010) -[2023-10-10 15:58:31,948][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000084192_86212608.pth... -[2023-10-10 15:58:31,988][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000082464_84443136.pth -[2023-10-10 15:58:33,119][76543] Updated weights for policy 0, policy_version 84353 (0.0009) -[2023-10-10 15:58:33,492][76543] Updated weights for policy 0, policy_version 84363 (0.0007) -[2023-10-10 15:58:33,860][76543] Updated weights for policy 0, policy_version 84373 (0.0007) -[2023-10-10 15:58:34,240][76543] Updated weights for policy 0, policy_version 84383 (0.0009) -[2023-10-10 15:58:35,630][76542] Updated weights for policy 1, policy_version 84200 (0.0008) -[2023-10-10 15:58:35,992][76542] Updated weights for policy 1, policy_version 84210 (0.0007) -[2023-10-10 15:58:36,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 172621824. Throughput: 0: 1823.5, 1: 1823.0. Samples: 43162566. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-10 15:58:36,077][75634] Avg episode reward: [(0, '36.230'), (1, '31.200')] -[2023-10-10 15:58:36,364][76542] Updated weights for policy 1, policy_version 84220 (0.0007) -[2023-10-10 15:58:37,932][76543] Updated weights for policy 0, policy_version 84393 (0.0010) -[2023-10-10 15:58:38,305][76543] Updated weights for policy 0, policy_version 84403 (0.0007) -[2023-10-10 15:58:38,672][76543] Updated weights for policy 0, policy_version 84413 (0.0008) -[2023-10-10 15:58:40,152][76542] Updated weights for policy 1, policy_version 84230 (0.0009) -[2023-10-10 15:58:40,517][76542] Updated weights for policy 1, policy_version 84240 (0.0010) -[2023-10-10 15:58:40,886][76542] Updated weights for policy 1, policy_version 84250 (0.0008) -[2023-10-10 15:58:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 172687360. Throughput: 0: 1823.5, 1: 1813.8. Samples: 43183636. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-10 15:58:41,076][75634] Avg episode reward: [(0, '39.190'), (1, '31.020')] -[2023-10-10 15:58:42,364][76543] Updated weights for policy 0, policy_version 84423 (0.0009) -[2023-10-10 15:58:42,735][76543] Updated weights for policy 0, policy_version 84433 (0.0011) -[2023-10-10 15:58:43,108][76543] Updated weights for policy 0, policy_version 84443 (0.0010) -[2023-10-10 15:58:44,595][76542] Updated weights for policy 1, policy_version 84260 (0.0008) -[2023-10-10 15:58:44,967][76542] Updated weights for policy 1, policy_version 84270 (0.0009) -[2023-10-10 15:58:45,325][76542] Updated weights for policy 1, policy_version 84280 (0.0009) -[2023-10-10 15:58:46,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 172785664. Throughput: 0: 1816.3, 1: 1812.1. Samples: 43204672. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-10 15:58:46,077][75634] Avg episode reward: [(0, '41.990'), (1, '34.200')] -[2023-10-10 15:58:46,825][76543] Updated weights for policy 0, policy_version 84453 (0.0010) -[2023-10-10 15:58:47,197][76543] Updated weights for policy 0, policy_version 84463 (0.0010) -[2023-10-10 15:58:47,575][76543] Updated weights for policy 0, policy_version 84473 (0.0010) -[2023-10-10 15:58:49,039][76542] Updated weights for policy 1, policy_version 84290 (0.0008) -[2023-10-10 15:58:49,413][76542] Updated weights for policy 1, policy_version 84300 (0.0008) -[2023-10-10 15:58:49,782][76542] Updated weights for policy 1, policy_version 84310 (0.0008) -[2023-10-10 15:58:50,157][76542] Updated weights for policy 1, policy_version 84320 (0.0008) -[2023-10-10 15:58:51,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 172851200. Throughput: 0: 1816.5, 1: 1810.2. Samples: 43216186. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-10 15:58:51,077][75634] Avg episode reward: [(0, '42.260'), (1, '34.670')] -[2023-10-10 15:58:51,408][76543] Updated weights for policy 0, policy_version 84483 (0.0011) -[2023-10-10 15:58:51,779][76543] Updated weights for policy 0, policy_version 84493 (0.0007) -[2023-10-10 15:58:52,147][76543] Updated weights for policy 0, policy_version 84503 (0.0010) -[2023-10-10 15:58:54,003][76542] Updated weights for policy 1, policy_version 84330 (0.0008) -[2023-10-10 15:58:54,366][76542] Updated weights for policy 1, policy_version 84340 (0.0010) -[2023-10-10 15:58:54,728][76542] Updated weights for policy 1, policy_version 84350 (0.0009) -[2023-10-10 15:58:55,813][76543] Updated weights for policy 0, policy_version 84513 (0.0009) -[2023-10-10 15:58:56,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 172916736. Throughput: 0: 1807.0, 1: 1806.4. Samples: 43237178. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-10 15:58:56,077][75634] Avg episode reward: [(0, '41.050'), (1, '33.930')] -[2023-10-10 15:58:56,183][76543] Updated weights for policy 0, policy_version 84523 (0.0009) -[2023-10-10 15:58:56,557][76543] Updated weights for policy 0, policy_version 84533 (0.0011) -[2023-10-10 15:58:56,926][76543] Updated weights for policy 0, policy_version 84543 (0.0007) -[2023-10-10 15:58:58,381][76542] Updated weights for policy 1, policy_version 84360 (0.0009) -[2023-10-10 15:58:58,743][76542] Updated weights for policy 1, policy_version 84370 (0.0008) -[2023-10-10 15:58:59,117][76542] Updated weights for policy 1, policy_version 84380 (0.0008) -[2023-10-10 15:59:00,708][76543] Updated weights for policy 0, policy_version 84553 (0.0010) -[2023-10-10 15:59:01,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 172982272. Throughput: 0: 1816.9, 1: 1793.3. Samples: 43259606. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-10 15:59:01,076][75634] Avg episode reward: [(0, '42.320'), (1, '37.810')] -[2023-10-10 15:59:01,080][76543] Updated weights for policy 0, policy_version 84563 (0.0010) -[2023-10-10 15:59:01,454][76543] Updated weights for policy 0, policy_version 84573 (0.0008) -[2023-10-10 15:59:02,817][76542] Updated weights for policy 1, policy_version 84390 (0.0007) -[2023-10-10 15:59:03,192][76542] Updated weights for policy 1, policy_version 84400 (0.0008) -[2023-10-10 15:59:03,559][76542] Updated weights for policy 1, policy_version 84410 (0.0008) -[2023-10-10 15:59:05,169][76543] Updated weights for policy 0, policy_version 84583 (0.0007) -[2023-10-10 15:59:05,547][76543] Updated weights for policy 0, policy_version 84593 (0.0009) -[2023-10-10 15:59:05,911][76543] Updated weights for policy 0, policy_version 84603 (0.0008) -[2023-10-10 15:59:06,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 173047808. Throughput: 0: 1808.2, 1: 1800.5. Samples: 43269806. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:59:06,076][75634] Avg episode reward: [(0, '41.150'), (1, '37.740')] -[2023-10-10 15:59:07,387][76542] Updated weights for policy 1, policy_version 84420 (0.0009) -[2023-10-10 15:59:07,756][76542] Updated weights for policy 1, policy_version 84430 (0.0008) -[2023-10-10 15:59:08,116][76542] Updated weights for policy 1, policy_version 84440 (0.0009) -[2023-10-10 15:59:09,526][76543] Updated weights for policy 0, policy_version 84613 (0.0008) -[2023-10-10 15:59:09,893][76543] Updated weights for policy 0, policy_version 84623 (0.0010) -[2023-10-10 15:59:10,277][76543] Updated weights for policy 0, policy_version 84633 (0.0010) -[2023-10-10 15:59:11,076][75634] Fps is (10 sec: 16383.5, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 173146112. Throughput: 0: 1817.0, 1: 1792.2. Samples: 43292122. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:59:11,077][75634] Avg episode reward: [(0, '35.610'), (1, '36.970')] -[2023-10-10 15:59:11,846][76542] Updated weights for policy 1, policy_version 84450 (0.0008) -[2023-10-10 15:59:12,205][76542] Updated weights for policy 1, policy_version 84460 (0.0009) -[2023-10-10 15:59:12,569][76542] Updated weights for policy 1, policy_version 84470 (0.0010) -[2023-10-10 15:59:12,939][76542] Updated weights for policy 1, policy_version 84480 (0.0010) -[2023-10-10 15:59:13,965][76543] Updated weights for policy 0, policy_version 84643 (0.0008) -[2023-10-10 15:59:14,327][76543] Updated weights for policy 0, policy_version 84653 (0.0009) -[2023-10-10 15:59:14,699][76543] Updated weights for policy 0, policy_version 84663 (0.0010) -[2023-10-10 15:59:16,076][75634] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 173211648. Throughput: 0: 1808.6, 1: 1795.5. Samples: 43313536. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:59:16,077][75634] Avg episode reward: [(0, '34.540'), (1, '37.950')] -[2023-10-10 15:59:16,633][76542] Updated weights for policy 1, policy_version 84490 (0.0011) -[2023-10-10 15:59:17,001][76542] Updated weights for policy 1, policy_version 84500 (0.0011) -[2023-10-10 15:59:17,371][76542] Updated weights for policy 1, policy_version 84510 (0.0009) -[2023-10-10 15:59:18,425][76543] Updated weights for policy 0, policy_version 84673 (0.0009) -[2023-10-10 15:59:18,791][76543] Updated weights for policy 0, policy_version 84683 (0.0007) -[2023-10-10 15:59:19,158][76543] Updated weights for policy 0, policy_version 84693 (0.0008) -[2023-10-10 15:59:19,524][76543] Updated weights for policy 0, policy_version 84703 (0.0007) -[2023-10-10 15:59:21,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 173277184. Throughput: 0: 1813.1, 1: 1792.4. Samples: 43324814. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:59:21,076][75634] Avg episode reward: [(0, '29.020'), (1, '36.140')] -[2023-10-10 15:59:21,310][76542] Updated weights for policy 1, policy_version 84520 (0.0009) -[2023-10-10 15:59:21,679][76542] Updated weights for policy 1, policy_version 84530 (0.0009) -[2023-10-10 15:59:22,057][76542] Updated weights for policy 1, policy_version 84540 (0.0008) -[2023-10-10 15:59:23,111][76543] Updated weights for policy 0, policy_version 84713 (0.0007) -[2023-10-10 15:59:23,494][76543] Updated weights for policy 0, policy_version 84723 (0.0009) -[2023-10-10 15:59:23,855][76543] Updated weights for policy 0, policy_version 84733 (0.0007) -[2023-10-10 15:59:25,757][76542] Updated weights for policy 1, policy_version 84550 (0.0007) -[2023-10-10 15:59:26,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 173342720. Throughput: 0: 1810.1, 1: 1791.9. Samples: 43345726. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:59:26,076][75634] Avg episode reward: [(0, '30.750'), (1, '35.750')] -[2023-10-10 15:59:26,119][76542] Updated weights for policy 1, policy_version 84560 (0.0010) -[2023-10-10 15:59:26,484][76542] Updated weights for policy 1, policy_version 84570 (0.0011) -[2023-10-10 15:59:27,714][76543] Updated weights for policy 0, policy_version 84743 (0.0009) -[2023-10-10 15:59:28,091][76543] Updated weights for policy 0, policy_version 84753 (0.0008) -[2023-10-10 15:59:28,454][76543] Updated weights for policy 0, policy_version 84763 (0.0008) -[2023-10-10 15:59:30,198][76542] Updated weights for policy 1, policy_version 84580 (0.0010) -[2023-10-10 15:59:30,565][76542] Updated weights for policy 1, policy_version 84590 (0.0009) -[2023-10-10 15:59:30,925][76542] Updated weights for policy 1, policy_version 84600 (0.0009) -[2023-10-10 15:59:31,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 173408256. Throughput: 0: 1812.5, 1: 1810.1. Samples: 43367690. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:59:31,077][75634] Avg episode reward: [(0, '28.390'), (1, '33.300')] -[2023-10-10 15:59:32,158][76543] Updated weights for policy 0, policy_version 84773 (0.0007) -[2023-10-10 15:59:32,527][76543] Updated weights for policy 0, policy_version 84783 (0.0008) -[2023-10-10 15:59:32,895][76543] Updated weights for policy 0, policy_version 84793 (0.0007) -[2023-10-10 15:59:34,655][76542] Updated weights for policy 1, policy_version 84610 (0.0011) -[2023-10-10 15:59:35,023][76542] Updated weights for policy 1, policy_version 84620 (0.0010) -[2023-10-10 15:59:35,383][76542] Updated weights for policy 1, policy_version 84630 (0.0010) -[2023-10-10 15:59:35,756][76542] Updated weights for policy 1, policy_version 84640 (0.0009) -[2023-10-10 15:59:36,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 173506560. Throughput: 0: 1811.4, 1: 1789.5. Samples: 43378226. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:59:36,077][75634] Avg episode reward: [(0, '35.100'), (1, '34.810')] -[2023-10-10 15:59:36,553][76543] Updated weights for policy 0, policy_version 84803 (0.0008) -[2023-10-10 15:59:36,919][76543] Updated weights for policy 0, policy_version 84813 (0.0008) -[2023-10-10 15:59:37,288][76543] Updated weights for policy 0, policy_version 84823 (0.0008) -[2023-10-10 15:59:39,457][76542] Updated weights for policy 1, policy_version 84650 (0.0009) -[2023-10-10 15:59:39,832][76542] Updated weights for policy 1, policy_version 84660 (0.0011) -[2023-10-10 15:59:40,206][76542] Updated weights for policy 1, policy_version 84670 (0.0011) -[2023-10-10 15:59:40,912][76543] Updated weights for policy 0, policy_version 84833 (0.0010) -[2023-10-10 15:59:41,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 173572096. Throughput: 0: 1817.7, 1: 1810.8. Samples: 43400460. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:59:41,077][75634] Avg episode reward: [(0, '34.600'), (1, '33.490')] -[2023-10-10 15:59:41,276][76543] Updated weights for policy 0, policy_version 84843 (0.0008) -[2023-10-10 15:59:41,645][76543] Updated weights for policy 0, policy_version 84853 (0.0008) -[2023-10-10 15:59:42,021][76543] Updated weights for policy 0, policy_version 84863 (0.0008) -[2023-10-10 15:59:43,919][76542] Updated weights for policy 1, policy_version 84680 (0.0009) -[2023-10-10 15:59:44,288][76542] Updated weights for policy 1, policy_version 84690 (0.0008) -[2023-10-10 15:59:44,647][76542] Updated weights for policy 1, policy_version 84700 (0.0009) -[2023-10-10 15:59:45,646][76543] Updated weights for policy 0, policy_version 84873 (0.0009) -[2023-10-10 15:59:46,015][76543] Updated weights for policy 0, policy_version 84883 (0.0011) -[2023-10-10 15:59:46,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 173637632. Throughput: 0: 1818.9, 1: 1794.7. Samples: 43422218. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:59:46,077][75634] Avg episode reward: [(0, '33.040'), (1, '32.930')] -[2023-10-10 15:59:46,380][76543] Updated weights for policy 0, policy_version 84893 (0.0011) -[2023-10-10 15:59:48,479][76542] Updated weights for policy 1, policy_version 84710 (0.0009) -[2023-10-10 15:59:48,851][76542] Updated weights for policy 1, policy_version 84720 (0.0011) -[2023-10-10 15:59:49,206][76542] Updated weights for policy 1, policy_version 84730 (0.0010) -[2023-10-10 15:59:50,054][76543] Updated weights for policy 0, policy_version 84903 (0.0007) -[2023-10-10 15:59:50,435][76543] Updated weights for policy 0, policy_version 84913 (0.0007) -[2023-10-10 15:59:50,804][76543] Updated weights for policy 0, policy_version 84923 (0.0009) -[2023-10-10 15:59:51,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 173735936. Throughput: 0: 1816.4, 1: 1809.6. Samples: 43432978. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 15:59:51,077][75634] Avg episode reward: [(0, '35.850'), (1, '33.990')] -[2023-10-10 15:59:52,952][76542] Updated weights for policy 1, policy_version 84740 (0.0010) -[2023-10-10 15:59:53,312][76542] Updated weights for policy 1, policy_version 84750 (0.0007) -[2023-10-10 15:59:53,690][76542] Updated weights for policy 1, policy_version 84760 (0.0010) -[2023-10-10 15:59:54,507][76543] Updated weights for policy 0, policy_version 84933 (0.0011) -[2023-10-10 15:59:54,876][76543] Updated weights for policy 0, policy_version 84943 (0.0009) -[2023-10-10 15:59:55,250][76543] Updated weights for policy 0, policy_version 84953 (0.0007) -[2023-10-10 15:59:56,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 173801472. Throughput: 0: 1816.4, 1: 1800.1. Samples: 43454864. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-10 15:59:56,076][75634] Avg episode reward: [(0, '35.520'), (1, '33.570')] -[2023-10-10 15:59:57,157][76542] Updated weights for policy 1, policy_version 84770 (0.0008) -[2023-10-10 15:59:57,528][76542] Updated weights for policy 1, policy_version 84780 (0.0011) -[2023-10-10 15:59:57,904][76542] Updated weights for policy 1, policy_version 84790 (0.0010) -[2023-10-10 15:59:58,262][76542] Updated weights for policy 1, policy_version 84800 (0.0011) -[2023-10-10 15:59:58,891][76543] Updated weights for policy 0, policy_version 84963 (0.0008) -[2023-10-10 15:59:59,261][76543] Updated weights for policy 0, policy_version 84973 (0.0009) -[2023-10-10 15:59:59,634][76543] Updated weights for policy 0, policy_version 84983 (0.0009) -[2023-10-10 16:00:01,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 173867008. Throughput: 0: 1814.5, 1: 1809.4. Samples: 43476612. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-10 16:00:01,076][75634] Avg episode reward: [(0, '35.320'), (1, '35.380')] -[2023-10-10 16:00:01,951][76542] Updated weights for policy 1, policy_version 84810 (0.0010) -[2023-10-10 16:00:02,319][76542] Updated weights for policy 1, policy_version 84820 (0.0008) -[2023-10-10 16:00:02,682][76542] Updated weights for policy 1, policy_version 84830 (0.0009) -[2023-10-10 16:00:03,399][76543] Updated weights for policy 0, policy_version 84993 (0.0010) -[2023-10-10 16:00:03,773][76543] Updated weights for policy 0, policy_version 85003 (0.0007) -[2023-10-10 16:00:04,141][76543] Updated weights for policy 0, policy_version 85013 (0.0008) -[2023-10-10 16:00:04,509][76543] Updated weights for policy 0, policy_version 85023 (0.0008) -[2023-10-10 16:00:06,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 173932544. Throughput: 0: 1819.2, 1: 1808.5. Samples: 43488062. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-10 16:00:06,077][75634] Avg episode reward: [(0, '35.050'), (1, '41.240')] -[2023-10-10 16:00:06,455][76542] Updated weights for policy 1, policy_version 84840 (0.0007) -[2023-10-10 16:00:06,831][76542] Updated weights for policy 1, policy_version 84850 (0.0007) -[2023-10-10 16:00:07,198][76542] Updated weights for policy 1, policy_version 84860 (0.0007) -[2023-10-10 16:00:08,339][76543] Updated weights for policy 0, policy_version 85033 (0.0009) -[2023-10-10 16:00:08,710][76543] Updated weights for policy 0, policy_version 85043 (0.0010) -[2023-10-10 16:00:09,089][76543] Updated weights for policy 0, policy_version 85053 (0.0007) -[2023-10-10 16:00:10,943][76542] Updated weights for policy 1, policy_version 84870 (0.0008) -[2023-10-10 16:00:11,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 173998080. Throughput: 0: 1818.6, 1: 1817.2. Samples: 43509338. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-10 16:00:11,077][75634] Avg episode reward: [(0, '32.740'), (1, '36.930')] -[2023-10-10 16:00:11,315][76542] Updated weights for policy 1, policy_version 84880 (0.0009) -[2023-10-10 16:00:11,692][76542] Updated weights for policy 1, policy_version 84890 (0.0009) -[2023-10-10 16:00:12,812][76543] Updated weights for policy 0, policy_version 85063 (0.0009) -[2023-10-10 16:00:13,176][76543] Updated weights for policy 0, policy_version 85073 (0.0010) -[2023-10-10 16:00:13,556][76543] Updated weights for policy 0, policy_version 85083 (0.0010) -[2023-10-10 16:00:15,415][76542] Updated weights for policy 1, policy_version 84900 (0.0010) -[2023-10-10 16:00:15,772][76542] Updated weights for policy 1, policy_version 84910 (0.0009) -[2023-10-10 16:00:16,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 174063616. Throughput: 0: 1821.3, 1: 1817.8. Samples: 43531450. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-10 16:00:16,076][75634] Avg episode reward: [(0, '32.840'), (1, '37.280')] -[2023-10-10 16:00:16,136][76542] Updated weights for policy 1, policy_version 84920 (0.0010) -[2023-10-10 16:00:17,143][76543] Updated weights for policy 0, policy_version 85093 (0.0008) -[2023-10-10 16:00:17,511][76543] Updated weights for policy 0, policy_version 85103 (0.0009) -[2023-10-10 16:00:17,888][76543] Updated weights for policy 0, policy_version 85113 (0.0010) -[2023-10-10 16:00:19,689][76542] Updated weights for policy 1, policy_version 84930 (0.0009) -[2023-10-10 16:00:20,063][76542] Updated weights for policy 1, policy_version 84940 (0.0010) -[2023-10-10 16:00:20,424][76542] Updated weights for policy 1, policy_version 84950 (0.0010) -[2023-10-10 16:00:20,794][76542] Updated weights for policy 1, policy_version 84960 (0.0011) -[2023-10-10 16:00:21,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 174161920. Throughput: 0: 1824.2, 1: 1821.2. Samples: 43542268. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-10 16:00:21,077][75634] Avg episode reward: [(0, '39.720'), (1, '36.410')] -[2023-10-10 16:00:21,406][76543] Updated weights for policy 0, policy_version 85123 (0.0008) -[2023-10-10 16:00:21,777][76543] Updated weights for policy 0, policy_version 85133 (0.0010) -[2023-10-10 16:00:22,152][76543] Updated weights for policy 0, policy_version 85143 (0.0008) -[2023-10-10 16:00:24,557][76542] Updated weights for policy 1, policy_version 84970 (0.0009) -[2023-10-10 16:00:24,915][76542] Updated weights for policy 1, policy_version 84980 (0.0009) -[2023-10-10 16:00:25,282][76542] Updated weights for policy 1, policy_version 84990 (0.0007) -[2023-10-10 16:00:25,822][76543] Updated weights for policy 0, policy_version 85153 (0.0008) -[2023-10-10 16:00:26,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 174227456. Throughput: 0: 1823.5, 1: 1819.2. Samples: 43564382. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-10 16:00:26,076][75634] Avg episode reward: [(0, '42.380'), (1, '37.630')] -[2023-10-10 16:00:26,196][76543] Updated weights for policy 0, policy_version 85163 (0.0008) -[2023-10-10 16:00:26,565][76543] Updated weights for policy 0, policy_version 85173 (0.0007) -[2023-10-10 16:00:26,927][76543] Updated weights for policy 0, policy_version 85183 (0.0007) -[2023-10-10 16:00:28,921][76542] Updated weights for policy 1, policy_version 85000 (0.0009) -[2023-10-10 16:00:29,286][76542] Updated weights for policy 1, policy_version 85010 (0.0008) -[2023-10-10 16:00:29,649][76542] Updated weights for policy 1, policy_version 85020 (0.0008) -[2023-10-10 16:00:30,819][76543] Updated weights for policy 0, policy_version 85193 (0.0009) -[2023-10-10 16:00:31,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 174292992. Throughput: 0: 1820.8, 1: 1828.7. Samples: 43586448. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-10 16:00:31,077][75634] Avg episode reward: [(0, '38.730'), (1, '36.390')] -[2023-10-10 16:00:31,084][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000085024_87064576.pth... -[2023-10-10 16:00:31,119][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000083328_85327872.pth -[2023-10-10 16:00:31,122][76421] Saving a milestone ./train_atari/atari_defender_APPO/checkpoint_p1/milestones/checkpoint_000085024_87064576.pth -[2023-10-10 16:00:31,184][76543] Updated weights for policy 0, policy_version 85203 (0.0011) -[2023-10-10 16:00:31,548][76543] Updated weights for policy 0, policy_version 85213 (0.0010) -[2023-10-10 16:00:31,658][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000085216_87261184.pth... -[2023-10-10 16:00:31,694][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000083488_85491712.pth -[2023-10-10 16:00:31,698][76362] Saving a milestone ./train_atari/atari_defender_APPO/checkpoint_p0/milestones/checkpoint_000085216_87261184.pth -[2023-10-10 16:00:33,458][76542] Updated weights for policy 1, policy_version 85030 (0.0011) -[2023-10-10 16:00:33,835][76542] Updated weights for policy 1, policy_version 85040 (0.0011) -[2023-10-10 16:00:34,190][76542] Updated weights for policy 1, policy_version 85050 (0.0009) -[2023-10-10 16:00:35,181][76543] Updated weights for policy 0, policy_version 85223 (0.0010) -[2023-10-10 16:00:35,546][76543] Updated weights for policy 0, policy_version 85233 (0.0008) -[2023-10-10 16:00:35,914][76543] Updated weights for policy 0, policy_version 85243 (0.0009) -[2023-10-10 16:00:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 174358528. Throughput: 0: 1825.9, 1: 1822.6. Samples: 43597162. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-10 16:00:36,076][75634] Avg episode reward: [(0, '41.070'), (1, '34.250')] -[2023-10-10 16:00:37,922][76542] Updated weights for policy 1, policy_version 85060 (0.0011) -[2023-10-10 16:00:38,280][76542] Updated weights for policy 1, policy_version 85070 (0.0009) -[2023-10-10 16:00:38,647][76542] Updated weights for policy 1, policy_version 85080 (0.0010) -[2023-10-10 16:00:39,595][76543] Updated weights for policy 0, policy_version 85253 (0.0009) -[2023-10-10 16:00:39,969][76543] Updated weights for policy 0, policy_version 85263 (0.0010) -[2023-10-10 16:00:40,337][76543] Updated weights for policy 0, policy_version 85273 (0.0007) -[2023-10-10 16:00:41,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 174456832. Throughput: 0: 1825.7, 1: 1821.5. Samples: 43618992. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-10 16:00:41,077][75634] Avg episode reward: [(0, '39.390'), (1, '35.090')] -[2023-10-10 16:00:42,448][76542] Updated weights for policy 1, policy_version 85090 (0.0008) -[2023-10-10 16:00:42,808][76542] Updated weights for policy 1, policy_version 85100 (0.0009) -[2023-10-10 16:00:43,169][76542] Updated weights for policy 1, policy_version 85110 (0.0010) -[2023-10-10 16:00:43,533][76542] Updated weights for policy 1, policy_version 85120 (0.0010) -[2023-10-10 16:00:43,961][76543] Updated weights for policy 0, policy_version 85283 (0.0007) -[2023-10-10 16:00:44,337][76543] Updated weights for policy 0, policy_version 85293 (0.0008) -[2023-10-10 16:00:44,695][76543] Updated weights for policy 0, policy_version 85303 (0.0011) -[2023-10-10 16:00:46,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 174522368. Throughput: 0: 1827.0, 1: 1812.6. Samples: 43640396. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-10 16:00:46,077][75634] Avg episode reward: [(0, '37.930'), (1, '35.240')] -[2023-10-10 16:00:47,152][76542] Updated weights for policy 1, policy_version 85130 (0.0008) -[2023-10-10 16:00:47,513][76542] Updated weights for policy 1, policy_version 85140 (0.0010) -[2023-10-10 16:00:47,883][76542] Updated weights for policy 1, policy_version 85150 (0.0010) -[2023-10-10 16:00:48,355][76543] Updated weights for policy 0, policy_version 85313 (0.0011) -[2023-10-10 16:00:48,723][76543] Updated weights for policy 0, policy_version 85323 (0.0008) -[2023-10-10 16:00:49,103][76543] Updated weights for policy 0, policy_version 85333 (0.0007) -[2023-10-10 16:00:49,462][76543] Updated weights for policy 0, policy_version 85343 (0.0008) -[2023-10-10 16:00:51,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 174587904. Throughput: 0: 1824.2, 1: 1814.2. Samples: 43651790. Policy #0 lag: (min: 23.0, avg: 26.0, max: 55.0) -[2023-10-10 16:00:51,076][75634] Avg episode reward: [(0, '37.680'), (1, '37.600')] -[2023-10-10 16:00:51,734][76542] Updated weights for policy 1, policy_version 85160 (0.0009) -[2023-10-10 16:00:52,108][76542] Updated weights for policy 1, policy_version 85170 (0.0009) -[2023-10-10 16:00:52,481][76542] Updated weights for policy 1, policy_version 85180 (0.0008) -[2023-10-10 16:00:53,301][76543] Updated weights for policy 0, policy_version 85353 (0.0007) -[2023-10-10 16:00:53,675][76543] Updated weights for policy 0, policy_version 85363 (0.0007) -[2023-10-10 16:00:54,044][76543] Updated weights for policy 0, policy_version 85373 (0.0009) -[2023-10-10 16:00:56,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 174653440. Throughput: 0: 1818.3, 1: 1808.1. Samples: 43672528. Policy #0 lag: (min: 23.0, avg: 26.0, max: 55.0) -[2023-10-10 16:00:56,077][75634] Avg episode reward: [(0, '35.190'), (1, '38.500')] -[2023-10-10 16:00:56,148][76542] Updated weights for policy 1, policy_version 85190 (0.0008) -[2023-10-10 16:00:56,519][76542] Updated weights for policy 1, policy_version 85200 (0.0011) -[2023-10-10 16:00:56,889][76542] Updated weights for policy 1, policy_version 85210 (0.0008) -[2023-10-10 16:00:57,756][76543] Updated weights for policy 0, policy_version 85383 (0.0009) -[2023-10-10 16:00:58,123][76543] Updated weights for policy 0, policy_version 85393 (0.0010) -[2023-10-10 16:00:58,498][76543] Updated weights for policy 0, policy_version 85403 (0.0007) -[2023-10-10 16:01:00,668][76542] Updated weights for policy 1, policy_version 85220 (0.0009) -[2023-10-10 16:01:01,036][76542] Updated weights for policy 1, policy_version 85230 (0.0012) -[2023-10-10 16:01:01,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 174718976. Throughput: 0: 1814.5, 1: 1819.6. Samples: 43694986. Policy #0 lag: (min: 23.0, avg: 26.0, max: 55.0) -[2023-10-10 16:01:01,077][75634] Avg episode reward: [(0, '35.510'), (1, '39.170')] -[2023-10-10 16:01:01,397][76542] Updated weights for policy 1, policy_version 85240 (0.0011) -[2023-10-10 16:01:02,134][76543] Updated weights for policy 0, policy_version 85413 (0.0007) -[2023-10-10 16:01:02,503][76543] Updated weights for policy 0, policy_version 85423 (0.0009) -[2023-10-10 16:01:02,875][76543] Updated weights for policy 0, policy_version 85433 (0.0008) -[2023-10-10 16:01:05,057][76542] Updated weights for policy 1, policy_version 85250 (0.0007) -[2023-10-10 16:01:05,418][76542] Updated weights for policy 1, policy_version 85260 (0.0008) -[2023-10-10 16:01:05,783][76542] Updated weights for policy 1, policy_version 85270 (0.0007) -[2023-10-10 16:01:06,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 174784512. Throughput: 0: 1815.5, 1: 1806.3. Samples: 43705246. Policy #0 lag: (min: 23.0, avg: 26.0, max: 55.0) -[2023-10-10 16:01:06,076][75634] Avg episode reward: [(0, '38.660'), (1, '44.510')] -[2023-10-10 16:01:06,152][76421] Saving new best policy, reward=44.510! -[2023-10-10 16:01:06,154][76542] Updated weights for policy 1, policy_version 85280 (0.0009) -[2023-10-10 16:01:06,484][76543] Updated weights for policy 0, policy_version 85443 (0.0007) -[2023-10-10 16:01:06,856][76543] Updated weights for policy 0, policy_version 85453 (0.0008) -[2023-10-10 16:01:07,229][76543] Updated weights for policy 0, policy_version 85463 (0.0008) -[2023-10-10 16:01:09,869][76542] Updated weights for policy 1, policy_version 85290 (0.0009) -[2023-10-10 16:01:10,241][76542] Updated weights for policy 1, policy_version 85300 (0.0007) -[2023-10-10 16:01:10,609][76542] Updated weights for policy 1, policy_version 85310 (0.0009) -[2023-10-10 16:01:10,916][76543] Updated weights for policy 0, policy_version 85473 (0.0009) -[2023-10-10 16:01:11,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 174882816. Throughput: 0: 1817.3, 1: 1815.2. Samples: 43727842. Policy #0 lag: (min: 23.0, avg: 26.0, max: 55.0) -[2023-10-10 16:01:11,076][75634] Avg episode reward: [(0, '40.150'), (1, '38.200')] -[2023-10-10 16:01:11,274][76543] Updated weights for policy 0, policy_version 85483 (0.0008) -[2023-10-10 16:01:11,644][76543] Updated weights for policy 0, policy_version 85493 (0.0008) -[2023-10-10 16:01:12,026][76543] Updated weights for policy 0, policy_version 85503 (0.0008) -[2023-10-10 16:01:14,197][76542] Updated weights for policy 1, policy_version 85320 (0.0008) -[2023-10-10 16:01:14,566][76542] Updated weights for policy 1, policy_version 85330 (0.0010) -[2023-10-10 16:01:14,937][76542] Updated weights for policy 1, policy_version 85340 (0.0010) -[2023-10-10 16:01:15,635][76543] Updated weights for policy 0, policy_version 85513 (0.0011) -[2023-10-10 16:01:15,999][76543] Updated weights for policy 0, policy_version 85523 (0.0011) -[2023-10-10 16:01:16,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 174948352. Throughput: 0: 1820.2, 1: 1808.4. Samples: 43749734. Policy #0 lag: (min: 23.0, avg: 26.0, max: 55.0) -[2023-10-10 16:01:16,076][75634] Avg episode reward: [(0, '37.150'), (1, '37.440')] -[2023-10-10 16:01:16,361][76543] Updated weights for policy 0, policy_version 85533 (0.0010) -[2023-10-10 16:01:18,500][76542] Updated weights for policy 1, policy_version 85350 (0.0009) -[2023-10-10 16:01:18,869][76542] Updated weights for policy 1, policy_version 85360 (0.0009) -[2023-10-10 16:01:19,242][76542] Updated weights for policy 1, policy_version 85370 (0.0008) -[2023-10-10 16:01:20,132][76543] Updated weights for policy 0, policy_version 85543 (0.0010) -[2023-10-10 16:01:20,520][76543] Updated weights for policy 0, policy_version 85553 (0.0008) -[2023-10-10 16:01:20,883][76543] Updated weights for policy 0, policy_version 85563 (0.0008) -[2023-10-10 16:01:21,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 175046656. Throughput: 0: 1815.3, 1: 1815.9. Samples: 43760564. Policy #0 lag: (min: 23.0, avg: 26.0, max: 55.0) -[2023-10-10 16:01:21,076][75634] Avg episode reward: [(0, '37.920'), (1, '31.960')] -[2023-10-10 16:01:22,840][76542] Updated weights for policy 1, policy_version 85380 (0.0009) -[2023-10-10 16:01:23,199][76542] Updated weights for policy 1, policy_version 85390 (0.0007) -[2023-10-10 16:01:23,566][76542] Updated weights for policy 1, policy_version 85400 (0.0009) -[2023-10-10 16:01:24,477][76543] Updated weights for policy 0, policy_version 85573 (0.0009) -[2023-10-10 16:01:24,856][76543] Updated weights for policy 0, policy_version 85583 (0.0008) -[2023-10-10 16:01:25,236][76543] Updated weights for policy 0, policy_version 85593 (0.0009) -[2023-10-10 16:01:26,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 175112192. Throughput: 0: 1820.5, 1: 1817.6. Samples: 43782708. Policy #0 lag: (min: 23.0, avg: 26.0, max: 55.0) -[2023-10-10 16:01:26,077][75634] Avg episode reward: [(0, '37.490'), (1, '29.330')] -[2023-10-10 16:01:27,242][76542] Updated weights for policy 1, policy_version 85410 (0.0009) -[2023-10-10 16:01:27,606][76542] Updated weights for policy 1, policy_version 85420 (0.0009) -[2023-10-10 16:01:27,976][76542] Updated weights for policy 1, policy_version 85430 (0.0008) -[2023-10-10 16:01:28,342][76542] Updated weights for policy 1, policy_version 85440 (0.0009) -[2023-10-10 16:01:28,845][76543] Updated weights for policy 0, policy_version 85603 (0.0009) -[2023-10-10 16:01:29,222][76543] Updated weights for policy 0, policy_version 85613 (0.0008) -[2023-10-10 16:01:29,583][76543] Updated weights for policy 0, policy_version 85623 (0.0008) -[2023-10-10 16:01:31,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 175177728. Throughput: 0: 1821.5, 1: 1820.6. Samples: 43804290. Policy #0 lag: (min: 23.0, avg: 26.0, max: 55.0) -[2023-10-10 16:01:31,076][75634] Avg episode reward: [(0, '36.990'), (1, '27.690')] -[2023-10-10 16:01:31,912][76542] Updated weights for policy 1, policy_version 85450 (0.0008) -[2023-10-10 16:01:32,284][76542] Updated weights for policy 1, policy_version 85460 (0.0008) -[2023-10-10 16:01:32,654][76542] Updated weights for policy 1, policy_version 85470 (0.0008) -[2023-10-10 16:01:33,415][76543] Updated weights for policy 0, policy_version 85633 (0.0009) -[2023-10-10 16:01:33,779][76543] Updated weights for policy 0, policy_version 85643 (0.0010) -[2023-10-10 16:01:34,154][76543] Updated weights for policy 0, policy_version 85653 (0.0008) -[2023-10-10 16:01:34,524][76543] Updated weights for policy 0, policy_version 85663 (0.0008) -[2023-10-10 16:01:36,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 175243264. Throughput: 0: 1817.5, 1: 1823.0. Samples: 43815610. Policy #0 lag: (min: 23.0, avg: 26.0, max: 55.0) -[2023-10-10 16:01:36,076][75634] Avg episode reward: [(0, '36.740'), (1, '31.010')] -[2023-10-10 16:01:36,392][76542] Updated weights for policy 1, policy_version 85480 (0.0008) -[2023-10-10 16:01:36,765][76542] Updated weights for policy 1, policy_version 85490 (0.0008) -[2023-10-10 16:01:37,129][76542] Updated weights for policy 1, policy_version 85500 (0.0008) -[2023-10-10 16:01:38,193][76543] Updated weights for policy 0, policy_version 85673 (0.0007) -[2023-10-10 16:01:38,564][76543] Updated weights for policy 0, policy_version 85683 (0.0008) -[2023-10-10 16:01:38,940][76543] Updated weights for policy 0, policy_version 85693 (0.0008) -[2023-10-10 16:01:40,852][76542] Updated weights for policy 1, policy_version 85510 (0.0008) -[2023-10-10 16:01:41,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 175308800. Throughput: 0: 1821.5, 1: 1831.6. Samples: 43836916. Policy #0 lag: (min: 23.0, avg: 26.0, max: 55.0) -[2023-10-10 16:01:41,077][75634] Avg episode reward: [(0, '31.930'), (1, '33.380')] -[2023-10-10 16:01:41,232][76542] Updated weights for policy 1, policy_version 85520 (0.0007) -[2023-10-10 16:01:41,594][76542] Updated weights for policy 1, policy_version 85530 (0.0010) -[2023-10-10 16:01:42,812][76543] Updated weights for policy 0, policy_version 85703 (0.0009) -[2023-10-10 16:01:43,181][76543] Updated weights for policy 0, policy_version 85713 (0.0009) -[2023-10-10 16:01:43,547][76543] Updated weights for policy 0, policy_version 85723 (0.0008) -[2023-10-10 16:01:45,080][76542] Updated weights for policy 1, policy_version 85540 (0.0009) -[2023-10-10 16:01:45,446][76542] Updated weights for policy 1, policy_version 85550 (0.0007) -[2023-10-10 16:01:45,817][76542] Updated weights for policy 1, policy_version 85560 (0.0008) -[2023-10-10 16:01:46,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 175374336. Throughput: 0: 1820.4, 1: 1817.7. Samples: 43858700. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-10 16:01:46,077][75634] Avg episode reward: [(0, '35.420'), (1, '35.380')] -[2023-10-10 16:01:47,074][76543] Updated weights for policy 0, policy_version 85733 (0.0009) -[2023-10-10 16:01:47,442][76543] Updated weights for policy 0, policy_version 85743 (0.0011) -[2023-10-10 16:01:47,816][76543] Updated weights for policy 0, policy_version 85753 (0.0009) -[2023-10-10 16:01:49,636][76542] Updated weights for policy 1, policy_version 85570 (0.0007) -[2023-10-10 16:01:50,007][76542] Updated weights for policy 1, policy_version 85580 (0.0010) -[2023-10-10 16:01:50,380][76542] Updated weights for policy 1, policy_version 85590 (0.0009) -[2023-10-10 16:01:50,746][76542] Updated weights for policy 1, policy_version 85600 (0.0008) -[2023-10-10 16:01:51,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 175472640. Throughput: 0: 1820.2, 1: 1832.3. Samples: 43869608. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-10 16:01:51,077][75634] Avg episode reward: [(0, '36.320'), (1, '34.200')] -[2023-10-10 16:01:51,537][76543] Updated weights for policy 0, policy_version 85763 (0.0010) -[2023-10-10 16:01:51,897][76543] Updated weights for policy 0, policy_version 85773 (0.0008) -[2023-10-10 16:01:52,269][76543] Updated weights for policy 0, policy_version 85783 (0.0008) -[2023-10-10 16:01:54,408][76542] Updated weights for policy 1, policy_version 85610 (0.0009) -[2023-10-10 16:01:54,776][76542] Updated weights for policy 1, policy_version 85620 (0.0008) -[2023-10-10 16:01:55,142][76542] Updated weights for policy 1, policy_version 85630 (0.0009) -[2023-10-10 16:01:55,913][76543] Updated weights for policy 0, policy_version 85793 (0.0007) -[2023-10-10 16:01:56,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 175538176. Throughput: 0: 1814.4, 1: 1831.5. Samples: 43891908. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-10 16:01:56,077][75634] Avg episode reward: [(0, '35.970'), (1, '37.860')] -[2023-10-10 16:01:56,285][76543] Updated weights for policy 0, policy_version 85803 (0.0008) -[2023-10-10 16:01:56,649][76543] Updated weights for policy 0, policy_version 85813 (0.0009) -[2023-10-10 16:01:57,019][76543] Updated weights for policy 0, policy_version 85823 (0.0008) -[2023-10-10 16:01:58,881][76542] Updated weights for policy 1, policy_version 85640 (0.0008) -[2023-10-10 16:01:59,245][76542] Updated weights for policy 1, policy_version 85650 (0.0010) -[2023-10-10 16:01:59,619][76542] Updated weights for policy 1, policy_version 85660 (0.0009) -[2023-10-10 16:02:00,790][76543] Updated weights for policy 0, policy_version 85833 (0.0009) -[2023-10-10 16:02:01,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 175603712. Throughput: 0: 1814.2, 1: 1840.9. Samples: 43914214. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-10 16:02:01,077][75634] Avg episode reward: [(0, '35.120'), (1, '34.190')] -[2023-10-10 16:02:01,165][76543] Updated weights for policy 0, policy_version 85843 (0.0008) -[2023-10-10 16:02:01,529][76543] Updated weights for policy 0, policy_version 85853 (0.0007) -[2023-10-10 16:02:03,258][76542] Updated weights for policy 1, policy_version 85670 (0.0009) -[2023-10-10 16:02:03,627][76542] Updated weights for policy 1, policy_version 85680 (0.0007) -[2023-10-10 16:02:03,989][76542] Updated weights for policy 1, policy_version 85690 (0.0007) -[2023-10-10 16:02:05,345][76543] Updated weights for policy 0, policy_version 85863 (0.0008) -[2023-10-10 16:02:05,727][76543] Updated weights for policy 0, policy_version 85873 (0.0009) -[2023-10-10 16:02:06,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 175669248. Throughput: 0: 1815.0, 1: 1834.3. Samples: 43924784. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-10 16:02:06,076][75634] Avg episode reward: [(0, '34.400'), (1, '31.010')] -[2023-10-10 16:02:06,096][76543] Updated weights for policy 0, policy_version 85883 (0.0008) -[2023-10-10 16:02:07,649][76542] Updated weights for policy 1, policy_version 85700 (0.0008) -[2023-10-10 16:02:08,023][76542] Updated weights for policy 1, policy_version 85710 (0.0008) -[2023-10-10 16:02:08,392][76542] Updated weights for policy 1, policy_version 85720 (0.0008) -[2023-10-10 16:02:09,692][76543] Updated weights for policy 0, policy_version 85893 (0.0008) -[2023-10-10 16:02:10,072][76543] Updated weights for policy 0, policy_version 85903 (0.0009) -[2023-10-10 16:02:10,431][76543] Updated weights for policy 0, policy_version 85913 (0.0007) -[2023-10-10 16:02:11,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 175767552. Throughput: 0: 1813.2, 1: 1838.1. Samples: 43947020. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-10 16:02:11,077][75634] Avg episode reward: [(0, '37.370'), (1, '32.370')] -[2023-10-10 16:02:12,009][76542] Updated weights for policy 1, policy_version 85730 (0.0008) -[2023-10-10 16:02:12,385][76542] Updated weights for policy 1, policy_version 85740 (0.0008) -[2023-10-10 16:02:12,760][76542] Updated weights for policy 1, policy_version 85750 (0.0008) -[2023-10-10 16:02:13,123][76542] Updated weights for policy 1, policy_version 85760 (0.0008) -[2023-10-10 16:02:14,249][76543] Updated weights for policy 0, policy_version 85923 (0.0011) -[2023-10-10 16:02:14,612][76543] Updated weights for policy 0, policy_version 85933 (0.0009) -[2023-10-10 16:02:14,994][76543] Updated weights for policy 0, policy_version 85943 (0.0010) -[2023-10-10 16:02:16,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 175833088. Throughput: 0: 1812.9, 1: 1837.5. Samples: 43968560. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-10 16:02:16,077][75634] Avg episode reward: [(0, '38.630'), (1, '35.450')] -[2023-10-10 16:02:16,676][76542] Updated weights for policy 1, policy_version 85770 (0.0010) -[2023-10-10 16:02:17,047][76542] Updated weights for policy 1, policy_version 85780 (0.0011) -[2023-10-10 16:02:17,416][76542] Updated weights for policy 1, policy_version 85790 (0.0011) -[2023-10-10 16:02:18,425][76543] Updated weights for policy 0, policy_version 85953 (0.0010) -[2023-10-10 16:02:18,801][76543] Updated weights for policy 0, policy_version 85963 (0.0008) -[2023-10-10 16:02:19,167][76543] Updated weights for policy 0, policy_version 85973 (0.0009) -[2023-10-10 16:02:19,531][76543] Updated weights for policy 0, policy_version 85983 (0.0009) -[2023-10-10 16:02:21,051][76542] Updated weights for policy 1, policy_version 85800 (0.0010) -[2023-10-10 16:02:21,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 175898624. Throughput: 0: 1818.1, 1: 1834.8. Samples: 43979992. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-10 16:02:21,076][75634] Avg episode reward: [(0, '34.350'), (1, '39.000')] -[2023-10-10 16:02:21,421][76542] Updated weights for policy 1, policy_version 85810 (0.0008) -[2023-10-10 16:02:21,795][76542] Updated weights for policy 1, policy_version 85820 (0.0007) -[2023-10-10 16:02:23,079][76543] Updated weights for policy 0, policy_version 85993 (0.0009) -[2023-10-10 16:02:23,459][76543] Updated weights for policy 0, policy_version 86003 (0.0010) -[2023-10-10 16:02:23,830][76543] Updated weights for policy 0, policy_version 86013 (0.0007) -[2023-10-10 16:02:25,625][76542] Updated weights for policy 1, policy_version 85830 (0.0008) -[2023-10-10 16:02:25,998][76542] Updated weights for policy 1, policy_version 85840 (0.0007) -[2023-10-10 16:02:26,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 175964160. Throughput: 0: 1821.3, 1: 1834.7. Samples: 44001434. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-10 16:02:26,076][75634] Avg episode reward: [(0, '33.190'), (1, '41.460')] -[2023-10-10 16:02:26,364][76542] Updated weights for policy 1, policy_version 85850 (0.0007) -[2023-10-10 16:02:27,661][76543] Updated weights for policy 0, policy_version 86023 (0.0009) -[2023-10-10 16:02:28,033][76543] Updated weights for policy 0, policy_version 86033 (0.0008) -[2023-10-10 16:02:28,412][76543] Updated weights for policy 0, policy_version 86043 (0.0007) -[2023-10-10 16:02:30,164][76542] Updated weights for policy 1, policy_version 85860 (0.0007) -[2023-10-10 16:02:30,532][76542] Updated weights for policy 1, policy_version 85870 (0.0008) -[2023-10-10 16:02:30,898][76542] Updated weights for policy 1, policy_version 85880 (0.0009) -[2023-10-10 16:02:31,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 176029696. Throughput: 0: 1829.8, 1: 1831.6. Samples: 44023462. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-10 16:02:31,077][75634] Avg episode reward: [(0, '36.880'), (1, '36.130')] -[2023-10-10 16:02:31,085][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000086048_88113152.pth... -[2023-10-10 16:02:31,117][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000084352_86376448.pth -[2023-10-10 16:02:31,181][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000085888_87949312.pth... -[2023-10-10 16:02:31,211][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000084192_86212608.pth -[2023-10-10 16:02:31,964][76543] Updated weights for policy 0, policy_version 86053 (0.0008) -[2023-10-10 16:02:32,341][76543] Updated weights for policy 0, policy_version 86063 (0.0009) -[2023-10-10 16:02:32,704][76543] Updated weights for policy 0, policy_version 86073 (0.0009) -[2023-10-10 16:02:34,739][76542] Updated weights for policy 1, policy_version 85890 (0.0010) -[2023-10-10 16:02:35,115][76542] Updated weights for policy 1, policy_version 85900 (0.0007) -[2023-10-10 16:02:35,478][76542] Updated weights for policy 1, policy_version 85910 (0.0008) -[2023-10-10 16:02:35,848][76542] Updated weights for policy 1, policy_version 85920 (0.0010) -[2023-10-10 16:02:36,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 176128000. Throughput: 0: 1827.7, 1: 1826.8. Samples: 44034062. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-10 16:02:36,077][75634] Avg episode reward: [(0, '35.320'), (1, '35.470')] -[2023-10-10 16:02:36,323][76543] Updated weights for policy 0, policy_version 86083 (0.0009) -[2023-10-10 16:02:36,692][76543] Updated weights for policy 0, policy_version 86093 (0.0010) -[2023-10-10 16:02:37,060][76543] Updated weights for policy 0, policy_version 86103 (0.0009) -[2023-10-10 16:02:39,500][76542] Updated weights for policy 1, policy_version 85930 (0.0009) -[2023-10-10 16:02:39,874][76542] Updated weights for policy 1, policy_version 85940 (0.0009) -[2023-10-10 16:02:40,238][76542] Updated weights for policy 1, policy_version 85950 (0.0007) -[2023-10-10 16:02:40,850][76543] Updated weights for policy 0, policy_version 86113 (0.0009) -[2023-10-10 16:02:41,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 176193536. Throughput: 0: 1827.4, 1: 1818.5. Samples: 44055974. Policy #0 lag: (min: 31.0, avg: 32.7, max: 61.0) -[2023-10-10 16:02:41,077][75634] Avg episode reward: [(0, '35.830'), (1, '34.150')] -[2023-10-10 16:02:41,229][76543] Updated weights for policy 0, policy_version 86123 (0.0008) -[2023-10-10 16:02:41,606][76543] Updated weights for policy 0, policy_version 86133 (0.0009) -[2023-10-10 16:02:41,966][76543] Updated weights for policy 0, policy_version 86143 (0.0008) -[2023-10-10 16:02:43,899][76542] Updated weights for policy 1, policy_version 85960 (0.0009) -[2023-10-10 16:02:44,269][76542] Updated weights for policy 1, policy_version 85970 (0.0009) -[2023-10-10 16:02:44,647][76542] Updated weights for policy 1, policy_version 85980 (0.0010) -[2023-10-10 16:02:45,649][76543] Updated weights for policy 0, policy_version 86153 (0.0011) -[2023-10-10 16:02:46,023][76543] Updated weights for policy 0, policy_version 86163 (0.0011) -[2023-10-10 16:02:46,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 176259072. Throughput: 0: 1831.6, 1: 1816.0. Samples: 44078358. Policy #0 lag: (min: 31.0, avg: 32.7, max: 61.0) -[2023-10-10 16:02:46,077][75634] Avg episode reward: [(0, '37.050'), (1, '30.570')] -[2023-10-10 16:02:46,402][76543] Updated weights for policy 0, policy_version 86173 (0.0011) -[2023-10-10 16:02:48,323][76542] Updated weights for policy 1, policy_version 85990 (0.0010) -[2023-10-10 16:02:48,699][76542] Updated weights for policy 1, policy_version 86000 (0.0009) -[2023-10-10 16:02:49,078][76542] Updated weights for policy 1, policy_version 86010 (0.0009) -[2023-10-10 16:02:50,127][76543] Updated weights for policy 0, policy_version 86183 (0.0007) -[2023-10-10 16:02:50,512][76543] Updated weights for policy 0, policy_version 86193 (0.0008) -[2023-10-10 16:02:50,886][76543] Updated weights for policy 0, policy_version 86203 (0.0010) -[2023-10-10 16:02:51,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 176357376. Throughput: 0: 1830.1, 1: 1820.4. Samples: 44089058. Policy #0 lag: (min: 31.0, avg: 32.7, max: 61.0) -[2023-10-10 16:02:51,077][75634] Avg episode reward: [(0, '36.380'), (1, '30.770')] -[2023-10-10 16:02:52,779][76542] Updated weights for policy 1, policy_version 86020 (0.0009) -[2023-10-10 16:02:53,151][76542] Updated weights for policy 1, policy_version 86030 (0.0011) -[2023-10-10 16:02:53,528][76542] Updated weights for policy 1, policy_version 86040 (0.0009) -[2023-10-10 16:02:54,452][76543] Updated weights for policy 0, policy_version 86213 (0.0008) -[2023-10-10 16:02:54,824][76543] Updated weights for policy 0, policy_version 86223 (0.0008) -[2023-10-10 16:02:55,193][76543] Updated weights for policy 0, policy_version 86233 (0.0010) -[2023-10-10 16:02:56,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 176422912. Throughput: 0: 1833.2, 1: 1816.7. Samples: 44111264. Policy #0 lag: (min: 31.0, avg: 32.7, max: 61.0) -[2023-10-10 16:02:56,077][75634] Avg episode reward: [(0, '37.320'), (1, '30.460')] -[2023-10-10 16:02:56,974][76542] Updated weights for policy 1, policy_version 86050 (0.0008) -[2023-10-10 16:02:57,352][76542] Updated weights for policy 1, policy_version 86060 (0.0009) -[2023-10-10 16:02:57,712][76542] Updated weights for policy 1, policy_version 86070 (0.0011) -[2023-10-10 16:02:58,093][76542] Updated weights for policy 1, policy_version 86080 (0.0009) -[2023-10-10 16:02:58,745][76543] Updated weights for policy 0, policy_version 86243 (0.0008) -[2023-10-10 16:02:59,108][76543] Updated weights for policy 0, policy_version 86253 (0.0007) -[2023-10-10 16:02:59,480][76543] Updated weights for policy 0, policy_version 86263 (0.0009) -[2023-10-10 16:03:01,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 176488448. Throughput: 0: 1833.5, 1: 1813.2. Samples: 44132658. Policy #0 lag: (min: 31.0, avg: 32.7, max: 61.0) -[2023-10-10 16:03:01,077][75634] Avg episode reward: [(0, '38.200'), (1, '33.630')] -[2023-10-10 16:03:01,740][76542] Updated weights for policy 1, policy_version 86090 (0.0009) -[2023-10-10 16:03:02,118][76542] Updated weights for policy 1, policy_version 86100 (0.0009) -[2023-10-10 16:03:02,477][76542] Updated weights for policy 1, policy_version 86110 (0.0008) -[2023-10-10 16:03:03,028][76543] Updated weights for policy 0, policy_version 86273 (0.0008) -[2023-10-10 16:03:03,404][76543] Updated weights for policy 0, policy_version 86283 (0.0009) -[2023-10-10 16:03:03,769][76543] Updated weights for policy 0, policy_version 86293 (0.0008) -[2023-10-10 16:03:04,134][76543] Updated weights for policy 0, policy_version 86303 (0.0007) -[2023-10-10 16:03:06,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 176553984. Throughput: 0: 1827.8, 1: 1817.6. Samples: 44144034. Policy #0 lag: (min: 31.0, avg: 32.7, max: 61.0) -[2023-10-10 16:03:06,078][75634] Avg episode reward: [(0, '38.660'), (1, '38.770')] -[2023-10-10 16:03:06,106][76542] Updated weights for policy 1, policy_version 86120 (0.0007) -[2023-10-10 16:03:06,481][76542] Updated weights for policy 1, policy_version 86130 (0.0007) -[2023-10-10 16:03:06,850][76542] Updated weights for policy 1, policy_version 86140 (0.0008) -[2023-10-10 16:03:07,802][76543] Updated weights for policy 0, policy_version 86313 (0.0008) -[2023-10-10 16:03:08,176][76543] Updated weights for policy 0, policy_version 86323 (0.0007) -[2023-10-10 16:03:08,543][76543] Updated weights for policy 0, policy_version 86333 (0.0008) -[2023-10-10 16:03:10,447][76542] Updated weights for policy 1, policy_version 86150 (0.0007) -[2023-10-10 16:03:10,833][76542] Updated weights for policy 1, policy_version 86160 (0.0010) -[2023-10-10 16:03:11,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 176619520. Throughput: 0: 1832.3, 1: 1817.1. Samples: 44165656. Policy #0 lag: (min: 31.0, avg: 32.7, max: 61.0) -[2023-10-10 16:03:11,076][75634] Avg episode reward: [(0, '39.890'), (1, '39.260')] -[2023-10-10 16:03:11,206][76542] Updated weights for policy 1, policy_version 86170 (0.0010) -[2023-10-10 16:03:12,314][76543] Updated weights for policy 0, policy_version 86343 (0.0009) -[2023-10-10 16:03:12,689][76543] Updated weights for policy 0, policy_version 86353 (0.0008) -[2023-10-10 16:03:13,048][76543] Updated weights for policy 0, policy_version 86363 (0.0007) -[2023-10-10 16:03:14,841][76542] Updated weights for policy 1, policy_version 86180 (0.0009) -[2023-10-10 16:03:15,206][76542] Updated weights for policy 1, policy_version 86190 (0.0008) -[2023-10-10 16:03:15,567][76542] Updated weights for policy 1, policy_version 86200 (0.0007) -[2023-10-10 16:03:16,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 176717824. Throughput: 0: 1825.8, 1: 1814.1. Samples: 44187258. Policy #0 lag: (min: 31.0, avg: 32.7, max: 61.0) -[2023-10-10 16:03:16,077][75634] Avg episode reward: [(0, '37.500'), (1, '41.740')] -[2023-10-10 16:03:16,709][76543] Updated weights for policy 0, policy_version 86373 (0.0008) -[2023-10-10 16:03:17,068][76543] Updated weights for policy 0, policy_version 86383 (0.0008) -[2023-10-10 16:03:17,440][76543] Updated weights for policy 0, policy_version 86393 (0.0008) -[2023-10-10 16:03:19,241][76542] Updated weights for policy 1, policy_version 86210 (0.0009) -[2023-10-10 16:03:19,607][76542] Updated weights for policy 1, policy_version 86220 (0.0009) -[2023-10-10 16:03:19,976][76542] Updated weights for policy 1, policy_version 86230 (0.0009) -[2023-10-10 16:03:20,330][76542] Updated weights for policy 1, policy_version 86240 (0.0009) -[2023-10-10 16:03:21,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 176783360. Throughput: 0: 1822.1, 1: 1828.4. Samples: 44198332. Policy #0 lag: (min: 31.0, avg: 32.7, max: 61.0) -[2023-10-10 16:03:21,076][75634] Avg episode reward: [(0, '36.980'), (1, '40.120')] -[2023-10-10 16:03:21,174][76543] Updated weights for policy 0, policy_version 86403 (0.0009) -[2023-10-10 16:03:21,552][76543] Updated weights for policy 0, policy_version 86413 (0.0007) -[2023-10-10 16:03:21,925][76543] Updated weights for policy 0, policy_version 86423 (0.0009) -[2023-10-10 16:03:24,014][76542] Updated weights for policy 1, policy_version 86250 (0.0008) -[2023-10-10 16:03:24,383][76542] Updated weights for policy 1, policy_version 86260 (0.0011) -[2023-10-10 16:03:24,745][76542] Updated weights for policy 1, policy_version 86270 (0.0009) -[2023-10-10 16:03:25,414][76543] Updated weights for policy 0, policy_version 86433 (0.0008) -[2023-10-10 16:03:25,790][76543] Updated weights for policy 0, policy_version 86443 (0.0007) -[2023-10-10 16:03:26,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 176848896. Throughput: 0: 1827.4, 1: 1819.8. Samples: 44220098. Policy #0 lag: (min: 31.0, avg: 32.7, max: 61.0) -[2023-10-10 16:03:26,076][75634] Avg episode reward: [(0, '39.770'), (1, '31.810')] -[2023-10-10 16:03:26,158][76543] Updated weights for policy 0, policy_version 86453 (0.0009) -[2023-10-10 16:03:26,542][76543] Updated weights for policy 0, policy_version 86463 (0.0010) -[2023-10-10 16:03:28,608][76542] Updated weights for policy 1, policy_version 86280 (0.0008) -[2023-10-10 16:03:28,971][76542] Updated weights for policy 1, policy_version 86290 (0.0007) -[2023-10-10 16:03:29,338][76542] Updated weights for policy 1, policy_version 86300 (0.0008) -[2023-10-10 16:03:30,264][76543] Updated weights for policy 0, policy_version 86473 (0.0009) -[2023-10-10 16:03:30,634][76543] Updated weights for policy 0, policy_version 86483 (0.0008) -[2023-10-10 16:03:31,001][76543] Updated weights for policy 0, policy_version 86493 (0.0008) -[2023-10-10 16:03:31,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 176914432. Throughput: 0: 1815.1, 1: 1827.6. Samples: 44242278. Policy #0 lag: (min: 31.0, avg: 32.7, max: 61.0) -[2023-10-10 16:03:31,077][75634] Avg episode reward: [(0, '39.320'), (1, '30.170')] -[2023-10-10 16:03:33,153][76542] Updated weights for policy 1, policy_version 86310 (0.0010) -[2023-10-10 16:03:33,524][76542] Updated weights for policy 1, policy_version 86320 (0.0007) -[2023-10-10 16:03:33,887][76542] Updated weights for policy 1, policy_version 86330 (0.0007) -[2023-10-10 16:03:34,770][76543] Updated weights for policy 0, policy_version 86503 (0.0009) -[2023-10-10 16:03:35,156][76543] Updated weights for policy 0, policy_version 86513 (0.0010) -[2023-10-10 16:03:35,525][76543] Updated weights for policy 0, policy_version 86523 (0.0008) -[2023-10-10 16:03:36,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 177012736. Throughput: 0: 1829.7, 1: 1818.1. Samples: 44253210. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 16:03:36,077][75634] Avg episode reward: [(0, '36.610'), (1, '28.850')] -[2023-10-10 16:03:37,455][76542] Updated weights for policy 1, policy_version 86340 (0.0008) -[2023-10-10 16:03:37,822][76542] Updated weights for policy 1, policy_version 86350 (0.0008) -[2023-10-10 16:03:38,180][76542] Updated weights for policy 1, policy_version 86360 (0.0008) -[2023-10-10 16:03:39,377][76543] Updated weights for policy 0, policy_version 86533 (0.0011) -[2023-10-10 16:03:39,753][76543] Updated weights for policy 0, policy_version 86543 (0.0009) -[2023-10-10 16:03:40,127][76543] Updated weights for policy 0, policy_version 86553 (0.0008) -[2023-10-10 16:03:41,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 177078272. Throughput: 0: 1811.8, 1: 1827.5. Samples: 44275032. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 16:03:41,076][75634] Avg episode reward: [(0, '38.260'), (1, '32.170')] -[2023-10-10 16:03:41,847][76542] Updated weights for policy 1, policy_version 86370 (0.0007) -[2023-10-10 16:03:42,229][76542] Updated weights for policy 1, policy_version 86380 (0.0007) -[2023-10-10 16:03:42,598][76542] Updated weights for policy 1, policy_version 86390 (0.0008) -[2023-10-10 16:03:42,962][76542] Updated weights for policy 1, policy_version 86400 (0.0009) -[2023-10-10 16:03:43,815][76543] Updated weights for policy 0, policy_version 86563 (0.0008) -[2023-10-10 16:03:44,186][76543] Updated weights for policy 0, policy_version 86573 (0.0007) -[2023-10-10 16:03:44,559][76543] Updated weights for policy 0, policy_version 86583 (0.0008) -[2023-10-10 16:03:46,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 177143808. Throughput: 0: 1811.4, 1: 1831.3. Samples: 44296580. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 16:03:46,077][75634] Avg episode reward: [(0, '40.730'), (1, '30.940')] -[2023-10-10 16:03:46,702][76542] Updated weights for policy 1, policy_version 86410 (0.0010) -[2023-10-10 16:03:47,065][76542] Updated weights for policy 1, policy_version 86420 (0.0009) -[2023-10-10 16:03:47,436][76542] Updated weights for policy 1, policy_version 86430 (0.0010) -[2023-10-10 16:03:48,344][76543] Updated weights for policy 0, policy_version 86593 (0.0008) -[2023-10-10 16:03:48,714][76543] Updated weights for policy 0, policy_version 86603 (0.0009) -[2023-10-10 16:03:49,079][76543] Updated weights for policy 0, policy_version 86613 (0.0008) -[2023-10-10 16:03:49,451][76543] Updated weights for policy 0, policy_version 86623 (0.0009) -[2023-10-10 16:03:50,889][76542] Updated weights for policy 1, policy_version 86440 (0.0010) -[2023-10-10 16:03:51,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 177209344. Throughput: 0: 1813.5, 1: 1830.1. Samples: 44307996. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 16:03:51,077][75634] Avg episode reward: [(0, '39.400'), (1, '34.440')] -[2023-10-10 16:03:51,266][76542] Updated weights for policy 1, policy_version 86450 (0.0010) -[2023-10-10 16:03:51,629][76542] Updated weights for policy 1, policy_version 86460 (0.0008) -[2023-10-10 16:03:53,209][76543] Updated weights for policy 0, policy_version 86633 (0.0009) -[2023-10-10 16:03:53,572][76543] Updated weights for policy 0, policy_version 86643 (0.0008) -[2023-10-10 16:03:53,942][76543] Updated weights for policy 0, policy_version 86653 (0.0009) -[2023-10-10 16:03:55,265][76542] Updated weights for policy 1, policy_version 86470 (0.0007) -[2023-10-10 16:03:55,649][76542] Updated weights for policy 1, policy_version 86480 (0.0007) -[2023-10-10 16:03:56,028][76542] Updated weights for policy 1, policy_version 86490 (0.0009) -[2023-10-10 16:03:56,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 177274880. Throughput: 0: 1810.1, 1: 1833.5. Samples: 44329618. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 16:03:56,076][75634] Avg episode reward: [(0, '35.440'), (1, '36.820')] -[2023-10-10 16:03:57,840][76543] Updated weights for policy 0, policy_version 86663 (0.0012) -[2023-10-10 16:03:58,200][76543] Updated weights for policy 0, policy_version 86673 (0.0010) -[2023-10-10 16:03:58,569][76543] Updated weights for policy 0, policy_version 86683 (0.0007) -[2023-10-10 16:03:59,726][76542] Updated weights for policy 1, policy_version 86500 (0.0009) -[2023-10-10 16:04:00,096][76542] Updated weights for policy 1, policy_version 86510 (0.0008) -[2023-10-10 16:04:00,465][76542] Updated weights for policy 1, policy_version 86520 (0.0008) -[2023-10-10 16:04:01,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 177373184. Throughput: 0: 1806.2, 1: 1830.1. Samples: 44350890. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 16:04:01,077][75634] Avg episode reward: [(0, '37.620'), (1, '39.900')] -[2023-10-10 16:04:02,250][76543] Updated weights for policy 0, policy_version 86693 (0.0010) -[2023-10-10 16:04:02,628][76543] Updated weights for policy 0, policy_version 86703 (0.0012) -[2023-10-10 16:04:02,986][76543] Updated weights for policy 0, policy_version 86713 (0.0008) -[2023-10-10 16:04:04,195][76542] Updated weights for policy 1, policy_version 86530 (0.0008) -[2023-10-10 16:04:04,551][76542] Updated weights for policy 1, policy_version 86540 (0.0010) -[2023-10-10 16:04:04,928][76542] Updated weights for policy 1, policy_version 86550 (0.0009) -[2023-10-10 16:04:05,297][76542] Updated weights for policy 1, policy_version 86560 (0.0008) -[2023-10-10 16:04:06,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 177438720. Throughput: 0: 1811.5, 1: 1829.2. Samples: 44362162. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 16:04:06,077][75634] Avg episode reward: [(0, '39.220'), (1, '41.740')] -[2023-10-10 16:04:06,570][76543] Updated weights for policy 0, policy_version 86723 (0.0007) -[2023-10-10 16:04:06,947][76543] Updated weights for policy 0, policy_version 86733 (0.0007) -[2023-10-10 16:04:07,325][76543] Updated weights for policy 0, policy_version 86743 (0.0009) -[2023-10-10 16:04:08,946][76542] Updated weights for policy 1, policy_version 86570 (0.0008) -[2023-10-10 16:04:09,326][76542] Updated weights for policy 1, policy_version 86580 (0.0008) -[2023-10-10 16:04:09,685][76542] Updated weights for policy 1, policy_version 86590 (0.0010) -[2023-10-10 16:04:11,057][76543] Updated weights for policy 0, policy_version 86753 (0.0008) -[2023-10-10 16:04:11,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 177504256. Throughput: 0: 1808.5, 1: 1828.0. Samples: 44383742. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 16:04:11,076][75634] Avg episode reward: [(0, '36.760'), (1, '38.930')] -[2023-10-10 16:04:11,435][76543] Updated weights for policy 0, policy_version 86763 (0.0009) -[2023-10-10 16:04:11,804][76543] Updated weights for policy 0, policy_version 86773 (0.0007) -[2023-10-10 16:04:12,177][76543] Updated weights for policy 0, policy_version 86783 (0.0007) -[2023-10-10 16:04:13,333][76542] Updated weights for policy 1, policy_version 86600 (0.0010) -[2023-10-10 16:04:13,700][76542] Updated weights for policy 1, policy_version 86610 (0.0009) -[2023-10-10 16:04:14,074][76542] Updated weights for policy 1, policy_version 86620 (0.0007) -[2023-10-10 16:04:15,896][76543] Updated weights for policy 0, policy_version 86793 (0.0008) -[2023-10-10 16:04:16,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 177569792. Throughput: 0: 1812.7, 1: 1835.5. Samples: 44406446. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 16:04:16,076][75634] Avg episode reward: [(0, '39.320'), (1, '34.330')] -[2023-10-10 16:04:16,266][76543] Updated weights for policy 0, policy_version 86803 (0.0009) -[2023-10-10 16:04:16,637][76543] Updated weights for policy 0, policy_version 86813 (0.0009) -[2023-10-10 16:04:17,800][76542] Updated weights for policy 1, policy_version 86630 (0.0008) -[2023-10-10 16:04:18,161][76542] Updated weights for policy 1, policy_version 86640 (0.0010) -[2023-10-10 16:04:18,527][76542] Updated weights for policy 1, policy_version 86650 (0.0012) -[2023-10-10 16:04:20,208][76543] Updated weights for policy 0, policy_version 86823 (0.0008) -[2023-10-10 16:04:20,586][76543] Updated weights for policy 0, policy_version 86833 (0.0010) -[2023-10-10 16:04:20,957][76543] Updated weights for policy 0, policy_version 86843 (0.0007) -[2023-10-10 16:04:21,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 177635328. Throughput: 0: 1803.3, 1: 1824.9. Samples: 44416478. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-10 16:04:21,076][75634] Avg episode reward: [(0, '36.070'), (1, '32.400')] -[2023-10-10 16:04:22,101][76542] Updated weights for policy 1, policy_version 86660 (0.0008) -[2023-10-10 16:04:22,465][76542] Updated weights for policy 1, policy_version 86670 (0.0008) -[2023-10-10 16:04:22,825][76542] Updated weights for policy 1, policy_version 86680 (0.0008) -[2023-10-10 16:04:24,599][76543] Updated weights for policy 0, policy_version 86853 (0.0009) -[2023-10-10 16:04:24,967][76543] Updated weights for policy 0, policy_version 86863 (0.0008) -[2023-10-10 16:04:25,342][76543] Updated weights for policy 0, policy_version 86873 (0.0009) -[2023-10-10 16:04:26,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 177733632. Throughput: 0: 1821.1, 1: 1831.7. Samples: 44439410. Policy #0 lag: (min: 30.0, avg: 38.0, max: 62.0) -[2023-10-10 16:04:26,077][75634] Avg episode reward: [(0, '35.110'), (1, '33.270')] -[2023-10-10 16:04:26,611][76542] Updated weights for policy 1, policy_version 86690 (0.0009) -[2023-10-10 16:04:26,984][76542] Updated weights for policy 1, policy_version 86700 (0.0009) -[2023-10-10 16:04:27,355][76542] Updated weights for policy 1, policy_version 86710 (0.0008) -[2023-10-10 16:04:27,719][76542] Updated weights for policy 1, policy_version 86720 (0.0008) -[2023-10-10 16:04:28,882][76543] Updated weights for policy 0, policy_version 86883 (0.0007) -[2023-10-10 16:04:29,257][76543] Updated weights for policy 0, policy_version 86893 (0.0007) -[2023-10-10 16:04:29,627][76543] Updated weights for policy 0, policy_version 86903 (0.0009) -[2023-10-10 16:04:31,076][75634] Fps is (10 sec: 16383.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 177799168. Throughput: 0: 1825.0, 1: 1824.7. Samples: 44460816. Policy #0 lag: (min: 30.0, avg: 38.0, max: 62.0) -[2023-10-10 16:04:31,077][75634] Avg episode reward: [(0, '37.940'), (1, '37.280')] -[2023-10-10 16:04:31,085][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000086912_88997888.pth... -[2023-10-10 16:04:31,116][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000085216_87261184.pth -[2023-10-10 16:04:31,493][76542] Updated weights for policy 1, policy_version 86730 (0.0009) -[2023-10-10 16:04:31,862][76542] Updated weights for policy 1, policy_version 86740 (0.0008) -[2023-10-10 16:04:32,217][76542] Updated weights for policy 1, policy_version 86750 (0.0008) -[2023-10-10 16:04:32,289][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000086752_88834048.pth... -[2023-10-10 16:04:32,329][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000085024_87064576.pth -[2023-10-10 16:04:33,217][76543] Updated weights for policy 0, policy_version 86913 (0.0010) -[2023-10-10 16:04:33,586][76543] Updated weights for policy 0, policy_version 86923 (0.0008) -[2023-10-10 16:04:33,949][76543] Updated weights for policy 0, policy_version 86933 (0.0007) -[2023-10-10 16:04:34,323][76543] Updated weights for policy 0, policy_version 86943 (0.0009) -[2023-10-10 16:04:35,851][76542] Updated weights for policy 1, policy_version 86760 (0.0008) -[2023-10-10 16:04:36,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 177864704. Throughput: 0: 1826.0, 1: 1824.7. Samples: 44472276. Policy #0 lag: (min: 30.0, avg: 38.0, max: 62.0) -[2023-10-10 16:04:36,077][75634] Avg episode reward: [(0, '38.500'), (1, '36.620')] -[2023-10-10 16:04:36,220][76542] Updated weights for policy 1, policy_version 86770 (0.0008) -[2023-10-10 16:04:36,580][76542] Updated weights for policy 1, policy_version 86780 (0.0008) -[2023-10-10 16:04:37,926][76543] Updated weights for policy 0, policy_version 86953 (0.0008) -[2023-10-10 16:04:38,285][76543] Updated weights for policy 0, policy_version 86963 (0.0007) -[2023-10-10 16:04:38,661][76543] Updated weights for policy 0, policy_version 86973 (0.0011) -[2023-10-10 16:04:40,365][76542] Updated weights for policy 1, policy_version 86790 (0.0008) -[2023-10-10 16:04:40,745][76542] Updated weights for policy 1, policy_version 86800 (0.0008) -[2023-10-10 16:04:41,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 177930240. Throughput: 0: 1832.0, 1: 1819.5. Samples: 44493934. Policy #0 lag: (min: 30.0, avg: 38.0, max: 62.0) -[2023-10-10 16:04:41,076][75634] Avg episode reward: [(0, '37.320'), (1, '33.900')] -[2023-10-10 16:04:41,102][76542] Updated weights for policy 1, policy_version 86810 (0.0007) -[2023-10-10 16:04:42,223][76543] Updated weights for policy 0, policy_version 86983 (0.0009) -[2023-10-10 16:04:42,580][76543] Updated weights for policy 0, policy_version 86993 (0.0009) -[2023-10-10 16:04:42,956][76543] Updated weights for policy 0, policy_version 87003 (0.0010) -[2023-10-10 16:04:44,753][76542] Updated weights for policy 1, policy_version 86820 (0.0009) -[2023-10-10 16:04:45,131][76542] Updated weights for policy 1, policy_version 86830 (0.0008) -[2023-10-10 16:04:45,491][76542] Updated weights for policy 1, policy_version 86840 (0.0007) -[2023-10-10 16:04:46,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 178028544. Throughput: 0: 1841.6, 1: 1816.4. Samples: 44515500. Policy #0 lag: (min: 30.0, avg: 38.0, max: 62.0) -[2023-10-10 16:04:46,077][75634] Avg episode reward: [(0, '35.130'), (1, '34.080')] -[2023-10-10 16:04:46,609][76543] Updated weights for policy 0, policy_version 87013 (0.0008) -[2023-10-10 16:04:46,973][76543] Updated weights for policy 0, policy_version 87023 (0.0008) -[2023-10-10 16:04:47,349][76543] Updated weights for policy 0, policy_version 87033 (0.0010) -[2023-10-10 16:04:49,089][76542] Updated weights for policy 1, policy_version 86850 (0.0010) -[2023-10-10 16:04:49,454][76542] Updated weights for policy 1, policy_version 86860 (0.0009) -[2023-10-10 16:04:49,827][76542] Updated weights for policy 1, policy_version 86870 (0.0010) -[2023-10-10 16:04:50,203][76542] Updated weights for policy 1, policy_version 86880 (0.0009) -[2023-10-10 16:04:51,000][76543] Updated weights for policy 0, policy_version 87043 (0.0007) -[2023-10-10 16:04:51,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 178094080. Throughput: 0: 1839.8, 1: 1820.0. Samples: 44526850. Policy #0 lag: (min: 30.0, avg: 38.0, max: 62.0) -[2023-10-10 16:04:51,076][75634] Avg episode reward: [(0, '35.260'), (1, '38.090')] -[2023-10-10 16:04:51,367][76543] Updated weights for policy 0, policy_version 87053 (0.0007) -[2023-10-10 16:04:51,729][76543] Updated weights for policy 0, policy_version 87063 (0.0008) -[2023-10-10 16:04:53,938][76542] Updated weights for policy 1, policy_version 86890 (0.0012) -[2023-10-10 16:04:54,313][76542] Updated weights for policy 1, policy_version 86900 (0.0011) -[2023-10-10 16:04:54,678][76542] Updated weights for policy 1, policy_version 86910 (0.0010) -[2023-10-10 16:04:55,320][76543] Updated weights for policy 0, policy_version 87073 (0.0007) -[2023-10-10 16:04:55,688][76543] Updated weights for policy 0, policy_version 87083 (0.0007) -[2023-10-10 16:04:56,053][76543] Updated weights for policy 0, policy_version 87093 (0.0008) -[2023-10-10 16:04:56,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 178159616. Throughput: 0: 1842.6, 1: 1813.1. Samples: 44548246. Policy #0 lag: (min: 30.0, avg: 38.0, max: 62.0) -[2023-10-10 16:04:56,076][75634] Avg episode reward: [(0, '34.930'), (1, '36.210')] -[2023-10-10 16:04:56,420][76543] Updated weights for policy 0, policy_version 87103 (0.0008) -[2023-10-10 16:04:58,388][76542] Updated weights for policy 1, policy_version 86920 (0.0008) -[2023-10-10 16:04:58,755][76542] Updated weights for policy 1, policy_version 86930 (0.0008) -[2023-10-10 16:04:59,119][76542] Updated weights for policy 1, policy_version 86940 (0.0007) -[2023-10-10 16:05:00,155][76543] Updated weights for policy 0, policy_version 87113 (0.0009) -[2023-10-10 16:05:00,525][76543] Updated weights for policy 0, policy_version 87123 (0.0010) -[2023-10-10 16:05:00,892][76543] Updated weights for policy 0, policy_version 87133 (0.0009) -[2023-10-10 16:05:01,076][75634] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 178257920. Throughput: 0: 1836.2, 1: 1812.0. Samples: 44570616. Policy #0 lag: (min: 30.0, avg: 38.0, max: 62.0) -[2023-10-10 16:05:01,077][75634] Avg episode reward: [(0, '38.560'), (1, '33.090')] -[2023-10-10 16:05:02,824][76542] Updated weights for policy 1, policy_version 86950 (0.0008) -[2023-10-10 16:05:03,206][76542] Updated weights for policy 1, policy_version 86960 (0.0007) -[2023-10-10 16:05:03,571][76542] Updated weights for policy 1, policy_version 86970 (0.0008) -[2023-10-10 16:05:04,588][76543] Updated weights for policy 0, policy_version 87143 (0.0009) -[2023-10-10 16:05:04,948][76543] Updated weights for policy 0, policy_version 87153 (0.0010) -[2023-10-10 16:05:05,322][76543] Updated weights for policy 0, policy_version 87163 (0.0007) -[2023-10-10 16:05:06,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 178323456. Throughput: 0: 1844.8, 1: 1818.6. Samples: 44581334. Policy #0 lag: (min: 30.0, avg: 38.0, max: 62.0) -[2023-10-10 16:05:06,077][75634] Avg episode reward: [(0, '37.680'), (1, '38.670')] -[2023-10-10 16:05:07,367][76542] Updated weights for policy 1, policy_version 86980 (0.0010) -[2023-10-10 16:05:07,746][76542] Updated weights for policy 1, policy_version 86990 (0.0010) -[2023-10-10 16:05:08,105][76542] Updated weights for policy 1, policy_version 87000 (0.0009) -[2023-10-10 16:05:09,011][76543] Updated weights for policy 0, policy_version 87173 (0.0009) -[2023-10-10 16:05:09,388][76543] Updated weights for policy 0, policy_version 87183 (0.0007) -[2023-10-10 16:05:09,756][76543] Updated weights for policy 0, policy_version 87193 (0.0008) -[2023-10-10 16:05:11,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 178388992. Throughput: 0: 1834.0, 1: 1818.4. Samples: 44603768. Policy #0 lag: (min: 30.0, avg: 38.0, max: 62.0) -[2023-10-10 16:05:11,077][75634] Avg episode reward: [(0, '34.910'), (1, '36.500')] -[2023-10-10 16:05:11,712][76542] Updated weights for policy 1, policy_version 87010 (0.0010) -[2023-10-10 16:05:12,076][76542] Updated weights for policy 1, policy_version 87020 (0.0012) -[2023-10-10 16:05:12,448][76542] Updated weights for policy 1, policy_version 87030 (0.0011) -[2023-10-10 16:05:12,819][76542] Updated weights for policy 1, policy_version 87040 (0.0010) -[2023-10-10 16:05:13,457][76543] Updated weights for policy 0, policy_version 87203 (0.0008) -[2023-10-10 16:05:13,835][76543] Updated weights for policy 0, policy_version 87213 (0.0009) -[2023-10-10 16:05:14,197][76543] Updated weights for policy 0, policy_version 87223 (0.0009) -[2023-10-10 16:05:16,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 178454528. Throughput: 0: 1836.9, 1: 1816.5. Samples: 44625218. Policy #0 lag: (min: 30.0, avg: 38.0, max: 62.0) -[2023-10-10 16:05:16,076][75634] Avg episode reward: [(0, '35.700'), (1, '35.360')] -[2023-10-10 16:05:16,668][76542] Updated weights for policy 1, policy_version 87050 (0.0009) -[2023-10-10 16:05:17,039][76542] Updated weights for policy 1, policy_version 87060 (0.0007) -[2023-10-10 16:05:17,408][76542] Updated weights for policy 1, policy_version 87070 (0.0008) -[2023-10-10 16:05:17,942][76543] Updated weights for policy 0, policy_version 87233 (0.0008) -[2023-10-10 16:05:18,308][76543] Updated weights for policy 0, policy_version 87243 (0.0007) -[2023-10-10 16:05:18,676][76543] Updated weights for policy 0, policy_version 87253 (0.0008) -[2023-10-10 16:05:19,049][76543] Updated weights for policy 0, policy_version 87263 (0.0008) -[2023-10-10 16:05:21,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 178520064. Throughput: 0: 1829.6, 1: 1815.6. Samples: 44636310. Policy #0 lag: (min: 30.0, avg: 38.0, max: 62.0) -[2023-10-10 16:05:21,077][75634] Avg episode reward: [(0, '36.880'), (1, '39.590')] -[2023-10-10 16:05:21,086][76542] Updated weights for policy 1, policy_version 87080 (0.0010) -[2023-10-10 16:05:21,449][76542] Updated weights for policy 1, policy_version 87090 (0.0012) -[2023-10-10 16:05:21,817][76542] Updated weights for policy 1, policy_version 87100 (0.0009) -[2023-10-10 16:05:22,622][76543] Updated weights for policy 0, policy_version 87273 (0.0008) -[2023-10-10 16:05:22,993][76543] Updated weights for policy 0, policy_version 87283 (0.0008) -[2023-10-10 16:05:23,369][76543] Updated weights for policy 0, policy_version 87293 (0.0008) -[2023-10-10 16:05:25,464][76542] Updated weights for policy 1, policy_version 87110 (0.0009) -[2023-10-10 16:05:25,841][76542] Updated weights for policy 1, policy_version 87120 (0.0008) -[2023-10-10 16:05:26,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 178585600. Throughput: 0: 1834.3, 1: 1821.1. Samples: 44658432. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 16:05:26,077][75634] Avg episode reward: [(0, '36.100'), (1, '35.320')] -[2023-10-10 16:05:26,207][76542] Updated weights for policy 1, policy_version 87130 (0.0008) -[2023-10-10 16:05:27,081][76543] Updated weights for policy 0, policy_version 87303 (0.0008) -[2023-10-10 16:05:27,454][76543] Updated weights for policy 0, policy_version 87313 (0.0009) -[2023-10-10 16:05:27,826][76543] Updated weights for policy 0, policy_version 87323 (0.0007) -[2023-10-10 16:05:29,972][76542] Updated weights for policy 1, policy_version 87140 (0.0008) -[2023-10-10 16:05:30,346][76542] Updated weights for policy 1, policy_version 87150 (0.0009) -[2023-10-10 16:05:30,706][76542] Updated weights for policy 1, policy_version 87160 (0.0009) -[2023-10-10 16:05:31,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 178683904. Throughput: 0: 1827.8, 1: 1825.0. Samples: 44679878. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 16:05:31,077][75634] Avg episode reward: [(0, '33.630'), (1, '33.800')] -[2023-10-10 16:05:31,368][76543] Updated weights for policy 0, policy_version 87333 (0.0008) -[2023-10-10 16:05:31,737][76543] Updated weights for policy 0, policy_version 87343 (0.0008) -[2023-10-10 16:05:32,100][76543] Updated weights for policy 0, policy_version 87353 (0.0010) -[2023-10-10 16:05:34,376][76542] Updated weights for policy 1, policy_version 87170 (0.0009) -[2023-10-10 16:05:34,749][76542] Updated weights for policy 1, policy_version 87180 (0.0009) -[2023-10-10 16:05:35,121][76542] Updated weights for policy 1, policy_version 87190 (0.0008) -[2023-10-10 16:05:35,490][76542] Updated weights for policy 1, policy_version 87200 (0.0009) -[2023-10-10 16:05:35,909][76543] Updated weights for policy 0, policy_version 87363 (0.0007) -[2023-10-10 16:05:36,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 178749440. Throughput: 0: 1829.0, 1: 1819.5. Samples: 44691034. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 16:05:36,077][75634] Avg episode reward: [(0, '36.040'), (1, '30.300')] -[2023-10-10 16:05:36,267][76543] Updated weights for policy 0, policy_version 87373 (0.0008) -[2023-10-10 16:05:36,645][76543] Updated weights for policy 0, policy_version 87383 (0.0009) -[2023-10-10 16:05:39,290][76542] Updated weights for policy 1, policy_version 87210 (0.0008) -[2023-10-10 16:05:39,651][76542] Updated weights for policy 1, policy_version 87220 (0.0008) -[2023-10-10 16:05:40,024][76542] Updated weights for policy 1, policy_version 87230 (0.0008) -[2023-10-10 16:05:40,309][76543] Updated weights for policy 0, policy_version 87393 (0.0010) -[2023-10-10 16:05:40,682][76543] Updated weights for policy 0, policy_version 87403 (0.0008) -[2023-10-10 16:05:41,044][76543] Updated weights for policy 0, policy_version 87413 (0.0010) -[2023-10-10 16:05:41,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 178814976. Throughput: 0: 1827.1, 1: 1829.2. Samples: 44712778. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 16:05:41,076][75634] Avg episode reward: [(0, '31.800'), (1, '34.060')] -[2023-10-10 16:05:41,414][76543] Updated weights for policy 0, policy_version 87423 (0.0009) -[2023-10-10 16:05:43,621][76542] Updated weights for policy 1, policy_version 87240 (0.0007) -[2023-10-10 16:05:43,988][76542] Updated weights for policy 1, policy_version 87250 (0.0010) -[2023-10-10 16:05:44,353][76542] Updated weights for policy 1, policy_version 87260 (0.0008) -[2023-10-10 16:05:45,094][76543] Updated weights for policy 0, policy_version 87433 (0.0008) -[2023-10-10 16:05:45,465][76543] Updated weights for policy 0, policy_version 87443 (0.0008) -[2023-10-10 16:05:45,842][76543] Updated weights for policy 0, policy_version 87453 (0.0007) -[2023-10-10 16:05:46,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 178913280. Throughput: 0: 1828.1, 1: 1824.0. Samples: 44734958. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 16:05:46,076][75634] Avg episode reward: [(0, '36.660'), (1, '40.860')] -[2023-10-10 16:05:47,912][76542] Updated weights for policy 1, policy_version 87270 (0.0009) -[2023-10-10 16:05:48,281][76542] Updated weights for policy 1, policy_version 87280 (0.0008) -[2023-10-10 16:05:48,649][76542] Updated weights for policy 1, policy_version 87290 (0.0008) -[2023-10-10 16:05:49,428][76543] Updated weights for policy 0, policy_version 87463 (0.0010) -[2023-10-10 16:05:49,792][76543] Updated weights for policy 0, policy_version 87473 (0.0008) -[2023-10-10 16:05:50,156][76543] Updated weights for policy 0, policy_version 87483 (0.0010) -[2023-10-10 16:05:51,076][75634] Fps is (10 sec: 16383.4, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 178978816. Throughput: 0: 1829.4, 1: 1824.3. Samples: 44745752. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 16:05:51,077][75634] Avg episode reward: [(0, '36.190'), (1, '43.270')] -[2023-10-10 16:05:52,291][76542] Updated weights for policy 1, policy_version 87300 (0.0007) -[2023-10-10 16:05:52,669][76542] Updated weights for policy 1, policy_version 87310 (0.0007) -[2023-10-10 16:05:53,034][76542] Updated weights for policy 1, policy_version 87320 (0.0007) -[2023-10-10 16:05:53,850][76543] Updated weights for policy 0, policy_version 87493 (0.0008) -[2023-10-10 16:05:54,233][76543] Updated weights for policy 0, policy_version 87503 (0.0007) -[2023-10-10 16:05:54,600][76543] Updated weights for policy 0, policy_version 87513 (0.0008) -[2023-10-10 16:05:56,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 179044352. Throughput: 0: 1823.0, 1: 1821.3. Samples: 44767762. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 16:05:56,076][75634] Avg episode reward: [(0, '39.650'), (1, '37.300')] -[2023-10-10 16:05:56,831][76542] Updated weights for policy 1, policy_version 87330 (0.0007) -[2023-10-10 16:05:57,202][76542] Updated weights for policy 1, policy_version 87340 (0.0007) -[2023-10-10 16:05:57,563][76542] Updated weights for policy 1, policy_version 87350 (0.0008) -[2023-10-10 16:05:57,925][76542] Updated weights for policy 1, policy_version 87360 (0.0008) -[2023-10-10 16:05:58,007][76543] Updated weights for policy 0, policy_version 87523 (0.0009) -[2023-10-10 16:05:58,376][76543] Updated weights for policy 0, policy_version 87533 (0.0010) -[2023-10-10 16:05:58,750][76543] Updated weights for policy 0, policy_version 87543 (0.0008) -[2023-10-10 16:06:01,076][75634] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14662.3). Total num frames: 179109888. Throughput: 0: 1836.2, 1: 1826.6. Samples: 44790046. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 16:06:01,076][75634] Avg episode reward: [(0, '35.860'), (1, '38.720')] -[2023-10-10 16:06:01,438][76542] Updated weights for policy 1, policy_version 87370 (0.0007) -[2023-10-10 16:06:01,807][76542] Updated weights for policy 1, policy_version 87380 (0.0007) -[2023-10-10 16:06:02,172][76542] Updated weights for policy 1, policy_version 87390 (0.0008) -[2023-10-10 16:06:02,533][76543] Updated weights for policy 0, policy_version 87553 (0.0007) -[2023-10-10 16:06:02,892][76543] Updated weights for policy 0, policy_version 87563 (0.0007) -[2023-10-10 16:06:03,256][76543] Updated weights for policy 0, policy_version 87573 (0.0007) -[2023-10-10 16:06:03,623][76543] Updated weights for policy 0, policy_version 87583 (0.0008) -[2023-10-10 16:06:05,884][76542] Updated weights for policy 1, policy_version 87400 (0.0007) -[2023-10-10 16:06:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 179175424. Throughput: 0: 1825.7, 1: 1828.4. Samples: 44800748. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 16:06:06,077][75634] Avg episode reward: [(0, '34.650'), (1, '36.530')] -[2023-10-10 16:06:06,253][76542] Updated weights for policy 1, policy_version 87410 (0.0008) -[2023-10-10 16:06:06,618][76542] Updated weights for policy 1, policy_version 87420 (0.0008) -[2023-10-10 16:06:07,354][76543] Updated weights for policy 0, policy_version 87593 (0.0008) -[2023-10-10 16:06:07,724][76543] Updated weights for policy 0, policy_version 87603 (0.0008) -[2023-10-10 16:06:08,099][76543] Updated weights for policy 0, policy_version 87613 (0.0009) -[2023-10-10 16:06:10,425][76542] Updated weights for policy 1, policy_version 87430 (0.0007) -[2023-10-10 16:06:10,804][76542] Updated weights for policy 1, policy_version 87440 (0.0010) -[2023-10-10 16:06:11,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 179240960. Throughput: 0: 1834.4, 1: 1827.0. Samples: 44823194. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 16:06:11,077][75634] Avg episode reward: [(0, '36.190'), (1, '37.270')] -[2023-10-10 16:06:11,175][76542] Updated weights for policy 1, policy_version 87450 (0.0009) -[2023-10-10 16:06:11,717][76543] Updated weights for policy 0, policy_version 87623 (0.0007) -[2023-10-10 16:06:12,096][76543] Updated weights for policy 0, policy_version 87633 (0.0009) -[2023-10-10 16:06:12,474][76543] Updated weights for policy 0, policy_version 87643 (0.0009) -[2023-10-10 16:06:14,625][76542] Updated weights for policy 1, policy_version 87460 (0.0008) -[2023-10-10 16:06:15,002][76542] Updated weights for policy 1, policy_version 87470 (0.0009) -[2023-10-10 16:06:15,372][76542] Updated weights for policy 1, policy_version 87480 (0.0007) -[2023-10-10 16:06:16,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 179339264. Throughput: 0: 1836.9, 1: 1823.7. Samples: 44844602. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 16:06:16,076][75634] Avg episode reward: [(0, '34.650'), (1, '32.530')] -[2023-10-10 16:06:16,212][76543] Updated weights for policy 0, policy_version 87653 (0.0009) -[2023-10-10 16:06:16,588][76543] Updated weights for policy 0, policy_version 87663 (0.0007) -[2023-10-10 16:06:16,958][76543] Updated weights for policy 0, policy_version 87673 (0.0008) -[2023-10-10 16:06:19,105][76542] Updated weights for policy 1, policy_version 87490 (0.0008) -[2023-10-10 16:06:19,477][76542] Updated weights for policy 1, policy_version 87500 (0.0011) -[2023-10-10 16:06:19,850][76542] Updated weights for policy 1, policy_version 87510 (0.0011) -[2023-10-10 16:06:20,221][76542] Updated weights for policy 1, policy_version 87520 (0.0007) -[2023-10-10 16:06:20,574][76543] Updated weights for policy 0, policy_version 87683 (0.0008) -[2023-10-10 16:06:20,942][76543] Updated weights for policy 0, policy_version 87693 (0.0008) -[2023-10-10 16:06:21,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 179404800. Throughput: 0: 1836.2, 1: 1829.5. Samples: 44855988. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-10 16:06:21,076][75634] Avg episode reward: [(0, '38.670'), (1, '30.600')] -[2023-10-10 16:06:21,315][76543] Updated weights for policy 0, policy_version 87703 (0.0009) -[2023-10-10 16:06:23,709][76542] Updated weights for policy 1, policy_version 87530 (0.0008) -[2023-10-10 16:06:24,080][76542] Updated weights for policy 1, policy_version 87540 (0.0008) -[2023-10-10 16:06:24,450][76542] Updated weights for policy 1, policy_version 87550 (0.0008) -[2023-10-10 16:06:25,020][76543] Updated weights for policy 0, policy_version 87713 (0.0008) -[2023-10-10 16:06:25,385][76543] Updated weights for policy 0, policy_version 87723 (0.0008) -[2023-10-10 16:06:25,753][76543] Updated weights for policy 0, policy_version 87733 (0.0007) -[2023-10-10 16:06:26,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 179470336. Throughput: 0: 1837.4, 1: 1822.5. Samples: 44877474. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-10 16:06:26,077][75634] Avg episode reward: [(0, '39.020'), (1, '32.420')] -[2023-10-10 16:06:26,113][76543] Updated weights for policy 0, policy_version 87743 (0.0007) -[2023-10-10 16:06:28,144][76542] Updated weights for policy 1, policy_version 87560 (0.0009) -[2023-10-10 16:06:28,497][76542] Updated weights for policy 1, policy_version 87570 (0.0007) -[2023-10-10 16:06:28,867][76542] Updated weights for policy 1, policy_version 87580 (0.0007) -[2023-10-10 16:06:29,823][76543] Updated weights for policy 0, policy_version 87753 (0.0008) -[2023-10-10 16:06:30,198][76543] Updated weights for policy 0, policy_version 87763 (0.0010) -[2023-10-10 16:06:30,571][76543] Updated weights for policy 0, policy_version 87773 (0.0010) -[2023-10-10 16:06:31,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 179568640. Throughput: 0: 1829.8, 1: 1833.5. Samples: 44899808. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-10 16:06:31,077][75634] Avg episode reward: [(0, '39.700'), (1, '33.400')] -[2023-10-10 16:06:31,086][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000087776_89882624.pth... -[2023-10-10 16:06:31,087][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000087584_89686016.pth... -[2023-10-10 16:06:31,122][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000086048_88113152.pth -[2023-10-10 16:06:31,130][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000085888_87949312.pth -[2023-10-10 16:06:32,594][76542] Updated weights for policy 1, policy_version 87590 (0.0009) -[2023-10-10 16:06:32,955][76542] Updated weights for policy 1, policy_version 87600 (0.0008) -[2023-10-10 16:06:33,325][76542] Updated weights for policy 1, policy_version 87610 (0.0007) -[2023-10-10 16:06:34,256][76543] Updated weights for policy 0, policy_version 87783 (0.0008) -[2023-10-10 16:06:34,624][76543] Updated weights for policy 0, policy_version 87793 (0.0008) -[2023-10-10 16:06:35,000][76543] Updated weights for policy 0, policy_version 87803 (0.0008) -[2023-10-10 16:06:36,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 179634176. Throughput: 0: 1835.9, 1: 1822.4. Samples: 44910374. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-10 16:06:36,076][75634] Avg episode reward: [(0, '41.570'), (1, '37.430')] -[2023-10-10 16:06:36,941][76542] Updated weights for policy 1, policy_version 87620 (0.0007) -[2023-10-10 16:06:37,314][76542] Updated weights for policy 1, policy_version 87630 (0.0008) -[2023-10-10 16:06:37,685][76542] Updated weights for policy 1, policy_version 87640 (0.0009) -[2023-10-10 16:06:38,660][76543] Updated weights for policy 0, policy_version 87813 (0.0009) -[2023-10-10 16:06:39,052][76543] Updated weights for policy 0, policy_version 87823 (0.0007) -[2023-10-10 16:06:39,422][76543] Updated weights for policy 0, policy_version 87833 (0.0009) -[2023-10-10 16:06:41,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 179699712. Throughput: 0: 1824.9, 1: 1832.7. Samples: 44932354. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-10 16:06:41,077][75634] Avg episode reward: [(0, '39.290'), (1, '38.560')] -[2023-10-10 16:06:41,378][76542] Updated weights for policy 1, policy_version 87650 (0.0009) -[2023-10-10 16:06:41,748][76542] Updated weights for policy 1, policy_version 87660 (0.0008) -[2023-10-10 16:06:42,114][76542] Updated weights for policy 1, policy_version 87670 (0.0007) -[2023-10-10 16:06:42,484][76542] Updated weights for policy 1, policy_version 87680 (0.0010) -[2023-10-10 16:06:42,893][76543] Updated weights for policy 0, policy_version 87843 (0.0008) -[2023-10-10 16:06:43,261][76543] Updated weights for policy 0, policy_version 87853 (0.0010) -[2023-10-10 16:06:43,633][76543] Updated weights for policy 0, policy_version 87863 (0.0010) -[2023-10-10 16:06:46,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 179765248. Throughput: 0: 1827.0, 1: 1832.8. Samples: 44954738. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-10 16:06:46,077][75634] Avg episode reward: [(0, '38.280'), (1, '37.930')] -[2023-10-10 16:06:46,089][76542] Updated weights for policy 1, policy_version 87690 (0.0007) -[2023-10-10 16:06:46,455][76542] Updated weights for policy 1, policy_version 87700 (0.0007) -[2023-10-10 16:06:46,825][76542] Updated weights for policy 1, policy_version 87710 (0.0007) -[2023-10-10 16:06:47,353][76543] Updated weights for policy 0, policy_version 87873 (0.0008) -[2023-10-10 16:06:47,719][76543] Updated weights for policy 0, policy_version 87883 (0.0008) -[2023-10-10 16:06:48,084][76543] Updated weights for policy 0, policy_version 87893 (0.0008) -[2023-10-10 16:06:48,457][76543] Updated weights for policy 0, policy_version 87903 (0.0007) -[2023-10-10 16:06:50,561][76542] Updated weights for policy 1, policy_version 87720 (0.0008) -[2023-10-10 16:06:50,925][76542] Updated weights for policy 1, policy_version 87730 (0.0011) -[2023-10-10 16:06:51,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.6, 300 sec: 14551.2). Total num frames: 179830784. Throughput: 0: 1824.3, 1: 1829.5. Samples: 44965170. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-10 16:06:51,076][75634] Avg episode reward: [(0, '38.980'), (1, '39.330')] -[2023-10-10 16:06:51,292][76542] Updated weights for policy 1, policy_version 87740 (0.0011) -[2023-10-10 16:06:52,248][76543] Updated weights for policy 0, policy_version 87913 (0.0008) -[2023-10-10 16:06:52,624][76543] Updated weights for policy 0, policy_version 87923 (0.0008) -[2023-10-10 16:06:52,990][76543] Updated weights for policy 0, policy_version 87933 (0.0010) -[2023-10-10 16:06:55,143][76542] Updated weights for policy 1, policy_version 87750 (0.0008) -[2023-10-10 16:06:55,519][76542] Updated weights for policy 1, policy_version 87760 (0.0011) -[2023-10-10 16:06:55,895][76542] Updated weights for policy 1, policy_version 87770 (0.0008) -[2023-10-10 16:06:56,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 179896320. Throughput: 0: 1825.1, 1: 1822.9. Samples: 44987354. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-10 16:06:56,078][75634] Avg episode reward: [(0, '38.730'), (1, '36.580')] -[2023-10-10 16:06:56,668][76543] Updated weights for policy 0, policy_version 87943 (0.0008) -[2023-10-10 16:06:57,026][76543] Updated weights for policy 0, policy_version 87953 (0.0007) -[2023-10-10 16:06:57,399][76543] Updated weights for policy 0, policy_version 87963 (0.0007) -[2023-10-10 16:06:59,619][76542] Updated weights for policy 1, policy_version 87780 (0.0007) -[2023-10-10 16:07:00,007][76542] Updated weights for policy 1, policy_version 87790 (0.0011) -[2023-10-10 16:07:00,370][76542] Updated weights for policy 1, policy_version 87800 (0.0008) -[2023-10-10 16:07:01,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 179994624. Throughput: 0: 1825.7, 1: 1818.3. Samples: 45008584. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-10 16:07:01,077][75634] Avg episode reward: [(0, '31.580'), (1, '33.780')] -[2023-10-10 16:07:01,162][76543] Updated weights for policy 0, policy_version 87973 (0.0009) -[2023-10-10 16:07:01,531][76543] Updated weights for policy 0, policy_version 87983 (0.0009) -[2023-10-10 16:07:01,907][76543] Updated weights for policy 0, policy_version 87993 (0.0008) -[2023-10-10 16:07:03,961][76542] Updated weights for policy 1, policy_version 87810 (0.0007) -[2023-10-10 16:07:04,337][76542] Updated weights for policy 1, policy_version 87820 (0.0007) -[2023-10-10 16:07:04,710][76542] Updated weights for policy 1, policy_version 87830 (0.0007) -[2023-10-10 16:07:05,081][76542] Updated weights for policy 1, policy_version 87840 (0.0007) -[2023-10-10 16:07:05,553][76543] Updated weights for policy 0, policy_version 88003 (0.0009) -[2023-10-10 16:07:05,913][76543] Updated weights for policy 0, policy_version 88013 (0.0011) -[2023-10-10 16:07:06,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 180060160. Throughput: 0: 1824.9, 1: 1820.0. Samples: 45020010. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-10 16:07:06,077][75634] Avg episode reward: [(0, '30.870'), (1, '31.270')] -[2023-10-10 16:07:06,280][76543] Updated weights for policy 0, policy_version 88023 (0.0010) -[2023-10-10 16:07:08,720][76542] Updated weights for policy 1, policy_version 87850 (0.0009) -[2023-10-10 16:07:09,089][76542] Updated weights for policy 1, policy_version 87860 (0.0009) -[2023-10-10 16:07:09,457][76542] Updated weights for policy 1, policy_version 87870 (0.0008) -[2023-10-10 16:07:09,975][76543] Updated weights for policy 0, policy_version 88033 (0.0011) -[2023-10-10 16:07:10,330][76543] Updated weights for policy 0, policy_version 88043 (0.0010) -[2023-10-10 16:07:10,697][76543] Updated weights for policy 0, policy_version 88053 (0.0010) -[2023-10-10 16:07:11,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 180125696. Throughput: 0: 1824.4, 1: 1820.0. Samples: 45041476. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-10 16:07:11,077][75634] Avg episode reward: [(0, '29.230'), (1, '29.950')] -[2023-10-10 16:07:11,079][76543] Updated weights for policy 0, policy_version 88063 (0.0009) -[2023-10-10 16:07:13,323][76542] Updated weights for policy 1, policy_version 87880 (0.0010) -[2023-10-10 16:07:13,697][76542] Updated weights for policy 1, policy_version 87890 (0.0007) -[2023-10-10 16:07:14,066][76542] Updated weights for policy 1, policy_version 87900 (0.0011) -[2023-10-10 16:07:14,849][76543] Updated weights for policy 0, policy_version 88073 (0.0009) -[2023-10-10 16:07:15,217][76543] Updated weights for policy 0, policy_version 88083 (0.0008) -[2023-10-10 16:07:15,591][76543] Updated weights for policy 0, policy_version 88093 (0.0008) -[2023-10-10 16:07:16,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 180224000. Throughput: 0: 1816.8, 1: 1812.1. Samples: 45063108. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-10 16:07:16,076][75634] Avg episode reward: [(0, '33.500'), (1, '32.850')] -[2023-10-10 16:07:17,907][76542] Updated weights for policy 1, policy_version 87910 (0.0010) -[2023-10-10 16:07:18,269][76542] Updated weights for policy 1, policy_version 87920 (0.0008) -[2023-10-10 16:07:18,640][76542] Updated weights for policy 1, policy_version 87930 (0.0007) -[2023-10-10 16:07:19,147][76543] Updated weights for policy 0, policy_version 88103 (0.0007) -[2023-10-10 16:07:19,506][76543] Updated weights for policy 0, policy_version 88113 (0.0009) -[2023-10-10 16:07:19,881][76543] Updated weights for policy 0, policy_version 88123 (0.0011) -[2023-10-10 16:07:21,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 180289536. Throughput: 0: 1820.0, 1: 1815.6. Samples: 45073972. Policy #0 lag: (min: 24.0, avg: 48.8, max: 56.0) -[2023-10-10 16:07:21,077][75634] Avg episode reward: [(0, '32.530'), (1, '36.780')] -[2023-10-10 16:07:22,280][76542] Updated weights for policy 1, policy_version 87940 (0.0007) -[2023-10-10 16:07:22,652][76542] Updated weights for policy 1, policy_version 87950 (0.0007) -[2023-10-10 16:07:23,013][76542] Updated weights for policy 1, policy_version 87960 (0.0008) -[2023-10-10 16:07:23,641][76543] Updated weights for policy 0, policy_version 88133 (0.0008) -[2023-10-10 16:07:24,012][76543] Updated weights for policy 0, policy_version 88143 (0.0008) -[2023-10-10 16:07:24,377][76543] Updated weights for policy 0, policy_version 88153 (0.0007) -[2023-10-10 16:07:26,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 180355072. Throughput: 0: 1816.9, 1: 1805.3. Samples: 45095356. Policy #0 lag: (min: 24.0, avg: 48.8, max: 56.0) -[2023-10-10 16:07:26,077][75634] Avg episode reward: [(0, '37.010'), (1, '34.320')] -[2023-10-10 16:07:26,678][76542] Updated weights for policy 1, policy_version 87970 (0.0007) -[2023-10-10 16:07:27,051][76542] Updated weights for policy 1, policy_version 87980 (0.0008) -[2023-10-10 16:07:27,416][76542] Updated weights for policy 1, policy_version 87990 (0.0008) -[2023-10-10 16:07:27,777][76542] Updated weights for policy 1, policy_version 88000 (0.0009) -[2023-10-10 16:07:28,078][76543] Updated weights for policy 0, policy_version 88163 (0.0009) -[2023-10-10 16:07:28,439][76543] Updated weights for policy 0, policy_version 88173 (0.0008) -[2023-10-10 16:07:28,822][76543] Updated weights for policy 0, policy_version 88183 (0.0009) -[2023-10-10 16:07:31,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 180420608. Throughput: 0: 1813.2, 1: 1806.8. Samples: 45117640. Policy #0 lag: (min: 24.0, avg: 48.8, max: 56.0) -[2023-10-10 16:07:31,077][75634] Avg episode reward: [(0, '38.450'), (1, '36.660')] -[2023-10-10 16:07:31,405][76542] Updated weights for policy 1, policy_version 88010 (0.0007) -[2023-10-10 16:07:31,774][76542] Updated weights for policy 1, policy_version 88020 (0.0008) -[2023-10-10 16:07:32,141][76542] Updated weights for policy 1, policy_version 88030 (0.0009) -[2023-10-10 16:07:32,631][76543] Updated weights for policy 0, policy_version 88193 (0.0009) -[2023-10-10 16:07:33,007][76543] Updated weights for policy 0, policy_version 88203 (0.0010) -[2023-10-10 16:07:33,369][76543] Updated weights for policy 0, policy_version 88213 (0.0007) -[2023-10-10 16:07:33,747][76543] Updated weights for policy 0, policy_version 88223 (0.0008) -[2023-10-10 16:07:35,755][76542] Updated weights for policy 1, policy_version 88040 (0.0009) -[2023-10-10 16:07:36,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 180486144. Throughput: 0: 1816.8, 1: 1807.2. Samples: 45128254. Policy #0 lag: (min: 24.0, avg: 48.8, max: 56.0) -[2023-10-10 16:07:36,076][75634] Avg episode reward: [(0, '36.710'), (1, '39.640')] -[2023-10-10 16:07:36,126][76542] Updated weights for policy 1, policy_version 88050 (0.0010) -[2023-10-10 16:07:36,498][76542] Updated weights for policy 1, policy_version 88060 (0.0007) -[2023-10-10 16:07:37,464][76543] Updated weights for policy 0, policy_version 88233 (0.0010) -[2023-10-10 16:07:37,836][76543] Updated weights for policy 0, policy_version 88243 (0.0009) -[2023-10-10 16:07:38,210][76543] Updated weights for policy 0, policy_version 88253 (0.0009) -[2023-10-10 16:07:40,282][76542] Updated weights for policy 1, policy_version 88070 (0.0008) -[2023-10-10 16:07:40,655][76542] Updated weights for policy 1, policy_version 88080 (0.0008) -[2023-10-10 16:07:41,020][76542] Updated weights for policy 1, policy_version 88090 (0.0010) -[2023-10-10 16:07:41,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 180551680. Throughput: 0: 1807.4, 1: 1810.5. Samples: 45150162. Policy #0 lag: (min: 24.0, avg: 48.8, max: 56.0) -[2023-10-10 16:07:41,077][75634] Avg episode reward: [(0, '39.690'), (1, '38.160')] -[2023-10-10 16:07:42,100][76543] Updated weights for policy 0, policy_version 88263 (0.0008) -[2023-10-10 16:07:42,471][76543] Updated weights for policy 0, policy_version 88273 (0.0009) -[2023-10-10 16:07:42,844][76543] Updated weights for policy 0, policy_version 88283 (0.0009) -[2023-10-10 16:07:44,632][76542] Updated weights for policy 1, policy_version 88100 (0.0009) -[2023-10-10 16:07:45,021][76542] Updated weights for policy 1, policy_version 88110 (0.0007) -[2023-10-10 16:07:45,387][76542] Updated weights for policy 1, policy_version 88120 (0.0009) -[2023-10-10 16:07:46,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 180649984. Throughput: 0: 1809.2, 1: 1815.0. Samples: 45171670. Policy #0 lag: (min: 24.0, avg: 48.8, max: 56.0) -[2023-10-10 16:07:46,076][75634] Avg episode reward: [(0, '38.920'), (1, '36.780')] -[2023-10-10 16:07:46,400][76543] Updated weights for policy 0, policy_version 88293 (0.0009) -[2023-10-10 16:07:46,775][76543] Updated weights for policy 0, policy_version 88303 (0.0009) -[2023-10-10 16:07:47,153][76543] Updated weights for policy 0, policy_version 88313 (0.0009) -[2023-10-10 16:07:49,096][76542] Updated weights for policy 1, policy_version 88130 (0.0009) -[2023-10-10 16:07:49,467][76542] Updated weights for policy 1, policy_version 88140 (0.0008) -[2023-10-10 16:07:49,827][76542] Updated weights for policy 1, policy_version 88150 (0.0010) -[2023-10-10 16:07:50,189][76542] Updated weights for policy 1, policy_version 88160 (0.0007) -[2023-10-10 16:07:50,725][76543] Updated weights for policy 0, policy_version 88323 (0.0008) -[2023-10-10 16:07:51,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 180715520. Throughput: 0: 1807.4, 1: 1816.4. Samples: 45183080. Policy #0 lag: (min: 24.0, avg: 48.8, max: 56.0) -[2023-10-10 16:07:51,077][75634] Avg episode reward: [(0, '35.100'), (1, '33.510')] -[2023-10-10 16:07:51,097][76543] Updated weights for policy 0, policy_version 88333 (0.0009) -[2023-10-10 16:07:51,472][76543] Updated weights for policy 0, policy_version 88343 (0.0008) -[2023-10-10 16:07:53,819][76542] Updated weights for policy 1, policy_version 88170 (0.0008) -[2023-10-10 16:07:54,183][76542] Updated weights for policy 1, policy_version 88180 (0.0008) -[2023-10-10 16:07:54,544][76542] Updated weights for policy 1, policy_version 88190 (0.0009) -[2023-10-10 16:07:55,036][76543] Updated weights for policy 0, policy_version 88353 (0.0007) -[2023-10-10 16:07:55,401][76543] Updated weights for policy 0, policy_version 88363 (0.0008) -[2023-10-10 16:07:55,773][76543] Updated weights for policy 0, policy_version 88373 (0.0007) -[2023-10-10 16:07:56,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 180781056. Throughput: 0: 1813.1, 1: 1816.4. Samples: 45204802. Policy #0 lag: (min: 24.0, avg: 48.8, max: 56.0) -[2023-10-10 16:07:56,076][75634] Avg episode reward: [(0, '37.300'), (1, '37.210')] -[2023-10-10 16:07:56,145][76543] Updated weights for policy 0, policy_version 88383 (0.0008) -[2023-10-10 16:07:58,193][76542] Updated weights for policy 1, policy_version 88200 (0.0007) -[2023-10-10 16:07:58,559][76542] Updated weights for policy 1, policy_version 88210 (0.0009) -[2023-10-10 16:07:58,929][76542] Updated weights for policy 1, policy_version 88220 (0.0007) -[2023-10-10 16:07:59,684][76543] Updated weights for policy 0, policy_version 88393 (0.0009) -[2023-10-10 16:08:00,050][76543] Updated weights for policy 0, policy_version 88403 (0.0007) -[2023-10-10 16:08:00,416][76543] Updated weights for policy 0, policy_version 88413 (0.0007) -[2023-10-10 16:08:01,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 180879360. Throughput: 0: 1821.1, 1: 1826.3. Samples: 45227242. Policy #0 lag: (min: 24.0, avg: 48.8, max: 56.0) -[2023-10-10 16:08:01,077][75634] Avg episode reward: [(0, '36.920'), (1, '36.460')] -[2023-10-10 16:08:02,621][76542] Updated weights for policy 1, policy_version 88230 (0.0009) -[2023-10-10 16:08:02,989][76542] Updated weights for policy 1, policy_version 88240 (0.0011) -[2023-10-10 16:08:03,352][76542] Updated weights for policy 1, policy_version 88250 (0.0010) -[2023-10-10 16:08:04,217][76543] Updated weights for policy 0, policy_version 88423 (0.0009) -[2023-10-10 16:08:04,593][76543] Updated weights for policy 0, policy_version 88433 (0.0008) -[2023-10-10 16:08:04,966][76543] Updated weights for policy 0, policy_version 88443 (0.0009) -[2023-10-10 16:08:06,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 180944896. Throughput: 0: 1824.9, 1: 1827.2. Samples: 45238318. Policy #0 lag: (min: 24.0, avg: 48.8, max: 56.0) -[2023-10-10 16:08:06,077][75634] Avg episode reward: [(0, '35.230'), (1, '35.390')] -[2023-10-10 16:08:07,068][76542] Updated weights for policy 1, policy_version 88260 (0.0008) -[2023-10-10 16:08:07,429][76542] Updated weights for policy 1, policy_version 88270 (0.0010) -[2023-10-10 16:08:07,791][76542] Updated weights for policy 1, policy_version 88280 (0.0007) -[2023-10-10 16:08:08,674][76543] Updated weights for policy 0, policy_version 88453 (0.0010) -[2023-10-10 16:08:09,047][76543] Updated weights for policy 0, policy_version 88463 (0.0008) -[2023-10-10 16:08:09,416][76543] Updated weights for policy 0, policy_version 88473 (0.0007) -[2023-10-10 16:08:11,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 181010432. Throughput: 0: 1831.5, 1: 1834.8. Samples: 45260340. Policy #0 lag: (min: 24.0, avg: 48.8, max: 56.0) -[2023-10-10 16:08:11,077][75634] Avg episode reward: [(0, '36.110'), (1, '40.110')] -[2023-10-10 16:08:11,477][76542] Updated weights for policy 1, policy_version 88290 (0.0008) -[2023-10-10 16:08:11,840][76542] Updated weights for policy 1, policy_version 88300 (0.0008) -[2023-10-10 16:08:12,208][76542] Updated weights for policy 1, policy_version 88310 (0.0008) -[2023-10-10 16:08:12,574][76542] Updated weights for policy 1, policy_version 88320 (0.0008) -[2023-10-10 16:08:13,082][76543] Updated weights for policy 0, policy_version 88483 (0.0009) -[2023-10-10 16:08:13,445][76543] Updated weights for policy 0, policy_version 88493 (0.0008) -[2023-10-10 16:08:13,815][76543] Updated weights for policy 0, policy_version 88503 (0.0008) -[2023-10-10 16:08:16,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 181075968. Throughput: 0: 1830.0, 1: 1833.8. Samples: 45282508. Policy #0 lag: (min: 24.0, avg: 48.8, max: 56.0) -[2023-10-10 16:08:16,076][75634] Avg episode reward: [(0, '38.180'), (1, '37.710')] -[2023-10-10 16:08:16,196][76542] Updated weights for policy 1, policy_version 88330 (0.0010) -[2023-10-10 16:08:16,556][76542] Updated weights for policy 1, policy_version 88340 (0.0011) -[2023-10-10 16:08:16,921][76542] Updated weights for policy 1, policy_version 88350 (0.0009) -[2023-10-10 16:08:17,526][76543] Updated weights for policy 0, policy_version 88513 (0.0009) -[2023-10-10 16:08:17,896][76543] Updated weights for policy 0, policy_version 88523 (0.0008) -[2023-10-10 16:08:18,258][76543] Updated weights for policy 0, policy_version 88533 (0.0011) -[2023-10-10 16:08:18,629][76543] Updated weights for policy 0, policy_version 88543 (0.0012) -[2023-10-10 16:08:20,520][76542] Updated weights for policy 1, policy_version 88360 (0.0009) -[2023-10-10 16:08:20,888][76542] Updated weights for policy 1, policy_version 88370 (0.0009) -[2023-10-10 16:08:21,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 181141504. Throughput: 0: 1829.0, 1: 1837.4. Samples: 45293244. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:08:21,077][75634] Avg episode reward: [(0, '34.750'), (1, '36.370')] -[2023-10-10 16:08:21,267][76542] Updated weights for policy 1, policy_version 88380 (0.0008) -[2023-10-10 16:08:22,342][76543] Updated weights for policy 0, policy_version 88553 (0.0008) -[2023-10-10 16:08:22,716][76543] Updated weights for policy 0, policy_version 88563 (0.0009) -[2023-10-10 16:08:23,094][76543] Updated weights for policy 0, policy_version 88573 (0.0012) -[2023-10-10 16:08:25,007][76542] Updated weights for policy 1, policy_version 88390 (0.0009) -[2023-10-10 16:08:25,386][76542] Updated weights for policy 1, policy_version 88400 (0.0009) -[2023-10-10 16:08:25,752][76542] Updated weights for policy 1, policy_version 88410 (0.0008) -[2023-10-10 16:08:26,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 181239808. Throughput: 0: 1834.5, 1: 1837.6. Samples: 45315408. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:08:26,077][75634] Avg episode reward: [(0, '37.330'), (1, '35.210')] -[2023-10-10 16:08:26,697][76543] Updated weights for policy 0, policy_version 88583 (0.0009) -[2023-10-10 16:08:27,076][76543] Updated weights for policy 0, policy_version 88593 (0.0009) -[2023-10-10 16:08:27,449][76543] Updated weights for policy 0, policy_version 88603 (0.0007) -[2023-10-10 16:08:29,482][76542] Updated weights for policy 1, policy_version 88420 (0.0008) -[2023-10-10 16:08:29,872][76542] Updated weights for policy 1, policy_version 88430 (0.0008) -[2023-10-10 16:08:30,246][76542] Updated weights for policy 1, policy_version 88440 (0.0010) -[2023-10-10 16:08:31,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 181305344. Throughput: 0: 1835.4, 1: 1831.3. Samples: 45336674. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:08:31,076][75634] Avg episode reward: [(0, '39.600'), (1, '32.280')] -[2023-10-10 16:08:31,085][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000088448_90570752.pth... -[2023-10-10 16:08:31,122][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000086752_88834048.pth -[2023-10-10 16:08:31,152][76543] Updated weights for policy 0, policy_version 88613 (0.0008) -[2023-10-10 16:08:31,523][76543] Updated weights for policy 0, policy_version 88623 (0.0008) -[2023-10-10 16:08:31,897][76543] Updated weights for policy 0, policy_version 88633 (0.0010) -[2023-10-10 16:08:32,156][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000088640_90767360.pth... -[2023-10-10 16:08:32,186][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000086912_88997888.pth -[2023-10-10 16:08:33,880][76542] Updated weights for policy 1, policy_version 88450 (0.0009) -[2023-10-10 16:08:34,260][76542] Updated weights for policy 1, policy_version 88460 (0.0009) -[2023-10-10 16:08:34,633][76542] Updated weights for policy 1, policy_version 88470 (0.0008) -[2023-10-10 16:08:35,002][76542] Updated weights for policy 1, policy_version 88480 (0.0008) -[2023-10-10 16:08:35,626][76543] Updated weights for policy 0, policy_version 88643 (0.0008) -[2023-10-10 16:08:35,993][76543] Updated weights for policy 0, policy_version 88653 (0.0008) -[2023-10-10 16:08:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 181370880. Throughput: 0: 1837.1, 1: 1831.2. Samples: 45348154. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:08:36,077][75634] Avg episode reward: [(0, '38.100'), (1, '31.120')] -[2023-10-10 16:08:36,375][76543] Updated weights for policy 0, policy_version 88663 (0.0008) -[2023-10-10 16:08:38,727][76542] Updated weights for policy 1, policy_version 88490 (0.0008) -[2023-10-10 16:08:39,096][76542] Updated weights for policy 1, policy_version 88500 (0.0009) -[2023-10-10 16:08:39,465][76542] Updated weights for policy 1, policy_version 88510 (0.0008) -[2023-10-10 16:08:39,908][76543] Updated weights for policy 0, policy_version 88673 (0.0008) -[2023-10-10 16:08:40,281][76543] Updated weights for policy 0, policy_version 88683 (0.0007) -[2023-10-10 16:08:40,657][76543] Updated weights for policy 0, policy_version 88693 (0.0008) -[2023-10-10 16:08:41,014][76543] Updated weights for policy 0, policy_version 88703 (0.0010) -[2023-10-10 16:08:41,076][75634] Fps is (10 sec: 16384.1, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 181469184. Throughput: 0: 1830.0, 1: 1829.7. Samples: 45369488. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:08:41,076][75634] Avg episode reward: [(0, '36.100'), (1, '35.130')] -[2023-10-10 16:08:43,262][76542] Updated weights for policy 1, policy_version 88520 (0.0009) -[2023-10-10 16:08:43,626][76542] Updated weights for policy 1, policy_version 88530 (0.0008) -[2023-10-10 16:08:43,996][76542] Updated weights for policy 1, policy_version 88540 (0.0009) -[2023-10-10 16:08:44,514][76543] Updated weights for policy 0, policy_version 88713 (0.0008) -[2023-10-10 16:08:44,888][76543] Updated weights for policy 0, policy_version 88723 (0.0011) -[2023-10-10 16:08:45,253][76543] Updated weights for policy 0, policy_version 88733 (0.0008) -[2023-10-10 16:08:46,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 181534720. Throughput: 0: 1823.7, 1: 1824.2. Samples: 45391400. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:08:46,077][75634] Avg episode reward: [(0, '35.590'), (1, '34.530')] -[2023-10-10 16:08:47,551][76542] Updated weights for policy 1, policy_version 88550 (0.0009) -[2023-10-10 16:08:47,907][76542] Updated weights for policy 1, policy_version 88560 (0.0011) -[2023-10-10 16:08:48,273][76542] Updated weights for policy 1, policy_version 88570 (0.0009) -[2023-10-10 16:08:48,830][76543] Updated weights for policy 0, policy_version 88743 (0.0009) -[2023-10-10 16:08:49,202][76543] Updated weights for policy 0, policy_version 88753 (0.0010) -[2023-10-10 16:08:49,574][76543] Updated weights for policy 0, policy_version 88763 (0.0011) -[2023-10-10 16:08:51,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 181600256. Throughput: 0: 1829.2, 1: 1822.4. Samples: 45402638. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:08:51,077][75634] Avg episode reward: [(0, '35.540'), (1, '37.710')] -[2023-10-10 16:08:51,903][76542] Updated weights for policy 1, policy_version 88580 (0.0007) -[2023-10-10 16:08:52,265][76542] Updated weights for policy 1, policy_version 88590 (0.0008) -[2023-10-10 16:08:52,630][76542] Updated weights for policy 1, policy_version 88600 (0.0008) -[2023-10-10 16:08:53,279][76543] Updated weights for policy 0, policy_version 88773 (0.0009) -[2023-10-10 16:08:53,659][76543] Updated weights for policy 0, policy_version 88783 (0.0008) -[2023-10-10 16:08:54,017][76543] Updated weights for policy 0, policy_version 88793 (0.0007) -[2023-10-10 16:08:56,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 181665792. Throughput: 0: 1817.7, 1: 1822.5. Samples: 45424148. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:08:56,076][75634] Avg episode reward: [(0, '40.020'), (1, '35.010')] -[2023-10-10 16:08:56,357][76542] Updated weights for policy 1, policy_version 88610 (0.0009) -[2023-10-10 16:08:56,719][76542] Updated weights for policy 1, policy_version 88620 (0.0008) -[2023-10-10 16:08:57,085][76542] Updated weights for policy 1, policy_version 88630 (0.0007) -[2023-10-10 16:08:57,447][76542] Updated weights for policy 1, policy_version 88640 (0.0007) -[2023-10-10 16:08:57,728][76543] Updated weights for policy 0, policy_version 88803 (0.0008) -[2023-10-10 16:08:58,137][76543] Updated weights for policy 0, policy_version 88813 (0.0009) -[2023-10-10 16:08:58,519][76543] Updated weights for policy 0, policy_version 88823 (0.0007) -[2023-10-10 16:09:01,038][76542] Updated weights for policy 1, policy_version 88650 (0.0010) -[2023-10-10 16:09:01,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 181731328. Throughput: 0: 1832.9, 1: 1824.9. Samples: 45447108. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:09:01,076][75634] Avg episode reward: [(0, '38.980'), (1, '36.030')] -[2023-10-10 16:09:01,406][76542] Updated weights for policy 1, policy_version 88660 (0.0010) -[2023-10-10 16:09:01,775][76542] Updated weights for policy 1, policy_version 88670 (0.0008) -[2023-10-10 16:09:01,882][76543] Updated weights for policy 0, policy_version 88833 (0.0008) -[2023-10-10 16:09:02,257][76543] Updated weights for policy 0, policy_version 88843 (0.0008) -[2023-10-10 16:09:02,637][76543] Updated weights for policy 0, policy_version 88853 (0.0007) -[2023-10-10 16:09:02,998][76543] Updated weights for policy 0, policy_version 88863 (0.0008) -[2023-10-10 16:09:05,639][76542] Updated weights for policy 1, policy_version 88680 (0.0008) -[2023-10-10 16:09:06,009][76542] Updated weights for policy 1, policy_version 88690 (0.0010) -[2023-10-10 16:09:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 181796864. Throughput: 0: 1822.9, 1: 1822.9. Samples: 45457306. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:09:06,076][75634] Avg episode reward: [(0, '37.670'), (1, '37.260')] -[2023-10-10 16:09:06,375][76542] Updated weights for policy 1, policy_version 88700 (0.0007) -[2023-10-10 16:09:06,752][76543] Updated weights for policy 0, policy_version 88873 (0.0007) -[2023-10-10 16:09:07,120][76543] Updated weights for policy 0, policy_version 88883 (0.0007) -[2023-10-10 16:09:07,501][76543] Updated weights for policy 0, policy_version 88893 (0.0007) -[2023-10-10 16:09:10,231][76542] Updated weights for policy 1, policy_version 88710 (0.0009) -[2023-10-10 16:09:10,607][76542] Updated weights for policy 1, policy_version 88720 (0.0008) -[2023-10-10 16:09:10,975][76542] Updated weights for policy 1, policy_version 88730 (0.0009) -[2023-10-10 16:09:11,074][76543] Updated weights for policy 0, policy_version 88903 (0.0009) -[2023-10-10 16:09:11,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 181862400. Throughput: 0: 1840.0, 1: 1821.7. Samples: 45480188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:09:11,076][75634] Avg episode reward: [(0, '37.390'), (1, '34.710')] -[2023-10-10 16:09:11,455][76543] Updated weights for policy 0, policy_version 88913 (0.0010) -[2023-10-10 16:09:11,841][76543] Updated weights for policy 0, policy_version 88923 (0.0011) -[2023-10-10 16:09:14,612][76542] Updated weights for policy 1, policy_version 88740 (0.0008) -[2023-10-10 16:09:15,005][76542] Updated weights for policy 1, policy_version 88750 (0.0008) -[2023-10-10 16:09:15,371][76542] Updated weights for policy 1, policy_version 88760 (0.0008) -[2023-10-10 16:09:15,542][76543] Updated weights for policy 0, policy_version 88933 (0.0009) -[2023-10-10 16:09:15,905][76543] Updated weights for policy 0, policy_version 88943 (0.0007) -[2023-10-10 16:09:16,076][75634] Fps is (10 sec: 16383.5, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 181960704. Throughput: 0: 1833.7, 1: 1824.8. Samples: 45501306. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:09:16,077][75634] Avg episode reward: [(0, '37.090'), (1, '33.090')] -[2023-10-10 16:09:16,288][76543] Updated weights for policy 0, policy_version 88953 (0.0010) -[2023-10-10 16:09:19,072][76542] Updated weights for policy 1, policy_version 88770 (0.0007) -[2023-10-10 16:09:19,427][76542] Updated weights for policy 1, policy_version 88780 (0.0007) -[2023-10-10 16:09:19,799][76542] Updated weights for policy 1, policy_version 88790 (0.0009) -[2023-10-10 16:09:19,917][76543] Updated weights for policy 0, policy_version 88963 (0.0009) -[2023-10-10 16:09:20,163][76542] Updated weights for policy 1, policy_version 88800 (0.0008) -[2023-10-10 16:09:20,284][76543] Updated weights for policy 0, policy_version 88973 (0.0008) -[2023-10-10 16:09:20,656][76543] Updated weights for policy 0, policy_version 88983 (0.0008) -[2023-10-10 16:09:21,076][75634] Fps is (10 sec: 19660.4, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 182059008. Throughput: 0: 1833.0, 1: 1824.4. Samples: 45512736. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:09:21,077][75634] Avg episode reward: [(0, '35.910'), (1, '36.090')] -[2023-10-10 16:09:23,973][76542] Updated weights for policy 1, policy_version 88810 (0.0007) -[2023-10-10 16:09:24,338][76542] Updated weights for policy 1, policy_version 88820 (0.0007) -[2023-10-10 16:09:24,359][76543] Updated weights for policy 0, policy_version 88993 (0.0008) -[2023-10-10 16:09:24,701][76542] Updated weights for policy 1, policy_version 88830 (0.0009) -[2023-10-10 16:09:24,727][76543] Updated weights for policy 0, policy_version 89003 (0.0008) -[2023-10-10 16:09:25,093][76543] Updated weights for policy 0, policy_version 89013 (0.0008) -[2023-10-10 16:09:25,461][76543] Updated weights for policy 0, policy_version 89023 (0.0011) -[2023-10-10 16:09:26,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 182124544. Throughput: 0: 1834.3, 1: 1824.9. Samples: 45534152. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:09:26,077][75634] Avg episode reward: [(0, '41.210'), (1, '35.920')] -[2023-10-10 16:09:28,274][76542] Updated weights for policy 1, policy_version 88840 (0.0010) -[2023-10-10 16:09:28,630][76542] Updated weights for policy 1, policy_version 88850 (0.0010) -[2023-10-10 16:09:29,002][76542] Updated weights for policy 1, policy_version 88860 (0.0007) -[2023-10-10 16:09:29,181][76543] Updated weights for policy 0, policy_version 89033 (0.0009) -[2023-10-10 16:09:29,553][76543] Updated weights for policy 0, policy_version 89043 (0.0008) -[2023-10-10 16:09:29,938][76543] Updated weights for policy 0, policy_version 89053 (0.0009) -[2023-10-10 16:09:31,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 182190080. Throughput: 0: 1828.0, 1: 1824.4. Samples: 45555756. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:09:31,076][75634] Avg episode reward: [(0, '42.410'), (1, '40.710')] -[2023-10-10 16:09:32,497][76542] Updated weights for policy 1, policy_version 88870 (0.0007) -[2023-10-10 16:09:32,871][76542] Updated weights for policy 1, policy_version 88880 (0.0009) -[2023-10-10 16:09:33,236][76542] Updated weights for policy 1, policy_version 88890 (0.0007) -[2023-10-10 16:09:33,695][76543] Updated weights for policy 0, policy_version 89063 (0.0008) -[2023-10-10 16:09:34,073][76543] Updated weights for policy 0, policy_version 89073 (0.0008) -[2023-10-10 16:09:34,444][76543] Updated weights for policy 0, policy_version 89083 (0.0009) -[2023-10-10 16:09:36,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 182255616. Throughput: 0: 1831.2, 1: 1828.5. Samples: 45567328. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:09:36,076][75634] Avg episode reward: [(0, '39.030'), (1, '40.630')] -[2023-10-10 16:09:36,882][76542] Updated weights for policy 1, policy_version 88900 (0.0007) -[2023-10-10 16:09:37,254][76542] Updated weights for policy 1, policy_version 88910 (0.0008) -[2023-10-10 16:09:37,621][76542] Updated weights for policy 1, policy_version 88920 (0.0008) -[2023-10-10 16:09:38,047][76543] Updated weights for policy 0, policy_version 89093 (0.0008) -[2023-10-10 16:09:38,423][76543] Updated weights for policy 0, policy_version 89103 (0.0010) -[2023-10-10 16:09:38,793][76543] Updated weights for policy 0, policy_version 89113 (0.0009) -[2023-10-10 16:09:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 182321152. Throughput: 0: 1831.2, 1: 1830.1. Samples: 45588906. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:09:41,076][75634] Avg episode reward: [(0, '36.600'), (1, '33.620')] -[2023-10-10 16:09:41,146][76542] Updated weights for policy 1, policy_version 88930 (0.0009) -[2023-10-10 16:09:41,515][76542] Updated weights for policy 1, policy_version 88940 (0.0007) -[2023-10-10 16:09:41,881][76542] Updated weights for policy 1, policy_version 88950 (0.0007) -[2023-10-10 16:09:42,250][76542] Updated weights for policy 1, policy_version 88960 (0.0007) -[2023-10-10 16:09:42,640][76543] Updated weights for policy 0, policy_version 89123 (0.0010) -[2023-10-10 16:09:43,036][76543] Updated weights for policy 0, policy_version 89133 (0.0007) -[2023-10-10 16:09:43,404][76543] Updated weights for policy 0, policy_version 89143 (0.0008) -[2023-10-10 16:09:46,042][76542] Updated weights for policy 1, policy_version 88970 (0.0007) -[2023-10-10 16:09:46,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 182386688. Throughput: 0: 1827.0, 1: 1822.1. Samples: 45611318. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:09:46,077][75634] Avg episode reward: [(0, '39.920'), (1, '35.090')] -[2023-10-10 16:09:46,410][76542] Updated weights for policy 1, policy_version 88980 (0.0007) -[2023-10-10 16:09:46,775][76542] Updated weights for policy 1, policy_version 88990 (0.0008) -[2023-10-10 16:09:46,945][76543] Updated weights for policy 0, policy_version 89153 (0.0010) -[2023-10-10 16:09:47,306][76543] Updated weights for policy 0, policy_version 89163 (0.0010) -[2023-10-10 16:09:47,676][76543] Updated weights for policy 0, policy_version 89173 (0.0008) -[2023-10-10 16:09:48,056][76543] Updated weights for policy 0, policy_version 89183 (0.0010) -[2023-10-10 16:09:50,539][76542] Updated weights for policy 1, policy_version 89000 (0.0007) -[2023-10-10 16:09:50,913][76542] Updated weights for policy 1, policy_version 89010 (0.0009) -[2023-10-10 16:09:51,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 182452224. Throughput: 0: 1822.2, 1: 1821.3. Samples: 45621264. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:09:51,077][75634] Avg episode reward: [(0, '39.490'), (1, '37.710')] -[2023-10-10 16:09:51,264][76542] Updated weights for policy 1, policy_version 89020 (0.0011) -[2023-10-10 16:09:52,017][76543] Updated weights for policy 0, policy_version 89193 (0.0007) -[2023-10-10 16:09:52,390][76543] Updated weights for policy 0, policy_version 89203 (0.0007) -[2023-10-10 16:09:52,766][76543] Updated weights for policy 0, policy_version 89213 (0.0007) -[2023-10-10 16:09:55,055][76542] Updated weights for policy 1, policy_version 89030 (0.0010) -[2023-10-10 16:09:55,425][76542] Updated weights for policy 1, policy_version 89040 (0.0008) -[2023-10-10 16:09:55,796][76542] Updated weights for policy 1, policy_version 89050 (0.0009) -[2023-10-10 16:09:56,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 182550528. Throughput: 0: 1820.9, 1: 1816.7. Samples: 45643878. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:09:56,077][75634] Avg episode reward: [(0, '37.860'), (1, '35.640')] -[2023-10-10 16:09:56,305][76543] Updated weights for policy 0, policy_version 89223 (0.0007) -[2023-10-10 16:09:56,678][76543] Updated weights for policy 0, policy_version 89233 (0.0007) -[2023-10-10 16:09:57,050][76543] Updated weights for policy 0, policy_version 89243 (0.0010) -[2023-10-10 16:09:59,652][76542] Updated weights for policy 1, policy_version 89060 (0.0007) -[2023-10-10 16:10:00,028][76542] Updated weights for policy 1, policy_version 89070 (0.0008) -[2023-10-10 16:10:00,383][76542] Updated weights for policy 1, policy_version 89080 (0.0009) -[2023-10-10 16:10:00,666][76543] Updated weights for policy 0, policy_version 89253 (0.0009) -[2023-10-10 16:10:01,039][76543] Updated weights for policy 0, policy_version 89263 (0.0009) -[2023-10-10 16:10:01,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 182616064. Throughput: 0: 1828.6, 1: 1815.8. Samples: 45665304. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:10:01,077][75634] Avg episode reward: [(0, '35.750'), (1, '34.520')] -[2023-10-10 16:10:01,420][76543] Updated weights for policy 0, policy_version 89273 (0.0009) -[2023-10-10 16:10:04,093][76542] Updated weights for policy 1, policy_version 89090 (0.0009) -[2023-10-10 16:10:04,459][76542] Updated weights for policy 1, policy_version 89100 (0.0007) -[2023-10-10 16:10:04,839][76542] Updated weights for policy 1, policy_version 89110 (0.0008) -[2023-10-10 16:10:05,091][76543] Updated weights for policy 0, policy_version 89283 (0.0011) -[2023-10-10 16:10:05,194][76542] Updated weights for policy 1, policy_version 89120 (0.0008) -[2023-10-10 16:10:05,453][76543] Updated weights for policy 0, policy_version 89293 (0.0010) -[2023-10-10 16:10:05,820][76543] Updated weights for policy 0, policy_version 89303 (0.0009) -[2023-10-10 16:10:06,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 182681600. Throughput: 0: 1828.9, 1: 1812.9. Samples: 45676620. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:10:06,077][75634] Avg episode reward: [(0, '35.260'), (1, '36.660')] -[2023-10-10 16:10:08,975][76542] Updated weights for policy 1, policy_version 89130 (0.0008) -[2023-10-10 16:10:09,350][76542] Updated weights for policy 1, policy_version 89140 (0.0008) -[2023-10-10 16:10:09,514][76543] Updated weights for policy 0, policy_version 89313 (0.0009) -[2023-10-10 16:10:09,720][76542] Updated weights for policy 1, policy_version 89150 (0.0009) -[2023-10-10 16:10:09,882][76543] Updated weights for policy 0, policy_version 89323 (0.0009) -[2023-10-10 16:10:10,250][76543] Updated weights for policy 0, policy_version 89333 (0.0009) -[2023-10-10 16:10:10,618][76543] Updated weights for policy 0, policy_version 89343 (0.0011) -[2023-10-10 16:10:11,076][75634] Fps is (10 sec: 16384.1, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 182779904. Throughput: 0: 1821.7, 1: 1813.9. Samples: 45697754. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:10:11,077][75634] Avg episode reward: [(0, '35.760'), (1, '39.900')] -[2023-10-10 16:10:13,370][76542] Updated weights for policy 1, policy_version 89160 (0.0008) -[2023-10-10 16:10:13,740][76542] Updated weights for policy 1, policy_version 89170 (0.0010) -[2023-10-10 16:10:14,089][76542] Updated weights for policy 1, policy_version 89180 (0.0008) -[2023-10-10 16:10:14,310][76543] Updated weights for policy 0, policy_version 89353 (0.0008) -[2023-10-10 16:10:14,684][76543] Updated weights for policy 0, policy_version 89363 (0.0010) -[2023-10-10 16:10:15,055][76543] Updated weights for policy 0, policy_version 89373 (0.0008) -[2023-10-10 16:10:16,076][75634] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 182845440. Throughput: 0: 1812.9, 1: 1811.0. Samples: 45718832. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 16:10:16,077][75634] Avg episode reward: [(0, '35.020'), (1, '40.730')] -[2023-10-10 16:10:17,714][76542] Updated weights for policy 1, policy_version 89190 (0.0008) -[2023-10-10 16:10:18,082][76542] Updated weights for policy 1, policy_version 89200 (0.0010) -[2023-10-10 16:10:18,445][76542] Updated weights for policy 1, policy_version 89210 (0.0008) -[2023-10-10 16:10:18,620][76543] Updated weights for policy 0, policy_version 89383 (0.0007) -[2023-10-10 16:10:18,990][76543] Updated weights for policy 0, policy_version 89393 (0.0007) -[2023-10-10 16:10:19,364][76543] Updated weights for policy 0, policy_version 89403 (0.0008) -[2023-10-10 16:10:21,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14662.3). Total num frames: 182910976. Throughput: 0: 1815.6, 1: 1809.0. Samples: 45730434. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 16:10:21,076][75634] Avg episode reward: [(0, '35.220'), (1, '32.560')] -[2023-10-10 16:10:22,048][76542] Updated weights for policy 1, policy_version 89220 (0.0008) -[2023-10-10 16:10:22,411][76542] Updated weights for policy 1, policy_version 89230 (0.0007) -[2023-10-10 16:10:22,776][76542] Updated weights for policy 1, policy_version 89240 (0.0008) -[2023-10-10 16:10:23,011][76543] Updated weights for policy 0, policy_version 89413 (0.0009) -[2023-10-10 16:10:23,373][76543] Updated weights for policy 0, policy_version 89423 (0.0008) -[2023-10-10 16:10:23,743][76543] Updated weights for policy 0, policy_version 89433 (0.0007) -[2023-10-10 16:10:26,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 182976512. Throughput: 0: 1815.2, 1: 1807.5. Samples: 45751926. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 16:10:26,077][75634] Avg episode reward: [(0, '35.170'), (1, '36.150')] -[2023-10-10 16:10:26,566][76542] Updated weights for policy 1, policy_version 89250 (0.0008) -[2023-10-10 16:10:26,937][76542] Updated weights for policy 1, policy_version 89260 (0.0009) -[2023-10-10 16:10:27,299][76542] Updated weights for policy 1, policy_version 89270 (0.0011) -[2023-10-10 16:10:27,480][76543] Updated weights for policy 0, policy_version 89443 (0.0009) -[2023-10-10 16:10:27,667][76542] Updated weights for policy 1, policy_version 89280 (0.0008) -[2023-10-10 16:10:27,848][76543] Updated weights for policy 0, policy_version 89453 (0.0007) -[2023-10-10 16:10:28,220][76543] Updated weights for policy 0, policy_version 89463 (0.0010) -[2023-10-10 16:10:31,076][75634] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 183042048. Throughput: 0: 1817.4, 1: 1811.0. Samples: 45774594. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 16:10:31,077][75634] Avg episode reward: [(0, '32.420'), (1, '32.700')] -[2023-10-10 16:10:31,085][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000089472_91619328.pth... -[2023-10-10 16:10:31,118][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000087776_89882624.pth -[2023-10-10 16:10:31,280][76542] Updated weights for policy 1, policy_version 89290 (0.0007) -[2023-10-10 16:10:31,644][76542] Updated weights for policy 1, policy_version 89300 (0.0007) -[2023-10-10 16:10:31,979][76543] Updated weights for policy 0, policy_version 89473 (0.0009) -[2023-10-10 16:10:32,016][76542] Updated weights for policy 1, policy_version 89310 (0.0007) -[2023-10-10 16:10:32,081][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000089312_91455488.pth... -[2023-10-10 16:10:32,114][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000087584_89686016.pth -[2023-10-10 16:10:32,386][76543] Updated weights for policy 0, policy_version 89483 (0.0008) -[2023-10-10 16:10:32,755][76543] Updated weights for policy 0, policy_version 89493 (0.0008) -[2023-10-10 16:10:33,121][76543] Updated weights for policy 0, policy_version 89503 (0.0010) -[2023-10-10 16:10:35,662][76542] Updated weights for policy 1, policy_version 89320 (0.0008) -[2023-10-10 16:10:36,027][76542] Updated weights for policy 1, policy_version 89330 (0.0009) -[2023-10-10 16:10:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 183107584. Throughput: 0: 1815.2, 1: 1814.8. Samples: 45784618. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 16:10:36,077][75634] Avg episode reward: [(0, '33.520'), (1, '32.910')] -[2023-10-10 16:10:36,398][76542] Updated weights for policy 1, policy_version 89340 (0.0008) -[2023-10-10 16:10:37,017][76543] Updated weights for policy 0, policy_version 89513 (0.0009) -[2023-10-10 16:10:37,396][76543] Updated weights for policy 0, policy_version 89523 (0.0009) -[2023-10-10 16:10:37,755][76543] Updated weights for policy 0, policy_version 89533 (0.0007) -[2023-10-10 16:10:40,225][76542] Updated weights for policy 1, policy_version 89350 (0.0009) -[2023-10-10 16:10:40,602][76542] Updated weights for policy 1, policy_version 89360 (0.0008) -[2023-10-10 16:10:40,964][76542] Updated weights for policy 1, policy_version 89370 (0.0009) -[2023-10-10 16:10:41,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 183173120. Throughput: 0: 1818.7, 1: 1814.1. Samples: 45807354. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 16:10:41,077][75634] Avg episode reward: [(0, '33.210'), (1, '32.160')] -[2023-10-10 16:10:41,395][76543] Updated weights for policy 0, policy_version 89543 (0.0009) -[2023-10-10 16:10:41,759][76543] Updated weights for policy 0, policy_version 89553 (0.0009) -[2023-10-10 16:10:42,128][76543] Updated weights for policy 0, policy_version 89563 (0.0008) -[2023-10-10 16:10:44,811][76542] Updated weights for policy 1, policy_version 89380 (0.0007) -[2023-10-10 16:10:45,201][76542] Updated weights for policy 1, policy_version 89390 (0.0007) -[2023-10-10 16:10:45,573][76542] Updated weights for policy 1, policy_version 89400 (0.0009) -[2023-10-10 16:10:45,822][76543] Updated weights for policy 0, policy_version 89573 (0.0008) -[2023-10-10 16:10:46,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 183271424. Throughput: 0: 1812.1, 1: 1820.4. Samples: 45828768. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 16:10:46,077][75634] Avg episode reward: [(0, '38.660'), (1, '34.670')] -[2023-10-10 16:10:46,205][76543] Updated weights for policy 0, policy_version 89583 (0.0010) -[2023-10-10 16:10:46,567][76543] Updated weights for policy 0, policy_version 89593 (0.0008) -[2023-10-10 16:10:49,299][76542] Updated weights for policy 1, policy_version 89410 (0.0008) -[2023-10-10 16:10:49,669][76542] Updated weights for policy 1, policy_version 89420 (0.0007) -[2023-10-10 16:10:50,035][76542] Updated weights for policy 1, policy_version 89430 (0.0007) -[2023-10-10 16:10:50,170][76543] Updated weights for policy 0, policy_version 89603 (0.0008) -[2023-10-10 16:10:50,403][76542] Updated weights for policy 1, policy_version 89440 (0.0007) -[2023-10-10 16:10:50,544][76543] Updated weights for policy 0, policy_version 89613 (0.0009) -[2023-10-10 16:10:50,911][76543] Updated weights for policy 0, policy_version 89623 (0.0008) -[2023-10-10 16:10:51,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 183336960. Throughput: 0: 1811.9, 1: 1814.6. Samples: 45839812. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 16:10:51,077][75634] Avg episode reward: [(0, '36.020'), (1, '35.920')] -[2023-10-10 16:10:54,052][76542] Updated weights for policy 1, policy_version 89450 (0.0007) -[2023-10-10 16:10:54,430][76542] Updated weights for policy 1, policy_version 89460 (0.0010) -[2023-10-10 16:10:54,567][76543] Updated weights for policy 0, policy_version 89633 (0.0007) -[2023-10-10 16:10:54,794][76542] Updated weights for policy 1, policy_version 89470 (0.0010) -[2023-10-10 16:10:54,940][76543] Updated weights for policy 0, policy_version 89643 (0.0009) -[2023-10-10 16:10:55,307][76543] Updated weights for policy 0, policy_version 89653 (0.0007) -[2023-10-10 16:10:55,667][76543] Updated weights for policy 0, policy_version 89663 (0.0011) -[2023-10-10 16:10:56,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 183435264. Throughput: 0: 1821.6, 1: 1822.1. Samples: 45861724. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 16:10:56,077][75634] Avg episode reward: [(0, '36.860'), (1, '38.020')] -[2023-10-10 16:10:58,487][76542] Updated weights for policy 1, policy_version 89480 (0.0008) -[2023-10-10 16:10:58,859][76542] Updated weights for policy 1, policy_version 89490 (0.0009) -[2023-10-10 16:10:59,214][76542] Updated weights for policy 1, policy_version 89500 (0.0010) -[2023-10-10 16:10:59,281][76543] Updated weights for policy 0, policy_version 89673 (0.0009) -[2023-10-10 16:10:59,656][76543] Updated weights for policy 0, policy_version 89683 (0.0008) -[2023-10-10 16:11:00,017][76543] Updated weights for policy 0, policy_version 89693 (0.0011) -[2023-10-10 16:11:01,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 183500800. Throughput: 0: 1827.2, 1: 1817.9. Samples: 45882860. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 16:11:01,077][75634] Avg episode reward: [(0, '40.490'), (1, '38.080')] -[2023-10-10 16:11:02,958][76542] Updated weights for policy 1, policy_version 89510 (0.0009) -[2023-10-10 16:11:03,317][76542] Updated weights for policy 1, policy_version 89520 (0.0009) -[2023-10-10 16:11:03,604][76543] Updated weights for policy 0, policy_version 89703 (0.0008) -[2023-10-10 16:11:03,685][76542] Updated weights for policy 1, policy_version 89530 (0.0009) -[2023-10-10 16:11:03,969][76543] Updated weights for policy 0, policy_version 89713 (0.0008) -[2023-10-10 16:11:04,338][76543] Updated weights for policy 0, policy_version 89723 (0.0008) -[2023-10-10 16:11:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 183566336. Throughput: 0: 1828.7, 1: 1818.8. Samples: 45894572. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 16:11:06,077][75634] Avg episode reward: [(0, '38.600'), (1, '33.300')] -[2023-10-10 16:11:07,362][76542] Updated weights for policy 1, policy_version 89540 (0.0009) -[2023-10-10 16:11:07,724][76542] Updated weights for policy 1, policy_version 89550 (0.0008) -[2023-10-10 16:11:07,943][76543] Updated weights for policy 0, policy_version 89733 (0.0009) -[2023-10-10 16:11:08,086][76542] Updated weights for policy 1, policy_version 89560 (0.0007) -[2023-10-10 16:11:08,305][76543] Updated weights for policy 0, policy_version 89743 (0.0009) -[2023-10-10 16:11:08,682][76543] Updated weights for policy 0, policy_version 89753 (0.0007) -[2023-10-10 16:11:11,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 183631872. Throughput: 0: 1823.7, 1: 1812.1. Samples: 45915536. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 16:11:11,077][75634] Avg episode reward: [(0, '38.500'), (1, '35.730')] -[2023-10-10 16:11:11,477][76542] Updated weights for policy 1, policy_version 89570 (0.0007) -[2023-10-10 16:11:11,850][76542] Updated weights for policy 1, policy_version 89580 (0.0008) -[2023-10-10 16:11:12,220][76542] Updated weights for policy 1, policy_version 89590 (0.0007) -[2023-10-10 16:11:12,386][76543] Updated weights for policy 0, policy_version 89763 (0.0007) -[2023-10-10 16:11:12,588][76542] Updated weights for policy 1, policy_version 89600 (0.0007) -[2023-10-10 16:11:12,757][76543] Updated weights for policy 0, policy_version 89773 (0.0007) -[2023-10-10 16:11:13,128][76543] Updated weights for policy 0, policy_version 89783 (0.0007) -[2023-10-10 16:11:16,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 183697408. Throughput: 0: 1831.7, 1: 1814.6. Samples: 45938678. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:11:16,076][75634] Avg episode reward: [(0, '39.630'), (1, '34.720')] -[2023-10-10 16:11:16,443][76542] Updated weights for policy 1, policy_version 89610 (0.0009) -[2023-10-10 16:11:16,807][76542] Updated weights for policy 1, policy_version 89620 (0.0008) -[2023-10-10 16:11:16,858][76543] Updated weights for policy 0, policy_version 89793 (0.0008) -[2023-10-10 16:11:17,179][76542] Updated weights for policy 1, policy_version 89630 (0.0008) -[2023-10-10 16:11:17,270][76543] Updated weights for policy 0, policy_version 89803 (0.0007) -[2023-10-10 16:11:17,639][76543] Updated weights for policy 0, policy_version 89813 (0.0007) -[2023-10-10 16:11:18,018][76543] Updated weights for policy 0, policy_version 89823 (0.0007) -[2023-10-10 16:11:20,759][76542] Updated weights for policy 1, policy_version 89640 (0.0008) -[2023-10-10 16:11:21,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 183762944. Throughput: 0: 1831.6, 1: 1808.9. Samples: 45948442. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:11:21,077][75634] Avg episode reward: [(0, '36.980'), (1, '34.870')] -[2023-10-10 16:11:21,133][76542] Updated weights for policy 1, policy_version 89650 (0.0008) -[2023-10-10 16:11:21,493][76542] Updated weights for policy 1, policy_version 89660 (0.0009) -[2023-10-10 16:11:21,727][76543] Updated weights for policy 0, policy_version 89833 (0.0008) -[2023-10-10 16:11:22,095][76543] Updated weights for policy 0, policy_version 89843 (0.0008) -[2023-10-10 16:11:22,460][76543] Updated weights for policy 0, policy_version 89853 (0.0008) -[2023-10-10 16:11:25,189][76542] Updated weights for policy 1, policy_version 89670 (0.0010) -[2023-10-10 16:11:25,558][76542] Updated weights for policy 1, policy_version 89680 (0.0008) -[2023-10-10 16:11:25,925][76542] Updated weights for policy 1, policy_version 89690 (0.0008) -[2023-10-10 16:11:26,076][76543] Updated weights for policy 0, policy_version 89863 (0.0007) -[2023-10-10 16:11:26,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 183828480. Throughput: 0: 1826.1, 1: 1818.2. Samples: 45971348. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:11:26,076][75634] Avg episode reward: [(0, '37.630'), (1, '35.090')] -[2023-10-10 16:11:26,445][76543] Updated weights for policy 0, policy_version 89873 (0.0008) -[2023-10-10 16:11:26,825][76543] Updated weights for policy 0, policy_version 89883 (0.0009) -[2023-10-10 16:11:29,662][76542] Updated weights for policy 1, policy_version 89700 (0.0007) -[2023-10-10 16:11:30,051][76542] Updated weights for policy 1, policy_version 89710 (0.0009) -[2023-10-10 16:11:30,427][76542] Updated weights for policy 1, policy_version 89720 (0.0009) -[2023-10-10 16:11:30,458][76543] Updated weights for policy 0, policy_version 89893 (0.0009) -[2023-10-10 16:11:30,815][76543] Updated weights for policy 0, policy_version 89903 (0.0009) -[2023-10-10 16:11:31,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 183926784. Throughput: 0: 1831.9, 1: 1813.1. Samples: 45992792. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:11:31,076][75634] Avg episode reward: [(0, '36.890'), (1, '37.120')] -[2023-10-10 16:11:31,179][76543] Updated weights for policy 0, policy_version 89913 (0.0008) -[2023-10-10 16:11:34,075][76542] Updated weights for policy 1, policy_version 89730 (0.0007) -[2023-10-10 16:11:34,443][76542] Updated weights for policy 1, policy_version 89740 (0.0009) -[2023-10-10 16:11:34,732][76543] Updated weights for policy 0, policy_version 89923 (0.0008) -[2023-10-10 16:11:34,813][76542] Updated weights for policy 1, policy_version 89750 (0.0008) -[2023-10-10 16:11:35,101][76543] Updated weights for policy 0, policy_version 89933 (0.0007) -[2023-10-10 16:11:35,170][76542] Updated weights for policy 1, policy_version 89760 (0.0009) -[2023-10-10 16:11:35,470][76543] Updated weights for policy 0, policy_version 89943 (0.0007) -[2023-10-10 16:11:36,076][75634] Fps is (10 sec: 19660.8, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 184025088. Throughput: 0: 1834.9, 1: 1820.4. Samples: 46004300. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:11:36,076][75634] Avg episode reward: [(0, '36.680'), (1, '40.860')] -[2023-10-10 16:11:38,823][76542] Updated weights for policy 1, policy_version 89770 (0.0007) -[2023-10-10 16:11:39,105][76543] Updated weights for policy 0, policy_version 89953 (0.0009) -[2023-10-10 16:11:39,192][76542] Updated weights for policy 1, policy_version 89780 (0.0008) -[2023-10-10 16:11:39,465][76543] Updated weights for policy 0, policy_version 89963 (0.0008) -[2023-10-10 16:11:39,563][76542] Updated weights for policy 1, policy_version 89790 (0.0009) -[2023-10-10 16:11:39,837][76543] Updated weights for policy 0, policy_version 89973 (0.0009) -[2023-10-10 16:11:40,199][76543] Updated weights for policy 0, policy_version 89983 (0.0009) -[2023-10-10 16:11:41,076][75634] Fps is (10 sec: 16384.0, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 184090624. Throughput: 0: 1833.3, 1: 1812.5. Samples: 46025784. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:11:41,076][75634] Avg episode reward: [(0, '37.900'), (1, '36.450')] -[2023-10-10 16:11:43,268][76542] Updated weights for policy 1, policy_version 89800 (0.0011) -[2023-10-10 16:11:43,629][76542] Updated weights for policy 1, policy_version 89810 (0.0010) -[2023-10-10 16:11:43,890][76543] Updated weights for policy 0, policy_version 89993 (0.0008) -[2023-10-10 16:11:44,001][76542] Updated weights for policy 1, policy_version 89820 (0.0009) -[2023-10-10 16:11:44,257][76543] Updated weights for policy 0, policy_version 90003 (0.0009) -[2023-10-10 16:11:44,628][76543] Updated weights for policy 0, policy_version 90013 (0.0009) -[2023-10-10 16:11:46,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 184156160. Throughput: 0: 1838.6, 1: 1817.9. Samples: 46047402. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:11:46,077][75634] Avg episode reward: [(0, '35.830'), (1, '37.250')] -[2023-10-10 16:11:47,622][76542] Updated weights for policy 1, policy_version 89830 (0.0008) -[2023-10-10 16:11:47,990][76542] Updated weights for policy 1, policy_version 89840 (0.0009) -[2023-10-10 16:11:48,356][76543] Updated weights for policy 0, policy_version 90023 (0.0010) -[2023-10-10 16:11:48,364][76542] Updated weights for policy 1, policy_version 89850 (0.0007) -[2023-10-10 16:11:48,732][76543] Updated weights for policy 0, policy_version 90033 (0.0009) -[2023-10-10 16:11:49,091][76543] Updated weights for policy 0, policy_version 90043 (0.0008) -[2023-10-10 16:11:51,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 184221696. Throughput: 0: 1829.3, 1: 1818.0. Samples: 46058700. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:11:51,077][75634] Avg episode reward: [(0, '37.440'), (1, '39.500')] -[2023-10-10 16:11:52,028][76542] Updated weights for policy 1, policy_version 89860 (0.0008) -[2023-10-10 16:11:52,395][76542] Updated weights for policy 1, policy_version 89870 (0.0011) -[2023-10-10 16:11:52,631][76543] Updated weights for policy 0, policy_version 90053 (0.0008) -[2023-10-10 16:11:52,762][76542] Updated weights for policy 1, policy_version 89880 (0.0008) -[2023-10-10 16:11:52,997][76543] Updated weights for policy 0, policy_version 90063 (0.0011) -[2023-10-10 16:11:53,357][76543] Updated weights for policy 0, policy_version 90073 (0.0009) -[2023-10-10 16:11:56,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 184287232. Throughput: 0: 1841.7, 1: 1829.5. Samples: 46080740. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:11:56,077][75634] Avg episode reward: [(0, '36.770'), (1, '37.380')] -[2023-10-10 16:11:56,356][76542] Updated weights for policy 1, policy_version 89890 (0.0007) -[2023-10-10 16:11:56,728][76542] Updated weights for policy 1, policy_version 89900 (0.0009) -[2023-10-10 16:11:57,102][76542] Updated weights for policy 1, policy_version 89910 (0.0008) -[2023-10-10 16:11:57,126][76543] Updated weights for policy 0, policy_version 90083 (0.0007) -[2023-10-10 16:11:57,463][76542] Updated weights for policy 1, policy_version 89920 (0.0009) -[2023-10-10 16:11:57,488][76543] Updated weights for policy 0, policy_version 90093 (0.0009) -[2023-10-10 16:11:57,866][76543] Updated weights for policy 0, policy_version 90103 (0.0010) -[2023-10-10 16:12:01,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 184352768. Throughput: 0: 1835.9, 1: 1832.1. Samples: 46103738. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:12:01,076][75634] Avg episode reward: [(0, '32.620'), (1, '36.670')] -[2023-10-10 16:12:01,156][76542] Updated weights for policy 1, policy_version 89930 (0.0007) -[2023-10-10 16:12:01,519][76542] Updated weights for policy 1, policy_version 89940 (0.0009) -[2023-10-10 16:12:01,572][76543] Updated weights for policy 0, policy_version 90113 (0.0009) -[2023-10-10 16:12:01,888][76542] Updated weights for policy 1, policy_version 89950 (0.0007) -[2023-10-10 16:12:01,974][76543] Updated weights for policy 0, policy_version 90123 (0.0008) -[2023-10-10 16:12:02,341][76543] Updated weights for policy 0, policy_version 90133 (0.0007) -[2023-10-10 16:12:02,717][76543] Updated weights for policy 0, policy_version 90143 (0.0009) -[2023-10-10 16:12:05,605][76542] Updated weights for policy 1, policy_version 89960 (0.0007) -[2023-10-10 16:12:05,965][76542] Updated weights for policy 1, policy_version 89970 (0.0007) -[2023-10-10 16:12:06,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 184418304. Throughput: 0: 1836.4, 1: 1835.4. Samples: 46113674. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:12:06,076][75634] Avg episode reward: [(0, '37.380'), (1, '38.180')] -[2023-10-10 16:12:06,331][76542] Updated weights for policy 1, policy_version 89980 (0.0008) -[2023-10-10 16:12:06,391][76543] Updated weights for policy 0, policy_version 90153 (0.0009) -[2023-10-10 16:12:06,762][76543] Updated weights for policy 0, policy_version 90163 (0.0009) -[2023-10-10 16:12:07,122][76543] Updated weights for policy 0, policy_version 90173 (0.0007) -[2023-10-10 16:12:10,050][76542] Updated weights for policy 1, policy_version 89990 (0.0007) -[2023-10-10 16:12:10,424][76542] Updated weights for policy 1, policy_version 90000 (0.0009) -[2023-10-10 16:12:10,773][76543] Updated weights for policy 0, policy_version 90183 (0.0008) -[2023-10-10 16:12:10,792][76542] Updated weights for policy 1, policy_version 90010 (0.0008) -[2023-10-10 16:12:11,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 184516608. Throughput: 0: 1835.9, 1: 1830.4. Samples: 46136334. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:12:11,077][75634] Avg episode reward: [(0, '41.300'), (1, '37.050')] -[2023-10-10 16:12:11,131][76543] Updated weights for policy 0, policy_version 90193 (0.0009) -[2023-10-10 16:12:11,502][76543] Updated weights for policy 0, policy_version 90203 (0.0008) -[2023-10-10 16:12:14,643][76542] Updated weights for policy 1, policy_version 90020 (0.0008) -[2023-10-10 16:12:15,029][76542] Updated weights for policy 1, policy_version 90030 (0.0008) -[2023-10-10 16:12:15,072][76543] Updated weights for policy 0, policy_version 90213 (0.0008) -[2023-10-10 16:12:15,397][76542] Updated weights for policy 1, policy_version 90040 (0.0009) -[2023-10-10 16:12:15,433][76543] Updated weights for policy 0, policy_version 90223 (0.0008) -[2023-10-10 16:12:15,809][76543] Updated weights for policy 0, policy_version 90233 (0.0008) -[2023-10-10 16:12:16,076][75634] Fps is (10 sec: 19660.3, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 184614912. Throughput: 0: 1829.1, 1: 1831.8. Samples: 46157536. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) -[2023-10-10 16:12:16,077][75634] Avg episode reward: [(0, '39.720'), (1, '32.790')] -[2023-10-10 16:12:19,073][76542] Updated weights for policy 1, policy_version 90050 (0.0008) -[2023-10-10 16:12:19,419][76543] Updated weights for policy 0, policy_version 90243 (0.0009) -[2023-10-10 16:12:19,450][76542] Updated weights for policy 1, policy_version 90060 (0.0008) -[2023-10-10 16:12:19,785][76543] Updated weights for policy 0, policy_version 90253 (0.0010) -[2023-10-10 16:12:19,809][76542] Updated weights for policy 1, policy_version 90070 (0.0009) -[2023-10-10 16:12:20,165][76543] Updated weights for policy 0, policy_version 90263 (0.0009) -[2023-10-10 16:12:20,176][76542] Updated weights for policy 1, policy_version 90080 (0.0008) -[2023-10-10 16:12:21,076][75634] Fps is (10 sec: 16383.6, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 184680448. Throughput: 0: 1835.4, 1: 1830.2. Samples: 46169252. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) -[2023-10-10 16:12:21,077][75634] Avg episode reward: [(0, '33.580'), (1, '35.230')] -[2023-10-10 16:12:23,781][76543] Updated weights for policy 0, policy_version 90273 (0.0008) -[2023-10-10 16:12:23,938][76542] Updated weights for policy 1, policy_version 90090 (0.0008) -[2023-10-10 16:12:24,142][76543] Updated weights for policy 0, policy_version 90283 (0.0007) -[2023-10-10 16:12:24,307][76542] Updated weights for policy 1, policy_version 90100 (0.0010) -[2023-10-10 16:12:24,521][76543] Updated weights for policy 0, policy_version 90293 (0.0008) -[2023-10-10 16:12:24,674][76542] Updated weights for policy 1, policy_version 90110 (0.0009) -[2023-10-10 16:12:24,884][76543] Updated weights for policy 0, policy_version 90303 (0.0008) -[2023-10-10 16:12:26,076][75634] Fps is (10 sec: 13107.4, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 184745984. Throughput: 0: 1829.0, 1: 1826.6. Samples: 46190286. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) -[2023-10-10 16:12:26,077][75634] Avg episode reward: [(0, '35.410'), (1, '36.420')] -[2023-10-10 16:12:28,216][76542] Updated weights for policy 1, policy_version 90120 (0.0008) -[2023-10-10 16:12:28,529][76543] Updated weights for policy 0, policy_version 90313 (0.0009) -[2023-10-10 16:12:28,582][76542] Updated weights for policy 1, policy_version 90130 (0.0007) -[2023-10-10 16:12:28,904][76543] Updated weights for policy 0, policy_version 90323 (0.0009) -[2023-10-10 16:12:28,947][76542] Updated weights for policy 1, policy_version 90140 (0.0007) -[2023-10-10 16:12:29,271][76543] Updated weights for policy 0, policy_version 90333 (0.0008) -[2023-10-10 16:12:31,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 184811520. Throughput: 0: 1834.9, 1: 1823.4. Samples: 46212026. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) -[2023-10-10 16:12:31,077][75634] Avg episode reward: [(0, '33.910'), (1, '30.430')] -[2023-10-10 16:12:31,090][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000090336_92504064.pth... -[2023-10-10 16:12:31,090][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000090144_92307456.pth... -[2023-10-10 16:12:31,126][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000088448_90570752.pth -[2023-10-10 16:12:31,126][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000088640_90767360.pth -[2023-10-10 16:12:32,845][76542] Updated weights for policy 1, policy_version 90150 (0.0009) -[2023-10-10 16:12:33,013][76543] Updated weights for policy 0, policy_version 90343 (0.0007) -[2023-10-10 16:12:33,208][76542] Updated weights for policy 1, policy_version 90160 (0.0008) -[2023-10-10 16:12:33,391][76543] Updated weights for policy 0, policy_version 90353 (0.0008) -[2023-10-10 16:12:33,576][76542] Updated weights for policy 1, policy_version 90170 (0.0008) -[2023-10-10 16:12:33,759][76543] Updated weights for policy 0, policy_version 90363 (0.0009) -[2023-10-10 16:12:36,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14662.3). Total num frames: 184877056. Throughput: 0: 1827.1, 1: 1823.5. Samples: 46222976. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) -[2023-10-10 16:12:36,077][75634] Avg episode reward: [(0, '35.230'), (1, '29.120')] -[2023-10-10 16:12:37,184][76542] Updated weights for policy 1, policy_version 90180 (0.0008) -[2023-10-10 16:12:37,553][76542] Updated weights for policy 1, policy_version 90190 (0.0008) -[2023-10-10 16:12:37,554][76543] Updated weights for policy 0, policy_version 90373 (0.0007) -[2023-10-10 16:12:37,917][76542] Updated weights for policy 1, policy_version 90200 (0.0008) -[2023-10-10 16:12:37,924][76543] Updated weights for policy 0, policy_version 90383 (0.0007) -[2023-10-10 16:12:38,291][76543] Updated weights for policy 0, policy_version 90393 (0.0008) -[2023-10-10 16:12:41,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 184942592. Throughput: 0: 1825.5, 1: 1816.2. Samples: 46244616. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) -[2023-10-10 16:12:41,077][75634] Avg episode reward: [(0, '35.040'), (1, '33.830')] -[2023-10-10 16:12:41,675][76542] Updated weights for policy 1, policy_version 90210 (0.0009) -[2023-10-10 16:12:41,842][76543] Updated weights for policy 0, policy_version 90403 (0.0009) -[2023-10-10 16:12:42,048][76542] Updated weights for policy 1, policy_version 90220 (0.0008) -[2023-10-10 16:12:42,217][76543] Updated weights for policy 0, policy_version 90413 (0.0009) -[2023-10-10 16:12:42,411][76542] Updated weights for policy 1, policy_version 90230 (0.0007) -[2023-10-10 16:12:42,578][76543] Updated weights for policy 0, policy_version 90423 (0.0007) -[2023-10-10 16:12:42,782][76542] Updated weights for policy 1, policy_version 90240 (0.0007) -[2023-10-10 16:12:46,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 185008128. Throughput: 0: 1827.3, 1: 1809.9. Samples: 46267414. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) -[2023-10-10 16:12:46,077][75634] Avg episode reward: [(0, '37.930'), (1, '37.530')] -[2023-10-10 16:12:46,341][76543] Updated weights for policy 0, policy_version 90433 (0.0007) -[2023-10-10 16:12:46,526][76542] Updated weights for policy 1, policy_version 90250 (0.0009) -[2023-10-10 16:12:46,718][76543] Updated weights for policy 0, policy_version 90443 (0.0008) -[2023-10-10 16:12:46,891][76542] Updated weights for policy 1, policy_version 90260 (0.0010) -[2023-10-10 16:12:47,083][76543] Updated weights for policy 0, policy_version 90453 (0.0008) -[2023-10-10 16:12:47,258][76542] Updated weights for policy 1, policy_version 90270 (0.0008) -[2023-10-10 16:12:47,443][76543] Updated weights for policy 0, policy_version 90463 (0.0008) -[2023-10-10 16:12:51,025][76542] Updated weights for policy 1, policy_version 90280 (0.0008) -[2023-10-10 16:12:51,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 185073664. Throughput: 0: 1825.1, 1: 1805.7. Samples: 46277062. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) -[2023-10-10 16:12:51,076][75634] Avg episode reward: [(0, '42.660'), (1, '40.190')] -[2023-10-10 16:12:51,272][76543] Updated weights for policy 0, policy_version 90473 (0.0009) -[2023-10-10 16:12:51,380][76542] Updated weights for policy 1, policy_version 90290 (0.0007) -[2023-10-10 16:12:51,640][76543] Updated weights for policy 0, policy_version 90483 (0.0008) -[2023-10-10 16:12:51,750][76542] Updated weights for policy 1, policy_version 90300 (0.0007) -[2023-10-10 16:12:52,006][76543] Updated weights for policy 0, policy_version 90493 (0.0009) -[2023-10-10 16:12:55,325][76542] Updated weights for policy 1, policy_version 90310 (0.0008) -[2023-10-10 16:12:55,685][76542] Updated weights for policy 1, policy_version 90320 (0.0008) -[2023-10-10 16:12:55,737][76543] Updated weights for policy 0, policy_version 90503 (0.0008) -[2023-10-10 16:12:56,056][76542] Updated weights for policy 1, policy_version 90330 (0.0008) -[2023-10-10 16:12:56,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 185139200. Throughput: 0: 1823.5, 1: 1808.5. Samples: 46299776. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) -[2023-10-10 16:12:56,077][75634] Avg episode reward: [(0, '38.900'), (1, '39.250')] -[2023-10-10 16:12:56,102][76543] Updated weights for policy 0, policy_version 90513 (0.0009) -[2023-10-10 16:12:56,472][76543] Updated weights for policy 0, policy_version 90523 (0.0008) -[2023-10-10 16:12:59,986][76542] Updated weights for policy 1, policy_version 90340 (0.0007) -[2023-10-10 16:13:00,024][76543] Updated weights for policy 0, policy_version 90533 (0.0008) -[2023-10-10 16:13:00,382][76542] Updated weights for policy 1, policy_version 90350 (0.0008) -[2023-10-10 16:13:00,400][76543] Updated weights for policy 0, policy_version 90543 (0.0007) -[2023-10-10 16:13:00,741][76542] Updated weights for policy 1, policy_version 90360 (0.0007) -[2023-10-10 16:13:00,757][76543] Updated weights for policy 0, policy_version 90553 (0.0009) -[2023-10-10 16:13:01,076][75634] Fps is (10 sec: 19660.8, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 185270272. Throughput: 0: 1821.2, 1: 1810.4. Samples: 46320954. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) -[2023-10-10 16:13:01,076][75634] Avg episode reward: [(0, '36.610'), (1, '39.640')] -[2023-10-10 16:13:04,394][76542] Updated weights for policy 1, policy_version 90370 (0.0007) -[2023-10-10 16:13:04,422][76543] Updated weights for policy 0, policy_version 90563 (0.0008) -[2023-10-10 16:13:04,755][76542] Updated weights for policy 1, policy_version 90380 (0.0009) -[2023-10-10 16:13:04,794][76543] Updated weights for policy 0, policy_version 90573 (0.0008) -[2023-10-10 16:13:05,125][76542] Updated weights for policy 1, policy_version 90390 (0.0007) -[2023-10-10 16:13:05,162][76543] Updated weights for policy 0, policy_version 90583 (0.0007) -[2023-10-10 16:13:05,490][76542] Updated weights for policy 1, policy_version 90400 (0.0009) -[2023-10-10 16:13:06,076][75634] Fps is (10 sec: 19660.8, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 185335808. Throughput: 0: 1823.3, 1: 1806.1. Samples: 46332574. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) -[2023-10-10 16:13:06,077][75634] Avg episode reward: [(0, '40.370'), (1, '36.330')] -[2023-10-10 16:13:08,765][76543] Updated weights for policy 0, policy_version 90593 (0.0007) -[2023-10-10 16:13:09,141][76543] Updated weights for policy 0, policy_version 90603 (0.0009) -[2023-10-10 16:13:09,202][76542] Updated weights for policy 1, policy_version 90410 (0.0007) -[2023-10-10 16:13:09,514][76543] Updated weights for policy 0, policy_version 90613 (0.0010) -[2023-10-10 16:13:09,560][76542] Updated weights for policy 1, policy_version 90420 (0.0009) -[2023-10-10 16:13:09,888][76543] Updated weights for policy 0, policy_version 90623 (0.0008) -[2023-10-10 16:13:09,930][76542] Updated weights for policy 1, policy_version 90430 (0.0010) -[2023-10-10 16:13:11,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 185401344. Throughput: 0: 1811.8, 1: 1816.8. Samples: 46353572. Policy #0 lag: (min: 20.0, avg: 27.6, max: 52.0) -[2023-10-10 16:13:11,076][75634] Avg episode reward: [(0, '37.740'), (1, '35.780')] -[2023-10-10 16:13:13,605][76542] Updated weights for policy 1, policy_version 90440 (0.0008) -[2023-10-10 16:13:13,800][76543] Updated weights for policy 0, policy_version 90633 (0.0009) -[2023-10-10 16:13:13,972][76542] Updated weights for policy 1, policy_version 90450 (0.0008) -[2023-10-10 16:13:14,173][76543] Updated weights for policy 0, policy_version 90643 (0.0008) -[2023-10-10 16:13:14,337][76542] Updated weights for policy 1, policy_version 90460 (0.0009) -[2023-10-10 16:13:14,531][76543] Updated weights for policy 0, policy_version 90653 (0.0008) -[2023-10-10 16:13:16,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14662.3). Total num frames: 185466880. Throughput: 0: 1805.2, 1: 1803.3. Samples: 46374412. Policy #0 lag: (min: 20.0, avg: 27.6, max: 52.0) -[2023-10-10 16:13:16,077][75634] Avg episode reward: [(0, '38.310'), (1, '35.690')] -[2023-10-10 16:13:18,038][76542] Updated weights for policy 1, policy_version 90470 (0.0010) -[2023-10-10 16:13:18,403][76542] Updated weights for policy 1, policy_version 90480 (0.0008) -[2023-10-10 16:13:18,428][76543] Updated weights for policy 0, policy_version 90663 (0.0008) -[2023-10-10 16:13:18,775][76542] Updated weights for policy 1, policy_version 90490 (0.0008) -[2023-10-10 16:13:18,794][76543] Updated weights for policy 0, policy_version 90673 (0.0007) -[2023-10-10 16:13:19,171][76543] Updated weights for policy 0, policy_version 90683 (0.0013) -[2023-10-10 16:13:21,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 185532416. Throughput: 0: 1812.6, 1: 1815.5. Samples: 46386238. Policy #0 lag: (min: 20.0, avg: 27.6, max: 52.0) -[2023-10-10 16:13:21,077][75634] Avg episode reward: [(0, '41.120'), (1, '34.750')] -[2023-10-10 16:13:22,505][76542] Updated weights for policy 1, policy_version 90500 (0.0009) -[2023-10-10 16:13:22,847][76543] Updated weights for policy 0, policy_version 90693 (0.0009) -[2023-10-10 16:13:22,866][76542] Updated weights for policy 1, policy_version 90510 (0.0009) -[2023-10-10 16:13:23,217][76543] Updated weights for policy 0, policy_version 90703 (0.0009) -[2023-10-10 16:13:23,237][76542] Updated weights for policy 1, policy_version 90520 (0.0009) -[2023-10-10 16:13:23,595][76543] Updated weights for policy 0, policy_version 90713 (0.0008) -[2023-10-10 16:13:26,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 185597952. Throughput: 0: 1804.4, 1: 1803.9. Samples: 46406986. Policy #0 lag: (min: 20.0, avg: 27.6, max: 52.0) -[2023-10-10 16:13:26,076][75634] Avg episode reward: [(0, '41.210'), (1, '36.310')] -[2023-10-10 16:13:26,963][76542] Updated weights for policy 1, policy_version 90530 (0.0008) -[2023-10-10 16:13:27,327][76542] Updated weights for policy 1, policy_version 90540 (0.0011) -[2023-10-10 16:13:27,383][76543] Updated weights for policy 0, policy_version 90723 (0.0007) -[2023-10-10 16:13:27,688][76542] Updated weights for policy 1, policy_version 90550 (0.0007) -[2023-10-10 16:13:27,750][76543] Updated weights for policy 0, policy_version 90733 (0.0007) -[2023-10-10 16:13:28,056][76542] Updated weights for policy 1, policy_version 90560 (0.0007) -[2023-10-10 16:13:28,113][76543] Updated weights for policy 0, policy_version 90743 (0.0008) -[2023-10-10 16:13:31,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 185663488. Throughput: 0: 1802.8, 1: 1800.6. Samples: 46429568. Policy #0 lag: (min: 20.0, avg: 27.6, max: 52.0) -[2023-10-10 16:13:31,077][75634] Avg episode reward: [(0, '36.090'), (1, '34.070')] -[2023-10-10 16:13:31,766][76542] Updated weights for policy 1, policy_version 90570 (0.0009) -[2023-10-10 16:13:31,834][76543] Updated weights for policy 0, policy_version 90753 (0.0009) -[2023-10-10 16:13:32,140][76542] Updated weights for policy 1, policy_version 90580 (0.0008) -[2023-10-10 16:13:32,211][76543] Updated weights for policy 0, policy_version 90763 (0.0008) -[2023-10-10 16:13:32,503][76542] Updated weights for policy 1, policy_version 90590 (0.0007) -[2023-10-10 16:13:32,573][76543] Updated weights for policy 0, policy_version 90773 (0.0008) -[2023-10-10 16:13:32,942][76543] Updated weights for policy 0, policy_version 90783 (0.0010) -[2023-10-10 16:13:36,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 185729024. Throughput: 0: 1805.2, 1: 1802.5. Samples: 46439408. Policy #0 lag: (min: 20.0, avg: 27.6, max: 52.0) -[2023-10-10 16:13:36,076][75634] Avg episode reward: [(0, '35.130'), (1, '37.940')] -[2023-10-10 16:13:36,261][76542] Updated weights for policy 1, policy_version 90600 (0.0009) -[2023-10-10 16:13:36,545][76543] Updated weights for policy 0, policy_version 90793 (0.0009) -[2023-10-10 16:13:36,632][76542] Updated weights for policy 1, policy_version 90610 (0.0010) -[2023-10-10 16:13:36,920][76543] Updated weights for policy 0, policy_version 90803 (0.0009) -[2023-10-10 16:13:36,996][76542] Updated weights for policy 1, policy_version 90620 (0.0007) -[2023-10-10 16:13:37,285][76543] Updated weights for policy 0, policy_version 90813 (0.0008) -[2023-10-10 16:13:40,831][76542] Updated weights for policy 1, policy_version 90630 (0.0008) -[2023-10-10 16:13:41,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 185794560. Throughput: 0: 1811.9, 1: 1798.4. Samples: 46462238. Policy #0 lag: (min: 20.0, avg: 27.6, max: 52.0) -[2023-10-10 16:13:41,076][75634] Avg episode reward: [(0, '37.370'), (1, '35.860')] -[2023-10-10 16:13:41,193][76542] Updated weights for policy 1, policy_version 90640 (0.0007) -[2023-10-10 16:13:41,203][76543] Updated weights for policy 0, policy_version 90823 (0.0009) -[2023-10-10 16:13:41,566][76542] Updated weights for policy 1, policy_version 90650 (0.0007) -[2023-10-10 16:13:41,587][76543] Updated weights for policy 0, policy_version 90833 (0.0007) -[2023-10-10 16:13:41,939][76543] Updated weights for policy 0, policy_version 90843 (0.0008) -[2023-10-10 16:13:45,432][76542] Updated weights for policy 1, policy_version 90660 (0.0009) -[2023-10-10 16:13:45,449][76543] Updated weights for policy 0, policy_version 90853 (0.0007) -[2023-10-10 16:13:45,808][76543] Updated weights for policy 0, policy_version 90863 (0.0007) -[2023-10-10 16:13:45,814][76542] Updated weights for policy 1, policy_version 90670 (0.0007) -[2023-10-10 16:13:46,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 185860096. Throughput: 0: 1814.6, 1: 1810.6. Samples: 46484088. Policy #0 lag: (min: 20.0, avg: 27.6, max: 52.0) -[2023-10-10 16:13:46,077][75634] Avg episode reward: [(0, '37.530'), (1, '37.270')] -[2023-10-10 16:13:46,170][76543] Updated weights for policy 0, policy_version 90873 (0.0007) -[2023-10-10 16:13:46,178][76542] Updated weights for policy 1, policy_version 90680 (0.0007) -[2023-10-10 16:13:49,862][76543] Updated weights for policy 0, policy_version 90883 (0.0007) -[2023-10-10 16:13:49,954][76542] Updated weights for policy 1, policy_version 90690 (0.0008) -[2023-10-10 16:13:50,235][76543] Updated weights for policy 0, policy_version 90893 (0.0008) -[2023-10-10 16:13:50,309][76542] Updated weights for policy 1, policy_version 90700 (0.0007) -[2023-10-10 16:13:50,610][76543] Updated weights for policy 0, policy_version 90903 (0.0009) -[2023-10-10 16:13:50,679][76542] Updated weights for policy 1, policy_version 90710 (0.0008) -[2023-10-10 16:13:51,034][76542] Updated weights for policy 1, policy_version 90720 (0.0009) -[2023-10-10 16:13:51,076][75634] Fps is (10 sec: 19660.7, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 185991168. Throughput: 0: 1803.5, 1: 1791.6. Samples: 46494354. Policy #0 lag: (min: 20.0, avg: 27.6, max: 52.0) -[2023-10-10 16:13:51,076][75634] Avg episode reward: [(0, '40.280'), (1, '37.310')] -[2023-10-10 16:13:54,171][76543] Updated weights for policy 0, policy_version 90913 (0.0008) -[2023-10-10 16:13:54,535][76543] Updated weights for policy 0, policy_version 90923 (0.0008) -[2023-10-10 16:13:54,661][76542] Updated weights for policy 1, policy_version 90730 (0.0007) -[2023-10-10 16:13:54,889][76543] Updated weights for policy 0, policy_version 90933 (0.0007) -[2023-10-10 16:13:55,031][76542] Updated weights for policy 1, policy_version 90740 (0.0008) -[2023-10-10 16:13:55,253][76543] Updated weights for policy 0, policy_version 90943 (0.0008) -[2023-10-10 16:13:55,392][76542] Updated weights for policy 1, policy_version 90750 (0.0007) -[2023-10-10 16:13:56,076][75634] Fps is (10 sec: 19661.2, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 186056704. Throughput: 0: 1819.6, 1: 1807.0. Samples: 46516770. Policy #0 lag: (min: 20.0, avg: 27.6, max: 52.0) -[2023-10-10 16:13:56,076][75634] Avg episode reward: [(0, '38.710'), (1, '39.440')] -[2023-10-10 16:13:58,916][76543] Updated weights for policy 0, policy_version 90953 (0.0008) -[2023-10-10 16:13:59,025][76542] Updated weights for policy 1, policy_version 90760 (0.0007) -[2023-10-10 16:13:59,294][76543] Updated weights for policy 0, policy_version 90963 (0.0008) -[2023-10-10 16:13:59,393][76542] Updated weights for policy 1, policy_version 90770 (0.0008) -[2023-10-10 16:13:59,657][76543] Updated weights for policy 0, policy_version 90973 (0.0007) -[2023-10-10 16:13:59,763][76542] Updated weights for policy 1, policy_version 90780 (0.0007) -[2023-10-10 16:14:01,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14662.3). Total num frames: 186122240. Throughput: 0: 1817.5, 1: 1807.7. Samples: 46537544. Policy #0 lag: (min: 20.0, avg: 27.6, max: 52.0) -[2023-10-10 16:14:01,076][75634] Avg episode reward: [(0, '37.060'), (1, '39.080')] -[2023-10-10 16:14:03,185][76543] Updated weights for policy 0, policy_version 90983 (0.0010) -[2023-10-10 16:14:03,471][76542] Updated weights for policy 1, policy_version 90790 (0.0007) -[2023-10-10 16:14:03,550][76543] Updated weights for policy 0, policy_version 90993 (0.0008) -[2023-10-10 16:14:03,839][76542] Updated weights for policy 1, policy_version 90800 (0.0007) -[2023-10-10 16:14:03,928][76543] Updated weights for policy 0, policy_version 91003 (0.0007) -[2023-10-10 16:14:04,202][76542] Updated weights for policy 1, policy_version 90810 (0.0007) -[2023-10-10 16:14:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14662.3). Total num frames: 186187776. Throughput: 0: 1820.4, 1: 1815.8. Samples: 46549868. Policy #0 lag: (min: 20.0, avg: 27.6, max: 52.0) -[2023-10-10 16:14:06,076][75634] Avg episode reward: [(0, '29.640'), (1, '37.080')] -[2023-10-10 16:14:07,612][76543] Updated weights for policy 0, policy_version 91013 (0.0010) -[2023-10-10 16:14:07,884][76542] Updated weights for policy 1, policy_version 90820 (0.0008) -[2023-10-10 16:14:07,976][76543] Updated weights for policy 0, policy_version 91023 (0.0008) -[2023-10-10 16:14:08,251][76542] Updated weights for policy 1, policy_version 90830 (0.0008) -[2023-10-10 16:14:08,345][76543] Updated weights for policy 0, policy_version 91033 (0.0008) -[2023-10-10 16:14:08,631][76542] Updated weights for policy 1, policy_version 90840 (0.0009) -[2023-10-10 16:14:11,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 186253312. Throughput: 0: 1827.7, 1: 1801.6. Samples: 46570306. Policy #0 lag: (min: 19.0, avg: 22.7, max: 51.0) -[2023-10-10 16:14:11,077][75634] Avg episode reward: [(0, '33.750'), (1, '37.610')] -[2023-10-10 16:14:11,959][76543] Updated weights for policy 0, policy_version 91043 (0.0007) -[2023-10-10 16:14:12,320][76542] Updated weights for policy 1, policy_version 90850 (0.0007) -[2023-10-10 16:14:12,334][76543] Updated weights for policy 0, policy_version 91053 (0.0007) -[2023-10-10 16:14:12,686][76542] Updated weights for policy 1, policy_version 90860 (0.0009) -[2023-10-10 16:14:12,696][76543] Updated weights for policy 0, policy_version 91063 (0.0008) -[2023-10-10 16:14:13,050][76542] Updated weights for policy 1, policy_version 90870 (0.0007) -[2023-10-10 16:14:13,419][76542] Updated weights for policy 1, policy_version 90880 (0.0007) -[2023-10-10 16:14:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 186318848. Throughput: 0: 1830.4, 1: 1813.0. Samples: 46593520. Policy #0 lag: (min: 19.0, avg: 22.7, max: 51.0) -[2023-10-10 16:14:16,077][75634] Avg episode reward: [(0, '35.970'), (1, '36.690')] -[2023-10-10 16:14:16,429][76543] Updated weights for policy 0, policy_version 91073 (0.0008) -[2023-10-10 16:14:16,797][76543] Updated weights for policy 0, policy_version 91083 (0.0008) -[2023-10-10 16:14:17,055][76542] Updated weights for policy 1, policy_version 90890 (0.0007) -[2023-10-10 16:14:17,164][76543] Updated weights for policy 0, policy_version 91093 (0.0007) -[2023-10-10 16:14:17,422][76542] Updated weights for policy 1, policy_version 90900 (0.0007) -[2023-10-10 16:14:17,544][76543] Updated weights for policy 0, policy_version 91103 (0.0007) -[2023-10-10 16:14:17,787][76542] Updated weights for policy 1, policy_version 90910 (0.0009) -[2023-10-10 16:14:21,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 186384384. Throughput: 0: 1833.7, 1: 1811.3. Samples: 46603436. Policy #0 lag: (min: 19.0, avg: 22.7, max: 51.0) -[2023-10-10 16:14:21,076][75634] Avg episode reward: [(0, '35.750'), (1, '38.320')] -[2023-10-10 16:14:21,155][76543] Updated weights for policy 0, policy_version 91113 (0.0009) -[2023-10-10 16:14:21,501][76542] Updated weights for policy 1, policy_version 90920 (0.0008) -[2023-10-10 16:14:21,522][76543] Updated weights for policy 0, policy_version 91123 (0.0008) -[2023-10-10 16:14:21,871][76542] Updated weights for policy 1, policy_version 90930 (0.0009) -[2023-10-10 16:14:21,901][76543] Updated weights for policy 0, policy_version 91133 (0.0009) -[2023-10-10 16:14:22,230][76542] Updated weights for policy 1, policy_version 90940 (0.0009) -[2023-10-10 16:14:25,591][76543] Updated weights for policy 0, policy_version 91143 (0.0008) -[2023-10-10 16:14:25,969][76543] Updated weights for policy 0, policy_version 91153 (0.0007) -[2023-10-10 16:14:26,028][76542] Updated weights for policy 1, policy_version 90950 (0.0008) -[2023-10-10 16:14:26,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 186449920. Throughput: 0: 1830.9, 1: 1810.6. Samples: 46626104. Policy #0 lag: (min: 19.0, avg: 22.7, max: 51.0) -[2023-10-10 16:14:26,077][75634] Avg episode reward: [(0, '32.390'), (1, '32.290')] -[2023-10-10 16:14:26,326][76543] Updated weights for policy 0, policy_version 91163 (0.0007) -[2023-10-10 16:14:26,394][76542] Updated weights for policy 1, policy_version 90960 (0.0007) -[2023-10-10 16:14:26,762][76542] Updated weights for policy 1, policy_version 90970 (0.0007) -[2023-10-10 16:14:30,255][76543] Updated weights for policy 0, policy_version 91173 (0.0007) -[2023-10-10 16:14:30,466][76542] Updated weights for policy 1, policy_version 90980 (0.0008) -[2023-10-10 16:14:30,631][76543] Updated weights for policy 0, policy_version 91183 (0.0007) -[2023-10-10 16:14:30,861][76542] Updated weights for policy 1, policy_version 90990 (0.0008) -[2023-10-10 16:14:30,993][76543] Updated weights for policy 0, policy_version 91193 (0.0009) -[2023-10-10 16:14:31,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 186515456. Throughput: 0: 1825.7, 1: 1818.3. Samples: 46648066. Policy #0 lag: (min: 19.0, avg: 22.7, max: 51.0) -[2023-10-10 16:14:31,077][75634] Avg episode reward: [(0, '34.630'), (1, '33.050')] -[2023-10-10 16:14:31,226][76542] Updated weights for policy 1, policy_version 91000 (0.0008) -[2023-10-10 16:14:31,251][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000091200_93388800.pth... -[2023-10-10 16:14:31,279][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000089472_91619328.pth -[2023-10-10 16:14:31,513][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000091008_93192192.pth... -[2023-10-10 16:14:31,550][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000089312_91455488.pth -[2023-10-10 16:14:34,555][76543] Updated weights for policy 0, policy_version 91203 (0.0008) -[2023-10-10 16:14:34,903][76542] Updated weights for policy 1, policy_version 91010 (0.0009) -[2023-10-10 16:14:34,915][76543] Updated weights for policy 0, policy_version 91213 (0.0008) -[2023-10-10 16:14:35,266][76542] Updated weights for policy 1, policy_version 91020 (0.0009) -[2023-10-10 16:14:35,289][76543] Updated weights for policy 0, policy_version 91223 (0.0008) -[2023-10-10 16:14:35,636][76542] Updated weights for policy 1, policy_version 91030 (0.0008) -[2023-10-10 16:14:35,995][76542] Updated weights for policy 1, policy_version 91040 (0.0010) -[2023-10-10 16:14:36,076][75634] Fps is (10 sec: 19660.8, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 186646528. Throughput: 0: 1833.1, 1: 1818.1. Samples: 46658660. Policy #0 lag: (min: 19.0, avg: 22.7, max: 51.0) -[2023-10-10 16:14:36,077][75634] Avg episode reward: [(0, '32.490'), (1, '33.900')] -[2023-10-10 16:14:39,037][76543] Updated weights for policy 0, policy_version 91233 (0.0007) -[2023-10-10 16:14:39,409][76543] Updated weights for policy 0, policy_version 91243 (0.0007) -[2023-10-10 16:14:39,773][76543] Updated weights for policy 0, policy_version 91253 (0.0008) -[2023-10-10 16:14:39,880][76542] Updated weights for policy 1, policy_version 91050 (0.0009) -[2023-10-10 16:14:40,144][76543] Updated weights for policy 0, policy_version 91263 (0.0008) -[2023-10-10 16:14:40,248][76542] Updated weights for policy 1, policy_version 91060 (0.0009) -[2023-10-10 16:14:40,613][76542] Updated weights for policy 1, policy_version 91070 (0.0008) -[2023-10-10 16:14:41,076][75634] Fps is (10 sec: 19661.0, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 186712064. Throughput: 0: 1825.5, 1: 1813.9. Samples: 46680544. Policy #0 lag: (min: 19.0, avg: 22.7, max: 51.0) -[2023-10-10 16:14:41,077][75634] Avg episode reward: [(0, '35.340'), (1, '35.660')] -[2023-10-10 16:14:43,950][76543] Updated weights for policy 0, policy_version 91273 (0.0007) -[2023-10-10 16:14:44,282][76542] Updated weights for policy 1, policy_version 91080 (0.0008) -[2023-10-10 16:14:44,310][76543] Updated weights for policy 0, policy_version 91283 (0.0008) -[2023-10-10 16:14:44,647][76542] Updated weights for policy 1, policy_version 91090 (0.0009) -[2023-10-10 16:14:44,681][76543] Updated weights for policy 0, policy_version 91293 (0.0008) -[2023-10-10 16:14:45,014][76542] Updated weights for policy 1, policy_version 91100 (0.0010) -[2023-10-10 16:14:46,076][75634] Fps is (10 sec: 13107.5, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 186777600. Throughput: 0: 1824.5, 1: 1800.2. Samples: 46700654. Policy #0 lag: (min: 19.0, avg: 22.7, max: 51.0) -[2023-10-10 16:14:46,076][75634] Avg episode reward: [(0, '39.330'), (1, '36.400')] -[2023-10-10 16:14:48,313][76543] Updated weights for policy 0, policy_version 91303 (0.0007) -[2023-10-10 16:14:48,676][76543] Updated weights for policy 0, policy_version 91313 (0.0008) -[2023-10-10 16:14:48,784][76542] Updated weights for policy 1, policy_version 91110 (0.0009) -[2023-10-10 16:14:49,050][76543] Updated weights for policy 0, policy_version 91323 (0.0008) -[2023-10-10 16:14:49,151][76542] Updated weights for policy 1, policy_version 91120 (0.0009) -[2023-10-10 16:14:49,518][76542] Updated weights for policy 1, policy_version 91130 (0.0009) -[2023-10-10 16:14:51,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 186843136. Throughput: 0: 1821.3, 1: 1806.6. Samples: 46713124. Policy #0 lag: (min: 19.0, avg: 22.7, max: 51.0) -[2023-10-10 16:14:51,077][75634] Avg episode reward: [(0, '42.570'), (1, '33.730')] -[2023-10-10 16:14:52,727][76543] Updated weights for policy 0, policy_version 91333 (0.0009) -[2023-10-10 16:14:53,095][76543] Updated weights for policy 0, policy_version 91343 (0.0009) -[2023-10-10 16:14:53,266][76542] Updated weights for policy 1, policy_version 91140 (0.0010) -[2023-10-10 16:14:53,466][76543] Updated weights for policy 0, policy_version 91353 (0.0008) -[2023-10-10 16:14:53,633][76542] Updated weights for policy 1, policy_version 91150 (0.0009) -[2023-10-10 16:14:53,992][76542] Updated weights for policy 1, policy_version 91160 (0.0009) -[2023-10-10 16:14:56,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 186908672. Throughput: 0: 1823.1, 1: 1802.1. Samples: 46733436. Policy #0 lag: (min: 19.0, avg: 22.7, max: 51.0) -[2023-10-10 16:14:56,076][75634] Avg episode reward: [(0, '38.900'), (1, '33.820')] -[2023-10-10 16:14:57,186][76543] Updated weights for policy 0, policy_version 91363 (0.0008) -[2023-10-10 16:14:57,537][76542] Updated weights for policy 1, policy_version 91170 (0.0008) -[2023-10-10 16:14:57,547][76543] Updated weights for policy 0, policy_version 91373 (0.0009) -[2023-10-10 16:14:57,900][76542] Updated weights for policy 1, policy_version 91180 (0.0008) -[2023-10-10 16:14:57,922][76543] Updated weights for policy 0, policy_version 91383 (0.0009) -[2023-10-10 16:14:58,262][76542] Updated weights for policy 1, policy_version 91190 (0.0007) -[2023-10-10 16:14:58,629][76542] Updated weights for policy 1, policy_version 91200 (0.0011) -[2023-10-10 16:15:01,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 186974208. Throughput: 0: 1825.8, 1: 1797.3. Samples: 46756560. Policy #0 lag: (min: 19.0, avg: 22.7, max: 51.0) -[2023-10-10 16:15:01,077][75634] Avg episode reward: [(0, '38.740'), (1, '37.880')] -[2023-10-10 16:15:01,555][76543] Updated weights for policy 0, policy_version 91393 (0.0008) -[2023-10-10 16:15:01,928][76543] Updated weights for policy 0, policy_version 91403 (0.0008) -[2023-10-10 16:15:02,298][76543] Updated weights for policy 0, policy_version 91413 (0.0009) -[2023-10-10 16:15:02,509][76542] Updated weights for policy 1, policy_version 91210 (0.0008) -[2023-10-10 16:15:02,662][76543] Updated weights for policy 0, policy_version 91423 (0.0008) -[2023-10-10 16:15:02,880][76542] Updated weights for policy 1, policy_version 91220 (0.0011) -[2023-10-10 16:15:03,241][76542] Updated weights for policy 1, policy_version 91230 (0.0011) -[2023-10-10 16:15:06,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 187039744. Throughput: 0: 1822.0, 1: 1798.3. Samples: 46766350. Policy #0 lag: (min: 19.0, avg: 22.7, max: 51.0) -[2023-10-10 16:15:06,077][75634] Avg episode reward: [(0, '38.960'), (1, '33.860')] -[2023-10-10 16:15:06,320][76543] Updated weights for policy 0, policy_version 91433 (0.0010) -[2023-10-10 16:15:06,701][76543] Updated weights for policy 0, policy_version 91443 (0.0011) -[2023-10-10 16:15:06,928][76542] Updated weights for policy 1, policy_version 91240 (0.0010) -[2023-10-10 16:15:07,066][76543] Updated weights for policy 0, policy_version 91453 (0.0009) -[2023-10-10 16:15:07,293][76542] Updated weights for policy 1, policy_version 91250 (0.0011) -[2023-10-10 16:15:07,667][76542] Updated weights for policy 1, policy_version 91260 (0.0010) -[2023-10-10 16:15:10,627][76543] Updated weights for policy 0, policy_version 91463 (0.0008) -[2023-10-10 16:15:10,995][76543] Updated weights for policy 0, policy_version 91473 (0.0009) -[2023-10-10 16:15:11,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 187105280. Throughput: 0: 1826.3, 1: 1804.1. Samples: 46789472. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-10 16:15:11,077][75634] Avg episode reward: [(0, '34.820'), (1, '31.920')] -[2023-10-10 16:15:11,343][76542] Updated weights for policy 1, policy_version 91270 (0.0009) -[2023-10-10 16:15:11,360][76543] Updated weights for policy 0, policy_version 91483 (0.0011) -[2023-10-10 16:15:11,713][76542] Updated weights for policy 1, policy_version 91280 (0.0007) -[2023-10-10 16:15:12,068][76542] Updated weights for policy 1, policy_version 91290 (0.0009) -[2023-10-10 16:15:15,096][76543] Updated weights for policy 0, policy_version 91493 (0.0008) -[2023-10-10 16:15:15,474][76543] Updated weights for policy 0, policy_version 91503 (0.0007) -[2023-10-10 16:15:15,849][76543] Updated weights for policy 0, policy_version 91513 (0.0007) -[2023-10-10 16:15:15,872][76542] Updated weights for policy 1, policy_version 91300 (0.0009) -[2023-10-10 16:15:16,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 187170816. Throughput: 0: 1825.4, 1: 1814.9. Samples: 46811876. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-10 16:15:16,076][75634] Avg episode reward: [(0, '37.400'), (1, '35.170')] -[2023-10-10 16:15:16,253][76542] Updated weights for policy 1, policy_version 91310 (0.0007) -[2023-10-10 16:15:16,628][76542] Updated weights for policy 1, policy_version 91320 (0.0007) -[2023-10-10 16:15:19,462][76543] Updated weights for policy 0, policy_version 91523 (0.0007) -[2023-10-10 16:15:19,833][76543] Updated weights for policy 0, policy_version 91533 (0.0008) -[2023-10-10 16:15:20,197][76543] Updated weights for policy 0, policy_version 91543 (0.0008) -[2023-10-10 16:15:20,207][76542] Updated weights for policy 1, policy_version 91330 (0.0008) -[2023-10-10 16:15:20,584][76542] Updated weights for policy 1, policy_version 91340 (0.0007) -[2023-10-10 16:15:20,947][76542] Updated weights for policy 1, policy_version 91350 (0.0008) -[2023-10-10 16:15:21,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 187269120. Throughput: 0: 1833.3, 1: 1805.1. Samples: 46822386. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-10 16:15:21,076][75634] Avg episode reward: [(0, '34.220'), (1, '38.070')] -[2023-10-10 16:15:21,308][76542] Updated weights for policy 1, policy_version 91360 (0.0009) -[2023-10-10 16:15:23,879][76543] Updated weights for policy 0, policy_version 91553 (0.0007) -[2023-10-10 16:15:24,246][76543] Updated weights for policy 0, policy_version 91563 (0.0010) -[2023-10-10 16:15:24,613][76543] Updated weights for policy 0, policy_version 91573 (0.0011) -[2023-10-10 16:15:24,989][76543] Updated weights for policy 0, policy_version 91583 (0.0008) -[2023-10-10 16:15:25,091][76542] Updated weights for policy 1, policy_version 91370 (0.0008) -[2023-10-10 16:15:25,457][76542] Updated weights for policy 1, policy_version 91380 (0.0009) -[2023-10-10 16:15:25,823][76542] Updated weights for policy 1, policy_version 91390 (0.0007) -[2023-10-10 16:15:26,076][75634] Fps is (10 sec: 19660.5, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 187367424. Throughput: 0: 1830.5, 1: 1822.6. Samples: 46844934. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-10 16:15:26,077][75634] Avg episode reward: [(0, '32.050'), (1, '33.410')] -[2023-10-10 16:15:28,764][76543] Updated weights for policy 0, policy_version 91593 (0.0007) -[2023-10-10 16:15:29,128][76543] Updated weights for policy 0, policy_version 91603 (0.0007) -[2023-10-10 16:15:29,391][76542] Updated weights for policy 1, policy_version 91400 (0.0009) -[2023-10-10 16:15:29,494][76543] Updated weights for policy 0, policy_version 91613 (0.0009) -[2023-10-10 16:15:29,758][76542] Updated weights for policy 1, policy_version 91410 (0.0009) -[2023-10-10 16:15:30,127][76542] Updated weights for policy 1, policy_version 91420 (0.0011) -[2023-10-10 16:15:31,076][75634] Fps is (10 sec: 16384.0, 60 sec: 15291.8, 300 sec: 14662.3). Total num frames: 187432960. Throughput: 0: 1839.0, 1: 1815.9. Samples: 46865122. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-10 16:15:31,076][75634] Avg episode reward: [(0, '31.970'), (1, '36.900')] -[2023-10-10 16:15:32,924][76543] Updated weights for policy 0, policy_version 91623 (0.0008) -[2023-10-10 16:15:33,284][76543] Updated weights for policy 0, policy_version 91633 (0.0008) -[2023-10-10 16:15:33,663][76543] Updated weights for policy 0, policy_version 91643 (0.0010) -[2023-10-10 16:15:33,820][76542] Updated weights for policy 1, policy_version 91430 (0.0009) -[2023-10-10 16:15:34,195][76542] Updated weights for policy 1, policy_version 91440 (0.0008) -[2023-10-10 16:15:34,563][76542] Updated weights for policy 1, policy_version 91450 (0.0007) -[2023-10-10 16:15:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14662.3). Total num frames: 187498496. Throughput: 0: 1832.4, 1: 1821.6. Samples: 46877556. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-10 16:15:36,077][75634] Avg episode reward: [(0, '30.910'), (1, '39.850')] -[2023-10-10 16:15:37,374][76543] Updated weights for policy 0, policy_version 91653 (0.0009) -[2023-10-10 16:15:37,743][76543] Updated weights for policy 0, policy_version 91663 (0.0011) -[2023-10-10 16:15:38,120][76543] Updated weights for policy 0, policy_version 91673 (0.0011) -[2023-10-10 16:15:38,411][76542] Updated weights for policy 1, policy_version 91460 (0.0008) -[2023-10-10 16:15:38,797][76542] Updated weights for policy 1, policy_version 91470 (0.0008) -[2023-10-10 16:15:39,166][76542] Updated weights for policy 1, policy_version 91480 (0.0010) -[2023-10-10 16:15:41,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 187564032. Throughput: 0: 1838.7, 1: 1815.5. Samples: 46897878. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-10 16:15:41,077][75634] Avg episode reward: [(0, '30.020'), (1, '37.010')] -[2023-10-10 16:15:41,649][76543] Updated weights for policy 0, policy_version 91683 (0.0008) -[2023-10-10 16:15:42,024][76543] Updated weights for policy 0, policy_version 91693 (0.0009) -[2023-10-10 16:15:42,387][76543] Updated weights for policy 0, policy_version 91703 (0.0008) -[2023-10-10 16:15:42,867][76542] Updated weights for policy 1, policy_version 91490 (0.0007) -[2023-10-10 16:15:43,236][76542] Updated weights for policy 1, policy_version 91500 (0.0008) -[2023-10-10 16:15:43,612][76542] Updated weights for policy 1, policy_version 91510 (0.0010) -[2023-10-10 16:15:43,982][76542] Updated weights for policy 1, policy_version 91520 (0.0008) -[2023-10-10 16:15:46,034][76543] Updated weights for policy 0, policy_version 91713 (0.0008) -[2023-10-10 16:15:46,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 187629568. Throughput: 0: 1836.1, 1: 1815.2. Samples: 46920866. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-10 16:15:46,076][75634] Avg episode reward: [(0, '34.020'), (1, '36.900')] -[2023-10-10 16:15:46,400][76543] Updated weights for policy 0, policy_version 91723 (0.0008) -[2023-10-10 16:15:46,780][76543] Updated weights for policy 0, policy_version 91733 (0.0008) -[2023-10-10 16:15:47,146][76543] Updated weights for policy 0, policy_version 91743 (0.0009) -[2023-10-10 16:15:47,629][76542] Updated weights for policy 1, policy_version 91530 (0.0010) -[2023-10-10 16:15:48,002][76542] Updated weights for policy 1, policy_version 91540 (0.0010) -[2023-10-10 16:15:48,363][76542] Updated weights for policy 1, policy_version 91550 (0.0008) -[2023-10-10 16:15:50,834][76543] Updated weights for policy 0, policy_version 91753 (0.0007) -[2023-10-10 16:15:51,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 187695104. Throughput: 0: 1841.1, 1: 1816.1. Samples: 46930922. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-10 16:15:51,076][75634] Avg episode reward: [(0, '36.460'), (1, '36.250')] -[2023-10-10 16:15:51,202][76543] Updated weights for policy 0, policy_version 91763 (0.0011) -[2023-10-10 16:15:51,570][76543] Updated weights for policy 0, policy_version 91773 (0.0010) -[2023-10-10 16:15:51,929][76542] Updated weights for policy 1, policy_version 91560 (0.0008) -[2023-10-10 16:15:52,302][76542] Updated weights for policy 1, policy_version 91570 (0.0008) -[2023-10-10 16:15:52,668][76542] Updated weights for policy 1, policy_version 91580 (0.0008) -[2023-10-10 16:15:55,351][76543] Updated weights for policy 0, policy_version 91783 (0.0008) -[2023-10-10 16:15:55,716][76543] Updated weights for policy 0, policy_version 91793 (0.0008) -[2023-10-10 16:15:56,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 187760640. Throughput: 0: 1833.4, 1: 1819.6. Samples: 46953860. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-10 16:15:56,076][75634] Avg episode reward: [(0, '33.920'), (1, '40.380')] -[2023-10-10 16:15:56,081][76543] Updated weights for policy 0, policy_version 91803 (0.0008) -[2023-10-10 16:15:56,276][76542] Updated weights for policy 1, policy_version 91590 (0.0008) -[2023-10-10 16:15:56,638][76542] Updated weights for policy 1, policy_version 91600 (0.0007) -[2023-10-10 16:15:57,001][76542] Updated weights for policy 1, policy_version 91610 (0.0008) -[2023-10-10 16:15:59,794][76543] Updated weights for policy 0, policy_version 91813 (0.0008) -[2023-10-10 16:16:00,173][76543] Updated weights for policy 0, policy_version 91823 (0.0008) -[2023-10-10 16:16:00,540][76543] Updated weights for policy 0, policy_version 91833 (0.0007) -[2023-10-10 16:16:00,676][76542] Updated weights for policy 1, policy_version 91620 (0.0008) -[2023-10-10 16:16:01,075][76542] Updated weights for policy 1, policy_version 91630 (0.0008) -[2023-10-10 16:16:01,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 187858944. Throughput: 0: 1823.1, 1: 1819.6. Samples: 46975800. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-10 16:16:01,076][75634] Avg episode reward: [(0, '35.120'), (1, '40.970')] -[2023-10-10 16:16:01,436][76542] Updated weights for policy 1, policy_version 91640 (0.0009) -[2023-10-10 16:16:04,195][76543] Updated weights for policy 0, policy_version 91843 (0.0008) -[2023-10-10 16:16:04,576][76543] Updated weights for policy 0, policy_version 91853 (0.0010) -[2023-10-10 16:16:04,938][76543] Updated weights for policy 0, policy_version 91863 (0.0009) -[2023-10-10 16:16:05,161][76542] Updated weights for policy 1, policy_version 91650 (0.0009) -[2023-10-10 16:16:05,526][76542] Updated weights for policy 1, policy_version 91660 (0.0010) -[2023-10-10 16:16:05,887][76542] Updated weights for policy 1, policy_version 91670 (0.0007) -[2023-10-10 16:16:06,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 187924480. Throughput: 0: 1824.6, 1: 1824.3. Samples: 46986586. Policy #0 lag: (min: 8.0, avg: 32.6, max: 40.0) -[2023-10-10 16:16:06,076][75634] Avg episode reward: [(0, '38.310'), (1, '37.870')] -[2023-10-10 16:16:06,258][76542] Updated weights for policy 1, policy_version 91680 (0.0010) -[2023-10-10 16:16:08,513][76543] Updated weights for policy 0, policy_version 91873 (0.0008) -[2023-10-10 16:16:08,881][76543] Updated weights for policy 0, policy_version 91883 (0.0008) -[2023-10-10 16:16:09,249][76543] Updated weights for policy 0, policy_version 91893 (0.0010) -[2023-10-10 16:16:09,630][76543] Updated weights for policy 0, policy_version 91903 (0.0008) -[2023-10-10 16:16:09,856][76542] Updated weights for policy 1, policy_version 91690 (0.0010) -[2023-10-10 16:16:10,224][76542] Updated weights for policy 1, policy_version 91700 (0.0008) -[2023-10-10 16:16:10,587][76542] Updated weights for policy 1, policy_version 91710 (0.0010) -[2023-10-10 16:16:11,076][75634] Fps is (10 sec: 16383.6, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 188022784. Throughput: 0: 1820.3, 1: 1816.3. Samples: 47008580. Policy #0 lag: (min: 8.0, avg: 32.6, max: 40.0) -[2023-10-10 16:16:11,077][75634] Avg episode reward: [(0, '37.400'), (1, '34.990')] -[2023-10-10 16:16:13,253][76543] Updated weights for policy 0, policy_version 91913 (0.0009) -[2023-10-10 16:16:13,620][76543] Updated weights for policy 0, policy_version 91923 (0.0009) -[2023-10-10 16:16:13,992][76543] Updated weights for policy 0, policy_version 91933 (0.0008) -[2023-10-10 16:16:14,168][76542] Updated weights for policy 1, policy_version 91720 (0.0011) -[2023-10-10 16:16:14,542][76542] Updated weights for policy 1, policy_version 91730 (0.0009) -[2023-10-10 16:16:14,906][76542] Updated weights for policy 1, policy_version 91740 (0.0010) -[2023-10-10 16:16:16,076][75634] Fps is (10 sec: 16383.5, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 188088320. Throughput: 0: 1833.2, 1: 1831.8. Samples: 47030048. Policy #0 lag: (min: 8.0, avg: 32.6, max: 40.0) -[2023-10-10 16:16:16,077][75634] Avg episode reward: [(0, '37.300'), (1, '36.870')] -[2023-10-10 16:16:17,655][76543] Updated weights for policy 0, policy_version 91943 (0.0008) -[2023-10-10 16:16:18,029][76543] Updated weights for policy 0, policy_version 91953 (0.0008) -[2023-10-10 16:16:18,390][76543] Updated weights for policy 0, policy_version 91963 (0.0007) -[2023-10-10 16:16:18,651][76542] Updated weights for policy 1, policy_version 91750 (0.0008) -[2023-10-10 16:16:19,019][76542] Updated weights for policy 1, policy_version 91760 (0.0010) -[2023-10-10 16:16:19,387][76542] Updated weights for policy 1, policy_version 91770 (0.0011) -[2023-10-10 16:16:21,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 188153856. Throughput: 0: 1819.0, 1: 1823.7. Samples: 47041476. Policy #0 lag: (min: 8.0, avg: 32.6, max: 40.0) -[2023-10-10 16:16:21,077][75634] Avg episode reward: [(0, '38.320'), (1, '34.890')] -[2023-10-10 16:16:22,059][76543] Updated weights for policy 0, policy_version 91973 (0.0008) -[2023-10-10 16:16:22,432][76543] Updated weights for policy 0, policy_version 91983 (0.0008) -[2023-10-10 16:16:22,811][76543] Updated weights for policy 0, policy_version 91993 (0.0011) -[2023-10-10 16:16:23,102][76542] Updated weights for policy 1, policy_version 91780 (0.0010) -[2023-10-10 16:16:23,481][76542] Updated weights for policy 1, policy_version 91790 (0.0008) -[2023-10-10 16:16:23,845][76542] Updated weights for policy 1, policy_version 91800 (0.0010) -[2023-10-10 16:16:26,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 188219392. Throughput: 0: 1830.0, 1: 1830.2. Samples: 47062590. Policy #0 lag: (min: 8.0, avg: 32.6, max: 40.0) -[2023-10-10 16:16:26,076][75634] Avg episode reward: [(0, '34.180'), (1, '35.090')] -[2023-10-10 16:16:26,467][76543] Updated weights for policy 0, policy_version 92003 (0.0007) -[2023-10-10 16:16:26,839][76543] Updated weights for policy 0, policy_version 92013 (0.0009) -[2023-10-10 16:16:27,209][76543] Updated weights for policy 0, policy_version 92023 (0.0008) -[2023-10-10 16:16:27,596][76542] Updated weights for policy 1, policy_version 91810 (0.0010) -[2023-10-10 16:16:27,968][76542] Updated weights for policy 1, policy_version 91820 (0.0010) -[2023-10-10 16:16:28,337][76542] Updated weights for policy 1, policy_version 91830 (0.0010) -[2023-10-10 16:16:28,703][76542] Updated weights for policy 1, policy_version 91840 (0.0009) -[2023-10-10 16:16:30,887][76543] Updated weights for policy 0, policy_version 92033 (0.0009) -[2023-10-10 16:16:31,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 188284928. Throughput: 0: 1826.8, 1: 1825.6. Samples: 47085228. Policy #0 lag: (min: 8.0, avg: 32.6, max: 40.0) -[2023-10-10 16:16:31,076][75634] Avg episode reward: [(0, '35.500'), (1, '34.490')] -[2023-10-10 16:16:31,084][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000091840_94044160.pth... -[2023-10-10 16:16:31,118][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000090144_92307456.pth -[2023-10-10 16:16:31,266][76543] Updated weights for policy 0, policy_version 92043 (0.0010) -[2023-10-10 16:16:31,634][76543] Updated weights for policy 0, policy_version 92053 (0.0008) -[2023-10-10 16:16:32,003][76543] Updated weights for policy 0, policy_version 92063 (0.0008) -[2023-10-10 16:16:32,033][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000092064_94273536.pth... -[2023-10-10 16:16:32,071][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000090336_92504064.pth -[2023-10-10 16:16:32,459][76542] Updated weights for policy 1, policy_version 91850 (0.0008) -[2023-10-10 16:16:32,826][76542] Updated weights for policy 1, policy_version 91860 (0.0008) -[2023-10-10 16:16:33,202][76542] Updated weights for policy 1, policy_version 91870 (0.0007) -[2023-10-10 16:16:35,602][76543] Updated weights for policy 0, policy_version 92073 (0.0008) -[2023-10-10 16:16:35,969][76543] Updated weights for policy 0, policy_version 92083 (0.0008) -[2023-10-10 16:16:36,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 188350464. Throughput: 0: 1826.5, 1: 1824.3. Samples: 47095210. Policy #0 lag: (min: 8.0, avg: 32.6, max: 40.0) -[2023-10-10 16:16:36,077][75634] Avg episode reward: [(0, '37.760'), (1, '34.820')] -[2023-10-10 16:16:36,350][76543] Updated weights for policy 0, policy_version 92093 (0.0007) -[2023-10-10 16:16:36,767][76542] Updated weights for policy 1, policy_version 91880 (0.0007) -[2023-10-10 16:16:37,132][76542] Updated weights for policy 1, policy_version 91890 (0.0011) -[2023-10-10 16:16:37,509][76542] Updated weights for policy 1, policy_version 91900 (0.0009) -[2023-10-10 16:16:40,010][76543] Updated weights for policy 0, policy_version 92103 (0.0007) -[2023-10-10 16:16:40,380][76543] Updated weights for policy 0, policy_version 92113 (0.0008) -[2023-10-10 16:16:40,752][76543] Updated weights for policy 0, policy_version 92123 (0.0009) -[2023-10-10 16:16:41,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 188448768. Throughput: 0: 1834.6, 1: 1817.5. Samples: 47118202. Policy #0 lag: (min: 8.0, avg: 32.6, max: 40.0) -[2023-10-10 16:16:41,077][75634] Avg episode reward: [(0, '38.680'), (1, '34.080')] -[2023-10-10 16:16:41,264][76542] Updated weights for policy 1, policy_version 91910 (0.0008) -[2023-10-10 16:16:41,630][76542] Updated weights for policy 1, policy_version 91920 (0.0008) -[2023-10-10 16:16:42,007][76542] Updated weights for policy 1, policy_version 91930 (0.0008) -[2023-10-10 16:16:44,292][76543] Updated weights for policy 0, policy_version 92133 (0.0009) -[2023-10-10 16:16:44,670][76543] Updated weights for policy 0, policy_version 92143 (0.0009) -[2023-10-10 16:16:45,036][76543] Updated weights for policy 0, policy_version 92153 (0.0008) -[2023-10-10 16:16:45,698][76542] Updated weights for policy 1, policy_version 91940 (0.0007) -[2023-10-10 16:16:46,063][76542] Updated weights for policy 1, policy_version 91950 (0.0008) -[2023-10-10 16:16:46,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 188514304. Throughput: 0: 1827.7, 1: 1817.1. Samples: 47139818. Policy #0 lag: (min: 8.0, avg: 32.6, max: 40.0) -[2023-10-10 16:16:46,076][75634] Avg episode reward: [(0, '37.300'), (1, '34.200')] -[2023-10-10 16:16:46,427][76542] Updated weights for policy 1, policy_version 91960 (0.0007) -[2023-10-10 16:16:48,736][76543] Updated weights for policy 0, policy_version 92163 (0.0009) -[2023-10-10 16:16:49,131][76543] Updated weights for policy 0, policy_version 92173 (0.0010) -[2023-10-10 16:16:49,503][76543] Updated weights for policy 0, policy_version 92183 (0.0009) -[2023-10-10 16:16:50,163][76542] Updated weights for policy 1, policy_version 91970 (0.0007) -[2023-10-10 16:16:50,525][76542] Updated weights for policy 1, policy_version 91980 (0.0007) -[2023-10-10 16:16:50,891][76542] Updated weights for policy 1, policy_version 91990 (0.0009) -[2023-10-10 16:16:51,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 188579840. Throughput: 0: 1846.8, 1: 1814.3. Samples: 47151338. Policy #0 lag: (min: 8.0, avg: 32.6, max: 40.0) -[2023-10-10 16:16:51,076][75634] Avg episode reward: [(0, '40.000'), (1, '33.030')] -[2023-10-10 16:16:51,258][76542] Updated weights for policy 1, policy_version 92000 (0.0009) -[2023-10-10 16:16:53,101][76543] Updated weights for policy 0, policy_version 92193 (0.0008) -[2023-10-10 16:16:53,467][76543] Updated weights for policy 0, policy_version 92203 (0.0010) -[2023-10-10 16:16:53,854][76543] Updated weights for policy 0, policy_version 92213 (0.0010) -[2023-10-10 16:16:54,218][76543] Updated weights for policy 0, policy_version 92223 (0.0010) -[2023-10-10 16:16:54,857][76542] Updated weights for policy 1, policy_version 92010 (0.0010) -[2023-10-10 16:16:55,222][76542] Updated weights for policy 1, policy_version 92020 (0.0009) -[2023-10-10 16:16:55,601][76542] Updated weights for policy 1, policy_version 92030 (0.0009) -[2023-10-10 16:16:56,076][75634] Fps is (10 sec: 16383.6, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 188678144. Throughput: 0: 1827.5, 1: 1817.0. Samples: 47172582. Policy #0 lag: (min: 8.0, avg: 32.6, max: 40.0) -[2023-10-10 16:16:56,077][75634] Avg episode reward: [(0, '35.280'), (1, '34.540')] -[2023-10-10 16:16:57,703][76543] Updated weights for policy 0, policy_version 92233 (0.0007) -[2023-10-10 16:16:58,080][76543] Updated weights for policy 0, policy_version 92243 (0.0009) -[2023-10-10 16:16:58,453][76543] Updated weights for policy 0, policy_version 92253 (0.0010) -[2023-10-10 16:16:59,310][76542] Updated weights for policy 1, policy_version 92040 (0.0009) -[2023-10-10 16:16:59,667][76542] Updated weights for policy 1, policy_version 92050 (0.0008) -[2023-10-10 16:17:00,031][76542] Updated weights for policy 1, policy_version 92060 (0.0008) -[2023-10-10 16:17:01,076][75634] Fps is (10 sec: 16383.4, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 188743680. Throughput: 0: 1840.1, 1: 1811.4. Samples: 47194366. Policy #0 lag: (min: 8.0, avg: 32.6, max: 40.0) -[2023-10-10 16:17:01,078][75634] Avg episode reward: [(0, '35.830'), (1, '36.290')] -[2023-10-10 16:17:02,089][76543] Updated weights for policy 0, policy_version 92263 (0.0009) -[2023-10-10 16:17:02,461][76543] Updated weights for policy 0, policy_version 92273 (0.0008) -[2023-10-10 16:17:02,828][76543] Updated weights for policy 0, policy_version 92283 (0.0009) -[2023-10-10 16:17:03,754][76542] Updated weights for policy 1, policy_version 92070 (0.0008) -[2023-10-10 16:17:04,112][76542] Updated weights for policy 1, policy_version 92080 (0.0008) -[2023-10-10 16:17:04,467][76542] Updated weights for policy 1, policy_version 92090 (0.0008) -[2023-10-10 16:17:06,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 188809216. Throughput: 0: 1831.1, 1: 1815.7. Samples: 47205584. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) -[2023-10-10 16:17:06,077][75634] Avg episode reward: [(0, '37.650'), (1, '39.600')] -[2023-10-10 16:17:06,499][76543] Updated weights for policy 0, policy_version 92293 (0.0007) -[2023-10-10 16:17:06,864][76543] Updated weights for policy 0, policy_version 92303 (0.0007) -[2023-10-10 16:17:07,240][76543] Updated weights for policy 0, policy_version 92313 (0.0010) -[2023-10-10 16:17:08,172][76542] Updated weights for policy 1, policy_version 92100 (0.0007) -[2023-10-10 16:17:08,540][76542] Updated weights for policy 1, policy_version 92110 (0.0008) -[2023-10-10 16:17:08,896][76542] Updated weights for policy 1, policy_version 92120 (0.0008) -[2023-10-10 16:17:10,868][76543] Updated weights for policy 0, policy_version 92323 (0.0009) -[2023-10-10 16:17:11,076][75634] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 188874752. Throughput: 0: 1844.1, 1: 1820.1. Samples: 47227482. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) -[2023-10-10 16:17:11,076][75634] Avg episode reward: [(0, '37.190'), (1, '40.080')] -[2023-10-10 16:17:11,242][76543] Updated weights for policy 0, policy_version 92333 (0.0009) -[2023-10-10 16:17:11,621][76543] Updated weights for policy 0, policy_version 92343 (0.0008) -[2023-10-10 16:17:12,482][76542] Updated weights for policy 1, policy_version 92130 (0.0008) -[2023-10-10 16:17:12,850][76542] Updated weights for policy 1, policy_version 92140 (0.0009) -[2023-10-10 16:17:13,216][76542] Updated weights for policy 1, policy_version 92150 (0.0007) -[2023-10-10 16:17:13,581][76542] Updated weights for policy 1, policy_version 92160 (0.0009) -[2023-10-10 16:17:15,223][76543] Updated weights for policy 0, policy_version 92353 (0.0008) -[2023-10-10 16:17:15,585][76543] Updated weights for policy 0, policy_version 92363 (0.0008) -[2023-10-10 16:17:15,964][76543] Updated weights for policy 0, policy_version 92373 (0.0009) -[2023-10-10 16:17:16,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14440.2). Total num frames: 188940288. Throughput: 0: 1847.4, 1: 1826.4. Samples: 47250552. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) -[2023-10-10 16:17:16,076][75634] Avg episode reward: [(0, '34.510'), (1, '35.450')] -[2023-10-10 16:17:16,329][76543] Updated weights for policy 0, policy_version 92383 (0.0010) -[2023-10-10 16:17:17,303][76542] Updated weights for policy 1, policy_version 92170 (0.0008) -[2023-10-10 16:17:17,682][76542] Updated weights for policy 1, policy_version 92180 (0.0010) -[2023-10-10 16:17:18,052][76542] Updated weights for policy 1, policy_version 92190 (0.0008) -[2023-10-10 16:17:20,045][76543] Updated weights for policy 0, policy_version 92393 (0.0009) -[2023-10-10 16:17:20,418][76543] Updated weights for policy 0, policy_version 92403 (0.0008) -[2023-10-10 16:17:20,795][76543] Updated weights for policy 0, policy_version 92413 (0.0009) -[2023-10-10 16:17:21,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 189038592. Throughput: 0: 1847.2, 1: 1827.9. Samples: 47260586. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) -[2023-10-10 16:17:21,077][75634] Avg episode reward: [(0, '35.140'), (1, '34.370')] -[2023-10-10 16:17:21,707][76542] Updated weights for policy 1, policy_version 92200 (0.0009) -[2023-10-10 16:17:22,074][76542] Updated weights for policy 1, policy_version 92210 (0.0011) -[2023-10-10 16:17:22,453][76542] Updated weights for policy 1, policy_version 92220 (0.0009) -[2023-10-10 16:17:24,452][76543] Updated weights for policy 0, policy_version 92423 (0.0011) -[2023-10-10 16:17:24,828][76543] Updated weights for policy 0, policy_version 92433 (0.0011) -[2023-10-10 16:17:25,193][76543] Updated weights for policy 0, policy_version 92443 (0.0008) -[2023-10-10 16:17:26,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 189104128. Throughput: 0: 1842.2, 1: 1826.6. Samples: 47283298. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) -[2023-10-10 16:17:26,076][75634] Avg episode reward: [(0, '38.360'), (1, '36.700')] -[2023-10-10 16:17:26,145][76542] Updated weights for policy 1, policy_version 92230 (0.0007) -[2023-10-10 16:17:26,518][76542] Updated weights for policy 1, policy_version 92240 (0.0011) -[2023-10-10 16:17:26,888][76542] Updated weights for policy 1, policy_version 92250 (0.0011) -[2023-10-10 16:17:28,655][76543] Updated weights for policy 0, policy_version 92453 (0.0009) -[2023-10-10 16:17:29,020][76543] Updated weights for policy 0, policy_version 92463 (0.0008) -[2023-10-10 16:17:29,399][76543] Updated weights for policy 0, policy_version 92473 (0.0008) -[2023-10-10 16:17:30,712][76542] Updated weights for policy 1, policy_version 92260 (0.0008) -[2023-10-10 16:17:31,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 189169664. Throughput: 0: 1840.4, 1: 1822.7. Samples: 47304656. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) -[2023-10-10 16:17:31,076][75634] Avg episode reward: [(0, '37.110'), (1, '38.190')] -[2023-10-10 16:17:31,121][76542] Updated weights for policy 1, policy_version 92270 (0.0008) -[2023-10-10 16:17:31,489][76542] Updated weights for policy 1, policy_version 92280 (0.0007) -[2023-10-10 16:17:33,101][76543] Updated weights for policy 0, policy_version 92483 (0.0008) -[2023-10-10 16:17:33,472][76543] Updated weights for policy 0, policy_version 92493 (0.0008) -[2023-10-10 16:17:33,844][76543] Updated weights for policy 0, policy_version 92503 (0.0007) -[2023-10-10 16:17:35,101][76542] Updated weights for policy 1, policy_version 92290 (0.0008) -[2023-10-10 16:17:35,467][76542] Updated weights for policy 1, policy_version 92300 (0.0008) -[2023-10-10 16:17:35,829][76542] Updated weights for policy 1, policy_version 92310 (0.0008) -[2023-10-10 16:17:36,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 189235200. Throughput: 0: 1827.7, 1: 1827.6. Samples: 47315828. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) -[2023-10-10 16:17:36,077][75634] Avg episode reward: [(0, '40.950'), (1, '36.100')] -[2023-10-10 16:17:36,194][76542] Updated weights for policy 1, policy_version 92320 (0.0007) -[2023-10-10 16:17:37,615][76543] Updated weights for policy 0, policy_version 92513 (0.0007) -[2023-10-10 16:17:37,980][76543] Updated weights for policy 0, policy_version 92523 (0.0008) -[2023-10-10 16:17:38,355][76543] Updated weights for policy 0, policy_version 92533 (0.0007) -[2023-10-10 16:17:38,723][76543] Updated weights for policy 0, policy_version 92543 (0.0008) -[2023-10-10 16:17:39,880][76542] Updated weights for policy 1, policy_version 92330 (0.0010) -[2023-10-10 16:17:40,251][76542] Updated weights for policy 1, policy_version 92340 (0.0007) -[2023-10-10 16:17:40,613][76542] Updated weights for policy 1, policy_version 92350 (0.0009) -[2023-10-10 16:17:41,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 189333504. Throughput: 0: 1832.7, 1: 1825.4. Samples: 47337196. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) -[2023-10-10 16:17:41,076][75634] Avg episode reward: [(0, '38.650'), (1, '35.820')] -[2023-10-10 16:17:42,508][76543] Updated weights for policy 0, policy_version 92553 (0.0008) -[2023-10-10 16:17:42,895][76543] Updated weights for policy 0, policy_version 92563 (0.0011) -[2023-10-10 16:17:43,269][76543] Updated weights for policy 0, policy_version 92573 (0.0010) -[2023-10-10 16:17:44,186][76542] Updated weights for policy 1, policy_version 92360 (0.0009) -[2023-10-10 16:17:44,555][76542] Updated weights for policy 1, policy_version 92370 (0.0009) -[2023-10-10 16:17:44,924][76542] Updated weights for policy 1, policy_version 92380 (0.0011) -[2023-10-10 16:17:46,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 189399040. Throughput: 0: 1826.5, 1: 1827.1. Samples: 47358776. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) -[2023-10-10 16:17:46,077][75634] Avg episode reward: [(0, '38.880'), (1, '35.060')] -[2023-10-10 16:17:47,052][76543] Updated weights for policy 0, policy_version 92583 (0.0010) -[2023-10-10 16:17:47,418][76543] Updated weights for policy 0, policy_version 92593 (0.0012) -[2023-10-10 16:17:47,797][76543] Updated weights for policy 0, policy_version 92603 (0.0010) -[2023-10-10 16:17:48,679][76542] Updated weights for policy 1, policy_version 92390 (0.0008) -[2023-10-10 16:17:49,039][76542] Updated weights for policy 1, policy_version 92400 (0.0007) -[2023-10-10 16:17:49,400][76542] Updated weights for policy 1, policy_version 92410 (0.0007) -[2023-10-10 16:17:51,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 189464576. Throughput: 0: 1823.9, 1: 1823.5. Samples: 47369716. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) -[2023-10-10 16:17:51,077][75634] Avg episode reward: [(0, '40.020'), (1, '38.800')] -[2023-10-10 16:17:51,528][76543] Updated weights for policy 0, policy_version 92613 (0.0009) -[2023-10-10 16:17:51,900][76543] Updated weights for policy 0, policy_version 92623 (0.0008) -[2023-10-10 16:17:52,288][76543] Updated weights for policy 0, policy_version 92633 (0.0008) -[2023-10-10 16:17:53,117][76542] Updated weights for policy 1, policy_version 92420 (0.0008) -[2023-10-10 16:17:53,484][76542] Updated weights for policy 1, policy_version 92430 (0.0009) -[2023-10-10 16:17:53,846][76542] Updated weights for policy 1, policy_version 92440 (0.0008) -[2023-10-10 16:17:55,917][76543] Updated weights for policy 0, policy_version 92643 (0.0007) -[2023-10-10 16:17:56,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 189530112. Throughput: 0: 1819.5, 1: 1820.9. Samples: 47391300. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) -[2023-10-10 16:17:56,076][75634] Avg episode reward: [(0, '41.130'), (1, '34.100')] -[2023-10-10 16:17:56,273][76543] Updated weights for policy 0, policy_version 92653 (0.0009) -[2023-10-10 16:17:56,645][76543] Updated weights for policy 0, policy_version 92663 (0.0009) -[2023-10-10 16:17:57,490][76542] Updated weights for policy 1, policy_version 92450 (0.0008) -[2023-10-10 16:17:57,858][76542] Updated weights for policy 1, policy_version 92460 (0.0011) -[2023-10-10 16:17:58,227][76542] Updated weights for policy 1, policy_version 92470 (0.0009) -[2023-10-10 16:17:58,585][76542] Updated weights for policy 1, policy_version 92480 (0.0007) -[2023-10-10 16:18:00,558][76543] Updated weights for policy 0, policy_version 92673 (0.0007) -[2023-10-10 16:18:00,938][76543] Updated weights for policy 0, policy_version 92683 (0.0008) -[2023-10-10 16:18:01,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 189595648. Throughput: 0: 1810.7, 1: 1818.7. Samples: 47413876. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) -[2023-10-10 16:18:01,077][75634] Avg episode reward: [(0, '39.020'), (1, '35.750')] -[2023-10-10 16:18:01,311][76543] Updated weights for policy 0, policy_version 92693 (0.0008) -[2023-10-10 16:18:01,672][76543] Updated weights for policy 0, policy_version 92703 (0.0007) -[2023-10-10 16:18:02,206][76542] Updated weights for policy 1, policy_version 92490 (0.0008) -[2023-10-10 16:18:02,568][76542] Updated weights for policy 1, policy_version 92500 (0.0009) -[2023-10-10 16:18:02,933][76542] Updated weights for policy 1, policy_version 92510 (0.0010) -[2023-10-10 16:18:05,199][76543] Updated weights for policy 0, policy_version 92713 (0.0008) -[2023-10-10 16:18:05,562][76543] Updated weights for policy 0, policy_version 92723 (0.0007) -[2023-10-10 16:18:05,924][76543] Updated weights for policy 0, policy_version 92733 (0.0007) -[2023-10-10 16:18:06,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 189693952. Throughput: 0: 1811.3, 1: 1818.8. Samples: 47423944. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:18:06,077][75634] Avg episode reward: [(0, '36.490'), (1, '30.530')] -[2023-10-10 16:18:06,749][76542] Updated weights for policy 1, policy_version 92520 (0.0008) -[2023-10-10 16:18:07,112][76542] Updated weights for policy 1, policy_version 92530 (0.0008) -[2023-10-10 16:18:07,485][76542] Updated weights for policy 1, policy_version 92540 (0.0008) -[2023-10-10 16:18:09,700][76543] Updated weights for policy 0, policy_version 92743 (0.0008) -[2023-10-10 16:18:10,066][76543] Updated weights for policy 0, policy_version 92753 (0.0009) -[2023-10-10 16:18:10,435][76543] Updated weights for policy 0, policy_version 92763 (0.0008) -[2023-10-10 16:18:11,060][76542] Updated weights for policy 1, policy_version 92550 (0.0010) -[2023-10-10 16:18:11,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 189759488. Throughput: 0: 1816.8, 1: 1823.4. Samples: 47447108. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:18:11,077][75634] Avg episode reward: [(0, '36.810'), (1, '32.060')] -[2023-10-10 16:18:11,428][76542] Updated weights for policy 1, policy_version 92560 (0.0009) -[2023-10-10 16:18:11,799][76542] Updated weights for policy 1, policy_version 92570 (0.0007) -[2023-10-10 16:18:14,172][76543] Updated weights for policy 0, policy_version 92773 (0.0007) -[2023-10-10 16:18:14,554][76543] Updated weights for policy 0, policy_version 92783 (0.0011) -[2023-10-10 16:18:14,912][76543] Updated weights for policy 0, policy_version 92793 (0.0010) -[2023-10-10 16:18:15,479][76542] Updated weights for policy 1, policy_version 92580 (0.0008) -[2023-10-10 16:18:15,868][76542] Updated weights for policy 1, policy_version 92590 (0.0007) -[2023-10-10 16:18:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 189825024. Throughput: 0: 1813.0, 1: 1825.5. Samples: 47468392. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:18:16,077][75634] Avg episode reward: [(0, '39.080'), (1, '36.170')] -[2023-10-10 16:18:16,241][76542] Updated weights for policy 1, policy_version 92600 (0.0010) -[2023-10-10 16:18:18,471][76543] Updated weights for policy 0, policy_version 92803 (0.0008) -[2023-10-10 16:18:18,839][76543] Updated weights for policy 0, policy_version 92813 (0.0008) -[2023-10-10 16:18:19,212][76543] Updated weights for policy 0, policy_version 92823 (0.0010) -[2023-10-10 16:18:19,940][76542] Updated weights for policy 1, policy_version 92610 (0.0009) -[2023-10-10 16:18:20,306][76542] Updated weights for policy 1, policy_version 92620 (0.0008) -[2023-10-10 16:18:20,674][76542] Updated weights for policy 1, policy_version 92630 (0.0009) -[2023-10-10 16:18:21,045][76542] Updated weights for policy 1, policy_version 92640 (0.0007) -[2023-10-10 16:18:21,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 189923328. Throughput: 0: 1827.3, 1: 1828.7. Samples: 47480348. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:18:21,077][75634] Avg episode reward: [(0, '41.180'), (1, '40.510')] -[2023-10-10 16:18:22,827][76543] Updated weights for policy 0, policy_version 92833 (0.0007) -[2023-10-10 16:18:23,193][76543] Updated weights for policy 0, policy_version 92843 (0.0007) -[2023-10-10 16:18:23,564][76543] Updated weights for policy 0, policy_version 92853 (0.0008) -[2023-10-10 16:18:23,932][76543] Updated weights for policy 0, policy_version 92863 (0.0007) -[2023-10-10 16:18:24,787][76542] Updated weights for policy 1, policy_version 92650 (0.0008) -[2023-10-10 16:18:25,152][76542] Updated weights for policy 1, policy_version 92660 (0.0010) -[2023-10-10 16:18:25,519][76542] Updated weights for policy 1, policy_version 92670 (0.0008) -[2023-10-10 16:18:26,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 189988864. Throughput: 0: 1820.8, 1: 1824.7. Samples: 47501248. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:18:26,077][75634] Avg episode reward: [(0, '39.460'), (1, '35.030')] -[2023-10-10 16:18:27,648][76543] Updated weights for policy 0, policy_version 92873 (0.0008) -[2023-10-10 16:18:28,011][76543] Updated weights for policy 0, policy_version 92883 (0.0008) -[2023-10-10 16:18:28,385][76543] Updated weights for policy 0, policy_version 92893 (0.0010) -[2023-10-10 16:18:29,245][76542] Updated weights for policy 1, policy_version 92680 (0.0008) -[2023-10-10 16:18:29,614][76542] Updated weights for policy 1, policy_version 92690 (0.0010) -[2023-10-10 16:18:29,994][76542] Updated weights for policy 1, policy_version 92700 (0.0009) -[2023-10-10 16:18:31,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 190054400. Throughput: 0: 1827.0, 1: 1822.4. Samples: 47523000. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:18:31,077][75634] Avg episode reward: [(0, '37.890'), (1, '36.610')] -[2023-10-10 16:18:31,085][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000092896_95125504.pth... -[2023-10-10 16:18:31,086][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000092704_94928896.pth... -[2023-10-10 16:18:31,118][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000091200_93388800.pth -[2023-10-10 16:18:31,123][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000091008_93192192.pth -[2023-10-10 16:18:31,961][76543] Updated weights for policy 0, policy_version 92903 (0.0010) -[2023-10-10 16:18:32,332][76543] Updated weights for policy 0, policy_version 92913 (0.0009) -[2023-10-10 16:18:32,688][76543] Updated weights for policy 0, policy_version 92923 (0.0008) -[2023-10-10 16:18:33,816][76542] Updated weights for policy 1, policy_version 92710 (0.0008) -[2023-10-10 16:18:34,181][76542] Updated weights for policy 1, policy_version 92720 (0.0010) -[2023-10-10 16:18:34,548][76542] Updated weights for policy 1, policy_version 92730 (0.0009) -[2023-10-10 16:18:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 190119936. Throughput: 0: 1832.5, 1: 1823.8. Samples: 47534252. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:18:36,077][75634] Avg episode reward: [(0, '40.500'), (1, '38.900')] -[2023-10-10 16:18:36,404][76543] Updated weights for policy 0, policy_version 92933 (0.0008) -[2023-10-10 16:18:36,765][76543] Updated weights for policy 0, policy_version 92943 (0.0008) -[2023-10-10 16:18:37,137][76543] Updated weights for policy 0, policy_version 92953 (0.0007) -[2023-10-10 16:18:38,188][76542] Updated weights for policy 1, policy_version 92740 (0.0008) -[2023-10-10 16:18:38,561][76542] Updated weights for policy 1, policy_version 92750 (0.0010) -[2023-10-10 16:18:38,930][76542] Updated weights for policy 1, policy_version 92760 (0.0010) -[2023-10-10 16:18:40,720][76543] Updated weights for policy 0, policy_version 92963 (0.0008) -[2023-10-10 16:18:41,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14662.3). Total num frames: 190185472. Throughput: 0: 1832.4, 1: 1820.9. Samples: 47555702. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:18:41,077][75634] Avg episode reward: [(0, '37.200'), (1, '38.180')] -[2023-10-10 16:18:41,086][76543] Updated weights for policy 0, policy_version 92973 (0.0008) -[2023-10-10 16:18:41,456][76543] Updated weights for policy 0, policy_version 92983 (0.0008) -[2023-10-10 16:18:42,726][76542] Updated weights for policy 1, policy_version 92770 (0.0010) -[2023-10-10 16:18:43,081][76542] Updated weights for policy 1, policy_version 92780 (0.0008) -[2023-10-10 16:18:43,462][76542] Updated weights for policy 1, policy_version 92790 (0.0009) -[2023-10-10 16:18:43,820][76542] Updated weights for policy 1, policy_version 92800 (0.0008) -[2023-10-10 16:18:45,087][76543] Updated weights for policy 0, policy_version 92993 (0.0008) -[2023-10-10 16:18:45,456][76543] Updated weights for policy 0, policy_version 93003 (0.0008) -[2023-10-10 16:18:45,827][76543] Updated weights for policy 0, policy_version 93013 (0.0008) -[2023-10-10 16:18:46,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 190251008. Throughput: 0: 1835.0, 1: 1819.2. Samples: 47578312. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:18:46,076][75634] Avg episode reward: [(0, '37.490'), (1, '35.860')] -[2023-10-10 16:18:46,202][76543] Updated weights for policy 0, policy_version 93023 (0.0008) -[2023-10-10 16:18:47,504][76542] Updated weights for policy 1, policy_version 92810 (0.0009) -[2023-10-10 16:18:47,871][76542] Updated weights for policy 1, policy_version 92820 (0.0009) -[2023-10-10 16:18:48,250][76542] Updated weights for policy 1, policy_version 92830 (0.0009) -[2023-10-10 16:18:49,919][76543] Updated weights for policy 0, policy_version 93033 (0.0010) -[2023-10-10 16:18:50,292][76543] Updated weights for policy 0, policy_version 93043 (0.0008) -[2023-10-10 16:18:50,664][76543] Updated weights for policy 0, policy_version 93053 (0.0008) -[2023-10-10 16:18:51,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 190349312. Throughput: 0: 1837.2, 1: 1821.2. Samples: 47588574. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:18:51,076][75634] Avg episode reward: [(0, '40.320'), (1, '35.560')] -[2023-10-10 16:18:51,759][76542] Updated weights for policy 1, policy_version 92840 (0.0008) -[2023-10-10 16:18:52,127][76542] Updated weights for policy 1, policy_version 92850 (0.0009) -[2023-10-10 16:18:52,499][76542] Updated weights for policy 1, policy_version 92860 (0.0010) -[2023-10-10 16:18:54,459][76543] Updated weights for policy 0, policy_version 93063 (0.0008) -[2023-10-10 16:18:54,823][76543] Updated weights for policy 0, policy_version 93073 (0.0008) -[2023-10-10 16:18:55,196][76543] Updated weights for policy 0, policy_version 93083 (0.0008) -[2023-10-10 16:18:56,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 190414848. Throughput: 0: 1830.4, 1: 1818.9. Samples: 47611328. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:18:56,077][75634] Avg episode reward: [(0, '39.950'), (1, '37.500')] -[2023-10-10 16:18:56,245][76542] Updated weights for policy 1, policy_version 92870 (0.0008) -[2023-10-10 16:18:56,602][76542] Updated weights for policy 1, policy_version 92880 (0.0010) -[2023-10-10 16:18:56,978][76542] Updated weights for policy 1, policy_version 92890 (0.0010) -[2023-10-10 16:18:58,889][76543] Updated weights for policy 0, policy_version 93093 (0.0007) -[2023-10-10 16:18:59,257][76543] Updated weights for policy 0, policy_version 93103 (0.0007) -[2023-10-10 16:18:59,633][76543] Updated weights for policy 0, policy_version 93113 (0.0008) -[2023-10-10 16:19:00,683][76542] Updated weights for policy 1, policy_version 92900 (0.0007) -[2023-10-10 16:19:01,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 190480384. Throughput: 0: 1831.9, 1: 1821.6. Samples: 47632798. Policy #0 lag: (min: 31.0, avg: 45.9, max: 63.0) -[2023-10-10 16:19:01,076][75634] Avg episode reward: [(0, '41.720'), (1, '39.310')] -[2023-10-10 16:19:01,079][76542] Updated weights for policy 1, policy_version 92910 (0.0010) -[2023-10-10 16:19:01,435][76542] Updated weights for policy 1, policy_version 92920 (0.0010) -[2023-10-10 16:19:03,397][76543] Updated weights for policy 0, policy_version 93123 (0.0009) -[2023-10-10 16:19:03,770][76543] Updated weights for policy 0, policy_version 93133 (0.0007) -[2023-10-10 16:19:04,131][76543] Updated weights for policy 0, policy_version 93143 (0.0008) -[2023-10-10 16:19:04,980][76542] Updated weights for policy 1, policy_version 92930 (0.0010) -[2023-10-10 16:19:05,357][76542] Updated weights for policy 1, policy_version 92940 (0.0008) -[2023-10-10 16:19:05,725][76542] Updated weights for policy 1, policy_version 92950 (0.0008) -[2023-10-10 16:19:06,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 190545920. Throughput: 0: 1830.4, 1: 1819.5. Samples: 47644592. Policy #0 lag: (min: 31.0, avg: 45.9, max: 63.0) -[2023-10-10 16:19:06,076][75634] Avg episode reward: [(0, '38.670'), (1, '41.080')] -[2023-10-10 16:19:06,091][76542] Updated weights for policy 1, policy_version 92960 (0.0008) -[2023-10-10 16:19:07,628][76543] Updated weights for policy 0, policy_version 93153 (0.0009) -[2023-10-10 16:19:08,001][76543] Updated weights for policy 0, policy_version 93163 (0.0007) -[2023-10-10 16:19:08,370][76543] Updated weights for policy 0, policy_version 93173 (0.0007) -[2023-10-10 16:19:08,737][76543] Updated weights for policy 0, policy_version 93183 (0.0007) -[2023-10-10 16:19:09,539][76542] Updated weights for policy 1, policy_version 92970 (0.0008) -[2023-10-10 16:19:09,907][76542] Updated weights for policy 1, policy_version 92980 (0.0009) -[2023-10-10 16:19:10,276][76542] Updated weights for policy 1, policy_version 92990 (0.0010) -[2023-10-10 16:19:11,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 190644224. Throughput: 0: 1832.4, 1: 1821.4. Samples: 47665668. Policy #0 lag: (min: 31.0, avg: 45.9, max: 63.0) -[2023-10-10 16:19:11,077][75634] Avg episode reward: [(0, '35.020'), (1, '40.070')] -[2023-10-10 16:19:12,570][76543] Updated weights for policy 0, policy_version 93193 (0.0008) -[2023-10-10 16:19:12,943][76543] Updated weights for policy 0, policy_version 93203 (0.0008) -[2023-10-10 16:19:13,315][76543] Updated weights for policy 0, policy_version 93213 (0.0010) -[2023-10-10 16:19:14,005][76542] Updated weights for policy 1, policy_version 93000 (0.0010) -[2023-10-10 16:19:14,372][76542] Updated weights for policy 1, policy_version 93010 (0.0010) -[2023-10-10 16:19:14,742][76542] Updated weights for policy 1, policy_version 93020 (0.0008) -[2023-10-10 16:19:16,076][75634] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 190709760. Throughput: 0: 1823.5, 1: 1832.6. Samples: 47687524. Policy #0 lag: (min: 31.0, avg: 45.9, max: 63.0) -[2023-10-10 16:19:16,077][75634] Avg episode reward: [(0, '34.510'), (1, '37.890')] -[2023-10-10 16:19:17,120][76543] Updated weights for policy 0, policy_version 93223 (0.0008) -[2023-10-10 16:19:17,502][76543] Updated weights for policy 0, policy_version 93233 (0.0008) -[2023-10-10 16:19:17,864][76543] Updated weights for policy 0, policy_version 93243 (0.0009) -[2023-10-10 16:19:18,171][76542] Updated weights for policy 1, policy_version 93030 (0.0009) -[2023-10-10 16:19:18,540][76542] Updated weights for policy 1, policy_version 93040 (0.0011) -[2023-10-10 16:19:18,908][76542] Updated weights for policy 1, policy_version 93050 (0.0011) -[2023-10-10 16:19:21,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14662.3). Total num frames: 190775296. Throughput: 0: 1820.1, 1: 1819.8. Samples: 47698048. Policy #0 lag: (min: 31.0, avg: 45.9, max: 63.0) -[2023-10-10 16:19:21,077][75634] Avg episode reward: [(0, '31.580'), (1, '37.120')] -[2023-10-10 16:19:21,532][76543] Updated weights for policy 0, policy_version 93253 (0.0009) -[2023-10-10 16:19:21,906][76543] Updated weights for policy 0, policy_version 93263 (0.0009) -[2023-10-10 16:19:22,285][76543] Updated weights for policy 0, policy_version 93273 (0.0009) -[2023-10-10 16:19:22,624][76542] Updated weights for policy 1, policy_version 93060 (0.0007) -[2023-10-10 16:19:22,991][76542] Updated weights for policy 1, policy_version 93070 (0.0011) -[2023-10-10 16:19:23,368][76542] Updated weights for policy 1, policy_version 93080 (0.0007) -[2023-10-10 16:19:25,900][76543] Updated weights for policy 0, policy_version 93283 (0.0008) -[2023-10-10 16:19:26,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14662.3). Total num frames: 190840832. Throughput: 0: 1818.0, 1: 1840.8. Samples: 47720348. Policy #0 lag: (min: 31.0, avg: 45.9, max: 63.0) -[2023-10-10 16:19:26,076][75634] Avg episode reward: [(0, '32.960'), (1, '36.410')] -[2023-10-10 16:19:26,265][76543] Updated weights for policy 0, policy_version 93293 (0.0008) -[2023-10-10 16:19:26,635][76543] Updated weights for policy 0, policy_version 93303 (0.0010) -[2023-10-10 16:19:26,984][76542] Updated weights for policy 1, policy_version 93090 (0.0008) -[2023-10-10 16:19:27,360][76542] Updated weights for policy 1, policy_version 93100 (0.0012) -[2023-10-10 16:19:27,718][76542] Updated weights for policy 1, policy_version 93110 (0.0010) -[2023-10-10 16:19:28,090][76542] Updated weights for policy 1, policy_version 93120 (0.0010) -[2023-10-10 16:19:30,230][76543] Updated weights for policy 0, policy_version 93313 (0.0008) -[2023-10-10 16:19:30,602][76543] Updated weights for policy 0, policy_version 93323 (0.0010) -[2023-10-10 16:19:30,981][76543] Updated weights for policy 0, policy_version 93333 (0.0007) -[2023-10-10 16:19:31,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 190906368. Throughput: 0: 1821.6, 1: 1844.0. Samples: 47743268. Policy #0 lag: (min: 31.0, avg: 45.9, max: 63.0) -[2023-10-10 16:19:31,076][75634] Avg episode reward: [(0, '30.110'), (1, '34.110')] -[2023-10-10 16:19:31,355][76543] Updated weights for policy 0, policy_version 93343 (0.0007) -[2023-10-10 16:19:31,814][76542] Updated weights for policy 1, policy_version 93130 (0.0008) -[2023-10-10 16:19:32,183][76542] Updated weights for policy 1, policy_version 93140 (0.0008) -[2023-10-10 16:19:32,544][76542] Updated weights for policy 1, policy_version 93150 (0.0007) -[2023-10-10 16:19:35,097][76543] Updated weights for policy 0, policy_version 93353 (0.0007) -[2023-10-10 16:19:35,462][76543] Updated weights for policy 0, policy_version 93363 (0.0008) -[2023-10-10 16:19:35,838][76543] Updated weights for policy 0, policy_version 93373 (0.0010) -[2023-10-10 16:19:36,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 191004672. Throughput: 0: 1819.6, 1: 1841.0. Samples: 47753304. Policy #0 lag: (min: 31.0, avg: 45.9, max: 63.0) -[2023-10-10 16:19:36,076][75634] Avg episode reward: [(0, '27.730'), (1, '33.820')] -[2023-10-10 16:19:36,375][76542] Updated weights for policy 1, policy_version 93160 (0.0008) -[2023-10-10 16:19:36,739][76542] Updated weights for policy 1, policy_version 93170 (0.0010) -[2023-10-10 16:19:37,112][76542] Updated weights for policy 1, policy_version 93180 (0.0011) -[2023-10-10 16:19:39,599][76543] Updated weights for policy 0, policy_version 93383 (0.0008) -[2023-10-10 16:19:39,970][76543] Updated weights for policy 0, policy_version 93393 (0.0008) -[2023-10-10 16:19:40,332][76543] Updated weights for policy 0, policy_version 93403 (0.0010) -[2023-10-10 16:19:40,696][76542] Updated weights for policy 1, policy_version 93190 (0.0009) -[2023-10-10 16:19:41,067][76542] Updated weights for policy 1, policy_version 93200 (0.0011) -[2023-10-10 16:19:41,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 191070208. Throughput: 0: 1823.4, 1: 1842.9. Samples: 47776312. Policy #0 lag: (min: 31.0, avg: 45.9, max: 63.0) -[2023-10-10 16:19:41,076][75634] Avg episode reward: [(0, '30.210'), (1, '33.390')] -[2023-10-10 16:19:41,426][76542] Updated weights for policy 1, policy_version 93210 (0.0007) -[2023-10-10 16:19:43,987][76543] Updated weights for policy 0, policy_version 93413 (0.0009) -[2023-10-10 16:19:44,361][76543] Updated weights for policy 0, policy_version 93423 (0.0012) -[2023-10-10 16:19:44,727][76543] Updated weights for policy 0, policy_version 93433 (0.0011) -[2023-10-10 16:19:45,058][76542] Updated weights for policy 1, policy_version 93220 (0.0009) -[2023-10-10 16:19:45,430][76542] Updated weights for policy 1, policy_version 93230 (0.0008) -[2023-10-10 16:19:45,809][76542] Updated weights for policy 1, policy_version 93240 (0.0007) -[2023-10-10 16:19:46,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 191135744. Throughput: 0: 1816.5, 1: 1825.9. Samples: 47796706. Policy #0 lag: (min: 31.0, avg: 45.9, max: 63.0) -[2023-10-10 16:19:46,077][75634] Avg episode reward: [(0, '30.650'), (1, '34.090')] -[2023-10-10 16:19:48,377][76543] Updated weights for policy 0, policy_version 93443 (0.0009) -[2023-10-10 16:19:48,758][76543] Updated weights for policy 0, policy_version 93453 (0.0008) -[2023-10-10 16:19:49,138][76543] Updated weights for policy 0, policy_version 93463 (0.0008) -[2023-10-10 16:19:49,513][76542] Updated weights for policy 1, policy_version 93250 (0.0007) -[2023-10-10 16:19:49,923][76542] Updated weights for policy 1, policy_version 93260 (0.0011) -[2023-10-10 16:19:50,280][76542] Updated weights for policy 1, policy_version 93270 (0.0010) -[2023-10-10 16:19:50,646][76542] Updated weights for policy 1, policy_version 93280 (0.0010) -[2023-10-10 16:19:51,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 191234048. Throughput: 0: 1816.9, 1: 1839.7. Samples: 47809140. Policy #0 lag: (min: 31.0, avg: 45.9, max: 63.0) -[2023-10-10 16:19:51,076][75634] Avg episode reward: [(0, '35.180'), (1, '32.470')] -[2023-10-10 16:19:52,828][76543] Updated weights for policy 0, policy_version 93473 (0.0010) -[2023-10-10 16:19:53,194][76543] Updated weights for policy 0, policy_version 93483 (0.0009) -[2023-10-10 16:19:53,570][76543] Updated weights for policy 0, policy_version 93493 (0.0008) -[2023-10-10 16:19:53,940][76543] Updated weights for policy 0, policy_version 93503 (0.0009) -[2023-10-10 16:19:54,465][76542] Updated weights for policy 1, policy_version 93290 (0.0008) -[2023-10-10 16:19:54,833][76542] Updated weights for policy 1, policy_version 93300 (0.0007) -[2023-10-10 16:19:55,201][76542] Updated weights for policy 1, policy_version 93310 (0.0008) -[2023-10-10 16:19:56,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 191299584. Throughput: 0: 1813.9, 1: 1825.2. Samples: 47829426. Policy #0 lag: (min: 31.0, avg: 45.9, max: 63.0) -[2023-10-10 16:19:56,077][75634] Avg episode reward: [(0, '34.880'), (1, '30.280')] -[2023-10-10 16:19:57,679][76543] Updated weights for policy 0, policy_version 93513 (0.0011) -[2023-10-10 16:19:58,046][76543] Updated weights for policy 0, policy_version 93523 (0.0009) -[2023-10-10 16:19:58,420][76543] Updated weights for policy 0, policy_version 93533 (0.0008) -[2023-10-10 16:19:58,818][76542] Updated weights for policy 1, policy_version 93320 (0.0010) -[2023-10-10 16:19:59,187][76542] Updated weights for policy 1, policy_version 93330 (0.0008) -[2023-10-10 16:19:59,545][76542] Updated weights for policy 1, policy_version 93340 (0.0007) -[2023-10-10 16:20:01,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 191365120. Throughput: 0: 1815.1, 1: 1831.5. Samples: 47851620. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 16:20:01,077][75634] Avg episode reward: [(0, '33.230'), (1, '35.190')] -[2023-10-10 16:20:02,183][76543] Updated weights for policy 0, policy_version 93543 (0.0007) -[2023-10-10 16:20:02,561][76543] Updated weights for policy 0, policy_version 93553 (0.0007) -[2023-10-10 16:20:02,936][76543] Updated weights for policy 0, policy_version 93563 (0.0009) -[2023-10-10 16:20:03,206][76542] Updated weights for policy 1, policy_version 93350 (0.0008) -[2023-10-10 16:20:03,570][76542] Updated weights for policy 1, policy_version 93360 (0.0009) -[2023-10-10 16:20:03,936][76542] Updated weights for policy 1, policy_version 93370 (0.0008) -[2023-10-10 16:20:06,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 191430656. Throughput: 0: 1816.1, 1: 1831.3. Samples: 47862180. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 16:20:06,076][75634] Avg episode reward: [(0, '37.170'), (1, '39.390')] -[2023-10-10 16:20:06,613][76543] Updated weights for policy 0, policy_version 93573 (0.0008) -[2023-10-10 16:20:06,977][76543] Updated weights for policy 0, policy_version 93583 (0.0007) -[2023-10-10 16:20:07,355][76543] Updated weights for policy 0, policy_version 93593 (0.0010) -[2023-10-10 16:20:07,488][76542] Updated weights for policy 1, policy_version 93380 (0.0008) -[2023-10-10 16:20:07,849][76542] Updated weights for policy 1, policy_version 93390 (0.0008) -[2023-10-10 16:20:08,215][76542] Updated weights for policy 1, policy_version 93400 (0.0009) -[2023-10-10 16:20:10,820][76543] Updated weights for policy 0, policy_version 93603 (0.0008) -[2023-10-10 16:20:11,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14662.3). Total num frames: 191496192. Throughput: 0: 1822.4, 1: 1829.7. Samples: 47884694. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 16:20:11,076][75634] Avg episode reward: [(0, '38.140'), (1, '41.340')] -[2023-10-10 16:20:11,197][76543] Updated weights for policy 0, policy_version 93613 (0.0011) -[2023-10-10 16:20:11,563][76543] Updated weights for policy 0, policy_version 93623 (0.0010) -[2023-10-10 16:20:11,953][76542] Updated weights for policy 1, policy_version 93410 (0.0010) -[2023-10-10 16:20:12,314][76542] Updated weights for policy 1, policy_version 93420 (0.0009) -[2023-10-10 16:20:12,682][76542] Updated weights for policy 1, policy_version 93430 (0.0010) -[2023-10-10 16:20:13,047][76542] Updated weights for policy 1, policy_version 93440 (0.0010) -[2023-10-10 16:20:15,418][76543] Updated weights for policy 0, policy_version 93633 (0.0007) -[2023-10-10 16:20:15,784][76543] Updated weights for policy 0, policy_version 93643 (0.0007) -[2023-10-10 16:20:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 191561728. Throughput: 0: 1820.7, 1: 1829.2. Samples: 47907514. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 16:20:16,076][75634] Avg episode reward: [(0, '38.410'), (1, '39.300')] -[2023-10-10 16:20:16,153][76543] Updated weights for policy 0, policy_version 93653 (0.0008) -[2023-10-10 16:20:16,523][76543] Updated weights for policy 0, policy_version 93663 (0.0008) -[2023-10-10 16:20:16,674][76542] Updated weights for policy 1, policy_version 93450 (0.0009) -[2023-10-10 16:20:17,045][76542] Updated weights for policy 1, policy_version 93460 (0.0008) -[2023-10-10 16:20:17,416][76542] Updated weights for policy 1, policy_version 93470 (0.0009) -[2023-10-10 16:20:20,218][76543] Updated weights for policy 0, policy_version 93673 (0.0011) -[2023-10-10 16:20:20,578][76543] Updated weights for policy 0, policy_version 93683 (0.0010) -[2023-10-10 16:20:20,951][76543] Updated weights for policy 0, policy_version 93693 (0.0010) -[2023-10-10 16:20:21,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 191660032. Throughput: 0: 1817.8, 1: 1828.7. Samples: 47917398. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 16:20:21,077][75634] Avg episode reward: [(0, '38.570'), (1, '39.100')] -[2023-10-10 16:20:21,134][76542] Updated weights for policy 1, policy_version 93480 (0.0010) -[2023-10-10 16:20:21,495][76542] Updated weights for policy 1, policy_version 93490 (0.0010) -[2023-10-10 16:20:21,857][76542] Updated weights for policy 1, policy_version 93500 (0.0011) -[2023-10-10 16:20:24,522][76543] Updated weights for policy 0, policy_version 93703 (0.0009) -[2023-10-10 16:20:24,882][76543] Updated weights for policy 0, policy_version 93713 (0.0008) -[2023-10-10 16:20:25,265][76543] Updated weights for policy 0, policy_version 93723 (0.0007) -[2023-10-10 16:20:25,593][76542] Updated weights for policy 1, policy_version 93510 (0.0009) -[2023-10-10 16:20:25,963][76542] Updated weights for policy 1, policy_version 93520 (0.0010) -[2023-10-10 16:20:26,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 191725568. Throughput: 0: 1816.7, 1: 1823.9. Samples: 47940140. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 16:20:26,077][75634] Avg episode reward: [(0, '38.160'), (1, '34.650')] -[2023-10-10 16:20:26,317][76542] Updated weights for policy 1, policy_version 93530 (0.0008) -[2023-10-10 16:20:28,818][76543] Updated weights for policy 0, policy_version 93733 (0.0010) -[2023-10-10 16:20:29,189][76543] Updated weights for policy 0, policy_version 93743 (0.0009) -[2023-10-10 16:20:29,561][76543] Updated weights for policy 0, policy_version 93753 (0.0008) -[2023-10-10 16:20:30,011][76542] Updated weights for policy 1, policy_version 93540 (0.0009) -[2023-10-10 16:20:30,376][76542] Updated weights for policy 1, policy_version 93550 (0.0008) -[2023-10-10 16:20:30,741][76542] Updated weights for policy 1, policy_version 93560 (0.0010) -[2023-10-10 16:20:31,076][75634] Fps is (10 sec: 16384.3, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 191823872. Throughput: 0: 1822.5, 1: 1821.0. Samples: 47960660. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 16:20:31,076][75634] Avg episode reward: [(0, '34.220'), (1, '29.160')] -[2023-10-10 16:20:31,085][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000093760_96010240.pth... -[2023-10-10 16:20:31,085][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000093568_95813632.pth... -[2023-10-10 16:20:31,124][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000091840_94044160.pth -[2023-10-10 16:20:31,126][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000092064_94273536.pth -[2023-10-10 16:20:31,130][76421] Saving a milestone ./train_atari/atari_defender_APPO/checkpoint_p1/milestones/checkpoint_000093568_95813632.pth -[2023-10-10 16:20:31,131][76362] Saving a milestone ./train_atari/atari_defender_APPO/checkpoint_p0/milestones/checkpoint_000093760_96010240.pth -[2023-10-10 16:20:33,333][76543] Updated weights for policy 0, policy_version 93763 (0.0010) -[2023-10-10 16:20:33,707][76543] Updated weights for policy 0, policy_version 93773 (0.0009) -[2023-10-10 16:20:34,088][76543] Updated weights for policy 0, policy_version 93783 (0.0008) -[2023-10-10 16:20:34,419][76542] Updated weights for policy 1, policy_version 93570 (0.0012) -[2023-10-10 16:20:34,806][76542] Updated weights for policy 1, policy_version 93580 (0.0009) -[2023-10-10 16:20:35,180][76542] Updated weights for policy 1, policy_version 93590 (0.0010) -[2023-10-10 16:20:35,551][76542] Updated weights for policy 1, policy_version 93600 (0.0010) -[2023-10-10 16:20:36,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 191889408. Throughput: 0: 1817.2, 1: 1826.2. Samples: 47973094. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 16:20:36,076][75634] Avg episode reward: [(0, '37.720'), (1, '32.710')] -[2023-10-10 16:20:37,741][76543] Updated weights for policy 0, policy_version 93793 (0.0009) -[2023-10-10 16:20:38,102][76543] Updated weights for policy 0, policy_version 93803 (0.0007) -[2023-10-10 16:20:38,475][76543] Updated weights for policy 0, policy_version 93813 (0.0008) -[2023-10-10 16:20:38,844][76543] Updated weights for policy 0, policy_version 93823 (0.0008) -[2023-10-10 16:20:39,134][76542] Updated weights for policy 1, policy_version 93610 (0.0007) -[2023-10-10 16:20:39,493][76542] Updated weights for policy 1, policy_version 93620 (0.0011) -[2023-10-10 16:20:39,861][76542] Updated weights for policy 1, policy_version 93630 (0.0010) -[2023-10-10 16:20:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 191954944. Throughput: 0: 1816.8, 1: 1826.5. Samples: 47993376. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 16:20:41,076][75634] Avg episode reward: [(0, '39.890'), (1, '31.930')] -[2023-10-10 16:20:42,575][76543] Updated weights for policy 0, policy_version 93833 (0.0008) -[2023-10-10 16:20:42,950][76543] Updated weights for policy 0, policy_version 93843 (0.0007) -[2023-10-10 16:20:43,318][76543] Updated weights for policy 0, policy_version 93853 (0.0007) -[2023-10-10 16:20:43,670][76542] Updated weights for policy 1, policy_version 93640 (0.0010) -[2023-10-10 16:20:44,043][76542] Updated weights for policy 1, policy_version 93650 (0.0010) -[2023-10-10 16:20:44,418][76542] Updated weights for policy 1, policy_version 93660 (0.0010) -[2023-10-10 16:20:46,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 192020480. Throughput: 0: 1819.3, 1: 1825.0. Samples: 48015612. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 16:20:46,076][75634] Avg episode reward: [(0, '38.680'), (1, '33.040')] -[2023-10-10 16:20:46,913][76543] Updated weights for policy 0, policy_version 93863 (0.0007) -[2023-10-10 16:20:47,287][76543] Updated weights for policy 0, policy_version 93873 (0.0009) -[2023-10-10 16:20:47,650][76543] Updated weights for policy 0, policy_version 93883 (0.0010) -[2023-10-10 16:20:48,153][76542] Updated weights for policy 1, policy_version 93670 (0.0010) -[2023-10-10 16:20:48,519][76542] Updated weights for policy 1, policy_version 93680 (0.0007) -[2023-10-10 16:20:48,883][76542] Updated weights for policy 1, policy_version 93690 (0.0008) -[2023-10-10 16:20:51,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14662.3). Total num frames: 192086016. Throughput: 0: 1819.3, 1: 1822.2. Samples: 48026050. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 16:20:51,077][75634] Avg episode reward: [(0, '37.140'), (1, '37.110')] -[2023-10-10 16:20:51,342][76543] Updated weights for policy 0, policy_version 93893 (0.0008) -[2023-10-10 16:20:51,708][76543] Updated weights for policy 0, policy_version 93903 (0.0008) -[2023-10-10 16:20:52,084][76543] Updated weights for policy 0, policy_version 93913 (0.0010) -[2023-10-10 16:20:52,587][76542] Updated weights for policy 1, policy_version 93700 (0.0009) -[2023-10-10 16:20:52,949][76542] Updated weights for policy 1, policy_version 93710 (0.0010) -[2023-10-10 16:20:53,325][76542] Updated weights for policy 1, policy_version 93720 (0.0008) -[2023-10-10 16:20:55,620][76543] Updated weights for policy 0, policy_version 93923 (0.0008) -[2023-10-10 16:20:55,989][76543] Updated weights for policy 0, policy_version 93933 (0.0009) -[2023-10-10 16:20:56,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 192151552. Throughput: 0: 1821.3, 1: 1819.4. Samples: 48048524. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-10 16:20:56,077][75634] Avg episode reward: [(0, '38.230'), (1, '41.860')] -[2023-10-10 16:20:56,361][76543] Updated weights for policy 0, policy_version 93943 (0.0010) -[2023-10-10 16:20:56,956][76542] Updated weights for policy 1, policy_version 93730 (0.0008) -[2023-10-10 16:20:57,331][76542] Updated weights for policy 1, policy_version 93740 (0.0010) -[2023-10-10 16:20:57,688][76542] Updated weights for policy 1, policy_version 93750 (0.0011) -[2023-10-10 16:20:58,058][76542] Updated weights for policy 1, policy_version 93760 (0.0011) -[2023-10-10 16:20:59,981][76543] Updated weights for policy 0, policy_version 93953 (0.0008) -[2023-10-10 16:21:00,355][76543] Updated weights for policy 0, policy_version 93963 (0.0007) -[2023-10-10 16:21:00,728][76543] Updated weights for policy 0, policy_version 93973 (0.0008) -[2023-10-10 16:21:01,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 192217088. Throughput: 0: 1824.6, 1: 1814.4. Samples: 48071270. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-10 16:21:01,076][75634] Avg episode reward: [(0, '39.700'), (1, '39.340')] -[2023-10-10 16:21:01,105][76543] Updated weights for policy 0, policy_version 93983 (0.0008) -[2023-10-10 16:21:01,961][76542] Updated weights for policy 1, policy_version 93770 (0.0007) -[2023-10-10 16:21:02,331][76542] Updated weights for policy 1, policy_version 93780 (0.0009) -[2023-10-10 16:21:02,703][76542] Updated weights for policy 1, policy_version 93790 (0.0008) -[2023-10-10 16:21:04,794][76543] Updated weights for policy 0, policy_version 93993 (0.0008) -[2023-10-10 16:21:05,154][76543] Updated weights for policy 0, policy_version 94003 (0.0009) -[2023-10-10 16:21:05,530][76543] Updated weights for policy 0, policy_version 94013 (0.0008) -[2023-10-10 16:21:06,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 192315392. Throughput: 0: 1836.5, 1: 1814.7. Samples: 48081702. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-10 16:21:06,077][75634] Avg episode reward: [(0, '37.460'), (1, '33.820')] -[2023-10-10 16:21:06,296][76542] Updated weights for policy 1, policy_version 93800 (0.0010) -[2023-10-10 16:21:06,669][76542] Updated weights for policy 1, policy_version 93810 (0.0009) -[2023-10-10 16:21:07,041][76542] Updated weights for policy 1, policy_version 93820 (0.0009) -[2023-10-10 16:21:09,158][76543] Updated weights for policy 0, policy_version 94023 (0.0009) -[2023-10-10 16:21:09,525][76543] Updated weights for policy 0, policy_version 94033 (0.0011) -[2023-10-10 16:21:09,901][76543] Updated weights for policy 0, policy_version 94043 (0.0010) -[2023-10-10 16:21:10,868][76542] Updated weights for policy 1, policy_version 93830 (0.0007) -[2023-10-10 16:21:11,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 192380928. Throughput: 0: 1827.1, 1: 1815.4. Samples: 48104052. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-10 16:21:11,076][75634] Avg episode reward: [(0, '38.140'), (1, '31.580')] -[2023-10-10 16:21:11,249][76542] Updated weights for policy 1, policy_version 93840 (0.0010) -[2023-10-10 16:21:11,619][76542] Updated weights for policy 1, policy_version 93850 (0.0010) -[2023-10-10 16:21:13,601][76543] Updated weights for policy 0, policy_version 94053 (0.0008) -[2023-10-10 16:21:13,974][76543] Updated weights for policy 0, policy_version 94063 (0.0008) -[2023-10-10 16:21:14,347][76543] Updated weights for policy 0, policy_version 94073 (0.0009) -[2023-10-10 16:21:15,237][76542] Updated weights for policy 1, policy_version 93860 (0.0011) -[2023-10-10 16:21:15,598][76542] Updated weights for policy 1, policy_version 93870 (0.0008) -[2023-10-10 16:21:15,965][76542] Updated weights for policy 1, policy_version 93880 (0.0007) -[2023-10-10 16:21:16,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 192446464. Throughput: 0: 1831.7, 1: 1819.8. Samples: 48124978. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-10 16:21:16,077][75634] Avg episode reward: [(0, '37.250'), (1, '32.260')] -[2023-10-10 16:21:17,961][76543] Updated weights for policy 0, policy_version 94083 (0.0008) -[2023-10-10 16:21:18,334][76543] Updated weights for policy 0, policy_version 94093 (0.0008) -[2023-10-10 16:21:18,699][76543] Updated weights for policy 0, policy_version 94103 (0.0009) -[2023-10-10 16:21:19,550][76542] Updated weights for policy 1, policy_version 93890 (0.0008) -[2023-10-10 16:21:19,966][76542] Updated weights for policy 1, policy_version 93900 (0.0007) -[2023-10-10 16:21:20,327][76542] Updated weights for policy 1, policy_version 93910 (0.0008) -[2023-10-10 16:21:20,695][76542] Updated weights for policy 1, policy_version 93920 (0.0009) -[2023-10-10 16:21:21,076][75634] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 192544768. Throughput: 0: 1824.3, 1: 1813.7. Samples: 48136804. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-10 16:21:21,077][75634] Avg episode reward: [(0, '33.390'), (1, '34.360')] -[2023-10-10 16:21:22,509][76543] Updated weights for policy 0, policy_version 94113 (0.0010) -[2023-10-10 16:21:22,880][76543] Updated weights for policy 0, policy_version 94123 (0.0008) -[2023-10-10 16:21:23,257][76543] Updated weights for policy 0, policy_version 94133 (0.0009) -[2023-10-10 16:21:23,623][76543] Updated weights for policy 0, policy_version 94143 (0.0008) -[2023-10-10 16:21:24,314][76542] Updated weights for policy 1, policy_version 93930 (0.0007) -[2023-10-10 16:21:24,676][76542] Updated weights for policy 1, policy_version 93940 (0.0009) -[2023-10-10 16:21:25,032][76542] Updated weights for policy 1, policy_version 93950 (0.0009) -[2023-10-10 16:21:26,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 192610304. Throughput: 0: 1834.4, 1: 1814.5. Samples: 48157578. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-10 16:21:26,077][75634] Avg episode reward: [(0, '36.170'), (1, '36.310')] -[2023-10-10 16:21:27,414][76543] Updated weights for policy 0, policy_version 94153 (0.0007) -[2023-10-10 16:21:27,782][76543] Updated weights for policy 0, policy_version 94163 (0.0010) -[2023-10-10 16:21:28,144][76543] Updated weights for policy 0, policy_version 94173 (0.0008) -[2023-10-10 16:21:28,602][76542] Updated weights for policy 1, policy_version 93960 (0.0008) -[2023-10-10 16:21:28,977][76542] Updated weights for policy 1, policy_version 93970 (0.0007) -[2023-10-10 16:21:29,337][76542] Updated weights for policy 1, policy_version 93980 (0.0007) -[2023-10-10 16:21:31,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14662.3). Total num frames: 192675840. Throughput: 0: 1833.6, 1: 1819.1. Samples: 48179986. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-10 16:21:31,077][75634] Avg episode reward: [(0, '35.580'), (1, '38.070')] -[2023-10-10 16:21:31,866][76543] Updated weights for policy 0, policy_version 94183 (0.0009) -[2023-10-10 16:21:32,238][76543] Updated weights for policy 0, policy_version 94193 (0.0010) -[2023-10-10 16:21:32,600][76543] Updated weights for policy 0, policy_version 94203 (0.0010) -[2023-10-10 16:21:33,055][76542] Updated weights for policy 1, policy_version 93990 (0.0009) -[2023-10-10 16:21:33,418][76542] Updated weights for policy 1, policy_version 94000 (0.0010) -[2023-10-10 16:21:33,800][76542] Updated weights for policy 1, policy_version 94010 (0.0011) -[2023-10-10 16:21:36,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 192741376. Throughput: 0: 1832.7, 1: 1815.0. Samples: 48190196. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-10 16:21:36,076][75634] Avg episode reward: [(0, '34.490'), (1, '39.260')] -[2023-10-10 16:21:36,137][76543] Updated weights for policy 0, policy_version 94213 (0.0008) -[2023-10-10 16:21:36,511][76543] Updated weights for policy 0, policy_version 94223 (0.0008) -[2023-10-10 16:21:36,886][76543] Updated weights for policy 0, policy_version 94233 (0.0008) -[2023-10-10 16:21:37,643][76542] Updated weights for policy 1, policy_version 94020 (0.0010) -[2023-10-10 16:21:38,000][76542] Updated weights for policy 1, policy_version 94030 (0.0009) -[2023-10-10 16:21:38,371][76542] Updated weights for policy 1, policy_version 94040 (0.0010) -[2023-10-10 16:21:40,527][76543] Updated weights for policy 0, policy_version 94243 (0.0010) -[2023-10-10 16:21:40,900][76543] Updated weights for policy 0, policy_version 94253 (0.0008) -[2023-10-10 16:21:41,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 192806912. Throughput: 0: 1828.7, 1: 1812.4. Samples: 48212370. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-10 16:21:41,076][75634] Avg episode reward: [(0, '36.110'), (1, '39.520')] -[2023-10-10 16:21:41,278][76543] Updated weights for policy 0, policy_version 94263 (0.0007) -[2023-10-10 16:21:41,960][76542] Updated weights for policy 1, policy_version 94050 (0.0010) -[2023-10-10 16:21:42,331][76542] Updated weights for policy 1, policy_version 94060 (0.0010) -[2023-10-10 16:21:42,699][76542] Updated weights for policy 1, policy_version 94070 (0.0010) -[2023-10-10 16:21:43,072][76542] Updated weights for policy 1, policy_version 94080 (0.0009) -[2023-10-10 16:21:44,987][76543] Updated weights for policy 0, policy_version 94273 (0.0008) -[2023-10-10 16:21:45,353][76543] Updated weights for policy 0, policy_version 94283 (0.0009) -[2023-10-10 16:21:45,728][76543] Updated weights for policy 0, policy_version 94293 (0.0008) -[2023-10-10 16:21:46,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 192872448. Throughput: 0: 1821.3, 1: 1820.4. Samples: 48235150. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-10 16:21:46,077][75634] Avg episode reward: [(0, '34.340'), (1, '36.260')] -[2023-10-10 16:21:46,092][76543] Updated weights for policy 0, policy_version 94303 (0.0008) -[2023-10-10 16:21:46,865][76542] Updated weights for policy 1, policy_version 94090 (0.0010) -[2023-10-10 16:21:47,239][76542] Updated weights for policy 1, policy_version 94100 (0.0008) -[2023-10-10 16:21:47,605][76542] Updated weights for policy 1, policy_version 94110 (0.0010) -[2023-10-10 16:21:49,746][76543] Updated weights for policy 0, policy_version 94313 (0.0008) -[2023-10-10 16:21:50,108][76543] Updated weights for policy 0, policy_version 94323 (0.0009) -[2023-10-10 16:21:50,490][76543] Updated weights for policy 0, policy_version 94333 (0.0007) -[2023-10-10 16:21:51,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 192970752. Throughput: 0: 1820.4, 1: 1818.9. Samples: 48245474. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-10 16:21:51,076][75634] Avg episode reward: [(0, '35.700'), (1, '32.960')] -[2023-10-10 16:21:51,347][76542] Updated weights for policy 1, policy_version 94120 (0.0010) -[2023-10-10 16:21:51,707][76542] Updated weights for policy 1, policy_version 94130 (0.0008) -[2023-10-10 16:21:52,085][76542] Updated weights for policy 1, policy_version 94140 (0.0009) -[2023-10-10 16:21:54,100][76543] Updated weights for policy 0, policy_version 94343 (0.0008) -[2023-10-10 16:21:54,470][76543] Updated weights for policy 0, policy_version 94353 (0.0008) -[2023-10-10 16:21:54,839][76543] Updated weights for policy 0, policy_version 94363 (0.0009) -[2023-10-10 16:21:55,885][76542] Updated weights for policy 1, policy_version 94150 (0.0010) -[2023-10-10 16:21:56,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 193036288. Throughput: 0: 1817.7, 1: 1827.2. Samples: 48268074. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:21:56,077][75634] Avg episode reward: [(0, '33.580'), (1, '33.120')] -[2023-10-10 16:21:56,255][76542] Updated weights for policy 1, policy_version 94160 (0.0009) -[2023-10-10 16:21:56,621][76542] Updated weights for policy 1, policy_version 94170 (0.0010) -[2023-10-10 16:21:58,560][76543] Updated weights for policy 0, policy_version 94373 (0.0008) -[2023-10-10 16:21:58,927][76543] Updated weights for policy 0, policy_version 94383 (0.0010) -[2023-10-10 16:21:59,301][76543] Updated weights for policy 0, policy_version 94393 (0.0011) -[2023-10-10 16:22:00,169][76542] Updated weights for policy 1, policy_version 94180 (0.0009) -[2023-10-10 16:22:00,539][76542] Updated weights for policy 1, policy_version 94190 (0.0008) -[2023-10-10 16:22:00,911][76542] Updated weights for policy 1, policy_version 94200 (0.0009) -[2023-10-10 16:22:01,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 193101824. Throughput: 0: 1823.7, 1: 1824.6. Samples: 48289150. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:22:01,076][75634] Avg episode reward: [(0, '38.110'), (1, '33.650')] -[2023-10-10 16:22:02,943][76543] Updated weights for policy 0, policy_version 94403 (0.0011) -[2023-10-10 16:22:03,323][76543] Updated weights for policy 0, policy_version 94413 (0.0008) -[2023-10-10 16:22:03,698][76543] Updated weights for policy 0, policy_version 94423 (0.0009) -[2023-10-10 16:22:04,497][76542] Updated weights for policy 1, policy_version 94210 (0.0009) -[2023-10-10 16:22:04,890][76542] Updated weights for policy 1, policy_version 94220 (0.0010) -[2023-10-10 16:22:05,259][76542] Updated weights for policy 1, policy_version 94230 (0.0008) -[2023-10-10 16:22:05,626][76542] Updated weights for policy 1, policy_version 94240 (0.0007) -[2023-10-10 16:22:06,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 193200128. Throughput: 0: 1825.4, 1: 1825.9. Samples: 48301112. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:22:06,076][75634] Avg episode reward: [(0, '40.070'), (1, '36.630')] -[2023-10-10 16:22:07,395][76543] Updated weights for policy 0, policy_version 94433 (0.0007) -[2023-10-10 16:22:07,760][76543] Updated weights for policy 0, policy_version 94443 (0.0008) -[2023-10-10 16:22:08,133][76543] Updated weights for policy 0, policy_version 94453 (0.0007) -[2023-10-10 16:22:08,513][76543] Updated weights for policy 0, policy_version 94463 (0.0008) -[2023-10-10 16:22:09,381][76542] Updated weights for policy 1, policy_version 94250 (0.0007) -[2023-10-10 16:22:09,743][76542] Updated weights for policy 1, policy_version 94260 (0.0007) -[2023-10-10 16:22:10,109][76542] Updated weights for policy 1, policy_version 94270 (0.0008) -[2023-10-10 16:22:11,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 193265664. Throughput: 0: 1836.8, 1: 1823.4. Samples: 48322286. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:22:11,077][75634] Avg episode reward: [(0, '37.870'), (1, '38.630')] -[2023-10-10 16:22:12,128][76543] Updated weights for policy 0, policy_version 94473 (0.0008) -[2023-10-10 16:22:12,496][76543] Updated weights for policy 0, policy_version 94483 (0.0011) -[2023-10-10 16:22:12,865][76543] Updated weights for policy 0, policy_version 94493 (0.0008) -[2023-10-10 16:22:13,606][76542] Updated weights for policy 1, policy_version 94280 (0.0009) -[2023-10-10 16:22:13,980][76542] Updated weights for policy 1, policy_version 94290 (0.0009) -[2023-10-10 16:22:14,342][76542] Updated weights for policy 1, policy_version 94300 (0.0008) -[2023-10-10 16:22:16,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 193331200. Throughput: 0: 1832.5, 1: 1819.6. Samples: 48344330. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:22:16,077][75634] Avg episode reward: [(0, '33.890'), (1, '35.530')] -[2023-10-10 16:22:16,459][76543] Updated weights for policy 0, policy_version 94503 (0.0010) -[2023-10-10 16:22:16,825][76543] Updated weights for policy 0, policy_version 94513 (0.0011) -[2023-10-10 16:22:17,193][76543] Updated weights for policy 0, policy_version 94523 (0.0008) -[2023-10-10 16:22:18,089][76542] Updated weights for policy 1, policy_version 94310 (0.0009) -[2023-10-10 16:22:18,456][76542] Updated weights for policy 1, policy_version 94320 (0.0009) -[2023-10-10 16:22:18,822][76542] Updated weights for policy 1, policy_version 94330 (0.0007) -[2023-10-10 16:22:20,801][76543] Updated weights for policy 0, policy_version 94533 (0.0008) -[2023-10-10 16:22:21,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 193396736. Throughput: 0: 1834.4, 1: 1819.1. Samples: 48354600. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:22:21,076][75634] Avg episode reward: [(0, '36.910'), (1, '36.420')] -[2023-10-10 16:22:21,176][76543] Updated weights for policy 0, policy_version 94543 (0.0010) -[2023-10-10 16:22:21,544][76543] Updated weights for policy 0, policy_version 94553 (0.0008) -[2023-10-10 16:22:22,529][76542] Updated weights for policy 1, policy_version 94340 (0.0009) -[2023-10-10 16:22:22,888][76542] Updated weights for policy 1, policy_version 94350 (0.0009) -[2023-10-10 16:22:23,256][76542] Updated weights for policy 1, policy_version 94360 (0.0007) -[2023-10-10 16:22:25,344][76543] Updated weights for policy 0, policy_version 94563 (0.0009) -[2023-10-10 16:22:25,713][76543] Updated weights for policy 0, policy_version 94573 (0.0009) -[2023-10-10 16:22:26,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 193462272. Throughput: 0: 1834.4, 1: 1824.7. Samples: 48377028. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:22:26,076][75634] Avg episode reward: [(0, '39.540'), (1, '32.540')] -[2023-10-10 16:22:26,079][76543] Updated weights for policy 0, policy_version 94583 (0.0008) -[2023-10-10 16:22:26,916][76542] Updated weights for policy 1, policy_version 94370 (0.0008) -[2023-10-10 16:22:27,286][76542] Updated weights for policy 1, policy_version 94380 (0.0011) -[2023-10-10 16:22:27,661][76542] Updated weights for policy 1, policy_version 94390 (0.0007) -[2023-10-10 16:22:28,022][76542] Updated weights for policy 1, policy_version 94400 (0.0007) -[2023-10-10 16:22:29,754][76543] Updated weights for policy 0, policy_version 94593 (0.0007) -[2023-10-10 16:22:30,112][76543] Updated weights for policy 0, policy_version 94603 (0.0007) -[2023-10-10 16:22:30,482][76543] Updated weights for policy 0, policy_version 94613 (0.0007) -[2023-10-10 16:22:30,849][76543] Updated weights for policy 0, policy_version 94623 (0.0008) -[2023-10-10 16:22:31,076][75634] Fps is (10 sec: 16383.4, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 193560576. Throughput: 0: 1824.3, 1: 1830.5. Samples: 48399618. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:22:31,077][75634] Avg episode reward: [(0, '37.400'), (1, '31.770')] -[2023-10-10 16:22:31,086][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000094400_96665600.pth... -[2023-10-10 16:22:31,086][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000094624_96894976.pth... -[2023-10-10 16:22:31,117][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000092704_94928896.pth -[2023-10-10 16:22:31,126][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000092896_95125504.pth -[2023-10-10 16:22:31,625][76542] Updated weights for policy 1, policy_version 94410 (0.0009) -[2023-10-10 16:22:31,995][76542] Updated weights for policy 1, policy_version 94420 (0.0009) -[2023-10-10 16:22:32,364][76542] Updated weights for policy 1, policy_version 94430 (0.0007) -[2023-10-10 16:22:34,415][76543] Updated weights for policy 0, policy_version 94633 (0.0008) -[2023-10-10 16:22:34,782][76543] Updated weights for policy 0, policy_version 94643 (0.0008) -[2023-10-10 16:22:35,146][76543] Updated weights for policy 0, policy_version 94653 (0.0008) -[2023-10-10 16:22:36,072][76542] Updated weights for policy 1, policy_version 94440 (0.0008) -[2023-10-10 16:22:36,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 193626112. Throughput: 0: 1830.8, 1: 1834.6. Samples: 48410416. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:22:36,076][75634] Avg episode reward: [(0, '38.460'), (1, '32.270')] -[2023-10-10 16:22:36,433][76542] Updated weights for policy 1, policy_version 94450 (0.0007) -[2023-10-10 16:22:36,797][76542] Updated weights for policy 1, policy_version 94460 (0.0010) -[2023-10-10 16:22:38,812][76543] Updated weights for policy 0, policy_version 94663 (0.0010) -[2023-10-10 16:22:39,188][76543] Updated weights for policy 0, policy_version 94673 (0.0008) -[2023-10-10 16:22:39,565][76543] Updated weights for policy 0, policy_version 94683 (0.0009) -[2023-10-10 16:22:40,493][76542] Updated weights for policy 1, policy_version 94470 (0.0009) -[2023-10-10 16:22:40,859][76542] Updated weights for policy 1, policy_version 94480 (0.0008) -[2023-10-10 16:22:41,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 193691648. Throughput: 0: 1828.8, 1: 1830.1. Samples: 48432724. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:22:41,077][75634] Avg episode reward: [(0, '40.940'), (1, '31.290')] -[2023-10-10 16:22:41,220][76542] Updated weights for policy 1, policy_version 94490 (0.0007) -[2023-10-10 16:22:43,294][76543] Updated weights for policy 0, policy_version 94693 (0.0010) -[2023-10-10 16:22:43,668][76543] Updated weights for policy 0, policy_version 94703 (0.0009) -[2023-10-10 16:22:44,049][76543] Updated weights for policy 0, policy_version 94713 (0.0008) -[2023-10-10 16:22:44,924][76542] Updated weights for policy 1, policy_version 94500 (0.0008) -[2023-10-10 16:22:45,294][76542] Updated weights for policy 1, policy_version 94510 (0.0009) -[2023-10-10 16:22:45,664][76542] Updated weights for policy 1, policy_version 94520 (0.0007) -[2023-10-10 16:22:46,076][75634] Fps is (10 sec: 16383.6, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 193789952. Throughput: 0: 1829.9, 1: 1826.3. Samples: 48453680. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:22:46,077][75634] Avg episode reward: [(0, '39.560'), (1, '38.280')] -[2023-10-10 16:22:47,769][76543] Updated weights for policy 0, policy_version 94723 (0.0010) -[2023-10-10 16:22:48,137][76543] Updated weights for policy 0, policy_version 94733 (0.0008) -[2023-10-10 16:22:48,512][76543] Updated weights for policy 0, policy_version 94743 (0.0007) -[2023-10-10 16:22:49,290][76542] Updated weights for policy 1, policy_version 94530 (0.0007) -[2023-10-10 16:22:49,695][76542] Updated weights for policy 1, policy_version 94540 (0.0008) -[2023-10-10 16:22:50,071][76542] Updated weights for policy 1, policy_version 94550 (0.0009) -[2023-10-10 16:22:50,430][76542] Updated weights for policy 1, policy_version 94560 (0.0008) -[2023-10-10 16:22:51,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 193855488. Throughput: 0: 1821.1, 1: 1833.8. Samples: 48465584. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:22:51,077][75634] Avg episode reward: [(0, '33.680'), (1, '42.400')] -[2023-10-10 16:22:52,192][76543] Updated weights for policy 0, policy_version 94753 (0.0009) -[2023-10-10 16:22:52,570][76543] Updated weights for policy 0, policy_version 94763 (0.0008) -[2023-10-10 16:22:52,944][76543] Updated weights for policy 0, policy_version 94773 (0.0009) -[2023-10-10 16:22:53,309][76543] Updated weights for policy 0, policy_version 94783 (0.0009) -[2023-10-10 16:22:54,067][76542] Updated weights for policy 1, policy_version 94570 (0.0009) -[2023-10-10 16:22:54,437][76542] Updated weights for policy 1, policy_version 94580 (0.0009) -[2023-10-10 16:22:54,801][76542] Updated weights for policy 1, policy_version 94590 (0.0009) -[2023-10-10 16:22:56,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 193921024. Throughput: 0: 1819.6, 1: 1827.5. Samples: 48486406. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:22:56,077][75634] Avg episode reward: [(0, '35.310'), (1, '37.500')] -[2023-10-10 16:22:56,870][76543] Updated weights for policy 0, policy_version 94793 (0.0008) -[2023-10-10 16:22:57,242][76543] Updated weights for policy 0, policy_version 94803 (0.0008) -[2023-10-10 16:22:57,616][76543] Updated weights for policy 0, policy_version 94813 (0.0008) -[2023-10-10 16:22:58,364][76542] Updated weights for policy 1, policy_version 94600 (0.0008) -[2023-10-10 16:22:58,736][76542] Updated weights for policy 1, policy_version 94610 (0.0007) -[2023-10-10 16:22:59,108][76542] Updated weights for policy 1, policy_version 94620 (0.0007) -[2023-10-10 16:23:01,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 193986560. Throughput: 0: 1830.6, 1: 1836.9. Samples: 48509368. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:23:01,077][75634] Avg episode reward: [(0, '36.830'), (1, '35.680')] -[2023-10-10 16:23:01,223][76543] Updated weights for policy 0, policy_version 94823 (0.0008) -[2023-10-10 16:23:01,590][76543] Updated weights for policy 0, policy_version 94833 (0.0010) -[2023-10-10 16:23:01,954][76543] Updated weights for policy 0, policy_version 94843 (0.0008) -[2023-10-10 16:23:02,692][76542] Updated weights for policy 1, policy_version 94630 (0.0007) -[2023-10-10 16:23:03,058][76542] Updated weights for policy 1, policy_version 94640 (0.0007) -[2023-10-10 16:23:03,440][76542] Updated weights for policy 1, policy_version 94650 (0.0009) -[2023-10-10 16:23:05,680][76543] Updated weights for policy 0, policy_version 94853 (0.0008) -[2023-10-10 16:23:06,055][76543] Updated weights for policy 0, policy_version 94863 (0.0007) -[2023-10-10 16:23:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 194052096. Throughput: 0: 1831.8, 1: 1833.1. Samples: 48519520. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:23:06,077][75634] Avg episode reward: [(0, '38.740'), (1, '32.600')] -[2023-10-10 16:23:06,438][76543] Updated weights for policy 0, policy_version 94873 (0.0010) -[2023-10-10 16:23:07,014][76542] Updated weights for policy 1, policy_version 94660 (0.0009) -[2023-10-10 16:23:07,380][76542] Updated weights for policy 1, policy_version 94670 (0.0009) -[2023-10-10 16:23:07,749][76542] Updated weights for policy 1, policy_version 94680 (0.0007) -[2023-10-10 16:23:10,190][76543] Updated weights for policy 0, policy_version 94883 (0.0008) -[2023-10-10 16:23:10,569][76543] Updated weights for policy 0, policy_version 94893 (0.0008) -[2023-10-10 16:23:10,935][76543] Updated weights for policy 0, policy_version 94903 (0.0007) -[2023-10-10 16:23:11,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 194117632. Throughput: 0: 1825.1, 1: 1853.9. Samples: 48542584. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:23:11,077][75634] Avg episode reward: [(0, '35.680'), (1, '27.890')] -[2023-10-10 16:23:11,333][76542] Updated weights for policy 1, policy_version 94690 (0.0009) -[2023-10-10 16:23:11,707][76542] Updated weights for policy 1, policy_version 94700 (0.0010) -[2023-10-10 16:23:12,062][76542] Updated weights for policy 1, policy_version 94710 (0.0008) -[2023-10-10 16:23:12,426][76542] Updated weights for policy 1, policy_version 94720 (0.0007) -[2023-10-10 16:23:14,569][76543] Updated weights for policy 0, policy_version 94913 (0.0009) -[2023-10-10 16:23:14,938][76543] Updated weights for policy 0, policy_version 94923 (0.0008) -[2023-10-10 16:23:15,313][76543] Updated weights for policy 0, policy_version 94933 (0.0007) -[2023-10-10 16:23:15,694][76543] Updated weights for policy 0, policy_version 94943 (0.0009) -[2023-10-10 16:23:16,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 194215936. Throughput: 0: 1825.2, 1: 1843.9. Samples: 48564726. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:23:16,076][75634] Avg episode reward: [(0, '42.050'), (1, '30.840')] -[2023-10-10 16:23:16,201][76542] Updated weights for policy 1, policy_version 94730 (0.0007) -[2023-10-10 16:23:16,571][76542] Updated weights for policy 1, policy_version 94740 (0.0009) -[2023-10-10 16:23:16,938][76542] Updated weights for policy 1, policy_version 94750 (0.0009) -[2023-10-10 16:23:19,462][76543] Updated weights for policy 0, policy_version 94953 (0.0008) -[2023-10-10 16:23:19,829][76543] Updated weights for policy 0, policy_version 94963 (0.0009) -[2023-10-10 16:23:20,200][76543] Updated weights for policy 0, policy_version 94973 (0.0008) -[2023-10-10 16:23:20,597][76542] Updated weights for policy 1, policy_version 94760 (0.0009) -[2023-10-10 16:23:20,960][76542] Updated weights for policy 1, policy_version 94770 (0.0009) -[2023-10-10 16:23:21,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 194281472. Throughput: 0: 1824.3, 1: 1840.7. Samples: 48575340. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:23:21,076][75634] Avg episode reward: [(0, '41.920'), (1, '32.840')] -[2023-10-10 16:23:21,330][76542] Updated weights for policy 1, policy_version 94780 (0.0007) -[2023-10-10 16:23:23,740][76543] Updated weights for policy 0, policy_version 94983 (0.0009) -[2023-10-10 16:23:24,108][76543] Updated weights for policy 0, policy_version 94993 (0.0007) -[2023-10-10 16:23:24,475][76543] Updated weights for policy 0, policy_version 95003 (0.0009) -[2023-10-10 16:23:24,892][76542] Updated weights for policy 1, policy_version 94790 (0.0009) -[2023-10-10 16:23:25,262][76542] Updated weights for policy 1, policy_version 94800 (0.0007) -[2023-10-10 16:23:25,619][76542] Updated weights for policy 1, policy_version 94810 (0.0008) -[2023-10-10 16:23:26,076][75634] Fps is (10 sec: 16383.8, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 194379776. Throughput: 0: 1821.2, 1: 1842.6. Samples: 48597592. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:23:26,077][75634] Avg episode reward: [(0, '38.730'), (1, '37.090')] -[2023-10-10 16:23:28,256][76543] Updated weights for policy 0, policy_version 95013 (0.0008) -[2023-10-10 16:23:28,619][76543] Updated weights for policy 0, policy_version 95023 (0.0008) -[2023-10-10 16:23:28,997][76543] Updated weights for policy 0, policy_version 95033 (0.0007) -[2023-10-10 16:23:29,386][76542] Updated weights for policy 1, policy_version 94820 (0.0007) -[2023-10-10 16:23:29,747][76542] Updated weights for policy 1, policy_version 94830 (0.0008) -[2023-10-10 16:23:30,111][76542] Updated weights for policy 1, policy_version 94840 (0.0010) -[2023-10-10 16:23:31,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 194445312. Throughput: 0: 1824.0, 1: 1830.5. Samples: 48618132. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:23:31,077][75634] Avg episode reward: [(0, '38.650'), (1, '40.170')] -[2023-10-10 16:23:32,668][76543] Updated weights for policy 0, policy_version 95043 (0.0008) -[2023-10-10 16:23:33,043][76543] Updated weights for policy 0, policy_version 95053 (0.0009) -[2023-10-10 16:23:33,413][76543] Updated weights for policy 0, policy_version 95063 (0.0008) -[2023-10-10 16:23:33,704][76542] Updated weights for policy 1, policy_version 94850 (0.0008) -[2023-10-10 16:23:34,073][76542] Updated weights for policy 1, policy_version 94860 (0.0009) -[2023-10-10 16:23:34,438][76542] Updated weights for policy 1, policy_version 94870 (0.0009) -[2023-10-10 16:23:34,799][76542] Updated weights for policy 1, policy_version 94880 (0.0008) -[2023-10-10 16:23:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 194510848. Throughput: 0: 1825.4, 1: 1837.8. Samples: 48630428. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:23:36,077][75634] Avg episode reward: [(0, '38.510'), (1, '38.640')] -[2023-10-10 16:23:37,074][76543] Updated weights for policy 0, policy_version 95073 (0.0007) -[2023-10-10 16:23:37,450][76543] Updated weights for policy 0, policy_version 95083 (0.0008) -[2023-10-10 16:23:37,819][76543] Updated weights for policy 0, policy_version 95093 (0.0009) -[2023-10-10 16:23:38,187][76543] Updated weights for policy 0, policy_version 95103 (0.0009) -[2023-10-10 16:23:38,475][76542] Updated weights for policy 1, policy_version 94890 (0.0011) -[2023-10-10 16:23:38,850][76542] Updated weights for policy 1, policy_version 94900 (0.0011) -[2023-10-10 16:23:39,229][76542] Updated weights for policy 1, policy_version 94910 (0.0011) -[2023-10-10 16:23:41,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 194576384. Throughput: 0: 1829.3, 1: 1834.6. Samples: 48651282. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:23:41,077][75634] Avg episode reward: [(0, '39.810'), (1, '35.610')] -[2023-10-10 16:23:41,818][76543] Updated weights for policy 0, policy_version 95113 (0.0009) -[2023-10-10 16:23:42,196][76543] Updated weights for policy 0, policy_version 95123 (0.0008) -[2023-10-10 16:23:42,573][76543] Updated weights for policy 0, policy_version 95133 (0.0008) -[2023-10-10 16:23:43,073][76542] Updated weights for policy 1, policy_version 94920 (0.0010) -[2023-10-10 16:23:43,455][76542] Updated weights for policy 1, policy_version 94930 (0.0009) -[2023-10-10 16:23:43,826][76542] Updated weights for policy 1, policy_version 94940 (0.0011) -[2023-10-10 16:23:46,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 194641920. Throughput: 0: 1825.3, 1: 1834.6. Samples: 48674064. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:23:46,077][75634] Avg episode reward: [(0, '44.350'), (1, '34.580')] -[2023-10-10 16:23:46,202][76543] Updated weights for policy 0, policy_version 95143 (0.0009) -[2023-10-10 16:23:46,572][76543] Updated weights for policy 0, policy_version 95153 (0.0009) -[2023-10-10 16:23:46,945][76543] Updated weights for policy 0, policy_version 95163 (0.0008) -[2023-10-10 16:23:47,366][76542] Updated weights for policy 1, policy_version 94950 (0.0009) -[2023-10-10 16:23:47,734][76542] Updated weights for policy 1, policy_version 94960 (0.0010) -[2023-10-10 16:23:48,093][76542] Updated weights for policy 1, policy_version 94970 (0.0008) -[2023-10-10 16:23:50,605][76543] Updated weights for policy 0, policy_version 95173 (0.0010) -[2023-10-10 16:23:50,967][76543] Updated weights for policy 0, policy_version 95183 (0.0008) -[2023-10-10 16:23:51,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 194707456. Throughput: 0: 1824.9, 1: 1831.2. Samples: 48684040. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:23:51,076][75634] Avg episode reward: [(0, '44.620'), (1, '31.250')] -[2023-10-10 16:23:51,342][76543] Updated weights for policy 0, policy_version 95193 (0.0009) -[2023-10-10 16:23:51,842][76542] Updated weights for policy 1, policy_version 94980 (0.0010) -[2023-10-10 16:23:52,207][76542] Updated weights for policy 1, policy_version 94990 (0.0008) -[2023-10-10 16:23:52,573][76542] Updated weights for policy 1, policy_version 95000 (0.0010) -[2023-10-10 16:23:54,947][76543] Updated weights for policy 0, policy_version 95203 (0.0011) -[2023-10-10 16:23:55,316][76543] Updated weights for policy 0, policy_version 95213 (0.0009) -[2023-10-10 16:23:55,687][76543] Updated weights for policy 0, policy_version 95223 (0.0007) -[2023-10-10 16:23:56,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 194805760. Throughput: 0: 1838.0, 1: 1823.2. Samples: 48707338. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:23:56,076][75634] Avg episode reward: [(0, '40.380'), (1, '30.940')] -[2023-10-10 16:23:56,227][76542] Updated weights for policy 1, policy_version 95010 (0.0008) -[2023-10-10 16:23:56,592][76542] Updated weights for policy 1, policy_version 95020 (0.0008) -[2023-10-10 16:23:56,966][76542] Updated weights for policy 1, policy_version 95030 (0.0007) -[2023-10-10 16:23:57,334][76542] Updated weights for policy 1, policy_version 95040 (0.0008) -[2023-10-10 16:23:59,424][76543] Updated weights for policy 0, policy_version 95233 (0.0007) -[2023-10-10 16:23:59,787][76543] Updated weights for policy 0, policy_version 95243 (0.0009) -[2023-10-10 16:24:00,163][76543] Updated weights for policy 0, policy_version 95253 (0.0008) -[2023-10-10 16:24:00,535][76543] Updated weights for policy 0, policy_version 95263 (0.0010) -[2023-10-10 16:24:01,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 194871296. Throughput: 0: 1827.5, 1: 1825.4. Samples: 48729106. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:24:01,076][75634] Avg episode reward: [(0, '37.030'), (1, '32.840')] -[2023-10-10 16:24:01,080][76542] Updated weights for policy 1, policy_version 95050 (0.0008) -[2023-10-10 16:24:01,440][76542] Updated weights for policy 1, policy_version 95060 (0.0008) -[2023-10-10 16:24:01,814][76542] Updated weights for policy 1, policy_version 95070 (0.0007) -[2023-10-10 16:24:04,094][76543] Updated weights for policy 0, policy_version 95273 (0.0007) -[2023-10-10 16:24:04,458][76543] Updated weights for policy 0, policy_version 95283 (0.0008) -[2023-10-10 16:24:04,824][76543] Updated weights for policy 0, policy_version 95293 (0.0011) -[2023-10-10 16:24:05,542][76542] Updated weights for policy 1, policy_version 95080 (0.0009) -[2023-10-10 16:24:05,902][76542] Updated weights for policy 1, policy_version 95090 (0.0008) -[2023-10-10 16:24:06,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 194936832. Throughput: 0: 1836.8, 1: 1826.3. Samples: 48740180. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:24:06,076][75634] Avg episode reward: [(0, '36.790'), (1, '35.200')] -[2023-10-10 16:24:06,267][76542] Updated weights for policy 1, policy_version 95100 (0.0008) -[2023-10-10 16:24:08,465][76543] Updated weights for policy 0, policy_version 95303 (0.0008) -[2023-10-10 16:24:08,836][76543] Updated weights for policy 0, policy_version 95313 (0.0010) -[2023-10-10 16:24:09,208][76543] Updated weights for policy 0, policy_version 95323 (0.0007) -[2023-10-10 16:24:09,865][76542] Updated weights for policy 1, policy_version 95110 (0.0008) -[2023-10-10 16:24:10,238][76542] Updated weights for policy 1, policy_version 95120 (0.0007) -[2023-10-10 16:24:10,614][76542] Updated weights for policy 1, policy_version 95130 (0.0009) -[2023-10-10 16:24:11,076][75634] Fps is (10 sec: 16383.7, 60 sec: 15291.7, 300 sec: 14662.3). Total num frames: 195035136. Throughput: 0: 1825.7, 1: 1823.5. Samples: 48761806. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:24:11,077][75634] Avg episode reward: [(0, '32.410'), (1, '38.680')] -[2023-10-10 16:24:12,985][76543] Updated weights for policy 0, policy_version 95333 (0.0009) -[2023-10-10 16:24:13,355][76543] Updated weights for policy 0, policy_version 95343 (0.0008) -[2023-10-10 16:24:13,719][76543] Updated weights for policy 0, policy_version 95353 (0.0008) -[2023-10-10 16:24:14,275][76542] Updated weights for policy 1, policy_version 95140 (0.0010) -[2023-10-10 16:24:14,641][76542] Updated weights for policy 1, policy_version 95150 (0.0009) -[2023-10-10 16:24:15,014][76542] Updated weights for policy 1, policy_version 95160 (0.0010) -[2023-10-10 16:24:16,076][75634] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 195100672. Throughput: 0: 1835.3, 1: 1823.9. Samples: 48782796. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:24:16,077][75634] Avg episode reward: [(0, '32.230'), (1, '40.580')] -[2023-10-10 16:24:17,355][76543] Updated weights for policy 0, policy_version 95363 (0.0008) -[2023-10-10 16:24:17,724][76543] Updated weights for policy 0, policy_version 95373 (0.0008) -[2023-10-10 16:24:18,101][76543] Updated weights for policy 0, policy_version 95383 (0.0010) -[2023-10-10 16:24:18,881][76542] Updated weights for policy 1, policy_version 95170 (0.0009) -[2023-10-10 16:24:19,258][76542] Updated weights for policy 1, policy_version 95180 (0.0009) -[2023-10-10 16:24:19,636][76542] Updated weights for policy 1, policy_version 95190 (0.0008) -[2023-10-10 16:24:19,997][76542] Updated weights for policy 1, policy_version 95200 (0.0009) -[2023-10-10 16:24:21,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 195166208. Throughput: 0: 1825.4, 1: 1819.7. Samples: 48794454. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:24:21,076][75634] Avg episode reward: [(0, '36.780'), (1, '39.470')] -[2023-10-10 16:24:21,765][76543] Updated weights for policy 0, policy_version 95393 (0.0008) -[2023-10-10 16:24:22,137][76543] Updated weights for policy 0, policy_version 95403 (0.0009) -[2023-10-10 16:24:22,511][76543] Updated weights for policy 0, policy_version 95413 (0.0009) -[2023-10-10 16:24:22,874][76543] Updated weights for policy 0, policy_version 95423 (0.0008) -[2023-10-10 16:24:23,454][76542] Updated weights for policy 1, policy_version 95210 (0.0008) -[2023-10-10 16:24:23,832][76542] Updated weights for policy 1, policy_version 95220 (0.0007) -[2023-10-10 16:24:24,202][76542] Updated weights for policy 1, policy_version 95230 (0.0007) -[2023-10-10 16:24:26,076][75634] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14662.3). Total num frames: 195231744. Throughput: 0: 1831.4, 1: 1820.0. Samples: 48815596. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:24:26,076][75634] Avg episode reward: [(0, '40.200'), (1, '35.570')] -[2023-10-10 16:24:26,604][76543] Updated weights for policy 0, policy_version 95433 (0.0009) -[2023-10-10 16:24:26,965][76543] Updated weights for policy 0, policy_version 95443 (0.0007) -[2023-10-10 16:24:27,343][76543] Updated weights for policy 0, policy_version 95453 (0.0008) -[2023-10-10 16:24:27,989][76542] Updated weights for policy 1, policy_version 95240 (0.0008) -[2023-10-10 16:24:28,361][76542] Updated weights for policy 1, policy_version 95250 (0.0008) -[2023-10-10 16:24:28,735][76542] Updated weights for policy 1, policy_version 95260 (0.0007) -[2023-10-10 16:24:31,041][76543] Updated weights for policy 0, policy_version 95463 (0.0010) -[2023-10-10 16:24:31,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 195297280. Throughput: 0: 1831.2, 1: 1816.6. Samples: 48838216. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:24:31,077][75634] Avg episode reward: [(0, '37.920'), (1, '35.090')] -[2023-10-10 16:24:31,089][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000095264_97550336.pth... -[2023-10-10 16:24:31,124][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000093568_95813632.pth -[2023-10-10 16:24:31,416][76543] Updated weights for policy 0, policy_version 95473 (0.0008) -[2023-10-10 16:24:31,781][76543] Updated weights for policy 0, policy_version 95483 (0.0008) -[2023-10-10 16:24:31,964][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000095488_97779712.pth... -[2023-10-10 16:24:31,993][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000093760_96010240.pth -[2023-10-10 16:24:32,564][76542] Updated weights for policy 1, policy_version 95270 (0.0011) -[2023-10-10 16:24:32,930][76542] Updated weights for policy 1, policy_version 95280 (0.0009) -[2023-10-10 16:24:33,304][76542] Updated weights for policy 1, policy_version 95290 (0.0007) -[2023-10-10 16:24:35,436][76543] Updated weights for policy 0, policy_version 95493 (0.0008) -[2023-10-10 16:24:35,809][76543] Updated weights for policy 0, policy_version 95503 (0.0007) -[2023-10-10 16:24:36,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 195362816. Throughput: 0: 1830.7, 1: 1814.2. Samples: 48848062. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:24:36,076][75634] Avg episode reward: [(0, '39.930'), (1, '33.190')] -[2023-10-10 16:24:36,168][76543] Updated weights for policy 0, policy_version 95513 (0.0011) -[2023-10-10 16:24:36,948][76542] Updated weights for policy 1, policy_version 95300 (0.0007) -[2023-10-10 16:24:37,319][76542] Updated weights for policy 1, policy_version 95310 (0.0007) -[2023-10-10 16:24:37,697][76542] Updated weights for policy 1, policy_version 95320 (0.0010) -[2023-10-10 16:24:39,835][76543] Updated weights for policy 0, policy_version 95523 (0.0010) -[2023-10-10 16:24:40,209][76543] Updated weights for policy 0, policy_version 95533 (0.0008) -[2023-10-10 16:24:40,582][76543] Updated weights for policy 0, policy_version 95543 (0.0009) -[2023-10-10 16:24:41,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 195461120. Throughput: 0: 1820.8, 1: 1813.5. Samples: 48870882. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:24:41,077][75634] Avg episode reward: [(0, '36.670'), (1, '32.640')] -[2023-10-10 16:24:41,405][76542] Updated weights for policy 1, policy_version 95330 (0.0011) -[2023-10-10 16:24:41,771][76542] Updated weights for policy 1, policy_version 95340 (0.0009) -[2023-10-10 16:24:42,136][76542] Updated weights for policy 1, policy_version 95350 (0.0011) -[2023-10-10 16:24:42,506][76542] Updated weights for policy 1, policy_version 95360 (0.0009) -[2023-10-10 16:24:44,455][76543] Updated weights for policy 0, policy_version 95553 (0.0008) -[2023-10-10 16:24:44,829][76543] Updated weights for policy 0, policy_version 95563 (0.0007) -[2023-10-10 16:24:45,207][76543] Updated weights for policy 0, policy_version 95573 (0.0009) -[2023-10-10 16:24:45,574][76543] Updated weights for policy 0, policy_version 95583 (0.0008) -[2023-10-10 16:24:46,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 195526656. Throughput: 0: 1819.1, 1: 1813.9. Samples: 48892592. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:24:46,077][75634] Avg episode reward: [(0, '39.160'), (1, '36.670')] -[2023-10-10 16:24:46,324][76542] Updated weights for policy 1, policy_version 95370 (0.0007) -[2023-10-10 16:24:46,689][76542] Updated weights for policy 1, policy_version 95380 (0.0007) -[2023-10-10 16:24:47,069][76542] Updated weights for policy 1, policy_version 95390 (0.0010) -[2023-10-10 16:24:49,124][76543] Updated weights for policy 0, policy_version 95593 (0.0008) -[2023-10-10 16:24:49,499][76543] Updated weights for policy 0, policy_version 95603 (0.0008) -[2023-10-10 16:24:49,858][76543] Updated weights for policy 0, policy_version 95613 (0.0008) -[2023-10-10 16:24:50,911][76542] Updated weights for policy 1, policy_version 95400 (0.0009) -[2023-10-10 16:24:51,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 195592192. Throughput: 0: 1816.4, 1: 1809.4. Samples: 48903340. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:24:51,076][75634] Avg episode reward: [(0, '37.260'), (1, '36.460')] -[2023-10-10 16:24:51,283][76542] Updated weights for policy 1, policy_version 95410 (0.0007) -[2023-10-10 16:24:51,650][76542] Updated weights for policy 1, policy_version 95420 (0.0007) -[2023-10-10 16:24:53,604][76543] Updated weights for policy 0, policy_version 95623 (0.0009) -[2023-10-10 16:24:53,988][76543] Updated weights for policy 0, policy_version 95633 (0.0009) -[2023-10-10 16:24:54,353][76543] Updated weights for policy 0, policy_version 95643 (0.0008) -[2023-10-10 16:24:55,409][76542] Updated weights for policy 1, policy_version 95430 (0.0007) -[2023-10-10 16:24:55,777][76542] Updated weights for policy 1, policy_version 95440 (0.0008) -[2023-10-10 16:24:56,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 195657728. Throughput: 0: 1823.8, 1: 1805.7. Samples: 48925136. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:24:56,077][75634] Avg episode reward: [(0, '33.800'), (1, '35.830')] -[2023-10-10 16:24:56,146][76542] Updated weights for policy 1, policy_version 95450 (0.0008) -[2023-10-10 16:24:57,930][76543] Updated weights for policy 0, policy_version 95653 (0.0010) -[2023-10-10 16:24:58,292][76543] Updated weights for policy 0, policy_version 95663 (0.0009) -[2023-10-10 16:24:58,667][76543] Updated weights for policy 0, policy_version 95673 (0.0008) -[2023-10-10 16:24:59,784][76542] Updated weights for policy 1, policy_version 95460 (0.0007) -[2023-10-10 16:25:00,155][76542] Updated weights for policy 1, policy_version 95470 (0.0010) -[2023-10-10 16:25:00,517][76542] Updated weights for policy 1, policy_version 95480 (0.0009) -[2023-10-10 16:25:01,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 195756032. Throughput: 0: 1825.2, 1: 1808.0. Samples: 48946286. Policy #0 lag: (min: 7.0, avg: 13.9, max: 39.0) -[2023-10-10 16:25:01,077][75634] Avg episode reward: [(0, '31.080'), (1, '38.420')] -[2023-10-10 16:25:02,369][76543] Updated weights for policy 0, policy_version 95683 (0.0010) -[2023-10-10 16:25:02,748][76543] Updated weights for policy 0, policy_version 95693 (0.0009) -[2023-10-10 16:25:03,116][76543] Updated weights for policy 0, policy_version 95703 (0.0009) -[2023-10-10 16:25:04,277][76542] Updated weights for policy 1, policy_version 95490 (0.0010) -[2023-10-10 16:25:04,636][76542] Updated weights for policy 1, policy_version 95500 (0.0009) -[2023-10-10 16:25:05,002][76542] Updated weights for policy 1, policy_version 95510 (0.0010) -[2023-10-10 16:25:05,368][76542] Updated weights for policy 1, policy_version 95520 (0.0008) -[2023-10-10 16:25:06,076][75634] Fps is (10 sec: 16384.5, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 195821568. Throughput: 0: 1825.0, 1: 1806.7. Samples: 48957882. Policy #0 lag: (min: 7.0, avg: 13.9, max: 39.0) -[2023-10-10 16:25:06,076][75634] Avg episode reward: [(0, '33.290'), (1, '33.870')] -[2023-10-10 16:25:06,776][76543] Updated weights for policy 0, policy_version 95713 (0.0007) -[2023-10-10 16:25:07,145][76543] Updated weights for policy 0, policy_version 95723 (0.0009) -[2023-10-10 16:25:07,524][76543] Updated weights for policy 0, policy_version 95733 (0.0009) -[2023-10-10 16:25:07,888][76543] Updated weights for policy 0, policy_version 95743 (0.0008) -[2023-10-10 16:25:09,257][76542] Updated weights for policy 1, policy_version 95530 (0.0007) -[2023-10-10 16:25:09,616][76542] Updated weights for policy 1, policy_version 95540 (0.0010) -[2023-10-10 16:25:09,995][76542] Updated weights for policy 1, policy_version 95550 (0.0009) -[2023-10-10 16:25:11,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14662.3). Total num frames: 195887104. Throughput: 0: 1826.1, 1: 1809.1. Samples: 48979182. Policy #0 lag: (min: 7.0, avg: 13.9, max: 39.0) -[2023-10-10 16:25:11,077][75634] Avg episode reward: [(0, '35.760'), (1, '37.620')] -[2023-10-10 16:25:11,535][76543] Updated weights for policy 0, policy_version 95753 (0.0008) -[2023-10-10 16:25:11,905][76543] Updated weights for policy 0, policy_version 95763 (0.0007) -[2023-10-10 16:25:12,288][76543] Updated weights for policy 0, policy_version 95773 (0.0007) -[2023-10-10 16:25:13,815][76542] Updated weights for policy 1, policy_version 95560 (0.0008) -[2023-10-10 16:25:14,203][76542] Updated weights for policy 1, policy_version 95570 (0.0009) -[2023-10-10 16:25:14,571][76542] Updated weights for policy 1, policy_version 95580 (0.0009) -[2023-10-10 16:25:16,047][76543] Updated weights for policy 0, policy_version 95783 (0.0009) -[2023-10-10 16:25:16,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 195952640. Throughput: 0: 1827.3, 1: 1794.3. Samples: 49001188. Policy #0 lag: (min: 7.0, avg: 13.9, max: 39.0) -[2023-10-10 16:25:16,076][75634] Avg episode reward: [(0, '33.830'), (1, '41.150')] -[2023-10-10 16:25:16,430][76543] Updated weights for policy 0, policy_version 95793 (0.0011) -[2023-10-10 16:25:16,798][76543] Updated weights for policy 0, policy_version 95803 (0.0009) -[2023-10-10 16:25:18,119][76542] Updated weights for policy 1, policy_version 95590 (0.0008) -[2023-10-10 16:25:18,482][76542] Updated weights for policy 1, policy_version 95600 (0.0008) -[2023-10-10 16:25:18,846][76542] Updated weights for policy 1, policy_version 95610 (0.0008) -[2023-10-10 16:25:20,238][76543] Updated weights for policy 0, policy_version 95813 (0.0009) -[2023-10-10 16:25:20,610][76543] Updated weights for policy 0, policy_version 95823 (0.0008) -[2023-10-10 16:25:20,990][76543] Updated weights for policy 0, policy_version 95833 (0.0007) -[2023-10-10 16:25:21,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 196018176. Throughput: 0: 1823.1, 1: 1810.2. Samples: 49011562. Policy #0 lag: (min: 7.0, avg: 13.9, max: 39.0) -[2023-10-10 16:25:21,077][75634] Avg episode reward: [(0, '34.030'), (1, '40.210')] -[2023-10-10 16:25:22,524][76542] Updated weights for policy 1, policy_version 95620 (0.0009) -[2023-10-10 16:25:22,895][76542] Updated weights for policy 1, policy_version 95630 (0.0009) -[2023-10-10 16:25:23,254][76542] Updated weights for policy 1, policy_version 95640 (0.0007) -[2023-10-10 16:25:24,736][76543] Updated weights for policy 0, policy_version 95843 (0.0008) -[2023-10-10 16:25:25,106][76543] Updated weights for policy 0, policy_version 95853 (0.0010) -[2023-10-10 16:25:25,482][76543] Updated weights for policy 0, policy_version 95863 (0.0009) -[2023-10-10 16:25:26,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 196116480. Throughput: 0: 1829.6, 1: 1800.3. Samples: 49034228. Policy #0 lag: (min: 7.0, avg: 13.9, max: 39.0) -[2023-10-10 16:25:26,077][75634] Avg episode reward: [(0, '34.490'), (1, '39.010')] -[2023-10-10 16:25:26,952][76542] Updated weights for policy 1, policy_version 95650 (0.0010) -[2023-10-10 16:25:27,316][76542] Updated weights for policy 1, policy_version 95660 (0.0009) -[2023-10-10 16:25:27,695][76542] Updated weights for policy 1, policy_version 95670 (0.0007) -[2023-10-10 16:25:28,061][76542] Updated weights for policy 1, policy_version 95680 (0.0010) -[2023-10-10 16:25:29,099][76543] Updated weights for policy 0, policy_version 95873 (0.0009) -[2023-10-10 16:25:29,465][76543] Updated weights for policy 0, policy_version 95883 (0.0009) -[2023-10-10 16:25:29,831][76543] Updated weights for policy 0, policy_version 95893 (0.0009) -[2023-10-10 16:25:30,198][76543] Updated weights for policy 0, policy_version 95903 (0.0008) -[2023-10-10 16:25:31,076][75634] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 196182016. Throughput: 0: 1825.6, 1: 1796.3. Samples: 49055576. Policy #0 lag: (min: 7.0, avg: 13.9, max: 39.0) -[2023-10-10 16:25:31,077][75634] Avg episode reward: [(0, '37.540'), (1, '38.660')] -[2023-10-10 16:25:31,848][76542] Updated weights for policy 1, policy_version 95690 (0.0010) -[2023-10-10 16:25:32,219][76542] Updated weights for policy 1, policy_version 95700 (0.0008) -[2023-10-10 16:25:32,594][76542] Updated weights for policy 1, policy_version 95710 (0.0007) -[2023-10-10 16:25:33,916][76543] Updated weights for policy 0, policy_version 95913 (0.0007) -[2023-10-10 16:25:34,293][76543] Updated weights for policy 0, policy_version 95923 (0.0009) -[2023-10-10 16:25:34,648][76543] Updated weights for policy 0, policy_version 95933 (0.0009) -[2023-10-10 16:25:36,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 196247552. Throughput: 0: 1834.3, 1: 1795.7. Samples: 49066690. Policy #0 lag: (min: 7.0, avg: 13.9, max: 39.0) -[2023-10-10 16:25:36,076][75634] Avg episode reward: [(0, '37.650'), (1, '39.070')] -[2023-10-10 16:25:36,243][76542] Updated weights for policy 1, policy_version 95720 (0.0007) -[2023-10-10 16:25:36,619][76542] Updated weights for policy 1, policy_version 95730 (0.0008) -[2023-10-10 16:25:36,983][76542] Updated weights for policy 1, policy_version 95740 (0.0008) -[2023-10-10 16:25:38,263][76543] Updated weights for policy 0, policy_version 95943 (0.0009) -[2023-10-10 16:25:38,637][76543] Updated weights for policy 0, policy_version 95953 (0.0010) -[2023-10-10 16:25:39,009][76543] Updated weights for policy 0, policy_version 95963 (0.0010) -[2023-10-10 16:25:40,658][76542] Updated weights for policy 1, policy_version 95750 (0.0008) -[2023-10-10 16:25:41,022][76542] Updated weights for policy 1, policy_version 95760 (0.0007) -[2023-10-10 16:25:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 196313088. Throughput: 0: 1818.6, 1: 1805.2. Samples: 49088206. Policy #0 lag: (min: 7.0, avg: 13.9, max: 39.0) -[2023-10-10 16:25:41,077][75634] Avg episode reward: [(0, '37.330'), (1, '32.750')] -[2023-10-10 16:25:41,395][76542] Updated weights for policy 1, policy_version 95770 (0.0007) -[2023-10-10 16:25:42,682][76543] Updated weights for policy 0, policy_version 95973 (0.0010) -[2023-10-10 16:25:43,047][76543] Updated weights for policy 0, policy_version 95983 (0.0009) -[2023-10-10 16:25:43,415][76543] Updated weights for policy 0, policy_version 95993 (0.0008) -[2023-10-10 16:25:44,936][76542] Updated weights for policy 1, policy_version 95780 (0.0009) -[2023-10-10 16:25:45,303][76542] Updated weights for policy 1, policy_version 95790 (0.0010) -[2023-10-10 16:25:45,669][76542] Updated weights for policy 1, policy_version 95800 (0.0008) -[2023-10-10 16:25:46,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 196411392. Throughput: 0: 1826.9, 1: 1815.9. Samples: 49110208. Policy #0 lag: (min: 7.0, avg: 13.9, max: 39.0) -[2023-10-10 16:25:46,076][75634] Avg episode reward: [(0, '37.760'), (1, '28.220')] -[2023-10-10 16:25:47,017][76543] Updated weights for policy 0, policy_version 96003 (0.0007) -[2023-10-10 16:25:47,392][76543] Updated weights for policy 0, policy_version 96013 (0.0010) -[2023-10-10 16:25:47,758][76543] Updated weights for policy 0, policy_version 96023 (0.0007) -[2023-10-10 16:25:49,398][76542] Updated weights for policy 1, policy_version 95810 (0.0009) -[2023-10-10 16:25:49,760][76542] Updated weights for policy 1, policy_version 95820 (0.0010) -[2023-10-10 16:25:50,125][76542] Updated weights for policy 1, policy_version 95830 (0.0007) -[2023-10-10 16:25:50,502][76542] Updated weights for policy 1, policy_version 95840 (0.0007) -[2023-10-10 16:25:51,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 196476928. Throughput: 0: 1819.6, 1: 1811.2. Samples: 49121272. Policy #0 lag: (min: 7.0, avg: 13.9, max: 39.0) -[2023-10-10 16:25:51,077][75634] Avg episode reward: [(0, '37.880'), (1, '30.740')] -[2023-10-10 16:25:51,378][76543] Updated weights for policy 0, policy_version 96033 (0.0008) -[2023-10-10 16:25:51,751][76543] Updated weights for policy 0, policy_version 96043 (0.0007) -[2023-10-10 16:25:52,121][76543] Updated weights for policy 0, policy_version 96053 (0.0008) -[2023-10-10 16:25:52,504][76543] Updated weights for policy 0, policy_version 96063 (0.0008) -[2023-10-10 16:25:54,226][76542] Updated weights for policy 1, policy_version 95850 (0.0008) -[2023-10-10 16:25:54,585][76542] Updated weights for policy 1, policy_version 95860 (0.0009) -[2023-10-10 16:25:54,962][76542] Updated weights for policy 1, policy_version 95870 (0.0010) -[2023-10-10 16:25:56,044][76543] Updated weights for policy 0, policy_version 96073 (0.0008) -[2023-10-10 16:25:56,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 196542464. Throughput: 0: 1832.4, 1: 1817.8. Samples: 49143440. Policy #0 lag: (min: 7.0, avg: 13.9, max: 39.0) -[2023-10-10 16:25:56,076][75634] Avg episode reward: [(0, '38.370'), (1, '31.580')] -[2023-10-10 16:25:56,428][76543] Updated weights for policy 0, policy_version 96083 (0.0008) -[2023-10-10 16:25:56,795][76543] Updated weights for policy 0, policy_version 96093 (0.0008) -[2023-10-10 16:25:58,599][76542] Updated weights for policy 1, policy_version 95880 (0.0011) -[2023-10-10 16:25:58,973][76542] Updated weights for policy 1, policy_version 95890 (0.0010) -[2023-10-10 16:25:59,337][76542] Updated weights for policy 1, policy_version 95900 (0.0010) -[2023-10-10 16:26:00,467][76543] Updated weights for policy 0, policy_version 96103 (0.0008) -[2023-10-10 16:26:00,832][76543] Updated weights for policy 0, policy_version 96113 (0.0007) -[2023-10-10 16:26:01,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 196608000. Throughput: 0: 1835.2, 1: 1828.4. Samples: 49166048. Policy #0 lag: (min: 7.0, avg: 13.9, max: 39.0) -[2023-10-10 16:26:01,076][75634] Avg episode reward: [(0, '40.450'), (1, '35.860')] -[2023-10-10 16:26:01,202][76543] Updated weights for policy 0, policy_version 96123 (0.0008) -[2023-10-10 16:26:02,930][76542] Updated weights for policy 1, policy_version 95910 (0.0009) -[2023-10-10 16:26:03,303][76542] Updated weights for policy 1, policy_version 95920 (0.0009) -[2023-10-10 16:26:03,680][76542] Updated weights for policy 1, policy_version 95930 (0.0008) -[2023-10-10 16:26:05,067][76543] Updated weights for policy 0, policy_version 96133 (0.0010) -[2023-10-10 16:26:05,451][76543] Updated weights for policy 0, policy_version 96143 (0.0008) -[2023-10-10 16:26:05,825][76543] Updated weights for policy 0, policy_version 96153 (0.0007) -[2023-10-10 16:26:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 196673536. Throughput: 0: 1838.1, 1: 1820.7. Samples: 49176210. Policy #0 lag: (min: 8.0, avg: 35.9, max: 40.0) -[2023-10-10 16:26:06,076][75634] Avg episode reward: [(0, '44.810'), (1, '36.840')] -[2023-10-10 16:26:07,253][76542] Updated weights for policy 1, policy_version 95940 (0.0009) -[2023-10-10 16:26:07,628][76542] Updated weights for policy 1, policy_version 95950 (0.0008) -[2023-10-10 16:26:07,994][76542] Updated weights for policy 1, policy_version 95960 (0.0008) -[2023-10-10 16:26:09,539][76543] Updated weights for policy 0, policy_version 96163 (0.0009) -[2023-10-10 16:26:09,899][76543] Updated weights for policy 0, policy_version 96173 (0.0009) -[2023-10-10 16:26:10,270][76543] Updated weights for policy 0, policy_version 96183 (0.0007) -[2023-10-10 16:26:11,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 196771840. Throughput: 0: 1829.3, 1: 1824.5. Samples: 49198652. Policy #0 lag: (min: 8.0, avg: 35.9, max: 40.0) -[2023-10-10 16:26:11,077][75634] Avg episode reward: [(0, '44.490'), (1, '38.020')] -[2023-10-10 16:26:11,541][76542] Updated weights for policy 1, policy_version 95970 (0.0011) -[2023-10-10 16:26:11,917][76542] Updated weights for policy 1, policy_version 95980 (0.0010) -[2023-10-10 16:26:12,277][76542] Updated weights for policy 1, policy_version 95990 (0.0010) -[2023-10-10 16:26:12,648][76542] Updated weights for policy 1, policy_version 96000 (0.0011) -[2023-10-10 16:26:13,936][76543] Updated weights for policy 0, policy_version 96193 (0.0007) -[2023-10-10 16:26:14,293][76543] Updated weights for policy 0, policy_version 96203 (0.0007) -[2023-10-10 16:26:14,665][76543] Updated weights for policy 0, policy_version 96213 (0.0009) -[2023-10-10 16:26:15,032][76543] Updated weights for policy 0, policy_version 96223 (0.0007) -[2023-10-10 16:26:16,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 196837376. Throughput: 0: 1828.7, 1: 1823.1. Samples: 49219906. Policy #0 lag: (min: 8.0, avg: 35.9, max: 40.0) -[2023-10-10 16:26:16,076][75634] Avg episode reward: [(0, '41.670'), (1, '40.000')] -[2023-10-10 16:26:16,536][76542] Updated weights for policy 1, policy_version 96010 (0.0008) -[2023-10-10 16:26:16,910][76542] Updated weights for policy 1, policy_version 96020 (0.0007) -[2023-10-10 16:26:17,285][76542] Updated weights for policy 1, policy_version 96030 (0.0008) -[2023-10-10 16:26:18,601][76543] Updated weights for policy 0, policy_version 96233 (0.0009) -[2023-10-10 16:26:18,978][76543] Updated weights for policy 0, policy_version 96243 (0.0008) -[2023-10-10 16:26:19,352][76543] Updated weights for policy 0, policy_version 96253 (0.0008) -[2023-10-10 16:26:20,878][76542] Updated weights for policy 1, policy_version 96040 (0.0009) -[2023-10-10 16:26:21,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 196902912. Throughput: 0: 1831.2, 1: 1830.1. Samples: 49231448. Policy #0 lag: (min: 8.0, avg: 35.9, max: 40.0) -[2023-10-10 16:26:21,077][75634] Avg episode reward: [(0, '38.140'), (1, '38.140')] -[2023-10-10 16:26:21,243][76542] Updated weights for policy 1, policy_version 96050 (0.0009) -[2023-10-10 16:26:21,609][76542] Updated weights for policy 1, policy_version 96060 (0.0007) -[2023-10-10 16:26:23,043][76543] Updated weights for policy 0, policy_version 96263 (0.0007) -[2023-10-10 16:26:23,412][76543] Updated weights for policy 0, policy_version 96273 (0.0007) -[2023-10-10 16:26:23,767][76543] Updated weights for policy 0, policy_version 96283 (0.0008) -[2023-10-10 16:26:25,191][76542] Updated weights for policy 1, policy_version 96070 (0.0008) -[2023-10-10 16:26:25,554][76542] Updated weights for policy 1, policy_version 96080 (0.0008) -[2023-10-10 16:26:25,927][76542] Updated weights for policy 1, policy_version 96090 (0.0008) -[2023-10-10 16:26:26,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 196968448. Throughput: 0: 1832.5, 1: 1824.3. Samples: 49252762. Policy #0 lag: (min: 8.0, avg: 35.9, max: 40.0) -[2023-10-10 16:26:26,077][75634] Avg episode reward: [(0, '35.740'), (1, '37.030')] -[2023-10-10 16:26:27,420][76543] Updated weights for policy 0, policy_version 96293 (0.0009) -[2023-10-10 16:26:27,784][76543] Updated weights for policy 0, policy_version 96303 (0.0007) -[2023-10-10 16:26:28,161][76543] Updated weights for policy 0, policy_version 96313 (0.0011) -[2023-10-10 16:26:29,612][76542] Updated weights for policy 1, policy_version 96100 (0.0007) -[2023-10-10 16:26:29,978][76542] Updated weights for policy 1, policy_version 96110 (0.0009) -[2023-10-10 16:26:30,350][76542] Updated weights for policy 1, policy_version 96120 (0.0008) -[2023-10-10 16:26:31,076][75634] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 197066752. Throughput: 0: 1831.7, 1: 1813.0. Samples: 49274222. Policy #0 lag: (min: 8.0, avg: 35.9, max: 40.0) -[2023-10-10 16:26:31,077][75634] Avg episode reward: [(0, '36.070'), (1, '34.830')] -[2023-10-10 16:26:31,088][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000096320_98631680.pth... -[2023-10-10 16:26:31,088][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000096128_98435072.pth... -[2023-10-10 16:26:31,118][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000094624_96894976.pth -[2023-10-10 16:26:31,128][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000094400_96665600.pth -[2023-10-10 16:26:31,913][76543] Updated weights for policy 0, policy_version 96323 (0.0010) -[2023-10-10 16:26:32,284][76543] Updated weights for policy 0, policy_version 96333 (0.0007) -[2023-10-10 16:26:32,648][76543] Updated weights for policy 0, policy_version 96343 (0.0007) -[2023-10-10 16:26:34,157][76542] Updated weights for policy 1, policy_version 96130 (0.0008) -[2023-10-10 16:26:34,522][76542] Updated weights for policy 1, policy_version 96140 (0.0010) -[2023-10-10 16:26:34,887][76542] Updated weights for policy 1, policy_version 96150 (0.0010) -[2023-10-10 16:26:35,254][76542] Updated weights for policy 1, policy_version 96160 (0.0010) -[2023-10-10 16:26:36,076][75634] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 197132288. Throughput: 0: 1831.5, 1: 1822.2. Samples: 49285688. Policy #0 lag: (min: 8.0, avg: 35.9, max: 40.0) -[2023-10-10 16:26:36,076][75634] Avg episode reward: [(0, '32.700'), (1, '33.240')] -[2023-10-10 16:26:36,117][76543] Updated weights for policy 0, policy_version 96353 (0.0009) -[2023-10-10 16:26:36,483][76543] Updated weights for policy 0, policy_version 96363 (0.0011) -[2023-10-10 16:26:36,858][76543] Updated weights for policy 0, policy_version 96373 (0.0008) -[2023-10-10 16:26:37,227][76543] Updated weights for policy 0, policy_version 96383 (0.0008) -[2023-10-10 16:26:39,097][76542] Updated weights for policy 1, policy_version 96170 (0.0007) -[2023-10-10 16:26:39,457][76542] Updated weights for policy 1, policy_version 96180 (0.0007) -[2023-10-10 16:26:39,825][76542] Updated weights for policy 1, policy_version 96190 (0.0009) -[2023-10-10 16:26:41,042][76543] Updated weights for policy 0, policy_version 96393 (0.0008) -[2023-10-10 16:26:41,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 197197824. Throughput: 0: 1826.5, 1: 1813.9. Samples: 49307258. Policy #0 lag: (min: 8.0, avg: 35.9, max: 40.0) -[2023-10-10 16:26:41,077][75634] Avg episode reward: [(0, '32.230'), (1, '32.380')] -[2023-10-10 16:26:41,421][76543] Updated weights for policy 0, policy_version 96403 (0.0011) -[2023-10-10 16:26:41,804][76543] Updated weights for policy 0, policy_version 96413 (0.0010) -[2023-10-10 16:26:43,601][76542] Updated weights for policy 1, policy_version 96200 (0.0009) -[2023-10-10 16:26:43,968][76542] Updated weights for policy 1, policy_version 96210 (0.0008) -[2023-10-10 16:26:44,331][76542] Updated weights for policy 1, policy_version 96220 (0.0008) -[2023-10-10 16:26:45,454][76543] Updated weights for policy 0, policy_version 96423 (0.0010) -[2023-10-10 16:26:45,830][76543] Updated weights for policy 0, policy_version 96433 (0.0008) -[2023-10-10 16:26:46,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 197263360. Throughput: 0: 1826.7, 1: 1811.3. Samples: 49329760. Policy #0 lag: (min: 8.0, avg: 35.9, max: 40.0) -[2023-10-10 16:26:46,077][75634] Avg episode reward: [(0, '34.660'), (1, '33.910')] -[2023-10-10 16:26:46,213][76543] Updated weights for policy 0, policy_version 96443 (0.0007) -[2023-10-10 16:26:47,988][76542] Updated weights for policy 1, policy_version 96230 (0.0008) -[2023-10-10 16:26:48,360][76542] Updated weights for policy 1, policy_version 96240 (0.0008) -[2023-10-10 16:26:48,726][76542] Updated weights for policy 1, policy_version 96250 (0.0008) -[2023-10-10 16:26:49,872][76543] Updated weights for policy 0, policy_version 96453 (0.0008) -[2023-10-10 16:26:50,273][76543] Updated weights for policy 0, policy_version 96463 (0.0007) -[2023-10-10 16:26:50,637][76543] Updated weights for policy 0, policy_version 96473 (0.0009) -[2023-10-10 16:26:51,076][75634] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 197361664. Throughput: 0: 1826.6, 1: 1812.9. Samples: 49339988. Policy #0 lag: (min: 8.0, avg: 35.9, max: 40.0) -[2023-10-10 16:26:51,076][75634] Avg episode reward: [(0, '34.760'), (1, '33.670')] -[2023-10-10 16:26:52,454][76542] Updated weights for policy 1, policy_version 96260 (0.0008) -[2023-10-10 16:26:52,816][76542] Updated weights for policy 1, policy_version 96270 (0.0010) -[2023-10-10 16:26:53,185][76542] Updated weights for policy 1, policy_version 96280 (0.0009) -[2023-10-10 16:26:54,335][76543] Updated weights for policy 0, policy_version 96483 (0.0009) -[2023-10-10 16:26:54,717][76543] Updated weights for policy 0, policy_version 96493 (0.0008) -[2023-10-10 16:26:55,086][76543] Updated weights for policy 0, policy_version 96503 (0.0008) -[2023-10-10 16:26:56,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 197427200. Throughput: 0: 1828.4, 1: 1813.7. Samples: 49362546. Policy #0 lag: (min: 8.0, avg: 35.9, max: 40.0) -[2023-10-10 16:26:56,076][75634] Avg episode reward: [(0, '36.670'), (1, '36.550')] -[2023-10-10 16:26:56,678][76542] Updated weights for policy 1, policy_version 96290 (0.0009) -[2023-10-10 16:26:57,048][76542] Updated weights for policy 1, policy_version 96300 (0.0011) -[2023-10-10 16:26:57,410][76542] Updated weights for policy 1, policy_version 96310 (0.0009) -[2023-10-10 16:26:57,784][76542] Updated weights for policy 1, policy_version 96320 (0.0009) -[2023-10-10 16:26:58,872][76543] Updated weights for policy 0, policy_version 96513 (0.0008) -[2023-10-10 16:26:59,234][76543] Updated weights for policy 0, policy_version 96523 (0.0010) -[2023-10-10 16:26:59,596][76543] Updated weights for policy 0, policy_version 96533 (0.0009) -[2023-10-10 16:26:59,979][76543] Updated weights for policy 0, policy_version 96543 (0.0010) -[2023-10-10 16:27:01,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 197492736. Throughput: 0: 1825.4, 1: 1820.1. Samples: 49383954. Policy #0 lag: (min: 21.0, avg: 24.1, max: 53.0) -[2023-10-10 16:27:01,076][75634] Avg episode reward: [(0, '35.650'), (1, '35.590')] -[2023-10-10 16:27:01,531][76542] Updated weights for policy 1, policy_version 96330 (0.0009) -[2023-10-10 16:27:01,904][76542] Updated weights for policy 1, policy_version 96340 (0.0007) -[2023-10-10 16:27:02,279][76542] Updated weights for policy 1, policy_version 96350 (0.0009) -[2023-10-10 16:27:03,685][76543] Updated weights for policy 0, policy_version 96553 (0.0007) -[2023-10-10 16:27:04,060][76543] Updated weights for policy 0, policy_version 96563 (0.0010) -[2023-10-10 16:27:04,432][76543] Updated weights for policy 0, policy_version 96573 (0.0010) -[2023-10-10 16:27:05,913][76542] Updated weights for policy 1, policy_version 96360 (0.0007) -[2023-10-10 16:27:06,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 197558272. Throughput: 0: 1827.5, 1: 1816.8. Samples: 49395440. Policy #0 lag: (min: 21.0, avg: 24.1, max: 53.0) -[2023-10-10 16:27:06,076][75634] Avg episode reward: [(0, '32.570'), (1, '36.900')] -[2023-10-10 16:27:06,284][76542] Updated weights for policy 1, policy_version 96370 (0.0007) -[2023-10-10 16:27:06,657][76542] Updated weights for policy 1, policy_version 96380 (0.0007) -[2023-10-10 16:27:08,047][76543] Updated weights for policy 0, policy_version 96583 (0.0008) -[2023-10-10 16:27:08,420][76543] Updated weights for policy 0, policy_version 96593 (0.0008) -[2023-10-10 16:27:08,793][76543] Updated weights for policy 0, policy_version 96603 (0.0008) -[2023-10-10 16:27:10,366][76542] Updated weights for policy 1, policy_version 96390 (0.0007) -[2023-10-10 16:27:10,734][76542] Updated weights for policy 1, policy_version 96400 (0.0007) -[2023-10-10 16:27:11,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 197623808. Throughput: 0: 1826.9, 1: 1823.8. Samples: 49417046. Policy #0 lag: (min: 21.0, avg: 24.1, max: 53.0) -[2023-10-10 16:27:11,077][75634] Avg episode reward: [(0, '35.480'), (1, '37.300')] -[2023-10-10 16:27:11,102][76542] Updated weights for policy 1, policy_version 96410 (0.0007) -[2023-10-10 16:27:12,374][76543] Updated weights for policy 0, policy_version 96613 (0.0008) -[2023-10-10 16:27:12,750][76543] Updated weights for policy 0, policy_version 96623 (0.0008) -[2023-10-10 16:27:13,119][76543] Updated weights for policy 0, policy_version 96633 (0.0009) -[2023-10-10 16:27:14,794][76542] Updated weights for policy 1, policy_version 96420 (0.0008) -[2023-10-10 16:27:15,156][76542] Updated weights for policy 1, policy_version 96430 (0.0009) -[2023-10-10 16:27:15,532][76542] Updated weights for policy 1, policy_version 96440 (0.0008) -[2023-10-10 16:27:16,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 197722112. Throughput: 0: 1828.7, 1: 1826.6. Samples: 49438708. Policy #0 lag: (min: 21.0, avg: 24.1, max: 53.0) -[2023-10-10 16:27:16,077][75634] Avg episode reward: [(0, '38.390'), (1, '44.300')] -[2023-10-10 16:27:16,665][76543] Updated weights for policy 0, policy_version 96643 (0.0011) -[2023-10-10 16:27:17,039][76543] Updated weights for policy 0, policy_version 96653 (0.0010) -[2023-10-10 16:27:17,417][76543] Updated weights for policy 0, policy_version 96663 (0.0007) -[2023-10-10 16:27:19,165][76542] Updated weights for policy 1, policy_version 96450 (0.0007) -[2023-10-10 16:27:19,546][76542] Updated weights for policy 1, policy_version 96460 (0.0008) -[2023-10-10 16:27:19,906][76542] Updated weights for policy 1, policy_version 96470 (0.0009) -[2023-10-10 16:27:20,274][76542] Updated weights for policy 1, policy_version 96480 (0.0010) -[2023-10-10 16:27:21,024][76543] Updated weights for policy 0, policy_version 96673 (0.0010) -[2023-10-10 16:27:21,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 197787648. Throughput: 0: 1829.6, 1: 1821.6. Samples: 49449994. Policy #0 lag: (min: 21.0, avg: 24.1, max: 53.0) -[2023-10-10 16:27:21,077][75634] Avg episode reward: [(0, '35.410'), (1, '37.900')] -[2023-10-10 16:27:21,401][76543] Updated weights for policy 0, policy_version 96683 (0.0008) -[2023-10-10 16:27:21,777][76543] Updated weights for policy 0, policy_version 96693 (0.0007) -[2023-10-10 16:27:22,157][76543] Updated weights for policy 0, policy_version 96703 (0.0007) -[2023-10-10 16:27:23,923][76542] Updated weights for policy 1, policy_version 96490 (0.0010) -[2023-10-10 16:27:24,283][76542] Updated weights for policy 1, policy_version 96500 (0.0010) -[2023-10-10 16:27:24,645][76542] Updated weights for policy 1, policy_version 96510 (0.0011) -[2023-10-10 16:27:25,830][76543] Updated weights for policy 0, policy_version 96713 (0.0009) -[2023-10-10 16:27:26,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 197853184. Throughput: 0: 1829.7, 1: 1819.0. Samples: 49471446. Policy #0 lag: (min: 21.0, avg: 24.1, max: 53.0) -[2023-10-10 16:27:26,076][75634] Avg episode reward: [(0, '35.640'), (1, '33.570')] -[2023-10-10 16:27:26,195][76543] Updated weights for policy 0, policy_version 96723 (0.0008) -[2023-10-10 16:27:26,562][76543] Updated weights for policy 0, policy_version 96733 (0.0008) -[2023-10-10 16:27:28,416][76542] Updated weights for policy 1, policy_version 96520 (0.0009) -[2023-10-10 16:27:28,776][76542] Updated weights for policy 1, policy_version 96530 (0.0007) -[2023-10-10 16:27:29,134][76542] Updated weights for policy 1, policy_version 96540 (0.0008) -[2023-10-10 16:27:30,358][76543] Updated weights for policy 0, policy_version 96743 (0.0007) -[2023-10-10 16:27:30,719][76543] Updated weights for policy 0, policy_version 96753 (0.0008) -[2023-10-10 16:27:31,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 197918720. Throughput: 0: 1824.4, 1: 1831.4. Samples: 49494270. Policy #0 lag: (min: 21.0, avg: 24.1, max: 53.0) -[2023-10-10 16:27:31,076][75634] Avg episode reward: [(0, '36.360'), (1, '38.790')] -[2023-10-10 16:27:31,084][76543] Updated weights for policy 0, policy_version 96763 (0.0007) -[2023-10-10 16:27:32,904][76542] Updated weights for policy 1, policy_version 96550 (0.0009) -[2023-10-10 16:27:33,285][76542] Updated weights for policy 1, policy_version 96560 (0.0009) -[2023-10-10 16:27:33,652][76542] Updated weights for policy 1, policy_version 96570 (0.0007) -[2023-10-10 16:27:34,793][76543] Updated weights for policy 0, policy_version 96773 (0.0008) -[2023-10-10 16:27:35,176][76543] Updated weights for policy 0, policy_version 96783 (0.0008) -[2023-10-10 16:27:35,544][76543] Updated weights for policy 0, policy_version 96793 (0.0007) -[2023-10-10 16:27:36,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 198017024. Throughput: 0: 1829.3, 1: 1830.8. Samples: 49504696. Policy #0 lag: (min: 21.0, avg: 24.1, max: 53.0) -[2023-10-10 16:27:36,077][75634] Avg episode reward: [(0, '35.900'), (1, '36.850')] -[2023-10-10 16:27:37,347][76542] Updated weights for policy 1, policy_version 96580 (0.0008) -[2023-10-10 16:27:37,715][76542] Updated weights for policy 1, policy_version 96590 (0.0011) -[2023-10-10 16:27:38,081][76542] Updated weights for policy 1, policy_version 96600 (0.0009) -[2023-10-10 16:27:39,193][76543] Updated weights for policy 0, policy_version 96803 (0.0010) -[2023-10-10 16:27:39,560][76543] Updated weights for policy 0, policy_version 96813 (0.0008) -[2023-10-10 16:27:39,935][76543] Updated weights for policy 0, policy_version 96823 (0.0008) -[2023-10-10 16:27:41,076][75634] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 198082560. Throughput: 0: 1829.5, 1: 1831.5. Samples: 49527292. Policy #0 lag: (min: 21.0, avg: 24.1, max: 53.0) -[2023-10-10 16:27:41,077][75634] Avg episode reward: [(0, '39.510'), (1, '34.220')] -[2023-10-10 16:27:41,766][76542] Updated weights for policy 1, policy_version 96610 (0.0007) -[2023-10-10 16:27:42,139][76542] Updated weights for policy 1, policy_version 96620 (0.0007) -[2023-10-10 16:27:42,509][76542] Updated weights for policy 1, policy_version 96630 (0.0007) -[2023-10-10 16:27:42,875][76542] Updated weights for policy 1, policy_version 96640 (0.0009) -[2023-10-10 16:27:43,693][76543] Updated weights for policy 0, policy_version 96833 (0.0008) -[2023-10-10 16:27:44,060][76543] Updated weights for policy 0, policy_version 96843 (0.0007) -[2023-10-10 16:27:44,431][76543] Updated weights for policy 0, policy_version 96853 (0.0007) -[2023-10-10 16:27:44,798][76543] Updated weights for policy 0, policy_version 96863 (0.0009) -[2023-10-10 16:27:46,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 198148096. Throughput: 0: 1835.4, 1: 1825.8. Samples: 49548708. Policy #0 lag: (min: 21.0, avg: 24.1, max: 53.0) -[2023-10-10 16:27:46,077][75634] Avg episode reward: [(0, '42.110'), (1, '32.340')] -[2023-10-10 16:27:46,556][76542] Updated weights for policy 1, policy_version 96650 (0.0008) -[2023-10-10 16:27:46,918][76542] Updated weights for policy 1, policy_version 96660 (0.0008) -[2023-10-10 16:27:47,291][76542] Updated weights for policy 1, policy_version 96670 (0.0007) -[2023-10-10 16:27:48,355][76543] Updated weights for policy 0, policy_version 96873 (0.0009) -[2023-10-10 16:27:48,729][76543] Updated weights for policy 0, policy_version 96883 (0.0009) -[2023-10-10 16:27:49,101][76543] Updated weights for policy 0, policy_version 96893 (0.0008) -[2023-10-10 16:27:50,958][76542] Updated weights for policy 1, policy_version 96680 (0.0008) -[2023-10-10 16:27:51,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 198213632. Throughput: 0: 1827.2, 1: 1829.1. Samples: 49559976. Policy #0 lag: (min: 21.0, avg: 24.1, max: 53.0) -[2023-10-10 16:27:51,076][75634] Avg episode reward: [(0, '39.320'), (1, '37.080')] -[2023-10-10 16:27:51,317][76542] Updated weights for policy 1, policy_version 96690 (0.0009) -[2023-10-10 16:27:51,684][76542] Updated weights for policy 1, policy_version 96700 (0.0010) -[2023-10-10 16:27:52,821][76543] Updated weights for policy 0, policy_version 96903 (0.0009) -[2023-10-10 16:27:53,190][76543] Updated weights for policy 0, policy_version 96913 (0.0008) -[2023-10-10 16:27:53,562][76543] Updated weights for policy 0, policy_version 96923 (0.0008) -[2023-10-10 16:27:55,401][76542] Updated weights for policy 1, policy_version 96710 (0.0008) -[2023-10-10 16:27:55,765][76542] Updated weights for policy 1, policy_version 96720 (0.0007) -[2023-10-10 16:27:56,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14551.2). Total num frames: 198279168. Throughput: 0: 1831.1, 1: 1819.0. Samples: 49581298. Policy #0 lag: (min: 21.0, avg: 24.1, max: 53.0) -[2023-10-10 16:27:56,076][75634] Avg episode reward: [(0, '38.100'), (1, '39.620')] -[2023-10-10 16:27:56,137][76542] Updated weights for policy 1, policy_version 96730 (0.0007) -[2023-10-10 16:27:57,205][76543] Updated weights for policy 0, policy_version 96933 (0.0007) -[2023-10-10 16:27:57,574][76543] Updated weights for policy 0, policy_version 96943 (0.0007) -[2023-10-10 16:27:57,946][76543] Updated weights for policy 0, policy_version 96953 (0.0009) -[2023-10-10 16:27:59,679][76542] Updated weights for policy 1, policy_version 96740 (0.0008) -[2023-10-10 16:28:00,050][76542] Updated weights for policy 1, policy_version 96750 (0.0009) -[2023-10-10 16:28:00,416][76542] Updated weights for policy 1, policy_version 96760 (0.0009) -[2023-10-10 16:28:01,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 198377472. Throughput: 0: 1825.2, 1: 1820.9. Samples: 49602786. Policy #0 lag: (min: 21.0, avg: 24.1, max: 53.0) -[2023-10-10 16:28:01,076][75634] Avg episode reward: [(0, '39.280'), (1, '38.760')] -[2023-10-10 16:28:01,792][76543] Updated weights for policy 0, policy_version 96963 (0.0008) -[2023-10-10 16:28:02,164][76543] Updated weights for policy 0, policy_version 96973 (0.0007) -[2023-10-10 16:28:02,528][76543] Updated weights for policy 0, policy_version 96983 (0.0007) -[2023-10-10 16:28:04,247][76542] Updated weights for policy 1, policy_version 96770 (0.0008) -[2023-10-10 16:28:04,613][76542] Updated weights for policy 1, policy_version 96780 (0.0011) -[2023-10-10 16:28:04,983][76542] Updated weights for policy 1, policy_version 96790 (0.0009) -[2023-10-10 16:28:05,355][76542] Updated weights for policy 1, policy_version 96800 (0.0008) -[2023-10-10 16:28:06,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14662.3). Total num frames: 198443008. Throughput: 0: 1821.9, 1: 1823.1. Samples: 49614018. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 16:28:06,077][75634] Avg episode reward: [(0, '39.460'), (1, '35.020')] -[2023-10-10 16:28:06,121][76543] Updated weights for policy 0, policy_version 96993 (0.0008) -[2023-10-10 16:28:06,480][76543] Updated weights for policy 0, policy_version 97003 (0.0011) -[2023-10-10 16:28:06,857][76543] Updated weights for policy 0, policy_version 97013 (0.0007) -[2023-10-10 16:28:07,220][76543] Updated weights for policy 0, policy_version 97023 (0.0010) -[2023-10-10 16:28:09,058][76542] Updated weights for policy 1, policy_version 96810 (0.0008) -[2023-10-10 16:28:09,428][76542] Updated weights for policy 1, policy_version 96820 (0.0010) -[2023-10-10 16:28:09,794][76542] Updated weights for policy 1, policy_version 96830 (0.0009) -[2023-10-10 16:28:10,759][76543] Updated weights for policy 0, policy_version 97033 (0.0008) -[2023-10-10 16:28:11,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.7, 300 sec: 14551.2). Total num frames: 198508544. Throughput: 0: 1827.6, 1: 1827.5. Samples: 49635928. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 16:28:11,076][75634] Avg episode reward: [(0, '41.140'), (1, '32.920')] -[2023-10-10 16:28:11,121][76543] Updated weights for policy 0, policy_version 97043 (0.0010) -[2023-10-10 16:28:11,488][76543] Updated weights for policy 0, policy_version 97053 (0.0009) -[2023-10-10 16:28:13,424][76542] Updated weights for policy 1, policy_version 96840 (0.0011) -[2023-10-10 16:28:13,801][76542] Updated weights for policy 1, policy_version 96850 (0.0011) -[2023-10-10 16:28:14,167][76542] Updated weights for policy 1, policy_version 96860 (0.0008) -[2023-10-10 16:28:15,128][76543] Updated weights for policy 0, policy_version 97063 (0.0011) -[2023-10-10 16:28:15,491][76543] Updated weights for policy 0, policy_version 97073 (0.0008) -[2023-10-10 16:28:15,857][76543] Updated weights for policy 0, policy_version 97083 (0.0008) -[2023-10-10 16:28:16,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 198606848. Throughput: 0: 1819.5, 1: 1820.9. Samples: 49658086. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 16:28:16,076][75634] Avg episode reward: [(0, '40.400'), (1, '33.820')] -[2023-10-10 16:28:17,961][76542] Updated weights for policy 1, policy_version 96870 (0.0009) -[2023-10-10 16:28:18,350][76542] Updated weights for policy 1, policy_version 96880 (0.0010) -[2023-10-10 16:28:18,706][76542] Updated weights for policy 1, policy_version 96890 (0.0009) -[2023-10-10 16:28:19,627][76543] Updated weights for policy 0, policy_version 97093 (0.0009) -[2023-10-10 16:28:20,001][76543] Updated weights for policy 0, policy_version 97103 (0.0011) -[2023-10-10 16:28:20,374][76543] Updated weights for policy 0, policy_version 97113 (0.0010) -[2023-10-10 16:28:21,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 198672384. Throughput: 0: 1825.3, 1: 1817.1. Samples: 49668600. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 16:28:21,077][75634] Avg episode reward: [(0, '41.870'), (1, '31.710')] -[2023-10-10 16:28:22,372][76542] Updated weights for policy 1, policy_version 96900 (0.0009) -[2023-10-10 16:28:22,736][76542] Updated weights for policy 1, policy_version 96910 (0.0009) -[2023-10-10 16:28:23,112][76542] Updated weights for policy 1, policy_version 96920 (0.0007) -[2023-10-10 16:28:24,231][76543] Updated weights for policy 0, policy_version 97123 (0.0008) -[2023-10-10 16:28:24,617][76543] Updated weights for policy 0, policy_version 97133 (0.0008) -[2023-10-10 16:28:24,987][76543] Updated weights for policy 0, policy_version 97143 (0.0007) -[2023-10-10 16:28:26,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 198737920. Throughput: 0: 1818.6, 1: 1814.5. Samples: 49690784. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 16:28:26,077][75634] Avg episode reward: [(0, '38.500'), (1, '36.880')] -[2023-10-10 16:28:26,783][76542] Updated weights for policy 1, policy_version 96930 (0.0009) -[2023-10-10 16:28:27,151][76542] Updated weights for policy 1, policy_version 96940 (0.0007) -[2023-10-10 16:28:27,521][76542] Updated weights for policy 1, policy_version 96950 (0.0009) -[2023-10-10 16:28:27,891][76542] Updated weights for policy 1, policy_version 96960 (0.0010) -[2023-10-10 16:28:28,449][76543] Updated weights for policy 0, policy_version 97153 (0.0007) -[2023-10-10 16:28:28,813][76543] Updated weights for policy 0, policy_version 97163 (0.0007) -[2023-10-10 16:28:29,188][76543] Updated weights for policy 0, policy_version 97173 (0.0007) -[2023-10-10 16:28:29,555][76543] Updated weights for policy 0, policy_version 97183 (0.0007) -[2023-10-10 16:28:31,076][75634] Fps is (10 sec: 13106.8, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 198803456. Throughput: 0: 1817.2, 1: 1819.1. Samples: 49712344. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 16:28:31,077][75634] Avg episode reward: [(0, '38.760'), (1, '38.390')] -[2023-10-10 16:28:31,088][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000097184_99516416.pth... -[2023-10-10 16:28:31,128][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000095488_97779712.pth -[2023-10-10 16:28:31,521][76542] Updated weights for policy 1, policy_version 96970 (0.0007) -[2023-10-10 16:28:31,895][76542] Updated weights for policy 1, policy_version 96980 (0.0010) -[2023-10-10 16:28:32,260][76542] Updated weights for policy 1, policy_version 96990 (0.0010) -[2023-10-10 16:28:32,335][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000096992_99319808.pth... -[2023-10-10 16:28:32,364][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000095264_97550336.pth -[2023-10-10 16:28:33,201][76543] Updated weights for policy 0, policy_version 97193 (0.0010) -[2023-10-10 16:28:33,568][76543] Updated weights for policy 0, policy_version 97203 (0.0008) -[2023-10-10 16:28:33,935][76543] Updated weights for policy 0, policy_version 97213 (0.0007) -[2023-10-10 16:28:36,076][75634] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 198868992. Throughput: 0: 1813.5, 1: 1816.9. Samples: 49723342. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 16:28:36,077][75634] Avg episode reward: [(0, '37.420'), (1, '39.310')] -[2023-10-10 16:28:36,108][76542] Updated weights for policy 1, policy_version 97000 (0.0009) -[2023-10-10 16:28:36,482][76542] Updated weights for policy 1, policy_version 97010 (0.0008) -[2023-10-10 16:28:36,853][76542] Updated weights for policy 1, policy_version 97020 (0.0008) -[2023-10-10 16:28:37,661][76543] Updated weights for policy 0, policy_version 97223 (0.0008) -[2023-10-10 16:28:38,031][76543] Updated weights for policy 0, policy_version 97233 (0.0008) -[2023-10-10 16:28:38,397][76543] Updated weights for policy 0, policy_version 97243 (0.0007) -[2023-10-10 16:28:40,546][76542] Updated weights for policy 1, policy_version 97030 (0.0010) -[2023-10-10 16:28:40,904][76542] Updated weights for policy 1, policy_version 97040 (0.0007) -[2023-10-10 16:28:41,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 198934528. Throughput: 0: 1819.8, 1: 1816.5. Samples: 49744934. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 16:28:41,077][75634] Avg episode reward: [(0, '37.020'), (1, '39.040')] -[2023-10-10 16:28:41,281][76542] Updated weights for policy 1, policy_version 97050 (0.0007) -[2023-10-10 16:28:42,179][76543] Updated weights for policy 0, policy_version 97253 (0.0009) -[2023-10-10 16:28:42,548][76543] Updated weights for policy 0, policy_version 97263 (0.0009) -[2023-10-10 16:28:42,916][76543] Updated weights for policy 0, policy_version 97273 (0.0010) -[2023-10-10 16:28:44,854][76542] Updated weights for policy 1, policy_version 97060 (0.0008) -[2023-10-10 16:28:45,223][76542] Updated weights for policy 1, policy_version 97070 (0.0009) -[2023-10-10 16:28:45,589][76542] Updated weights for policy 1, policy_version 97080 (0.0011) -[2023-10-10 16:28:46,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 199032832. Throughput: 0: 1822.7, 1: 1821.2. Samples: 49766764. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 16:28:46,077][75634] Avg episode reward: [(0, '37.490'), (1, '40.520')] -[2023-10-10 16:28:46,575][76543] Updated weights for policy 0, policy_version 97283 (0.0010) -[2023-10-10 16:28:46,949][76543] Updated weights for policy 0, policy_version 97293 (0.0009) -[2023-10-10 16:28:47,323][76543] Updated weights for policy 0, policy_version 97303 (0.0009) -[2023-10-10 16:28:49,278][76542] Updated weights for policy 1, policy_version 97090 (0.0012) -[2023-10-10 16:28:49,650][76542] Updated weights for policy 1, policy_version 97100 (0.0011) -[2023-10-10 16:28:50,016][76542] Updated weights for policy 1, policy_version 97110 (0.0009) -[2023-10-10 16:28:50,389][76542] Updated weights for policy 1, policy_version 97120 (0.0011) -[2023-10-10 16:28:50,944][76543] Updated weights for policy 0, policy_version 97313 (0.0009) -[2023-10-10 16:28:51,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.5, 300 sec: 14551.2). Total num frames: 199098368. Throughput: 0: 1823.8, 1: 1817.6. Samples: 49777882. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 16:28:51,077][75634] Avg episode reward: [(0, '39.280'), (1, '29.330')] -[2023-10-10 16:28:51,310][76543] Updated weights for policy 0, policy_version 97323 (0.0010) -[2023-10-10 16:28:51,677][76543] Updated weights for policy 0, policy_version 97333 (0.0010) -[2023-10-10 16:28:52,050][76543] Updated weights for policy 0, policy_version 97343 (0.0007) -[2023-10-10 16:28:54,058][76542] Updated weights for policy 1, policy_version 97130 (0.0007) -[2023-10-10 16:28:54,432][76542] Updated weights for policy 1, policy_version 97140 (0.0009) -[2023-10-10 16:28:54,797][76542] Updated weights for policy 1, policy_version 97150 (0.0008) -[2023-10-10 16:28:55,708][76543] Updated weights for policy 0, policy_version 97353 (0.0009) -[2023-10-10 16:28:56,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 199163904. Throughput: 0: 1820.4, 1: 1815.7. Samples: 49799554. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 16:28:56,077][76543] Updated weights for policy 0, policy_version 97363 (0.0007) -[2023-10-10 16:28:56,077][75634] Avg episode reward: [(0, '40.870'), (1, '32.410')] -[2023-10-10 16:28:56,452][76543] Updated weights for policy 0, policy_version 97373 (0.0007) -[2023-10-10 16:28:58,529][76542] Updated weights for policy 1, policy_version 97160 (0.0007) -[2023-10-10 16:28:58,899][76542] Updated weights for policy 1, policy_version 97170 (0.0008) -[2023-10-10 16:28:59,260][76542] Updated weights for policy 1, policy_version 97180 (0.0007) -[2023-10-10 16:29:00,151][76543] Updated weights for policy 0, policy_version 97383 (0.0007) -[2023-10-10 16:29:00,522][76543] Updated weights for policy 0, policy_version 97393 (0.0007) -[2023-10-10 16:29:00,894][76543] Updated weights for policy 0, policy_version 97403 (0.0008) -[2023-10-10 16:29:01,076][75634] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 199262208. Throughput: 0: 1824.1, 1: 1818.4. Samples: 49822000. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-10 16:29:01,076][75634] Avg episode reward: [(0, '38.660'), (1, '35.020')] -[2023-10-10 16:29:02,844][76542] Updated weights for policy 1, policy_version 97190 (0.0008) -[2023-10-10 16:29:03,225][76542] Updated weights for policy 1, policy_version 97200 (0.0008) -[2023-10-10 16:29:03,588][76542] Updated weights for policy 1, policy_version 97210 (0.0007) -[2023-10-10 16:29:04,582][76543] Updated weights for policy 0, policy_version 97413 (0.0008) -[2023-10-10 16:29:04,941][76543] Updated weights for policy 0, policy_version 97423 (0.0010) -[2023-10-10 16:29:05,312][76543] Updated weights for policy 0, policy_version 97433 (0.0007) -[2023-10-10 16:29:06,076][75634] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 199327744. Throughput: 0: 1824.8, 1: 1819.6. Samples: 49832598. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:29:06,077][75634] Avg episode reward: [(0, '36.160'), (1, '35.180')] -[2023-10-10 16:29:07,293][76542] Updated weights for policy 1, policy_version 97220 (0.0007) -[2023-10-10 16:29:07,662][76542] Updated weights for policy 1, policy_version 97230 (0.0007) -[2023-10-10 16:29:08,026][76542] Updated weights for policy 1, policy_version 97240 (0.0007) -[2023-10-10 16:29:08,965][76543] Updated weights for policy 0, policy_version 97443 (0.0008) -[2023-10-10 16:29:09,347][76543] Updated weights for policy 0, policy_version 97453 (0.0009) -[2023-10-10 16:29:09,717][76543] Updated weights for policy 0, policy_version 97463 (0.0010) -[2023-10-10 16:29:11,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 199393280. Throughput: 0: 1822.2, 1: 1823.3. Samples: 49854832. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:29:11,076][75634] Avg episode reward: [(0, '40.630'), (1, '33.680')] -[2023-10-10 16:29:11,671][76542] Updated weights for policy 1, policy_version 97250 (0.0008) -[2023-10-10 16:29:12,027][76542] Updated weights for policy 1, policy_version 97260 (0.0010) -[2023-10-10 16:29:12,401][76542] Updated weights for policy 1, policy_version 97270 (0.0008) -[2023-10-10 16:29:12,774][76542] Updated weights for policy 1, policy_version 97280 (0.0007) -[2023-10-10 16:29:13,234][76543] Updated weights for policy 0, policy_version 97473 (0.0010) -[2023-10-10 16:29:13,591][76543] Updated weights for policy 0, policy_version 97483 (0.0009) -[2023-10-10 16:29:13,961][76543] Updated weights for policy 0, policy_version 97493 (0.0008) -[2023-10-10 16:29:14,337][76543] Updated weights for policy 0, policy_version 97503 (0.0007) -[2023-10-10 16:29:16,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 199458816. Throughput: 0: 1832.8, 1: 1820.7. Samples: 49876748. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:29:16,076][75634] Avg episode reward: [(0, '34.840'), (1, '33.850')] -[2023-10-10 16:29:16,558][76542] Updated weights for policy 1, policy_version 97290 (0.0009) -[2023-10-10 16:29:16,922][76542] Updated weights for policy 1, policy_version 97300 (0.0010) -[2023-10-10 16:29:17,301][76542] Updated weights for policy 1, policy_version 97310 (0.0009) -[2023-10-10 16:29:17,963][76543] Updated weights for policy 0, policy_version 97513 (0.0008) -[2023-10-10 16:29:18,331][76543] Updated weights for policy 0, policy_version 97523 (0.0007) -[2023-10-10 16:29:18,709][76543] Updated weights for policy 0, policy_version 97533 (0.0008) -[2023-10-10 16:29:21,003][76542] Updated weights for policy 1, policy_version 97320 (0.0009) -[2023-10-10 16:29:21,076][75634] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 199524352. Throughput: 0: 1826.1, 1: 1822.0. Samples: 49887506. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:29:21,076][75634] Avg episode reward: [(0, '34.640'), (1, '33.030')] -[2023-10-10 16:29:21,367][76542] Updated weights for policy 1, policy_version 97330 (0.0008) -[2023-10-10 16:29:21,730][76542] Updated weights for policy 1, policy_version 97340 (0.0011) -[2023-10-10 16:29:22,358][76543] Updated weights for policy 0, policy_version 97543 (0.0010) -[2023-10-10 16:29:22,723][76543] Updated weights for policy 0, policy_version 97553 (0.0009) -[2023-10-10 16:29:23,090][76543] Updated weights for policy 0, policy_version 97563 (0.0007) -[2023-10-10 16:29:25,382][76542] Updated weights for policy 1, policy_version 97350 (0.0009) -[2023-10-10 16:29:25,761][76542] Updated weights for policy 1, policy_version 97360 (0.0007) -[2023-10-10 16:29:26,076][75634] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 199589888. Throughput: 0: 1837.1, 1: 1825.8. Samples: 49909762. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:29:26,077][75634] Avg episode reward: [(0, '34.830'), (1, '31.310')] -[2023-10-10 16:29:26,119][76542] Updated weights for policy 1, policy_version 97370 (0.0009) -[2023-10-10 16:29:26,731][76543] Updated weights for policy 0, policy_version 97573 (0.0007) -[2023-10-10 16:29:27,101][76543] Updated weights for policy 0, policy_version 97583 (0.0007) -[2023-10-10 16:29:27,468][76543] Updated weights for policy 0, policy_version 97593 (0.0011) -[2023-10-10 16:29:29,805][76542] Updated weights for policy 1, policy_version 97380 (0.0010) -[2023-10-10 16:29:30,181][76542] Updated weights for policy 1, policy_version 97390 (0.0011) -[2023-10-10 16:29:30,551][76542] Updated weights for policy 1, policy_version 97400 (0.0010) -[2023-10-10 16:29:31,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 199688192. Throughput: 0: 1841.4, 1: 1819.7. Samples: 49931510. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:29:31,076][75634] Avg episode reward: [(0, '34.540'), (1, '30.260')] -[2023-10-10 16:29:31,222][76543] Updated weights for policy 0, policy_version 97603 (0.0010) -[2023-10-10 16:29:31,594][76543] Updated weights for policy 0, policy_version 97613 (0.0010) -[2023-10-10 16:29:31,967][76543] Updated weights for policy 0, policy_version 97623 (0.0007) -[2023-10-10 16:29:34,115][76542] Updated weights for policy 1, policy_version 97410 (0.0007) -[2023-10-10 16:29:34,478][76542] Updated weights for policy 1, policy_version 97420 (0.0007) -[2023-10-10 16:29:34,846][76542] Updated weights for policy 1, policy_version 97430 (0.0008) -[2023-10-10 16:29:35,215][76542] Updated weights for policy 1, policy_version 97440 (0.0009) -[2023-10-10 16:29:35,628][76543] Updated weights for policy 0, policy_version 97633 (0.0009) -[2023-10-10 16:29:35,996][76543] Updated weights for policy 0, policy_version 97643 (0.0007) -[2023-10-10 16:29:36,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 199753728. Throughput: 0: 1841.1, 1: 1824.3. Samples: 49942826. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:29:36,077][75634] Avg episode reward: [(0, '33.710'), (1, '35.370')] -[2023-10-10 16:29:36,360][76543] Updated weights for policy 0, policy_version 97653 (0.0007) -[2023-10-10 16:29:36,725][76543] Updated weights for policy 0, policy_version 97663 (0.0007) -[2023-10-10 16:29:38,886][76542] Updated weights for policy 1, policy_version 97450 (0.0007) -[2023-10-10 16:29:39,256][76542] Updated weights for policy 1, policy_version 97460 (0.0011) -[2023-10-10 16:29:39,628][76542] Updated weights for policy 1, policy_version 97470 (0.0010) -[2023-10-10 16:29:40,389][76543] Updated weights for policy 0, policy_version 97673 (0.0007) -[2023-10-10 16:29:40,762][76543] Updated weights for policy 0, policy_version 97683 (0.0009) -[2023-10-10 16:29:41,076][75634] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 199819264. Throughput: 0: 1840.6, 1: 1823.2. Samples: 49964424. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:29:41,076][75634] Avg episode reward: [(0, '35.210'), (1, '37.020')] -[2023-10-10 16:29:41,127][76543] Updated weights for policy 0, policy_version 97693 (0.0011) -[2023-10-10 16:29:43,443][76542] Updated weights for policy 1, policy_version 97480 (0.0008) -[2023-10-10 16:29:43,817][76542] Updated weights for policy 1, policy_version 97490 (0.0007) -[2023-10-10 16:29:44,177][76542] Updated weights for policy 1, policy_version 97500 (0.0007) -[2023-10-10 16:29:44,636][76543] Updated weights for policy 0, policy_version 97703 (0.0010) -[2023-10-10 16:29:45,011][76543] Updated weights for policy 0, policy_version 97713 (0.0009) -[2023-10-10 16:29:45,382][76543] Updated weights for policy 0, policy_version 97723 (0.0007) -[2023-10-10 16:29:46,076][75634] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14662.3). Total num frames: 199917568. Throughput: 0: 1828.4, 1: 1828.3. Samples: 49986552. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:29:46,076][75634] Avg episode reward: [(0, '36.490'), (1, '39.960')] -[2023-10-10 16:29:48,022][76542] Updated weights for policy 1, policy_version 97510 (0.0009) -[2023-10-10 16:29:48,392][76542] Updated weights for policy 1, policy_version 97520 (0.0008) -[2023-10-10 16:29:48,759][76542] Updated weights for policy 1, policy_version 97530 (0.0008) -[2023-10-10 16:29:49,014][76543] Updated weights for policy 0, policy_version 97733 (0.0008) -[2023-10-10 16:29:49,372][76543] Updated weights for policy 0, policy_version 97743 (0.0008) -[2023-10-10 16:29:49,738][76543] Updated weights for policy 0, policy_version 97753 (0.0007) -[2023-10-10 16:29:51,076][75634] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14662.3). Total num frames: 199983104. Throughput: 0: 1841.0, 1: 1826.4. Samples: 49997628. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:29:51,077][75634] Avg episode reward: [(0, '33.700'), (1, '37.620')] -[2023-10-10 16:29:52,345][76542] Updated weights for policy 1, policy_version 97540 (0.0009) -[2023-10-10 16:29:52,721][76542] Updated weights for policy 1, policy_version 97550 (0.0008) -[2023-10-10 16:29:53,084][76542] Updated weights for policy 1, policy_version 97560 (0.0007) -[2023-10-10 16:29:53,484][76543] Updated weights for policy 0, policy_version 97763 (0.0008) -[2023-10-10 16:29:53,846][76543] Updated weights for policy 0, policy_version 97773 (0.0008) -[2023-10-10 16:29:54,224][76543] Updated weights for policy 0, policy_version 97783 (0.0007) -[2023-10-10 16:29:56,076][75634] Fps is (10 sec: 13106.9, 60 sec: 14745.6, 300 sec: 14551.2). Total num frames: 200048640. Throughput: 0: 1830.8, 1: 1826.8. Samples: 50019426. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:29:56,077][75634] Avg episode reward: [(0, '34.530'), (1, '36.600')] -[2023-10-10 16:29:56,642][76542] Updated weights for policy 1, policy_version 97570 (0.0007) -[2023-10-10 16:29:57,010][76542] Updated weights for policy 1, policy_version 97580 (0.0010) -[2023-10-10 16:29:57,385][76542] Updated weights for policy 1, policy_version 97590 (0.0008) -[2023-10-10 16:29:57,753][76542] Updated weights for policy 1, policy_version 97600 (0.0008) -[2023-10-10 16:29:57,894][76543] Updated weights for policy 0, policy_version 97793 (0.0008) -[2023-10-10 16:29:58,303][76543] Updated weights for policy 0, policy_version 97803 (0.0008) -[2023-10-10 16:29:58,675][76543] Updated weights for policy 0, policy_version 97813 (0.0009) -[2023-10-10 16:29:59,042][76543] Updated weights for policy 0, policy_version 97823 (0.0007) -[2023-10-10 16:30:01,076][75634] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 200114176. Throughput: 0: 1837.1, 1: 1830.1. Samples: 50041772. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:30:01,076][75634] Avg episode reward: [(0, '35.290'), (1, '37.340')] -[2023-10-10 16:30:01,332][76542] Updated weights for policy 1, policy_version 97610 (0.0010) -[2023-10-10 16:30:01,700][76542] Updated weights for policy 1, policy_version 97620 (0.0007) -[2023-10-10 16:30:02,074][76542] Updated weights for policy 1, policy_version 97630 (0.0007) -[2023-10-10 16:30:02,786][76543] Updated weights for policy 0, policy_version 97833 (0.0009) -[2023-10-10 16:30:03,151][76543] Updated weights for policy 0, policy_version 97843 (0.0008) -[2023-10-10 16:30:03,521][76543] Updated weights for policy 0, policy_version 97853 (0.0007) -[2023-10-10 16:30:05,924][76542] Updated weights for policy 1, policy_version 97640 (0.0007) -[2023-10-10 16:30:06,076][75634] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14551.2). Total num frames: 200179712. Throughput: 0: 1832.4, 1: 1831.0. Samples: 50052356. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-10 16:30:06,076][75634] Avg episode reward: [(0, '38.830'), (1, '36.850')] -[2023-10-10 16:30:06,296][76542] Updated weights for policy 1, policy_version 97650 (0.0008) -[2023-10-10 16:30:06,667][76542] Updated weights for policy 1, policy_version 97660 (0.0008) -[2023-10-10 16:30:07,334][76543] Updated weights for policy 0, policy_version 97863 (0.0009) -[2023-10-10 16:30:07,712][76543] Updated weights for policy 0, policy_version 97873 (0.0011) -[2023-10-10 16:30:08,079][76543] Updated weights for policy 0, policy_version 97883 (0.0008) -[2023-10-10 16:30:08,258][76590] Stopping RolloutWorker_w13... -[2023-10-10 16:30:08,258][76586] Stopping RolloutWorker_w8... -[2023-10-10 16:30:08,258][76421] Stopping Batcher_1... -[2023-10-10 16:30:08,258][76590] Loop rollout_proc13_evt_loop terminating... -[2023-10-10 16:30:08,259][76586] Loop rollout_proc8_evt_loop terminating... -[2023-10-10 16:30:08,258][76362] Stopping Batcher_0... -[2023-10-10 16:30:08,259][76421] Loop batcher_evt_loop terminating... -[2023-10-10 16:30:08,259][76583] Stopping RolloutWorker_w5... -[2023-10-10 16:30:08,259][76362] Loop batcher_evt_loop terminating... -[2023-10-10 16:30:08,259][76577] Stopping RolloutWorker_w0... -[2023-10-10 16:30:08,259][76592] Stopping RolloutWorker_w12... -[2023-10-10 16:30:08,259][76587] Stopping RolloutWorker_w10... -[2023-10-10 16:30:08,259][76583] Loop rollout_proc5_evt_loop terminating... -[2023-10-10 16:30:08,259][76585] Stopping RolloutWorker_w7... -[2023-10-10 16:30:08,260][76577] Loop rollout_proc0_evt_loop terminating... -[2023-10-10 16:30:08,259][77362] Stopping RolloutWorker_w15... -[2023-10-10 16:30:08,260][76587] Loop rollout_proc10_evt_loop terminating... -[2023-10-10 16:30:08,260][77297] Stopping RolloutWorker_w14... -[2023-10-10 16:30:08,260][76592] Loop rollout_proc12_evt_loop terminating... -[2023-10-10 16:30:08,260][76585] Loop rollout_proc7_evt_loop terminating... -[2023-10-10 16:30:08,260][77362] Loop rollout_proc15_evt_loop terminating... -[2023-10-10 16:30:08,260][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000097888_100237312.pth... -[2023-10-10 16:30:08,260][77297] Loop rollout_proc14_evt_loop terminating... -[2023-10-10 16:30:08,260][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000097664_100007936.pth... -[2023-10-10 16:30:08,261][76588] Stopping RolloutWorker_w9... -[2023-10-10 16:30:08,261][76588] Loop rollout_proc9_evt_loop terminating... -[2023-10-10 16:30:08,261][76580] Stopping RolloutWorker_w3... -[2023-10-10 16:30:08,261][76589] Stopping RolloutWorker_w11... -[2023-10-10 16:30:08,261][76584] Stopping RolloutWorker_w6... -[2023-10-10 16:30:08,262][76580] Loop rollout_proc3_evt_loop terminating... -[2023-10-10 16:30:08,262][76589] Loop rollout_proc11_evt_loop terminating... -[2023-10-10 16:30:08,262][76584] Loop rollout_proc6_evt_loop terminating... -[2023-10-10 16:30:08,262][76579] Stopping RolloutWorker_w1... -[2023-10-10 16:30:08,262][76579] Loop rollout_proc1_evt_loop terminating... -[2023-10-10 16:30:08,264][76582] Stopping RolloutWorker_w4... -[2023-10-10 16:30:08,263][75634] Component RolloutWorker_w13 stopped! -[2023-10-10 16:30:08,264][76582] Loop rollout_proc4_evt_loop terminating... -[2023-10-10 16:30:08,264][76581] Stopping RolloutWorker_w2... -[2023-10-10 16:30:08,265][75634] Component RolloutWorker_w8 stopped! -[2023-10-10 16:30:08,265][75634] Component Batcher_1 stopped! -[2023-10-10 16:30:08,265][76581] Loop rollout_proc2_evt_loop terminating... -[2023-10-10 16:30:08,265][75634] Component Batcher_0 stopped! -[2023-10-10 16:30:08,266][75634] Component RolloutWorker_w5 stopped! -[2023-10-10 16:30:08,266][75634] Component RolloutWorker_w12 stopped! -[2023-10-10 16:30:08,266][75634] Component RolloutWorker_w0 stopped! -[2023-10-10 16:30:08,266][75634] Component RolloutWorker_w10 stopped! -[2023-10-10 16:30:08,267][75634] Component RolloutWorker_w7 stopped! -[2023-10-10 16:30:08,267][75634] Component RolloutWorker_w15 stopped! -[2023-10-10 16:30:08,267][75634] Component RolloutWorker_w14 stopped! -[2023-10-10 16:30:08,267][75634] Component RolloutWorker_w9 stopped! -[2023-10-10 16:30:08,267][75634] Component RolloutWorker_w11 stopped! -[2023-10-10 16:30:08,267][75634] Component RolloutWorker_w3 stopped! -[2023-10-10 16:30:08,268][75634] Component RolloutWorker_w6 stopped! -[2023-10-10 16:30:08,268][75634] Component RolloutWorker_w1 stopped! -[2023-10-10 16:30:08,268][75634] Component RolloutWorker_w4 stopped! -[2023-10-10 16:30:08,268][75634] Component RolloutWorker_w2 stopped! -[2023-10-10 16:30:08,280][76542] Weights refcount: 2 0 -[2023-10-10 16:30:08,282][76542] Stopping InferenceWorker_p1-w0... -[2023-10-10 16:30:08,282][75634] Component InferenceWorker_p1-w0 stopped! -[2023-10-10 16:30:08,282][76542] Loop inference_proc1-0_evt_loop terminating... -[2023-10-10 16:30:08,291][76543] Weights refcount: 2 0 -[2023-10-10 16:30:08,293][76543] Stopping InferenceWorker_p0-w0... -[2023-10-10 16:30:08,293][75634] Component InferenceWorker_p0-w0 stopped! -[2023-10-10 16:30:08,293][76543] Loop inference_proc0-0_evt_loop terminating... -[2023-10-10 16:30:08,300][76362] Removing ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000096320_98631680.pth -[2023-10-10 16:30:08,304][76362] Saving ./train_atari/atari_defender_APPO/checkpoint_p0/checkpoint_000097888_100237312.pth... -[2023-10-10 16:30:08,310][76421] Removing ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000096128_98435072.pth -[2023-10-10 16:30:08,316][76421] Saving ./train_atari/atari_defender_APPO/checkpoint_p1/checkpoint_000097664_100007936.pth... -[2023-10-10 16:30:08,343][76362] Stopping LearnerWorker_p0... -[2023-10-10 16:30:08,343][76362] Loop learner_proc0_evt_loop terminating... -[2023-10-10 16:30:08,344][75634] Component LearnerWorker_p0 stopped! -[2023-10-10 16:30:08,374][76421] Stopping LearnerWorker_p1... -[2023-10-10 16:30:08,374][76421] Loop learner_proc1_evt_loop terminating... -[2023-10-10 16:30:08,374][75634] Component LearnerWorker_p1 stopped! -[2023-10-10 16:30:08,375][75634] Waiting for process learner_proc0 to stop... -[2023-10-10 16:30:09,135][75634] Waiting for process learner_proc1 to stop... -[2023-10-10 16:30:09,274][75634] Waiting for process inference_proc0-0 to join... -[2023-10-10 16:30:09,275][75634] Waiting for process inference_proc1-0 to join... -[2023-10-10 16:30:09,275][75634] Waiting for process rollout_proc0 to join... -[2023-10-10 16:30:09,276][75634] Waiting for process rollout_proc1 to join... -[2023-10-10 16:30:09,277][75634] Waiting for process rollout_proc2 to join... -[2023-10-10 16:30:09,277][75634] Waiting for process rollout_proc3 to join... -[2023-10-10 16:30:09,281][75634] Waiting for process rollout_proc4 to join... -[2023-10-10 16:30:09,282][75634] Waiting for process rollout_proc5 to join... -[2023-10-10 16:30:09,282][75634] Waiting for process rollout_proc6 to join... -[2023-10-10 16:30:09,283][75634] Waiting for process rollout_proc7 to join... -[2023-10-10 16:30:09,283][75634] Waiting for process rollout_proc8 to join... -[2023-10-10 16:30:09,284][75634] Waiting for process rollout_proc9 to join... -[2023-10-10 16:30:09,284][75634] Waiting for process rollout_proc10 to join... -[2023-10-10 16:30:09,285][75634] Waiting for process rollout_proc11 to join... -[2023-10-10 16:30:09,285][75634] Waiting for process rollout_proc12 to join... -[2023-10-10 16:30:09,286][75634] Waiting for process rollout_proc13 to join... -[2023-10-10 16:30:09,286][75634] Waiting for process rollout_proc14 to join... -[2023-10-10 16:30:09,287][75634] Waiting for process rollout_proc15 to join... -[2023-10-10 16:30:09,287][75634] Batcher 0 profile tree view: -batching: 172.7603, releasing_batches: 0.0905 -[2023-10-10 16:30:09,288][75634] Batcher 1 profile tree view: -batching: 173.1203, releasing_batches: 0.0930 -[2023-10-10 16:30:09,288][75634] InferenceWorker_p0-w0 profile tree view: -wait_policy: 0.0001 - wait_policy_total: 1751.1993 -update_model: 200.5491 - weight_update: 0.0009 -one_step: 0.0029 - handle_policy_step: 11142.0819 - deserialize: 62.1154, stack: 194.6070, obs_to_device_normalize: 2468.3923, forward: 5031.0958, prepare_outputs: 2436.6480, send_messages: 468.4987 -[2023-10-10 16:30:09,288][75634] InferenceWorker_p1-w0 profile tree view: -wait_policy: 0.0000 - wait_policy_total: 1819.9750 -update_model: 198.6789 - weight_update: 0.0009 -one_step: 0.0020 - handle_policy_step: 11088.0845 - deserialize: 62.1283, stack: 189.3483, obs_to_device_normalize: 2448.6946, forward: 5017.5174, prepare_outputs: 2439.8330, send_messages: 450.4826 -[2023-10-10 16:30:09,289][75634] Learner 0 profile tree view: -misc: 0.0177, prepare_batch: 262.9832 -train: 3646.4547 - epoch_init: 0.1887, minibatch_init: 13.0799, losses_postprocess: 896.5481, kl_divergence: 31.4526, update: 392.3217, after_optimizer: 2130.1475 - calculate_losses: 165.9428 - losses_init: 0.4213, forward_head: 55.6784, bptt_initial: 1.4109, bptt: 2.0121, tail: 37.8602, advantages_returns: 11.1017, losses: 43.8868 -[2023-10-10 16:30:09,289][75634] Learner 1 profile tree view: -misc: 0.0183, prepare_batch: 261.1067 -train: 3612.4136 - epoch_init: 0.1859, minibatch_init: 13.0260, losses_postprocess: 889.9423, kl_divergence: 31.0349, update: 389.0461, after_optimizer: 2106.0051 - calculate_losses: 166.2308 - losses_init: 0.4449, forward_head: 55.9271, bptt_initial: 1.5007, bptt: 1.9723, tail: 37.9143, advantages_returns: 11.0504, losses: 43.8925 -[2023-10-10 16:30:09,290][75634] RolloutWorker_w0 profile tree view: -wait_for_trajectories: 1.2457, enqueue_policy_requests: 407.4493, process_policy_outputs: 192.8046, env_step: 6357.9483, finalize_trajectories: 3.5551, complete_rollouts: 2.9166 -post_env_step: 378.4714 - process_env_step: 84.3345 -[2023-10-10 16:30:09,290][75634] RolloutWorker_w15 profile tree view: -wait_for_trajectories: 1.2233, enqueue_policy_requests: 406.2964, process_policy_outputs: 191.8709, env_step: 6394.9373, finalize_trajectories: 3.4272, complete_rollouts: 2.9026 -post_env_step: 373.0928 - process_env_step: 82.8462 -[2023-10-10 16:30:09,291][75634] Loop Runner_EvtLoop terminating... -[2023-10-10 16:30:09,291][75634] Runner profile tree view: -main_loop: 13773.6360 -[2023-10-10 16:30:09,291][75634] Collected {0: 100237312, 1: 100007936}, FPS: 14538.3 +version https://git-lfs.github.com/spec/v1 +oid sha256:4913b48927ba2f461a1d96956a681b67780b21b0b2fee6c9a6a1bfc69cd62314 +size 47923945